diff mbox series

[net,1/2] net/mlx4_en: Avoid scheduling restart task if it is already running

Message ID 20201209130339.21795-2-tariqt@nvidia.com (mailing list archive)
State Accepted
Delegated to: Netdev Maintainers
Headers show
Series mlx4_en fixes | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net
netdev/subject_prefix success Link
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 81 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 89 exceeds 80 columns WARNING: line length of 91 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Tariq Toukan Dec. 9, 2020, 1:03 p.m. UTC 
From: Moshe Shemesh <moshe@mellanox.com>

Add restarting state flag to avoid scheduling another restart task while
such task is already running. Change task name from watchdog_task to
restart_task to better fit the task role.

Fixes: 1e338db56e5a ("mlx4_en: Fix a race at restart task")
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx4/en_netdev.c    | 20 ++++++++++++-------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h  |  7 ++++++-
 2 files changed, 19 insertions(+), 8 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 106513f772c3..1a2b0bd64aa9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1378,8 +1378,10 @@  static void mlx4_en_tx_timeout(struct net_device *dev, unsigned int txqueue)
 		tx_ring->cons, tx_ring->prod);
 
 	priv->port_stats.tx_timeout++;
-	en_dbg(DRV, priv, "Scheduling watchdog\n");
-	queue_work(mdev->workqueue, &priv->watchdog_task);
+	if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state)) {
+		en_dbg(DRV, priv, "Scheduling port restart\n");
+		queue_work(mdev->workqueue, &priv->restart_task);
+	}
 }
 
 
@@ -1829,6 +1831,7 @@  int mlx4_en_start_port(struct net_device *dev)
 		local_bh_enable();
 	}
 
+	clear_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state);
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
 
@@ -1999,7 +2002,7 @@  void mlx4_en_stop_port(struct net_device *dev, int detach)
 static void mlx4_en_restart(struct work_struct *work)
 {
 	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
-						 watchdog_task);
+						 restart_task);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct net_device *dev = priv->dev;
 
@@ -2377,7 +2380,7 @@  static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 	if (netif_running(dev)) {
 		mutex_lock(&mdev->state_lock);
 		if (!mdev->device_up) {
-			/* NIC is probably restarting - let watchdog task reset
+			/* NIC is probably restarting - let restart task reset
 			 * the port */
 			en_dbg(DRV, priv, "Change MTU called with card down!?\n");
 		} else {
@@ -2386,7 +2389,9 @@  static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 			if (err) {
 				en_err(priv, "Failed restarting port:%d\n",
 					 priv->port);
-				queue_work(mdev->workqueue, &priv->watchdog_task);
+				if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING,
+						      &priv->state))
+					queue_work(mdev->workqueue, &priv->restart_task);
 			}
 		}
 		mutex_unlock(&mdev->state_lock);
@@ -2792,7 +2797,8 @@  static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 		if (err) {
 			en_err(priv, "Failed starting port %d for XDP change\n",
 			       priv->port);
-			queue_work(mdev->workqueue, &priv->watchdog_task);
+			if (!test_and_set_bit(MLX4_EN_STATE_FLAG_RESTARTING, &priv->state))
+				queue_work(mdev->workqueue, &priv->restart_task);
 		}
 	}
 
@@ -3165,7 +3171,7 @@  int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev);
 	spin_lock_init(&priv->stats_lock);
 	INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode);
-	INIT_WORK(&priv->watchdog_task, mlx4_en_restart);
+	INIT_WORK(&priv->restart_task, mlx4_en_restart);
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
 	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
 	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index a46efe37cfa9..fd9535bde1b8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -530,6 +530,10 @@  struct mlx4_en_stats_bitmap {
 	struct mutex mutex; /* for mutual access to stats bitmap */
 };
 
+enum {
+	MLX4_EN_STATE_FLAG_RESTARTING,
+};
+
 struct mlx4_en_priv {
 	struct mlx4_en_dev *mdev;
 	struct mlx4_en_port_profile *prof;
@@ -595,7 +599,7 @@  struct mlx4_en_priv {
 	struct mlx4_en_cq *rx_cq[MAX_RX_RINGS];
 	struct mlx4_qp drop_qp;
 	struct work_struct rx_mode_task;
-	struct work_struct watchdog_task;
+	struct work_struct restart_task;
 	struct work_struct linkstate_task;
 	struct delayed_work stats_task;
 	struct delayed_work service_task;
@@ -641,6 +645,7 @@  struct mlx4_en_priv {
 	u32 pflags;
 	u8 rss_key[MLX4_EN_RSS_KEY_SIZE];
 	u8 rss_hash_fn;
+	unsigned long state;
 };
 
 enum mlx4_en_wol {