summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2023-07-03 09:17:52 +0100
committerDavid S. Miller <davem@davemloft.net>2023-07-03 09:17:52 +0100
commit6da8cf8f6b42bd3785b866ce705fe97666081ec9 (patch)
tree89a51c16b42b25d96f862d99ec2e29cc20010d86
parent0ad466d99dbac3997ae4002d43663a4c1437c8bc (diff)
parent98788e31e3607f44785a59682ca7137eb2e4d15e (diff)
downloadwireguard-linux-trimmed-6da8cf8f6b42bd3785b866ce705fe97666081ec9.tar.gz
wireguard-linux-trimmed-6da8cf8f6b42bd3785b866ce705fe97666081ec9.zip
Merge branch 'wireguard-fixes'
Jason A. Donenfeld says: ==================== wireguard fixes for 6.4.2/6.5-rc1 Sorry to send these patches during the merge window, but they're net fixes, not netdev enhancements, and while I'd ordinarily wait anyway, I just got a first bug report for one of these fixes, which I originally had thought was mostly unlikely. So please apply the following three patches to net: 1) Make proper use of nr_cpu_ids with cpumask_next(), rather than awkwardly using modulo, to handle dynamic CPU topology changes. Linus noticed this a while ago and pointed it out, and today a user actually got hit by it. 2) Respect persistent keepalive and other staged packets when setting the private key after the interface is already up. 3) Use timer_delete_sync() instead of del_timer_sync(), per the documentation. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--drivers/net/wireguard/netlink.c14
-rw-r--r--drivers/net/wireguard/queueing.c1
-rw-r--r--drivers/net/wireguard/queueing.h25
-rw-r--r--drivers/net/wireguard/receive.c2
-rw-r--r--drivers/net/wireguard/send.c2
-rw-r--r--drivers/net/wireguard/timers.c10
6 files changed, 28 insertions, 26 deletions
diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c
index 43c8c84..6d1bd9f 100644
--- a/drivers/net/wireguard/netlink.c
+++ b/drivers/net/wireguard/netlink.c
@@ -546,6 +546,7 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]);
u8 public_key[NOISE_PUBLIC_KEY_LEN];
struct wg_peer *peer, *temp;
+ bool send_staged_packets;
if (!crypto_memneq(wg->static_identity.static_private,
private_key, NOISE_PUBLIC_KEY_LEN))
@@ -564,14 +565,17 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info)
}
down_write(&wg->static_identity.lock);
- wg_noise_set_static_identity_private_key(&wg->static_identity,
- private_key);
- list_for_each_entry_safe(peer, temp, &wg->peer_list,
- peer_list) {
+ send_staged_packets = !wg->static_identity.has_identity && netif_running(wg->dev);
+ wg_noise_set_static_identity_private_key(&wg->static_identity, private_key);
+ send_staged_packets = send_staged_packets && wg->static_identity.has_identity;
+
+ wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
+ list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) {
wg_noise_precompute_static_static(peer);
wg_noise_expire_current_peer_keypairs(peer);
+ if (send_staged_packets)
+ wg_packet_send_staged_packets(peer);
}
- wg_cookie_checker_precompute_device_keys(&wg->cookie_checker);
up_write(&wg->static_identity.lock);
}
skip_set_private_key:
diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
index 8084e74..26d235d 100644
--- a/drivers/net/wireguard/queueing.c
+++ b/drivers/net/wireguard/queueing.c
@@ -28,6 +28,7 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
int ret;
memset(queue, 0, sizeof(*queue));
+ queue->last_cpu = -1;
ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL);
if (ret)
return ret;
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 125284b..1ea4f87 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -117,20 +117,17 @@ static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id)
return cpu;
}
-/* This function is racy, in the sense that next is unlocked, so it could return
- * the same CPU twice. A race-free version of this would be to instead store an
- * atomic sequence number, do an increment-and-return, and then iterate through
- * every possible CPU until we get to that index -- choose_cpu. However that's
- * a bit slower, and it doesn't seem like this potential race actually
- * introduces any performance loss, so we live with it.
+/* This function is racy, in the sense that it's called while last_cpu is
+ * unlocked, so it could return the same CPU twice. Adding locking or using
+ * atomic sequence numbers is slower though, and the consequences of racing are
+ * harmless, so live with it.
*/
-static inline int wg_cpumask_next_online(int *next)
+static inline int wg_cpumask_next_online(int *last_cpu)
{
- int cpu = *next;
-
- while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask)))
- cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
- *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
+ int cpu = cpumask_next(*last_cpu, cpu_online_mask);
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(cpu_online_mask);
+ *last_cpu = cpu;
return cpu;
}
@@ -159,7 +156,7 @@ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue)
static inline int wg_queue_enqueue_per_device_and_peer(
struct crypt_queue *device_queue, struct prev_queue *peer_queue,
- struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
+ struct sk_buff *skb, struct workqueue_struct *wq)
{
int cpu;
@@ -173,7 +170,7 @@ static inline int wg_queue_enqueue_per_device_and_peer(
/* Then we queue it up in the device queue, which consumes the
* packet as soon as it can.
*/
- cpu = wg_cpumask_next_online(next_cpu);
+ cpu = wg_cpumask_next_online(&device_queue->last_cpu);
if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb)))
return -EPIPE;
queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work);
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 7135d51..0b3f0c8 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -524,7 +524,7 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb)
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);
+ wg->packet_crypt_wq);
if (unlikely(ret == -EPIPE))
wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD);
if (likely(!ret || ret == -EPIPE)) {
diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c
index 5368f7c..95c853b 100644
--- a/drivers/net/wireguard/send.c
+++ b/drivers/net/wireguard/send.c
@@ -318,7 +318,7 @@ static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first)
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);
+ wg->packet_crypt_wq);
if (unlikely(ret == -EPIPE))
wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD);
err:
diff --git a/drivers/net/wireguard/timers.c b/drivers/net/wireguard/timers.c
index 53d8a57..968bdb4 100644
--- a/drivers/net/wireguard/timers.c
+++ b/drivers/net/wireguard/timers.c
@@ -234,10 +234,10 @@ void wg_timers_init(struct wg_peer *peer)
void wg_timers_stop(struct wg_peer *peer)
{
- del_timer_sync(&peer->timer_retransmit_handshake);
- del_timer_sync(&peer->timer_send_keepalive);
- del_timer_sync(&peer->timer_new_handshake);
- del_timer_sync(&peer->timer_zero_key_material);
- del_timer_sync(&peer->timer_persistent_keepalive);
+ timer_delete_sync(&peer->timer_retransmit_handshake);
+ timer_delete_sync(&peer->timer_send_keepalive);
+ timer_delete_sync(&peer->timer_new_handshake);
+ timer_delete_sync(&peer->timer_zero_key_material);
+ timer_delete_sync(&peer->timer_persistent_keepalive);
flush_work(&peer->clear_peer_work);
}