[PATCH 6.12.y] mptcp: fix MSG_PEEK stream corruption

["Matthieu Baerts (NGI0)" <matttbe@kernel.org>]

From: Paolo Abeni <pabeni@redhat.com>

[ Upstream commit 8e04ce45a8db7a080220e86e249198fa676b83dc ]

If a MSG_PEEK | MSG_WAITALL read operation consumes all the bytes in the
receive queue and recvmsg() need to waits for more data - i.e. it's a
blocking one - upon arrival of the next packet the MPTCP protocol will
start again copying the oldest data present in the receive queue,
corrupting the data stream.

Address the issue explicitly tracking the peeked sequence number,
restarting from the last peeked byte.

Fixes: ca4fb892579f ("mptcp: add MSG_PEEK support")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Geliang Tang <geliang@kernel.org>
Tested-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-2-38ffff5a9ec8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[ Adjust context ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
---
Note: this is the patch Sasha sent for the v6.6 which applies on v6.12
without conflicts. On v6.12, Sasha sent another version with dependences
that caused some issues, see:
 https://lore.kernel.org/bbe84711-95b2-4257-9f01-560b4473a3da@kernel.org
---
 net/mptcp/protocol.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5ded0841b159..4798892aa178 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1977,19 +1977,35 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);
 
 static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
-				size_t len, int flags,
+				size_t len, int flags, int copied_total,
 				struct scm_timestamping_internal *tss,
 				int *cmsg_flags)
 {
 	struct sk_buff *skb, *tmp;
+	int total_data_len = 0;
 	int copied = 0;
 
 	skb_queue_walk_safe(&msk->receive_queue, skb, tmp) {
-		u32 offset = MPTCP_SKB_CB(skb)->offset;
+		u32 delta, offset = MPTCP_SKB_CB(skb)->offset;
 		u32 data_len = skb->len - offset;
-		u32 count = min_t(size_t, len - copied, data_len);
+		u32 count;
 		int err;
 
+		if (flags & MSG_PEEK) {
+			/* skip already peeked skbs */
+			if (total_data_len + data_len <= copied_total) {
+				total_data_len += data_len;
+				continue;
+			}
+
+			/* skip the already peeked data in the current skb */
+			delta = copied_total - total_data_len;
+			offset += delta;
+			data_len -= delta;
+		}
+
+		count = min_t(size_t, len - copied, data_len);
+
 		if (!(flags & MSG_TRUNC)) {
 			err = skb_copy_datagram_msg(skb, offset, msg, count);
 			if (unlikely(err < 0)) {
@@ -2006,22 +2022,19 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 
 		copied += count;
 
-		if (count < data_len) {
-			if (!(flags & MSG_PEEK)) {
+		if (!(flags & MSG_PEEK)) {
+			msk->bytes_consumed += count;
+			if (count < data_len) {
 				MPTCP_SKB_CB(skb)->offset += count;
 				MPTCP_SKB_CB(skb)->map_seq += count;
-				msk->bytes_consumed += count;
+				break;
 			}
-			break;
-		}
 
-		if (!(flags & MSG_PEEK)) {
 			/* we will bulk release the skb memory later */
 			skb->destructor = NULL;
 			WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
 			__skb_unlink(skb, &msk->receive_queue);
 			__kfree_skb(skb);
-			msk->bytes_consumed += count;
 		}
 
 		if (copied >= len)
@@ -2245,7 +2258,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	while (copied < len) {
 		int err, bytes_read;
 
-		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags);
+		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags,
+						  copied, &tss, &cmsg_flags);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
-- 
2.51.0