From: "Jason A. Donenfeld" Jason@zx2c4.com
[ Upstream commit 4005f5c3c9d006157ba716594e0d70c88a235c5e ]
Users with pathological hardware reported CPU stalls on CONFIG_ PREEMPT_VOLUNTARY=y, because the ringbuffers would stay full, meaning these workers would never terminate. That turned out not to be okay on systems without forced preemption, which Sultan observed. This commit adds a cond_resched() to the bottom of each loop iteration, so that these workers don't hog the core. Note that we don't need this on the napi poll worker, since that terminates after its budget is expended.
Suggested-by: Sultan Alsawaf sultan@kerneltoast.com Reported-by: Wang Jian larkwang@gmail.com Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireguard/receive.c | 2 ++ drivers/net/wireguard/send.c | 4 ++++ 2 files changed, 6 insertions(+)
--- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -516,6 +516,8 @@ void wg_packet_decrypt_worker(struct wor &PACKET_CB(skb)->keypair->receiving)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; wg_queue_enqueue_per_peer_napi(skb, state); + if (need_resched()) + cond_resched(); } }
--- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -281,6 +281,8 @@ void wg_packet_tx_worker(struct work_str
wg_noise_keypair_put(keypair, false); wg_peer_put(peer); + if (need_resched()) + cond_resched(); } }
@@ -305,6 +307,8 @@ void wg_packet_encrypt_worker(struct wor wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, state);
+ if (need_resched()) + cond_resched(); } }