diff options
author | Maciej Fijalkowski <maciej.fijalkowski@intel.com> | 2022-04-06 18:58:04 +0300 |
---|---|---|
committer | Daniel Borkmann <daniel@iogearbox.net> | 2022-04-08 00:09:08 +0300 |
commit | 8de8b71b787f38983d414d2dba169a3bfefa668a (patch) | |
tree | 3cbe894a066543b30f97213283d8402616d3b23c | |
parent | ec4eb8a86ade4d22633e1da2a7d85a846b7d1798 (diff) | |
download | linux-8de8b71b787f38983d414d2dba169a3bfefa668a.tar.xz |
xsk: Fix l2fwd for copy mode + busy poll combo
While checking AF_XDP copy mode combined with busy poll, strange
results were observed. rxdrop and txonly scenarios worked fine, but
l2fwd broke immediately.
After a deeper look, it turned out that for l2fwd, Tx side was exiting
early due to xsk_no_wakeup() returning true and in the end
xsk_generic_xmit() was never called. Note that AF_XDP Tx in copy mode
is syscall steered, so the current behavior is broken.
Txonly scenario only worked due to the fact that
sk_mark_napi_id_once_xdp() was never called - since Rx side is not in
the picture for this case and mentioned function is called in
xsk_rcv_check(), sk::sk_napi_id was never set, which in turn meant that
xsk_no_wakeup() was returning false (see the sk->sk_napi_id >=
MIN_NAPI_ID check in there).
To fix this, prefer busy poll in xsk_sendmsg() only when zero copy is
enabled on a given AF_XDP socket. By doing so, busy poll in copy mode
would not exit early on Tx side and eventually xsk_generic_xmit() will
be called.
Fixes: a0731952d9cd ("xsk: Add busy-poll support for {recv,send}msg()")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220406155804.434493-1-maciej.fijalkowski@intel.com
-rw-r--r-- | net/xdp/xsk.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2c34caee0fd1..7d3a00cb24ec 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -639,7 +639,7 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - if (xsk_no_wakeup(sk)) + if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; |