From cbff1538328ab180c65cc18c936e598c927cd88b Mon Sep 17 00:00:00 2001 Message-Id: In-Reply-To: <5b5a156f9808b1acf1205606e03da117214549ea.1601675151.git.zanussi@kernel.org> References: <5b5a156f9808b1acf1205606e03da117214549ea.1601675151.git.zanussi@kernel.org> From: Sebastian Andrzej Siewior Date: Wed, 30 Mar 2016 13:36:29 +0200 Subject: [PATCH 200/333] net: dev: always take qdisc's busylock in __dev_xmit_skb() Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.148-rt64.tar.xz The root-lock is dropped before dev_hard_start_xmit() is invoked and after setting the __QDISC___STATE_RUNNING bit. If this task is now pushed away by a task with a higher priority then the task with the higher priority won't be able to submit packets to the NIC directly instead they will be enqueued into the Qdisc. The NIC will remain idle until the task(s) with higher priority leave the CPU and the task with lower priority gets back and finishes the job. If we take always the busylock we ensure that the RT task can boost the low-prio task and submit the packet. Signed-off-by: Sebastian Andrzej Siewior --- net/core/dev.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 91040933006b..9b15c663b3f8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3464,7 +3464,11 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. */ +#ifdef CONFIG_PREEMPT_RT_FULL + contended = true; +#else contended = qdisc_is_running(q); +#endif if (unlikely(contended)) spin_lock(&q->busylock); -- 2.17.1