diff --git a/include/net/tcp.h b/include/net/tcp.h index a5af6be3a572..dd99679e2e51 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1161,6 +1161,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp) } bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); #undef STATE_TRACE diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ad41e8ecf796..53e80cd004b6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1532,6 +1532,34 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_prequeue); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) +{ + u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; + + /* Only socket owner can try to collapse/prune rx queues + * to reduce memory overhead, so add a little headroom here. + * Few sockets backlog are possibly concurrently non empty. + */ + limit += 64*1024; + + /* In case all data was pulled from skb frags (in __pskb_pull_tail()), + * we can fix skb->truesize to its real value to avoid future drops. + * This is valid because skb is not yet charged to the socket. + * It has been noticed pure SACK packets were sometimes dropped + * (if cooked by drivers without copybreak feature). + */ + if (!skb->data_len) + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + + if (unlikely(sk_add_backlog(sk, skb, limit))) { + bh_unlock_sock(sk); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + return true; + } + return false; +} +EXPORT_SYMBOL(tcp_add_backlog); + /* * From tcp_input.c */ @@ -1662,10 +1690,7 @@ process: if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) ret = tcp_v4_do_rcv(sk, skb); - } else if (unlikely(sk_add_backlog(sk, skb, - sk->sk_rcvbuf + sk->sk_sndbuf))) { - bh_unlock_sock(sk); - __NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP); + } else if (tcp_add_backlog(sk, skb)) { goto discard_and_relse; } bh_unlock_sock(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e4f55683af31..5bf460bd299f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1467,10 +1467,7 @@ process: if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) ret = tcp_v6_do_rcv(sk, skb); - } else if (unlikely(sk_add_backlog(sk, skb, - sk->sk_rcvbuf + sk->sk_sndbuf))) { - bh_unlock_sock(sk); - __NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP); + } else if (tcp_add_backlog(sk, skb)) { goto discard_and_relse; } bh_unlock_sock(sk);