Merge tag 'mlx5-updates-2021-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
This series provides some cleanups to mlx5 driver
For more information please see tag log below.

Please pull and let me know if there is any problem.

mlx5-updates-2021-03-11

Cleanups for mlx5 driver

1) Fix build warnings form Arnd and Vlad
2) Leon improves locking for driver load/unload flows
3) From Roi, Lockdep false dependency warning
4) Other trivial cleanups
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

20 files changed, 169 insertions, 118 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index d7d8a68ef23d..6729720e1ab7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -148,7 +148,7 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
-		mlx5_unload_one(dev, false);
+		mlx5_unload_one(dev);
 		return 0;
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
 		if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET)
@@ -170,13 +170,13 @@ static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a
 	*actions_performed = BIT(action);
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
-		return mlx5_load_one(dev, false);
+		return mlx5_load_one(dev);
 	case DEVLINK_RELOAD_ACTION_FW_ACTIVATE:
 		if (limit == DEVLINK_RELOAD_LIMIT_NO_RESET)
 			break;
 		/* On fw_activate action, also driver is reloaded and reinit performed */
 		*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
-		return mlx5_load_one(dev, false);
+		return mlx5_load_one(dev);
 	default:
 		/* Unsupported action should not get to this function */
 		WARN_ON(1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 2eb022ad7fd0..01a1d02dcf15 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -1100,7 +1100,7 @@ int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer)
 	int err;
 
 	if (IS_ERR_OR_NULL(tracer))
-		return -EINVAL;
+		return 0;
 
 	dev = tracer->dev;
 	mlx5_fw_tracer_cleanup(tracer);
@@ -1126,8 +1126,7 @@ static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void
 
 	switch (eqe->sub_type) {
 	case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
-		if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state))
-			queue_work(tracer->work_queue, &tracer->ownership_change_work);
+		queue_work(tracer->work_queue, &tracer->ownership_change_work);
 		break;
 	case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE:
 		if (likely(tracer->str_db.loaded))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index 065126370acd..fcae3c0a4e9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -621,11 +621,7 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	int err;
 
 	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
-	if (reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
-		reg_c0 = 0;
-	reg_c1 = be32_to_cpu(cqe->ft_metadata);
-
-	if (!reg_c0)
+	if (!reg_c0 || reg_c0 == MLX5_FS_DEFAULT_FLOW_TAG)
 		return true;
 
 	/* If reg_c0 is not equal to the default flow tag then skb->mark
@@ -633,6 +629,8 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	 */
 	skb->mark = 0;
 
+	reg_c1 = be32_to_cpu(cqe->ft_metadata);
+
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index f3f6eb081948..3a6095c912f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -695,7 +695,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 
 	zone_rule->nat = nat;
 
-	spec = kzalloc(sizeof(*spec), GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
 		return -ENOMEM;
 
@@ -737,7 +737,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 
 	zone_rule->attr = attr;
 
-	kfree(spec);
+	kvfree(spec);
 	ct_dbg("Offloaded ct entry rule in zone %d", entry->tuple.zone);
 
 	return 0;
@@ -749,7 +749,7 @@ err_rule:
 err_mod_hdr:
 	kfree(attr);
 err_attr:
-	kfree(spec);
+	kvfree(spec);
 	return err;
 }
 
@@ -1539,6 +1539,14 @@ mlx5_tc_ct_free_pre_ct_tables(struct mlx5_ct_ft *ft)
 	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct);
 }
 
+/* To avoid false lock dependency warning set the ct_entries_ht lock
+ * class different than the lock class of the ht being used when deleting
+ * last flow from a group and then deleting a group, we get into del_sw_flow_group()
+ * which call rhashtable_destroy on fg->ftes_hash which will take ht->mutex but
+ * it's different than the ht->mutex here.
+ */
+static struct lock_class_key ct_entries_ht_lock_key;
+
 static struct mlx5_ct_ft *
 mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone,
 		     struct nf_flowtable *nf_ft)
@@ -1573,6 +1581,8 @@ mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone,
 	if (err)
 		goto err_init;
 
+	lockdep_set_class(&ft->ct_entries_ht.mutex, &ct_entries_ht_lock_key);
+
 	err = rhashtable_insert_fast(&ct_priv->zone_ht, &ft->node,
 				     zone_params);
 	if (err)
@@ -1674,10 +1684,10 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 	struct mlx5_ct_ft *ft;
 	u32 fte_id = 1;
 
-	post_ct_spec = kzalloc(sizeof(*post_ct_spec), GFP_KERNEL);
+	post_ct_spec = kvzalloc(sizeof(*post_ct_spec), GFP_KERNEL);
 	ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL);
 	if (!post_ct_spec || !ct_flow) {
-		kfree(post_ct_spec);
+		kvfree(post_ct_spec);
 		kfree(ct_flow);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1812,7 +1822,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
 
 	attr->ct_attr.ct_flow = ct_flow;
 	dealloc_mod_hdr_actions(&pre_mod_acts);
-	kfree(post_ct_spec);
+	kvfree(post_ct_spec);
 
 	return rule;
 
@@ -1833,7 +1843,7 @@ err_alloc_pre:
 err_idr:
 	mlx5_tc_ct_del_ft_cb(ct_priv, ft);
 err_ft:
-	kfree(post_ct_spec);
+	kvfree(post_ct_spec);
 	kfree(ct_flow);
 	netdev_warn(priv->netdev, "Failed to offload ct flow, err %d\n", err);
 	return ERR_PTR(err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index 67de2bf36861..89d5ca91566e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -76,10 +76,12 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
 static inline int
 mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				struct net_device *mirred_dev,
-				struct mlx5e_encap_entry *e) { return -EOPNOTSUPP; }
-int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
-				    struct net_device *mirred_dev,
-				    struct mlx5e_encap_entry *e)
+				struct mlx5e_encap_entry *e)
+{ return -EOPNOTSUPP; }
+static inline int
+mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv,
+				struct net_device *mirred_dev,
+				struct mlx5e_encap_entry *e)
 { return -EOPNOTSUPP; }
 #endif
 int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 6a116335bb21..32d06fe94acc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2021 Mellanox Technologies. */
 
 #include <net/fib_notifier.h>
+#include <net/nexthop.h>
 #include "tc_tun_encap.h"
 #include "en_tc.h"
 #include "tc_tun.h"
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 381a9c8c9da9..34119ce92031 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -60,7 +60,7 @@ static int rx_err_add_rule(struct mlx5e_priv *priv,
 	struct mlx5_flow_spec *spec;
 	int err = 0;
 
-	spec = kzalloc(sizeof(*spec), GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
 		return -ENOMEM;
 
@@ -101,7 +101,7 @@ out:
 	if (err)
 		mlx5_modify_header_dealloc(mdev, modify_hdr);
 out_spec:
-	kfree(spec);
+	kvfree(spec);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0da69b98f38f..dc126389291d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4646,10 +4646,6 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 
 	tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr,
 				 MLX5_FLOW_NAMESPACE_KERNEL);
-	if (IS_ERR(tc->ct)) {
-		err = PTR_ERR(tc->ct);
-		goto err_ct;
-	}
 
 	tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
 	err = register_netdevice_notifier_dev_net(priv->netdev,
@@ -4665,7 +4661,6 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 
 err_reg:
 	mlx5_tc_ct_clean(tc->ct);
-err_ct:
 	mlx5_chains_destroy(tc->chains);
 err_chains:
 	rhashtable_destroy(&tc->ht);
@@ -4724,8 +4719,6 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 					       esw_chains(esw),
 					       &esw->offloads.mod_hdr,
 					       MLX5_FLOW_NAMESPACE_FDB);
-	if (IS_ERR(uplink_priv->ct_priv))
-		goto err_ct;
 
 	mapping = mapping_create(sizeof(struct tunnel_match_key),
 				 TUNNEL_INFO_BITS_MASK, true);
@@ -4765,7 +4758,6 @@ err_enc_opts_mapping:
 	mapping_destroy(uplink_priv->tunnel_mapping);
 err_tun_mapping:
 	mlx5_tc_ct_clean(uplink_priv->ct_priv);
-err_ct:
 	netdev_warn(priv->netdev,
 		    "Failed to initialize tc (eswitch), err: %d", err);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index cb1e181f4c6a..7bfc84238b3d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -120,7 +120,7 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	return vport->dl_port;
+	return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port;
 }
 
 int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h
index cb9eafd1b4ee..21d56b49d14b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h
@@ -30,13 +30,13 @@ mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr);
 
 #else
 /* indir API stubs */
-struct mlx5_esw_indir_table *
+static inline struct mlx5_esw_indir_table *
 mlx5_esw_indir_table_init(void)
 {
 	return NULL;
 }
 
-void
+static inline void
 mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir)
 {
 }
@@ -57,7 +57,7 @@ mlx5_esw_indir_table_put(struct mlx5_eswitch *esw,
 {
 }
 
-bool
+static inline bool
 mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw,
 			    struct mlx5_flow_attr *attr,
 			    u16 vport_num,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index aba17835465b..fe1e06d95a12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1141,6 +1141,8 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
 
 	if (!vport->qos.enabled)
 		return -EOPNOTSUPP;
@@ -1279,6 +1281,8 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, u16 vport_num,
 	int ret;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
 
 	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
@@ -1326,6 +1330,8 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num)
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return;
 
 	mutex_lock(&esw->state_lock);
 	if (!vport->enabled)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 94cb0217b4f3..a215ccee3e61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1446,7 +1446,7 @@ esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag)
 	if (!mlx5_eswitch_reg_c1_loopback_supported(esw))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	spec = kzalloc(sizeof(*spec), GFP_KERNEL);
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
 		return ERR_PTR(-ENOMEM);
 
@@ -1469,7 +1469,7 @@ esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag)
 	dest.ft = esw->offloads.ft_offloads;
 
 	flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
-	kfree(spec);
+	kvfree(spec);
 
 	if (IS_ERR(flow_rule))
 		esw_warn(esw->dev,
@@ -2554,6 +2554,9 @@ static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
 	return esw_vport_create_offloads_acl_tables(esw, vport);
 }
 
@@ -2562,6 +2565,9 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 	struct mlx5_vport *vport;
 
 	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+	if (IS_ERR(vport))
+		return;
+
 	esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 66ad599bd488..f5517ea2f6be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2395,14 +2395,12 @@ static int init_root_tree(struct mlx5_flow_steering *steering,
 			  struct init_tree_node *init_node,
 			  struct fs_node *fs_parent_node)
 {
-	int i;
-	struct mlx5_flow_namespace *fs_ns;
 	int err;
+	int i;
 
-	fs_get_obj(fs_ns, fs_parent_node);
 	for (i = 0; i < init_node->ar_size; i++) {
 		err = init_root_tree_recursive(steering, &init_node->children[i],
-					       &fs_ns->node,
+					       fs_parent_node,
 					       init_node, i);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index f9042e147c7f..d5d57630015f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -104,7 +104,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		mlx5_load_one(dev, false);
+		mlx5_load_one(dev);
 		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
@@ -119,7 +119,7 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work)
 	int err;
 
 	mlx5_enter_error_state(dev, true);
-	mlx5_unload_one(dev, false);
+	mlx5_unload_one(dev);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
@@ -199,16 +199,11 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
 						      fw_live_patch_work);
 	struct mlx5_core_dev *dev = fw_reset->dev;
-	struct mlx5_fw_tracer *tracer;
 
 	mlx5_core_info(dev, "Live patch updated firmware version: %d.%d.%d\n", fw_rev_maj(dev),
 		       fw_rev_min(dev), fw_rev_sub(dev));
 
-	tracer = dev->tracer;
-	if (IS_ERR_OR_NULL(tracer))
-		return;
-
-	if (mlx5_fw_tracer_reload(tracer))
+	if (mlx5_fw_tracer_reload(dev->tracer))
 		mlx5_core_err(dev, "Failed to reload FW tracer\n");
 }
 
@@ -342,7 +337,7 @@ static void mlx5_sync_reset_now_event(struct work_struct *work)
 	}
 
 	mlx5_enter_error_state(dev, true);
-	mlx5_unload_one(dev, false);
+	mlx5_unload_one(dev);
 done:
 	fw_reset->ret = err;
 	mlx5_fw_reset_complete_reload(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 0c32c485eb58..a0a851640804 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -335,12 +335,12 @@ static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
 		return -EIO;
 	}
 	mlx5_core_err(dev, "starting health recovery flow\n");
-	mlx5_recover_device(dev);
-	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state) ||
-	    mlx5_health_check_fatal_sensors(dev)) {
+	if (mlx5_recover_device(dev) || mlx5_health_check_fatal_sensors(dev)) {
 		mlx5_core_err(dev, "health recovery failed\n");
 		return -EIO;
 	}
+
+	mlx5_core_info(dev, "health revovery succeded\n");
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c
index a68738c8f4bc..97324d9d4f2a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/gid.c
@@ -55,10 +55,6 @@ void mlx5_cleanup_reserved_gids(struct mlx5_core_dev *dev)
 
 int mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count)
 {
-	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		mlx5_core_err(dev, "Cannot reserve GIDs when interfaces are up\n");
-		return -EPERM;
-	}
 	if (dev->roce.reserved_gids.start < count) {
 		mlx5_core_warn(dev, "GID table exhausted attempting to reserve %d more GIDs\n",
 			       count);
@@ -79,7 +75,6 @@ int mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count)
 
 void mlx5_core_unreserve_gids(struct mlx5_core_dev *dev, unsigned int count)
 {
-	WARN(test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state), "Unreserving GIDs when interfaces are up");
 	WARN(count > dev->roce.reserved_gids.count, "Unreserving %u GIDs when only %u reserved",
 	     count, dev->roce.reserved_gids.count);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c568896cfb23..e3a417d17707 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1235,7 +1235,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_put_uars_page(dev, dev->priv.uar);
 }
 
-int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
+int mlx5_init_one(struct mlx5_core_dev *dev)
 {
 	int err = 0;
 
@@ -1247,16 +1247,14 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 	/* remove any previous indication of internal error */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
-	err = mlx5_function_setup(dev, boot);
+	err = mlx5_function_setup(dev, true);
 	if (err)
 		goto err_function;
 
-	if (boot) {
-		err = mlx5_init_once(dev);
-		if (err) {
-			mlx5_core_err(dev, "sw objs init failed\n");
-			goto function_teardown;
-		}
+	err = mlx5_init_once(dev);
+	if (err) {
+		mlx5_core_err(dev, "sw objs init failed\n");
+		goto function_teardown;
 	}
 
 	err = mlx5_load(dev);
@@ -1265,16 +1263,11 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 
 	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 
-	if (boot) {
-		err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
-		if (err)
-			goto err_devlink_reg;
-
-		err = mlx5_register_device(dev);
-	} else {
-		err = mlx5_attach_device(dev);
-	}
+	err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
+	if (err)
+		goto err_devlink_reg;
 
+	err = mlx5_register_device(dev);
 	if (err)
 		goto err_register;
 
@@ -1282,16 +1275,14 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 	return 0;
 
 err_register:
-	if (boot)
-		mlx5_devlink_unregister(priv_to_devlink(dev));
+	mlx5_devlink_unregister(priv_to_devlink(dev));
 err_devlink_reg:
 	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 	mlx5_unload(dev);
 err_load:
-	if (boot)
-		mlx5_cleanup_once(dev);
+	mlx5_cleanup_once(dev);
 function_teardown:
-	mlx5_function_teardown(dev, boot);
+	mlx5_function_teardown(dev, true);
 err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 out:
@@ -1299,33 +1290,84 @@ out:
 	return err;
 }
 
-void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
+void mlx5_uninit_one(struct mlx5_core_dev *dev)
 {
 	mutex_lock(&dev->intf_state_mutex);
 
-	if (cleanup) {
-		mlx5_unregister_device(dev);
-		mlx5_devlink_unregister(priv_to_devlink(dev));
-	} else {
-		mlx5_detach_device(dev);
-	}
+	mlx5_unregister_device(dev);
+	mlx5_devlink_unregister(priv_to_devlink(dev));
 
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
 			       __func__);
-		if (cleanup)
-			mlx5_cleanup_once(dev);
+		mlx5_cleanup_once(dev);
 		goto out;
 	}
 
 	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+	mlx5_unload(dev);
+	mlx5_cleanup_once(dev);
+	mlx5_function_teardown(dev, true);
+out:
+	mutex_unlock(&dev->intf_state_mutex);
+}
+
+int mlx5_load_one(struct mlx5_core_dev *dev)
+{
+	int err = 0;
+
+	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, false);
+	if (err)
+		goto err_function;
+
+	err = mlx5_load(dev);
+	if (err)
+		goto err_load;
+
+	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+
+	err = mlx5_attach_device(dev);
+	if (err)
+		goto err_attach;
+
+	mutex_unlock(&dev->intf_state_mutex);
+	return 0;
 
+err_attach:
+	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 	mlx5_unload(dev);
+err_load:
+	mlx5_function_teardown(dev, false);
+err_function:
+	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+out:
+	mutex_unlock(&dev->intf_state_mutex);
+	return err;
+}
 
-	if (cleanup)
-		mlx5_cleanup_once(dev);
+void mlx5_unload_one(struct mlx5_core_dev *dev)
+{
+	mutex_lock(&dev->intf_state_mutex);
 
-	mlx5_function_teardown(dev, cleanup);
+	mlx5_detach_device(dev);
+
+	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
+		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
+			       __func__);
+		goto out;
+	}
+
+	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+	mlx5_unload(dev);
+	mlx5_function_teardown(dev, false);
 out:
 	mutex_unlock(&dev->intf_state_mutex);
 }
@@ -1397,7 +1439,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mutex_destroy(&dev->intf_state_mutex);
 }
 
-static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct mlx5_core_dev *dev;
 	struct devlink *devlink;
@@ -1433,11 +1475,11 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto pci_init_err;
 	}
 
-	err = mlx5_load_one(dev, true);
+	err = mlx5_init_one(dev);
 	if (err) {
-		mlx5_core_err(dev, "mlx5_load_one failed with error code %d\n",
+		mlx5_core_err(dev, "mlx5_init_one failed with error code %d\n",
 			      err);
-		goto err_load_one;
+		goto err_init_one;
 	}
 
 	err = mlx5_crdump_enable(dev);
@@ -1449,7 +1491,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		devlink_reload_enable(devlink);
 	return 0;
 
-err_load_one:
+err_init_one:
 	mlx5_pci_close(dev);
 pci_init_err:
 	mlx5_mdev_uninit(dev);
@@ -1469,7 +1511,7 @@ static void remove_one(struct pci_dev *pdev)
 	devlink_reload_disable(devlink);
 	mlx5_crdump_disable(dev);
 	mlx5_drain_health_wq(dev);
-	mlx5_unload_one(dev, true);
+	mlx5_uninit_one(dev);
 	mlx5_pci_close(dev);
 	mlx5_mdev_uninit(dev);
 	mlx5_adev_idx_free(dev->priv.adev_idx);
@@ -1485,7 +1527,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 
 	mlx5_enter_error_state(dev, false);
 	mlx5_error_sw_reset(dev);
-	mlx5_unload_one(dev, false);
+	mlx5_unload_one(dev);
 	mlx5_drain_health_wq(dev);
 	mlx5_pci_disable_device(dev);
 
@@ -1555,7 +1597,7 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
 
 	mlx5_core_info(dev, "%s was called\n", __func__);
 
-	err = mlx5_load_one(dev, false);
+	err = mlx5_load_one(dev);
 	if (err)
 		mlx5_core_err(dev, "%s: mlx5_load_one failed with error code: %d\n",
 			      __func__, err);
@@ -1627,7 +1669,7 @@ static void shutdown(struct pci_dev *pdev)
 	mlx5_core_info(dev, "Shutdown was called\n");
 	err = mlx5_try_fast_unload(dev);
 	if (err)
-		mlx5_unload_one(dev, false);
+		mlx5_unload_one(dev);
 	mlx5_pci_disable_device(dev);
 }
 
@@ -1635,7 +1677,7 @@ static int mlx5_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 
-	mlx5_unload_one(dev, false);
+	mlx5_unload_one(dev);
 
 	return 0;
 }
@@ -1644,7 +1686,7 @@ static int mlx5_resume(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 
-	return mlx5_load_one(dev, false);
+	return mlx5_load_one(dev);
 }
 
 static const struct pci_device_id mlx5_core_pci_table[] = {
@@ -1676,20 +1718,23 @@ MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
 void mlx5_disable_device(struct mlx5_core_dev *dev)
 {
 	mlx5_error_sw_reset(dev);
-	mlx5_unload_one(dev, false);
+	mlx5_unload_one(dev);
 }
 
-void mlx5_recover_device(struct mlx5_core_dev *dev)
+int mlx5_recover_device(struct mlx5_core_dev *dev)
 {
+	int ret = -EIO;
+
 	mlx5_pci_disable_device(dev);
 	if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED)
-		mlx5_pci_resume(dev->pdev);
+		ret = mlx5_load_one(dev);
+	return ret;
 }
 
 static struct pci_driver mlx5_core_driver = {
 	.name           = KBUILD_MODNAME,
 	.id_table       = mlx5_core_pci_table,
-	.probe          = init_one,
+	.probe          = probe_one,
 	.remove         = remove_one,
 	.suspend        = mlx5_suspend,
 	.resume         = mlx5_resume,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index efe403c7e354..37c8ec7d2217 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -134,7 +134,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev);
 u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev);
 int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
-void mlx5_recover_device(struct mlx5_core_dev *dev);
+int mlx5_recover_device(struct mlx5_core_dev *dev);
 int mlx5_sriov_init(struct mlx5_core_dev *dev);
 void mlx5_sriov_cleanup(struct mlx5_core_dev *dev);
 int mlx5_sriov_attach(struct mlx5_core_dev *dev);
@@ -267,8 +267,10 @@ static inline bool mlx5_core_is_sf(const struct mlx5_core_dev *dev)
 
 int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx);
 void mlx5_mdev_uninit(struct mlx5_core_dev *dev);
-void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup);
-int mlx5_load_one(struct mlx5_core_dev *dev, bool boot);
+int mlx5_init_one(struct mlx5_core_dev *dev);
+void mlx5_uninit_one(struct mlx5_core_dev *dev);
+void mlx5_unload_one(struct mlx5_core_dev *dev);
+int mlx5_load_one(struct mlx5_core_dev *dev);
 
 int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
index 4de02902aef1..149fd9e698cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -47,7 +47,7 @@ static inline void mlx5_sf_driver_unregister(void)
 
 static inline bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev)
 {
-	return 0;
+	return false;
 }
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index c4bf555c25ea..42c8ee03fe3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -41,14 +41,15 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia
 		goto remap_err;
 	}
 
-	err = mlx5_load_one(mdev, true);
+	err = mlx5_init_one(mdev);
 	if (err) {
-		mlx5_core_warn(mdev, "mlx5_load_one err=%d\n", err);
-		goto load_one_err;
+		mlx5_core_warn(mdev, "mlx5_init_one err=%d\n", err);
+		goto init_one_err;
 	}
+	devlink_reload_enable(devlink);
 	return 0;
 
-load_one_err:
+init_one_err:
 	iounmap(mdev->iseg);
 remap_err:
 	mlx5_mdev_uninit(mdev);
@@ -63,7 +64,8 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev)
 	struct devlink *devlink;
 
 	devlink = priv_to_devlink(sf_dev->mdev);
-	mlx5_unload_one(sf_dev->mdev, true);
+	devlink_reload_disable(devlink);
+	mlx5_uninit_one(sf_dev->mdev);
 	iounmap(sf_dev->mdev->iseg);
 	mlx5_mdev_uninit(sf_dev->mdev);
 	mlx5_devlink_free(devlink);
@@ -73,7 +75,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
 {
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
 
-	mlx5_unload_one(sf_dev->mdev, false);
+	mlx5_unload_one(sf_dev->mdev);
 }
 
 static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = {