From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: "Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
stable@vger.kernel.org,
"Ilpo J�rvinen" <ilpo.jarvinen@helsinki.fi>,
"Eric Dumazet" <edumazet@google.com>,
"Neal Cardwell" <ncardwell@google.com>,
"David S. Miller" <davem@davemloft.net>
Subject: [ 18/22] tcp: fix for zero packets_in_flight was too broad
Date: Tue, 12 Feb 2013 12:37:01 -0800 [thread overview]
Message-ID: <20130212203416.994086828@linuxfoundation.org> (raw)
In-Reply-To: <20130212203413.459836020@linuxfoundation.org>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=UTF-8, Size: 1846 bytes --]
3.0-stable review patch. If anyone has any objections, please let me know.
------------------
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@helsinki.fi>
[ Upstream commit 6731d2095bd4aef18027c72ef845ab1087c3ba63 ]
There are transients during normal FRTO procedure during which
the packets_in_flight can go to zero between write_queue state
updates and firing the resulting segments out. As FRTO processing
occurs during that window the check must be more precise to
not match "spuriously" :-). More specificly, e.g., when
packets_in_flight is zero but FLAG_DATA_ACKED is true the problematic
branch that set cwnd into zero would not be taken and new segments
might be sent out later.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Tested-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/tcp_input.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3568,8 +3568,7 @@ static int tcp_process_frto(struct sock
((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED)))
tp->undo_marker = 0;
- if (!before(tp->snd_una, tp->frto_highmark) ||
- !tcp_packets_in_flight(tp)) {
+ if (!before(tp->snd_una, tp->frto_highmark)) {
tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
return 1;
}
@@ -3589,6 +3588,11 @@ static int tcp_process_frto(struct sock
}
} else {
if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
+ if (!tcp_packets_in_flight(tp)) {
+ tcp_enter_frto_loss(sk, 2, flag);
+ return true;
+ }
+
/* Prevent sending of new data. */
tp->snd_cwnd = min(tp->snd_cwnd,
tcp_packets_in_flight(tp));
next prev parent reply other threads:[~2013-02-12 20:39 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-12 20:36 [ 00/22] 3.0.64-stable review Greg Kroah-Hartman
2013-02-12 20:36 ` [ 01/22] rtlwifi: Fix the usage of the wrong variable in usb.c Greg Kroah-Hartman
2013-02-12 20:36 ` [ 02/22] virtio_console: Dont access uninitialized data Greg Kroah-Hartman
2013-02-12 20:36 ` [ 03/22] kernel/resource.c: fix stack overflow in __reserve_region_with_split() Greg Kroah-Hartman
2013-02-12 20:36 ` [ 04/22] mac80211: synchronize scan off/on-channel and PS states Greg Kroah-Hartman
2013-02-12 20:36 ` [ 05/22] net: prevent setting ttl=0 via IP_TTL Greg Kroah-Hartman
2013-02-12 20:36 ` [ 06/22] MAINTAINERS: Stephen Hemminger email change Greg Kroah-Hartman
2013-02-12 20:36 ` [ 07/22] isdn/gigaset: fix zero size border case in debug dump Greg Kroah-Hartman
2013-02-12 20:36 ` [ 08/22] r8169: remove the obsolete and incorrect AMD workaround Greg Kroah-Hartman
2013-02-12 20:36 ` [ 09/22] net: loopback: fix a dst refcounting issue Greg Kroah-Hartman
2013-02-12 20:36 ` [ 10/22] pktgen: correctly handle failures when adding a device Greg Kroah-Hartman
2013-02-12 20:36 ` [ 11/22] ipv6: do not create neighbor entries for local delivery Greg Kroah-Hartman
2013-02-12 20:36 ` [ 12/22] packet: fix leakage of tx_ring memory Greg Kroah-Hartman
2013-02-12 20:36 ` [ 13/22] atm/iphase: rename fregt_t -> ffreg_t Greg Kroah-Hartman
2013-02-12 20:36 ` [ 14/22] sctp: refactor sctp_outq_teardown to insure proper re-initalization Greg Kroah-Hartman
2013-02-12 20:36 ` [ 15/22] net: sctp: sctp_setsockopt_auth_key: use kzfree instead of kfree Greg Kroah-Hartman
2013-02-12 20:36 ` [ 16/22] net: sctp: sctp_endpoint_free: zero out secret key data Greg Kroah-Hartman
2013-02-12 20:37 ` [ 17/22] tcp: frto should not set snd_cwnd to 0 Greg Kroah-Hartman
2013-02-12 20:37 ` Greg Kroah-Hartman [this message]
2013-02-12 20:37 ` [ 19/22] tcp: fix MSG_SENDPAGE_NOTLAST logic Greg Kroah-Hartman
2013-02-12 20:37 ` [ 20/22] bridge: Pull ip header into skb->data before looking into ip header Greg Kroah-Hartman
2013-02-12 20:37 ` [ 21/22] tg3: Avoid null pointer dereference in tg3_interrupt in netconsole mode Greg Kroah-Hartman
2013-02-12 20:37 ` [ 22/22] tg3: Fix crc errors on jumbo frame receive Greg Kroah-Hartman
2013-02-13 8:06 ` [ 00/22] 3.0.64-stable review Satoru Takeuchi
2013-02-13 15:51 ` Shuah Khan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20130212203416.994086828@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=ilpo.jarvinen@helsinki.fi \
--cc=linux-kernel@vger.kernel.org \
--cc=ncardwell@google.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).