[PATCH 4.9 074/109] tcp: correct memory barrier usage in tcp_check_space()

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Jason Baron <jba...@akamai.com>


[ Upstream commit 56d806222ace4c3aeae516cd7a855340fb2839d8 ]

sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.

Fixes: 3c7151275c0c ("tcp: add memory barriers to write space paths")
Cc: Eric Dumazet <eric.duma...@gmail.com>
Cc: Oleg Nesterov <o...@redhat.com>
Signed-off-by: Jason Baron <jba...@akamai.com>
Acked-by: Eric Dumazet <eduma...@google.com>
Reported-by: Oleg Nesterov <o...@redhat.com>
Signed-off-by: David S. Miller <da...@davemloft.net>
Signed-off-by: Sasha Levin <alexander.le...@verizon.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
 net/ipv4/tcp_input.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5081,7 +5081,7 @@ static void tcp_check_space(struct sock
        if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
                sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
                /* pairs with tcp_poll() */
-               smp_mb__after_atomic();
+               smp_mb();
                if (sk->sk_socket &&
                    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
                        tcp_new_space(sk);