wireguard: send/receive: cond_resched() when processing worker ringbuffers

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: e7096c131e ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Jason A. Donenfeld 2020-05-06 15:33:04 -06:00 committed by David S. Miller
parent b673e24aad
commit 4005f5c3c9
2 changed files with 6 additions and 0 deletions

View file

@ -516,6 +516,8 @@ void wg_packet_decrypt_worker(struct work_struct *work)
&PACKET_CB(skb)->keypair->receiving)) ?
PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
wg_queue_enqueue_per_peer_napi(skb, state);
if (need_resched())
cond_resched();
}
}

View file

@ -281,6 +281,8 @@ void wg_packet_tx_worker(struct work_struct *work)
wg_noise_keypair_put(keypair, false);
wg_peer_put(peer);
if (need_resched())
cond_resched();
}
}
@ -304,6 +306,8 @@ void wg_packet_encrypt_worker(struct work_struct *work)
}
wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
state);
if (need_resched())
cond_resched();
}
}