From 10cb940429c20238c7aa0a8f0e2b183c553571dc Mon Sep 17 00:00:00 2001 From: Praveen Kumar Kannoju Date: Wed, 8 May 2024 19:06:17 +0530 Subject: [PATCH] net/sched: adjust device watchdog timer to detect stopped queue at right time [ Upstream commit 33fb988b67050d9bb512f77f08453fa00088943c ] Applications are sensitive to long network latency, particularly heartbeat monitoring ones. Longer the tx timeout recovery higher the risk with such applications on a production machines. This patch remedies, yet honoring device set tx timeout. Modify watchdog next timeout to be shorter than the device specified. Compute the next timeout be equal to device watchdog timeout less the how long ago queue stop had been done. At next watchdog timeout tx timeout handler is called into if still in stopped state. Either called or not called, restore the watchdog timeout back to device specified. Signed-off-by: Praveen Kumar Kannoju Link: https://lore.kernel.org/r/20240508133617.4424-1-praveen.kannoju@oracle.com Signed-off-by: Jakub Kicinski Stable-dep-of: 95ecba62e2fd ("net: fix races in netdev_tx_sent_queue()/dev_watchdog()") Signed-off-by: Sasha Levin --- net/sched/sch_generic.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6ab9359c1706..7f0c8df7b63e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -505,19 +505,22 @@ static void dev_watchdog(struct timer_list *t) unsigned int timedout_ms = 0; unsigned int i; unsigned long trans_start; + unsigned long oldest_start = jiffies; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); trans_start = READ_ONCE(txq->trans_start); - if (netif_xmit_stopped(txq) && - time_after(jiffies, (trans_start + - dev->watchdog_timeo))) { + if (!netif_xmit_stopped(txq)) + continue; + if (time_after(jiffies, trans_start + dev->watchdog_timeo)) { timedout_ms = jiffies_to_msecs(jiffies - trans_start); atomic_long_inc(&txq->trans_timeout); break; } + if (time_after(oldest_start, trans_start)) + oldest_start = trans_start; } if (unlikely(timedout_ms)) { @@ -530,7 +533,7 @@ static void dev_watchdog(struct timer_list *t) netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, - round_jiffies(jiffies + + round_jiffies(oldest_start + dev->watchdog_timeo))) release = false; }