From 15c041759bfcd9ab0a4e43f1c16e2644977d0467 Mon Sep 17 00:00:00 2001
From: Michal Kubeček <mkubecek@suse.cz>
Date: Fri, 14 Sep 2012 04:59:52 +0000
Subject: tcp: flush DMA queue before sk_wait_data if rcv_wnd is zero
If recv() syscall is called for a TCP socket so that
- IOAT DMA is used
- MSG_WAITALL flag is used
- requested length is bigger than sk_rcvbuf
- enough data has already arrived to bring rcv_wnd to zero
then when tcp_recvmsg() gets to calling sk_wait_data(), receive
window can be still zero while sk_async_wait_queue exhausts
enough space to keep it zero. As this queue isn't cleaned until
the tcp_service_net_dma() call, sk_wait_data() cannot receive
any data and blocks forever.
If zero receive window and non-empty sk_async_wait_queue is
detected before calling sk_wait_data(), process the queue first.
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
(limited to 'net/ipv4/tcp.c')
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2109ff4a1da..bf9a8ab2945 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1762,8 +1762,14 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
}
#ifdef CONFIG_NET_DMA
- if (tp->ucopy.dma_chan)
- dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+ if (tp->ucopy.dma_chan) {
+ if (tp->rcv_wnd == 0 &&
+ !skb_queue_empty(&sk->sk_async_wait_queue)) {
+ tcp_service_net_dma(sk, true);
+ tcp_cleanup_rbuf(sk, copied);
+ } else
+ dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+ }
#endif
if (copied >= target) {
/* Do not sleep, just process backlog. */
--
cgit v1.2.3-70-g09d2
From bc26ccd8fc756749de95606d28314efd0ce5aec3 Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Wed, 19 Sep 2012 09:40:00 +0000
Subject: tcp: restore rcv_wscale in a repair mode (v2)
rcv_wscale is a symetric parameter with snd_wscale.
Both this parameters are set on a connection handshake.
Without this value a remote window size can not be interpreted correctly,
because a value from a packet should be shifted on rcv_wscale.
And one more thing is that wscale_ok should be set too.
This patch doesn't break a backward compatibility.
If someone uses it in a old scheme, a rcv window
will be restored with the same bug (rcv_wscale = 0).
v2: Save backward compatibility on big-endian system. Before
the first two bytes were snd_wscale and the second two bytes were
rcv_wscale. Now snd_wscale is opt_val & 0xFFFF and rcv_wscale >> 16.
This approach is independent on byte ordering.
Cc: David S. Miller <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
CC: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
(limited to 'net/ipv4/tcp.c')
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bf9a8ab2945..5f641934182 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2331,10 +2331,17 @@ static int tcp_repair_options_est(struct tcp_sock *tp,
tp->rx_opt.mss_clamp = opt.opt_val;
break;
case TCPOPT_WINDOW:
- if (opt.opt_val > 14)
- return -EFBIG;
+ {
+ u16 snd_wscale = opt.opt_val & 0xFFFF;
+ u16 rcv_wscale = opt.opt_val >> 16;
+
+ if (snd_wscale > 14 || rcv_wscale > 14)
+ return -EFBIG;
- tp->rx_opt.snd_wscale = opt.opt_val;
+ tp->rx_opt.snd_wscale = snd_wscale;
+ tp->rx_opt.rcv_wscale = rcv_wscale;
+ tp->rx_opt.wscale_ok = 1;
+ }
break;
case TCPOPT_SACK_PERM:
if (opt.opt_val != 0)
--
cgit v1.2.3-70-g09d2