@@ -235,8 +235,8 @@ static void wg_destruct(struct net_devic
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));
@@ -338,12 +338,12 @@ static int wg_newlink(struct net *src_ne
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;
@@ -368,9 +368,9 @@ static int wg_newlink(struct net *src_ne
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:
@@ -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 {
@@ -32,27 +32,22 @@ struct wg_peer *wg_peer_create(struct 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
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
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.
@@ -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;
struct noise_keypairs keypairs;
@@ -45,7 +45,7 @@ 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;
@@ -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(
}
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_qu
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
@@ -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);
@@ -135,8 +136,31 @@ static inline int wg_cpumask_next_online
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;
@@ -145,8 +169,9 @@ static inline int wg_queue_enqueue_per_d
/* 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.
*/
@@ -157,9 +182,7 @@ static inline int wg_queue_enqueue_per_d
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.
@@ -167,14 +190,12 @@ static inline void wg_queue_enqueue_per_
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.
@@ -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
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 wor
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(struc
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;
@@ -239,8 +239,7 @@ void wg_packet_send_keepalive(struct wg_
wg_packet_send_staged_packets(peer);
}
-static void wg_packet_create_data_done(struct sk_buff *first,
- struct wg_peer *peer)
+static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first)
{
struct sk_buff *skb, *next;
bool is_keepalive, data_sent = false;
@@ -262,22 +261,19 @@ static void wg_packet_create_data_done(s
void wg_packet_tx_worker(struct work_struct *work)
{
- struct crypt_queue *queue = container_of(work, struct crypt_queue,
- work);
+ struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work);
struct noise_keypair *keypair;
enum packet_state state;
struct sk_buff *first;
- struct wg_peer *peer;
- while ((first = __ptr_ring_peek(&queue->ring)) != NULL &&
+ while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL &&
(state = atomic_read_acquire(&PACKET_CB(first)->state)) !=
PACKET_STATE_UNCRYPTED) {
- __ptr_ring_discard_one(&queue->ring);
- peer = PACKET_PEER(first);
+ wg_prev_queue_drop_peeked(&peer->tx_queue);
keypair = PACKET_CB(first)->keypair;
if (likely(state == PACKET_STATE_CRYPTED))
- wg_packet_create_data_done(first, peer);
+ wg_packet_create_data_done(peer, first);
else
kfree_skb_list(first);
@@ -306,16 +302,14 @@ void wg_packet_encrypt_worker(struct wor
break;
}
}
- wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first,
- state);
+ wg_queue_enqueue_per_peer_tx(first, state);
if (need_resched())
cond_resched();
}
}
-static void wg_packet_create_data(struct sk_buff *first)
+static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first)
{
- struct wg_peer *peer = PACKET_PEER(first);
struct wg_device *wg = peer->device;
int ret = -EINVAL;
@@ -323,13 +317,10 @@ static void wg_packet_create_data(struct
if (unlikely(READ_ONCE(peer->is_dead)))
goto err;
- ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue,
- &peer->tx_queue, first,
- wg->packet_crypt_wq,
- &wg->encrypt_queue.last_cpu);
+ ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first,
+ wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu);
if (unlikely(ret == -EPIPE))
- wg_queue_enqueue_per_peer(&peer->tx_queue, first,
- PACKET_STATE_DEAD);
+ wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD);
err:
rcu_read_unlock_bh();
if (likely(!ret || ret == -EPIPE))
@@ -393,7 +384,7 @@ void wg_packet_send_staged_packets(struc
packets.prev->next = NULL;
wg_peer_get(keypair->entry.peer);
PACKET_CB(packets.next)->keypair = keypair;
- wg_packet_create_data(packets.next);
+ wg_packet_create_data(peer, packets.next);
return;
out_invalid: