From e639bc695f05335c11a5e387b6ad44249b35d673 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 24 Nov 2022 13:34:12 +0200 Subject: [PATCH] net/mlx5: Avoid recovery in probe flows [ Upstream commit 9078e843efec530f279a155f262793c58b0746bd ] Currently, recovery is done without considering whether the device is still in probe flow. This may lead to recovery before device have finished probed successfully. e.g.: while mlx5_init_one() is running. Recovery flow is using functionality that is loaded only by mlx5_init_one(), and there is no point in running recovery without mlx5_init_one() finished successfully. Fix it by waiting for probe flow to finish and checking whether the device is probed before trying to perform recovery. Fixes: 51d138c2610a ("net/mlx5: Fix health error state handling") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 86ed87d..96417c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -674,6 +674,12 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) dev = container_of(priv, struct mlx5_core_dev, priv); devlink = priv_to_devlink(dev); + mutex_lock(&dev->intf_state_mutex); + if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { + mlx5_core_err(dev, "health works are not permitted at this stage\n"); + return; + } + mutex_unlock(&dev->intf_state_mutex); enter_error_state(dev, false); if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) { devl_lock(devlink); -- 2.7.4