tcp: fix splice() and tcp collapsing interaction

Under unusual circumstances, TCP collapse can split a big GRO TCP packet
while its being used in a splice(socket->pipe) operation.

skb_splice_bits() releases the socket lock before calling
splice_to_pipe().

[ 1081.353685] WARNING: at net/ipv4/tcp.c:1330 tcp_cleanup_rbuf+0x4d/0xfc()
[ 1081.371956] Hardware name: System x3690 X5 -[7148Z68]-
[ 1081.391820] cleanup rbuf bug: copied AD3BCF1 seq AD370AF rcvnxt AD3CF13

To fix this problem, we must eat skbs in tcp_recv_skb().

Remove the inline keyword from tcp_recv_skb() definition since
it has three call sites.

Reported-by: Christian Becker <c.becker@traviangames.com>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5f173dccd1e90fc7cad5944577a3ebb360ab64cc..2aa69c8ae60c1990c76e69fe5aef46b990b6da6e 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1428,12 +1428,12 @@ static void tcp_service_net_dma(struct sock *sk, bool wait)
 }
 #endif
 
-static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
+static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
        struct sk_buff *skb;
        u32 offset;
 
-       skb_queue_walk(&sk->sk_receive_queue, skb) {
+       while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
                offset = seq - TCP_SKB_CB(skb)->seq;
                if (tcp_hdr(skb)->syn)
                        offset--;
@@ -1441,6 +1441,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
                        *off = offset;
                        return skb;
                }
+               /* This looks weird, but this can happen if TCP collapsing
+                * splitted a fat GRO packet, while we released socket lock
+                * in skb_splice_bits()
+                */
+               sk_eat_skb(sk, skb, false);
        }
        return NULL;
 }
@@ -1520,8 +1525,10 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
        tcp_rcv_space_adjust(sk);
 
        /* Clean up data we have read: This will do ACK frames. */
-       if (copied > 0)
+       if (copied > 0) {
+               tcp_recv_skb(sk, seq, &offset);
                tcp_cleanup_rbuf(sk, copied);
+       }
        return copied;
 }
 EXPORT_SYMBOL(tcp_read_sock);