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, so we form the per-peer
queue around the unused skb->prev pointer, which makes sense because the
links are pointing backwards. 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 queue
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.

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.

Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

Author: zx2c4

src/compat/compat.h

@@ -1068,6 +1068,22 @@ static const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tun
 #define kfree_sensitive(a) kzfree(a)
 #endif
 
+#if LINUX_VERSION_CODE < KERNEL_VERSION(4, 3, 0) && !defined(ISRHEL7)
+#define xchg_release xchg
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 14, 0) && !defined(ISRHEL7)
+#include <asm/barrier.h>
+#ifndef smp_load_acquire
+#define smp_load_acquire(p)                                            \
+({                                                                     \
+       typeof(*p) ___p1 = ACCESS_ONCE(*p);                             \
+       smp_mb();                                                       \
+       ___p1;                                                          \
+})
+#endif
+#endif
+
 #if defined(ISUBUNTU1604) || defined(ISRHEL7)
 #include <linux/siphash.h>
 #ifndef _WG_LINUX_SIPHASH_H

src/device.c

@@ -242,8 +242,8 @@ static void wg_destruct(struct net_device *dev)
 	destroy_workqueue(wg->handshake_receive_wq);
 	destroy_workqueue(wg->handshake_send_wq);
 	destroy_workqueue(wg->packet_crypt_wq);
-	wg_packet_queue_free(&wg->decrypt_queue, true);
-	wg_packet_queue_free(&wg->encrypt_queue, true);
+	wg_packet_queue_free(&wg->decrypt_queue);
+	wg_packet_queue_free(&wg->encrypt_queue);
 	rcu_barrier(); /* Wait for all the peers to be actually freed. */
 	wg_ratelimiter_uninit();
 	memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
@@ -351,12 +351,12 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 		goto err_destroy_handshake_send;
 
 	ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker,
-				   true, MAX_QUEUED_PACKETS);
+				   MAX_QUEUED_PACKETS);
 	if (ret < 0)
 		goto err_destroy_packet_crypt;
 
 	ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
-				   true, MAX_QUEUED_PACKETS);
+				   MAX_QUEUED_PACKETS);
 	if (ret < 0)
 		goto err_free_encrypt_queue;
 
@@ -381,9 +381,9 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 err_uninit_ratelimiter:
 	wg_ratelimiter_uninit();
 err_free_decrypt_queue:
-	wg_packet_queue_free(&wg->decrypt_queue, true);
+	wg_packet_queue_free(&wg->decrypt_queue);
 err_free_encrypt_queue:
-	wg_packet_queue_free(&wg->encrypt_queue, true);
+	wg_packet_queue_free(&wg->encrypt_queue);
 err_destroy_packet_crypt:
 	destroy_workqueue(wg->packet_crypt_wq);
 err_destroy_handshake_send:

src/device.h

@@ -27,13 +27,14 @@ struct multicore_worker {
 
 struct crypt_queue {
 	struct ptr_ring ring;
-	union {
-		struct {
-			struct multicore_worker __percpu *worker;
-			int last_cpu;
-		};
-		struct work_struct work;
-	};
+	struct multicore_worker __percpu *worker;
+	int last_cpu;
+};
+
+struct prev_queue {
+	struct sk_buff *head, *tail, *peeked;
+	struct { struct sk_buff *next, *prev; } empty; // Match first 2 members of struct sk_buff.
+	atomic_t count;
 };
 
 struct wg_device {

src/peer.c

@@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	peer = kzalloc(sizeof(*peer), GFP_KERNEL);
 	if (unlikely(!peer))
 		return ERR_PTR(ret);
-	peer->device = wg;
+	if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
+		goto err;
 
+	peer->device = wg;
 	wg_noise_handshake_init(&peer->handshake, &wg->static_identity,
 				public_key, preshared_key, peer);
-	if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
-		goto err_1;
-	if (wg_packet_queue_init(&peer->tx_queue, wg_packet_tx_worker, false,
-				 MAX_QUEUED_PACKETS))
-		goto err_2;
-	if (wg_packet_queue_init(&peer->rx_queue, NULL, false,
-				 MAX_QUEUED_PACKETS))
-		goto err_3;
-
 	peer->internal_id = atomic64_inc_return(&peer_counter);
 	peer->serial_work_cpu = nr_cpumask_bits;
 	wg_cookie_init(&peer->latest_cookie);
 	wg_timers_init(peer);
 	wg_cookie_checker_precompute_peer_keys(peer);
 	spin_lock_init(&peer->keypairs.keypair_update_lock);
-	INIT_WORK(&peer->transmit_handshake_work,
-		  wg_packet_handshake_send_worker);
+	INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker);
+	INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker);
+	wg_prev_queue_init(&peer->tx_queue);
+	wg_prev_queue_init(&peer->rx_queue);
 	rwlock_init(&peer->endpoint_lock);
 	kref_init(&peer->refcount);
 	skb_queue_head_init(&peer->staged_packet_queue);
@@ -68,11 +63,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id);
 	return peer;
 
-err_3:
-	wg_packet_queue_free(&peer->tx_queue, false);
-err_2:
-	dst_cache_destroy(&peer->endpoint_cache);
-err_1:
+err:
 	kfree(peer);
 	return ERR_PTR(ret);
 }
@@ -197,8 +188,7 @@ static void rcu_release(struct rcu_head *rcu)
 	struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu);
 
 	dst_cache_destroy(&peer->endpoint_cache);
-	wg_packet_queue_free(&peer->rx_queue, false);
-	wg_packet_queue_free(&peer->tx_queue, false);
+	WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue));
 
 	/* The final zeroing takes care of clearing any remaining handshake key
 	 * material and other potentially sensitive information.

src/peer.h

@@ -36,7 +36,7 @@ struct endpoint {
 
 struct wg_peer {
 	struct wg_device *device;
-	struct crypt_queue tx_queue, rx_queue;
+	struct prev_queue tx_queue, rx_queue;
 	struct sk_buff_head staged_packet_queue;
 	int serial_work_cpu;
 	bool is_dead;
@@ -46,7 +46,7 @@ struct wg_peer {
 	rwlock_t endpoint_lock;
 	struct noise_handshake handshake;
 	atomic64_t last_sent_handshake;
-	struct work_struct transmit_handshake_work, clear_peer_work;
+	struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work;
 	struct cookie latest_cookie;
 	struct hlist_node pubkey_hash;
 	u64 rx_bytes, tx_bytes;

src/queueing.c

@@ -9,8 +9,7 @@ struct multicore_worker __percpu *
 wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
 {
 	int cpu;
-	struct multicore_worker __percpu *worker =
-		alloc_percpu(struct multicore_worker);
+	struct multicore_worker __percpu *worker = alloc_percpu(struct multicore_worker);
 
 	if (!worker)
 		return NULL;
@@ -23,33 +22,86 @@ wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr)
 }
 
 int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
-			 bool multicore, unsigned int len)
+			 unsigned int len)
 {
 	int ret;
 
 	memset(queue, 0, sizeof(*queue));
 	ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
 	if (ret)
 		return ret;
-	if (function) {
-		if (multicore) {
-			queue->worker = wg_packet_percpu_multicore_worker_alloc(
-				function, queue);
-			if (!queue->worker) {
-				ptr_ring_cleanup(&queue->ring, NULL);
-				return -ENOMEM;
-			}
-		} else {
-			INIT_WORK(&queue->work, function);
-		}
+	queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue);
+	if (!queue->worker) {
+		ptr_ring_cleanup(&queue->ring, NULL);
+		return -ENOMEM;
 	}
 	return 0;
 }
 
-void wg_packet_queue_free(struct crypt_queue *queue, bool multicore)
+void wg_packet_queue_free(struct crypt_queue *queue)
 {
-	if (multicore)
-		free_percpu(queue->worker);
+	free_percpu(queue->worker);
 	WARN_ON(!__ptr_ring_empty(&queue->ring));
 	ptr_ring_cleanup(&queue->ring, NULL);
 }
+
+#define NEXT(skb) ((skb)->prev)
+#define STUB(queue) ((struct sk_buff *)&queue->empty)
+
+void wg_prev_queue_init(struct prev_queue *queue)
+{
+	NEXT(STUB(queue)) = NULL;
+	queue->head = queue->tail = STUB(queue);
+	queue->peeked = NULL;
+	atomic_set(&queue->count, 0);
+	BUILD_BUG_ON(
+		offsetof(struct sk_buff, next) != offsetof(struct prev_queue, empty.next) -
+							offsetof(struct prev_queue, empty) ||
+		offsetof(struct sk_buff, prev) != offsetof(struct prev_queue, empty.prev) -
+							 offsetof(struct prev_queue, empty));
+}
+
+static void __wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
+{
+	WRITE_ONCE(NEXT(skb), NULL);
+	WRITE_ONCE(NEXT(xchg_release(&queue->head, skb)), skb);
+}
+
+bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb)
+{
+	if (!atomic_add_unless(&queue->count, 1, MAX_QUEUED_PACKETS))
+		return false;
+	__wg_prev_queue_enqueue(queue, skb);
+	return true;
+}
+
+struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue)
+{
+	struct sk_buff *tail = queue->tail, *next = smp_load_acquire(&NEXT(tail));
+
+	if (tail == STUB(queue)) {
+		if (!next)
+			return NULL;
+		queue->tail = next;
+		tail = next;
+		next = smp_load_acquire(&NEXT(next));
+	}
+	if (next) {
+		queue->tail = next;
+		atomic_dec(&queue->count);
+		return tail;
+	}
+	if (tail != READ_ONCE(queue->head))
+		return NULL;
+	__wg_prev_queue_enqueue(queue, STUB(queue));
+	next = smp_load_acquire(&NEXT(tail));
+	if (next) {
+		queue->tail = next;
+		atomic_dec(&queue->count);
+		return tail;
+	}
+	return NULL;
+}
+
+#undef NEXT
+#undef STUB

src/queueing.h

@@ -17,12 +17,13 @@ struct wg_device;
 struct wg_peer;
 struct multicore_worker;
 struct crypt_queue;
+struct prev_queue;
 struct sk_buff;
 
 /* queueing.c APIs: */
 int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
-			 bool multicore, unsigned int len);
-void wg_packet_queue_free(struct crypt_queue *queue, bool multicore);
+			 unsigned int len);
+void wg_packet_queue_free(struct crypt_queue *queue);
 struct multicore_worker __percpu *
 wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
 
@@ -138,8 +139,31 @@ static inline int wg_cpumask_next_online(int *next)
 	return cpu;
 }
 
+void wg_prev_queue_init(struct prev_queue *queue);
+
+/* Multi producer */
+bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb);
+
+/* Single consumer */
+struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue);
+
+/* Single consumer */
+static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue)
+{
+	if (queue->peeked)
+		return queue->peeked;
+	queue->peeked = wg_prev_queue_dequeue(queue);
+	return queue->peeked;
+}
+
+/* Single consumer */
+static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue)
+{
+	queue->peeked = NULL;
+}
+
 static inline int wg_queue_enqueue_per_device_and_peer(
-	struct crypt_queue *device_queue, struct crypt_queue *peer_queue,
+	struct crypt_queue *device_queue, struct prev_queue *peer_queue,
 	struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
 {
 	int cpu;
@@ -148,8 +172,9 @@ static inline int wg_queue_enqueue_per_device_and_peer(
 	/* We first queue this up for the peer ingestion, but the consumer
 	 * will wait for the state to change to CRYPTED or DEAD before.
 	 */
-	if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb)))
+	if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb)))
 		return -ENOSPC;
+
 	/* Then we queue it up in the device queue, which consumes the
 	 * packet as soon as it can.
 	 */
@@ -160,24 +185,20 @@ static inline int wg_queue_enqueue_per_device_and_peer(
 	return 0;
 }
 
-static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue,
-					     struct sk_buff *skb,
-					     enum packet_state state)
+static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state)
 {
 	/* We take a reference, because as soon as we call atomic_set, the
 	 * peer can be freed from below us.
 	 */
 	struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
 
 	atomic_set_release(&PACKET_CB(skb)->state, state);
-	queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu,
-					       peer->internal_id),
-		      peer->device->packet_crypt_wq, &queue->work);
+	queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id),
+		      peer->device->packet_crypt_wq, &peer->transmit_packet_work);
 	wg_peer_put(peer);
 }
 
-static inline void wg_queue_enqueue_per_peer_napi(struct sk_buff *skb,
-						  enum packet_state state)
+static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state)
 {
 	/* We take a reference, because as soon as we call atomic_set, the
 	 * peer can be freed from below us.