netdev - [PATCH net 2/4] mptcp: fix MSG

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20251028-net-mptcp-send-timeout-v1-2-38ffff5a9ec8@kernel.org>
Date: Tue, 28 Oct 2025 09:16:53 +0100
From: "Matthieu Baerts (NGI0)" <matttbe@...nel.org>
To: Mat Martineau <martineau@...nel.org>, Geliang Tang <geliang@...nel.org>, 
 "David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>, 
 Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>, 
 Simon Horman <horms@...nel.org>, Florian Westphal <fw@...len.de>, 
 Yonglong Li <liyonglong@...natelecom.cn>
Cc: netdev@...r.kernel.org, mptcp@...ts.linux.dev, 
 linux-kernel@...r.kernel.org, "Matthieu Baerts (NGI0)" <matttbe@...nel.org>, 
 stable@...r.kernel.org
Subject: [PATCH net 2/4] mptcp: fix MSG_PEEK stream corruption

From: Paolo Abeni <pabeni@...hat.com>

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@...r.kernel.org
Signed-off-by: Paolo Abeni <pabeni@...hat.com>
Reviewed-by: Geliang Tang <geliang@...nel.org>
Tested-by: Geliang Tang <geliang@...nel.org>
Reviewed-by: Mat Martineau <martineau@...nel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@...nel.org>
---
 net/mptcp/protocol.c | 38 +++++++++++++++++++++++++-------------
 1 file changed, 25 insertions(+), 13 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index bf2c9e4f3ba9..d6d1553fbd61 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1936,22 +1936,36 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);
 
-static int __mptcp_recvmsg_mskq(struct sock *sk,
-				struct msghdr *msg,
-				size_t len, int flags,
+static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
+				size_t len, int flags, int copied_total,
 				struct scm_timestamping_internal *tss,
 				int *cmsg_flags)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sk_buff *skb, *tmp;
+	int total_data_len = 0;
 	int copied = 0;
 
 	skb_queue_walk_safe(&sk->sk_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)) {
@@ -1968,16 +1982,14 @@ static int __mptcp_recvmsg_mskq(struct sock *sk,
 
 		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)) {
 			/* avoid the indirect call, we know the destructor is sock_rfree */
 			skb->destructor = NULL;
 			skb->sk = NULL;
@@ -1985,7 +1997,6 @@ static int __mptcp_recvmsg_mskq(struct sock *sk,
 			sk_mem_uncharge(sk, skb->truesize);
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			skb_attempt_defer_free(skb);
-			msk->bytes_consumed += count;
 		}
 
 		if (copied >= len)
@@ -2183,7 +2194,8 @@ 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(sk, msg, len - copied, flags, &tss, &cmsg_flags);
+		bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags,
+						  copied, &tss, &cmsg_flags);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;

-- 
2.51.0