From 6f226ffe4458ea3b8c33287cb8c86f87dc198dce Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Tue, 12 Oct 2021 13:20:19 +0800
Subject: [PATCH] tcp_bpf: Fix one concurrency problem in the tcp_bpf_send_verdict function
Git-commit: cd9733f5d75c94a32544d6ce5be47e14194cf137
Patch-mainline: v5.15
References: stable-5.14.16

commit cd9733f5d75c94a32544d6ce5be47e14194cf137 upstream.

With two Msgs, msgA and msgB and a user doing nonblocking sendmsg calls (or
multiple cores) on a single socket 'sk' we could get the following flow.

 msgA, sk                               msgB, sk
 -----------                            ---------------
 tcp_bpf_sendmsg()
 lock(sk)
 psock = sk->psock
                                        tcp_bpf_sendmsg()
                                        lock(sk) ... blocking
tcp_bpf_send_verdict
if (psock->eval == NONE)
   psock->eval = sk_psock_msg_verdict
 ..
 < handle SK_REDIRECT case >
   release_sock(sk)                     < lock dropped so grab here >
   ret = tcp_bpf_sendmsg_redir
                                        psock = sk->psock
                                        tcp_bpf_send_verdict
 lock_sock(sk) ... blocking on B
                                        if (psock->eval == NONE) <- boom.
                                         psock->eval will have msgA state

The problem here is we dropped the lock on msgA and grabbed it with msgB.
Now we have old state in psock and importantly psock->eval has not been
cleared. So msgB will run whatever action was done on A and the verdict
program may never see it.

Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211012052019.184398-1-liujian56@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 net/ipv4/tcp_bpf.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386b493e..9d068153c316 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -232,6 +232,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
+	u32 eval = __SK_NONE;
 	int ret;
 
 more_data:
@@ -275,13 +276,24 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 	case __SK_REDIRECT:
 		sk_redir = psock->sk_redir;
 		sk_msg_apply_bytes(psock, tosend);
+		if (!psock->apply_bytes) {
+			/* Clean up before releasing the sock lock. */
+			eval = psock->eval;
+			psock->eval = __SK_NONE;
+			psock->sk_redir = NULL;
+		}
 		if (psock->cork) {
 			cork = true;
 			psock->cork = NULL;
 		}
 		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
+
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+		if (eval == __SK_REDIRECT)
+			sock_put(sk_redir);
+
 		lock_sock(sk);
 		if (unlikely(ret < 0)) {
 			int free = sk_msg_free_nocharge(sk, msg);
-- 
2.26.2