| Message ID | 20241202155620.1719-1-ffmancera@riseup.net (mailing list archive) |
|---|---|
| State | Accepted |
| Commit | 3d501f562f63b290351169e3e9931ffe3d57b2ae |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | [net] Revert "udp: avoid calling sock_def_readable() if possible" | expand |
On Mon, Dec 2, 2024 at 4:56 PM Fernando Fernandez Mancera <ffmancera@riseup.net> wrote: > > This reverts commit 612b1c0dec5bc7367f90fc508448b8d0d7c05414. On a > scenario with multiple threads blocking on a recvfrom(), we need to call > sock_def_readable() on every __udp_enqueue_schedule_skb() otherwise the > threads won't be woken up as __skb_wait_for_more_packets() is using > prepare_to_wait_exclusive(). > > Link: https://bugzilla.redhat.com/2308477 > Fixes: 612b1c0dec5b ("udp: avoid calling sock_def_readable() if possible") > Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net> Reviewed-by: Eric Dumazet <edumazet@google.com>
Hello: This patch was applied to netdev/net.git (main) by Jakub Kicinski <kuba@kernel.org>: On Mon, 2 Dec 2024 15:56:08 +0000 you wrote: > This reverts commit 612b1c0dec5bc7367f90fc508448b8d0d7c05414. On a > scenario with multiple threads blocking on a recvfrom(), we need to call > sock_def_readable() on every __udp_enqueue_schedule_skb() otherwise the > threads won't be woken up as __skb_wait_for_more_packets() is using > prepare_to_wait_exclusive(). > > Link: https://bugzilla.redhat.com/2308477 > Fixes: 612b1c0dec5b ("udp: avoid calling sock_def_readable() if possible") > Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net> > > [...] Here is the summary with links: - [net] Revert "udp: avoid calling sock_def_readable() if possible" https://git.kernel.org/netdev/net/c/3d501f562f63 You are awesome, thank you!
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6a01905d379f..e8953e88efef 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1674,7 +1674,6 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) struct sk_buff_head *list = &sk->sk_receive_queue; int rmem, err = -ENOMEM; spinlock_t *busy = NULL; - bool becomes_readable; int size, rcvbuf; /* Immediately drop when the receive queue is full. @@ -1715,19 +1714,12 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ sock_skb_set_dropcount(sk, skb); - becomes_readable = skb_queue_empty(list); __skb_queue_tail(list, skb); spin_unlock(&list->lock); - if (!sock_flag(sk, SOCK_DEAD)) { - if (becomes_readable || - sk->sk_data_ready != sock_def_readable || - READ_ONCE(sk->sk_peek_off) >= 0) - INDIRECT_CALL_1(sk->sk_data_ready, - sock_def_readable, sk); - else - sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); - } + if (!sock_flag(sk, SOCK_DEAD)) + INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk); + busylock_release(busy); return 0;
This reverts commit 612b1c0dec5bc7367f90fc508448b8d0d7c05414. On a scenario with multiple threads blocking on a recvfrom(), we need to call sock_def_readable() on every __udp_enqueue_schedule_skb() otherwise the threads won't be woken up as __skb_wait_for_more_packets() is using prepare_to_wait_exclusive(). Link: https://bugzilla.redhat.com/2308477 Fixes: 612b1c0dec5b ("udp: avoid calling sock_def_readable() if possible") Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net> --- net/ipv4/udp.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-)