Re: [PATCH net V2 1/4] net/mlx5: SD, serialize SD LAG init/cleanup against LAG mode changes
From: Paolo Abeni <pabeni@redhat.com>
Date: 2026-09-10 11:08:19
Also in:
linux-rdma, lkml
On 9/6/26 9:13 AM, Tariq Toukan wrote:
quoted hunk ↗ jump to hunk
void mlx5_lag_enable_change(struct mlx5_core_dev *dev)diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 4cdc50cd6f03..99cf455a61e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c@@ -345,7 +345,14 @@ static void sd_lag_init(struct mlx5_core_dev *dev) return; } +recheck: mutex_lock(&ldev->lock); + if (ldev->mode_changes_in_progress) { + mutex_unlock(&ldev->lock); + msleep(100); + goto recheck;
My reading of the clashiko report is that the above introduces a deadlock. While I agree that the fairness issue raised by sashiko.dev could be deferred to net-next, I think we must avoid introducing the mentioned deadlock. /P