wireguard: receive: use ring buffer for incoming handshakes

Apparently the spinlock on incoming_handshake's skb_queue is highly
contended, and a torrent of handshake or cookie packets can bring the
data plane to its knees, simply by virtue of enqueueing the handshake
packets to be processed asynchronously. So, we try switching this to a
ring buffer to hopefully have less lock contention. This alleviates the
problem somewhat, though it still isn't perfect, so future patches will
have to improve this further. However, it at least doesn't completely
diminish the data plane.

Reported-by: Streun Fabio <fstreun@student.ethz.ch>
Reported-by: Joel Wanner <joel.wanner@inf.ethz.ch>
Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 3 insertions, 6 deletions

diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index 854bc3d97150..43c7cebbf50b 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -39,21 +39,18 @@ struct prev_queue {
 
 struct wg_device {
 	struct net_device *dev;
-	struct crypt_queue encrypt_queue, decrypt_queue;
+	struct crypt_queue encrypt_queue, decrypt_queue, handshake_queue;
 	struct sock __rcu *sock4, *sock6;
 	struct net __rcu *creating_net;
 	struct noise_static_identity static_identity;
-	struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
-	struct workqueue_struct *packet_crypt_wq;
-	struct sk_buff_head incoming_handshakes;
-	int incoming_handshake_cpu;
-	struct multicore_worker __percpu *incoming_handshakes_worker;
+	struct workqueue_struct *packet_crypt_wq,*handshake_receive_wq, *handshake_send_wq;
 	struct cookie_checker cookie_checker;
 	struct pubkey_hashtable *peer_hashtable;
 	struct index_hashtable *index_hashtable;
 	struct allowedips peer_allowedips;
 	struct mutex device_update_lock, socket_update_lock;
 	struct list_head device_list, peer_list;
+	atomic_t handshake_queue_len;
 	unsigned int num_peers, device_update_gen;
 	u32 fwmark;
 	u16 incoming_port;