Re: [PATCH bpf-next v5 1/3] bpf, sockmap: Fix incorrect copied_seq calculation

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()")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
---
 include/linux/skmsg.h |  2 ++
 net/core/skmsg.c      | 25 ++++++++++++++++++++++---
 net/ipv4/tcp_bpf.c    |  5 +++--
 3 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 49847888c287..0323a2b6cf5e 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h

@@ -141,6 +141,8 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes);
 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 *from_self_copied);
 bool sk_msg_is_readable(struct sock *sk);
 
 static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2ac7731e1e0a..d73e03f7713a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c

@@ -409,14 +409,14 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 }
 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 *from_self_copied)
 {
 	struct iov_iter *iter = &msg->msg_iter;
 	int peek = flags & MSG_PEEK;
 	struct sk_msg *msg_rx;
 	int i, copied = 0;
+	bool to_self;