Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 61a5ff15 authored by Amos Kong's avatar Amos Kong Committed by David S. Miller
Browse files

tun: do not put self in waitq if doing a nonblock read 



Perf shows a relatively high rate (about 8%) race in
spin_lock_irqsave() when doing netperf between external host and
guest. It's mainly becuase the lock contention between the
tun_do_read() and tun_xmit_skb(), so this patch do not put self into
waitqueue to reduce this kind of race. After this patch, it drops to
4%.

Signed-off-by: default avatarJason Wang <jasowang@redhat.com>
Signed-off-by: default avatarAmos Kong <akong@redhat.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 6f7c156c

drivers/net/tun.c

+4 −2
Original line number Original line Diff line number Diff line
@@ -817,6 +817,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, 




	tun_debug(KERN_INFO, tun, "tun_chr_read\n");

	tun_debug(KERN_INFO, tun, "tun_chr_read\n");





	if (unlikely(!noblock))

		add_wait_queue(&tun->wq.wait, &wait);

		add_wait_queue(&tun->wq.wait, &wait);

	while (len) {

	while (len) {

		current->state = TASK_INTERRUPTIBLE;

		current->state = TASK_INTERRUPTIBLE;
@@ -848,6 +849,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, 
	}

	}





	current->state = TASK_RUNNING;

	current->state = TASK_RUNNING;

	if (unlikely(!noblock))

		remove_wait_queue(&tun->wq.wait, &wait);

		remove_wait_queue(&tun->wq.wait, &wait);





	return ret;

	return ret;