public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Tariq Toukan <tariqt@nvidia.com>
To: Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
	Leon Romanovsky <leon@kernel.org>,
	Tariq Toukan <tariqt@nvidia.com>, Mark Bloch <mbloch@nvidia.com>,
	<netdev@vger.kernel.org>, <linux-rdma@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, Gal Pressman <gal@nvidia.com>,
	Moshe Shemesh <moshe@nvidia.com>,
	Carolina Jubran <cjubran@nvidia.com>,
	Cosmin Ratiu <cratiu@nvidia.com>, Jiri Pirko <jiri@nvidia.com>
Subject: [PATCH net-next 6/6] net/mlx5: Move SF dev table notifier registration outside the PF devlink lock
Date: Sun, 16 Nov 2025 22:45:40 +0200	[thread overview]
Message-ID: <1763325940-1231508-7-git-send-email-tariqt@nvidia.com> (raw)
In-Reply-To: <1763325940-1231508-1-git-send-email-tariqt@nvidia.com>

From: Cosmin Ratiu <cratiu@nvidia.com>

This completes the previous patches by moving notifier registration for
SF dev tables outside the devlink locked critical section in
mlx5_init_one() / mlx5_uninit_one() and into the mlx5_mdev_init() /
mlx5_mdev_uninit() functions.

This is only done for non-SFs, since SFs do not have a SF HW table
themselves.

After this patch, notifiers can grab the PF devlink lock (soon to be
necessary) without creating a locking cycle.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/main.c    |  7 +++
 .../ethernet/mellanox/mlx5/core/sf/dev/dev.c  | 47 ++++++++++++-------
 .../ethernet/mellanox/mlx5/core/sf/dev/dev.h  | 11 +++++
 include/linux/mlx5/driver.h                   |  1 +
 4 files changed, 49 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0c3613ef39b1..024339ce41f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1837,8 +1837,14 @@ static int mlx5_notifiers_init(struct mlx5_core_dev *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:
@@ -1848,6 +1854,7 @@ static int mlx5_notifiers_init(struct mlx5_core_dev *dev)
 
 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);
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 a68a8ee24dce..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;
@@ -380,7 +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);
 
 	/* 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/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7dbef112deaf..6ff52bde1f40 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -616,6 +616,7 @@ struct mlx5_priv {
 #ifdef CONFIG_MLX5_SF
 	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
-- 
2.31.1


  parent reply	other threads:[~2025-11-16 20:47 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-16 20:45 [PATCH net-next 0/6] net/mlx5: Move notifiers outside the devlink lock Tariq Toukan
2025-11-16 20:45 ` [PATCH net-next 1/6] net/mlx5: Initialize events outside " Tariq Toukan
2025-11-16 20:45 ` [PATCH net-next 2/6] net/mlx5: Move the esw mode notifier chain outside the " Tariq Toukan
2025-11-16 20:45 ` [PATCH net-next 3/6] net/mlx5: Move the vhca event notifier outside of " Tariq Toukan
2025-11-16 20:45 ` [PATCH net-next 4/6] net/mlx5: Move the SF HW table notifier outside " Tariq Toukan
2025-11-16 20:45 ` [PATCH net-next 5/6] net/mlx5: Move the SF table notifiers " Tariq Toukan
2025-11-16 20:45 ` Tariq Toukan [this message]
2025-11-20  4:40 ` [PATCH net-next 0/6] net/mlx5: Move " patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1763325940-1231508-7-git-send-email-tariqt@nvidia.com \
    --to=tariqt@nvidia.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=cjubran@nvidia.com \
    --cc=cratiu@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=gal@nvidia.com \
    --cc=jiri@nvidia.com \
    --cc=kuba@kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mbloch@nvidia.com \
    --cc=moshe@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeedm@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox