From fb32c890e6cf38a3f6f2b848154c88049e42f051 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Tue, 12 May 2020 10:54:36 -0400 Subject: [PATCH 166/312] [netdrv] net/mlx5e: Do not recover from a non-fatal syndrome Message-id: <20200512105530.4207-71-ahleihel@redhat.com> Patchwork-id: 306943 Patchwork-instance: patchwork O-Subject: [RHEL8.3 BZ 1789382 070/124] net/mlx5e: Do not recover from a non-fatal syndrome Bugzilla: 1789382 RH-Acked-by: Tony Camuso RH-Acked-by: Kamal Heib RH-Acked-by: Jarod Wilson Bugzilla: http://bugzilla.redhat.com/1789382 Upstream: v5.6 commit 187a9830c921d92c4a9a8e2921ecc4b35a97532c Author: Aya Levin Date: Thu Mar 19 13:25:17 2020 +0200 net/mlx5e: Do not recover from a non-fatal syndrome For non-fatal syndromes like LOCAL_LENGTH_ERR, recovery shouldn't be triggered. In these scenarios, the RQ is not actually in ERR state. This misleads the recovery flow which assumes that the RQ is really in error state and no more completions arrive, causing crashes on bad page state. Fixes: 8276ea1353a4 ("net/mlx5e: Report and recover from CQE with error on RQ") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Alaa Hleihel Signed-off-by: Frantisek Hrbata --- drivers/net/ethernet/mellanox/mlx5/core/en/health.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index d3693fa547ac..e54f70d9af22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -10,8 +10,7 @@ static inline bool cqe_syndrome_needs_recover(u8 syndrome) { - return syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR || - syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR || + return syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR || syndrome == MLX5_CQE_SYNDROME_LOCAL_PROT_ERR || syndrome == MLX5_CQE_SYNDROME_WR_FLUSH_ERR; } -- 2.13.6