git: 3705d679a634 - main - if_wg: use proper barriers around pkt->p_state

The branch main has been updated by kevans:

URL: https://cgit.FreeBSD.org/src/commit/?id=3705d679a6344c957cae7a1b6372a8bfb8c44f0e

commit 3705d679a6344c957cae7a1b6372a8bfb8c44f0e
Author:     Kyle Evans <kevans@FreeBSD.org>
AuthorDate: 2024-03-15 01:19:18 +0000
Commit:     Kyle Evans <kevans@FreeBSD.org>
CommitDate: 2024-03-15 01:19:21 +0000

    if_wg: use proper barriers around pkt->p_state
    
    Without appropriate load-synchronization to pair with store barriers in
    wg_encrypt() and wg_decrypt(), the compiler and hardware are often
    allowed to reorder these loads in wg_deliver_out() and wg_deliver_in()
    such that we end up with a garbage or intermediate mbuf that we try to
    pass on.  The issue is particularly prevalent with the weaker
    memory models of !x86 platforms.
    
    Switch from the big-hammer wmb() to more explicit acq/rel atomics to
    both make it obvious what we're syncing up with, and to avoid somewhat
    hefty fences on platforms that don't necessarily need this.
    
    With this patch, my dual-iperf3 reproducer is dramatically more stable
    than it is without on aarch64.
    
    PR:             264115
    MFC after:      1 week
    Reviewed by:    andrew, zlei
    Differential Revision:  https://reviews.freebsd.org/D44283
---
 sys/dev/wg/if_wg.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/sys/dev/wg/if_wg.c b/sys/dev/wg/if_wg.c
index c7649e2b4059..42c426ac1819 100644
--- a/sys/dev/wg/if_wg.c
+++ b/sys/dev/wg/if_wg.c
@@ -1517,8 +1517,7 @@ wg_encrypt(struct wg_softc *sc, struct wg_packet *pkt)
 	state = WG_PACKET_CRYPTED;
 out:
 	pkt->p_mbuf = m;
-	wmb();
-	pkt->p_state = state;
+	atomic_store_rel_int(&pkt->p_state, state);
 	GROUPTASK_ENQUEUE(&peer->p_send);
 	noise_remote_put(remote);
 }
@@ -1590,8 +1589,7 @@ wg_decrypt(struct wg_softc *sc, struct wg_packet *pkt)
 	state = WG_PACKET_CRYPTED;
 out:
 	pkt->p_mbuf = m;
-	wmb();
-	pkt->p_state = state;
+	atomic_store_rel_int(&pkt->p_state, state);
 	GROUPTASK_ENQUEUE(&peer->p_recv);
 	noise_remote_put(remote);
 }
@@ -1647,7 +1645,7 @@ wg_deliver_out(struct wg_peer *peer)
 	wg_peer_get_endpoint(peer, &endpoint);
 
 	while ((pkt = wg_queue_dequeue_serial(&peer->p_encrypt_serial)) != NULL) {
-		if (pkt->p_state != WG_PACKET_CRYPTED)
+		if (atomic_load_acq_int(&pkt->p_state) != WG_PACKET_CRYPTED)
 			goto error;
 
 		m = pkt->p_mbuf;
@@ -1689,7 +1687,7 @@ wg_deliver_in(struct wg_peer *peer)
 	struct epoch_tracker	 et;
 
 	while ((pkt = wg_queue_dequeue_serial(&peer->p_decrypt_serial)) != NULL) {
-		if (pkt->p_state != WG_PACKET_CRYPTED)
+		if (atomic_load_acq_int(&pkt->p_state) != WG_PACKET_CRYPTED)
 			goto error;
 
 		m = pkt->p_mbuf;