From dfbafc995304ebb9a9b03f65083e6e9cea143b20 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 24 Jul 2015 18:19:25 +0200 Subject: tcp: fix recv with flags MSG_WAITALL | MSG_PEEK Currently, tcp_recvmsg enters a busy loop in sk_wait_data if called with flags = MSG_WAITALL | MSG_PEEK. sk_wait_data waits for sk_receive_queue not empty, but in this case, the receive queue is not empty, but does not contain any skb that we can use. Add a "last skb seen on receive queue" argument to sk_wait_data, so that it sleeps until the receive queue has new skbs. Link: https://bugzilla.kernel.org/show_bug.cgi?id=99461 Link: https://sourceware.org/bugzilla/show_bug.cgi?id=18493 Link: https://bugzilla.redhat.com/show_bug.cgi?id=1205258 Reported-by: Enrico Scholz Reported-by: Dan Searle Signed-off-by: Sabrina Dubroca Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7f4056785acc..45534a5ab430 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -780,7 +780,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, ret = -EAGAIN; break; } - sk_wait_data(sk, &timeo); + sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -1575,7 +1575,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int target; /* Read at least this many bytes */ long timeo; struct task_struct *user_recv = NULL; - struct sk_buff *skb; + struct sk_buff *skb, *last; u32 urg_hole = 0; if (unlikely(flags & MSG_ERRQUEUE)) @@ -1635,7 +1635,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Next get a buffer. */ + last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { + last = skb; /* Now that we have two receive queues this * shouldn't happen. */ @@ -1754,8 +1756,9 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); - } else - sk_wait_data(sk, &timeo); + } else { + sk_wait_data(sk, &timeo, last); + } if (user_recv) { int chunk; -- cgit v1.2.3 From 6f021c62d64f38092bc2a0c5fe7b81d5e5b21a00 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Aug 2015 12:30:00 -0700 Subject: tcp: fix slow start after idle vs TSO/GSO slow start after idle might reduce cwnd, but we perform this after first packet was cooked and sent. With TSO/GSO, it means that we might send a full TSO packet even if cwnd should have been reduced to IW10. Moving the SSAI check in skb_entail() makes sense, because we slightly reduce number of times this check is done, especially for large send() and TCP Small queue callbacks from softirq context. As Neal pointed out, we also need to perform the check if/when receive window opens. Tested: Following packetdrill test demonstrates the problem // Test of slow start after idle `sysctl -q net.ipv4.tcp_slow_start_after_idle=1` 0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +0 < S 0:0(0) win 65535 +0 > S. 0:0(0) ack 1 +.100 < . 1:1(0) ack 1 win 511 +0 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0 +0 write(4, ..., 26000) = 26000 +0 > . 1:5001(5000) ack 1 +0 > . 5001:10001(5000) ack 1 +0 %{ assert tcpi_snd_cwnd == 10 }% +.100 < . 1:1(0) ack 10001 win 511 +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }% +0 > . 10001:20001(10000) ack 1 +0 > P. 20001:26001(6000) ack 1 +.100 < . 1:1(0) ack 26001 win 511 +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }% +4 write(4, ..., 20000) = 20000 // If slow start after idle works properly, we should send 5 MSS here (cwnd/2) +0 > . 26001:31001(5000) ack 1 +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }% +0 > . 31001:36001(5000) ack 1 Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/tcp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 45534a5ab430..b8b8fa184f75 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -627,6 +627,8 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; + + tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) -- cgit v1.2.3