Commit 192fe573 authored Dec 17, 2021 by Magnus Karlsson Committed by Greg Kroah-Hartman Dec 22, 2021

Revert "xsk: Do not sleep in poll() when need_wakeup set"



commit 0706a78f31c4217ca144f630063ec9561a21548d upstream.

This reverts commit bd0687c18e635b63233dc87f38058cd728802ab4.

This patch causes a Tx only workload to go to sleep even when it does
not have to, leading to misserable performance in skb mode. It fixed
one rare problem but created a much worse one, so this need to be
reverted while I try to craft a proper solution to the original
problem.

Fixes: bd0687c18e63 ("xsk: Do not sleep in poll() when need_wakeup set")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211217145646.26449-1-magnus.karlsson@gmail.com


Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

parent e281b719

net/xdp/xsk.c

+2 −2

Original line number	Diff line number	Diff line
		@@ -434,6 +434,8 @@ static __poll_t xsk_poll(struct file file, struct socket sock,
		struct xdp_sock *xs = xdp_sk(sk);
		struct xdp_umem *umem;

		sock_poll_wait(file, sock, wait);

		if (unlikely(!xsk_is_bound(xs)))
		return mask;

		@@ -445,8 +447,6 @@ static __poll_t xsk_poll(struct file file, struct socket sock,
		else
		/* Poll needs to drive Tx also in copy mode */
		__xsk_sendmsg(sk);
		} else {
		sock_poll_wait(file, sock, wait);
		}

		if (xs->rx && !xskq_empty_desc(xs->rx))