mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-01-17 02:15:57 +00:00
net: fix races in netdev_tx_sent_queue()/dev_watchdog()
Some workloads hit the infamous dev_watchdog() message: "NETDEV WATCHDOG: eth0 (xxxx): transmit queue XX timed out" It seems possible to hit this even for perfectly normal BQL enabled drivers: 1) Assume a TX queue was idle for more than dev->watchdog_timeo (5 seconds unless changed by the driver) 2) Assume a big packet is sent, exceeding current BQL limit. 3) Driver ndo_start_xmit() puts the packet in TX ring, and netdev_tx_sent_queue() is called. 4) QUEUE_STATE_STACK_XOFF could be set from netdev_tx_sent_queue() before txq->trans_start has been written. 5) txq->trans_start is written later, from netdev_start_xmit() if (rc == NETDEV_TX_OK) txq_trans_update(txq) dev_watchdog() running on another cpu could read the old txq->trans_start, and then see QUEUE_STATE_STACK_XOFF, because 5) did not happen yet. To solve the issue, write txq->trans_start right before one XOFF bit is set : - _QUEUE_STATE_DRV_XOFF from netif_tx_stop_queue() - __QUEUE_STATE_STACK_XOFF from netdev_tx_sent_queue() From dev_watchdog(), we have to read txq->state before txq->trans_start. Add memory barriers to enforce correct ordering. In the future, we could avoid writing over txq->trans_start for normal operations, and rename this field to txq->xoff_start_time. Fixes: bec251bc8b6a ("net: no longer stop all TX queues in dev_watchdog()") Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://patch.msgid.link/20241015194118.3951657-1-edumazet@google.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This commit is contained in:
parent
47dd5447ca
commit
95ecba62e2
@ -3325,6 +3325,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev)
|
||||
|
||||
static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
|
||||
{
|
||||
/* Paired with READ_ONCE() from dev_watchdog() */
|
||||
WRITE_ONCE(dev_queue->trans_start, jiffies);
|
||||
|
||||
/* This barrier is paired with smp_mb() from dev_watchdog() */
|
||||
smp_mb__before_atomic();
|
||||
|
||||
/* Must be an atomic op see netif_txq_try_stop() */
|
||||
set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
|
||||
}
|
||||
@ -3451,6 +3457,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
|
||||
if (likely(dql_avail(&dev_queue->dql) >= 0))
|
||||
return;
|
||||
|
||||
/* Paired with READ_ONCE() from dev_watchdog() */
|
||||
WRITE_ONCE(dev_queue->trans_start, jiffies);
|
||||
|
||||
/* This barrier is paired with smp_mb() from dev_watchdog() */
|
||||
smp_mb__before_atomic();
|
||||
|
||||
set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
|
||||
|
||||
/*
|
||||
|
@ -512,9 +512,15 @@ static void dev_watchdog(struct timer_list *t)
|
||||
struct netdev_queue *txq;
|
||||
|
||||
txq = netdev_get_tx_queue(dev, i);
|
||||
trans_start = READ_ONCE(txq->trans_start);
|
||||
if (!netif_xmit_stopped(txq))
|
||||
continue;
|
||||
|
||||
/* Paired with WRITE_ONCE() + smp_mb...() in
|
||||
* netdev_tx_sent_queue() and netif_tx_stop_queue().
|
||||
*/
|
||||
smp_mb();
|
||||
trans_start = READ_ONCE(txq->trans_start);
|
||||
|
||||
if (time_after(jiffies, trans_start + dev->watchdog_timeo)) {
|
||||
timedout_ms = jiffies_to_msecs(jiffies - trans_start);
|
||||
atomic_long_inc(&txq->trans_timeout);
|
||||
|
Loading…
x
Reference in New Issue
Block a user