summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2020-05-12 06:54:30 -0700
committerDavid S. Miller <davem@davemloft.net>2020-05-12 12:49:47 -0700
commit24adbc1676af4e134e709ddc7f34cf2adc2131e4 (patch)
treeab86c8315f4652959c283cb29739dfeb437da15a /net
parent92db978f0d686468e527d49268e7c7e8d97d334b (diff)
tcp: fix SO_RCVLOWAT hangs with fat skbs
We autotune rcvbuf whenever SO_RCVLOWAT is set to account for 100% overhead in tcp_set_rcvlowat() This works well when skb->len/skb->truesize ratio is bigger than 0.5 But if we receive packets with small MSS, we can end up in a situation where not enough bytes are available in the receive queue to satisfy RCVLOWAT setting. As our sk_rcvbuf limit is hit, we send zero windows in ACK packets, preventing remote peer from sending more data. Even autotuning does not help, because it only triggers at the time user process drains the queue. If no EPOLLIN is generated, this can not happen. Note poll() has a similar issue, after commit c7004482e8dc ("tcp: Respect SO_RCVLOWAT in tcp_poll().") Fixes: 03f45c883c6f ("tcp: avoid extra wakeups for SO_RCVLOWAT users") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp.c14
-rw-r--r--net/ipv4/tcp_input.c3
2 files changed, 13 insertions, 4 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e72bd651d21a..a385fcaaa03b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
int target, struct sock *sk)
{
- return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
- (sk->sk_prot->stream_memory_read ?
- sk->sk_prot->stream_memory_read(sk) : false);
+ int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
+
+ if (avail > 0) {
+ if (avail >= target)
+ return true;
+ if (tcp_rmem_pressure(sk))
+ return true;
+ }
+ if (sk->sk_prot->stream_memory_read)
+ return sk->sk_prot->stream_memory_read(sk);
+ return false;
}
/*
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b996dc1069c5..29c6fc8c7716 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4757,7 +4757,8 @@ void tcp_data_ready(struct sock *sk)
const struct tcp_sock *tp = tcp_sk(sk);
int avail = tp->rcv_nxt - tp->copied_seq;
- if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE))
+ if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
+ !sock_flag(sk, SOCK_DONE))
return;
sk->sk_data_ready(sk);