netdev - [net-next 11/15] net/mlx5e: Move all TX timeout logic to be under state lock

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: <20180328004249.3796-12-saeedm@mellanox.com>
Date:   Tue, 27 Mar 2018 17:42:45 -0700
From:   Saeed Mahameed <saeedm@...lanox.com>
To:     "David S. Miller" <davem@...emloft.net>
Cc:     netdev@...r.kernel.org, Eran Ben Elisha <eranbe@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: [net-next 11/15] net/mlx5e: Move all TX timeout logic to be under state lock

From: Eran Ben Elisha <eranbe@...lanox.com>

Driver callback for handling TX timeout should access some internal
resources (SQ, CQ) in order to decide if the tx timeout work should be
scheduled.  These resources might be unavailable if channels are closed
in parallel (ifdown for example).

The state lock is the mechanism to protect from such races.
Move all TX timeout logic to be in the work under a state lock.

In addition, Move the work from the global WQ to mlx5e WQ to make sure
this work is flushed when device is detached..

Also, move the mlx5e_tx_timeout_work code to be next to the TX timeout
NDO for better code locality.

Fixes: 3947ca185999 ("net/mlx5e: Implement ndo_tx_timeout callback")
Signed-off-by: Eran Ben Elisha <eranbe@...lanox.com>
Signed-off-by: Saeed Mahameed <saeedm@...lanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 61 +++++++++++++----------
 1 file changed, 34 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5d8eb0a9c0f0..e0b75f52d556 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -177,26 +177,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
-static void mlx5e_tx_timeout_work(struct work_struct *work)
-{
-	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
-					       tx_timeout_work);
-	int err;
-
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
-	mlx5e_close_locked(priv->netdev);
-	err = mlx5e_open_locked(priv->netdev);
-	if (err)
-		netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
-			   err);
-unlock:
-	mutex_unlock(&priv->state_lock);
-	rtnl_unlock();
-}
-
 void mlx5e_update_stats(struct mlx5e_priv *priv)
 {
 	int i;
@@ -3658,13 +3638,19 @@ static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
 	return true;
 }
 
-static void mlx5e_tx_timeout(struct net_device *dev)
+static void mlx5e_tx_timeout_work(struct work_struct *work)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       tx_timeout_work);
+	struct net_device *dev = priv->netdev;
 	bool reopen_channels = false;
-	int i;
+	int i, err;
 
-	netdev_err(dev, "TX timeout detected\n");
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
 
 	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
 		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
@@ -3672,7 +3658,9 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
-		netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
+
+		netdev_err(dev,
+			   "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
 			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
 			   jiffies_to_usecs(jiffies - dev_queue->trans_start));
 
@@ -3685,8 +3673,27 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 		}
 	}
 
-	if (reopen_channels && test_bit(MLX5E_STATE_OPENED, &priv->state))
-		schedule_work(&priv->tx_timeout_work);
+	if (!reopen_channels)
+		goto unlock;
+
+	mlx5e_close_locked(dev);
+	err = mlx5e_open_locked(dev);
+	if (err)
+		netdev_err(priv->netdev,
+			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   err);
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+}
+
+static void mlx5e_tx_timeout(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	netdev_err(dev, "TX timeout detected\n");
+	queue_work(priv->wq, &priv->tx_timeout_work);
 }
 
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
-- 
2.14.3