Revert "queueing: get rid of per-peer ring buffers"

This reverts commit bd2c339.

Signed-off-by: Jason A. Donenfeld <[email protected]>

src/compat/compat.h

@@ -1068,22 +1068,6 @@ 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);
-	wg_packet_queue_free(&wg->encrypt_queue);
+	wg_packet_queue_free(&wg->decrypt_queue, true);
+	wg_packet_queue_free(&wg->encrypt_queue, true);
 	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,
-				   MAX_QUEUED_PACKETS);
+				   true, MAX_QUEUED_PACKETS);
 	if (ret < 0)
 		goto err_destroy_packet_crypt;
 
 	ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker,
-				   MAX_QUEUED_PACKETS);
+				   true, 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);
+	wg_packet_queue_free(&wg->decrypt_queue, true);
 err_free_encrypt_queue:
-	wg_packet_queue_free(&wg->encrypt_queue);
+	wg_packet_queue_free(&wg->encrypt_queue, true);
 err_destroy_packet_crypt:
 	destroy_workqueue(wg->packet_crypt_wq);
 err_destroy_handshake_send:

src/device.h

@@ -27,14 +27,13 @@ struct multicore_worker {
 
 struct crypt_queue {
 	struct ptr_ring ring;
-	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;
+	union {
+		struct {
+			struct multicore_worker __percpu *worker;
+			int last_cpu;
+		};
+		struct work_struct work;
+	};
 };
 
 struct wg_device {

src/peer.c

@@ -32,22 +32,27 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	peer = kzalloc(sizeof(*peer), GFP_KERNEL);
 	if (unlikely(!peer))
 		return ERR_PTR(ret);
-	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_packet_work, wg_packet_tx_worker);
-	wg_prev_queue_init(&peer->tx_queue);
-	wg_prev_queue_init(&peer->rx_queue);
+	INIT_WORK(&peer->transmit_handshake_work,
+		  wg_packet_handshake_send_worker);
 	rwlock_init(&peer->endpoint_lock);
 	kref_init(&peer->refcount);
 	skb_queue_head_init(&peer->staged_packet_queue);
@@ -63,7 +68,11 @@ 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:
+err_3:
+	wg_packet_queue_free(&peer->tx_queue, false);
+err_2:
+	dst_cache_destroy(&peer->endpoint_cache);
+err_1:
 	kfree(peer);
 	return ERR_PTR(ret);
 }
@@ -188,7 +197,8 @@ 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);
-	WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue));
+	wg_packet_queue_free(&peer->rx_queue, false);
+	wg_packet_queue_free(&peer->tx_queue, false);
 
 	/* 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 prev_queue tx_queue, rx_queue;
+	struct crypt_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, transmit_packet_work;
+	struct work_struct transmit_handshake_work, clear_peer_work;
 	struct cookie latest_cookie;
 	struct hlist_node pubkey_hash;
 	u64 rx_bytes, tx_bytes;

src/queueing.c

@@ -9,7 +9,8 @@ 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;
@@ -22,86 +23,33 @@ 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,
-			 unsigned int len)
+			 bool multicore, unsigned int len)
 {
 	int ret;
 
 	memset(queue, 0, sizeof(*queue));
 	ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
 	if (ret)
 		return ret;
-	queue->worker = wg_packet_percpu_multicore_worker_alloc(function, queue);
-	if (!queue->worker) {
-		ptr_ring_cleanup(&queue->ring, NULL);
-		return -ENOMEM;
+	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);
+		}
 	}
 	return 0;
 }
 
-void wg_packet_queue_free(struct crypt_queue *queue)
+void wg_packet_queue_free(struct crypt_queue *queue, bool multicore)
 {
-	free_percpu(queue->worker);
+	if (multicore)
+		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

@@ -17,13 +17,12 @@ 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,
-			 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, bool multicore);
 struct multicore_worker __percpu *
 wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
 
@@ -139,31 +138,8 @@ 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 prev_queue *peer_queue,
+	struct crypt_queue *device_queue, struct crypt_queue *peer_queue,
 	struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
 {
 	int cpu;
@@ -172,9 +148,8 @@ 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(!wg_prev_queue_enqueue(peer_queue, skb)))
+	if (unlikely(ptr_ring_produce_bh(&peer_queue->ring, skb)))
 		return -ENOSPC;
-
 	/* Then we queue it up in the device queue, which consumes the
 	 * packet as soon as it can.
 	 */
@@ -185,20 +160,24 @@ static inline int wg_queue_enqueue_per_device_and_peer(
 	return 0;
 }
 
-static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state)
+static inline void wg_queue_enqueue_per_peer(struct crypt_queue *queue,
+					     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, &peer->transmit_packet_work);
+	queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu,
+					       peer->internal_id),
+		      peer->device->packet_crypt_wq, &queue->work);
 	wg_peer_put(peer);
 }
 
-static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state)
+static inline void wg_queue_enqueue_per_peer_napi(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.