From: Or Har-Toov <ohartoov@nvidia.com>

When querying speed information for a representor in switchdev mode,
the code previously used the first device in the eswitch, which may not
match the device that actually owns the representor. In setups such as
multi-port eswitch or LAG, this led to incorrect port attributes being
reported.

Fix this by retrieving the correct core device from the representor's
eswitch before querying its port attributes.

Fixes: 27f9e0ccb6da ("net/mlx5: Lag, Add single RDMA device in multiport mode")
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Edward Srouji <edwards@nvidia.com>
---
Changes in v2:
- Replace unnecessary NULL check and fallback for
  mlx5_eswitch_get_core_dev() return value with a WARN_ON().
  In this flow, the function cannot return NULL unless there is a driver
  bug elsewhere.
- Link to v1:
  https://lore.kernel.org/r/20260113-port-speed-query-fix-v1-1-234cacc991fa@nvidia.com
---
 drivers/infiniband/hw/mlx5/main.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e81080622283..8ea01edfaf45 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -561,12 +561,20 @@ static int mlx5_query_port_roce(struct ib_device *device, u32 port_num,
 	 * of an error it will still be zeroed out.
 	 * Use native port in case of reps
 	 */
-	if (dev->is_rep)
-		err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
-					   1, 0);
-	else
-		err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
-					   mdev_port_num, 0);
+	if (dev->is_rep) {
+		struct mlx5_eswitch_rep *rep;
+
+		rep = dev->port[port_num - 1].rep;
+		if (rep) {
+			mdev = mlx5_eswitch_get_core_dev(rep->esw);
+			WARN_ON(!mdev);
+		}
+		mdev_port_num = 1;
+	}
+
+	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
+				   mdev_port_num, 0);
+
 	if (err)
 		goto out;
 	ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability);

---
base-commit: 325e3b5431ddd27c5f93156b36838a351e3b2f72
change-id: 20260113-port-speed-query-fix-592efa2b4e36

Best regards,
-- 
Edward Srouji <edwards@nvidia.com>

On Thu, 15 Jan 2026 14:26:45 +0200, Edward Srouji wrote:
> When querying speed information for a representor in switchdev mode,
> the code previously used the first device in the eswitch, which may not
> match the device that actually owns the representor. In setups such as
> multi-port eswitch or LAG, this led to incorrect port attributes being
> reported.
> 
> Fix this by retrieving the correct core device from the representor's
> eswitch before querying its port attributes.
> 
> [...]

Applied, thanks!

[1/1] IB/mlx5: Fix port speed query for representors
      https://git.kernel.org/rdma/rdma/c/18ea78e2ae83d1

Best regards,
-- 
Leon Romanovsky <leon@kernel.org>