diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2026-08-28 15:39:17 -0700 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-08-28 15:39:17 -0700 |
| commit | b873bf81412eb9292ec6028dca2c66d08f8d526e (patch) | |
| tree | 03a79ac701047df11460abc2f5c4488a16a7c14f | |
| parent | a5d946466a95621fa2769720d59ea336003aa1a5 (diff) | |
| parent | 63811edf512584c946e5e96b100e9e280703bbb5 (diff) | |
Merge branch 'net-mlx5e-prevent-stale-xsk-buffer-release-on-refill-retries'
Jerome Tollet says:
====================
net/mlx5e: Prevent stale XSK buffer release on refill retries
Prevent duplicate XSK buffer release when a deferred RX refill fails and
the same WQE is retried.
Patch 1 fixes legacy cyclic RQ. It is unchanged from v3 and retains
Dragos' Reviewed-by tag.
Patch 2 fixes the analogous striding-RQ MPWQE path. Following Dragos'
review, it now fills skip_release_bitmap in the common error path of
mlx5e_xsk_alloc_rx_mpwqe(), consistently with mlx5e_alloc_rx_mpwqe().
Targeted fault injection covered both an early allocation failure and a
partial 8-of-16-buffer unwind. With three consecutive failures for one
MPWQE, the original 16 XSK buffers were released only once, retries saw a
full bitmap, and a later successful allocation cleared it. A clean
20-second AF_XDP zero-copy pressure run exercised 1,575,262 buffer
allocation failures without invalid descriptors, WQE errors, or kernel
warnings.
====================
Link: https://patch.msgid.link/20260824141645.23700-1-jtollet@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 2 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 7 |
2 files changed, 7 insertions, 2 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 4f984f6a2cb9..55ec6387ab28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -3,6 +3,7 @@ #include "rx.h" #include "en/xdp.h" +#include <linux/bitmap.h> #include <net/xdp_sock_drv.h> #include <linux/filter.h> @@ -156,6 +157,7 @@ err_reuse_batch: xsk_buff_free(xsk_buffs[batch]); err: + bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe); rq->stats->buff_alloc_err++; return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 206cf9db3466..7bd0606a5253 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -410,8 +410,11 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, static void mlx5e_xsk_free_rx_wqe(struct mlx5e_wqe_frag_info *wi) { - if (!(wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE))) - xsk_buff_free(*wi->xskp); + if (wi->flags & BIT(MLX5E_WQE_FRAG_SKIP_RELEASE)) + return; + + xsk_buff_free(*wi->xskp); + wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); } static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) |
