diff mbox series

[net-next,26/27] net/mlx5: Report devlink health on FW fatal issues

Message ID 1547737521-29888-27-git-send-email-eranbe@mellanox.com
State Changes Requested
Delegated to: David Miller
Headers show
Series Devlink health reporting and recovery system | expand

Commit Message

Eran Ben Elisha Jan. 17, 2019, 3:05 p.m. UTC 
From: Moshe Shemesh <moshe@mellanox.com>

Report devlink health on FW fatal issues via FW_fatal_reporter. The
driver recover flow for FW fatal error is now being handled by the
devlink health.

Having the recovery controlled by devlink health, the user has the
ability to cancel the auto-recovery for debug session and run it
manually.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.c | 19 +++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/devlink.h |  1 +
 .../net/ethernet/mellanox/mlx5/core/health.c  | 23 +------------------
 3 files changed, 21 insertions(+), 22 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 406856002dd1..e03160626171 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -235,6 +235,25 @@  static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
 		.diagnose = mlx5_fw_reporter_diagnose,
 };
 
+void mlx5_fw_fatal_reporter_work(struct work_struct *work)
+{
+	struct mlx5_fw_reporter_ctx fw_reporter_ctx;
+	struct mlx5_core_health *health;
+	struct delayed_work *dwork;
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+
+	dwork = container_of(work, struct delayed_work, work);
+	health = container_of(dwork, struct mlx5_core_health, recover_work);
+	priv = container_of(health, struct mlx5_priv, health);
+	dev = container_of(priv, struct mlx5_core_dev, priv);
+
+	fw_reporter_ctx.err_synd = health->synd;
+	fw_reporter_ctx.miss_counter = health->miss_counter;
+	devlink_health_report(dev->fw_fatal_reporter, "FW recovery",
+			      &fw_reporter_ctx);
+}
+
 static int
 mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
 			       void *priv_ctx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 9b544f677aa7..9c5eba632293 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -17,5 +17,6 @@  void mlx5_devlink_unregister(struct devlink *devlink);
 int mlx5_fw_reporters_create(struct mlx5_core_dev *dev);
 void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev);
 void mlx5_fw_reporter_err_work(struct work_struct *work);
+void mlx5_fw_fatal_reporter_work(struct work_struct *work);
 
 #endif /* __MLX5_DEVLINK_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d3ea624bd03c..189000545162 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -303,27 +303,6 @@  static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 	mlx5_disable_device(dev);
 }
 
-static void health_recover(struct work_struct *work)
-{
-	struct mlx5_core_health *health;
-	struct delayed_work *dwork;
-	struct mlx5_core_dev *dev;
-	struct mlx5_priv *priv;
-
-	dwork = container_of(work, struct delayed_work, work);
-	health = container_of(dwork, struct mlx5_core_health, recover_work);
-	priv = container_of(health, struct mlx5_priv, health);
-	dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	if (mlx5_sensor_pci_not_working(dev)) {
-		dev_err(&dev->pdev->dev, "health recovery flow aborted, PCI reads still not working\n");
-		return;
-	}
-
-	dev_err(&dev->pdev->dev, "starting health recovery flow\n");
-	mlx5_recover_device(dev);
-}
-
 /* How much time to wait until health resetting the driver (in msecs) */
 #define MLX5_RECOVERY_DELAY_MSECS 60000
 #define MLX5_RECOVERY_NO_DELAY 0
@@ -586,7 +565,7 @@  int mlx5_health_init(struct mlx5_core_dev *dev)
 	spin_lock_init(&health->wq_lock);
 	INIT_WORK(&health->work, health_care);
 	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
-	INIT_DELAYED_WORK(&health->recover_work, health_recover);
+	INIT_DELAYED_WORK(&health->recover_work, mlx5_fw_fatal_reporter_work);
 	health->crdump = NULL;
 
 	return 0;