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

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

1 files changed, 69 insertions, 17 deletions

diff --git a/src/queueing.c b/src/queueing.c
index 71b8e80..48e7b98 100644
--- a/src/queueing.c
+++ b/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;
@@ -23,7 +22,7 @@ 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;
 
@@ -31,25 +30,78 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 	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