bpf/sockmap: Read psock ingress_msg before sk_receive_queue

Right now in tcp_bpf_recvmsg, sock read data first from sk_receive_queue
if not empty than psock->ingress_msg otherwise. If a FIN packet arrives
and there's also some data in psock->ingress_msg, the data in
psock->ingress_msg will be purged. It is always happen when request to a
HTTP1.0 server like python SimpleHTTPServer since the server send FIN
packet after data is sent out.

Fixes: 38506f4bbc9de ("bpf, sockmap: convert to generic sk_msg interface")
Reported-by: Arika Chen <eaglesora@gmail.com>
Suggested-by: Arika Chen <eaglesora@gmail.com>
Signed-off-by: Lingpeng Chen <forrest0579@gmail.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20200109014833.18951-1-forrest0579@gmail.com

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index e38705165ac9bd48910348169fc9904c41fb48dc..e6b08b5a089559ae400336c3e4fee0dc1752a91e 100644 (file)
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -121,14 +121,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
        struct sk_psock *psock;
        int copied, ret;
 
-       if (unlikely(flags & MSG_ERRQUEUE))
-               return inet_recv_error(sk, msg, len, addr_len);
-       if (!skb_queue_empty(&sk->sk_receive_queue))
-               return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-
        psock = sk_psock_get(sk);
        if (unlikely(!psock))
                return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+       if (unlikely(flags & MSG_ERRQUEUE))
+               return inet_recv_error(sk, msg, len, addr_len);
+       if (!skb_queue_empty(&sk->sk_receive_queue) &&
+           sk_psock_queue_empty(psock))
+               return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
        lock_sock(sk);
 msg_bytes_ready:
        copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +139,7 @@ msg_bytes_ready:
                timeo = sock_rcvtimeo(sk, nonblock);
                data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
                if (data) {
-                       if (skb_queue_empty(&sk->sk_receive_queue))
+                       if (!sk_psock_queue_empty(psock))
                                goto msg_bytes_ready;
                        release_sock(sk);
                        sk_psock_put(sk, psock);