From: Tariq Toukan <tariqt@nvidia.com>
To: Andrew Lunn <andrew+netdev@lunn.ch>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, <netdev@vger.kernel.org>,
Paolo Abeni <pabeni@redhat.com>
Cc: Adithya Jayachandran <ajayachandra@nvidia.com>,
Edward Srouji <edwards@nvidia.com>, Gal Pressman <gal@nvidia.com>,
Jason Gunthorpe <jgg@ziepe.ca>, Jiri Pirko <jiri@resnulli.us>,
Leon Romanovsky <leon@kernel.org>, <linux-kernel@vger.kernel.org>,
<linux-rdma@vger.kernel.org>, Maher Sanalla <msanalla@nvidia.com>,
Mark Bloch <mbloch@nvidia.com>, Moshe Shemesh <moshe@nvidia.com>,
Or Har-Toov <ohartoov@nvidia.com>,
Saeed Mahameed <saeedm@nvidia.com>, Shay Drori <shayd@nvidia.com>,
Simon Horman <horms@kernel.org>, Tariq Toukan <tariqt@nvidia.com>
Subject: [PATCH net 1/3] net/mlx5: E-Switch, use state lock for vport state changes
Date: Sun, 16 Aug 2026 09:50:13 +0300 [thread overview]
Message-ID: <20260816065015.3280733-2-tariqt@nvidia.com> (raw)
In-Reply-To: <20260816065015.3280733-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
Protect vport admin state modifications and vport iteration with the
eswitch state_lock mutex to ensure proper serialization of concurrent
vport state changes.
Currently, calls to mlx5_modify_vport_admin_state() and loops iterating
over eswitch vports can race with each other, potentially leading to
inconsistent vport state. Fix this by acquiring esw->state_lock
Fixes: 7d0314b11cdd ("net/mlx5e: Modify uplink state on interface up/down")
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Reviewed-by: Or Har-Toov <ohartoov@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/en_rep.c | 20 ++++++++++++++-----
.../mellanox/mlx5/core/esw/adj_vport.c | 2 ++
.../mellanox/mlx5/core/eswitch_offloads.c | 4 ++++
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 2 ++
.../net/ethernet/mellanox/mlx5/core/vport.c | 8 ++++++++
5 files changed, 31 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index c8b76d301c92..3d544fe4e6f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -689,11 +689,13 @@ static int mlx5e_rep_open(struct net_device *dev)
if (err)
goto unlock;
+ mutex_lock(&rep->esw->state_lock);
if (!mlx5_modify_vport_admin_state(priv->mdev,
MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
rep->vport, 1,
MLX5_VPORT_ADMIN_STATE_UP))
netif_carrier_on(dev);
+ mutex_unlock(&rep->esw->state_lock);
unlock:
mutex_unlock(&priv->state_lock);
@@ -708,10 +710,12 @@ static int mlx5e_rep_close(struct net_device *dev)
int ret;
mutex_lock(&priv->state_lock);
+ mutex_lock(&rep->esw->state_lock);
mlx5_modify_vport_admin_state(priv->mdev,
MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
rep->vport, 1,
MLX5_VPORT_ADMIN_STATE_DOWN);
+ mutex_unlock(&rep->esw->state_lock);
ret = mlx5e_close_locked(dev);
mutex_unlock(&priv->state_lock);
return ret;
@@ -783,22 +787,25 @@ static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier)
struct mlx5e_priv *priv = netdev_priv(dev);
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep = rpriv->rep;
- int err;
+ int err = 0;
+ mutex_lock(&rep->esw->state_lock);
if (new_carrier) {
err = mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
rep->vport, 1, MLX5_VPORT_ADMIN_STATE_UP);
if (err)
- return err;
+ goto unlock;
netif_carrier_on(dev);
} else {
err = mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
rep->vport, 1, MLX5_VPORT_ADMIN_STATE_DOWN);
if (err)
- return err;
+ goto unlock;
netif_carrier_off(dev);
}
- return 0;
+unlock:
+ mutex_unlock(&rep->esw->state_lock);
+ return err;
}
static const struct net_device_ops mlx5e_netdev_ops_rep = {
@@ -1337,9 +1344,12 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
mlx5e_rep_tc_enable(priv);
- if (MLX5_CAP_GEN(mdev, uplink_follow))
+ if (MLX5_CAP_GEN(mdev, uplink_follow)) {
+ mutex_lock(&mdev->priv.eswitch->state_lock);
mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
+ mutex_unlock(&mdev->priv.eswitch->state_lock);
+ }
mlx5_lag_add_netdev(mdev, netdev);
priv->events_nb.notifier_call = uplink_rep_async_event;
mlx5_notifier_register(mdev, &priv->events_nb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c
index ca249b50f830..3624c680a861 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c
@@ -9,6 +9,8 @@ int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, u16 vport,
{
u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {};
+ lockdep_assert_held(&dev->priv.eswitch->state_lock);
+
MLX5_SET(modify_vport_state_in, in, opcode,
MLX5_CMD_OP_MODIFY_VPORT_STATE);
MLX5_SET(modify_vport_state_in, in, op_mod,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 247e5d85ec36..d603e294ee0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2567,6 +2567,7 @@ static void mlx5_esw_fdb_active(struct mlx5_eswitch *esw)
mlx5_esw_fdb_drop_destroy(esw);
mlx5_mpfs_enable(esw->dev);
+ mutex_lock(&esw->state_lock);
mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
if (!vport->adjacent)
continue;
@@ -2574,6 +2575,7 @@ static void mlx5_esw_fdb_active(struct mlx5_eswitch *esw)
vport->vport);
mlx5_esw_adj_vport_modify(esw->dev, vport->vport, true);
}
+ mutex_unlock(&esw->state_lock);
esw->offloads_inactive = false;
esw_warn(esw->dev, "MPFS/FDB active\n");
@@ -2587,6 +2589,7 @@ static void mlx5_esw_fdb_inactive(struct mlx5_eswitch *esw)
mlx5_mpfs_disable(esw->dev);
mlx5_esw_fdb_drop_create(esw);
+ mutex_lock(&esw->state_lock);
mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) {
if (!vport->adjacent)
continue;
@@ -2595,6 +2598,7 @@ static void mlx5_esw_fdb_inactive(struct mlx5_eswitch *esw)
mlx5_esw_adj_vport_modify(esw->dev, vport->vport, false);
}
+ mutex_unlock(&esw->state_lock);
esw->offloads_inactive = true;
esw_warn(esw->dev, "MPFS/FDB inactive\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 28d16fdc3f06..2285c889c215 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1471,6 +1471,7 @@ static void mlx5_lag_modify_device_vports_speed(struct mlx5_core_dev *mdev,
if (!MLX5_CAP_ESW(mdev, esw_vport_state_max_tx_speed))
return;
+ mutex_lock(&esw->state_lock);
mlx5_esw_for_each_vport(esw, i, vport) {
if (!vport)
continue;
@@ -1490,6 +1491,7 @@ static void mlx5_lag_modify_device_vports_speed(struct mlx5_core_dev *mdev,
"Failed to set vport %d speed %d, err=%d\n",
vport->vport, speed, ret);
}
+ mutex_unlock(&esw->state_lock);
}
void mlx5_lag_set_vports_agg_speed(struct mlx5_lag *ldev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 3676e26ac6b0..080f097b7bfa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -89,6 +89,10 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
{
u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {};
+#ifdef CONFIG_MLX5_ESWITCH
+ lockdep_assert_held(&mdev->priv.eswitch->state_lock);
+#endif
+
MLX5_SET(modify_vport_state_in, in, opcode,
MLX5_CMD_OP_MODIFY_VPORT_STATE);
MLX5_SET(modify_vport_state_in, in, op_mod, opmod);
@@ -106,6 +110,10 @@ int mlx5_modify_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 opmod,
u8 admin_state;
int err;
+#ifdef CONFIG_MLX5_ESWITCH
+ lockdep_assert_held(&mdev->priv.eswitch->state_lock);
+#endif
+
err = mlx5_query_vport_admin_state(mdev, opmod, vport, other_vport,
&admin_state);
if (err)
--
2.44.0
next prev parent reply other threads:[~2026-08-16 6:51 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-16 6:50 [PATCH net 0/3] net/mlx5: Preserve speed and state across vport modify commands Tariq Toukan
2026-08-16 6:50 ` Tariq Toukan [this message]
2026-08-16 6:50 ` [PATCH net 2/3] net/mlx5: Move vport DOWN state check out of mlx5_query_vport_max_tx_speed() Tariq Toukan
2026-08-16 6:50 ` [PATCH net 3/3] net/mlx5: E-Switch, preserve max tx speed on vport state modification Tariq Toukan
2026-08-19 14:36 ` [PATCH net 0/3] net/mlx5: Preserve speed and state across vport modify commands Simon Horman
2026-08-20 19:30 ` 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=20260816065015.3280733-2-tariqt@nvidia.com \
--to=tariqt@nvidia.com \
--cc=ajayachandra@nvidia.com \
--cc=andrew+netdev@lunn.ch \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=edwards@nvidia.com \
--cc=gal@nvidia.com \
--cc=horms@kernel.org \
--cc=jgg@ziepe.ca \
--cc=jiri@resnulli.us \
--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=msanalla@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=ohartoov@nvidia.com \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=shayd@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.