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

14 files changed, 83 insertions, 119 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 015198c14fa8..504461a464c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -245,13 +245,9 @@ static u32 freq_to_shift(u16 freq)
 {
 	u32 freq_khz = freq * 1000;
 	u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
-	u64 tmp_rounded =
-		roundup_pow_of_two(max_val_cycles) > max_val_cycles ?
-		roundup_pow_of_two(max_val_cycles) - 1 : UINT_MAX;
-	u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
-		max_val_cycles : tmp_rounded;
+	u64 max_val_cycles_rounded = 1ULL << fls64(max_val_cycles - 1);
 	/* calculate max possible multiplier in order to fit in 64bit */
-	u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
+	u64 max_mul = div64_u64(ULLONG_MAX, max_val_cycles_rounded);
 
 	/* This comes from the reverse of clocksource_khz2mult */
 	return ilog2(div_u64(max_mul * freq_khz, 1000000));
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 3c37e216bbf3..eac527e25ec9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -445,8 +445,14 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
 		ring->cqn = priv->rx_cq[ring_ind]->mcq.cqn;
 
 		ring->stride = stride;
-		if (ring->stride <= TXBB_SIZE)
+		if (ring->stride <= TXBB_SIZE) {
+			/* Stamp first unused send wqe */
+			__be32 *ptr = (__be32 *)ring->buf;
+			__be32 stamp = cpu_to_be32(1 << STAMP_SHIFT);
+			*ptr = stamp;
+			/* Move pointer to start of rx section */
 			ring->buf += TXBB_SIZE;
+		}
 
 		ring->log_stride = ffs(ring->stride) - 1;
 		ring->buf_size = ring->size * ring->stride;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 2a9dd460a95f..e1f9e7cebf8f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -118,8 +118,13 @@ static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem,
 	if (!buf)
 		return -ENOMEM;
 
+	if (offset_in_page(buf)) {
+		dma_free_coherent(dev, PAGE_SIZE << order,
+				  buf, sg_dma_address(mem));
+		return -ENOMEM;
+	}
+
 	sg_set_buf(mem, buf, PAGE_SIZE << order);
-	BUG_ON(mem->offset);
 	sg_dma_len(mem) = PAGE_SIZE << order;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5e7840a7a33b..bffa6f345f2f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -42,6 +42,7 @@
 #include <linux/io-mapping.h>
 #include <linux/delay.h>
 #include <linux/kmod.h>
+#include <linux/etherdevice.h>
 #include <net/devlink.h>
 
 #include <linux/mlx4/device.h>
@@ -782,6 +783,23 @@ int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
 }
 EXPORT_SYMBOL(mlx4_is_slave_active);
 
+void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
+				       struct _rule_hw *eth_header)
+{
+	if (is_multicast_ether_addr(eth_header->eth.dst_mac) ||
+	    is_broadcast_ether_addr(eth_header->eth.dst_mac)) {
+		struct mlx4_net_trans_rule_hw_eth *eth =
+			(struct mlx4_net_trans_rule_hw_eth *)eth_header;
+		struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1);
+		bool last_rule = next_rule->size == 0 && next_rule->id == 0 &&
+			next_rule->rsvd == 0;
+
+		if (last_rule)
+			ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC);
+	}
+}
+EXPORT_SYMBOL(mlx4_handle_eth_header_mcast_prio);
+
 static void slave_adjust_steering_mode(struct mlx4_dev *dev,
 				       struct mlx4_dev_cap *dev_cap,
 				       struct mlx4_init_hca_param *hca_param)
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index c548beaaf910..56185a0b827d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -4164,22 +4164,6 @@ static int validate_eth_header_mac(int slave, struct _rule_hw *eth_header,
 	return 0;
 }
 
-static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
-					 struct _rule_hw *eth_header)
-{
-	if (is_multicast_ether_addr(eth_header->eth.dst_mac) ||
-	    is_broadcast_ether_addr(eth_header->eth.dst_mac)) {
-		struct mlx4_net_trans_rule_hw_eth *eth =
-			(struct mlx4_net_trans_rule_hw_eth *)eth_header;
-		struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1);
-		bool last_rule = next_rule->size == 0 && next_rule->id == 0 &&
-			next_rule->rsvd == 0;
-
-		if (last_rule)
-			ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC);
-	}
-}
-
 /*
  * In case of missing eth header, append eth header with a MAC address
  * assigned to the VF.
@@ -4363,10 +4347,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 	header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id));
 
 	if (header_id == MLX4_NET_TRANS_RULE_ID_ETH)
-		handle_eth_header_mcast_prio(ctrl, rule_header);
-
-	if (slave == dev->caps.function)
-		goto execute;
+		mlx4_handle_eth_header_mcast_prio(ctrl, rule_header);
 
 	switch (header_id) {
 	case MLX4_NET_TRANS_RULE_ID_ETH:
@@ -4394,7 +4375,6 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 		goto err_put_qp;
 	}
 
-execute:
 	err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
 			   vhcr->in_modifier, 0,
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
@@ -4473,6 +4453,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
 	struct res_qp *rqp;
 	struct res_fs_rule *rrule;
 	u64 mirr_reg_id;
+	int qpn;
 
 	if (dev->caps.steering_mode !=
 	    MLX4_STEERING_MODE_DEVICE_MANAGED)
@@ -4489,10 +4470,11 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
 	}
 	mirr_reg_id = rrule->mirr_rule_id;
 	kfree(rrule->mirr_mbox);
+	qpn = rrule->qpn;
 
 	/* Release the rule form busy state before removal */
 	put_res(dev, slave, vhcr->in_param, RES_FS_RULE);
-	err = get_res(dev, slave, rrule->qpn, RES_QP, &rqp);
+	err = get_res(dev, slave, qpn, RES_QP, &rqp);
 	if (err)
 		return err;
 
@@ -4517,7 +4499,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
 	if (!err)
 		atomic_dec(&rqp->ref_count);
 out:
-	put_res(dev, slave, rrule->qpn, RES_QP);
+	put_res(dev, slave, qpn, RES_QP);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 7f6c225666c1..f0b460f47f29 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 352462af8d51..33a399a8b5d5 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 3691451c728c..d088effd7160 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 5ff86f0ecb7b..88dd731bb8cb 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 f202f872f57f..ba5db1dd23a9 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 d6807c3cc461..f14d9c9ba773 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 466e161010f7..03293ed1cc22 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 a263d8904a4c..0ac7a2fc916c 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 f4115135e30b..f1ed009b871c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -523,6 +523,13 @@ 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);
@@ -595,7 +602,6 @@ 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)) {
@@ -603,7 +609,7 @@ 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);
@@ -1210,6 +1216,8 @@ 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",
@@ -1388,10 +1396,9 @@ 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);
 	}