From: Magnus Karlsson <magnus.karlsson@xxxxxxxxx> commit bd0687c18e635b63233dc87f38058cd728802ab4 upstream. Do not sleep in poll() when the need_wakeup flag is set. When this flag is set, the application needs to explicitly wake up the driver with a syscall (poll, recvmsg, sendmsg, etc.) to guarantee that Rx and/or Tx processing will be processed promptly. But the current code in poll(), sleeps first then wakes up the driver. This means that no driver processing will occur (baring any interrupts) until the timeout has expired. Fix this by checking the need_wakeup flag first and if set, wake the driver and return to the application. Only if need_wakeup is not set should the process sleep if there is a timeout set in the poll() call. Fixes: 77cd0d7b3f25 ("xsk: add support for need_wakeup flag in AF_XDP rings") Reported-by: Keith Wiles <keith.wiles@xxxxxxxxx> Signed-off-by: Magnus Karlsson <magnus.karlsson@xxxxxxxxx> Signed-off-by: Daniel Borkmann <daniel@xxxxxxxxxxxxx> Acked-by: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx> Link: https://lore.kernel.org/bpf/20211214102607.7677-1-magnus.karlsson@xxxxxxxxx Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- net/xdp/xsk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -434,8 +434,6 @@ static __poll_t xsk_poll(struct file *fi 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; @@ -447,6 +445,8 @@ static __poll_t xsk_poll(struct file *fi 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))