aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/wireguard/receive.c
diff options
context:
space:
mode:
authorJason A. Donenfeld2021-02-22 17:25:48 +0100
committerJakub Kicinski2021-02-23 15:59:34 -0800
commit8b5553ace83cced775eefd0f3f18b5c6214ccf7a (patch)
tree92da5f1edf673c656e9f4b05bb3876d9e4a860fe /drivers/net/wireguard/receive.c
parent99fff5264e7ab06f45b0ad60243475be0a8d0559 (diff)
wireguard: queueing: get rid of per-peer ring buffers
Having two ring buffers per-peer means that every peer results in two massive ring allocations. On an 8-core x86_64 machine, this commit reduces the per-peer allocation from 18,688 bytes to 1,856 bytes, which is an 90% reduction. Ninety percent! With some single-machine deployments approaching 500,000 peers, we're talking about a reduction from 7 gigs of memory down to 700 megs of memory. In order to get rid of these per-peer allocations, this commit switches to using a list-based queueing approach. Currently GSO fragments are chained together using the skb->next pointer (the skb_list_* singly linked list approach), so we form the per-peer queue around the unused skb->prev pointer (which sort of makes sense because the links are pointing backwards). Use of skb_queue_* is not possible here, because that is based on doubly linked lists and spinlocks. Multiple cores can write into the queue at any given time, because its writes occur in the start_xmit path or in the udp_recv path. But reads happen in a single workqueue item per-peer, amounting to a multi-producer, single-consumer paradigm. The MPSC queue is implemented locklessly and never blocks. However, it is not linearizable (though it is serializable), with a very tight and unlikely race on writes, which, when hit (some tiny fraction of the 0.15% of partial adds on a fully loaded 16-core x86_64 system), causes the queue reader to terminate early. However, because every packet sent queues up the same workqueue item after it is fully added, the worker resumes again, and stopping early isn't actually a problem, since at that point the packet wouldn't have yet been added to the encryption queue. These properties allow us to avoid disabling interrupts or spinning. The design is based on Dmitry Vyukov's algorithm [1]. Performance-wise, ordinarily list-based queues aren't preferable to ringbuffers, because of cache misses when following pointers around. However, we *already* have to follow the adjacent pointers when working through fragments, so there shouldn't actually be any change there. A potential downside is that dequeueing is a bit more complicated, but the ptr_ring structure used prior had a spinlock when dequeueing, so all and all the difference appears to be a wash. Actually, from profiling, the biggest performance hit, by far, of this commit winds up being atomic_add_unless(count, 1, max) and atomic_ dec(count), which account for the majority of CPU time, according to perf. In that sense, the previous ring buffer was superior in that it could check if it was full by head==tail, which the list-based approach cannot do. But all and all, this enables us to get massive memory savings, allowing WireGuard to scale for real world deployments, without taking much of a performance hit. [1] http://www.1024cores.net/home/lock-free-algorithms/queues/intrusive-mpsc-node-based-queue Reviewed-by: Dmitry Vyukov <dvyukov@google.com> Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com> Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'drivers/net/wireguard/receive.c')
-rw-r--r--drivers/net/wireguard/receive.c16
1 files changed, 6 insertions, 10 deletions
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 2c9551ea6dc7..7dc84bcca261 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -444,7 +444,6 @@ packet_processed:
int wg_packet_rx_poll(struct napi_struct *napi, int budget)
{
struct wg_peer *peer = container_of(napi, struct wg_peer, napi);
- struct crypt_queue *queue = &peer->rx_queue;
struct noise_keypair *keypair;
struct endpoint endpoint;
enum packet_state state;
@@ -455,11 +454,10 @@ int wg_packet_rx_poll(struct napi_struct *napi, int budget)
if (unlikely(budget <= 0))
return 0;
- while ((skb = __ptr_ring_peek(&queue->ring)) != NULL &&
+ while ((skb = wg_prev_queue_peek(&peer->rx_queue)) != NULL &&
(state = atomic_read_acquire(&PACKET_CB(skb)->state)) !=
PACKET_STATE_UNCRYPTED) {
- __ptr_ring_discard_one(&queue->ring);
- peer = PACKET_PEER(skb);
+ wg_prev_queue_drop_peeked(&peer->rx_queue);
keypair = PACKET_CB(skb)->keypair;
free = true;
@@ -508,7 +506,7 @@ void wg_packet_decrypt_worker(struct work_struct *work)
enum packet_state state =
likely(decrypt_packet(skb, PACKET_CB(skb)->keypair)) ?
PACKET_STATE_CRYPTED : PACKET_STATE_DEAD;
- wg_queue_enqueue_per_peer_napi(skb, state);
+ wg_queue_enqueue_per_peer_rx(skb, state);
if (need_resched())
cond_resched();
}
@@ -531,12 +529,10 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb)
if (unlikely(READ_ONCE(peer->is_dead)))
goto err;
- ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue,
- &peer->rx_queue, skb,
- wg->packet_crypt_wq,
- &wg->decrypt_queue.last_cpu);
+ ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb,
+ wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu);
if (unlikely(ret == -EPIPE))
- wg_queue_enqueue_per_peer_napi(skb, PACKET_STATE_DEAD);
+ wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD);
if (likely(!ret || ret == -EPIPE)) {
rcu_read_unlock_bh();
return;