[net-next 13/15] net/mlx5: Add fw fatal devlink health reporter

[Saeed Mahameed <saeedm@mellanox.com>]

From: Moshe Shemesh <moshe@mellanox.com>

Create mlx5_devlink_health_reporter for fw fatal reporter.
The fw fatal reporter is added in addition to the fw reporter and
implements the recover callback.
The point of having two reporters for FW issues, is that we
don't want to run FW recover on any issue, but only fatal ones.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/health.c  | 70 ++++++++++++++-----
 include/linux/mlx5/driver.h                   |  1 +
 2 files changed, 54 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 03b9fc9ebd6e..e64f0e32cd67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -301,31 +301,43 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 
 /* How much time to wait until health resetting the driver (in msecs) */
 #define MLX5_RECOVERY_WAIT_MSECS 60000
-static void health_care(struct work_struct *work)
+static int mlx5_health_care(struct mlx5_core_dev *dev)
 {
-	struct mlx5_core_health *health;
-	struct mlx5_core_dev *dev;
-	struct mlx5_priv *priv;
 	unsigned long end;
 
-	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_core_warn(dev, "handling bad device here\n");
 	mlx5_handle_bad_state(dev);
-
 	end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS);
 	while (sensor_pci_not_working(dev)) {
 		if (time_after(jiffies, end)) {
 			mlx5_core_err(dev,
 				      "health recovery flow aborted, PCI reads still not working\n");
-			return;
+			return -EIO;
 		}
 		msleep(100);
 	}
 
 	mlx5_core_err(dev, "starting health recovery flow\n");
 	mlx5_recover_device(dev);
+	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state) ||
+	    check_fatal_sensors(dev)) {
+		mlx5_core_err(dev, "health recovery failed\n");
+		return -EIO;
+	}
+	return 0;
+}
+
+static void health_care_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_care(dev);
 }
 
 static const char *hsynd_str(u8 synd)
@@ -526,7 +538,22 @@ static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
 		.dump = mlx5_fw_reporter_dump,
 };
 
-static void mlx5_fw_reporter_create(struct mlx5_core_dev *dev)
+static int
+mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
+			       void *priv_ctx)
+{
+	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+
+	return mlx5_health_care(dev);
+}
+
+static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
+		.name = "fw_fatal",
+		.recover = mlx5_fw_fatal_reporter_recover,
+};
+
+#define MLX5_REPORTER_FW_GRACEFUL_PERIOD 1200000
+static void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct devlink *devlink = priv_to_devlink(dev);
@@ -537,16 +564,25 @@ static void mlx5_fw_reporter_create(struct mlx5_core_dev *dev)
 	if (IS_ERR(health->fw_reporter))
 		mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n",
 			       PTR_ERR(health->fw_reporter));
+
+	health->fw_fatal_reporter =
+		devlink_health_reporter_create(devlink, &mlx5_fw_fatal_reporter_ops,
+					       MLX5_REPORTER_FW_GRACEFUL_PERIOD,
+					       true, dev);
+	if (IS_ERR(health->fw_fatal_reporter))
+		mlx5_core_warn(dev, "Failed to create fw fatal reporter, err = %ld\n",
+			       PTR_ERR(health->fw_fatal_reporter));
 }
 
-static void mlx5_fw_reporter_destroy(struct mlx5_core_dev *dev)
+static void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 
-	if (IS_ERR_OR_NULL(health->fw_reporter))
-		return;
+	if (!IS_ERR_OR_NULL(health->fw_reporter))
+		devlink_health_reporter_destroy(health->fw_reporter);
 
-	devlink_health_reporter_destroy(health->fw_reporter);
+	if (!IS_ERR_OR_NULL(health->fw_fatal_reporter))
+		devlink_health_reporter_destroy(health->fw_fatal_reporter);
 }
 
 static unsigned long get_next_poll_jiffies(void)
@@ -669,7 +705,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 
 	kfree(health->info_buf);
 	destroy_workqueue(health->wq);
-	mlx5_fw_reporter_destroy(dev);
+	mlx5_fw_reporters_destroy(dev);
 }
 
 int mlx5_health_init(struct mlx5_core_dev *dev)
@@ -689,7 +725,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	if (!health->wq)
 		return -ENOMEM;
 	spin_lock_init(&health->wq_lock);
-	INIT_WORK(&health->work, health_care);
+	INIT_WORK(&health->work, health_care_work);
 	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
 	health->crdump = NULL;
 	health->info_buf = kmalloc(HEALTH_INFO_MAX_BUFF, GFP_KERNEL);
@@ -697,7 +733,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 		goto err_alloc_buff;
 	mutex_init(&health->info_buf_lock);
 
-	mlx5_fw_reporter_create(dev);
+	mlx5_fw_reporters_create(dev);
 
 	return 0;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 604079b4706c..6f65787bf91b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -452,6 +452,7 @@ struct mlx5_core_health {
 	/* protect info buf access */
 	struct mutex			info_buf_lock;
 	struct devlink_health_reporter *fw_reporter;
+	struct devlink_health_reporter *fw_fatal_reporter;
 };
 
 struct mlx5_qp_table {
-- 
2.20.1