[PATCH net] wireguard: wait for per-peer crypto during removal

[Chris J Arges]

Calling peer_remove_after_dead() currently flushes device-wide packet
crypto and handshake workqueues while holding RTNL. This is problematic as
unrelated peers can continue adding work onto those queues blocking other
tasks that want to take the RTNL lock.

Instead, this patch proposes tracking pending crypto handoffs for each
peer using a counter. After marking the peer dead, synchronize_net()
prevents new submissions; wait for pending crypto workers to schedule TX
work or RX NAPI. Then flush only the peer's transmit packet and handshake
work.

This scopes teardown synchronization to the removed peer and prevents
unrelated peers from extending the RTNL hold time.

Fixes: e7096c131e51 ("net: WireGuard secure network tunnel")
Signed-off-by: Chris J Arges <carges@xxxxxxxxxxxxxx>
---
 drivers/net/wireguard/peer.c     | 30 ++++++++++++++++--------------
 drivers/net/wireguard/peer.h     |  1 +
 drivers/net/wireguard/queueing.h |  6 ++++++
 3 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c
index 1cb502a932e0..f7a9c437b5b8 100644
--- a/drivers/net/wireguard/peer.c
+++ b/drivers/net/wireguard/peer.c
@@ -14,6 +14,7 @@
 #include <linux/lockdep.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
+#include <linux/wait_bit.h>
 
 static struct kmem_cache *peer_cache;
 static atomic64_t peer_counter = ATOMIC64_INIT(0);
@@ -49,6 +50,8 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
 	INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker);
 	wg_prev_queue_init(&peer->tx_queue);
 	wg_prev_queue_init(&peer->rx_queue);
+	/* Keep this above zero until teardown prevents new packet handoffs. */
+	atomic_set(&peer->packet_crypt_pending, 1);
 	rwlock_init(&peer->endpoint_lock);
 	kref_init(&peer->refcount);
 	skb_queue_head_init(&peer->staged_packet_queue);
@@ -105,28 +108,27 @@ static void peer_remove_after_dead(struct wg_peer *peer)
 	 */
 	wg_timers_stop(peer);
 
-	/* The transition between packet encryption/decryption queues isn't
-	 * guarded by is_dead, but each reference's life is strictly bounded by
-	 * two generations: once for parallel crypto and once for serial
-	 * ingestion, so we can simply flush twice, and be sure that we no
-	 * longer have references inside these queues.
+	/* Lookup removal and is_dead prevent new packets from entering the
+	 * parallel crypto queues after synchronize_net() waits for pre-existing
+	 * submission paths. Drop the initial count and wait for existing packets
+	 * to finish scheduling their serial TX work or RX NAPI processing.
 	 */
+	atomic_dec(&peer->packet_crypt_pending);
+	wait_var_event(&peer->packet_crypt_pending,
+		       !atomic_read_acquire(&peer->packet_crypt_pending));
+
+	flush_work(&peer->transmit_packet_work);
 
-	/* a) For encrypt/decrypt. */
-	flush_workqueue(peer->device->packet_crypt_wq);
-	/* b.1) For send (but not receive, since that's napi). */
-	flush_workqueue(peer->device->packet_crypt_wq);
-	/* b.2.1) For receive (but not send, since that's wq). */
 	napi_disable(&peer->napi);
-	/* b.2.1) It's now safe to remove the napi struct, which must be done
+	/* It's now safe to remove the napi struct, which must be done
 	 * here from process context.
 	 */
 	netif_napi_del(&peer->napi);
 
-	/* Ensure any workstructs we own (like transmit_handshake_work or
-	 * clear_peer_work) no longer are in use.
+	/* clear_peer_work was flushed by wg_timers_stop(). Ensure the remaining
+	 * peer-owned handshake work is no longer in use.
 	 */
-	flush_workqueue(peer->device->handshake_send_wq);
+	flush_work(&peer->transmit_handshake_work);
 
 	/* After the above flushes, a peer might still be active in a few
 	 * different contexts: 1) from xmit(), before hitting is_dead and
diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h
index 718fb42bdac7..64412c67f413 100644
--- a/drivers/net/wireguard/peer.h
+++ b/drivers/net/wireguard/peer.h
@@ -37,6 +37,7 @@ struct endpoint {
 struct wg_peer {
 	struct wg_device *device;
 	struct prev_queue tx_queue, rx_queue;
+	atomic_t packet_crypt_pending;
 	struct sk_buff_head staged_packet_queue;
 	int serial_work_cpu;
 	bool is_dead;
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 79b6d70de236..fdd34f0f15a6 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -11,6 +11,7 @@
 #include <linux/skbuff.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/wait_bit.h>
 #include <net/ip_tunnels.h>
 
 struct wg_device;
@@ -161,6 +162,7 @@ static inline int wg_queue_enqueue_per_device_and_peer(
 	 */
 	if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb)))
 		return -ENOSPC;
+	atomic_inc(&PACKET_PEER(skb)->packet_crypt_pending);
 
 	/* Then we queue it up in the device queue, which consumes the
 	 * packet as soon as it can.
@@ -182,6 +184,8 @@ static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet
 	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);
+	if (atomic_dec_and_test(&peer->packet_crypt_pending))
+		wake_up_var(&peer->packet_crypt_pending);
 	wg_peer_put(peer);
 }
 
@@ -194,6 +198,8 @@ static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet
 
 	atomic_set_release(&PACKET_CB(skb)->state, state);
 	napi_schedule(&peer->napi);
+	if (atomic_dec_and_test(&peer->packet_crypt_pending))
+		wake_up_var(&peer->packet_crypt_pending);
 	wg_peer_put(peer);
 }
 

---
base-commit: 70f3995830d3f1e79faa14eb0605914f778feca9
change-id: 20260901-fix-wg-peer-removal-43fc390d0311

Best regards,
--  
Chris J Arges <carges@xxxxxxxxxxxxxx>