[PATCH net 0/4] net/mlx5: SD LAG and devcom stability fixes · Tariq Toukan <tariqt@nvidia.com> · 2026-09-02
[PATCH net 2/4] net/mlx5: devcom, Base component size on linked devices · Tariq Toukan <tariqt@nvidia.com> · 2026-09-02
[PATCH net 1/4] net/mlx5: SD, serialize SD LAG init/cleanup against LAG mode changes · Tariq Toukan <tariqt@nvidia.com> · 2026-09-02
[PATCH net 3/4] net/mlx5: SD, unload reps on shared FDB create error path · Tariq Toukan <tariqt@nvidia.com> · 2026-09-02
[PATCH net 4/4] net/mlx5: LAG, reload IB reps of LAG master before the rest · Tariq Toukan <tariqt@nvidia.com> · 2026-09-02
Re: [PATCH net 0/4] net/mlx5: SD LAG and devcom stability fixes · Jakub Kicinski <kuba@kernel.org> · 2026-09-05

Re: [PATCH net 0/4] net/mlx5: SD LAG and devcom stability fixes

From: Jakub Kicinski <kuba@kernel.org>
Date: 2026-09-05 20:12:42
Also in: linux-rdma, lkml

On Wed, 2 Sep 2026 19:37:12 +0300 Tariq Toukan wrote:

Hi,

This series by Shay fixes four bugs in the Socket Direct LAG and devcom
subsystems, all related to initialization/teardown ordering and
concurrent access to the LAG device.

Patchwork seems right, this doesn't apply.

Failed to apply patch:
Applying: net/mlx5: SD, serialize SD LAG init/cleanup against LAG mode changes
error: git diff header lacks filename information when removing 1 leading pathname component at .git/rebase-apply/patch:10
error: could not build fake ancestor

The format of the pre-replies seems to break git am?

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help