[PATCH net-next v4 3/4] veth: add tx_timeout watchdog as BQL safety net

[hawk]

From: Jesper Dangaard Brouer <hawk@xxxxxxxxxx>

With the introduction of BQL (Byte Queue Limits) for veth, there are
now two independent mechanisms that can stop a transmit queue:

 - DRV_XOFF: set by netif_tx_stop_queue() when the ptr_ring is full
 - STACK_XOFF: set by BQL when the byte-in-flight limit is reached

If either mechanism stalls without a corresponding wake/completion,
the queue stops permanently. Enable the net device watchdog timer and
implement ndo_tx_timeout as a failsafe recovery.

The timeout handler resets BQL state (clearing STACK_XOFF) and wakes
the queue (clearing DRV_XOFF), covering both stop mechanisms. The
watchdog fires after 16 seconds, which accommodates worst-case NAPI
processing (budget=64 packets x 250ms per-packet consumer delay)
without false positives under normal backpressure.

Signed-off-by: Jesper Dangaard Brouer <hawk@xxxxxxxxxx>
Tested-by: Jonas Köppeler <j.koeppeler@xxxxxxxxxxxx>
---
 drivers/net/veth.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 3de25ba34a90..9d7b085c9548 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1431,6 +1431,22 @@ static int veth_set_channels(struct net_device *dev,
 	goto out;
 }
 
+static void veth_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct netdev_queue *txq = netdev_get_tx_queue(dev, txqueue);
+
+	netdev_err(dev,
+		   "veth backpressure(0x%lX) stalled(n:%ld) TXQ(%u) re-enable\n",
+		   txq->state, atomic_long_read(&txq->trans_timeout), txqueue);
+
+	/* Cannot call netdev_tx_reset_queue(): dql_reset() races with
+	 * peer NAPI calling dql_completed() concurrently.
+	 * Just clear the stop bits; the qdisc will re-stop if still stuck.
+	 */
+	clear_bit(__QUEUE_STATE_STACK_XOFF, &txq->state);
+	netif_tx_wake_queue(txq);
+}
+
 static int veth_open(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
@@ -1769,6 +1785,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_bpf		= veth_xdp,
 	.ndo_xdp_xmit		= veth_ndo_xdp_xmit,
 	.ndo_get_peer_dev	= veth_peer_dev,
+	.ndo_tx_timeout		= veth_tx_timeout,
 };
 
 static const struct xdp_metadata_ops veth_xdp_metadata_ops = {
@@ -1808,6 +1825,7 @@ static void veth_setup(struct net_device *dev)
 	dev->priv_destructor = veth_dev_free;
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	dev->max_mtu = ETH_MAX_MTU;
+	dev->watchdog_timeo = msecs_to_jiffies(16000);
 
 	dev->hw_features = VETH_FEATURES;
 	dev->hw_enc_features = VETH_FEATURES;
-- 
2.43.0