When application runs in zero copy busy poll mode and does not receive a
single packet but only sends them, it is currently impossible to get
into napi_busy_loop() as napi_id is only marked on Rx side in
xsk_rcv_check(). In there, napi_id is being taken from xdp_rxq_info
carried by xdp_buff. From Tx perspective, we do not have access to it.
What we have handy is the xsk pool.
Xsk pool works on a pool of internal xdp_buff wrappers called
xdp_buff_xsk. AF_XDP ZC enabled drivers call xp_set_rxq_info() so each
of xdp_buff_xsk has a valid pointer to xdp_rxq_info of underlying queue.
Therefore, on Tx side, napi_id can be pulled from
xs->pool->heads[0].xdp.rxq->napi_id.
Do this only for sockets working in ZC mode as otherwise rxq pointers
would not be initialized.
Fixes: a0731952d9cd ("xsk: Add busy-poll support for {recv,send}msg()")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@xxxxxxxxx>
---
net/xdp/xsk.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 19ac872a6624..eafd512d38b1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -637,8 +637,11 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len
if (unlikely(need_wait))
return -EOPNOTSUPP;
- if (sk_can_busy_loop(sk))
+ if (sk_can_busy_loop(sk)) {
+ if (xs->zc)
+ __sk_mark_napi_id_once(sk, xs->pool->heads[0].xdp.rxq->napi_id);
sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+ }
if (xs->zc && xsk_no_wakeup(sk))
return 0;
--
2.27.0
