diff mbox series

[net-next,12/15] net/mlx5: Report devlink health on FW issues

Message ID 20190505003207.1353-13-saeedm@mellanox.com
State Changes Requested
Delegated to: David Miller
Headers show
Series [net-next,01/15] net/mlx5: Move all devlink related functions calls to devlink.c | expand

Commit Message

Saeed Mahameed May 5, 2019, 12:33 a.m. UTC
From: Moshe Shemesh <moshe@mellanox.com>

Use devlink_health_report() to report any symptom of FW issue as FW
counter miss or new health syndrom.
The FW issues detected in mlx5 during poll_health which is called in
timer atomic context and so health work queue is used to schedule the
reports.

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  | 33 +++++++++++++++++++
 include/linux/mlx5/driver.h                   |  2 ++
 2 files changed, 35 insertions(+)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 34b8252afad5..03b9fc9ebd6e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -497,6 +497,29 @@  mlx5_fw_reporter_dump(struct devlink_health_reporter *reporter,
 	return mlx5_fw_tracer_get_saved_traces_objects(dev->tracer, fmsg);
 }
 
+static void mlx5_fw_reporter_err_work(struct work_struct *work)
+{
+	struct mlx5_fw_reporter_ctx fw_reporter_ctx;
+	struct mlx5_core_health *health;
+
+	health = container_of(work, struct mlx5_core_health, report_work);
+
+	if (IS_ERR_OR_NULL(health->fw_reporter))
+		return;
+
+	fw_reporter_ctx.err_synd = health->synd;
+	fw_reporter_ctx.miss_counter = health->miss_counter;
+	if (fw_reporter_ctx.err_synd) {
+		devlink_health_report(health->fw_reporter,
+				      "FW syndrome reported", &fw_reporter_ctx);
+		return;
+	}
+	if (fw_reporter_ctx.miss_counter)
+		devlink_health_report(health->fw_reporter,
+				      "FW miss counter reported",
+				      &fw_reporter_ctx);
+}
+
 static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
 		.name = "fw",
 		.diagnose = mlx5_fw_reporter_diagnose,
@@ -554,8 +577,10 @@  static void poll_health(struct timer_list *t)
 {
 	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
 	struct mlx5_core_health *health = &dev->priv.health;
+	struct health_buffer __iomem *h = health->health;
 	u32 fatal_error;
 	u32 count;
+	u8 prev_synd;
 
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
@@ -570,8 +595,14 @@  static void poll_health(struct timer_list *t)
 	if (health->miss_counter == MAX_MISSES) {
 		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
 		mlx5_print_health_info(dev);
+		queue_work(health->wq, &health->report_work);
 	}
 
+	prev_synd = health->synd;
+	health->synd = ioread8(&h->synd);
+	if (health->synd && health->synd != prev_synd)
+		queue_work(health->wq, &health->report_work);
+
 	fatal_error = check_fatal_sensors(dev);
 
 	if (fatal_error && !health->fatal_error) {
@@ -621,6 +652,7 @@  void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 	spin_lock_irqsave(&health->wq_lock, flags);
 	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);
 }
 
@@ -658,6 +690,7 @@  int mlx5_health_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 	spin_lock_init(&health->wq_lock);
 	INIT_WORK(&health->work, health_care);
+	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
 	health->crdump = NULL;
 	health->info_buf = kmalloc(HEALTH_INFO_MAX_BUFF, GFP_KERNEL);
 	if (!health->info_buf)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ebda70984601..604079b4706c 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -437,12 +437,14 @@  struct mlx5_core_health {
 	struct timer_list		timer;
 	u32				prev;
 	int				miss_counter;
+	u8				synd;
 	u32				fatal_error;
 	/* wq spinlock to synchronize draining */
 	spinlock_t			wq_lock;
 	struct workqueue_struct	       *wq;
 	unsigned long			flags;
 	struct work_struct		work;
+	struct work_struct		report_work;
 	struct delayed_work		recover_work;
 	struct mlx5_fw_crdump	       *crdump;
 	char			       *info_buf;