diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index 6bcc63aaa50b..be95ac5aeb30 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -148,7 +148,7 @@ int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
 			return ret;
 		}
 
-		*addr = pci_resource_start(dev->pdev, 0) +
+		*addr = dev->bar_addr +
 			MLX5_GET64(alloc_memic_out, out, memic_start_addr);
 
 		return 0;
@@ -167,7 +167,7 @@ int mlx5_cmd_dealloc_memic(struct mlx5_memic *memic, u64 addr, u64 length)
 	u64 start_page_idx;
 	int err;
 
-	addr -= pci_resource_start(dev->pdev, 0);
+	addr -= dev->bar_addr;
 	start_page_idx = (addr - hw_start_addr) >> PAGE_SHIFT;
 
 	MLX5_SET(dealloc_memic_in, in, opcode, MLX5_CMD_OP_DEALLOC_MEMIC);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 531ff20b32ad..0845e95d2d11 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2009,7 +2009,7 @@ static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
 
 	fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1;
 
-	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
+	return (dev->mdev->bar_addr >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
 }
 
 static int get_command(unsigned long offset)
@@ -2199,7 +2199,7 @@ static int dm_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 	    page_idx + npages)
 		return -EINVAL;
 
-	pfn = ((pci_resource_start(dev->mdev->pdev, 0) +
+	pfn = ((dev->mdev->bar_addr +
 	      MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
 	      PAGE_SHIFT) +
 	      page_idx;
@@ -2283,7 +2283,7 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 		goto err_free;
 
 	start_offset = memic_addr & ~PAGE_MASK;
-	page_idx = (memic_addr - pci_resource_start(memic->dev->pdev, 0) -
+	page_idx = (memic_addr - memic->dev->bar_addr -
 		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
 		    PAGE_SHIFT;
 
@@ -2326,7 +2326,7 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm)
 	if (ret)
 		return ret;
 
-	page_idx = (dm->dev_addr - pci_resource_start(memic->dev->pdev, 0) -
+	page_idx = (dm->dev_addr - memic->dev->bar_addr -
 		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
 		    PAGE_SHIFT;
 	bitmap_clear(to_mucontext(ibdm->uobject->context)->dm_pages,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index c85f00255884..ca921fd40499 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1194,8 +1194,7 @@ static struct ib_mr *mlx5_ib_get_memic_mr(struct ib_pd *pd, u64 memic_addr,
 	MLX5_SET64(mkc, mkc, len, length);
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
-	MLX5_SET64(mkc, mkc, start_addr,
-		   memic_addr - pci_resource_start(dev->mdev->pdev, 0));
+	MLX5_SET64(mkc, mkc, start_addr, memic_addr - dev->mdev->bar_addr);
 
 	err = mlx5_core_create_mkey(mdev, &mr->mmkey, in, inlen);
 	if (err)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7cd006da1dae..ef7d69269a88 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -5119,7 +5119,7 @@ out:
 		wmb();
 
 		/* currently we support only regular doorbells */
-		mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset, NULL);
+		mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset);
 		/* Make sure doorbells don't leak out of SQ spinlock
 		 * and reach the HCA out of order.
 		 */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index be48c6440251..0a2ffe794a54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1347,7 +1347,7 @@ static void set_wqname(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 
 	snprintf(cmd->wq_name, sizeof(cmd->wq_name), "mlx5_cmd_%s",
-		 dev_name(&dev->pdev->dev));
+		 dev->priv.name);
 }
 
 static void clean_debug_files(struct mlx5_core_dev *dev)
@@ -1902,9 +1902,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	memset(cmd, 0, sizeof(*cmd));
 	cmd_if_rev = cmdif_rev(dev);
 	if (cmd_if_rev != CMD_IF_REV) {
-		dev_err(&dev->pdev->dev,
-			"Driver cmdif rev(%d) differs from firmware's(%d)\n",
-			CMD_IF_REV, cmd_if_rev);
+		mlx5_core_err(dev,
+			      "Driver cmdif rev(%d) differs from firmware's(%d)\n",
+			      CMD_IF_REV, cmd_if_rev);
 		return -EINVAL;
 	}
 
@@ -1921,14 +1921,14 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	cmd->log_sz = cmd_l >> 4 & 0xf;
 	cmd->log_stride = cmd_l & 0xf;
 	if (1 << cmd->log_sz > MLX5_MAX_COMMANDS) {
-		dev_err(&dev->pdev->dev, "firmware reports too many outstanding commands %d\n",
-			1 << cmd->log_sz);
+		mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n",
+			      1 << cmd->log_sz);
 		err = -EINVAL;
 		goto err_free_page;
 	}
 
 	if (cmd->log_sz + cmd->log_stride > MLX5_ADAPTER_PAGE_SHIFT) {
-		dev_err(&dev->pdev->dev, "command queue size overflow\n");
+		mlx5_core_err(dev, "command queue size overflow\n");
 		err = -EINVAL;
 		goto err_free_page;
 	}
@@ -1939,8 +1939,8 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	cmd->cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
 	if (cmd->cmdif_rev > CMD_IF_REV) {
-		dev_err(&dev->pdev->dev, "driver does not support command interface version. driver %d, firmware %d\n",
-			CMD_IF_REV, cmd->cmdif_rev);
+		mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n",
+			      CMD_IF_REV, cmd->cmdif_rev);
 		err = -EOPNOTSUPP;
 		goto err_free_page;
 	}
@@ -1956,7 +1956,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);
 	if (cmd_l & 0xfff) {
-		dev_err(&dev->pdev->dev, "invalid command queue address\n");
+		mlx5_core_err(dev, "invalid command queue address\n");
 		err = -ENOMEM;
 		goto err_free_page;
 	}
@@ -1976,7 +1976,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	set_wqname(dev);
 	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
 	if (!cmd->wq) {
-		dev_err(&dev->pdev->dev, "failed to create command workqueue\n");
+		mlx5_core_err(dev, "failed to create command workqueue\n");
 		err = -ENOMEM;
 		goto err_cache;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
index 83f90e9aff45..7b5901d42994 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
@@ -47,7 +47,7 @@ TRACE_EVENT(mlx5_fw,
 	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
 
 	TP_STRUCT__entry(
-		__string(dev_name, dev_name(&tracer->dev->pdev->dev))
+		__string(dev_name, tracer->dev->priv.name)
 		__field(u64, trace_timestamp)
 		__field(bool, lost)
 		__field(u8, event_id)
@@ -55,7 +55,7 @@ TRACE_EVENT(mlx5_fw,
 	),
 
 	TP_fast_assign(
-		__assign_str(dev_name, dev_name(&tracer->dev->pdev->dev));
+		__assign_str(dev_name, tracer->dev->priv.name);
 		__entry->trace_timestamp = trace_timestamp;
 		__entry->lost = lost;
 		__entry->event_id = event_id;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3e1ea8b42c77..bd855ab8dfe2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -241,7 +241,6 @@ struct mlx5e_params {
 	struct net_dim_cq_moder rx_cq_moderation;
 	struct net_dim_cq_moder tx_cq_moderation;
 	bool lro_en;
-	u32 lro_wqe_sz;
 	u8  tx_min_inline_mode;
 	bool vlan_strip_disable;
 	bool scatter_fcs_en;
@@ -975,7 +974,7 @@ void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
 	 */
 	wmb();
 
-	mlx5_write64((__be32 *)ctrl, uar_map, NULL);
+	mlx5_write64((__be32 *)ctrl, uar_map);
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
@@ -1087,6 +1086,7 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *prof
 int mlx5e_attach_netdev(struct mlx5e_priv *priv);
 void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index fa2a3c444cdc..9ab3bd904295 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -96,7 +96,7 @@ static const char *mlx5e_netdev_kind(struct net_device *dev)
 	if (dev->rtnl_link_ops)
 		return dev->rtnl_link_ops->kind;
 	else
-		return "";
+		return "unknown";
 }
 
 static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
@@ -636,8 +636,10 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 						headers_c, headers_v);
 	} else {
 		netdev_warn(priv->netdev,
-			    "decapsulation offload is not supported for %s net device (%d)\n",
-			    mlx5e_netdev_kind(filter_dev), tunnel_type);
+			    "decapsulation offload is not supported for %s (kind: \"%s\")\n",
+			    netdev_name(filter_dev),
+			    mlx5e_netdev_kind(filter_dev));
+
 		return -EOPNOTSUPP;
 	}
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e08a1eb04e22..ba705392b46b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -204,7 +204,6 @@ static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params)
 {
-	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 	params->log_rq_mtu_frames = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
@@ -2637,7 +2636,7 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
-		 (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
@@ -2812,6 +2811,21 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 	return 0;
 }
 
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
+{
+	struct mlx5e_params *params = &priv->channels.params;
+	struct net_device *netdev   = priv->netdev;
+	struct mlx5_core_dev *mdev  = priv->mdev;
+	u16 max_mtu;
+
+	/* MTU range: 68 - hw-specific max */
+	netdev->min_mtu = ETH_MIN_MTU;
+
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->max_mtu = min_t(unsigned int, MLX5E_HW2SW_MTU(params, max_mtu),
+				ETH_MAX_MTU);
+}
+
 static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4913,7 +4927,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
 
 	mlx5e_init_l2_addr(priv);
 
@@ -4921,10 +4934,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (!netif_running(netdev))
 		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
 
-	/* MTU range: 68 - hw-specific max */
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	mlx5e_set_netdev_mtu_boundaries(priv);
 	mlx5e_set_dev_port_mtu(priv);
 
 	mlx5_lag_add(mdev, netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index a66b6ed80b30..6bfdefa8b9f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -795,7 +795,8 @@ static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
 
-	if (!mlx5e_tc_tun_device_to_offload(priv, netdev))
+	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
+	    !is_vlan_dev(netdev))
 		return NOTIFY_OK;
 
 	switch (event) {
@@ -1623,13 +1624,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 
 static void mlx5e_vf_rep_enable(struct mlx5e_priv *priv)
 {
-	struct net_device *netdev = priv->netdev;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
-
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	mlx5e_set_netdev_mtu_boundaries(priv);
 }
 
 static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ffc4a36551c8..a2070817a627 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1438,6 +1438,26 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static void *get_match_headers_criteria(u32 flags,
+					struct mlx5_flow_spec *spec)
+{
+	return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ?
+		MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			     inner_headers) :
+		MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			     outer_headers);
+}
+
+static void *get_match_headers_value(u32 flags,
+				     struct mlx5_flow_spec *spec)
+{
+	return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ?
+		MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			     inner_headers) :
+		MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			     outer_headers);
+}
+
 static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
 			      struct tc_cls_flower_offload *f,
@@ -1503,10 +1523,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		/* In decap flow, header pointers should point to the inner
 		 * headers, outer header were already set by parse_tunnel_attr
 		 */
-		headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-					 inner_headers);
-		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-					 inner_headers);
+		headers_c = get_match_headers_criteria(MLX5_FLOW_CONTEXT_ACTION_DECAP,
+						       spec);
+		headers_v = get_match_headers_value(MLX5_FLOW_CONTEXT_ACTION_DECAP,
+						    spec);
 	}
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
@@ -1521,11 +1541,23 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		if (match.mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
 	}
-
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN) ||
+	    is_vlan_dev(filter_dev)) {
+		struct flow_dissector_key_vlan filter_dev_mask;
+		struct flow_dissector_key_vlan filter_dev_key;
 		struct flow_match_vlan match;
 
-		flow_rule_match_vlan(rule, &match);
+		if (is_vlan_dev(filter_dev)) {
+			match.key = &filter_dev_key;
+			match.key->vlan_id = vlan_dev_vlan_id(filter_dev);
+			match.key->vlan_tpid = vlan_dev_vlan_proto(filter_dev);
+			match.key->vlan_priority = 0;
+			match.mask = &filter_dev_mask;
+			memset(match.mask, 0xff, sizeof(*match.mask));
+			match.mask->vlan_priority = 0;
+		} else {
+			flow_rule_match_vlan(rule, &match);
+		}
 		if (match.mask->vlan_id ||
 		    match.mask->vlan_priority ||
 		    match.mask->vlan_tpid) {
@@ -1875,39 +1907,73 @@ struct mlx5_fields {
 	u8  field;
 	u8  size;
 	u32 offset;
+	u32 match_offset;
 };
 
-#define OFFLOAD(fw_field, size, field, off) \
-		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, offsetof(struct pedit_headers, field) + (off)}
+#define OFFLOAD(fw_field, size, field, off, match_field) \
+		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, \
+		 offsetof(struct pedit_headers, field) + (off), \
+		 MLX5_BYTE_OFF(fte_match_set_lyr_2_4, match_field)}
+
+static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp,
+			 void *matchmaskp, int size)
+{
+	bool same = false;
+
+	switch (size) {
+	case sizeof(u8):
+		same = ((*(u8 *)valp) & (*(u8 *)maskp)) ==
+		       ((*(u8 *)matchvalp) & (*(u8 *)matchmaskp));
+		break;
+	case sizeof(u16):
+		same = ((*(u16 *)valp) & (*(u16 *)maskp)) ==
+		       ((*(u16 *)matchvalp) & (*(u16 *)matchmaskp));
+		break;
+	case sizeof(u32):
+		same = ((*(u32 *)valp) & (*(u32 *)maskp)) ==
+		       ((*(u32 *)matchvalp) & (*(u32 *)matchmaskp));
+		break;
+	}
+
+	return same;
+}
 
 static struct mlx5_fields fields[] = {
-	OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
-	OFFLOAD(DMAC_15_0,  2, eth.h_dest[4], 0),
-	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0),
-	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0),
-	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0),
-	OFFLOAD(FIRST_VID,  2, vlan.h_vlan_TCI, 0),
+	OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0, dmac_47_16),
+	OFFLOAD(DMAC_15_0,  2, eth.h_dest[4], 0, dmac_15_0),
+	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0, smac_47_16),
+	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0, smac_15_0),
+	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0, ethertype),
+	OFFLOAD(FIRST_VID,  2, vlan.h_vlan_TCI, 0, first_vid),
 
-	OFFLOAD(IP_TTL, 1, ip4.ttl,   0),
-	OFFLOAD(SIPV4,  4, ip4.saddr, 0),
-	OFFLOAD(DIPV4,  4, ip4.daddr, 0),
+	OFFLOAD(IP_TTL, 1, ip4.ttl,   0, ttl_hoplimit),
+	OFFLOAD(SIPV4,  4, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
+	OFFLOAD(DIPV4,  4, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 
-	OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0),
-	OFFLOAD(SIPV6_95_64,  4, ip6.saddr.s6_addr32[1], 0),
-	OFFLOAD(SIPV6_63_32,  4, ip6.saddr.s6_addr32[2], 0),
-	OFFLOAD(SIPV6_31_0,   4, ip6.saddr.s6_addr32[3], 0),
-	OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0),
-	OFFLOAD(DIPV6_95_64,  4, ip6.daddr.s6_addr32[1], 0),
-	OFFLOAD(DIPV6_63_32,  4, ip6.daddr.s6_addr32[2], 0),
-	OFFLOAD(DIPV6_31_0,   4, ip6.daddr.s6_addr32[3], 0),
-	OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0),
+	OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[0]),
+	OFFLOAD(SIPV6_95_64,  4, ip6.saddr.s6_addr32[1], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[4]),
+	OFFLOAD(SIPV6_63_32,  4, ip6.saddr.s6_addr32[2], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[8]),
+	OFFLOAD(SIPV6_31_0,   4, ip6.saddr.s6_addr32[3], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[12]),
+	OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[0]),
+	OFFLOAD(DIPV6_95_64,  4, ip6.daddr.s6_addr32[1], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[4]),
+	OFFLOAD(DIPV6_63_32,  4, ip6.daddr.s6_addr32[2], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[8]),
+	OFFLOAD(DIPV6_31_0,   4, ip6.daddr.s6_addr32[3], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
+	OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0, ttl_hoplimit),
 
-	OFFLOAD(TCP_SPORT, 2, tcp.source,  0),
-	OFFLOAD(TCP_DPORT, 2, tcp.dest,    0),
-	OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5),
+	OFFLOAD(TCP_SPORT, 2, tcp.source,  0, tcp_sport),
+	OFFLOAD(TCP_DPORT, 2, tcp.dest,    0, tcp_dport),
+	OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5, tcp_flags),
 
-	OFFLOAD(UDP_SPORT, 2, udp.source, 0),
-	OFFLOAD(UDP_DPORT, 2, udp.dest,   0),
+	OFFLOAD(UDP_SPORT, 2, udp.source, 0, udp_sport),
+	OFFLOAD(UDP_DPORT, 2, udp.dest,   0, udp_dport),
 };
 
 /* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
@@ -1916,9 +1982,14 @@ static struct mlx5_fields fields[] = {
  */
 static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
+				u32 *action_flags,
 				struct netlink_ext_ack *extack)
 {
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+	void *headers_c = get_match_headers_criteria(*action_flags,
+						     &parse_attr->spec);
+	void *headers_v = get_match_headers_value(*action_flags,
+						  &parse_attr->spec);
 	int i, action_size, nactions, max_actions, first, last, next_z;
 	void *s_masks_p, *a_masks_p, *vals_p;
 	struct mlx5_fields *f;
@@ -1942,6 +2013,8 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 	nactions = parse_attr->num_mod_hdr_actions;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		bool skip;
+
 		f = &fields[i];
 		/* avoid seeing bits set from previous iterations */
 		s_mask = 0;
@@ -1970,19 +2043,34 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 			return -EOPNOTSUPP;
 		}
 
+		skip = false;
 		if (s_mask) {
+			void *match_mask = headers_c + f->match_offset;
+			void *match_val = headers_v + f->match_offset;
+
 			cmd  = MLX5_ACTION_TYPE_SET;
 			mask = s_mask;
 			vals_p = (void *)set_vals + f->offset;
+			/* don't rewrite if we have a match on the same value */
+			if (cmp_val_mask(vals_p, s_masks_p, match_val,
+					 match_mask, f->size))
+				skip = true;
 			/* clear to denote we consumed this field */
 			memset(s_masks_p, 0, f->size);
 		} else {
+			u32 zero = 0;
+
 			cmd  = MLX5_ACTION_TYPE_ADD;
 			mask = a_mask;
 			vals_p = (void *)add_vals + f->offset;
+			/* add 0 is no change */
+			if (!memcmp(vals_p, &zero, f->size))
+				skip = true;
 			/* clear to denote we consumed this field */
 			memset(a_masks_p, 0, f->size);
 		}
+		if (skip)
+			continue;
 
 		field_bsize = f->size * BITS_PER_BYTE;
 
@@ -2029,6 +2117,15 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 	return 0;
 }
 
+static int mlx5e_flow_namespace_max_modify_action(struct mlx5_core_dev *mdev,
+						  int namespace)
+{
+	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
+		return MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, max_modify_header_actions);
+	else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
+		return MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_modify_header_actions);
+}
+
 static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 				 struct pedit_headers_action *hdrs,
 				 int namespace,
@@ -2040,11 +2137,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 		hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits;
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
 
-	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
-		max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, max_modify_header_actions);
-	else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
-		max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, max_modify_header_actions);
-
+	max_actions = mlx5e_flow_namespace_max_modify_action(priv->mdev, namespace);
 	/* can get up to crazingly 16 HW actions in 32 bits pedit SW key */
 	max_actions = min(max_actions, nkeys * 16);
 
@@ -2077,6 +2170,12 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv,
 		goto out_err;
 	}
 
+	if (!mlx5e_flow_namespace_max_modify_action(priv->mdev, namespace)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "The pedit offload action is not supported");
+		goto out_err;
+	}
+
 	mask = act->mangle.mask;
 	val = act->mangle.val;
 	offset = act->mangle.offset;
@@ -2095,6 +2194,7 @@ out_err:
 static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
 				 struct mlx5e_tc_flow_parse_attr *parse_attr,
 				 struct pedit_headers_action *hdrs,
+				 u32 *action_flags,
 				 struct netlink_ext_ack *extack)
 {
 	struct pedit_headers *cmd_masks;
@@ -2107,7 +2207,7 @@ static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
 			goto out_err;
 	}
 
-	err = offload_pedit_fields(hdrs, parse_attr, extack);
+	err = offload_pedit_fields(hdrs, parse_attr, action_flags, extack);
 	if (err < 0)
 		goto out_dealloc_parsed_actions;
 
@@ -2219,11 +2319,7 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	u8 ip_proto;
 	int i;
 
-	if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
-		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers);
-	else
-		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
-
+	headers_v = get_match_headers_value(actions, spec);
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
 
 	/* for non-IP we only re-write MACs, so we're okay */
@@ -2269,7 +2365,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 		actions = flow->nic_attr->action;
 
 	if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
-	    !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+	    !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) ||
+	      (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)))
 		return false;
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -2309,10 +2406,25 @@ static int add_vlan_rewrite_action(struct mlx5e_priv *priv, int namespace,
 		.mangle.mask = ~(u32)be16_to_cpu(*(__be16 *)&mask16),
 		.mangle.val = (u32)be16_to_cpu(*(__be16 *)&val16),
 	};
+	u8 match_prio_mask, match_prio_val;
+	void *headers_c, *headers_v;
 	int err;
 
-	if (act->vlan.prio) {
-		NL_SET_ERR_MSG_MOD(extack, "Setting VLAN prio is not supported");
+	headers_c = get_match_headers_criteria(*action, &parse_attr->spec);
+	headers_v = get_match_headers_value(*action, &parse_attr->spec);
+
+	if (!(MLX5_GET(fte_match_set_lyr_2_4, headers_c, cvlan_tag) &&
+	      MLX5_GET(fte_match_set_lyr_2_4, headers_v, cvlan_tag))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "VLAN rewrite action must have VLAN protocol match");
+		return -EOPNOTSUPP;
+	}
+
+	match_prio_mask = MLX5_GET(fte_match_set_lyr_2_4, headers_c, first_prio);
+	match_prio_val = MLX5_GET(fte_match_set_lyr_2_4, headers_v, first_prio);
+	if (act->vlan.prio != (match_prio_val & match_prio_mask)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Changing VLAN prio is not supported");
 		return -EOPNOTSUPP;
 	}
 
@@ -2406,16 +2518,22 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 			}
 			break;
 		default:
-			return -EINVAL;
+			NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
+			return -EOPNOTSUPP;
 		}
 	}
 
 	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
 	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
 		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
-					    parse_attr, hdrs, extack);
+					    parse_attr, hdrs, &action, extack);
 		if (err)
 			return err;
+		/* in case all pedit actions are skipped, remove the MOD_HDR
+		 * flag.
+		 */
+		if (parse_attr->num_mod_hdr_actions == 0)
+			action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 	}
 
 	attr->action = action;
@@ -2593,15 +2711,60 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static int add_vlan_push_action(struct mlx5e_priv *priv,
+				struct mlx5_esw_flow_attr *attr,
+				struct net_device **out_dev,
+				u32 *action)
+{
+	struct net_device *vlan_dev = *out_dev;
+	struct flow_action_entry vlan_act = {
+		.id = FLOW_ACTION_VLAN_PUSH,
+		.vlan.vid = vlan_dev_vlan_id(vlan_dev),
+		.vlan.proto = vlan_dev_vlan_proto(vlan_dev),
+		.vlan.prio = 0,
+	};
+	int err;
+
+	err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+	if (err)
+		return err;
+
+	*out_dev = dev_get_by_index_rcu(dev_net(vlan_dev),
+					dev_get_iflink(vlan_dev));
+	if (is_vlan_dev(*out_dev))
+		err = add_vlan_push_action(priv, attr, out_dev, action);
+
+	return err;
+}
+
+static int add_vlan_pop_action(struct mlx5e_priv *priv,
+			       struct mlx5_esw_flow_attr *attr,
+			       u32 *action)
+{
+	int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev);
+	struct flow_action_entry vlan_act = {
+		.id = FLOW_ACTION_VLAN_POP,
+	};
+	int err = 0;
+
+	while (nest_level--) {
+		err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				struct flow_action *flow_action,
-				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
 	struct pedit_headers_action hdrs[2] = {};
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	const struct ip_tunnel_info *info = NULL;
 	const struct flow_action_entry *act;
@@ -2673,6 +2836,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				    uplink_upper == out_dev)
 					out_dev = uplink_dev;
 
+				if (is_vlan_dev(out_dev)) {
+					err = add_vlan_push_action(priv, attr,
+								   &out_dev,
+								   &action);
+					if (err)
+						return err;
+				}
+				if (is_vlan_dev(parse_attr->filter_dev)) {
+					err = add_vlan_pop_action(priv, attr,
+								  &action);
+					if (err)
+						return err;
+				}
+
 				if (!mlx5e_eswitch_rep(out_dev))
 					return -EOPNOTSUPP;
 
@@ -2686,7 +2863,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 					out_dev->ifindex;
 				parse_attr->tun_info[attr->out_count] = *info;
 				encap = false;
-				attr->parse_attr = parse_attr;
 				attr->dests[attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
 				attr->out_count++;
@@ -2765,16 +2941,27 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			break;
 			}
 		default:
-			return -EINVAL;
+			NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
+			return -EOPNOTSUPP;
 		}
 	}
 
 	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
 	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
 		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB,
-					    parse_attr, hdrs, extack);
+					    parse_attr, hdrs, &action, extack);
 		if (err)
 			return err;
+		/* in case all pedit actions are skipped, remove the MOD_HDR
+		 * flag. we might have set split_count either by pedit or
+		 * pop/push. if there is no pop/push either, reset it too.
+		 */
+		if (parse_attr->num_mod_hdr_actions == 0) {
+			action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+			if (!((action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
+			      (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)))
+				attr->split_count = 0;
+		}
 	}
 
 	attr->action = action;
@@ -2943,7 +3130,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	err = parse_tc_fdb_actions(priv, &rule->action, parse_attr, flow, extack);
+	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack);
 	if (err)
 		goto err_free;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 46a747f7c162..e9837aeb7088 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -707,7 +707,7 @@ void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
 
 	__raw_writel((__force u32)cpu_to_be32(val), addr);
 	/* We still want ordering, just not swabbing, so add a barrier */
-	mb();
+	wmb();
 }
 EXPORT_SYMBOL(mlx5_eq_update_ci);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index fe770cd2151c..1a3cab34b850 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1698,8 +1698,6 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
 {
 	int err;
 
-	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
-
 	err = esw_offloads_steering_init(esw, total_nvports);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 5d5864e8df3c..a81e8d2168d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -21,6 +21,7 @@ struct mlx5_event_nb {
 static int any_notifier(struct notifier_block *, unsigned long, void *);
 static int temp_warn(struct notifier_block *, unsigned long, void *);
 static int port_module(struct notifier_block *, unsigned long, void *);
+static int pcie_core(struct notifier_block *, unsigned long, void *);
 
 /* handler which forwards the event to events->nh, driver notifiers */
 static int forward_event(struct notifier_block *, unsigned long, void *);
@@ -30,6 +31,7 @@ static struct mlx5_nb events_nbs_ref[] = {
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+	{.nb.notifier_call = pcie_core,     .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
 
 	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
@@ -51,11 +53,14 @@ static struct mlx5_nb events_nbs_ref[] = {
 
 struct mlx5_events {
 	struct mlx5_core_dev *dev;
+	struct workqueue_struct *wq;
 	struct mlx5_event_nb  notifiers[ARRAY_SIZE(events_nbs_ref)];
 	/* driver notifier chain */
 	struct atomic_notifier_head nh;
 	/* port module events stats */
 	struct mlx5_pme_stats pme_stats;
+	/*pcie_core*/
+	struct work_struct pcie_core_work;
 };
 
 static const char *eqe_type_str(u8 type)
@@ -249,6 +254,69 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 	return NOTIFY_OK;
 }
 
+enum {
+	MLX5_PCI_POWER_COULD_NOT_BE_READ = 0x0,
+	MLX5_PCI_POWER_SUFFICIENT_REPORTED = 0x1,
+	MLX5_PCI_POWER_INSUFFICIENT_REPORTED = 0x2,
+};
+
+static void mlx5_pcie_event(struct work_struct *work)
+{
+	u32 out[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+	struct mlx5_events *events;
+	struct mlx5_core_dev *dev;
+	u8 power_status;
+	u16 pci_power;
+
+	events = container_of(work, struct mlx5_events, pcie_core_work);
+	dev  = events->dev;
+
+	if (!MLX5_CAP_MCAM_FEATURE(dev, pci_status_and_power))
+		return;
+
+	mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+			     MLX5_REG_MPEIN, 0, 0);
+	power_status = MLX5_GET(mpein_reg, out, pwr_status);
+	pci_power = MLX5_GET(mpein_reg, out, pci_power);
+
+	switch (power_status) {
+	case MLX5_PCI_POWER_COULD_NOT_BE_READ:
+		mlx5_core_info_rl(dev,
+				  "PCIe slot power capability was not advertised.\n");
+		break;
+	case MLX5_PCI_POWER_INSUFFICIENT_REPORTED:
+		mlx5_core_warn_rl(dev,
+				  "Detected insufficient power on the PCIe slot (%uW).\n",
+				  pci_power);
+		break;
+	case MLX5_PCI_POWER_SUFFICIENT_REPORTED:
+		mlx5_core_info_rl(dev,
+				  "PCIe slot advertised sufficient power (%uW).\n",
+				  pci_power);
+		break;
+	}
+}
+
+static int pcie_core(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb    *event_nb = mlx5_nb_cof(nb,
+							struct mlx5_event_nb,
+							nb);
+	struct mlx5_events      *events   = event_nb->ctx;
+	struct mlx5_eqe         *eqe      = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT:
+			queue_work(events->wq, &events->pcie_core_work);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
 void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
 {
 	*stats = dev->priv.events->pme_stats;
@@ -277,11 +345,17 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
 	events->dev = dev;
 	dev->priv.events = events;
+	events->wq = create_singlethread_workqueue("mlx5_events");
+	if (!events->wq)
+		return -ENOMEM;
+	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
+
 	return 0;
 }
 
 void mlx5_events_cleanup(struct mlx5_core_dev *dev)
 {
+	destroy_workqueue(dev->priv.events->wq);
 	kvfree(dev->priv.events);
 }
 
@@ -304,6 +378,7 @@ void mlx5_events_stop(struct mlx5_core_dev *dev)
 
 	for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
 		mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
+	flush_workqueue(events->wq);
 }
 
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 873541ef4c1b..ca2296a2f9ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -135,7 +135,7 @@ static void mlx5_fpga_conn_notify_hw(struct mlx5_fpga_conn *conn, void *wqe)
 	*conn->qp.wq.sq.db = cpu_to_be32(conn->qp.sq.pc);
 	/* Make sure that doorbell record is visible before ringing */
 	wmb();
-	mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET, NULL);
+	mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET);
 }
 
 static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index 7e2e871dbf83..52c9dee91ea4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -37,6 +37,7 @@
 
 #include <linux/mlx5/eq.h>
 
+#include "mlx5_core.h"
 #include "lib/eq.h"
 #include "fpga/cmd.h"
 
@@ -62,26 +63,26 @@ struct mlx5_fpga_device {
 };
 
 #define mlx5_fpga_dbg(__adev, format, ...) \
-	dev_dbg(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
-		 __func__, __LINE__, current->pid, ##__VA_ARGS__)
+	mlx5_core_dbg((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+		       __func__, __LINE__, current->pid, ##__VA_ARGS__)
 
 #define mlx5_fpga_err(__adev, format, ...) \
-	dev_err(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
-		__func__, __LINE__, current->pid, ##__VA_ARGS__)
+	mlx5_core_err((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+		      __func__, __LINE__, current->pid, ##__VA_ARGS__)
 
 #define mlx5_fpga_warn(__adev, format, ...) \
-	dev_warn(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
-		__func__, __LINE__, current->pid, ##__VA_ARGS__)
+	mlx5_core_warn((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+		       __func__, __LINE__, current->pid, ##__VA_ARGS__)
 
 #define mlx5_fpga_warn_ratelimited(__adev, format, ...) \
-	dev_warn_ratelimited(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d: " \
-		format, __func__, __LINE__, ##__VA_ARGS__)
+	mlx5_core_err_rl((__adev)->mdev, "FPGA: %s:%d: " \
+			 format, __func__, __LINE__, ##__VA_ARGS__)
 
 #define mlx5_fpga_notice(__adev, format, ...) \
-	dev_notice(&(__adev)->mdev->pdev->dev, "FPGA: " format, ##__VA_ARGS__)
+	mlx5_core_info((__adev)->mdev, "FPGA: " format, ##__VA_ARGS__)
 
 #define mlx5_fpga_info(__adev, format, ...) \
-	dev_info(&(__adev)->mdev->pdev->dev, "FPGA: " format, ##__VA_ARGS__)
+	mlx5_core_info((__adev)->mdev, "FPGA: " format, ##__VA_ARGS__)
 
 int mlx5_fpga_init(struct mlx5_core_dev *mdev);
 void mlx5_fpga_cleanup(struct mlx5_core_dev *mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 0be3eb86dd84..78e073243f40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -819,7 +819,7 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	struct mlx5_flow_root_namespace *root = find_root(&prio->node);
 	struct mlx5_ft_underlay_qp *uqp;
 	int min_level = INT_MAX;
-	int err;
+	int err = 0;
 	u32 qpn;
 
 	if (root->root_ft)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index cb9fa3430c53..3b98fcdd7d0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -152,11 +152,11 @@ static void health_recover(struct work_struct *work)
 
 	nic_state = mlx5_get_nic_state(dev);
 	if (nic_state == MLX5_NIC_IFC_INVALID) {
-		dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n");
+		mlx5_core_err(dev, "health recovery flow aborted since the nic state is invalid\n");
 		return;
 	}
 
-	dev_err(&dev->pdev->dev, "starting health recovery flow\n");
+	mlx5_core_err(dev, "starting health recovery flow\n");
 	mlx5_recover_device(dev);
 }
 
@@ -180,8 +180,8 @@ static void health_care(struct work_struct *work)
 	if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
 		schedule_delayed_work(&health->recover_work, recover_delay);
 	else
-		dev_err(&dev->pdev->dev,
-			"new health works are not permitted at this stage\n");
+		mlx5_core_err(dev,
+			      "new health works are not permitted at this stage\n");
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 }
 
@@ -228,18 +228,22 @@ static void print_health_info(struct mlx5_core_dev *dev)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(h->assert_var); i++)
-		dev_err(&dev->pdev->dev, "assert_var[%d] 0x%08x\n", i, ioread32be(h->assert_var + i));
+		mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i,
+			      ioread32be(h->assert_var + i));
 
-	dev_err(&dev->pdev->dev, "assert_exit_ptr 0x%08x\n", ioread32be(&h->assert_exit_ptr));
-	dev_err(&dev->pdev->dev, "assert_callra 0x%08x\n", ioread32be(&h->assert_callra));
+	mlx5_core_err(dev, "assert_exit_ptr 0x%08x\n",
+		      ioread32be(&h->assert_exit_ptr));
+	mlx5_core_err(dev, "assert_callra 0x%08x\n",
+		      ioread32be(&h->assert_callra));
 	sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev));
-	dev_err(&dev->pdev->dev, "fw_ver %s\n", fw_str);
-	dev_err(&dev->pdev->dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
-	dev_err(&dev->pdev->dev, "irisc_index %d\n", ioread8(&h->irisc_index));
-	dev_err(&dev->pdev->dev, "synd 0x%x: %s\n", ioread8(&h->synd), hsynd_str(ioread8(&h->synd)));
-	dev_err(&dev->pdev->dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
+	mlx5_core_err(dev, "fw_ver %s\n", fw_str);
+	mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
+	mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index));
+	mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd),
+		      hsynd_str(ioread8(&h->synd)));
+	mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
 	fw = ioread32be(&h->fw_ver);
-	dev_err(&dev->pdev->dev, "raw fw_ver 0x%08x\n", fw);
+	mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw);
 }
 
 static unsigned long get_next_poll_jiffies(void)
@@ -262,8 +266,7 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev)
 	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
 		queue_work(health->wq, &health->work);
 	else
-		dev_err(&dev->pdev->dev,
-			"new health works are not permitted at this stage\n");
+		mlx5_core_err(dev, "new health works are not permitted at this stage\n");
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 }
 
@@ -284,7 +287,7 @@ static void poll_health(struct timer_list *t)
 
 	health->prev = count;
 	if (health->miss_counter == MAX_MISSES) {
-		dev_err(&dev->pdev->dev, "device's health compromised - reached miss count\n");
+		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
 		print_health_info(dev);
 	}
 
@@ -352,6 +355,13 @@ void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
 	cancel_delayed_work_sync(&dev->priv.health.recover_work);
 }
 
+void mlx5_health_flush(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	flush_workqueue(health->wq);
+}
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -370,7 +380,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	strcpy(name, "mlx5_health");
-	strcat(name, dev_name(&dev->pdev->dev));
+	strcat(name, dev->priv.name);
 	health->wq = create_singlethread_workqueue(name);
 	kfree(name);
 	if (!health->wq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 4eac42555c7d..9b03ae1e1e10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -77,15 +77,14 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
 	       void *ppriv)
 {
 	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
-	u16 max_mtu;
 	int err;
 
 	err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
 	if (err)
 		return err;
 
-	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
-	netdev->mtu = max_mtu;
+	mlx5e_set_netdev_mtu_boundaries(priv);
+	netdev->mtu = netdev->max_mtu;
 
 	mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
 			       mlx5e_get_netdev_max_channels(netdev),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 76716419370d..5245b0b1770f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -567,24 +567,23 @@ query_ex:
 
 static int set_hca_cap(struct mlx5_core_dev *dev)
 {
-	struct pci_dev *pdev = dev->pdev;
 	int err;
 
 	err = handle_hca_cap(dev);
 	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap failed\n");
+		mlx5_core_err(dev, "handle_hca_cap failed\n");
 		goto out;
 	}
 
 	err = handle_hca_cap_atomic(dev);
 	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
+		mlx5_core_err(dev, "handle_hca_cap_atomic failed\n");
 		goto out;
 	}
 
 	err = handle_hca_cap_odp(dev);
 	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap_odp failed\n");
+		mlx5_core_err(dev, "handle_hca_cap_odp failed\n");
 		goto out;
 	}
 
@@ -716,36 +715,29 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 	return -EOPNOTSUPP;
 }
 
-static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
+			 const struct pci_device_id *id)
 {
-	struct pci_dev *pdev = dev->pdev;
+	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
+	dev->pdev = pdev;
+	priv->pci_dev_data = id->driver_data;
+
 	pci_set_drvdata(dev->pdev, dev);
-	strncpy(priv->name, dev_name(&pdev->dev), MLX5_MAX_NAME_LEN);
-	priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
-
-	mutex_init(&priv->pgdir_mutex);
-	INIT_LIST_HEAD(&priv->pgdir_list);
-	spin_lock_init(&priv->mkey_lock);
-
-	mutex_init(&priv->alloc_mutex);
 
+	dev->bar_addr = pci_resource_start(pdev, 0);
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
-	if (mlx5_debugfs_root)
-		priv->dbg_root =
-			debugfs_create_dir(pci_name(pdev), mlx5_debugfs_root);
-
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
-		goto err_dbg;
+		mlx5_core_err(dev, "Cannot enable PCI device, aborting\n");
+		return err;
 	}
 
 	err = request_bar(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "error requesting BARs, aborting\n");
+		mlx5_core_err(dev, "error requesting BARs, aborting\n");
 		goto err_disable;
 	}
 
@@ -753,7 +745,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	err = set_dma_caps(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed setting DMA capabilities mask, aborting\n");
+		mlx5_core_err(dev, "Failed setting DMA capabilities mask, aborting\n");
 		goto err_clr_master;
 	}
 
@@ -762,11 +754,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128))
 		mlx5_core_dbg(dev, "Enabling pci atomics failed\n");
 
-	dev->iseg_base = pci_resource_start(dev->pdev, 0);
+	dev->iseg_base = dev->bar_addr;
 	dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg));
 	if (!dev->iseg) {
 		err = -ENOMEM;
-		dev_err(&pdev->dev, "Failed mapping initialization segment, aborting\n");
+		mlx5_core_err(dev, "Failed mapping initialization segment, aborting\n");
 		goto err_clr_master;
 	}
 
@@ -777,52 +769,47 @@ err_clr_master:
 	release_bar(dev->pdev);
 err_disable:
 	mlx5_pci_disable_device(dev);
-
-err_dbg:
-	debugfs_remove(priv->dbg_root);
 	return err;
 }
 
-static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
 	mlx5_pci_disable_device(dev);
-	debugfs_remove_recursive(priv->dbg_root);
 }
 
-static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static int mlx5_init_once(struct mlx5_core_dev *dev)
 {
-	struct pci_dev *pdev = dev->pdev;
 	int err;
 
-	priv->devcom = mlx5_devcom_register_device(dev);
-	if (IS_ERR(priv->devcom))
-		dev_err(&pdev->dev, "failed to register with devcom (0x%p)\n",
-			priv->devcom);
+	dev->priv.devcom = mlx5_devcom_register_device(dev);
+	if (IS_ERR(dev->priv.devcom))
+		mlx5_core_err(dev, "failed to register with devcom (0x%p)\n",
+			      dev->priv.devcom);
 
 	err = mlx5_query_board_id(dev);
 	if (err) {
-		dev_err(&pdev->dev, "query board id failed\n");
+		mlx5_core_err(dev, "query board id failed\n");
 		goto err_devcom;
 	}
 
 	err = mlx5_eq_table_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to initialize eq\n");
+		mlx5_core_err(dev, "failed to initialize eq\n");
 		goto err_devcom;
 	}
 
 	err = mlx5_events_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to initialize events\n");
+		mlx5_core_err(dev, "failed to initialize events\n");
 		goto err_eq_cleanup;
 	}
 
 	err = mlx5_cq_debugfs_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to initialize cq debugfs\n");
+		mlx5_core_err(dev, "failed to initialize cq debugfs\n");
 		goto err_events_cleanup;
 	}
 
@@ -838,31 +825,31 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	err = mlx5_init_rl_table(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init rate limiting\n");
+		mlx5_core_err(dev, "Failed to init rate limiting\n");
 		goto err_tables_cleanup;
 	}
 
 	err = mlx5_mpfs_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init l2 table %d\n", err);
+		mlx5_core_err(dev, "Failed to init l2 table %d\n", err);
 		goto err_rl_cleanup;
 	}
 
 	err = mlx5_eswitch_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init eswitch %d\n", err);
+		mlx5_core_err(dev, "Failed to init eswitch %d\n", err);
 		goto err_mpfs_cleanup;
 	}
 
 	err = mlx5_sriov_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init sriov %d\n", err);
+		mlx5_core_err(dev, "Failed to init sriov %d\n", err);
 		goto err_eswitch_cleanup;
 	}
 
 	err = mlx5_fpga_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init fpga device %d\n", err);
+		mlx5_core_err(dev, "Failed to init fpga device %d\n", err);
 		goto err_sriov_cleanup;
 	}
 
@@ -912,93 +899,78 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
-static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
-			 bool boot)
+static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 {
-	struct pci_dev *pdev = dev->pdev;
 	int err;
 
-	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
-	mutex_lock(&dev->intf_state_mutex);
-	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n",
-			 __func__);
-		goto out;
-	}
-
-	dev_info(&pdev->dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev),
-		 fw_rev_min(dev), fw_rev_sub(dev));
+	mlx5_core_info(dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev),
+		       fw_rev_min(dev), fw_rev_sub(dev));
 
 	/* Only PFs hold the relevant PCIe information for this query */
 	if (mlx5_core_is_pf(dev))
 		pcie_print_link_status(dev->pdev);
 
-	/* on load removing any previous indication of internal error, device is
-	 * up
-	 */
-	dev->state = MLX5_DEVICE_STATE_UP;
-
 	/* wait for firmware to accept initialization segments configurations
 	 */
 	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
 	if (err) {
-		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
-			FW_PRE_INIT_TIMEOUT_MILI);
-		goto out_err;
+		mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+			      FW_PRE_INIT_TIMEOUT_MILI);
+		return err;
 	}
 
 	err = mlx5_cmd_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");
-		goto out_err;
+		mlx5_core_err(dev, "Failed initializing command interface, aborting\n");
+		return err;
 	}
 
 	err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI);
 	if (err) {
-		dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
-			FW_INIT_TIMEOUT_MILI);
+		mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n",
+			      FW_INIT_TIMEOUT_MILI);
 		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
-		dev_err(&pdev->dev, "enable hca failed\n");
+		mlx5_core_err(dev, "enable hca failed\n");
 		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_set_issi(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to set issi\n");
+		mlx5_core_err(dev, "failed to set issi\n");
 		goto err_disable_hca;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
-		dev_err(&pdev->dev, "failed to allocate boot pages\n");
+		mlx5_core_err(dev, "failed to allocate boot pages\n");
 		goto err_disable_hca;
 	}
 
 	err = set_hca_ctrl(dev);
 	if (err) {
-		dev_err(&pdev->dev, "set_hca_ctrl failed\n");
+		mlx5_core_err(dev, "set_hca_ctrl failed\n");
 		goto reclaim_boot_pages;
 	}
 
 	err = set_hca_cap(dev);
 	if (err) {
-		dev_err(&pdev->dev, "set_hca_cap failed\n");
+		mlx5_core_err(dev, "set_hca_cap failed\n");
 		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 0);
 	if (err) {
-		dev_err(&pdev->dev, "failed to allocate init pages\n");
+		mlx5_core_err(dev, "failed to allocate init pages\n");
 		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_cmd_init_hca(dev, sw_owner_id);
 	if (err) {
-		dev_err(&pdev->dev, "init hca failed\n");
+		mlx5_core_err(dev, "init hca failed\n");
 		goto reclaim_boot_pages;
 	}
 
@@ -1008,23 +980,50 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	err = mlx5_query_hca_caps(dev);
 	if (err) {
-		dev_err(&pdev->dev, "query hca failed\n");
-		goto err_stop_poll;
+		mlx5_core_err(dev, "query hca failed\n");
+		goto stop_health;
 	}
 
-	if (boot) {
-		err = mlx5_init_once(dev, priv);
-		if (err) {
-			dev_err(&pdev->dev, "sw objs init failed\n");
-			goto err_stop_poll;
-		}
+	return 0;
+
+stop_health:
+	mlx5_stop_health_poll(dev, boot);
+reclaim_boot_pages:
+	mlx5_reclaim_startup_pages(dev);
+err_disable_hca:
+	mlx5_core_disable_hca(dev, 0);
+err_cmd_cleanup:
+	mlx5_cmd_cleanup(dev);
+
+	return err;
+}
+
+static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
+{
+	int err;
+
+	mlx5_stop_health_poll(dev, boot);
+	err = mlx5_cmd_teardown_hca(dev);
+	if (err) {
+		mlx5_core_err(dev, "tear_down_hca failed, skip cleanup\n");
+		return err;
 	}
+	mlx5_reclaim_startup_pages(dev);
+	mlx5_core_disable_hca(dev, 0);
+	mlx5_cmd_cleanup(dev);
+
+	return 0;
+}
+
+static int mlx5_load(struct mlx5_core_dev *dev)
+{
+	int err;
 
 	dev->priv.uar = mlx5_get_uars_page(dev);
 	if (IS_ERR(dev->priv.uar)) {
-		dev_err(&pdev->dev, "Failed allocating uar, aborting\n");
+		mlx5_core_err(dev, "Failed allocating uar, aborting\n");
 		err = PTR_ERR(dev->priv.uar);
-		goto err_get_uars;
+		return err;
 	}
 
 	mlx5_events_start(dev);
@@ -1032,64 +1031,131 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	err = mlx5_eq_table_create(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to create EQs\n");
+		mlx5_core_err(dev, "Failed to create EQs\n");
 		goto err_eq_table;
 	}
 
 	err = mlx5_fw_tracer_init(dev->tracer);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init FW tracer\n");
+		mlx5_core_err(dev, "Failed to init FW tracer\n");
 		goto err_fw_tracer;
 	}
 
 	err = mlx5_fpga_device_start(dev);
 	if (err) {
-		dev_err(&pdev->dev, "fpga device start failed %d\n", err);
+		mlx5_core_err(dev, "fpga device start failed %d\n", err);
 		goto err_fpga_start;
 	}
 
 	err = mlx5_accel_ipsec_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "IPSec device start failed %d\n", err);
+		mlx5_core_err(dev, "IPSec device start failed %d\n", err);
 		goto err_ipsec_start;
 	}
 
 	err = mlx5_accel_tls_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "TLS device start failed %d\n", err);
+		mlx5_core_err(dev, "TLS device start failed %d\n", err);
 		goto err_tls_start;
 	}
 
 	err = mlx5_init_fs(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init flow steering\n");
+		mlx5_core_err(dev, "Failed to init flow steering\n");
 		goto err_fs;
 	}
 
 	err = mlx5_core_set_hca_defaults(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to set hca defaults\n");
+		mlx5_core_err(dev, "Failed to set hca defaults\n");
 		goto err_fs;
 	}
 
 	err = mlx5_sriov_attach(dev);
 	if (err) {
-		dev_err(&pdev->dev, "sriov init failed %d\n", err);
+		mlx5_core_err(dev, "sriov init failed %d\n", err);
 		goto err_sriov;
 	}
 
 	err = mlx5_ec_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init embedded CPU\n");
+		mlx5_core_err(dev, "Failed to init embedded CPU\n");
 		goto err_ec;
 	}
 
+	return 0;
+
+err_ec:
+	mlx5_sriov_detach(dev);
+err_sriov:
+	mlx5_cleanup_fs(dev);
+err_fs:
+	mlx5_accel_tls_cleanup(dev);
+err_tls_start:
+	mlx5_accel_ipsec_cleanup(dev);
+err_ipsec_start:
+	mlx5_fpga_device_stop(dev);
+err_fpga_start:
+	mlx5_fw_tracer_cleanup(dev->tracer);
+err_fw_tracer:
+	mlx5_eq_table_destroy(dev);
+err_eq_table:
+	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
+	mlx5_put_uars_page(dev, dev->priv.uar);
+	return err;
+}
+
+static void mlx5_unload(struct mlx5_core_dev *dev)
+{
+	mlx5_ec_cleanup(dev);
+	mlx5_sriov_detach(dev);
+	mlx5_cleanup_fs(dev);
+	mlx5_accel_ipsec_cleanup(dev);
+	mlx5_accel_tls_cleanup(dev);
+	mlx5_fpga_device_stop(dev);
+	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_eq_table_destroy(dev);
+	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
+	mlx5_put_uars_page(dev, dev->priv.uar);
+}
+
+static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
+{
+	int err = 0;
+
+	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
+	mutex_lock(&dev->intf_state_mutex);
+	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
+		mlx5_core_warn(dev, "interface is up, NOP\n");
+		goto out;
+	}
+	/* remove any previous indication of internal error */
+	dev->state = MLX5_DEVICE_STATE_UP;
+
+	err = mlx5_function_setup(dev, boot);
+	if (err)
+		goto out;
+
+	if (boot) {
+		err = mlx5_init_once(dev);
+		if (err) {
+			mlx5_core_err(dev, "sw objs init failed\n");
+			goto function_teardown;
+		}
+	}
+
+	err = mlx5_load(dev);
+	if (err)
+		goto err_load;
+
 	if (mlx5_device_registered(dev)) {
 		mlx5_attach_device(dev);
 	} else {
 		err = mlx5_register_device(dev);
 		if (err) {
-			dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err);
+			mlx5_core_err(dev, "register device failed %d\n", err);
 			goto err_reg_dev;
 		}
 	}
@@ -1098,66 +1164,22 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 out:
 	mutex_unlock(&dev->intf_state_mutex);
 
-	return 0;
+	return err;
 
 err_reg_dev:
-	mlx5_ec_cleanup(dev);
-
-err_ec:
-	mlx5_sriov_detach(dev);
-
-err_sriov:
-	mlx5_cleanup_fs(dev);
-
-err_fs:
-	mlx5_accel_tls_cleanup(dev);
-
-err_tls_start:
-	mlx5_accel_ipsec_cleanup(dev);
-
-err_ipsec_start:
-	mlx5_fpga_device_stop(dev);
-
-err_fpga_start:
-	mlx5_fw_tracer_cleanup(dev->tracer);
-
-err_fw_tracer:
-	mlx5_eq_table_destroy(dev);
-
-err_eq_table:
-	mlx5_pagealloc_stop(dev);
-	mlx5_events_stop(dev);
-	mlx5_put_uars_page(dev, priv->uar);
-
-err_get_uars:
+	mlx5_unload(dev);
+err_load:
 	if (boot)
 		mlx5_cleanup_once(dev);
-
-err_stop_poll:
-	mlx5_stop_health_poll(dev, boot);
-	if (mlx5_cmd_teardown_hca(dev)) {
-		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
-		goto out_err;
-	}
-
-reclaim_boot_pages:
-	mlx5_reclaim_startup_pages(dev);
-
-err_disable_hca:
-	mlx5_core_disable_hca(dev, 0);
-
-err_cmd_cleanup:
-	mlx5_cmd_cleanup(dev);
-
-out_err:
+function_teardown:
+	mlx5_function_teardown(dev, boot);
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 	mutex_unlock(&dev->intf_state_mutex);
 
 	return err;
 }
 
-static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
-			   bool cleanup)
+static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
 	int err = 0;
 
@@ -1166,8 +1188,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
-			 __func__);
+		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
+			       __func__);
 		if (cleanup)
 			mlx5_cleanup_once(dev);
 		goto out;
@@ -1178,30 +1200,12 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (mlx5_device_registered(dev))
 		mlx5_detach_device(dev);
 
-	mlx5_ec_cleanup(dev);
-	mlx5_sriov_detach(dev);
-	mlx5_cleanup_fs(dev);
-	mlx5_accel_ipsec_cleanup(dev);
-	mlx5_accel_tls_cleanup(dev);
-	mlx5_fpga_device_stop(dev);
-	mlx5_fw_tracer_cleanup(dev->tracer);
-	mlx5_eq_table_destroy(dev);
-	mlx5_pagealloc_stop(dev);
-	mlx5_events_stop(dev);
-	mlx5_put_uars_page(dev, priv->uar);
+	mlx5_unload(dev);
+
 	if (cleanup)
 		mlx5_cleanup_once(dev);
-	mlx5_stop_health_poll(dev, cleanup);
-
-	err = mlx5_cmd_teardown_hca(dev);
-	if (err) {
-		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
-		goto out;
-	}
-	mlx5_reclaim_startup_pages(dev);
-	mlx5_core_disable_hca(dev, 0);
-	mlx5_cmd_cleanup(dev);
 
+	mlx5_function_teardown(dev, cleanup);
 out:
 	mutex_unlock(&dev->intf_state_mutex);
 	return err;
@@ -1218,29 +1222,15 @@ static const struct devlink_ops mlx5_devlink_ops = {
 #endif
 };
 
-#define MLX5_IB_MOD "mlx5_ib"
-static int init_one(struct pci_dev *pdev,
-		    const struct pci_device_id *id)
+static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name)
 {
-	struct mlx5_core_dev *dev;
-	struct devlink *devlink;
-	struct mlx5_priv *priv;
+	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	devlink = devlink_alloc(&mlx5_devlink_ops, sizeof(*dev));
-	if (!devlink) {
-		dev_err(&pdev->dev, "kzalloc failed\n");
-		return -ENOMEM;
-	}
+	strncpy(priv->name, name, MLX5_MAX_NAME_LEN);
+	priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
 
-	dev = devlink_priv(devlink);
-	priv = &dev->priv;
-	priv->pci_dev_data = id->driver_data;
-
-	pci_set_drvdata(pdev, dev);
-
-	dev->pdev = pdev;
-	dev->profile = &profile[prof_sel];
+	dev->profile = &profile[profile_idx];
 
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
@@ -1252,25 +1242,72 @@ static int init_one(struct pci_dev *pdev,
 	INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
 	INIT_LIST_HEAD(&priv->bfregs.wc_head.list);
 
-	err = mlx5_pci_init(dev, priv);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
-		goto clean_dev;
+	mutex_init(&priv->alloc_mutex);
+	mutex_init(&priv->pgdir_mutex);
+	INIT_LIST_HEAD(&priv->pgdir_list);
+	spin_lock_init(&priv->mkey_lock);
+
+	priv->dbg_root = debugfs_create_dir(name, mlx5_debugfs_root);
+	if (!priv->dbg_root) {
+		pr_err("mlx5_core: %s error, Cannot create debugfs dir, aborting\n", name);
+		return -ENOMEM;
 	}
 
 	err = mlx5_health_init(dev);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_health_init failed with error code %d\n", err);
-		goto close_pci;
-	}
+	if (err)
+		goto err_health_init;
 
 	err = mlx5_pagealloc_init(dev);
 	if (err)
 		goto err_pagealloc_init;
 
-	err = mlx5_load_one(dev, priv, true);
+	return 0;
+
+err_pagealloc_init:
+	mlx5_health_cleanup(dev);
+err_health_init:
+	debugfs_remove(dev->priv.dbg_root);
+
+	return err;
+}
+
+static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
+{
+	mlx5_pagealloc_cleanup(dev);
+	mlx5_health_cleanup(dev);
+	debugfs_remove_recursive(dev->priv.dbg_root);
+}
+
+#define MLX5_IB_MOD "mlx5_ib"
+static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct mlx5_core_dev *dev;
+	struct devlink *devlink;
+	int err;
+
+	devlink = devlink_alloc(&mlx5_devlink_ops, sizeof(*dev));
+	if (!devlink) {
+		dev_err(&pdev->dev, "kzalloc failed\n");
+		return -ENOMEM;
+	}
+
+	dev = devlink_priv(devlink);
+
+	err = mlx5_mdev_init(dev, prof_sel, dev_name(&pdev->dev));
+	if (err)
+		goto mdev_init_err;
+
+	err = mlx5_pci_init(dev, pdev, id);
 	if (err) {
-		dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
+		mlx5_core_err(dev, "mlx5_pci_init failed with error code %d\n",
+			      err);
+		goto pci_init_err;
+	}
+
+	err = mlx5_load_one(dev, true);
+	if (err) {
+		mlx5_core_err(dev, "mlx5_load_one failed with error code %d\n",
+			      err);
 		goto err_load_one;
 	}
 
@@ -1284,14 +1321,13 @@ static int init_one(struct pci_dev *pdev,
 	return 0;
 
 clean_load:
-	mlx5_unload_one(dev, priv, true);
+	mlx5_unload_one(dev, true);
+
 err_load_one:
-	mlx5_pagealloc_cleanup(dev);
-err_pagealloc_init:
-	mlx5_health_cleanup(dev);
-close_pci:
-	mlx5_pci_close(dev, priv);
-clean_dev:
+	mlx5_pci_close(dev);
+pci_init_err:
+	mlx5_mdev_uninit(dev);
+mdev_init_err:
 	devlink_free(devlink);
 
 	return err;
@@ -1301,20 +1337,18 @@ static void remove_one(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_priv *priv = &dev->priv;
 
 	devlink_unregister(devlink);
 	mlx5_unregister_device(dev);
 
-	if (mlx5_unload_one(dev, priv, true)) {
-		dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n");
-		mlx5_health_cleanup(dev);
+	if (mlx5_unload_one(dev, true)) {
+		mlx5_core_err(dev, "mlx5_unload_one failed\n");
+		mlx5_health_flush(dev);
 		return;
 	}
 
-	mlx5_pagealloc_cleanup(dev);
-	mlx5_health_cleanup(dev);
-	mlx5_pci_close(dev, priv);
+	mlx5_pci_close(dev);
+	mlx5_mdev_uninit(dev);
 	devlink_free(devlink);
 }
 
@@ -1322,12 +1356,11 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 
-	dev_info(&pdev->dev, "%s was called\n", __func__);
+	mlx5_core_info(dev, "%s was called\n", __func__);
 
 	mlx5_enter_error_state(dev, false);
-	mlx5_unload_one(dev, priv, false);
+	mlx5_unload_one(dev, false);
 	/* In case of kernel call drain the health wq */
 	if (state) {
 		mlx5_drain_health_wq(dev);
@@ -1354,7 +1387,9 @@ static int wait_vital(struct pci_dev *pdev)
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
 			if (last_count && last_count != count) {
-				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				mlx5_core_info(dev,
+					       "wait vital counter value 0x%x after %d iterations\n",
+					       count, i);
 				return 0;
 			}
 			last_count = count;
@@ -1370,12 +1405,12 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	int err;
 
-	dev_info(&pdev->dev, "%s was called\n", __func__);
+	mlx5_core_info(dev, "%s was called\n", __func__);
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
-		dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
-			, __func__, err);
+		mlx5_core_err(dev, "%s: mlx5_pci_enable_device failed with error code: %d\n",
+			      __func__, err);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -1384,7 +1419,7 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 	pci_save_state(pdev);
 
 	if (wait_vital(pdev)) {
-		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		mlx5_core_err(dev, "%s: wait_vital timed out\n", __func__);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -1394,17 +1429,16 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 static void mlx5_pci_resume(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	dev_info(&pdev->dev, "%s was called\n", __func__);
+	mlx5_core_info(dev, "%s was called\n", __func__);
 
-	err = mlx5_load_one(dev, priv, false);
+	err = mlx5_load_one(dev, false);
 	if (err)
-		dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
-			, __func__, err);
+		mlx5_core_err(dev, "%s: mlx5_load_one failed with error code: %d\n",
+			      __func__, err);
 	else
-		dev_info(&pdev->dev, "%s: device recovered\n", __func__);
+		mlx5_core_info(dev, "%s: device recovered\n", __func__);
 }
 
 static const struct pci_error_handlers mlx5_err_handler = {
@@ -1466,13 +1500,12 @@ succeed:
 static void shutdown(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	dev_info(&pdev->dev, "Shutdown was called\n");
+	mlx5_core_info(dev, "Shutdown was called\n");
 	err = mlx5_try_fast_unload(dev);
 	if (err)
-		mlx5_unload_one(dev, priv, false);
+		mlx5_unload_one(dev, false);
 	mlx5_pci_disable_device(dev);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6fb99be60584..8213c994e205 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -48,12 +48,12 @@
 extern uint mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(__dev, format, ...)				\
-	dev_dbg(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,		\
+	pr_debug("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,      \
 		 __func__, __LINE__, current->pid,			\
 		 ##__VA_ARGS__)
 
 #define mlx5_core_dbg_once(__dev, format, ...)				\
-	dev_dbg_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+	pr_debug_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
 		     __func__, __LINE__, current->pid,			\
 		     ##__VA_ARGS__)
 
@@ -64,28 +64,37 @@ do {									\
 } while (0)
 
 #define mlx5_core_err(__dev, format, ...)				\
-	dev_err(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+	pr_err("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,        \
 		__func__, __LINE__, current->pid,	\
 	       ##__VA_ARGS__)
 
-#define mlx5_core_err_rl(__dev, format, ...)				\
-	dev_err_ratelimited(&(__dev)->pdev->dev,			\
-			   "%s:%d:(pid %d): " format,			\
-			   __func__, __LINE__, current->pid,		\
+#define mlx5_core_err_rl(__dev, format, ...)				     \
+	pr_err_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+			   __func__, __LINE__, current->pid,		     \
 			   ##__VA_ARGS__)
 
 #define mlx5_core_warn(__dev, format, ...)				\
-	dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+	pr_warn("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,       \
 		 __func__, __LINE__, current->pid,			\
 		##__VA_ARGS__)
 
 #define mlx5_core_warn_once(__dev, format, ...)				\
-	dev_warn_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+	pr_warn_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,  \
 		      __func__, __LINE__, current->pid,			\
 		      ##__VA_ARGS__)
 
+#define mlx5_core_warn_rl(__dev, format, ...)				      \
+	pr_warn_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+			   __func__, __LINE__, current->pid,		      \
+			   ##__VA_ARGS__)
+
 #define mlx5_core_info(__dev, format, ...)				\
-	dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
+	pr_info("%s " format, (__dev)->priv.name, ##__VA_ARGS__)
+
+#define mlx5_core_info_rl(__dev, format, ...)				      \
+	pr_info_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
+			   __func__, __LINE__, current->pid,		      \
+			   ##__VA_ARGS__)
 
 enum {
 	MLX5_CMD_DATA, /* print command payload only */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 94464723ff77..0d006224d7b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -79,7 +79,7 @@ static u64 uar2pfn(struct mlx5_core_dev *mdev, u32 index)
 	else
 		system_page_index = index;
 
-	return (pci_resource_start(mdev->pdev, 0) >> PAGE_SHIFT) + system_page_index;
+	return (mdev->bar_addr >> PAGE_SHIFT) + system_page_index;
 }
 
 static void up_rel_func(struct kref *kref)
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 612c8c2f2466..769326ea1d9b 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -170,7 +170,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd,
 	doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci);
 	doorbell[1] = cpu_to_be32(cq->cqn);
 
-	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL);
+	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL);
 }
 
 static inline void mlx5_cq_hold(struct mlx5_core_cq *cq)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f93a5598b942..db7dca75d726 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -361,6 +361,7 @@ enum {
 
 enum {
 	MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1,
+	MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5,
 };
 
 enum {
diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h
index 0787de28f2fc..5c267707e1df 100644
--- a/include/linux/mlx5/doorbell.h
+++ b/include/linux/mlx5/doorbell.h
@@ -36,46 +36,25 @@
 #define MLX5_BF_OFFSET	      0x800
 #define MLX5_CQ_DOORBELL      0x20
 
-#if BITS_PER_LONG == 64
 /* Assume that we can just write a 64-bit doorbell atomically.  s390
  * actually doesn't have writeq() but S/390 systems don't even have
  * PCI so we won't worry about it.
+ *
+ * Note that the write is not atomic on 32-bit systems! In contrast to 64-bit
+ * ones, it requires proper locking. mlx5_write64 doesn't do any locking, so use
+ * it at your own discretion, protected by some kind of lock on 32 bits.
+ *
+ * TODO: use write{q,l}_relaxed()
  */
 
-#define MLX5_DECLARE_DOORBELL_LOCK(name)
-#define MLX5_INIT_DOORBELL_LOCK(ptr)    do { } while (0)
-#define MLX5_GET_DOORBELL_LOCK(ptr)      (NULL)
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
-				spinlock_t *doorbell_lock)
+static inline void mlx5_write64(__be32 val[2], void __iomem *dest)
 {
+#if BITS_PER_LONG == 64
 	__raw_writeq(*(u64 *)val, dest);
-}
-
 #else
-
-/* Just fall back to a spinlock to protect the doorbell if
- * BITS_PER_LONG is 32 -- there's no portable way to do atomic 64-bit
- * MMIO writes.
- */
-
-#define MLX5_DECLARE_DOORBELL_LOCK(name) spinlock_t name;
-#define MLX5_INIT_DOORBELL_LOCK(ptr)     spin_lock_init(ptr)
-#define MLX5_GET_DOORBELL_LOCK(ptr)      (ptr)
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
-				spinlock_t *doorbell_lock)
-{
-	unsigned long flags;
-
-	if (doorbell_lock)
-		spin_lock_irqsave(doorbell_lock, flags);
 	__raw_writel((__force u32) val[0], dest);
 	__raw_writel((__force u32) val[1], dest + 4);
-	if (doorbell_lock)
-		spin_unlock_irqrestore(doorbell_lock, flags);
+#endif
 }
 
-#endif
-
 #endif /* MLX5_DOORBELL_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 0d0729648844..d2d380d5e415 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -133,6 +133,7 @@ enum {
 	MLX5_REG_MTRC_CONF	 = 0x9041,
 	MLX5_REG_MTRC_STDB	 = 0x9042,
 	MLX5_REG_MTRC_CTRL	 = 0x9043,
+	MLX5_REG_MPEIN		 = 0x9050,
 	MLX5_REG_MPCNT		 = 0x9051,
 	MLX5_REG_MTPPS		 = 0x9053,
 	MLX5_REG_MTPPSE		 = 0x9054,
@@ -662,6 +663,7 @@ struct mlx5_core_dev {
 	u64			sys_image_guid;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
+	phys_addr_t             bar_addr;
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
@@ -887,6 +889,7 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
+void mlx5_health_flush(struct mlx5_core_dev *dev);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index b0e17c94566c..0e0e63d4d7aa 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -8027,6 +8027,52 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
+struct mlx5_ifc_mpein_reg_bits {
+	u8         reserved_at_0[0x2];
+	u8         depth[0x6];
+	u8         pcie_index[0x8];
+	u8         node[0x8];
+	u8         reserved_at_18[0x8];
+
+	u8         capability_mask[0x20];
+
+	u8         reserved_at_40[0x8];
+	u8         link_width_enabled[0x8];
+	u8         link_speed_enabled[0x10];
+
+	u8         lane0_physical_position[0x8];
+	u8         link_width_active[0x8];
+	u8         link_speed_active[0x10];
+
+	u8         num_of_pfs[0x10];
+	u8         num_of_vfs[0x10];
+
+	u8         bdf0[0x10];
+	u8         reserved_at_b0[0x10];
+
+	u8         max_read_request_size[0x4];
+	u8         max_payload_size[0x4];
+	u8         reserved_at_c8[0x5];
+	u8         pwr_status[0x3];
+	u8         port_type[0x4];
+	u8         reserved_at_d4[0xb];
+	u8         lane_reversal[0x1];
+
+	u8         reserved_at_e0[0x14];
+	u8         pci_power[0xc];
+
+	u8         reserved_at_100[0x20];
+
+	u8         device_status[0x10];
+	u8         port_state[0x8];
+	u8         reserved_at_138[0x8];
+
+	u8         reserved_at_140[0x10];
+	u8         receiver_detect_result[0x10];
+
+	u8         reserved_at_160[0x20];
+};
+
 struct mlx5_ifc_mpcnt_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         pcie_index[0x8];
@@ -8346,7 +8392,9 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x74];
+	u8         reserved_at_0[0x6e];
+	u8         pci_status_and_power[0x1];
+	u8         reserved_at_6f[0x5];
 	u8         mark_tx_action_cnp[0x1];
 	u8         mark_tx_action_cqe[0x1];
 	u8         dynamic_tx_overflow[0x1];
@@ -8954,6 +9002,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
 	struct mlx5_ifc_ppad_reg_bits ppad_reg;
 	struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+	struct mlx5_ifc_mpein_reg_bits mpein_reg;
 	struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
 	struct mlx5_ifc_pplm_reg_bits pplm_reg;
 	struct mlx5_ifc_pplr_reg_bits pplr_reg;