[PATCH 5.13 083/104] net/mlx5: Unload device upon firmware fatal error

[Greg Kroah-Hartman]

From: Aya Levin <ayal@xxxxxxxxxx>

[ Upstream commit 7f331bf0f060c2727e36d64f9b098b4ee5f3dfad ]

When fw_fatal reporter reports an error, the firmware in not responding.
Unload the device to ensure that the driver closes all its resources,
even if recovery is not due (user disabled auto-recovery or reporter is
in grace period). On successful recovery the device is loaded back up.

Fixes: b3bd076f7501 ("net/mlx5: Report devlink health on FW fatal issues")
Signed-off-by: Aya Levin <ayal@xxxxxxxxxx>
Reviewed-by: Moshe Shemesh <moshe@xxxxxxxxxx>
Signed-off-by: Saeed Mahameed <saeedm@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 9ff163c5bcde..9abeb80ffa31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -626,8 +626,16 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 	}
 	fw_reporter_ctx.err_synd = health->synd;
 	fw_reporter_ctx.miss_counter = health->miss_counter;
-	devlink_health_report(health->fw_fatal_reporter,
-			      "FW fatal error reported", &fw_reporter_ctx);
+	if (devlink_health_report(health->fw_fatal_reporter,
+				  "FW fatal error reported", &fw_reporter_ctx) == -ECANCELED) {
+		/* If recovery wasn't performed, due to grace period,
+		 * unload the driver. This ensures that the driver
+		 * closes all its resources and it is not subjected to
+		 * requests from the kernel.
+		 */
+		mlx5_core_err(dev, "Driver is in error state. Unloading\n");
+		mlx5_unload_one(dev);
+	}
 }
 
 static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
-- 
2.30.2