[net-next v2 14/15] net/mlx5: Report devlink health on FW fatal issues

[Saeed Mahameed <saeedm@mellanox.com>]

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.

Call mlx5_enter_error_state() before calling devlink_health_report() to
ensure entering device error state even if auto-recovery is off.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/health.c  | 42 ++++++++++++-------
 .../net/ethernet/mellanox/mlx5/core/main.c    | 10 ++---
 include/linux/mlx5/driver.h                   |  2 +-
 3 files changed, 31 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 4ef62c6c6424..2fe6923f7ce0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -327,19 +327,6 @@ static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
 	return 0;
 }
 
-static void health_recover_work(struct work_struct *work)
-{
-	struct mlx5_core_health *health;
-	struct mlx5_core_dev *dev;
-	struct mlx5_priv *priv;
-
-	health = container_of(work, struct mlx5_core_health, work);
-	priv = container_of(health, struct mlx5_priv, health);
-	dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	mlx5_health_try_recover(dev);
-}
-
 static const char *hsynd_str(u8 synd)
 {
 	switch (synd) {
@@ -614,6 +601,29 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
 	return err;
 }
 
+static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
+{
+	struct mlx5_fw_reporter_ctx fw_reporter_ctx;
+	struct mlx5_core_health *health;
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+
+	health = container_of(work, struct mlx5_core_health, fatal_report_work);
+	priv = container_of(health, struct mlx5_priv, health);
+	dev = container_of(priv, struct mlx5_core_dev, priv);
+
+	mlx5_enter_error_state(dev, false);
+	if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
+		if (mlx5_health_try_recover(dev))
+			mlx5_core_err(dev, "health recovery failed\n");
+		return;
+	}
+	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);
+}
+
 static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
 		.name = "fw_fatal",
 		.recover = mlx5_fw_fatal_reporter_recover,
@@ -672,7 +682,7 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev)
 
 	spin_lock_irqsave(&health->wq_lock, flags);
 	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
-		queue_work(health->wq, &health->work);
+		queue_work(health->wq, &health->fatal_report_work);
 	else
 		mlx5_core_err(dev, "new health works are not permitted at this stage\n");
 	spin_unlock_irqrestore(&health->wq_lock, flags);
@@ -758,7 +768,7 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 	cancel_work_sync(&health->report_work);
-	cancel_work_sync(&health->work);
+	cancel_work_sync(&health->fatal_report_work);
 }
 
 void mlx5_health_flush(struct mlx5_core_dev *dev)
@@ -795,7 +805,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	if (!health->wq)
 		goto out_err;
 	spin_lock_init(&health->wq_lock);
-	INIT_WORK(&health->work, health_recover_work);
+	INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work);
 	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ec5287c51825..998eec938d3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1363,11 +1363,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 	mlx5_enter_error_state(dev, false);
 	mlx5_error_sw_reset(dev);
 	mlx5_unload_one(dev, false);
-	/* In case of kernel call drain the health wq */
-	if (state) {
-		mlx5_drain_health_wq(dev);
-		mlx5_pci_disable_device(dev);
-	}
+	mlx5_drain_health_wq(dev);
+	mlx5_pci_disable_device(dev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -1535,7 +1532,8 @@ MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
 
 void mlx5_disable_device(struct mlx5_core_dev *dev)
 {
-	mlx5_pci_err_detected(dev->pdev, 0);
+	mlx5_error_sw_reset(dev);
+	mlx5_unload_one(dev, false);
 }
 
 void mlx5_recover_device(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index caac96bf9c0d..25847beabd3f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -442,7 +442,7 @@ struct mlx5_core_health {
 	spinlock_t			wq_lock;
 	struct workqueue_struct	       *wq;
 	unsigned long			flags;
-	struct work_struct		work;
+	struct work_struct		fatal_report_work;
 	struct work_struct		report_work;
 	struct delayed_work		recover_work;
 	struct devlink_health_reporter *fw_reporter;
-- 
2.21.0