bpf, sockmap: Fix incorrect copied_seq calculation

[ Upstream commit b40cc5adaa80e1471095a62d78233b611d7a558c ]

A socket using sockmap has its own independent receive queue: ingress_msg.
This queue may contain data from its own protocol stack or from other
sockets.

The issue is that when reading from ingress_msg, we update tp->copied_seq
by default. However, if the data is not from its own protocol stack,
tcp->rcv_nxt is not increased. Later, if we convert this socket to a
native socket, reading from this socket may fail because copied_seq might
be significantly larger than rcv_nxt.

This fix also addresses the syzkaller-reported bug referenced in the
Closes tag.

This patch marks the skmsg objects in ingress_msg. When reading, we update
copied_seq only if the data is from its own protocol stack.

                                                     FD1:read()
                                                     --  FD1->copied_seq++
                                                         |  [read data]
                                                         |
                                [enqueue data]           v
                  [sockmap]     -> ingress to self ->  ingress_msg queue
FD1 native stack  ------>                                 ^
-- FD1->rcv_nxt++               -> redirect to other      | [enqueue data]
                                       |                  |
                                       |             ingress to FD1
                                       v                  ^
                                      ...                 |  [sockmap]
                                                     FD2 native stack

Closes: https://syzkaller.appspot.com/bug?extid=06dbd397158ec0ea4983
Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()")
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://lore.kernel.org/r/20260124113314.113584-2-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 24 insertions, 3 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6225547808a6..9f522835bfaf 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -408,22 +408,26 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-/* Receive sk_msg from psock->ingress_msg to @msg. */
-int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
-		   int len, int flags)
+int __sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
+		     int len, int flags, int *copied_from_self)
 {
 	struct iov_iter *iter = &msg->msg_iter;
 	int peek = flags & MSG_PEEK;
 	struct sk_msg *msg_rx;
 	int i, copied = 0;
+	bool from_self;
 
 	msg_rx = sk_psock_peek_msg(psock);
+	if (copied_from_self)
+		*copied_from_self = 0;
+
 	while (copied != len) {
 		struct scatterlist *sge;
 
 		if (unlikely(!msg_rx))
 			break;
 
+		from_self = msg_rx->sk == sk;
 		i = msg_rx->sg.start;
 		do {
 			struct page *page;
@@ -442,6 +446,9 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 			}
 
 			copied += copy;
+			if (from_self && copied_from_self)
+				*copied_from_self += copy;
+
 			if (likely(!peek)) {
 				sge->offset += copy;
 				sge->length -= copy;
@@ -486,6 +493,13 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 out:
 	return copied;
 }
+
+/* Receive sk_msg from psock->ingress_msg to @msg. */
+int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
+		   int len, int flags)
+{
+	return __sk_msg_recvmsg(sk, psock, msg, len, flags, NULL);
+}
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
 
 bool sk_msg_is_readable(struct sock *sk)
@@ -615,6 +629,12 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
 	if (unlikely(!msg))
 		return -EAGAIN;
 	skb_set_owner_r(skb, sk);
+
+	/* This is used in tcp_bpf_recvmsg_parser() to determine whether the
+	 * data originates from the socket's own protocol stack. No need to
+	 * refcount sk because msg's lifetime is bound to sk via the ingress_msg.
+	 */
+	msg->sk = sk;
 	err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref);
 	if (err < 0)
 		kfree(msg);
@@ -908,6 +928,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 	sk_msg_compute_data_pointers(msg);
 	msg->sk = sk;
 	ret = bpf_prog_run_pin_on_cpu(prog, msg);
+	msg->sk = NULL;
 	ret = sk_psock_map_verd(ret, msg->sk_redir);
 	psock->apply_bytes = msg->apply_bytes;
 	if (ret == __SK_REDIRECT) {