From: Prathamesh Deshpande <prathameshdeshpande7@gmail.com>
To: Leon Romanovsky <leon@kernel.org>, Jason Gunthorpe <jgg@ziepe.ca>
Cc: linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
dledford@redhat.com, haggaie@mellanox.com,
Prathamesh Deshpande <prathameshdeshpande7@gmail.com>
Subject: [PATCH v10 2/2] IB/mlx5: Serialize force-enable state and preserve loopback accounting
Date: Sun, 12 Apr 2026 02:18:50 +0100 [thread overview]
Message-ID: <20260412011942.13744-3-prathameshdeshpande7@gmail.com> (raw)
In-Reply-To: <20260412011942.13744-1-prathameshdeshpande7@gmail.com>
force_enable is shared between MP bind/unbind flows and regular loopback
enable/disable flows. MP helpers updated force_enable without lb.mutex,
while regular paths read it under lb.mutex, allowing races and state
mismatches.
Serialize MP force-enable transitions under lb.mutex. In regular loopback
paths, update counters before checking force_enable
and roll them back if HW enable fails. Also keep pre-existing
master loopback enabled when MP enable fails on the slave side.
Use a TD-capability-aware baseline for user_td transitions so threshold
checks are correct on both TD-capable and no-TD hardware.
Fixes: 08aae7860450 ("RDMA/mlx5: Fix vport loopback forcing for MPV device")
Signed-off-by: Prathamesh Deshpande <prathameshdeshpande7@gmail.com>
---
drivers/infiniband/hw/mlx5/main.c | 67 +++++++++++++++++++++++++------
1 file changed, 55 insertions(+), 12 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index b3b297bc2f2b..1f11ab443233 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1973,25 +1973,45 @@ static void deallocate_uars(struct mlx5_ib_dev *dev,
context->devx_uid);
}
+static inline u32 mlx5_ib_lb_td_base(struct mlx5_core_dev *mdev)
+{
+ return MLX5_CAP_GEN(mdev, log_max_transport_domain) ? 1 : 0;
+}
+
static int mlx5_ib_enable_lb_mp(struct mlx5_core_dev *master,
struct mlx5_core_dev *slave,
struct mlx5_ib_lb_state *lb_state)
{
+ bool user_enabled;
int err;
+ lockdep_assert_held(&mlx5_ib_multiport_mutex);
+
+ mutex_lock(&lb_state->mutex);
+ if (lb_state->force_enable) {
+ mutex_unlock(&lb_state->mutex);
+ return 0;
+ }
+ user_enabled = lb_state->enabled;
+
err = mlx5_nic_vport_update_local_lb(master, true);
if (err)
- return err;
+ goto unlock;
err = mlx5_nic_vport_update_local_lb(slave, true);
if (err)
goto out;
lb_state->force_enable = true;
+ lb_state->enabled = true;
+ mutex_unlock(&lb_state->mutex);
return 0;
out:
- mlx5_nic_vport_update_local_lb(master, false);
+ if (!user_enabled)
+ mlx5_nic_vport_update_local_lb(master, false);
+unlock:
+ mutex_unlock(&lb_state->mutex);
return err;
}
@@ -1999,33 +2019,53 @@ static void mlx5_ib_disable_lb_mp(struct mlx5_core_dev *master,
struct mlx5_core_dev *slave,
struct mlx5_ib_lb_state *lb_state)
{
- mlx5_nic_vport_update_local_lb(slave, false);
- mlx5_nic_vport_update_local_lb(master, false);
+ u32 td_base = mlx5_ib_lb_td_base(master);
+
+ lockdep_assert_held(&mlx5_ib_multiport_mutex);
+
+ mutex_lock(&lb_state->mutex);
+ mlx5_nic_vport_update_local_lb(slave, false);
lb_state->force_enable = false;
+ if (lb_state->enabled &&
+ lb_state->user_td <= td_base && lb_state->qps == 0) {
+ mlx5_nic_vport_update_local_lb(master, false);
+ lb_state->enabled = false;
+ }
+
+ mutex_unlock(&lb_state->mutex);
}
int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
{
+ u32 td_base = mlx5_ib_lb_td_base(dev->mdev);
int err = 0;
- if (dev->lb.force_enable)
- return 0;
-
mutex_lock(&dev->lb.mutex);
if (td)
dev->lb.user_td++;
if (qp)
dev->lb.qps++;
- if (dev->lb.user_td == 2 ||
+ if (dev->lb.force_enable)
+ goto unlock;
+
+ if (dev->lb.user_td == td_base + 1 ||
dev->lb.qps == 1) {
if (!dev->lb.enabled) {
err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
- dev->lb.enabled = true;
+ if (err) {
+ if (td)
+ dev->lb.user_td--;
+ if (qp)
+ dev->lb.qps--;
+ } else {
+ dev->lb.enabled = true;
+ }
}
}
+unlock:
mutex_unlock(&dev->lb.mutex);
return err;
@@ -2033,8 +2073,7 @@ int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
{
- if (dev->lb.force_enable)
- return;
+ u32 td_base = mlx5_ib_lb_td_base(dev->mdev);
mutex_lock(&dev->lb.mutex);
if (td)
@@ -2042,7 +2081,10 @@ void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
if (qp)
dev->lb.qps--;
- if (dev->lb.user_td == 1 &&
+ if (dev->lb.force_enable)
+ goto unlock;
+
+ if (dev->lb.user_td <= td_base &&
dev->lb.qps == 0) {
if (dev->lb.enabled) {
mlx5_nic_vport_update_local_lb(dev->mdev, false);
@@ -2050,6 +2092,7 @@ void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
}
}
+unlock:
mutex_unlock(&dev->lb.mutex);
}
--
2.43.0
prev parent reply other threads:[~2026-04-12 1:20 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-12 1:18 [PATCH v10 0/2] IB/mlx5: Fix loopback rollback and locking Prathamesh Deshpande
2026-04-12 1:18 ` [PATCH v10 1/2] IB/mlx5: Fix transport-domain rollback and initialize lb mutex earlier Prathamesh Deshpande
2026-04-12 1:18 ` Prathamesh Deshpande [this message]
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=20260412011942.13744-3-prathameshdeshpande7@gmail.com \
--to=prathameshdeshpande7@gmail.com \
--cc=dledford@redhat.com \
--cc=haggaie@mellanox.com \
--cc=jgg@ziepe.ca \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
/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