vsock: avoid timeout for non-blocking accept() with empty backlog
Subsystems (4)
PATCH v2 1/1 vsock: avoid timeout for non-blocking accept() with empty backlog
A common pattern in epoll network servers is to eagerly accept all pending connections from the non-blocking listening socket after epoll_wait indicates the socket is ready by calling accept in a loop until EAGAIN is returned indicating that the backlog is empty.
Scheduling a timeout for a non-blocking accept with an empty backlog meant AF_VSOCK sockets used by epoll network servers incurred hundreds of microseconds of additional latency per accept loop compared to AF_INET or AF_UNIX sockets.
---
Patch v2 with feedback from Stefano Garzarella and Bobby Eshleman:
- Move prepare_to_wait before release_sock to match previous behaviour.
- Simplify not connected case.
This fixes the observed issue for me:
1. With loopback vsock on the host running Linux v6.19.10 built with config-6.17.0-19-generic from Ubuntu 24.04 and make olddefconfig.
2. With Firecracker guests with current torvalds/master, v6.19.10, and amazonlinux/microvm-kernel-6.1.166-24.303.amzn2023 used in Firecracker CI and examples. (Firecracker guest vsocks are unix sockets on the host side so this fix works there with just a fixed guest kernel.)
I struggled to build a generic 6.1.166 kernel that worked as a Firecracker guest but the patch applies (conflict due to change of flags to arg->flags in surrounding context) so I believe it should work for generic v6.1.166 kernel.
Alternatively a minimal version of this fix is to just wrap the schedule_timeout in an if (timeout != 0) but that leaves an unnecessary additional lock_sock call.
There are ftrace's and reproduction tools at:
https://github.com/lrowe/linux-vsock-accept-timeout-investigation
--- net/vmw_vsock/af_vsock.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-)
net/vmw_vsock/af_vsock.c +6 -9
@@ -1864,10 +1864,10 @@ static int vsock_accept(struct socket *sock, struct socket *newsock,* created upon connection establishment. */ timeout =sock_rcvtimeo (listener, arg->flags &O_NONBLOCK ); -prepare_to_wait (sk_sleep (listener), &wait,TASK_INTERRUPTIBLE );while ((connected =vsock_dequeue_accept (listener)) ==NULL && - listener->sk_err ==0 ) { + listener->sk_err ==0 && timeout !=0 ) { +prepare_to_wait (sk_sleep (listener), &wait,TASK_INTERRUPTIBLE );release_sock (listener); timeout =schedule_timeout (timeout);finish_wait (sk_sleep (listener), &wait);
@@ -1876,17 +1876,14 @@ static int vsock_accept(struct socket *sock, struct socket *newsock,if (signal_pending (current)) { err =sock_intr_errno (timeout); goto out; - }else if (timeout ==0 ) { - err = -EAGAIN ; - goto out; } - -prepare_to_wait (sk_sleep (listener), &wait,TASK_INTERRUPTIBLE ); } -finish_wait (sk_sleep (listener), &wait); -if (listener->sk_err) +if (listener->sk_err) { err = -listener->sk_err; + }else if (!connected) { + err = -EAGAIN ; + }if (connected) {sk_acceptq_removed (listener);
base-commit: f35340f2d653f1003602878403c901396ab03c17
Signature · 1 line
2.43.0
Quoted 12 lines · Laurence Rowe
A common pattern in epoll network servers is to eagerly accept all pending connections from the non-blocking listening socket after
epoll_waitindicates the socket is ready by calling accept in a loop until EAGAIN is returned indicating that the backlog is empty.Scheduling a timeout for a non-blocking accept with an empty backlog meant
AF_VSOCKsockets used by epoll network servers incurred hundreds of microseconds of additional latency per accept loop compared toAF_INETorAF_UNIXsockets.Signed-off-by Laurence Rowe <[email protected]>Reviewed-by Bobby Eshleman <[email protected]>
Quoted 7 lines
---
Patch v2 with feedback from Stefano Garzarella and Bobby Eshleman:
- Move
prepare_to_waitbeforerelease_sockto match previous behaviour.- Simplify not connected case.
Thanks for addressing them, now LGTM!
This patch was applied to netdev/net-next.git (main) by Jakub Kicinski <[email protected]>:
Hello:
This patch was applied to netdev/net-next.git (main) by Jakub Kicinski <[email protected]>:
Quoted 11 lines · On Thu, 2 Apr 2026 13:49:18 -0700 you wrote:
A common pattern in epoll network servers is to eagerly accept all pending connections from the non-blocking listening socket after
epoll_waitindicates the socket is ready by calling accept in a loop until EAGAIN is returned indicating that the backlog is empty.Scheduling a timeout for a non-blocking accept with an empty backlog meant
AF_VSOCKsockets used by epoll network servers incurred hundreds of microseconds of additional latency per accept loop compared toAF_INETorAF_UNIXsockets.[...]
Here is the summary with links:
- [net-next,v2] vsock: avoid timeout for non-blocking accept() with empty backlog
https://git.kernel.org/netdev/net-next/c/98f28d8d6e5a
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html