[SRU][N:hwe-6.17][PATCH 1/1] vsock/virtio: fix zerocopy completion for multi-skb sends

[Cengiz Can]

From: Stefano Garzarella <sgarzare at redhat.com>

When a large message is fragmented into multiple skbs, the zerocopy
uarg is only allocated and attached to the last skb in the loop.
Non-final skbs carry pinned user pages with no completion tracking,
so the kernel has no way to notify userspace when those pages are safe
to reuse. If the loop breaks early the uarg is never allocated at all,
leaking pinned pages with no completion notification.

Fix this by following the approach used by TCP: allocate the zerocopy
uarg (if not provided by the caller) before the send loop and attach
it to every skb via skb_zcopy_set(), which takes a reference per skb.
Each skb's completion properly decrements the refcount, and the
notification only fires after the last skb is freed.
On failure, if no data was sent, the uarg is cleanly aborted via
net_zcopy_put_abort().

This issue was initially discovered by sashiko while reviewing commit
1cb36e252211 ("vsock/virtio: fix MSG_ZEROCOPY pinned-pages accounting")
but was pre-existing.

Fixes: 581512a6dc93 ("vsock/virtio: MSG_ZEROCOPY flag support")
Closes: https://sashiko.dev/#/patchset/20260420132051.217589-1-sgarzare%40redhat.com
Reported-by: Maher Azzouzi <maherazz04 at gmail.com>
Signed-off-by: Stefano Garzarella <sgarzare at redhat.com>
Acked-by: Michael S. Tsirkin <mst at redhat.com>
Acked-by: Arseniy Krasnov <avkrasnov at salutedevices.com>
Link: https://patch.msgid.link/20260514092948.268720-1-sgarzare@redhat.com
Signed-off-by: Jakub Kicinski <kuba at kernel.org>
(backported from commit ae38d9179190a956e2a87a69ef1dd6f451b51c4d)
[bot_kybele: Removed tree's virtio_transport_init_zcopy_skb (variant taking msg
 not pkt_len, using iter->count) and replaced its loop-body call with
 skb_zcopy_set; pre-loop uarg setup and post-loop have_uref cleanup had already
 applied cleanly, so only the two deletion hunks needed manual resolution.]
CVE-2026-53365
Assisted-by: kybele:claude-opus-4.8
Signed-off-by: Cengiz Can <cengiz.can at canonical.com>
---
 net/vmw_vsock/virtio_transport_common.c | 78 +++++++++++--------------
 1 file changed, 34 insertions(+), 44 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index d3e26025ef58..7a6a81eb6940 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -72,35 +72,6 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops,
 	return true;
 }
 
-static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk,
-					   struct sk_buff *skb,
-					   struct msghdr *msg,
-					   bool zerocopy)
-{
-	struct ubuf_info *uarg;
-
-	if (msg->msg_ubuf) {
-		uarg = msg->msg_ubuf;
-		net_zcopy_get(uarg);
-	} else {
-		struct iov_iter *iter = &msg->msg_iter;
-		struct ubuf_info_msgzc *uarg_zc;
-
-		uarg = msg_zerocopy_realloc(sk_vsock(vsk),
-					    iter->count,
-					    NULL, false);
-		if (!uarg)
-			return -1;
-
-		uarg_zc = uarg_to_msgzc(uarg);
-		uarg_zc->zerocopy = zerocopy ? 1 : 0;
-	}
-
-	skb_zcopy_init(skb, uarg);
-
-	return 0;
-}
-
 static int virtio_transport_fill_skb(struct sk_buff *skb,
 				     struct virtio_vsock_pkt_info *info,
 				     size_t len,
@@ -335,8 +306,10 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 	u32 src_cid, src_port, dst_cid, dst_port;
 	const struct virtio_transport *t_ops;
 	struct virtio_vsock_sock *vvs;
+	struct ubuf_info *uarg = NULL;
 	u32 pkt_len = info->pkt_len;
 	bool can_zcopy = false;
+	bool have_uref = false;
 	u32 rest_len;
 	int ret;
 
@@ -378,6 +351,25 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 		if (can_zcopy)
 			max_skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE,
 					    (MAX_SKB_FRAGS * PAGE_SIZE));
+
+		if (info->msg->msg_flags & MSG_ZEROCOPY &&
+		    info->op == VIRTIO_VSOCK_OP_RW) {
+			uarg = info->msg->msg_ubuf;
+
+			if (!uarg) {
+				uarg = msg_zerocopy_realloc(sk_vsock(vsk),
+							    pkt_len, NULL, false);
+				if (!uarg) {
+					virtio_transport_put_credit(vvs, pkt_len);
+					return -ENOMEM;
+				}
+
+				if (!can_zcopy)
+					uarg_to_msgzc(uarg)->zerocopy = 0;
+
+				have_uref = true;
+			}
+		}
 	}
 
 	rest_len = pkt_len;
@@ -396,21 +388,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 			break;
 		}
 
-		/* We process buffer part by part, allocating skb on
-		 * each iteration. If this is last skb for this buffer
-		 * and MSG_ZEROCOPY mode is in use - we must allocate
-		 * completion for the current syscall.
-		 */
-		if (info->msg && info->msg->msg_flags & MSG_ZEROCOPY &&
-		    skb_len == rest_len && info->op == VIRTIO_VSOCK_OP_RW) {
-			if (virtio_transport_init_zcopy_skb(vsk, skb,
-							    info->msg,
-							    can_zcopy)) {
-				kfree_skb(skb);
-				ret = -ENOMEM;
-				break;
-			}
-		}
+		skb_zcopy_set(skb, uarg, NULL);
 
 		virtio_transport_inc_tx_pkt(vvs, skb);
 
@@ -434,6 +412,18 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 
 	virtio_transport_put_credit(vvs, rest_len);
 
+	/* msg_zerocopy_realloc() initializes the ubuf_info refcnt to 1.
+	 * skb_zcopy_set() increases it for each skb, so we can drop that
+	 * initial reference to keep it balanced.
+	 */
+	if (have_uref) {
+		if (rest_len == pkt_len)
+			/* No data sent, abort the notification. */
+			net_zcopy_put_abort(uarg, true);
+		else
+			net_zcopy_put(uarg);
+	}
+
 	/* Return number of bytes, if any data has been sent. */
 	if (rest_len != pkt_len)
 		ret = pkt_len - rest_len;
-- 
2.53.0