Merge branch 'net-mlx5-move-notifiers-outside-the-devlink-lock'

Tariq Toukan says:

====================
net/mlx5: Move notifiers outside the devlink lock

This series by Cosmin moves blocking notifier registration in the mlx5
driver outside the devlink lock during probe.

This is mostly a no-op refactoring that consists of multiple pieces.
It is necessary because upcoming code will introduce a potential locking
cycle between the devlink lock and the blocking notifier head mutexes,
so these notifiers must move out of the devlink-locked critical section.
====================

Link: https://patch.msgid.link/1763325940-1231508-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 253 insertions, 151 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 25af8bd7f077..3adf2b1cd26a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1474,7 +1474,7 @@ static void mlx5_esw_mode_change_notify(struct mlx5_eswitch *esw, u16 mode)
 
 	info.new_mode = mode;
 
-	blocking_notifier_call_chain(&esw->n_head, 0, &info);
+	blocking_notifier_call_chain(&esw->dev->priv.esw_n_head, 0, &info);
 }
 
 static int mlx5_esw_egress_acls_init(struct mlx5_core_dev *dev)
@@ -2050,7 +2050,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
 	else
 		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
-	BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
 
 	esw_info(dev,
 		 "Total vports %d, per vport: max uc(%d) max mc(%d)\n",
@@ -2379,14 +2378,16 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 		dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
 }
 
-int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *nb)
+int mlx5_esw_event_notifier_register(struct mlx5_core_dev *dev,
+				     struct notifier_block *nb)
 {
-	return blocking_notifier_chain_register(&esw->n_head, nb);
+	return blocking_notifier_chain_register(&dev->priv.esw_n_head, nb);
 }
 
-void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *nb)
+void mlx5_esw_event_notifier_unregister(struct mlx5_core_dev *dev,
+					struct notifier_block *nb)
 {
-	blocking_notifier_chain_unregister(&esw->n_head, nb);
+	blocking_notifier_chain_unregister(&dev->priv.esw_n_head, nb);
 }
 
 /**
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index beaec450a734..ad1073f7b79f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -403,7 +403,6 @@ struct mlx5_eswitch {
 	struct {
 		u32             large_group_num;
 	}  params;
-	struct blocking_notifier_head n_head;
 	struct xarray paired;
 	struct mlx5_devcom_comp_dev *devcom;
 	u16 enabled_ipsec_vf_count;
@@ -864,8 +863,10 @@ struct mlx5_esw_event_info {
 	u16 new_mode;
 };
 
-int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *n);
-void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *n);
+int mlx5_esw_event_notifier_register(struct mlx5_core_dev *dev,
+				     struct notifier_block *n);
+void mlx5_esw_event_notifier_unregister(struct mlx5_core_dev *dev,
+					struct notifier_block *n);
 
 bool mlx5_esw_hold(struct mlx5_core_dev *dev);
 void mlx5_esw_release(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c904696cbc3a..024339ce41f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1010,16 +1010,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_irq_cleanup;
 	}
 
-	err = mlx5_events_init(dev);
-	if (err) {
-		mlx5_core_err(dev, "failed to initialize events\n");
-		goto err_eq_cleanup;
-	}
-
 	err = mlx5_fw_reset_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to initialize fw reset events\n");
-		goto err_events_cleanup;
+		goto err_eq_cleanup;
 	}
 
 	mlx5_cq_debugfs_init(dev);
@@ -1121,8 +1115,6 @@ err_tables_cleanup:
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
-err_events_cleanup:
-	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
 err_irq_cleanup:
@@ -1155,7 +1147,6 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
-	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);
 	mlx5_devcom_unregister_device(dev->priv.devc);
@@ -1386,12 +1377,6 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 
 	mlx5_vhca_event_start(dev);
 
-	err = mlx5_sf_hw_table_create(dev);
-	if (err) {
-		mlx5_core_err(dev, "sf table create failed %d\n", err);
-		goto err_vhca;
-	}
-
 	err = mlx5_ec_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init embedded CPU\n");
@@ -1420,8 +1405,6 @@ err_sriov:
 	mlx5_lag_remove_mdev(dev);
 	mlx5_ec_cleanup(dev);
 err_ec:
-	mlx5_sf_hw_table_destroy(dev);
-err_vhca:
 	mlx5_vhca_event_stop(dev);
 err_set_hca:
 	mlx5_fs_core_cleanup(dev);
@@ -1447,12 +1430,12 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 {
 	mlx5_eswitch_disable(dev->priv.eswitch);
 	mlx5_devlink_traps_unregister(priv_to_devlink(dev));
+	mlx5_vhca_event_stop(dev);
 	mlx5_sf_dev_table_destroy(dev);
 	mlx5_sriov_detach(dev);
 	mlx5_lag_remove_mdev(dev);
 	mlx5_ec_cleanup(dev);
 	mlx5_sf_hw_table_destroy(dev);
-	mlx5_vhca_event_stop(dev);
 	mlx5_fs_core_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
@@ -1833,6 +1816,50 @@ static int vhca_id_show(struct seq_file *file, void *priv)
 
 DEFINE_SHOW_ATTRIBUTE(vhca_id);
 
+static int mlx5_notifiers_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_events_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize events\n");
+		return err;
+	}
+
+	BLOCKING_INIT_NOTIFIER_HEAD(&dev->priv.esw_n_head);
+	mlx5_vhca_state_notifier_init(dev);
+
+	err = mlx5_sf_hw_notifier_init(dev);
+	if (err)
+		goto err_sf_hw_notifier;
+
+	err = mlx5_sf_notifiers_init(dev);
+	if (err)
+		goto err_sf_notifiers;
+
+	err = mlx5_sf_dev_notifier_init(dev);
+	if (err)
+		goto err_sf_dev_notifier;
+
+	return 0;
+
+err_sf_dev_notifier:
+	mlx5_sf_notifiers_cleanup(dev);
+err_sf_notifiers:
+	mlx5_sf_hw_notifier_cleanup(dev);
+err_sf_hw_notifier:
+	mlx5_events_cleanup(dev);
+	return err;
+}
+
+static void mlx5_notifiers_cleanup(struct mlx5_core_dev *dev)
+{
+	mlx5_sf_dev_notifier_cleanup(dev);
+	mlx5_sf_notifiers_cleanup(dev);
+	mlx5_sf_hw_notifier_cleanup(dev);
+	mlx5_events_cleanup(dev);
+}
+
 int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -1888,6 +1915,10 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	if (err)
 		goto err_hca_caps;
 
+	err = mlx5_notifiers_init(dev);
+	if (err)
+		goto err_hca_caps;
+
 	/* The conjunction of sw_vhca_id with sw_owner_id will be a global
 	 * unique id per function which uses mlx5_core.
 	 * Those values are supplied to FW as part of the init HCA command to
@@ -1930,6 +1961,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	if (priv->sw_vhca_id > 0)
 		ida_free(&sw_vhca_ida, dev->priv.sw_vhca_id);
 
+	mlx5_notifiers_cleanup(dev);
 	mlx5_hca_caps_free(dev);
 	mlx5_adev_cleanup(dev);
 	mlx5_pagealloc_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 99219ea52c4b..f310bde3d11f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -16,7 +16,6 @@ struct mlx5_sf_dev_table {
 	struct xarray devices;
 	phys_addr_t base_address;
 	u64 sf_bar_length;
-	struct notifier_block nb;
 	struct workqueue_struct *active_wq;
 	struct work_struct work;
 	u8 stop_active_wq:1;
@@ -156,18 +155,23 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de
 static int
 mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_code, void *data)
 {
-	struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_dev_nb);
+	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
 	const struct mlx5_vhca_state_event *event = data;
 	struct mlx5_sf_dev *sf_dev;
 	u16 max_functions;
 	u16 sf_index;
 	u16 base_id;
 
-	max_functions = mlx5_sf_max_functions(table->dev);
+	if (!table)
+		return 0;
+
+	max_functions = mlx5_sf_max_functions(dev);
 	if (!max_functions)
 		return 0;
 
-	base_id = mlx5_sf_start_function_id(table->dev);
+	base_id = mlx5_sf_start_function_id(dev);
 	if (event->function_id < base_id || event->function_id >= (base_id + max_functions))
 		return 0;
 
@@ -177,19 +181,19 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 	case MLX5_VHCA_STATE_INVALID:
 	case MLX5_VHCA_STATE_ALLOCATED:
 		if (sf_dev)
-			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+			mlx5_sf_dev_del(dev, sf_dev, sf_index);
 		break;
 	case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
 		if (sf_dev)
-			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+			mlx5_sf_dev_del(dev, sf_dev, sf_index);
 		else
-			mlx5_core_err(table->dev,
+			mlx5_core_err(dev,
 				      "SF DEV: teardown state for invalid dev index=%d sfnum=0x%x\n",
 				      sf_index, event->sw_function_id);
 		break;
 	case MLX5_VHCA_STATE_ACTIVE:
 		if (!sf_dev)
-			mlx5_sf_dev_add(table->dev, sf_index, event->function_id,
+			mlx5_sf_dev_add(dev, sf_index, event->function_id,
 					event->sw_function_id);
 		break;
 	default:
@@ -315,6 +319,15 @@ static void mlx5_sf_dev_destroy_active_works(struct mlx5_sf_dev_table *table)
 	}
 }
 
+int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
+	dev->priv.sf_dev_nb.notifier_call = mlx5_sf_dev_state_change_handler;
+	return mlx5_vhca_event_notifier_register(dev, &dev->priv.sf_dev_nb);
+}
+
 void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_dev_table *table;
@@ -329,17 +342,12 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 		goto table_err;
 	}
 
-	table->nb.notifier_call = mlx5_sf_dev_state_change_handler;
 	table->dev = dev;
 	table->sf_bar_length = 1 << (MLX5_CAP_GEN(dev, log_min_sf_size) + 12);
 	table->base_address = pci_resource_start(dev->pdev, 2);
 	xa_init(&table->devices);
 	dev->priv.sf_dev_table = table;
 
-	err = mlx5_vhca_event_notifier_register(dev, &table->nb);
-	if (err)
-		goto vhca_err;
-
 	err = mlx5_sf_dev_create_active_works(table);
 	if (err)
 		goto add_active_err;
@@ -351,10 +359,8 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 
 arm_err:
 	mlx5_sf_dev_destroy_active_works(table);
-add_active_err:
-	mlx5_vhca_event_notifier_unregister(dev, &table->nb);
 	mlx5_vhca_event_work_queues_flush(dev);
-vhca_err:
+add_active_err:
 	kfree(table);
 	dev->priv.sf_dev_table = NULL;
 table_err:
@@ -372,6 +378,14 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table)
 	}
 }
 
+void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_dev_nb);
+}
+
 void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
@@ -380,8 +394,6 @@ void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 		return;
 
 	mlx5_sf_dev_destroy_active_works(table);
-	mlx5_vhca_event_notifier_unregister(dev, &table->nb);
-	mlx5_vhca_event_work_queues_flush(dev);
 
 	/* Now that event handler is not running, it is safe to destroy
 	 * the sf device without race.
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 b99131e95e37..3ab0449c770c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -25,7 +25,9 @@ struct mlx5_sf_peer_devlink_event_ctx {
 	int err;
 };
 
+int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev);
 void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev);
+void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_sf_driver_register(void);
@@ -35,10 +37,19 @@ bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev);
 
 #else
 
+static inline int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
 static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
 {
 }
 
+static inline void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
 static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 {
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 3304f25cc805..b82323b8449e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -31,9 +31,6 @@ struct mlx5_sf_table {
 	struct mlx5_core_dev *dev; /* To refer from notifier context. */
 	struct xarray function_ids; /* function id based lookup. */
 	struct mutex sf_state_lock; /* Serializes sf state among user cmds & vhca event handler. */
-	struct notifier_block esw_nb;
-	struct notifier_block vhca_nb;
-	struct notifier_block mdev_nb;
 };
 
 static struct mlx5_sf *
@@ -391,11 +388,16 @@ static bool mlx5_sf_state_update_check(const struct mlx5_sf *sf, u8 new_state)
 
 static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
 {
-	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, vhca_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_table_vhca_nb);
+	struct mlx5_sf_table *table = dev->priv.sf_table;
 	const struct mlx5_vhca_state_event *event = data;
 	bool update = false;
 	struct mlx5_sf *sf;
 
+	if (!table)
+		return 0;
+
 	mutex_lock(&table->sf_state_lock);
 	sf = mlx5_sf_lookup_by_function_id(table, event->function_id);
 	if (!sf)
@@ -407,7 +409,7 @@ static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, v
 	update = mlx5_sf_state_update_check(sf, event->new_vhca_state);
 	if (update)
 		sf->hw_state = event->new_vhca_state;
-	trace_mlx5_sf_update_state(table->dev, sf->port_index, sf->controller,
+	trace_mlx5_sf_update_state(dev, sf->port_index, sf->controller,
 				   sf->hw_fn_id, sf->hw_state);
 unlock:
 	mutex_unlock(&table->sf_state_lock);
@@ -425,12 +427,16 @@ static void mlx5_sf_del_all(struct mlx5_sf_table *table)
 
 static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, void *data)
 {
-	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, esw_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_table_esw_nb);
 	const struct mlx5_esw_event_info *mode = data;
 
+	if (!dev->priv.sf_table)
+		return 0;
+
 	switch (mode->new_mode) {
 	case MLX5_ESWITCH_LEGACY:
-		mlx5_sf_del_all(table);
+		mlx5_sf_del_all(dev->priv.sf_table);
 		break;
 	default:
 		break;
@@ -441,15 +447,16 @@ static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, voi
 
 static int mlx5_sf_mdev_event(struct notifier_block *nb, unsigned long event, void *data)
 {
-	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, mdev_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_table_mdev_nb);
 	struct mlx5_sf_peer_devlink_event_ctx *event_ctx = data;
+	struct mlx5_sf_table *table = dev->priv.sf_table;
 	int ret = NOTIFY_DONE;
 	struct mlx5_sf *sf;
 
-	if (event != MLX5_DRIVER_EVENT_SF_PEER_DEVLINK)
+	if (!table || event != MLX5_DRIVER_EVENT_SF_PEER_DEVLINK)
 		return NOTIFY_DONE;
 
-
 	mutex_lock(&table->sf_state_lock);
 	sf = mlx5_sf_lookup_by_function_id(table, event_ctx->fn_id);
 	if (!sf)
@@ -464,10 +471,40 @@ out:
 	return ret;
 }
 
+int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
+	dev->priv.sf_table_esw_nb.notifier_call = mlx5_sf_esw_event;
+	err = mlx5_esw_event_notifier_register(dev, &dev->priv.sf_table_esw_nb);
+	if (err)
+		return err;
+
+	dev->priv.sf_table_vhca_nb.notifier_call = mlx5_sf_vhca_event;
+	err = mlx5_vhca_event_notifier_register(dev,
+						&dev->priv.sf_table_vhca_nb);
+	if (err)
+		goto vhca_err;
+
+	dev->priv.sf_table_mdev_nb.notifier_call = mlx5_sf_mdev_event;
+	err = mlx5_blocking_notifier_register(dev, &dev->priv.sf_table_mdev_nb);
+	if (err)
+		goto mdev_err;
+
+	return 0;
+mdev_err:
+	mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_table_vhca_nb);
+vhca_err:
+	mlx5_esw_event_notifier_unregister(dev, &dev->priv.sf_table_esw_nb);
+	return err;
+}
+
 int mlx5_sf_table_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_table *table;
-	int err;
 
 	if (!mlx5_sf_table_supported(dev) || !mlx5_vhca_event_supported(dev))
 		return 0;
@@ -480,28 +517,18 @@ int mlx5_sf_table_init(struct mlx5_core_dev *dev)
 	table->dev = dev;
 	xa_init(&table->function_ids);
 	dev->priv.sf_table = table;
-	table->esw_nb.notifier_call = mlx5_sf_esw_event;
-	err = mlx5_esw_event_notifier_register(dev->priv.eswitch, &table->esw_nb);
-	if (err)
-		goto reg_err;
-
-	table->vhca_nb.notifier_call = mlx5_sf_vhca_event;
-	err = mlx5_vhca_event_notifier_register(table->dev, &table->vhca_nb);
-	if (err)
-		goto vhca_err;
-
-	table->mdev_nb.notifier_call = mlx5_sf_mdev_event;
-	mlx5_blocking_notifier_register(dev, &table->mdev_nb);
 
 	return 0;
+}
 
-vhca_err:
-	mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
-reg_err:
-	mutex_destroy(&table->sf_state_lock);
-	kfree(table);
-	dev->priv.sf_table = NULL;
-	return err;
+void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	mlx5_blocking_notifier_unregister(dev, &dev->priv.sf_table_mdev_nb);
+	mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_table_vhca_nb);
+	mlx5_esw_event_notifier_unregister(dev, &dev->priv.sf_table_esw_nb);
 }
 
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
@@ -511,9 +538,6 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 	if (!table)
 		return;
 
-	mlx5_blocking_notifier_unregister(dev, &table->mdev_nb);
-	mlx5_vhca_event_notifier_unregister(table->dev, &table->vhca_nb);
-	mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
 	mutex_destroy(&table->sf_state_lock);
 	WARN_ON(!xa_empty(&table->function_ids));
 	kfree(table);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index 1f613320fe07..bd968f3b3855 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -30,9 +30,7 @@ enum mlx5_sf_hwc_index {
 };
 
 struct mlx5_sf_hw_table {
-	struct mlx5_core_dev *dev;
 	struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */
-	struct notifier_block vhca_nb;
 	struct mlx5_sf_hwc_table hwc[MLX5_SF_HWC_MAX];
 };
 
@@ -71,14 +69,16 @@ mlx5_sf_table_fn_to_hwc(struct mlx5_sf_hw_table *table, u16 fn_id)
 	return NULL;
 }
 
-static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 controller,
+static int mlx5_sf_hw_table_id_alloc(struct mlx5_core_dev *dev,
+				     struct mlx5_sf_hw_table *table,
+				     u32 controller,
 				     u32 usr_sfnum)
 {
 	struct mlx5_sf_hwc_table *hwc;
 	int free_idx = -1;
 	int i;
 
-	hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+	hwc = mlx5_sf_controller_to_hwc(dev, controller);
 	if (!hwc->sfs)
 		return -ENOSPC;
 
@@ -100,11 +100,13 @@ static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 control
 	return free_idx;
 }
 
-static void mlx5_sf_hw_table_id_free(struct mlx5_sf_hw_table *table, u32 controller, int id)
+static void mlx5_sf_hw_table_id_free(struct mlx5_core_dev *dev,
+				     struct mlx5_sf_hw_table *table,
+				     u32 controller, int id)
 {
 	struct mlx5_sf_hwc_table *hwc;
 
-	hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+	hwc = mlx5_sf_controller_to_hwc(dev, controller);
 	hwc->sfs[id].allocated = false;
 	hwc->sfs[id].pending_delete = false;
 }
@@ -120,7 +122,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr
 		return -EOPNOTSUPP;
 
 	mutex_lock(&table->table_lock);
-	sw_id = mlx5_sf_hw_table_id_alloc(table, controller, usr_sfnum);
+	sw_id = mlx5_sf_hw_table_id_alloc(dev, table, controller, usr_sfnum);
 	if (sw_id < 0) {
 		err = sw_id;
 		goto exist_err;
@@ -151,7 +153,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr
 vhca_err:
 	mlx5_cmd_dealloc_sf(dev, hw_fn_id);
 err:
-	mlx5_sf_hw_table_id_free(table, controller, sw_id);
+	mlx5_sf_hw_table_id_free(dev, table, controller, sw_id);
 exist_err:
 	mutex_unlock(&table->table_lock);
 	return err;
@@ -165,7 +167,7 @@ void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
 	mutex_lock(&table->table_lock);
 	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id);
 	mlx5_cmd_dealloc_sf(dev, hw_fn_id);
-	mlx5_sf_hw_table_id_free(table, controller, id);
+	mlx5_sf_hw_table_id_free(dev, table, controller, id);
 	mutex_unlock(&table->table_lock);
 }
 
@@ -216,10 +218,12 @@ static void mlx5_sf_hw_table_hwc_dealloc_all(struct mlx5_core_dev *dev,
 	}
 }
 
-static void mlx5_sf_hw_table_dealloc_all(struct mlx5_sf_hw_table *table)
+static void mlx5_sf_hw_table_dealloc_all(struct mlx5_core_dev *dev,
+					 struct mlx5_sf_hw_table *table)
 {
-	mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_EXTERNAL]);
-	mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_LOCAL]);
+	mlx5_sf_hw_table_hwc_dealloc_all(dev,
+					 &table->hwc[MLX5_SF_HWC_EXTERNAL]);
+	mlx5_sf_hw_table_hwc_dealloc_all(dev, &table->hwc[MLX5_SF_HWC_LOCAL]);
 }
 
 static int mlx5_sf_hw_table_hwc_init(struct mlx5_sf_hwc_table *hwc, u16 max_fn, u16 base_id)
@@ -301,7 +305,6 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 	}
 
 	mutex_init(&table->table_lock);
-	table->dev = dev;
 	dev->priv.sf_hw_table = table;
 
 	base_id = mlx5_sf_start_function_id(dev);
@@ -338,19 +341,22 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
 	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
 	mutex_destroy(&table->table_lock);
 	kfree(table);
+	dev->priv.sf_hw_table = NULL;
 res_unregister:
 	mlx5_sf_hw_table_res_unregister(dev);
 }
 
 static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data)
 {
-	struct mlx5_sf_hw_table *table = container_of(nb, struct mlx5_sf_hw_table, vhca_nb);
+	struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev,
+						 priv.sf_hw_table_vhca_nb);
+	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
 	const struct mlx5_vhca_state_event *event = data;
 	struct mlx5_sf_hwc_table *hwc;
 	struct mlx5_sf_hw *sf_hw;
 	u16 sw_id;
 
-	if (event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED)
+	if (!table || event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED)
 		return 0;
 
 	hwc = mlx5_sf_table_fn_to_hwc(table, event->function_id);
@@ -365,20 +371,28 @@ static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode
 	 * Hence recycle the sf hardware id for reuse.
 	 */
 	if (sf_hw->allocated && sf_hw->pending_delete)
-		mlx5_sf_hw_table_hwc_sf_free(table->dev, hwc, sw_id);
+		mlx5_sf_hw_table_hwc_sf_free(dev, hwc, sw_id);
 	mutex_unlock(&table->table_lock);
 	return 0;
 }
 
-int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev)
+int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev)
 {
-	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
-
-	if (!table)
+	if (mlx5_core_is_sf(dev))
 		return 0;
 
-	table->vhca_nb.notifier_call = mlx5_sf_hw_vhca_event;
-	return mlx5_vhca_event_notifier_register(dev, &table->vhca_nb);
+	dev->priv.sf_hw_table_vhca_nb.notifier_call = mlx5_sf_hw_vhca_event;
+	return mlx5_vhca_event_notifier_register(dev,
+						 &dev->priv.sf_hw_table_vhca_nb);
+}
+
+void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+	if (mlx5_core_is_sf(dev))
+		return;
+
+	mlx5_vhca_event_notifier_unregister(dev,
+					    &dev->priv.sf_hw_table_vhca_nb);
 }
 
 void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
@@ -388,9 +402,8 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
 	if (!table)
 		return;
 
-	mlx5_vhca_event_notifier_unregister(dev, &table->vhca_nb);
 	/* Dealloc SFs whose firmware event has been missed. */
-	mlx5_sf_hw_table_dealloc_all(table);
+	mlx5_sf_hw_table_dealloc_all(dev, table);
 }
 
 bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 89559a37997a..d8a934a0e968 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -12,10 +12,13 @@
 int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev);
 void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev);
 
-int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev);
+int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev);
+void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
 
+int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev);
 int mlx5_sf_table_init(struct mlx5_core_dev *dev);
+void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
 bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev);
 
@@ -44,20 +47,33 @@ static inline void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
 
-static inline int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev)
+static inline int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev)
 {
 	return 0;
 }
 
+static inline void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
 static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
 {
 }
 
+static inline int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
 static inline int mlx5_sf_table_init(struct mlx5_core_dev *dev)
 {
 	return 0;
 }
 
+static inline void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
 static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
index cda01ba441ae..b04cf6cf8956 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -9,15 +9,9 @@
 #define CREATE_TRACE_POINTS
 #include "diag/vhca_tracepoint.h"
 
-struct mlx5_vhca_state_notifier {
-	struct mlx5_core_dev *dev;
-	struct mlx5_nb nb;
-	struct blocking_notifier_head n_head;
-};
-
 struct mlx5_vhca_event_work {
 	struct work_struct work;
-	struct mlx5_vhca_state_notifier *notifier;
+	struct mlx5_core_dev *dev;
 	struct mlx5_vhca_state_event event;
 };
 
@@ -95,16 +89,14 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *
 	mlx5_vhca_event_arm(dev, event->function_id);
 	trace_mlx5_sf_vhca_event(dev, event);
 
-	blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
+	blocking_notifier_call_chain(&dev->priv.vhca_state_n_head, 0, event);
 }
 
 static void mlx5_vhca_state_work_handler(struct work_struct *_work)
 {
 	struct mlx5_vhca_event_work *work = container_of(_work, struct mlx5_vhca_event_work, work);
-	struct mlx5_vhca_state_notifier *notifier = work->notifier;
-	struct mlx5_core_dev *dev = notifier->dev;
 
-	mlx5_vhca_event_notify(dev, &work->event);
+	mlx5_vhca_event_notify(work->dev, &work->event);
 	kfree(work);
 }
 
@@ -116,8 +108,8 @@ void mlx5_vhca_events_work_enqueue(struct mlx5_core_dev *dev, int idx, struct wo
 static int
 mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, void *data)
 {
-	struct mlx5_vhca_state_notifier *notifier =
-				mlx5_nb_cof(nb, struct mlx5_vhca_state_notifier, nb);
+	struct mlx5_core_dev *dev = mlx5_nb_cof(nb, struct mlx5_core_dev,
+						priv.vhca_state_nb);
 	struct mlx5_vhca_event_work *work;
 	struct mlx5_eqe *eqe = data;
 	int wq_idx;
@@ -126,10 +118,10 @@ mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, v
 	if (!work)
 		return NOTIFY_DONE;
 	INIT_WORK(&work->work, &mlx5_vhca_state_work_handler);
-	work->notifier = notifier;
+	work->dev = dev;
 	work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id);
 	wq_idx = work->event.function_id % MLX5_DEV_MAX_WQS;
-	mlx5_vhca_events_work_enqueue(notifier->dev, wq_idx, &work->work);
+	mlx5_vhca_events_work_enqueue(dev, wq_idx, &work->work);
 	return NOTIFY_OK;
 }
 
@@ -145,9 +137,15 @@ void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
 	MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_teardown_request, 1);
 }
 
+void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev)
+{
+	BLOCKING_INIT_NOTIFIER_HEAD(&dev->priv.vhca_state_n_head);
+	MLX5_NB_INIT(&dev->priv.vhca_state_nb, mlx5_vhca_state_change_notifier,
+		     VHCA_STATE_CHANGE);
+}
+
 int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 {
-	struct mlx5_vhca_state_notifier *notifier;
 	char wq_name[MLX5_CMD_WQ_MAX_NAME];
 	struct mlx5_vhca_events *events;
 	int err, i;
@@ -160,7 +158,6 @@ int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	events->dev = dev;
-	dev->priv.vhca_events = events;
 	for (i = 0; i < MLX5_DEV_MAX_WQS; i++) {
 		snprintf(wq_name, MLX5_CMD_WQ_MAX_NAME, "mlx5_vhca_event%d", i);
 		events->handler[i].wq = create_singlethread_workqueue(wq_name);
@@ -169,20 +166,10 @@ int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 			goto err_create_wq;
 		}
 	}
+	dev->priv.vhca_events = events;
 
-	notifier = kzalloc(sizeof(*notifier), GFP_KERNEL);
-	if (!notifier) {
-		err = -ENOMEM;
-		goto err_notifier;
-	}
-
-	dev->priv.vhca_state_notifier = notifier;
-	notifier->dev = dev;
-	BLOCKING_INIT_NOTIFIER_HEAD(&notifier->n_head);
-	MLX5_NB_INIT(&notifier->nb, mlx5_vhca_state_change_notifier, VHCA_STATE_CHANGE);
 	return 0;
 
-err_notifier:
 err_create_wq:
 	for (--i; i >= 0; i--)
 		destroy_workqueue(events->handler[i].wq);
@@ -211,8 +198,6 @@ void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_vhca_event_supported(dev))
 		return;
 
-	kfree(dev->priv.vhca_state_notifier);
-	dev->priv.vhca_state_notifier = NULL;
 	vhca_events = dev->priv.vhca_events;
 	for (i = 0; i < MLX5_DEV_MAX_WQS; i++)
 		destroy_workqueue(vhca_events->handler[i].wq);
@@ -221,34 +206,30 @@ void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
 
 void mlx5_vhca_event_start(struct mlx5_core_dev *dev)
 {
-	struct mlx5_vhca_state_notifier *notifier;
-
-	if (!dev->priv.vhca_state_notifier)
+	if (!mlx5_vhca_event_supported(dev))
 		return;
 
-	notifier = dev->priv.vhca_state_notifier;
-	mlx5_eq_notifier_register(dev, &notifier->nb);
+	mlx5_eq_notifier_register(dev, &dev->priv.vhca_state_nb);
 }
 
 void mlx5_vhca_event_stop(struct mlx5_core_dev *dev)
 {
-	struct mlx5_vhca_state_notifier *notifier;
-
-	if (!dev->priv.vhca_state_notifier)
+	if (!mlx5_vhca_event_supported(dev))
 		return;
 
-	notifier = dev->priv.vhca_state_notifier;
-	mlx5_eq_notifier_unregister(dev, &notifier->nb);
+	mlx5_eq_notifier_unregister(dev, &dev->priv.vhca_state_nb);
+
+	/* Flush workqueues of all pending events. */
+	mlx5_vhca_event_work_queues_flush(dev);
 }
 
 int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
 {
-	if (!dev->priv.vhca_state_notifier)
-		return -EOPNOTSUPP;
-	return blocking_notifier_chain_register(&dev->priv.vhca_state_notifier->n_head, nb);
+	return blocking_notifier_chain_register(&dev->priv.vhca_state_n_head,
+						nb);
 }
 
 void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
 {
-	blocking_notifier_chain_unregister(&dev->priv.vhca_state_notifier->n_head, nb);
+	blocking_notifier_chain_unregister(&dev->priv.vhca_state_n_head, nb);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
index 1725ba64f8af..52790423874c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
@@ -18,6 +18,7 @@ static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev)
 }
 
 void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap);
+void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev);
 int mlx5_vhca_event_init(struct mlx5_core_dev *dev);
 void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev);
 void mlx5_vhca_event_start(struct mlx5_core_dev *dev);
@@ -37,6 +38,10 @@ static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *s
 {
 }
 
+static inline void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev)
+{
+}
+
 static inline int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
 {
 	return 0;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7aec53371cf0..1c54aa6f74fb 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -488,7 +488,6 @@ struct mlx5_devcom_dev;
 struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
-struct mlx5_vhca_state_notifier;
 struct mlx5_sf_dev_table;
 struct mlx5_sf_hw_table;
 struct mlx5_sf_table;
@@ -599,6 +598,7 @@ struct mlx5_priv {
 
 	struct mlx5_flow_steering *steering;
 	struct mlx5_mpfs        *mpfs;
+	struct blocking_notifier_head esw_n_head;
 	struct mlx5_eswitch     *eswitch;
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
@@ -614,12 +614,18 @@ struct mlx5_priv {
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_sq_bfreg bfreg;
 #ifdef CONFIG_MLX5_SF
-	struct mlx5_vhca_state_notifier *vhca_state_notifier;
+	struct mlx5_nb vhca_state_nb;
+	struct blocking_notifier_head vhca_state_n_head;
+	struct notifier_block sf_dev_nb;
 	struct mlx5_sf_dev_table *sf_dev_table;
 	struct mlx5_core_dev *parent_mdev;
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
+	struct notifier_block sf_hw_table_vhca_nb;
 	struct mlx5_sf_hw_table *sf_hw_table;
+	struct notifier_block sf_table_esw_nb;
+	struct notifier_block sf_table_vhca_nb;
+	struct notifier_block sf_table_mdev_nb;
 	struct mlx5_sf_table *sf_table;
 #endif
 	struct blocking_notifier_head lag_nh;