net/mlx5: Start health poll at earlier stage of driver load

Start health poll at earlier stage, so if fw fatal issue occurred before
or during initialization commands such as init_hca or set_hca_cap the
poll health can detect and indicate that the driver is already in error
state.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 19 insertions, 10 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 59205ba2ef7b..5bfc54a10621 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -843,9 +843,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 
 	health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms);
 	add_timer(&health->timer);
-
-	if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc))
-		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
 }
 
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
@@ -862,6 +859,14 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 	del_timer_sync(&health->timer);
 }
 
+void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc))
+		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
+}
+
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index daa7442f31c9..0b459d841c3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1092,7 +1092,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
-static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
+static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout)
 {
 	int err;
 
@@ -1130,10 +1130,12 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
 
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
+	mlx5_start_health_poll(dev);
+
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
-		goto err_cmd_cleanup;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_core_set_issi(dev);
@@ -1185,8 +1187,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
 		mlx5_core_err(dev, "query hca failed\n");
 		goto reclaim_boot_pages;
 	}
-
-	mlx5_start_health_poll(dev);
+	mlx5_start_health_fw_log_up(dev);
 
 	return 0;
 
@@ -1194,6 +1195,8 @@ reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
 err_disable_hca:
 	mlx5_core_disable_hca(dev, 0);
+stop_health_poll:
+	mlx5_stop_health_poll(dev, boot);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
@@ -1205,7 +1208,6 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 {
 	int err;
 
-	mlx5_stop_health_poll(dev, boot);
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		mlx5_core_err(dev, "tear_down_hca failed, skip cleanup\n");
@@ -1213,6 +1215,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	}
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
+	mlx5_stop_health_poll(dev, boot);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
@@ -1362,7 +1365,7 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 	mutex_lock(&dev->intf_state_mutex);
 	dev->state = MLX5_DEVICE_STATE_UP;
 
-	err = mlx5_function_setup(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
+	err = mlx5_function_setup(dev, true, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
 	if (err)
 		goto err_function;
 
@@ -1450,7 +1453,7 @@ int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery)
 		timeout = mlx5_tout_ms(dev, FW_PRE_INIT_ON_RECOVERY_TIMEOUT);
 	else
 		timeout = mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT);
-	err = mlx5_function_setup(dev, timeout);
+	err = mlx5_function_setup(dev, false, timeout);
 	if (err)
 		goto err_function;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 285f301a6390..a12929bc31b2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1017,6 +1017,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
+void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,