Commit e4d008d4 authored Dec 01, 2023 by Yewon Choi Committed by Daniel Borkmann Dec 05, 2023

xsk: Skip polling event check for unbound socket



In xsk_poll(), checking available events and setting mask bits should
be executed only when a socket has been bound. Setting mask bits for
unbound socket is meaningless.

Currently, it checks events even when xsk_check_common() failed.
To prevent this, we move goto location (skip_tx) after that checking.

Fixes: 1596dae2 ("xsk: check IFF_UP earlier in Tx path")
Signed-off-by: Yewon Choi <woni9911@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20231201061048.GA1510@libra05

parent dfce9cb3

net/xdp/xsk.c

+2 −3

Original line number	Diff line number	Diff line
		@@ -947,7 +947,7 @@ static __poll_t xsk_poll(struct file file, struct socket sock,

		rcu_read_lock();
		if (xsk_check_common(xs))
		goto skip_tx;
		goto out;

		pool = xs->pool;

		@@ -959,12 +959,11 @@ static __poll_t xsk_poll(struct file file, struct socket sock,
		xsk_generic_xmit(sk);
		}

		skip_tx:
		if (xs->rx && !xskq_prod_is_empty(xs->rx))
		mask \|= EPOLLIN \| EPOLLRDNORM;
		if (xs->tx && xsk_tx_writeable(xs))
		mask \|= EPOLLOUT \| EPOLLWRNORM;

		out:
		rcu_read_unlock();
		return mask;
		}