netdev - [net 2/3] net/mlx5: Cancel delayed recovery work when unloading the driver

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20170630071229.20357-3-saeedm@mellanox.com>
Date:   Fri, 30 Jun 2017 10:12:28 +0300
From:   Saeed Mahameed <saeedm@...lanox.com>
To:     "David S. Miller" <davem@...emloft.net>
Cc:     netdev@...r.kernel.org, Mohamad Haj Yahia <mohamad@...lanox.com>,
        Moshe Shemesh <moshe@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: [net 2/3] net/mlx5: Cancel delayed recovery work when unloading the driver

From: Mohamad Haj Yahia <mohamad@...lanox.com>

Draining the health workqueue will ignore future health works including
the one that report hardware failure and thus we can't enter error state
Instead cancel the recovery flow and make sure only recovery flow won't
be scheduled.

Fixes: 5e44fca50470 ('net/mlx5: Only cancel recovery work when cleaning up device')
Signed-off-by: Mohamad Haj Yahia <mohamad@...lanox.com>
Signed-off-by: Moshe Shemesh <moshe@...lanox.com>
Signed-off-by: Saeed Mahameed <saeedm@...lanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 15 ++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c   |  2 +-
 include/linux/mlx5/driver.h                      |  1 +
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index f27f84ffbc85..8a8b5f0e497c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -67,6 +67,7 @@ enum {
 
 enum {
 	MLX5_DROP_NEW_HEALTH_WORK,
+	MLX5_DROP_NEW_RECOVERY_WORK,
 };
 
 static u8 get_nic_state(struct mlx5_core_dev *dev)
@@ -193,7 +194,7 @@ static void health_care(struct work_struct *work)
 	mlx5_handle_bad_state(dev);
 
 	spin_lock(&health->wq_lock);
-	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+	if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
 		schedule_delayed_work(&health->recover_work, recover_delay);
 	else
 		dev_err(&dev->pdev->dev,
@@ -313,6 +314,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	init_timer(&health->timer);
 	health->sick = 0;
 	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;
 
@@ -335,11 +337,22 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 
 	spin_lock(&health->wq_lock);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	spin_unlock(&health->wq_lock);
 	cancel_delayed_work_sync(&health->recover_work);
 	cancel_work_sync(&health->work);
 }
 
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	spin_lock(&health->wq_lock);
+	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+	spin_unlock(&health->wq_lock);
+	cancel_delayed_work_sync(&dev->priv.health.recover_work);
+}
+
 void mlx5_health_cleanup(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 fd47b5134841..524c16f72e83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1228,7 +1228,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	int err = 0;
 
 	if (cleanup)
-		mlx5_drain_health_wq(dev);
+		mlx5_drain_health_recovery(dev);
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 93273d9ea4d1..ba260330ce5e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -925,6 +925,7 @@ 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);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
+void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);
 int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			struct mlx5_buf *buf, int node);
 int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
-- 
2.11.0