2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* INET An implementation of the TCP/IP protocol suite for the LINUX
|
|
|
|
* operating system. INET is implemented using the BSD Socket
|
|
|
|
* interface as the means of communication with the user level.
|
|
|
|
*
|
|
|
|
* Implementation of the Transmission Control Protocol(TCP).
|
|
|
|
*
|
2005-05-05 17:16:16 -06:00
|
|
|
* Authors: Ross Biro
|
2005-04-16 16:20:36 -06:00
|
|
|
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
|
|
|
|
* Mark Evans, <evansmp@uhura.aston.ac.uk>
|
|
|
|
* Corey Minyard <wf-rch!minyard@relay.EU.net>
|
|
|
|
* Florian La Roche, <flla@stud.uni-sb.de>
|
|
|
|
* Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
|
|
|
|
* Linus Torvalds, <torvalds@cs.helsinki.fi>
|
|
|
|
* Alan Cox, <gw4pts@gw4pts.ampr.org>
|
|
|
|
* Matthew Dillon, <dillon@apollo.west.oic.com>
|
|
|
|
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
|
|
|
|
* Jorge Cwik, <jorge@laser.satlink.net>
|
|
|
|
*
|
|
|
|
* Fixes:
|
|
|
|
* Alan Cox : Numerous verify_area() calls
|
|
|
|
* Alan Cox : Set the ACK bit on a reset
|
|
|
|
* Alan Cox : Stopped it crashing if it closed while
|
|
|
|
* sk->inuse=1 and was trying to connect
|
|
|
|
* (tcp_err()).
|
|
|
|
* Alan Cox : All icmp error handling was broken
|
|
|
|
* pointers passed where wrong and the
|
|
|
|
* socket was looked up backwards. Nobody
|
|
|
|
* tested any icmp error code obviously.
|
|
|
|
* Alan Cox : tcp_err() now handled properly. It
|
|
|
|
* wakes people on errors. poll
|
|
|
|
* behaves and the icmp error race
|
|
|
|
* has gone by moving it into sock.c
|
|
|
|
* Alan Cox : tcp_send_reset() fixed to work for
|
|
|
|
* everything not just packets for
|
|
|
|
* unknown sockets.
|
|
|
|
* Alan Cox : tcp option processing.
|
|
|
|
* Alan Cox : Reset tweaked (still not 100%) [Had
|
|
|
|
* syn rule wrong]
|
|
|
|
* Herp Rosmanith : More reset fixes
|
|
|
|
* Alan Cox : No longer acks invalid rst frames.
|
|
|
|
* Acking any kind of RST is right out.
|
|
|
|
* Alan Cox : Sets an ignore me flag on an rst
|
|
|
|
* receive otherwise odd bits of prattle
|
|
|
|
* escape still
|
|
|
|
* Alan Cox : Fixed another acking RST frame bug.
|
|
|
|
* Should stop LAN workplace lockups.
|
|
|
|
* Alan Cox : Some tidyups using the new skb list
|
|
|
|
* facilities
|
|
|
|
* Alan Cox : sk->keepopen now seems to work
|
|
|
|
* Alan Cox : Pulls options out correctly on accepts
|
|
|
|
* Alan Cox : Fixed assorted sk->rqueue->next errors
|
|
|
|
* Alan Cox : PSH doesn't end a TCP read. Switched a
|
|
|
|
* bit to skb ops.
|
|
|
|
* Alan Cox : Tidied tcp_data to avoid a potential
|
|
|
|
* nasty.
|
|
|
|
* Alan Cox : Added some better commenting, as the
|
|
|
|
* tcp is hard to follow
|
|
|
|
* Alan Cox : Removed incorrect check for 20 * psh
|
|
|
|
* Michael O'Reilly : ack < copied bug fix.
|
|
|
|
* Johannes Stille : Misc tcp fixes (not all in yet).
|
|
|
|
* Alan Cox : FIN with no memory -> CRASH
|
|
|
|
* Alan Cox : Added socket option proto entries.
|
|
|
|
* Also added awareness of them to accept.
|
|
|
|
* Alan Cox : Added TCP options (SOL_TCP)
|
|
|
|
* Alan Cox : Switched wakeup calls to callbacks,
|
|
|
|
* so the kernel can layer network
|
|
|
|
* sockets.
|
|
|
|
* Alan Cox : Use ip_tos/ip_ttl settings.
|
|
|
|
* Alan Cox : Handle FIN (more) properly (we hope).
|
|
|
|
* Alan Cox : RST frames sent on unsynchronised
|
|
|
|
* state ack error.
|
|
|
|
* Alan Cox : Put in missing check for SYN bit.
|
|
|
|
* Alan Cox : Added tcp_select_window() aka NET2E
|
|
|
|
* window non shrink trick.
|
|
|
|
* Alan Cox : Added a couple of small NET2E timer
|
|
|
|
* fixes
|
|
|
|
* Charles Hedrick : TCP fixes
|
|
|
|
* Toomas Tamm : TCP window fixes
|
|
|
|
* Alan Cox : Small URG fix to rlogin ^C ack fight
|
|
|
|
* Charles Hedrick : Rewrote most of it to actually work
|
|
|
|
* Linus : Rewrote tcp_read() and URG handling
|
|
|
|
* completely
|
|
|
|
* Gerhard Koerting: Fixed some missing timer handling
|
|
|
|
* Matthew Dillon : Reworked TCP machine states as per RFC
|
|
|
|
* Gerhard Koerting: PC/TCP workarounds
|
|
|
|
* Adam Caldwell : Assorted timer/timing errors
|
|
|
|
* Matthew Dillon : Fixed another RST bug
|
|
|
|
* Alan Cox : Move to kernel side addressing changes.
|
|
|
|
* Alan Cox : Beginning work on TCP fastpathing
|
|
|
|
* (not yet usable)
|
|
|
|
* Arnt Gulbrandsen: Turbocharged tcp_check() routine.
|
|
|
|
* Alan Cox : TCP fast path debugging
|
|
|
|
* Alan Cox : Window clamping
|
|
|
|
* Michael Riepe : Bug in tcp_check()
|
|
|
|
* Matt Dillon : More TCP improvements and RST bug fixes
|
|
|
|
* Matt Dillon : Yet more small nasties remove from the
|
|
|
|
* TCP code (Be very nice to this man if
|
|
|
|
* tcp finally works 100%) 8)
|
|
|
|
* Alan Cox : BSD accept semantics.
|
|
|
|
* Alan Cox : Reset on closedown bug.
|
|
|
|
* Peter De Schrijver : ENOTCONN check missing in tcp_sendto().
|
|
|
|
* Michael Pall : Handle poll() after URG properly in
|
|
|
|
* all cases.
|
|
|
|
* Michael Pall : Undo the last fix in tcp_read_urg()
|
|
|
|
* (multi URG PUSH broke rlogin).
|
|
|
|
* Michael Pall : Fix the multi URG PUSH problem in
|
|
|
|
* tcp_readable(), poll() after URG
|
|
|
|
* works now.
|
|
|
|
* Michael Pall : recv(...,MSG_OOB) never blocks in the
|
|
|
|
* BSD api.
|
|
|
|
* Alan Cox : Changed the semantics of sk->socket to
|
|
|
|
* fix a race and a signal problem with
|
|
|
|
* accept() and async I/O.
|
|
|
|
* Alan Cox : Relaxed the rules on tcp_sendto().
|
|
|
|
* Yury Shevchuk : Really fixed accept() blocking problem.
|
|
|
|
* Craig I. Hagan : Allow for BSD compatible TIME_WAIT for
|
|
|
|
* clients/servers which listen in on
|
|
|
|
* fixed ports.
|
|
|
|
* Alan Cox : Cleaned the above up and shrank it to
|
|
|
|
* a sensible code size.
|
|
|
|
* Alan Cox : Self connect lockup fix.
|
|
|
|
* Alan Cox : No connect to multicast.
|
|
|
|
* Ross Biro : Close unaccepted children on master
|
|
|
|
* socket close.
|
|
|
|
* Alan Cox : Reset tracing code.
|
|
|
|
* Alan Cox : Spurious resets on shutdown.
|
|
|
|
* Alan Cox : Giant 15 minute/60 second timer error
|
|
|
|
* Alan Cox : Small whoops in polling before an
|
|
|
|
* accept.
|
|
|
|
* Alan Cox : Kept the state trace facility since
|
|
|
|
* it's handy for debugging.
|
|
|
|
* Alan Cox : More reset handler fixes.
|
|
|
|
* Alan Cox : Started rewriting the code based on
|
|
|
|
* the RFC's for other useful protocol
|
|
|
|
* references see: Comer, KA9Q NOS, and
|
|
|
|
* for a reference on the difference
|
|
|
|
* between specifications and how BSD
|
|
|
|
* works see the 4.4lite source.
|
|
|
|
* A.N.Kuznetsov : Don't time wait on completion of tidy
|
|
|
|
* close.
|
|
|
|
* Linus Torvalds : Fin/Shutdown & copied_seq changes.
|
|
|
|
* Linus Torvalds : Fixed BSD port reuse to work first syn
|
|
|
|
* Alan Cox : Reimplemented timers as per the RFC
|
|
|
|
* and using multiple timers for sanity.
|
|
|
|
* Alan Cox : Small bug fixes, and a lot of new
|
|
|
|
* comments.
|
|
|
|
* Alan Cox : Fixed dual reader crash by locking
|
|
|
|
* the buffers (much like datagram.c)
|
|
|
|
* Alan Cox : Fixed stuck sockets in probe. A probe
|
|
|
|
* now gets fed up of retrying without
|
|
|
|
* (even a no space) answer.
|
|
|
|
* Alan Cox : Extracted closing code better
|
|
|
|
* Alan Cox : Fixed the closing state machine to
|
|
|
|
* resemble the RFC.
|
|
|
|
* Alan Cox : More 'per spec' fixes.
|
|
|
|
* Jorge Cwik : Even faster checksumming.
|
|
|
|
* Alan Cox : tcp_data() doesn't ack illegal PSH
|
|
|
|
* only frames. At least one pc tcp stack
|
|
|
|
* generates them.
|
|
|
|
* Alan Cox : Cache last socket.
|
|
|
|
* Alan Cox : Per route irtt.
|
|
|
|
* Matt Day : poll()->select() match BSD precisely on error
|
|
|
|
* Alan Cox : New buffers
|
|
|
|
* Marc Tamsky : Various sk->prot->retransmits and
|
|
|
|
* sk->retransmits misupdating fixed.
|
|
|
|
* Fixed tcp_write_timeout: stuck close,
|
|
|
|
* and TCP syn retries gets used now.
|
|
|
|
* Mark Yarvis : In tcp_read_wakeup(), don't send an
|
|
|
|
* ack if state is TCP_CLOSED.
|
|
|
|
* Alan Cox : Look up device on a retransmit - routes may
|
|
|
|
* change. Doesn't yet cope with MSS shrink right
|
|
|
|
* but it's a start!
|
|
|
|
* Marc Tamsky : Closing in closing fixes.
|
|
|
|
* Mike Shaver : RFC1122 verifications.
|
|
|
|
* Alan Cox : rcv_saddr errors.
|
|
|
|
* Alan Cox : Block double connect().
|
|
|
|
* Alan Cox : Small hooks for enSKIP.
|
|
|
|
* Alexey Kuznetsov: Path MTU discovery.
|
|
|
|
* Alan Cox : Support soft errors.
|
|
|
|
* Alan Cox : Fix MTU discovery pathological case
|
|
|
|
* when the remote claims no mtu!
|
|
|
|
* Marc Tamsky : TCP_CLOSE fix.
|
|
|
|
* Colin (G3TNE) : Send a reset on syn ack replies in
|
|
|
|
* window but wrong (fixes NT lpd problems)
|
|
|
|
* Pedro Roque : Better TCP window handling, delayed ack.
|
|
|
|
* Joerg Reuter : No modification of locked buffers in
|
|
|
|
* tcp_do_retransmit()
|
|
|
|
* Eric Schenk : Changed receiver side silly window
|
|
|
|
* avoidance algorithm to BSD style
|
|
|
|
* algorithm. This doubles throughput
|
|
|
|
* against machines running Solaris,
|
|
|
|
* and seems to result in general
|
|
|
|
* improvement.
|
|
|
|
* Stefan Magdalinski : adjusted tcp_readable() to fix FIONREAD
|
|
|
|
* Willy Konynenberg : Transparent proxying support.
|
|
|
|
* Mike McLagan : Routing by source
|
|
|
|
* Keith Owens : Do proper merging with partial SKB's in
|
|
|
|
* tcp_do_sendmsg to avoid burstiness.
|
|
|
|
* Eric Schenk : Fix fast close down bug with
|
|
|
|
* shutdown() followed by close().
|
|
|
|
* Andi Kleen : Make poll agree with SIGIO
|
|
|
|
* Salvatore Sanfilippo : Support SO_LINGER with linger == 1 and
|
|
|
|
* lingertime == 0 (RFC 793 ABORT Call)
|
|
|
|
* Hirokazu Takahashi : Use copy_from_user() instead of
|
|
|
|
* csum_and_copy_from_user() if possible.
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or(at your option) any later version.
|
|
|
|
*
|
|
|
|
* Description of States:
|
|
|
|
*
|
|
|
|
* TCP_SYN_SENT sent a connection request, waiting for ack
|
|
|
|
*
|
|
|
|
* TCP_SYN_RECV received a connection request, sent ack,
|
|
|
|
* waiting for final ack in three-way handshake.
|
|
|
|
*
|
|
|
|
* TCP_ESTABLISHED connection established
|
|
|
|
*
|
|
|
|
* TCP_FIN_WAIT1 our side has shutdown, waiting to complete
|
|
|
|
* transmission of remaining buffered data
|
|
|
|
*
|
|
|
|
* TCP_FIN_WAIT2 all buffered data sent, waiting for remote
|
|
|
|
* to shutdown
|
|
|
|
*
|
|
|
|
* TCP_CLOSING both sides have shutdown but we still have
|
|
|
|
* data we have to finish sending
|
|
|
|
*
|
|
|
|
* TCP_TIME_WAIT timeout to catch resent junk before entering
|
|
|
|
* closed, can only be entered from FIN_WAIT2
|
|
|
|
* or CLOSING. Required because the other end
|
|
|
|
* may not have gotten our last ACK causing it
|
|
|
|
* to retransmit the data packet (which we ignore)
|
|
|
|
*
|
|
|
|
* TCP_CLOSE_WAIT remote side has shutdown and is waiting for
|
|
|
|
* us to finish writing our data and to shutdown
|
|
|
|
* (we have to close() to move on to LAST_ACK)
|
|
|
|
*
|
|
|
|
* TCP_LAST_ACK out side has shutdown after remote has
|
|
|
|
* shutdown. There may still be data in our
|
|
|
|
* buffer that we have to finish sending
|
|
|
|
*
|
|
|
|
* TCP_CLOSE socket is finished
|
|
|
|
*/
|
|
|
|
|
2012-03-12 01:03:32 -06:00
|
|
|
#define pr_fmt(fmt) "TCP: " fmt
|
|
|
|
|
2007-08-28 16:50:33 -06:00
|
|
|
#include <linux/kernel.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/fcntl.h>
|
|
|
|
#include <linux/poll.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/fs.h>
|
2007-11-07 00:30:13 -07:00
|
|
|
#include <linux/skbuff.h>
|
2008-07-03 04:22:02 -06:00
|
|
|
#include <linux/scatterlist.h>
|
2007-11-07 00:30:13 -07:00
|
|
|
#include <linux/splice.h>
|
|
|
|
#include <linux/net.h>
|
|
|
|
#include <linux/socket.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <linux/random.h>
|
|
|
|
#include <linux/bootmem.h>
|
2008-06-27 18:23:57 -06:00
|
|
|
#include <linux/highmem.h>
|
|
|
|
#include <linux/swap.h>
|
2006-03-25 02:36:56 -07:00
|
|
|
#include <linux/cache.h>
|
2006-06-22 04:02:40 -06:00
|
|
|
#include <linux/err.h>
|
2006-11-14 20:07:45 -07:00
|
|
|
#include <linux/crypto.h>
|
2009-12-02 11:12:09 -07:00
|
|
|
#include <linux/time.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
|
|
|
#include <linux/slab.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#include <net/icmp.h>
|
2012-07-19 00:43:09 -06:00
|
|
|
#include <net/inet_common.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <net/tcp.h>
|
|
|
|
#include <net/xfrm.h>
|
|
|
|
#include <net/ip.h>
|
2006-05-23 19:05:53 -06:00
|
|
|
#include <net/netdma.h>
|
2007-11-07 00:30:13 -07:00
|
|
|
#include <net/sock.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <asm/ioctls.h>
|
2013-07-10 08:13:17 -06:00
|
|
|
#include <net/busy_poll.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-09-22 15:15:41 -06:00
|
|
|
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
tcp: TSO packets automatic sizing
After hearing many people over past years complaining against TSO being
bursty or even buggy, we are proud to present automatic sizing of TSO
packets.
One part of the problem is that tcp_tso_should_defer() uses an heuristic
relying on upcoming ACKS instead of a timer, but more generally, having
big TSO packets makes little sense for low rates, as it tends to create
micro bursts on the network, and general consensus is to reduce the
buffering amount.
This patch introduces a per socket sk_pacing_rate, that approximates
the current sending rate, and allows us to size the TSO packets so
that we try to send one packet every ms.
This field could be set by other transports.
Patch has no impact for high speed flows, where having large TSO packets
makes sense to reach line rate.
For other flows, this helps better packet scheduling and ACK clocking.
This patch increases performance of TCP flows in lossy environments.
A new sysctl (tcp_min_tso_segs) is added, to specify the
minimal size of a TSO packet (default being 2).
A follow-up patch will provide a new packet scheduler (FQ), using
sk_pacing_rate as an input to perform optional per flow pacing.
This explains why we chose to set sk_pacing_rate to twice the current
rate, allowing 'slow start' ramp up.
sk_pacing_rate = 2 * cwnd * mss / srtt
v2: Neal Cardwell reported a suspect deferring of last two segments on
initial write of 10 MSS, I had to change tcp_tso_should_defer() to take
into account tp->xmit_size_goal_segs
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Van Jacobson <vanj@google.com>
Cc: Tom Herbert <therbert@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-27 06:46:32 -06:00
|
|
|
int sysctl_tcp_min_tso_segs __read_mostly = 2;
|
|
|
|
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
int sysctl_tcp_autocorking __read_mostly = 1;
|
|
|
|
|
2008-11-25 22:17:14 -07:00
|
|
|
struct percpu_counter tcp_orphan_count;
|
2005-08-09 21:11:41 -06:00
|
|
|
EXPORT_SYMBOL_GPL(tcp_orphan_count);
|
|
|
|
|
2013-10-19 17:25:36 -06:00
|
|
|
long sysctl_tcp_mem[3] __read_mostly;
|
2006-03-25 02:36:56 -07:00
|
|
|
int sysctl_tcp_wmem[3] __read_mostly;
|
|
|
|
int sysctl_tcp_rmem[3] __read_mostly;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2013-10-19 17:25:36 -06:00
|
|
|
EXPORT_SYMBOL(sysctl_tcp_mem);
|
2005-04-16 16:20:36 -06:00
|
|
|
EXPORT_SYMBOL(sysctl_tcp_rmem);
|
|
|
|
EXPORT_SYMBOL(sysctl_tcp_wmem);
|
|
|
|
|
2010-11-09 16:24:26 -07:00
|
|
|
atomic_long_t tcp_memory_allocated; /* Current allocated memory. */
|
2005-04-16 16:20:36 -06:00
|
|
|
EXPORT_SYMBOL(tcp_memory_allocated);
|
2008-11-25 22:16:35 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Current number of TCP sockets.
|
|
|
|
*/
|
|
|
|
struct percpu_counter tcp_sockets_allocated;
|
2005-04-16 16:20:36 -06:00
|
|
|
EXPORT_SYMBOL(tcp_sockets_allocated);
|
|
|
|
|
2007-11-07 00:30:13 -07:00
|
|
|
/*
|
|
|
|
* TCP splice context
|
|
|
|
*/
|
|
|
|
struct tcp_splice_state {
|
|
|
|
struct pipe_inode_info *pipe;
|
|
|
|
size_t len;
|
|
|
|
unsigned int flags;
|
|
|
|
};
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* Pressure flag: try to collapse.
|
|
|
|
* Technical note: it is used by multiple contexts non atomically.
|
2007-12-31 01:11:19 -07:00
|
|
|
* All the __sk_mem_schedule() is of this nature: accounting
|
2005-04-16 16:20:36 -06:00
|
|
|
* is strict, actions are advisory and have some latency.
|
|
|
|
*/
|
2007-03-27 14:58:31 -06:00
|
|
|
int tcp_memory_pressure __read_mostly;
|
2005-04-16 16:20:36 -06:00
|
|
|
EXPORT_SYMBOL(tcp_memory_pressure);
|
|
|
|
|
2008-07-16 21:28:10 -06:00
|
|
|
void tcp_enter_memory_pressure(struct sock *sk)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
if (!tcp_memory_pressure) {
|
2008-07-16 21:30:14 -06:00
|
|
|
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
|
2005-04-16 16:20:36 -06:00
|
|
|
tcp_memory_pressure = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_enter_memory_pressure);
|
|
|
|
|
2009-10-19 04:10:40 -06:00
|
|
|
/* Convert seconds to retransmits based on initial and max timeout */
|
|
|
|
static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
|
|
|
|
{
|
|
|
|
u8 res = 0;
|
|
|
|
|
|
|
|
if (seconds > 0) {
|
|
|
|
int period = timeout;
|
|
|
|
|
|
|
|
res = 1;
|
|
|
|
while (seconds > period && res < 255) {
|
|
|
|
res++;
|
|
|
|
timeout <<= 1;
|
|
|
|
if (timeout > rto_max)
|
|
|
|
timeout = rto_max;
|
|
|
|
period += timeout;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Convert retransmits to seconds based on initial and max timeout */
|
|
|
|
static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
|
|
|
|
{
|
|
|
|
int period = 0;
|
|
|
|
|
|
|
|
if (retrans > 0) {
|
|
|
|
period = timeout;
|
|
|
|
while (--retrans) {
|
|
|
|
timeout <<= 1;
|
|
|
|
if (timeout > rto_max)
|
|
|
|
timeout = rto_max;
|
|
|
|
period += timeout;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return period;
|
|
|
|
}
|
|
|
|
|
2012-04-19 03:55:21 -06:00
|
|
|
/* Address-family independent initialization for a tcp_sock.
|
|
|
|
*
|
|
|
|
* NOTE: A lot of things set to zero explicitly by call to
|
|
|
|
* sk_alloc() so need not be done here.
|
|
|
|
*/
|
|
|
|
void tcp_init_sock(struct sock *sk)
|
|
|
|
{
|
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
2014-01-06 10:36:12 -07:00
|
|
|
__skb_queue_head_init(&tp->out_of_order_queue);
|
2012-04-19 03:55:21 -06:00
|
|
|
tcp_init_xmit_timers(sk);
|
|
|
|
tcp_prequeue_init(tp);
|
tcp: TCP Small Queues
This introduce TSQ (TCP Small Queues)
TSQ goal is to reduce number of TCP packets in xmit queues (qdisc &
device queues), to reduce RTT and cwnd bias, part of the bufferbloat
problem.
sk->sk_wmem_alloc not allowed to grow above a given limit,
allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a
given time.
TSO packets are sized/capped to half the limit, so that we have two
TSO packets in flight, allowing better bandwidth use.
As a side effect, setting the limit to 40000 automatically reduces the
standard gso max limit (65536) to 40000/2 : It can help to reduce
latencies of high prio packets, having smaller TSO packets.
This means we divert sock_wfree() to a tcp_wfree() handler, to
queue/send following frames when skb_orphan() [2] is called for the
already queued skbs.
Results on my dev machines (tg3/ixgbe nics) are really impressive,
using standard pfifo_fast, and with or without TSO/GSO.
Without reduction of nominal bandwidth, we have reduction of buffering
per bulk sender :
< 1ms on Gbit (instead of 50ms with TSO)
< 8ms on 100Mbit (instead of 132 ms)
I no longer have 4 MBytes backlogged in qdisc by a single netperf
session, and both side socket autotuning no longer use 4 Mbytes.
As skb destructor cannot restart xmit itself ( as qdisc lock might be
taken at this point ), we delegate the work to a tasklet. We use one
tasklest per cpu for performance reasons.
If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag.
This flag is tested in a new protocol method called from release_sock(),
to eventually send new segments.
[1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable
[2] skb_orphan() is usually called at TX completion time,
but some drivers call it in their start_xmit() handler.
These drivers should at least use BQL, or else a single TCP
session can still fill the whole NIC TX ring, since TSQ will
have no effect.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Dave Taht <dave.taht@bufferbloat.net>
Cc: Tom Herbert <therbert@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-10 23:50:31 -06:00
|
|
|
INIT_LIST_HEAD(&tp->tsq_node);
|
2012-04-19 03:55:21 -06:00
|
|
|
|
|
|
|
icsk->icsk_rto = TCP_TIMEOUT_INIT;
|
2014-02-26 15:02:48 -07:00
|
|
|
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
|
2012-04-19 03:55:21 -06:00
|
|
|
|
|
|
|
/* So many TCP implementations out there (incorrectly) count the
|
|
|
|
* initial SYN frame in their delayed-ACK and congestion control
|
|
|
|
* algorithms that we must have the following bandaid to talk
|
|
|
|
* efficiently to them. -DaveM
|
|
|
|
*/
|
|
|
|
tp->snd_cwnd = TCP_INIT_CWND;
|
|
|
|
|
|
|
|
/* See draft-stevens-tcpca-spec-01 for discussion of the
|
|
|
|
* initialization of these values.
|
|
|
|
*/
|
|
|
|
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
|
|
|
|
tp->snd_cwnd_clamp = ~0;
|
|
|
|
tp->mss_cache = TCP_MSS_DEFAULT;
|
|
|
|
|
|
|
|
tp->reordering = sysctl_tcp_reordering;
|
2012-05-02 07:30:03 -06:00
|
|
|
tcp_enable_early_retrans(tp);
|
2012-04-19 03:55:21 -06:00
|
|
|
icsk->icsk_ca_ops = &tcp_init_congestion_ops;
|
|
|
|
|
2013-02-10 22:50:17 -07:00
|
|
|
tp->tsoffset = 0;
|
|
|
|
|
2012-04-19 03:55:21 -06:00
|
|
|
sk->sk_state = TCP_CLOSE;
|
|
|
|
|
|
|
|
sk->sk_write_space = sk_stream_write_space;
|
|
|
|
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
|
|
|
|
|
|
|
|
icsk->icsk_sync_mss = tcp_sync_mss;
|
|
|
|
|
|
|
|
sk->sk_sndbuf = sysctl_tcp_wmem[1];
|
|
|
|
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
|
|
|
|
|
|
|
|
local_bh_disable();
|
|
|
|
sock_update_memcg(sk);
|
|
|
|
sk_sockets_allocated_inc(sk);
|
|
|
|
local_bh_enable();
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_init_sock);
|
|
|
|
|
2014-08-06 13:09:44 -06:00
|
|
|
static void tcp_tx_timestamp(struct sock *sk, struct sk_buff *skb)
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
{
|
2014-08-06 13:09:44 -06:00
|
|
|
if (sk->sk_tsflags) {
|
|
|
|
struct skb_shared_info *shinfo = skb_shinfo(skb);
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
|
2014-08-06 13:09:44 -06:00
|
|
|
sock_tx_timestamp(sk, &shinfo->tx_flags);
|
|
|
|
if (shinfo->tx_flags & SKBTX_ANY_TSTAMP)
|
|
|
|
shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
|
|
|
|
}
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* Wait for a TCP event.
|
|
|
|
*
|
|
|
|
* Note that we don't need to lock the socket, as the upper poll layers
|
|
|
|
* take care of normal races (between the test and the event) and we don't
|
|
|
|
* go look at any of the socket buffers directly.
|
|
|
|
*/
|
|
|
|
unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
|
|
|
|
{
|
|
|
|
unsigned int mask;
|
|
|
|
struct sock *sk = sock->sk;
|
2011-10-21 03:22:42 -06:00
|
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2013-05-31 07:15:38 -06:00
|
|
|
sock_rps_record_flow(sk);
|
|
|
|
|
2010-04-20 07:03:51 -06:00
|
|
|
sock_poll_wait(file, sk_sleep(sk), wait);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (sk->sk_state == TCP_LISTEN)
|
2005-08-23 22:52:58 -06:00
|
|
|
return inet_csk_listen_poll(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* Socket is not locked. We are protected from async events
|
2008-07-16 21:13:43 -06:00
|
|
|
* by poll logic and correct handling of state changes
|
|
|
|
* made by other threads is impossible in any case.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
|
|
|
|
|
|
|
mask = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* POLLHUP is certainly not done right. But poll() doesn't
|
|
|
|
* have a notion of HUP in just one direction, and for a
|
|
|
|
* socket the read side is more interesting.
|
|
|
|
*
|
|
|
|
* Some poll() documentation says that POLLHUP is incompatible
|
|
|
|
* with the POLLOUT/POLLWR flags, so somebody should check this
|
|
|
|
* all. But careful, it tends to be safer to return too many
|
|
|
|
* bits than too few, and you can easily break real applications
|
|
|
|
* if you don't tell them that something has hung up!
|
|
|
|
*
|
|
|
|
* Check-me.
|
|
|
|
*
|
|
|
|
* Check number 1. POLLHUP is _UNMASKABLE_ event (see UNIX98 and
|
|
|
|
* our fs/select.c). It means that after we received EOF,
|
|
|
|
* poll always returns immediately, making impossible poll() on write()
|
|
|
|
* in state CLOSE_WAIT. One solution is evident --- to set POLLHUP
|
|
|
|
* if and only if shutdown has been made in both directions.
|
|
|
|
* Actually, it is interesting to look how Solaris and DUX
|
2008-07-16 21:13:43 -06:00
|
|
|
* solve this dilemma. I would prefer, if POLLHUP were maskable,
|
2005-04-16 16:20:36 -06:00
|
|
|
* then we could set it on SND_SHUTDOWN. BTW examples given
|
|
|
|
* in Stevens' books assume exactly this behaviour, it explains
|
2008-07-16 21:13:43 -06:00
|
|
|
* why POLLHUP is incompatible with POLLOUT. --ANK
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* NOTE. Check for TCP_CLOSE is added. The goal is to prevent
|
|
|
|
* blocking on fresh not-connected or disconnected socket. --ANK
|
|
|
|
*/
|
|
|
|
if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
|
|
|
|
mask |= POLLHUP;
|
|
|
|
if (sk->sk_shutdown & RCV_SHUTDOWN)
|
2006-03-25 04:07:39 -07:00
|
|
|
mask |= POLLIN | POLLRDNORM | POLLRDHUP;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-08-31 06:29:12 -06:00
|
|
|
/* Connected or passive Fast Open socket? */
|
|
|
|
if (sk->sk_state != TCP_SYN_SENT &&
|
|
|
|
(sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) {
|
2008-10-06 11:43:54 -06:00
|
|
|
int target = sock_rcvlowat(sk, 0, INT_MAX);
|
|
|
|
|
|
|
|
if (tp->urg_seq == tp->copied_seq &&
|
|
|
|
!sock_flag(sk, SOCK_URGINLINE) &&
|
|
|
|
tp->urg_data)
|
2010-03-18 21:29:24 -06:00
|
|
|
target++;
|
2008-10-06 11:43:54 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Potential race condition. If read of tp below will
|
|
|
|
* escape above sk->sk_state, we can be illegally awaken
|
|
|
|
* in SYN_* states. */
|
2008-10-06 11:43:54 -06:00
|
|
|
if (tp->rcv_nxt - tp->copied_seq >= target)
|
2005-04-16 16:20:36 -06:00
|
|
|
mask |= POLLIN | POLLRDNORM;
|
|
|
|
|
|
|
|
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
|
2013-07-22 21:26:31 -06:00
|
|
|
if (sk_stream_is_writeable(sk)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
mask |= POLLOUT | POLLWRNORM;
|
|
|
|
} else { /* send SIGIO later */
|
|
|
|
set_bit(SOCK_ASYNC_NOSPACE,
|
|
|
|
&sk->sk_socket->flags);
|
|
|
|
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
|
|
|
|
|
|
|
|
/* Race breaker. If space is freed after
|
|
|
|
* wspace test but before the flags are set,
|
|
|
|
* IO signal will be lost.
|
|
|
|
*/
|
2013-07-22 21:26:31 -06:00
|
|
|
if (sk_stream_is_writeable(sk))
|
2005-04-16 16:20:36 -06:00
|
|
|
mask |= POLLOUT | POLLWRNORM;
|
|
|
|
}
|
2010-08-24 10:05:48 -06:00
|
|
|
} else
|
|
|
|
mask |= POLLOUT | POLLWRNORM;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (tp->urg_data & TCP_URG_VALID)
|
|
|
|
mask |= POLLPRI;
|
|
|
|
}
|
2010-09-20 16:42:05 -06:00
|
|
|
/* This barrier is coupled with smp_wmb() in tcp_reset() */
|
|
|
|
smp_rmb();
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
|
2010-09-20 16:42:05 -06:00
|
|
|
mask |= POLLERR;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
return mask;
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_poll);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
|
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
int answ;
|
2012-10-21 14:06:56 -06:00
|
|
|
bool slow;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
switch (cmd) {
|
|
|
|
case SIOCINQ:
|
|
|
|
if (sk->sk_state == TCP_LISTEN)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2012-10-21 14:06:56 -06:00
|
|
|
slow = lock_sock_fast(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
|
|
|
|
answ = 0;
|
|
|
|
else if (sock_flag(sk, SOCK_URGINLINE) ||
|
|
|
|
!tp->urg_data ||
|
|
|
|
before(tp->urg_seq, tp->copied_seq) ||
|
|
|
|
!before(tp->urg_seq, tp->rcv_nxt)) {
|
2009-05-28 22:35:47 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
answ = tp->rcv_nxt - tp->copied_seq;
|
|
|
|
|
2012-10-18 03:14:12 -06:00
|
|
|
/* Subtract 1, if FIN was received */
|
|
|
|
if (answ && sock_flag(sk, SOCK_DONE))
|
|
|
|
answ--;
|
2005-04-16 16:20:36 -06:00
|
|
|
} else
|
|
|
|
answ = tp->urg_seq - tp->copied_seq;
|
2012-10-21 14:06:56 -06:00
|
|
|
unlock_sock_fast(sk, slow);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case SIOCATMARK:
|
|
|
|
answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
|
|
|
|
break;
|
|
|
|
case SIOCOUTQ:
|
|
|
|
if (sk->sk_state == TCP_LISTEN)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
|
|
|
|
answ = 0;
|
|
|
|
else
|
|
|
|
answ = tp->write_seq - tp->snd_una;
|
|
|
|
break;
|
2011-03-09 15:08:09 -07:00
|
|
|
case SIOCOUTQNSD:
|
|
|
|
if (sk->sk_state == TCP_LISTEN)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
|
|
|
|
answ = 0;
|
|
|
|
else
|
|
|
|
answ = tp->write_seq - tp->snd_nxt;
|
|
|
|
break;
|
2005-04-16 16:20:36 -06:00
|
|
|
default:
|
|
|
|
return -ENOIOCTLCMD;
|
2007-04-20 18:09:22 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
return put_user(answ, (int __user *)arg);
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_ioctl);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
|
|
|
|
{
|
2011-09-27 11:25:05 -06:00
|
|
|
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
|
2005-04-16 16:20:36 -06:00
|
|
|
tp->pushed_seq = tp->write_seq;
|
|
|
|
}
|
|
|
|
|
2012-05-16 17:15:34 -06:00
|
|
|
static inline bool forced_push(const struct tcp_sock *tp)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
|
|
|
|
}
|
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
2006-11-17 14:59:12 -07:00
|
|
|
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
|
|
|
|
|
|
|
|
skb->csum = 0;
|
|
|
|
tcb->seq = tcb->end_seq = tp->write_seq;
|
2011-09-27 11:25:05 -06:00
|
|
|
tcb->tcp_flags = TCPHDR_ACK;
|
2006-11-17 14:59:12 -07:00
|
|
|
tcb->sacked = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
skb_header_release(skb);
|
2007-03-07 13:12:44 -07:00
|
|
|
tcp_add_write_queue_tail(sk, skb);
|
2007-12-31 01:11:19 -07:00
|
|
|
sk->sk_wmem_queued += skb->truesize;
|
|
|
|
sk_mem_charge(sk, skb->truesize);
|
2005-08-23 11:13:06 -06:00
|
|
|
if (tp->nonagle & TCP_NAGLE_PUSH)
|
2007-02-09 07:24:47 -07:00
|
|
|
tp->nonagle &= ~TCP_NAGLE_PUSH;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2009-12-10 00:16:52 -07:00
|
|
|
static inline void tcp_mark_urg(struct tcp_sock *tp, int flags)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2008-10-07 15:43:06 -06:00
|
|
|
if (flags & MSG_OOB)
|
2005-04-16 16:20:36 -06:00
|
|
|
tp->snd_up = tp->write_seq;
|
|
|
|
}
|
|
|
|
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
/* If a not yet filled skb is pushed, do not send it if
|
tcp: autocork should not hold first packet in write queue
Willem noticed a TCP_RR regression caused by TCP autocorking
on a Mellanox test bed. MLX4_EN_TX_COAL_TIME is 16 us, which can be
right above RTT between hosts.
We can receive a ACK for a packet still in NIC TX ring buffer or in a
softnet completion queue.
Fix this by always pushing the skb if it is at the head of write queue.
Also, as TX completion is lockless, it's safer to perform sk_wmem_alloc
test after setting TSQ_THROTTLED.
erd:~# MIB="MIN_LATENCY,MEAN_LATENCY,MAX_LATENCY,P99_LATENCY,STDDEV_LATENCY"
erd:~# ./netperf -H remote -t TCP_RR -- -o $MIB | tail -n 1
(repeat 3 times)
Before patch :
18,1049.87,41004,39631,6295.47
17,239.52,40804,48,2912.79
18,348.40,40877,54,3573.39
After patch :
18,22.84,4606,38,16.39
17,21.56,2871,36,13.51
17,22.46,2705,37,11.83
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: f54b311142a9 ("tcp: auto corking")
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-17 10:58:30 -07:00
|
|
|
* we have data packets in Qdisc or NIC queues :
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
* Because TX completion will happen shortly, it gives a chance
|
|
|
|
* to coalesce future sendmsg() payload into this skb, without
|
|
|
|
* need for a timer, and with no latency trade off.
|
|
|
|
* As packets containing data payload have a bigger truesize
|
tcp: autocork should not hold first packet in write queue
Willem noticed a TCP_RR regression caused by TCP autocorking
on a Mellanox test bed. MLX4_EN_TX_COAL_TIME is 16 us, which can be
right above RTT between hosts.
We can receive a ACK for a packet still in NIC TX ring buffer or in a
softnet completion queue.
Fix this by always pushing the skb if it is at the head of write queue.
Also, as TX completion is lockless, it's safer to perform sk_wmem_alloc
test after setting TSQ_THROTTLED.
erd:~# MIB="MIN_LATENCY,MEAN_LATENCY,MAX_LATENCY,P99_LATENCY,STDDEV_LATENCY"
erd:~# ./netperf -H remote -t TCP_RR -- -o $MIB | tail -n 1
(repeat 3 times)
Before patch :
18,1049.87,41004,39631,6295.47
17,239.52,40804,48,2912.79
18,348.40,40877,54,3573.39
After patch :
18,22.84,4606,38,16.39
17,21.56,2871,36,13.51
17,22.46,2705,37,11.83
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: f54b311142a9 ("tcp: auto corking")
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-17 10:58:30 -07:00
|
|
|
* than pure acks (dataless) packets, the last checks prevent
|
|
|
|
* autocorking if we only have an ACK in Qdisc/NIC queues,
|
|
|
|
* or if TX completion was delayed after we processed ACK packet.
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
*/
|
|
|
|
static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
|
|
|
|
int size_goal)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
return skb->len < size_goal &&
|
|
|
|
sysctl_tcp_autocorking &&
|
tcp: autocork should not hold first packet in write queue
Willem noticed a TCP_RR regression caused by TCP autocorking
on a Mellanox test bed. MLX4_EN_TX_COAL_TIME is 16 us, which can be
right above RTT between hosts.
We can receive a ACK for a packet still in NIC TX ring buffer or in a
softnet completion queue.
Fix this by always pushing the skb if it is at the head of write queue.
Also, as TX completion is lockless, it's safer to perform sk_wmem_alloc
test after setting TSQ_THROTTLED.
erd:~# MIB="MIN_LATENCY,MEAN_LATENCY,MAX_LATENCY,P99_LATENCY,STDDEV_LATENCY"
erd:~# ./netperf -H remote -t TCP_RR -- -o $MIB | tail -n 1
(repeat 3 times)
Before patch :
18,1049.87,41004,39631,6295.47
17,239.52,40804,48,2912.79
18,348.40,40877,54,3573.39
After patch :
18,22.84,4606,38,16.39
17,21.56,2871,36,13.51
17,22.46,2705,37,11.83
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: f54b311142a9 ("tcp: auto corking")
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-17 10:58:30 -07:00
|
|
|
skb != tcp_write_queue_head(sk) &&
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
atomic_read(&sk->sk_wmem_alloc) > skb->truesize;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void tcp_push(struct sock *sk, int flags, int mss_now,
|
|
|
|
int nonagle, int size_goal)
|
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
struct sk_buff *skb;
|
2009-12-10 00:16:52 -07:00
|
|
|
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
if (!tcp_send_head(sk))
|
|
|
|
return;
|
2009-12-10 00:16:52 -07:00
|
|
|
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
skb = tcp_write_queue_tail(sk);
|
|
|
|
if (!(flags & MSG_MORE) || forced_push(tp))
|
|
|
|
tcp_mark_push(tp, skb);
|
|
|
|
|
|
|
|
tcp_mark_urg(tp, flags);
|
|
|
|
|
|
|
|
if (tcp_should_autocork(sk, skb, size_goal)) {
|
|
|
|
|
|
|
|
/* avoid atomic op if TSQ_THROTTLED bit is already set */
|
|
|
|
if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
|
|
|
|
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
|
|
|
|
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
|
|
|
|
}
|
tcp: autocork should not hold first packet in write queue
Willem noticed a TCP_RR regression caused by TCP autocorking
on a Mellanox test bed. MLX4_EN_TX_COAL_TIME is 16 us, which can be
right above RTT between hosts.
We can receive a ACK for a packet still in NIC TX ring buffer or in a
softnet completion queue.
Fix this by always pushing the skb if it is at the head of write queue.
Also, as TX completion is lockless, it's safer to perform sk_wmem_alloc
test after setting TSQ_THROTTLED.
erd:~# MIB="MIN_LATENCY,MEAN_LATENCY,MAX_LATENCY,P99_LATENCY,STDDEV_LATENCY"
erd:~# ./netperf -H remote -t TCP_RR -- -o $MIB | tail -n 1
(repeat 3 times)
Before patch :
18,1049.87,41004,39631,6295.47
17,239.52,40804,48,2912.79
18,348.40,40877,54,3573.39
After patch :
18,22.84,4606,38,16.39
17,21.56,2871,36,13.51
17,22.46,2705,37,11.83
Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: f54b311142a9 ("tcp: auto corking")
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-17 10:58:30 -07:00
|
|
|
/* It is possible TX completion already happened
|
|
|
|
* before we set TSQ_THROTTLED.
|
|
|
|
*/
|
|
|
|
if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize)
|
|
|
|
return;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
|
|
|
|
if (flags & MSG_MORE)
|
|
|
|
nonagle = TCP_NAGLE_CORK;
|
|
|
|
|
|
|
|
__tcp_push_pending_frames(sk, mss_now, nonagle);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2007-11-07 00:32:26 -07:00
|
|
|
static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
|
|
|
|
unsigned int offset, size_t len)
|
2007-11-07 00:30:13 -07:00
|
|
|
{
|
|
|
|
struct tcp_splice_state *tss = rd_desc->arg.data;
|
2009-01-13 17:04:36 -07:00
|
|
|
int ret;
|
2007-11-07 00:30:13 -07:00
|
|
|
|
2009-01-26 23:15:31 -07:00
|
|
|
ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len),
|
|
|
|
tss->flags);
|
2009-01-13 17:04:36 -07:00
|
|
|
if (ret > 0)
|
|
|
|
rd_desc->count -= ret;
|
|
|
|
return ret;
|
2007-11-07 00:30:13 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
|
|
|
|
{
|
|
|
|
/* Store TCP splice context information in read_descriptor_t. */
|
|
|
|
read_descriptor_t rd_desc = {
|
|
|
|
.arg.data = tss,
|
2009-01-13 17:04:36 -07:00
|
|
|
.count = tss->len,
|
2007-11-07 00:30:13 -07:00
|
|
|
};
|
|
|
|
|
|
|
|
return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* tcp_splice_read - splice data from TCP socket to a pipe
|
|
|
|
* @sock: socket to splice from
|
|
|
|
* @ppos: position (not valid)
|
|
|
|
* @pipe: pipe to splice to
|
|
|
|
* @len: number of bytes to splice
|
|
|
|
* @flags: splice modifier flags
|
|
|
|
*
|
|
|
|
* Description:
|
|
|
|
* Will read pages from given socket and fill them into a pipe.
|
|
|
|
*
|
|
|
|
**/
|
|
|
|
ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
|
|
|
|
struct pipe_inode_info *pipe, size_t len,
|
|
|
|
unsigned int flags)
|
|
|
|
{
|
|
|
|
struct sock *sk = sock->sk;
|
|
|
|
struct tcp_splice_state tss = {
|
|
|
|
.pipe = pipe,
|
|
|
|
.len = len,
|
|
|
|
.flags = flags,
|
|
|
|
};
|
|
|
|
long timeo;
|
|
|
|
ssize_t spliced;
|
|
|
|
int ret;
|
|
|
|
|
2010-07-12 15:00:12 -06:00
|
|
|
sock_rps_record_flow(sk);
|
2007-11-07 00:30:13 -07:00
|
|
|
/*
|
|
|
|
* We can't seek on a socket input
|
|
|
|
*/
|
|
|
|
if (unlikely(*ppos))
|
|
|
|
return -ESPIPE;
|
|
|
|
|
|
|
|
ret = spliced = 0;
|
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
|
net: splice() from tcp to pipe should take into account O_NONBLOCK
tcp_splice_read() doesnt take into account socket's O_NONBLOCK flag
Before this patch :
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE);
causes a random endless block (if pipe is full) and
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE | SPLICE_F_NONBLOCK);
will return 0 immediately if the TCP buffer is empty.
User application has no way to instruct splice() that socket should be in blocking mode
but pipe in nonblock more.
Many projects cannot use splice(tcp -> pipe) because of this flaw.
http://git.samba.org/?p=samba.git;a=history;f=source3/lib/recvfile.c;h=ea0159642137390a0f7e57a123684e6e63e47581;hb=HEAD
http://lkml.indiana.edu/hypermail/linux/kernel/0807.2/0687.html
Linus introduced SPLICE_F_NONBLOCK in commit 29e350944fdc2dfca102500790d8ad6d6ff4f69d
(splice: add SPLICE_F_NONBLOCK flag )
It doesn't make the splice itself necessarily nonblocking (because the
actual file descriptors that are spliced from/to may block unless they
have the O_NONBLOCK flag set), but it makes the splice pipe operations
nonblocking.
Linus intention was clear : let SPLICE_F_NONBLOCK control the splice pipe mode only
This patch instruct tcp_splice_read() to use the underlying file O_NONBLOCK
flag, as other socket operations do.
Users will then call :
splice(socket,0,pipe,0,128*1024,SPLICE_F_MOVE | SPLICE_F_NONBLOCK );
to block on data coming from socket (if file is in blocking mode),
and not block on pipe output (to avoid deadlock)
First version of this patch was submitted by Octavian Purdila
Reported-by: Volker Lendecke <vl@samba.org>
Reported-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Octavian Purdila <opurdila@ixiacom.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-01 16:26:00 -06:00
|
|
|
timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
|
2007-11-07 00:30:13 -07:00
|
|
|
while (tss.len) {
|
|
|
|
ret = __tcp_splice_read(sk, &tss);
|
|
|
|
if (ret < 0)
|
|
|
|
break;
|
|
|
|
else if (!ret) {
|
|
|
|
if (spliced)
|
|
|
|
break;
|
|
|
|
if (sock_flag(sk, SOCK_DONE))
|
|
|
|
break;
|
|
|
|
if (sk->sk_err) {
|
|
|
|
ret = sock_error(sk);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (sk->sk_shutdown & RCV_SHUTDOWN)
|
|
|
|
break;
|
|
|
|
if (sk->sk_state == TCP_CLOSE) {
|
|
|
|
/*
|
|
|
|
* This occurs when user tries to read
|
|
|
|
* from never connected socket.
|
|
|
|
*/
|
|
|
|
if (!sock_flag(sk, SOCK_DONE))
|
|
|
|
ret = -ENOTCONN;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (!timeo) {
|
|
|
|
ret = -EAGAIN;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
sk_wait_data(sk, &timeo);
|
|
|
|
if (signal_pending(current)) {
|
|
|
|
ret = sock_intr_errno(timeo);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
tss.len -= ret;
|
|
|
|
spliced += ret;
|
|
|
|
|
2009-01-13 17:04:36 -07:00
|
|
|
if (!timeo)
|
|
|
|
break;
|
2007-11-07 00:30:13 -07:00
|
|
|
release_sock(sk);
|
|
|
|
lock_sock(sk);
|
|
|
|
|
|
|
|
if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
|
2009-01-13 17:04:36 -07:00
|
|
|
(sk->sk_shutdown & RCV_SHUTDOWN) ||
|
2007-11-07 00:30:13 -07:00
|
|
|
signal_pending(current))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
release_sock(sk);
|
|
|
|
|
|
|
|
if (spliced)
|
|
|
|
return spliced;
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_splice_read);
|
2007-11-07 00:30:13 -07:00
|
|
|
|
2007-11-29 03:22:33 -07:00
|
|
|
struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
|
2007-11-29 02:28:50 -07:00
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
|
|
|
/* The TCP header must be at least 32-bit aligned. */
|
|
|
|
size = ALIGN(size, 4);
|
|
|
|
|
|
|
|
skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
|
|
|
|
if (skb) {
|
2007-12-31 01:11:19 -07:00
|
|
|
if (sk_wmem_schedule(sk, skb->truesize)) {
|
2012-04-10 14:30:48 -06:00
|
|
|
skb_reserve(skb, sk->sk_prot->max_header);
|
2007-11-29 02:28:50 -07:00
|
|
|
/*
|
|
|
|
* Make sure that we have exactly size bytes
|
|
|
|
* available to the caller, no more, no less.
|
|
|
|
*/
|
2013-03-13 23:40:32 -06:00
|
|
|
skb->reserved_tailroom = skb->end - skb->tail - size;
|
2007-11-29 02:28:50 -07:00
|
|
|
return skb;
|
|
|
|
}
|
|
|
|
__kfree_skb(skb);
|
|
|
|
} else {
|
2008-07-16 21:28:10 -06:00
|
|
|
sk->sk_prot->enter_memory_pressure(sk);
|
2007-11-29 02:28:50 -07:00
|
|
|
sk_stream_moderate_sndbuf(sk);
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2009-03-14 08:23:05 -06:00
|
|
|
static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
|
|
|
|
int large_allowed)
|
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
2009-03-14 16:45:16 -06:00
|
|
|
u32 xmit_size_goal, old_size_goal;
|
2009-03-14 08:23:05 -06:00
|
|
|
|
|
|
|
xmit_size_goal = mss_now;
|
|
|
|
|
|
|
|
if (large_allowed && sk_can_gso(sk)) {
|
tcp: TSO packets automatic sizing
After hearing many people over past years complaining against TSO being
bursty or even buggy, we are proud to present automatic sizing of TSO
packets.
One part of the problem is that tcp_tso_should_defer() uses an heuristic
relying on upcoming ACKS instead of a timer, but more generally, having
big TSO packets makes little sense for low rates, as it tends to create
micro bursts on the network, and general consensus is to reduce the
buffering amount.
This patch introduces a per socket sk_pacing_rate, that approximates
the current sending rate, and allows us to size the TSO packets so
that we try to send one packet every ms.
This field could be set by other transports.
Patch has no impact for high speed flows, where having large TSO packets
makes sense to reach line rate.
For other flows, this helps better packet scheduling and ACK clocking.
This patch increases performance of TCP flows in lossy environments.
A new sysctl (tcp_min_tso_segs) is added, to specify the
minimal size of a TSO packet (default being 2).
A follow-up patch will provide a new packet scheduler (FQ), using
sk_pacing_rate as an input to perform optional per flow pacing.
This explains why we chose to set sk_pacing_rate to twice the current
rate, allowing 'slow start' ramp up.
sk_pacing_rate = 2 * cwnd * mss / srtt
v2: Neal Cardwell reported a suspect deferring of last two segments on
initial write of 10 MSS, I had to change tcp_tso_should_defer() to take
into account tp->xmit_size_goal_segs
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Van Jacobson <vanj@google.com>
Cc: Tom Herbert <therbert@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-27 06:46:32 -06:00
|
|
|
u32 gso_size, hlen;
|
|
|
|
|
|
|
|
/* Maybe we should/could use sk->sk_prot->max_header here ? */
|
|
|
|
hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
|
|
|
|
inet_csk(sk)->icsk_ext_hdr_len +
|
|
|
|
tp->tcp_header_len;
|
|
|
|
|
|
|
|
/* Goal is to send at least one packet per ms,
|
|
|
|
* not one big TSO packet every 100 ms.
|
|
|
|
* This preserves ACK clocking and is consistent
|
|
|
|
* with tcp_tso_should_defer() heuristic.
|
|
|
|
*/
|
|
|
|
gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
|
|
|
|
gso_size = max_t(u32, gso_size,
|
|
|
|
sysctl_tcp_min_tso_segs * mss_now);
|
|
|
|
|
|
|
|
xmit_size_goal = min_t(u32, gso_size,
|
|
|
|
sk->sk_gso_max_size - 1 - hlen);
|
|
|
|
|
2009-03-14 08:23:05 -06:00
|
|
|
xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
|
2009-03-14 16:45:16 -06:00
|
|
|
|
|
|
|
/* We try hard to avoid divides here */
|
|
|
|
old_size_goal = tp->xmit_size_goal_segs * mss_now;
|
|
|
|
|
|
|
|
if (likely(old_size_goal <= xmit_size_goal &&
|
|
|
|
old_size_goal + mss_now > xmit_size_goal)) {
|
|
|
|
xmit_size_goal = old_size_goal;
|
|
|
|
} else {
|
2012-07-30 10:11:42 -06:00
|
|
|
tp->xmit_size_goal_segs =
|
|
|
|
min_t(u16, xmit_size_goal / mss_now,
|
|
|
|
sk->sk_gso_max_segs);
|
2009-03-14 16:45:16 -06:00
|
|
|
xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
|
|
|
|
}
|
2009-03-14 08:23:05 -06:00
|
|
|
}
|
|
|
|
|
2009-03-14 08:23:07 -06:00
|
|
|
return max(xmit_size_goal, mss_now);
|
2009-03-14 08:23:05 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
|
|
|
|
{
|
|
|
|
int mss_now;
|
|
|
|
|
|
|
|
mss_now = tcp_current_mss(sk);
|
|
|
|
*size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));
|
|
|
|
|
|
|
|
return mss_now;
|
|
|
|
}
|
|
|
|
|
2012-12-01 06:07:02 -07:00
|
|
|
static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
|
|
|
|
size_t size, int flags)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
2005-07-05 16:24:38 -06:00
|
|
|
int mss_now, size_goal;
|
2005-04-16 16:20:36 -06:00
|
|
|
int err;
|
|
|
|
ssize_t copied;
|
|
|
|
long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
|
|
|
|
|
2012-08-31 06:29:12 -06:00
|
|
|
/* Wait for a connection to finish. One exception is TCP Fast Open
|
|
|
|
* (passive side) where data is allowed to be sent before a connection
|
|
|
|
* is fully established.
|
|
|
|
*/
|
|
|
|
if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
|
|
|
|
!tcp_passive_fastopen(sk)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
|
|
|
|
goto out_err;
|
2012-08-31 06:29:12 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
|
|
|
|
|
2009-03-14 08:23:05 -06:00
|
|
|
mss_now = tcp_send_mss(sk, &size_goal, flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
copied = 0;
|
|
|
|
|
|
|
|
err = -EPIPE;
|
|
|
|
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
|
2009-02-27 21:44:41 -07:00
|
|
|
goto out_err;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-12-01 06:07:02 -07:00
|
|
|
while (size > 0) {
|
2007-03-07 13:12:44 -07:00
|
|
|
struct sk_buff *skb = tcp_write_queue_tail(sk);
|
2012-04-23 11:48:27 -06:00
|
|
|
int copy, i;
|
|
|
|
bool can_coalesce;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2007-03-07 13:12:44 -07:00
|
|
|
if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
|
2005-04-16 16:20:36 -06:00
|
|
|
new_segment:
|
|
|
|
if (!sk_stream_memory_free(sk))
|
|
|
|
goto wait_for_sndbuf;
|
|
|
|
|
2007-11-29 03:22:33 -07:00
|
|
|
skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!skb)
|
|
|
|
goto wait_for_memory;
|
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
skb_entail(sk, skb);
|
2005-07-05 16:24:38 -06:00
|
|
|
copy = size_goal;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
if (copy > size)
|
|
|
|
copy = size;
|
|
|
|
|
|
|
|
i = skb_shinfo(skb)->nr_frags;
|
|
|
|
can_coalesce = skb_can_coalesce(skb, i, page, offset);
|
|
|
|
if (!can_coalesce && i >= MAX_SKB_FRAGS) {
|
|
|
|
tcp_mark_push(tp, skb);
|
|
|
|
goto new_segment;
|
|
|
|
}
|
2007-12-31 01:11:19 -07:00
|
|
|
if (!sk_wmem_schedule(sk, copy))
|
2005-04-16 16:20:36 -06:00
|
|
|
goto wait_for_memory;
|
2007-02-09 07:24:47 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (can_coalesce) {
|
2011-10-18 15:00:24 -06:00
|
|
|
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
|
|
|
get_page(page);
|
|
|
|
skb_fill_page_desc(skb, i, page, offset, copy);
|
|
|
|
}
|
2013-02-11 02:27:41 -07:00
|
|
|
skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
|
2013-01-25 13:34:37 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
skb->len += copy;
|
|
|
|
skb->data_len += copy;
|
|
|
|
skb->truesize += copy;
|
|
|
|
sk->sk_wmem_queued += copy;
|
2007-12-31 01:11:19 -07:00
|
|
|
sk_mem_charge(sk, copy);
|
2006-08-29 17:44:56 -06:00
|
|
|
skb->ip_summed = CHECKSUM_PARTIAL;
|
2005-04-16 16:20:36 -06:00
|
|
|
tp->write_seq += copy;
|
|
|
|
TCP_SKB_CB(skb)->end_seq += copy;
|
2006-06-22 03:40:14 -06:00
|
|
|
skb_shinfo(skb)->gso_segs = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (!copied)
|
2011-09-27 11:25:05 -06:00
|
|
|
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
copied += copy;
|
2012-12-01 06:07:02 -07:00
|
|
|
offset += copy;
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
if (!(size -= copy)) {
|
|
|
|
tcp_tx_timestamp(sk, skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-03-22 16:47:05 -06:00
|
|
|
if (skb->len < size_goal || (flags & MSG_OOB))
|
2005-04-16 16:20:36 -06:00
|
|
|
continue;
|
|
|
|
|
|
|
|
if (forced_push(tp)) {
|
|
|
|
tcp_mark_push(tp, skb);
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
|
2007-03-07 13:12:44 -07:00
|
|
|
} else if (skb == tcp_send_head(sk))
|
2005-04-16 16:20:36 -06:00
|
|
|
tcp_push_one(sk, mss_now);
|
|
|
|
continue;
|
|
|
|
|
|
|
|
wait_for_sndbuf:
|
|
|
|
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
|
|
|
|
wait_for_memory:
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
tcp_push(sk, flags & ~MSG_MORE, mss_now,
|
|
|
|
TCP_NAGLE_PUSH, size_goal);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
|
|
|
|
goto do_error;
|
|
|
|
|
2009-03-14 08:23:05 -06:00
|
|
|
mss_now = tcp_send_mss(sk, &size_goal, flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2012-04-04 21:05:35 -06:00
|
|
|
if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
|
2005-04-16 16:20:36 -06:00
|
|
|
return copied;
|
|
|
|
|
|
|
|
do_error:
|
|
|
|
if (copied)
|
|
|
|
goto out;
|
|
|
|
out_err:
|
|
|
|
return sk_stream_error(sk, flags, err);
|
|
|
|
}
|
|
|
|
|
2010-07-10 14:41:55 -06:00
|
|
|
int tcp_sendpage(struct sock *sk, struct page *page, int offset,
|
|
|
|
size_t size, int flags)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
ssize_t res;
|
|
|
|
|
|
|
|
if (!(sk->sk_route_caps & NETIF_F_SG) ||
|
2006-06-17 23:06:05 -06:00
|
|
|
!(sk->sk_route_caps & NETIF_F_ALL_CSUM))
|
2010-07-10 14:41:55 -06:00
|
|
|
return sock_no_sendpage(sk->sk_socket, page, offset, size,
|
|
|
|
flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
lock_sock(sk);
|
2012-12-01 06:07:02 -07:00
|
|
|
res = do_tcp_sendpages(sk, page, offset, size, flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
release_sock(sk);
|
|
|
|
return res;
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_sendpage);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2011-11-27 17:27:47 -07:00
|
|
|
static inline int select_size(const struct sock *sk, bool sg)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2011-10-21 03:22:42 -06:00
|
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
2005-07-05 16:24:38 -06:00
|
|
|
int tmp = tp->mss_cache;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-12-10 00:16:59 -07:00
|
|
|
if (sg) {
|
2011-11-28 15:41:47 -07:00
|
|
|
if (sk_can_gso(sk)) {
|
|
|
|
/* Small frames wont use a full page:
|
|
|
|
* Payload will immediately follow tcp header.
|
|
|
|
*/
|
|
|
|
tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
|
|
|
|
} else {
|
2005-07-05 16:20:27 -06:00
|
|
|
int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
|
|
|
|
|
|
|
|
if (tmp >= pgbreak &&
|
|
|
|
tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE)
|
|
|
|
tmp = pgbreak;
|
|
|
|
}
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
return tmp;
|
|
|
|
}
|
|
|
|
|
2012-07-19 00:43:09 -06:00
|
|
|
void tcp_free_fastopen_req(struct tcp_sock *tp)
|
|
|
|
{
|
|
|
|
if (tp->fastopen_req != NULL) {
|
|
|
|
kfree(tp->fastopen_req);
|
|
|
|
tp->fastopen_req = NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-02-20 11:09:18 -07:00
|
|
|
static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
|
|
|
|
int *copied, size_t size)
|
2012-07-19 00:43:09 -06:00
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
int err, flags;
|
|
|
|
|
|
|
|
if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
|
|
|
|
return -EOPNOTSUPP;
|
|
|
|
if (tp->fastopen_req != NULL)
|
|
|
|
return -EALREADY; /* Another Fast Open is in progress */
|
|
|
|
|
|
|
|
tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
|
|
|
|
sk->sk_allocation);
|
|
|
|
if (unlikely(tp->fastopen_req == NULL))
|
|
|
|
return -ENOBUFS;
|
|
|
|
tp->fastopen_req->data = msg;
|
2014-02-20 11:09:18 -07:00
|
|
|
tp->fastopen_req->size = size;
|
2012-07-19 00:43:09 -06:00
|
|
|
|
|
|
|
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
|
|
|
|
err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
|
|
|
|
msg->msg_namelen, flags);
|
2014-02-20 11:09:18 -07:00
|
|
|
*copied = tp->fastopen_req->copied;
|
2012-07-19 00:43:09 -06:00
|
|
|
tcp_free_fastopen_req(tp);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2010-07-10 14:41:55 -06:00
|
|
|
int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
|
2005-04-16 16:20:36 -06:00
|
|
|
size_t size)
|
|
|
|
{
|
|
|
|
struct iovec *iov;
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
struct sk_buff *skb;
|
2012-07-19 00:43:09 -06:00
|
|
|
int iovlen, flags, err, copied = 0;
|
|
|
|
int mss_now = 0, size_goal, copied_syn = 0, offset = 0;
|
2011-11-27 17:27:47 -07:00
|
|
|
bool sg;
|
2005-04-16 16:20:36 -06:00
|
|
|
long timeo;
|
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
|
|
|
|
flags = msg->msg_flags;
|
2012-07-19 00:43:09 -06:00
|
|
|
if (flags & MSG_FASTOPEN) {
|
2014-02-20 11:09:18 -07:00
|
|
|
err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
|
2012-07-19 00:43:09 -06:00
|
|
|
if (err == -EINPROGRESS && copied_syn > 0)
|
|
|
|
goto out;
|
|
|
|
else if (err)
|
|
|
|
goto out_err;
|
|
|
|
offset = copied_syn;
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
|
|
|
|
|
2012-08-31 06:29:12 -06:00
|
|
|
/* Wait for a connection to finish. One exception is TCP Fast Open
|
|
|
|
* (passive side) where data is allowed to be sent before a connection
|
|
|
|
* is fully established.
|
|
|
|
*/
|
|
|
|
if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
|
|
|
|
!tcp_passive_fastopen(sk)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
|
2012-07-19 00:43:09 -06:00
|
|
|
goto do_error;
|
2012-08-31 06:29:12 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-04-18 21:41:01 -06:00
|
|
|
if (unlikely(tp->repair)) {
|
|
|
|
if (tp->repair_queue == TCP_RECV_QUEUE) {
|
|
|
|
copied = tcp_send_rcvq(sk, msg, size);
|
tcp: Fix divide by zero when pushing during tcp-repair
When in repair-mode and TCP_RECV_QUEUE is set, we end up calling
tcp_push with mss_now being 0. If data is in the send-queue and
tcp_set_skb_tso_segs gets called, we crash because it will divide by
mss_now:
[ 347.151939] divide error: 0000 [#1] SMP
[ 347.152907] Modules linked in:
[ 347.152907] CPU: 1 PID: 1123 Comm: packetdrill Not tainted 3.16.0-rc2 #4
[ 347.152907] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
[ 347.152907] task: f5b88540 ti: f3c82000 task.ti: f3c82000
[ 347.152907] EIP: 0060:[<c1601359>] EFLAGS: 00210246 CPU: 1
[ 347.152907] EIP is at tcp_set_skb_tso_segs+0x49/0xa0
[ 347.152907] EAX: 00000b67 EBX: f5acd080 ECX: 00000000 EDX: 00000000
[ 347.152907] ESI: f5a28f40 EDI: f3c88f00 EBP: f3c83d10 ESP: f3c83d00
[ 347.152907] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
[ 347.152907] CR0: 80050033 CR2: 083158b0 CR3: 35146000 CR4: 000006b0
[ 347.152907] Stack:
[ 347.152907] c167f9d9 f5acd080 000005b4 00000002 f3c83d20 c16013e6 f3c88f00 f5acd080
[ 347.152907] f3c83da0 c1603b5a f3c83d38 c10a0188 00000000 00000000 f3c83d84 c10acc85
[ 347.152907] c1ad5ec0 00000000 00000000 c1ad679c 010003e0 00000000 00000000 f3c88fc8
[ 347.152907] Call Trace:
[ 347.152907] [<c167f9d9>] ? apic_timer_interrupt+0x2d/0x34
[ 347.152907] [<c16013e6>] tcp_init_tso_segs+0x36/0x50
[ 347.152907] [<c1603b5a>] tcp_write_xmit+0x7a/0xbf0
[ 347.152907] [<c10a0188>] ? up+0x28/0x40
[ 347.152907] [<c10acc85>] ? console_unlock+0x295/0x480
[ 347.152907] [<c10ad24f>] ? vprintk_emit+0x1ef/0x4b0
[ 347.152907] [<c1605716>] __tcp_push_pending_frames+0x36/0xd0
[ 347.152907] [<c15f4860>] tcp_push+0xf0/0x120
[ 347.152907] [<c15f7641>] tcp_sendmsg+0xf1/0xbf0
[ 347.152907] [<c116d920>] ? kmem_cache_free+0xf0/0x120
[ 347.152907] [<c106a682>] ? __sigqueue_free+0x32/0x40
[ 347.152907] [<c106a682>] ? __sigqueue_free+0x32/0x40
[ 347.152907] [<c114f0f0>] ? do_wp_page+0x3e0/0x850
[ 347.152907] [<c161c36a>] inet_sendmsg+0x4a/0xb0
[ 347.152907] [<c1150269>] ? handle_mm_fault+0x709/0xfb0
[ 347.152907] [<c15a006b>] sock_aio_write+0xbb/0xd0
[ 347.152907] [<c1180b79>] do_sync_write+0x69/0xa0
[ 347.152907] [<c1181023>] vfs_write+0x123/0x160
[ 347.152907] [<c1181d55>] SyS_write+0x55/0xb0
[ 347.152907] [<c167f0d8>] sysenter_do_call+0x12/0x28
This can easily be reproduced with the following packetdrill-script (the
"magic" with netem, sk_pacing and limit_output_bytes is done to prevent
the kernel from pushing all segments, because hitting the limit without
doing this is not so easy with packetdrill):
0 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 32792 <mss 1460>
+0 > S. 0:0(0) ack 1 <mss 1460>
+0.1 < . 1:1(0) ack 1 win 65000
+0 accept(3, ..., ...) = 4
// This forces that not all segments of the snd-queue will be pushed
+0 `tc qdisc add dev tun0 root netem delay 10ms`
+0 `sysctl -w net.ipv4.tcp_limit_output_bytes=2`
+0 setsockopt(4, SOL_SOCKET, 47, [2], 4) = 0
+0 write(4,...,10000) = 10000
+0 write(4,...,10000) = 10000
// Set tcp-repair stuff, particularly TCP_RECV_QUEUE
+0 setsockopt(4, SOL_TCP, 19, [1], 4) = 0
+0 setsockopt(4, SOL_TCP, 20, [1], 4) = 0
// This now will make the write push the remaining segments
+0 setsockopt(4, SOL_SOCKET, 47, [20000], 4) = 0
+0 `sysctl -w net.ipv4.tcp_limit_output_bytes=130000`
// Now we will crash
+0 write(4,...,1000) = 1000
This happens since ec3423257508 (tcp: fix retransmission in repair
mode). Prior to that, the call to tcp_push was prevented by a check for
tp->repair.
The patch fixes it, by adding the new goto-label out_nopush. When exiting
tcp_sendmsg and a push is not required, which is the case for tp->repair,
we go to this label.
When repairing and calling send() with TCP_RECV_QUEUE, the data is
actually put in the receive-queue. So, no push is required because no
data has been added to the send-queue.
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Fixes: ec3423257508 (tcp: fix retransmission in repair mode)
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Acked-by: Andrew Vagin <avagin@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-28 10:26:37 -06:00
|
|
|
goto out_nopush;
|
2012-04-18 21:41:01 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
if (tp->repair_queue == TCP_NO_QUEUE)
|
|
|
|
goto out_err;
|
|
|
|
|
|
|
|
/* 'common' sending to sendq */
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* This should be in poll */
|
|
|
|
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
|
|
|
|
|
2009-03-14 08:23:05 -06:00
|
|
|
mss_now = tcp_send_mss(sk, &size_goal, flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* Ok commence sending. */
|
|
|
|
iovlen = msg->msg_iovlen;
|
|
|
|
iov = msg->msg_iov;
|
|
|
|
copied = 0;
|
|
|
|
|
|
|
|
err = -EPIPE;
|
|
|
|
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
|
2009-02-27 21:44:41 -07:00
|
|
|
goto out_err;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2011-11-27 17:27:47 -07:00
|
|
|
sg = !!(sk->sk_route_caps & NETIF_F_SG);
|
2009-12-10 00:16:59 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
while (--iovlen >= 0) {
|
2010-09-27 21:24:54 -06:00
|
|
|
size_t seglen = iov->iov_len;
|
2005-04-16 16:20:36 -06:00
|
|
|
unsigned char __user *from = iov->iov_base;
|
|
|
|
|
|
|
|
iov++;
|
2012-07-19 00:43:09 -06:00
|
|
|
if (unlikely(offset > 0)) { /* Skip bytes copied in SYN */
|
|
|
|
if (offset >= seglen) {
|
|
|
|
offset -= seglen;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
seglen -= offset;
|
|
|
|
from += offset;
|
|
|
|
offset = 0;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
while (seglen > 0) {
|
2009-06-28 12:06:41 -06:00
|
|
|
int copy = 0;
|
|
|
|
int max = size_goal;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2007-03-07 13:12:44 -07:00
|
|
|
skb = tcp_write_queue_tail(sk);
|
2009-06-28 12:06:41 -06:00
|
|
|
if (tcp_send_head(sk)) {
|
|
|
|
if (skb->ip_summed == CHECKSUM_NONE)
|
|
|
|
max = mss_now;
|
|
|
|
copy = max - skb->len;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-06-28 12:06:41 -06:00
|
|
|
if (copy <= 0) {
|
2005-04-16 16:20:36 -06:00
|
|
|
new_segment:
|
|
|
|
/* Allocate new segment. If the interface is SG,
|
|
|
|
* allocate skb fitting to single page.
|
|
|
|
*/
|
|
|
|
if (!sk_stream_memory_free(sk))
|
|
|
|
goto wait_for_sndbuf;
|
|
|
|
|
2009-12-10 00:16:59 -07:00
|
|
|
skb = sk_stream_alloc_skb(sk,
|
|
|
|
select_size(sk, sg),
|
|
|
|
sk->sk_allocation);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!skb)
|
|
|
|
goto wait_for_memory;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check whether we can use HW checksum.
|
|
|
|
*/
|
2006-06-17 23:06:05 -06:00
|
|
|
if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
|
2006-08-29 17:44:56 -06:00
|
|
|
skb->ip_summed = CHECKSUM_PARTIAL;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
skb_entail(sk, skb);
|
2005-07-05 16:24:38 -06:00
|
|
|
copy = size_goal;
|
2009-06-28 12:06:41 -06:00
|
|
|
max = size_goal;
|
2014-08-13 06:03:10 -06:00
|
|
|
|
|
|
|
/* All packets are restored as if they have
|
|
|
|
* already been sent. skb_mstamp isn't set to
|
|
|
|
* avoid wrong rtt estimation.
|
|
|
|
*/
|
|
|
|
if (tp->repair)
|
|
|
|
TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Try to append data to the end of skb. */
|
|
|
|
if (copy > seglen)
|
|
|
|
copy = seglen;
|
|
|
|
|
|
|
|
/* Where to copy to? */
|
2012-04-10 14:30:48 -06:00
|
|
|
if (skb_availroom(skb) > 0) {
|
2005-04-16 16:20:36 -06:00
|
|
|
/* We have some space in skb head. Superb! */
|
2012-04-10 14:30:48 -06:00
|
|
|
copy = min_t(int, copy, skb_availroom(skb));
|
2011-04-04 23:30:30 -06:00
|
|
|
err = skb_add_data_nocache(sk, skb, from, copy);
|
|
|
|
if (err)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto do_fault;
|
|
|
|
} else {
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
bool merge = true;
|
2005-04-16 16:20:36 -06:00
|
|
|
int i = skb_shinfo(skb)->nr_frags;
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
struct page_frag *pfrag = sk_page_frag(sk);
|
|
|
|
|
|
|
|
if (!sk_page_frag_refill(sk, pfrag))
|
|
|
|
goto wait_for_memory;
|
|
|
|
|
|
|
|
if (!skb_can_coalesce(skb, i, pfrag->page,
|
|
|
|
pfrag->offset)) {
|
|
|
|
if (i == MAX_SKB_FRAGS || !sg) {
|
|
|
|
tcp_mark_push(tp, skb);
|
|
|
|
goto new_segment;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
merge = false;
|
|
|
|
}
|
2005-09-01 18:48:59 -06:00
|
|
|
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
copy = min_t(int, copy, pfrag->size - pfrag->offset);
|
2005-09-01 18:48:59 -06:00
|
|
|
|
2007-12-31 01:11:19 -07:00
|
|
|
if (!sk_wmem_schedule(sk, copy))
|
2005-09-01 18:48:59 -06:00
|
|
|
goto wait_for_memory;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2011-04-04 23:30:30 -06:00
|
|
|
err = skb_copy_to_page_nocache(sk, from, skb,
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
pfrag->page,
|
|
|
|
pfrag->offset,
|
|
|
|
copy);
|
|
|
|
if (err)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto do_error;
|
|
|
|
|
|
|
|
/* Update the skb. */
|
|
|
|
if (merge) {
|
2011-10-18 15:00:24 -06:00
|
|
|
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
skb_fill_page_desc(skb, i, pfrag->page,
|
|
|
|
pfrag->offset, copy);
|
|
|
|
get_page(pfrag->page);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
net: use a per task frag allocator
We currently use a per socket order-0 page cache for tcp_sendmsg()
operations.
This page is used to build fragments for skbs.
Its done to increase probability of coalescing small write() into
single segments in skbs still in write queue (not yet sent)
But it wastes a lot of memory for applications handling many mostly
idle sockets, since each socket holds one page in sk->sk_sndmsg_page
Its also quite inefficient to build TSO 64KB packets, because we need
about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit
page allocator more than wanted.
This patch adds a per task frag allocator and uses bigger pages,
if available. An automatic fallback is done in case of memory pressure.
(up to 32768 bytes per frag, thats order-3 pages on x86)
This increases TCP stream performance by 20% on loopback device,
but also benefits on other network devices, since 8x less frags are
mapped on transmit and unmapped on tx completion. Alexander Duyck
mentioned a probable performance win on systems with IOMMU enabled.
Its possible some SG enabled hardware cant cope with bigger fragments,
but their ndo_start_xmit() should already handle this, splitting a
fragment in sub fragments, since some arches have PAGE_SIZE=65536
Successfully tested on various ethernet devices.
(ixgbe, igb, bnx2x, tg3, mellanox mlx4)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 17:04:42 -06:00
|
|
|
pfrag->offset += copy;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
if (!copied)
|
2011-09-27 11:25:05 -06:00
|
|
|
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
tp->write_seq += copy;
|
|
|
|
TCP_SKB_CB(skb)->end_seq += copy;
|
2006-06-22 03:40:14 -06:00
|
|
|
skb_shinfo(skb)->gso_segs = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
from += copy;
|
|
|
|
copied += copy;
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
if ((seglen -= copy) == 0 && iovlen == 0) {
|
|
|
|
tcp_tx_timestamp(sk, skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-04-18 21:41:01 -06:00
|
|
|
if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
|
2005-04-16 16:20:36 -06:00
|
|
|
continue;
|
|
|
|
|
|
|
|
if (forced_push(tp)) {
|
|
|
|
tcp_mark_push(tp, skb);
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
|
2007-03-07 13:12:44 -07:00
|
|
|
} else if (skb == tcp_send_head(sk))
|
2005-04-16 16:20:36 -06:00
|
|
|
tcp_push_one(sk, mss_now);
|
|
|
|
continue;
|
|
|
|
|
|
|
|
wait_for_sndbuf:
|
|
|
|
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
|
|
|
|
wait_for_memory:
|
2012-11-14 21:03:17 -07:00
|
|
|
if (copied)
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
tcp_push(sk, flags & ~MSG_MORE, mss_now,
|
|
|
|
TCP_NAGLE_PUSH, size_goal);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
|
|
|
|
goto do_error;
|
|
|
|
|
2009-03-14 08:23:05 -06:00
|
|
|
mss_now = tcp_send_mss(sk, &size_goal, flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
2012-11-14 21:03:17 -07:00
|
|
|
if (copied)
|
tcp: auto corking
With the introduction of TCP Small Queues, TSO auto sizing, and TCP
pacing, we can implement Automatic Corking in the kernel, to help
applications doing small write()/sendmsg() to TCP sockets.
Idea is to change tcp_push() to check if the current skb payload is
under skb optimal size (a multiple of MSS bytes)
If under 'size_goal', and at least one packet is still in Qdisc or
NIC TX queues, set the TCP Small Queue Throttled bit, so that the push
will be delayed up to TX completion time.
This delay might allow the application to coalesce more bytes
in the skb in following write()/sendmsg()/sendfile() system calls.
The exact duration of the delay is depending on the dynamics
of the system, and might be zero if no packet for this flow
is actually held in Qdisc or NIC TX ring.
Using FQ/pacing is a way to increase the probability of
autocorking being triggered.
Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control
this feature and default it to 1 (enabled)
Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking
This counter is incremented every time we detected skb was under used
and its flush was deferred.
Tested:
Interesting effects when using line buffered commands under ssh.
Excellent performance results in term of cpu usage and total throughput.
lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
9410.39
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
35209.439626 task-clock # 2.901 CPUs utilized
2,294 context-switches # 0.065 K/sec
101 CPU-migrations # 0.003 K/sec
4,079 page-faults # 0.116 K/sec
97,923,241,298 cycles # 2.781 GHz [83.31%]
51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%]
25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%]
102,225,978,536 instructions # 1.04 insns per cycle
# 0.51 stalled cycles per insn [83.38%]
18,657,696,819 branches # 529.906 M/sec [83.29%]
91,679,646 branch-misses # 0.49% of all branches [83.40%]
12.136204899 seconds time elapsed
lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking
lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128
6624.89
Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128':
40045.864494 task-clock # 3.301 CPUs utilized
171 context-switches # 0.004 K/sec
53 CPU-migrations # 0.001 K/sec
4,080 page-faults # 0.102 K/sec
111,340,458,645 cycles # 2.780 GHz [83.34%]
61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%]
29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%]
108,654,349,355 instructions # 0.98 insns per cycle
# 0.57 stalled cycles per insn [83.34%]
19,552,170,748 branches # 488.244 M/sec [83.34%]
157,875,417 branch-misses # 0.81% of all branches [83.34%]
12.130267788 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-05 23:36:05 -07:00
|
|
|
tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
|
tcp: Fix divide by zero when pushing during tcp-repair
When in repair-mode and TCP_RECV_QUEUE is set, we end up calling
tcp_push with mss_now being 0. If data is in the send-queue and
tcp_set_skb_tso_segs gets called, we crash because it will divide by
mss_now:
[ 347.151939] divide error: 0000 [#1] SMP
[ 347.152907] Modules linked in:
[ 347.152907] CPU: 1 PID: 1123 Comm: packetdrill Not tainted 3.16.0-rc2 #4
[ 347.152907] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
[ 347.152907] task: f5b88540 ti: f3c82000 task.ti: f3c82000
[ 347.152907] EIP: 0060:[<c1601359>] EFLAGS: 00210246 CPU: 1
[ 347.152907] EIP is at tcp_set_skb_tso_segs+0x49/0xa0
[ 347.152907] EAX: 00000b67 EBX: f5acd080 ECX: 00000000 EDX: 00000000
[ 347.152907] ESI: f5a28f40 EDI: f3c88f00 EBP: f3c83d10 ESP: f3c83d00
[ 347.152907] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
[ 347.152907] CR0: 80050033 CR2: 083158b0 CR3: 35146000 CR4: 000006b0
[ 347.152907] Stack:
[ 347.152907] c167f9d9 f5acd080 000005b4 00000002 f3c83d20 c16013e6 f3c88f00 f5acd080
[ 347.152907] f3c83da0 c1603b5a f3c83d38 c10a0188 00000000 00000000 f3c83d84 c10acc85
[ 347.152907] c1ad5ec0 00000000 00000000 c1ad679c 010003e0 00000000 00000000 f3c88fc8
[ 347.152907] Call Trace:
[ 347.152907] [<c167f9d9>] ? apic_timer_interrupt+0x2d/0x34
[ 347.152907] [<c16013e6>] tcp_init_tso_segs+0x36/0x50
[ 347.152907] [<c1603b5a>] tcp_write_xmit+0x7a/0xbf0
[ 347.152907] [<c10a0188>] ? up+0x28/0x40
[ 347.152907] [<c10acc85>] ? console_unlock+0x295/0x480
[ 347.152907] [<c10ad24f>] ? vprintk_emit+0x1ef/0x4b0
[ 347.152907] [<c1605716>] __tcp_push_pending_frames+0x36/0xd0
[ 347.152907] [<c15f4860>] tcp_push+0xf0/0x120
[ 347.152907] [<c15f7641>] tcp_sendmsg+0xf1/0xbf0
[ 347.152907] [<c116d920>] ? kmem_cache_free+0xf0/0x120
[ 347.152907] [<c106a682>] ? __sigqueue_free+0x32/0x40
[ 347.152907] [<c106a682>] ? __sigqueue_free+0x32/0x40
[ 347.152907] [<c114f0f0>] ? do_wp_page+0x3e0/0x850
[ 347.152907] [<c161c36a>] inet_sendmsg+0x4a/0xb0
[ 347.152907] [<c1150269>] ? handle_mm_fault+0x709/0xfb0
[ 347.152907] [<c15a006b>] sock_aio_write+0xbb/0xd0
[ 347.152907] [<c1180b79>] do_sync_write+0x69/0xa0
[ 347.152907] [<c1181023>] vfs_write+0x123/0x160
[ 347.152907] [<c1181d55>] SyS_write+0x55/0xb0
[ 347.152907] [<c167f0d8>] sysenter_do_call+0x12/0x28
This can easily be reproduced with the following packetdrill-script (the
"magic" with netem, sk_pacing and limit_output_bytes is done to prevent
the kernel from pushing all segments, because hitting the limit without
doing this is not so easy with packetdrill):
0 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 32792 <mss 1460>
+0 > S. 0:0(0) ack 1 <mss 1460>
+0.1 < . 1:1(0) ack 1 win 65000
+0 accept(3, ..., ...) = 4
// This forces that not all segments of the snd-queue will be pushed
+0 `tc qdisc add dev tun0 root netem delay 10ms`
+0 `sysctl -w net.ipv4.tcp_limit_output_bytes=2`
+0 setsockopt(4, SOL_SOCKET, 47, [2], 4) = 0
+0 write(4,...,10000) = 10000
+0 write(4,...,10000) = 10000
// Set tcp-repair stuff, particularly TCP_RECV_QUEUE
+0 setsockopt(4, SOL_TCP, 19, [1], 4) = 0
+0 setsockopt(4, SOL_TCP, 20, [1], 4) = 0
// This now will make the write push the remaining segments
+0 setsockopt(4, SOL_SOCKET, 47, [20000], 4) = 0
+0 `sysctl -w net.ipv4.tcp_limit_output_bytes=130000`
// Now we will crash
+0 write(4,...,1000) = 1000
This happens since ec3423257508 (tcp: fix retransmission in repair
mode). Prior to that, the call to tcp_push was prevented by a check for
tp->repair.
The patch fixes it, by adding the new goto-label out_nopush. When exiting
tcp_sendmsg and a push is not required, which is the case for tp->repair,
we go to this label.
When repairing and calling send() with TCP_RECV_QUEUE, the data is
actually put in the receive-queue. So, no push is required because no
data has been added to the send-queue.
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Fixes: ec3423257508 (tcp: fix retransmission in repair mode)
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Acked-by: Andrew Vagin <avagin@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-28 10:26:37 -06:00
|
|
|
out_nopush:
|
2005-04-16 16:20:36 -06:00
|
|
|
release_sock(sk);
|
2012-07-19 00:43:09 -06:00
|
|
|
return copied + copied_syn;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
do_fault:
|
|
|
|
if (!skb->len) {
|
2007-03-07 13:12:44 -07:00
|
|
|
tcp_unlink_write_queue(skb, sk);
|
|
|
|
/* It is the one place in all of TCP, except connection
|
|
|
|
* reset, where we can be unlinking the send_head.
|
|
|
|
*/
|
|
|
|
tcp_check_send_head(sk, skb);
|
2007-12-31 01:11:19 -07:00
|
|
|
sk_wmem_free_skb(sk, skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
do_error:
|
2012-07-19 00:43:09 -06:00
|
|
|
if (copied + copied_syn)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
|
|
|
out_err:
|
|
|
|
err = sk_stream_error(sk, flags, err);
|
|
|
|
release_sock(sk);
|
|
|
|
return err;
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_sendmsg);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Handle reading urgent data. BSD has very simple semantics for
|
|
|
|
* this, no blocking and very strange errors 8)
|
|
|
|
*/
|
|
|
|
|
2009-03-31 15:43:17 -06:00
|
|
|
static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
|
|
|
/* No URG data to read. */
|
|
|
|
if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data ||
|
|
|
|
tp->urg_data == TCP_URG_READ)
|
|
|
|
return -EINVAL; /* Yes this is right ! */
|
|
|
|
|
|
|
|
if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE))
|
|
|
|
return -ENOTCONN;
|
|
|
|
|
|
|
|
if (tp->urg_data & TCP_URG_VALID) {
|
|
|
|
int err = 0;
|
|
|
|
char c = tp->urg_data;
|
|
|
|
|
|
|
|
if (!(flags & MSG_PEEK))
|
|
|
|
tp->urg_data = TCP_URG_READ;
|
|
|
|
|
|
|
|
/* Read urgent data. */
|
|
|
|
msg->msg_flags |= MSG_OOB;
|
|
|
|
|
|
|
|
if (len > 0) {
|
|
|
|
if (!(flags & MSG_TRUNC))
|
|
|
|
err = memcpy_toiovec(msg->msg_iov, &c, 1);
|
|
|
|
len = 1;
|
|
|
|
} else
|
|
|
|
msg->msg_flags |= MSG_TRUNC;
|
|
|
|
|
|
|
|
return err ? -EFAULT : len;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Fixed the recv(..., MSG_OOB) behaviour. BSD docs and
|
|
|
|
* the available implementations agree in this case:
|
|
|
|
* this call should never block, independent of the
|
|
|
|
* blocking state of the socket.
|
|
|
|
* Mike <pall@rz.uni-karlsruhe.de>
|
|
|
|
*/
|
|
|
|
return -EAGAIN;
|
|
|
|
}
|
|
|
|
|
2012-04-18 21:41:01 -06:00
|
|
|
static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int copied = 0, err = 0;
|
|
|
|
|
|
|
|
/* XXX -- need to support SO_PEEK_OFF */
|
|
|
|
|
|
|
|
skb_queue_walk(&sk->sk_write_queue, skb) {
|
|
|
|
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
|
|
|
|
copied += skb->len;
|
|
|
|
}
|
|
|
|
|
|
|
|
return err ?: copied;
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Clean up the receive buffer for full frames taken by the user,
|
|
|
|
* then send an ACK if necessary. COPIED is the number of bytes
|
|
|
|
* tcp_recvmsg has given to the user so far, it speeds up the
|
|
|
|
* calculation of whether or not we must ACK for the sake of
|
|
|
|
* a window update.
|
|
|
|
*/
|
2006-05-23 19:00:16 -06:00
|
|
|
void tcp_cleanup_rbuf(struct sock *sk, int copied)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
2012-05-16 17:15:34 -06:00
|
|
|
bool time_to_ack = false;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
|
|
|
|
|
2009-11-13 14:56:33 -07:00
|
|
|
WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
|
2010-10-30 05:08:53 -06:00
|
|
|
"cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
|
2009-11-13 14:56:33 -07:00
|
|
|
tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2005-08-09 21:10:42 -06:00
|
|
|
if (inet_csk_ack_scheduled(sk)) {
|
|
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Delayed ACKs frequently hit locked sockets during bulk
|
|
|
|
* receive. */
|
2005-08-09 21:10:42 -06:00
|
|
|
if (icsk->icsk_ack.blocked ||
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Once-per-two-segments ACK was not sent by tcp_input.c */
|
2005-08-09 21:10:42 -06:00
|
|
|
tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* If this read emptied read buffer, we send ACK, if
|
|
|
|
* connection is not bidirectional, user drained
|
|
|
|
* receive buffer and there was a small segment
|
|
|
|
* in queue.
|
|
|
|
*/
|
2006-09-19 13:52:50 -06:00
|
|
|
(copied > 0 &&
|
|
|
|
((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) ||
|
|
|
|
((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
|
|
|
|
!icsk->icsk_ack.pingpong)) &&
|
|
|
|
!atomic_read(&sk->sk_rmem_alloc)))
|
2012-05-16 17:15:34 -06:00
|
|
|
time_to_ack = true;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/* We send an ACK if we can now advertise a non-zero window
|
|
|
|
* which has been raised "significantly".
|
|
|
|
*
|
|
|
|
* Even if window raised up to infinity, do not send window open ACK
|
|
|
|
* in states, where we will not receive more. It is useless.
|
|
|
|
*/
|
|
|
|
if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
|
|
|
|
__u32 rcv_window_now = tcp_receive_window(tp);
|
|
|
|
|
|
|
|
/* Optimize, __tcp_select_window() is not cheap. */
|
|
|
|
if (2*rcv_window_now <= tp->window_clamp) {
|
|
|
|
__u32 new_window = __tcp_select_window(sk);
|
|
|
|
|
|
|
|
/* Send ACK now, if this read freed lots of space
|
|
|
|
* in our buffer. Certainly, new_window is new window.
|
|
|
|
* We can advertise it now, if it is not less than current one.
|
|
|
|
* "Lots" means "at least twice" here.
|
|
|
|
*/
|
|
|
|
if (new_window && new_window >= 2 * rcv_window_now)
|
2012-05-16 17:15:34 -06:00
|
|
|
time_to_ack = true;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
if (time_to_ack)
|
|
|
|
tcp_send_ack(sk);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void tcp_prequeue_process(struct sock *sk)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
2008-07-16 21:31:39 -06:00
|
|
|
NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPPREQUEUED);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* RX process wants to run with disabled BHs, though it is not
|
|
|
|
* necessary */
|
|
|
|
local_bh_disable();
|
|
|
|
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
|
2008-10-07 15:18:42 -06:00
|
|
|
sk_backlog_rcv(sk, skb);
|
2005-04-16 16:20:36 -06:00
|
|
|
local_bh_enable();
|
|
|
|
|
|
|
|
/* Clear memory counter. */
|
|
|
|
tp->ucopy.memory = 0;
|
|
|
|
}
|
|
|
|
|
2010-03-15 23:22:44 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
|
|
|
static void tcp_service_net_dma(struct sock *sk, bool wait)
|
|
|
|
{
|
|
|
|
dma_cookie_t done, used;
|
|
|
|
dma_cookie_t last_issued;
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
|
|
|
|
if (!tp->ucopy.dma_chan)
|
|
|
|
return;
|
|
|
|
|
|
|
|
last_issued = tp->ucopy.dma_cookie;
|
2012-11-08 02:59:54 -07:00
|
|
|
dma_async_issue_pending(tp->ucopy.dma_chan);
|
2010-03-15 23:22:44 -06:00
|
|
|
|
|
|
|
do {
|
2012-11-08 03:01:01 -07:00
|
|
|
if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
|
2010-03-15 23:22:44 -06:00
|
|
|
last_issued, &done,
|
2013-10-16 09:37:39 -06:00
|
|
|
&used) == DMA_COMPLETE) {
|
2010-03-15 23:22:44 -06:00
|
|
|
/* Safe to free early-copied skbs now */
|
|
|
|
__skb_queue_purge(&sk->sk_async_wait_queue);
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
struct sk_buff *skb;
|
|
|
|
while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
|
|
|
|
(dma_async_is_complete(skb->dma_cookie, done,
|
2013-10-16 09:37:39 -06:00
|
|
|
used) == DMA_COMPLETE)) {
|
2010-03-15 23:22:44 -06:00
|
|
|
__skb_dequeue(&sk->sk_async_wait_queue);
|
|
|
|
kfree_skb(skb);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} while (wait);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2013-01-09 13:59:09 -07:00
|
|
|
static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
u32 offset;
|
|
|
|
|
2013-01-09 13:59:09 -07:00
|
|
|
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
|
2005-04-16 16:20:36 -06:00
|
|
|
offset = seq - TCP_SKB_CB(skb)->seq;
|
2007-04-10 22:04:22 -06:00
|
|
|
if (tcp_hdr(skb)->syn)
|
2005-04-16 16:20:36 -06:00
|
|
|
offset--;
|
2007-04-10 22:04:22 -06:00
|
|
|
if (offset < skb->len || tcp_hdr(skb)->fin) {
|
2005-04-16 16:20:36 -06:00
|
|
|
*off = offset;
|
|
|
|
return skb;
|
|
|
|
}
|
2013-01-09 13:59:09 -07:00
|
|
|
/* This looks weird, but this can happen if TCP collapsing
|
|
|
|
* splitted a fat GRO packet, while we released socket lock
|
|
|
|
* in skb_splice_bits()
|
|
|
|
*/
|
|
|
|
sk_eat_skb(sk, skb, false);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This routine provides an alternative to tcp_recvmsg() for routines
|
|
|
|
* that would like to handle copying from skbuffs directly in 'sendfile'
|
|
|
|
* fashion.
|
|
|
|
* Note:
|
|
|
|
* - It is assumed that the socket was locked by the caller.
|
|
|
|
* - The routine does not block.
|
|
|
|
* - At present, there is no support for reading OOB data
|
|
|
|
* or for 'peeking' the socket using this routine
|
|
|
|
* (although both would be easy to implement).
|
|
|
|
*/
|
|
|
|
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
|
|
|
|
sk_read_actor_t recv_actor)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
u32 seq = tp->copied_seq;
|
|
|
|
u32 offset;
|
|
|
|
int copied = 0;
|
|
|
|
|
|
|
|
if (sk->sk_state == TCP_LISTEN)
|
|
|
|
return -ENOTCONN;
|
|
|
|
while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
|
|
|
|
if (offset < skb->len) {
|
2008-07-03 04:31:21 -06:00
|
|
|
int used;
|
|
|
|
size_t len;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
len = skb->len - offset;
|
|
|
|
/* Stop reading if we hit a patch of urgent data */
|
|
|
|
if (tp->urg_data) {
|
|
|
|
u32 urg_offset = tp->urg_seq - seq;
|
|
|
|
if (urg_offset < len)
|
|
|
|
len = urg_offset;
|
|
|
|
if (!len)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
used = recv_actor(desc, skb, offset, len);
|
2013-01-10 00:06:10 -07:00
|
|
|
if (used <= 0) {
|
2007-06-24 00:07:50 -06:00
|
|
|
if (!copied)
|
|
|
|
copied = used;
|
|
|
|
break;
|
|
|
|
} else if (used <= len) {
|
2005-04-16 16:20:36 -06:00
|
|
|
seq += used;
|
|
|
|
copied += used;
|
|
|
|
offset += used;
|
|
|
|
}
|
2012-12-02 04:49:27 -07:00
|
|
|
/* If recv_actor drops the lock (e.g. TCP splice
|
2008-06-04 16:45:58 -06:00
|
|
|
* receive) the skb pointer might be invalid when
|
|
|
|
* getting here: tcp_collapse might have deleted it
|
|
|
|
* while aggregating skbs from the socket queue.
|
|
|
|
*/
|
2012-12-02 04:49:27 -07:00
|
|
|
skb = tcp_recv_skb(sk, seq - 1, &offset);
|
|
|
|
if (!skb)
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
2012-12-02 04:49:27 -07:00
|
|
|
/* TCP coalescing might have appended data to the skb.
|
|
|
|
* Try to splice more frags
|
|
|
|
*/
|
|
|
|
if (offset + 1 != skb->len)
|
|
|
|
continue;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2007-04-10 22:04:22 -06:00
|
|
|
if (tcp_hdr(skb)->fin) {
|
2012-05-16 16:48:15 -06:00
|
|
|
sk_eat_skb(sk, skb, false);
|
2005-04-16 16:20:36 -06:00
|
|
|
++seq;
|
|
|
|
break;
|
|
|
|
}
|
2012-05-16 16:48:15 -06:00
|
|
|
sk_eat_skb(sk, skb, false);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!desc->count)
|
|
|
|
break;
|
2010-03-30 14:56:01 -06:00
|
|
|
tp->copied_seq = seq;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
tp->copied_seq = seq;
|
|
|
|
|
|
|
|
tcp_rcv_space_adjust(sk);
|
|
|
|
|
|
|
|
/* Clean up data we have read: This will do ACK frames. */
|
2013-01-09 13:59:09 -07:00
|
|
|
if (copied > 0) {
|
|
|
|
tcp_recv_skb(sk, seq, &offset);
|
2006-05-23 19:00:16 -06:00
|
|
|
tcp_cleanup_rbuf(sk, copied);
|
2013-01-09 13:59:09 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
return copied;
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_read_sock);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This routine copies from a sock struct into the user buffer.
|
|
|
|
*
|
|
|
|
* Technical note: in 2.3 we work on _locked_ socket, so that
|
|
|
|
* tricks with *seq access order and skb->users are not required.
|
|
|
|
* Probably, code can be easily improved even more.
|
|
|
|
*/
|
|
|
|
|
|
|
|
int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
|
|
|
|
size_t len, int nonblock, int flags, int *addr_len)
|
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
int copied = 0;
|
|
|
|
u32 peek_seq;
|
|
|
|
u32 *seq;
|
|
|
|
unsigned long used;
|
|
|
|
int err;
|
|
|
|
int target; /* Read at least this many bytes */
|
|
|
|
long timeo;
|
|
|
|
struct task_struct *user_recv = NULL;
|
2012-05-16 16:48:15 -06:00
|
|
|
bool copied_early = false;
|
2007-03-08 10:57:36 -07:00
|
|
|
struct sk_buff *skb;
|
2009-05-10 14:32:34 -06:00
|
|
|
u32 urg_hole = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
net-timestamp: TCP timestamping
TCP timestamping extends SO_TIMESTAMPING to bytestreams.
Bytestreams do not have a 1:1 relationship between send() buffers and
network packets. The feature interprets a send call on a bytestream as
a request for a timestamp for the last byte in that send() buffer.
The choice corresponds to a request for a timestamp when all bytes in
the buffer have been sent. That assumption depends on in-order kernel
transmission. This is the common case. That said, it is possible to
construct a traffic shaping tree that would result in reordering.
The guarantee is strong, then, but not ironclad.
This implementation supports send and sendpages (splice). GSO replaces
one large packet with multiple smaller packets. This patch also copies
the option into the correct smaller packet.
This patch does not yet support timestamping on data in an initial TCP
Fast Open SYN, because that takes a very different data path.
If ID generation in ee_data is enabled, bytestream timestamps return a
byte offset, instead of the packet counter for datagrams.
The implementation supports a single timestamp per packet. It silenty
replaces requests for previous timestamps. To avoid missing tstamps,
flush the tcp queue by disabling Nagle, cork and autocork. Missing
tstamps can be detected by offset when the ee_data ID is enabled.
Implementation details:
- On GSO, the timestamping code can be included in the main loop. I
moved it into its own loop to reduce the impact on the common case
to a single branch.
- To avoid leaking the absolute seqno to userspace, the offset
returned in ee_data must always be relative. It is an offset between
an skb and sk field. The first is always set (also for GSO & ACK).
The second must also never be uninitialized. Only allow the ID
option on sockets in the ESTABLISHED state, for which the seqno
is available. Never reset it to zero (instead, move it to the
current seqno when reenabling the option).
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-04 20:11:49 -06:00
|
|
|
if (unlikely(flags & MSG_ERRQUEUE))
|
|
|
|
return ip_recv_error(sk, msg, len, addr_len);
|
|
|
|
|
2013-07-08 07:20:34 -06:00
|
|
|
if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
|
|
|
|
(sk->sk_state == TCP_ESTABLISHED))
|
|
|
|
sk_busy_loop(sk, nonblock);
|
2013-06-10 02:40:10 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
lock_sock(sk);
|
|
|
|
|
|
|
|
err = -ENOTCONN;
|
|
|
|
if (sk->sk_state == TCP_LISTEN)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
timeo = sock_rcvtimeo(sk, nonblock);
|
|
|
|
|
|
|
|
/* Urgent data needs to be handled specially. */
|
|
|
|
if (flags & MSG_OOB)
|
|
|
|
goto recv_urg;
|
|
|
|
|
2012-04-18 21:41:01 -06:00
|
|
|
if (unlikely(tp->repair)) {
|
|
|
|
err = -EPERM;
|
|
|
|
if (!(flags & MSG_PEEK))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (tp->repair_queue == TCP_SEND_QUEUE)
|
|
|
|
goto recv_sndq;
|
|
|
|
|
|
|
|
err = -EINVAL;
|
|
|
|
if (tp->repair_queue == TCP_NO_QUEUE)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* 'common' recv queue MSG_PEEK-ing */
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
seq = &tp->copied_seq;
|
|
|
|
if (flags & MSG_PEEK) {
|
|
|
|
peek_seq = tp->copied_seq;
|
|
|
|
seq = &peek_seq;
|
|
|
|
}
|
|
|
|
|
|
|
|
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
|
|
|
|
|
2006-05-23 19:05:53 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
|
|
|
tp->ucopy.dma_chan = NULL;
|
|
|
|
preempt_disable();
|
2007-03-08 10:57:36 -07:00
|
|
|
skb = skb_peek_tail(&sk->sk_receive_queue);
|
2007-03-08 10:57:36 -07:00
|
|
|
{
|
|
|
|
int available = 0;
|
|
|
|
|
|
|
|
if (skb)
|
|
|
|
available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
|
|
|
|
if ((available < target) &&
|
|
|
|
(len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
|
|
|
|
!sysctl_tcp_low_latency &&
|
2012-04-04 17:10:46 -06:00
|
|
|
net_dma_find_channel()) {
|
2013-11-19 08:13:38 -07:00
|
|
|
preempt_enable();
|
2007-03-08 10:57:36 -07:00
|
|
|
tp->ucopy.pinned_list =
|
|
|
|
dma_pin_iovec_pages(msg->msg_iov, len);
|
|
|
|
} else {
|
2013-11-19 08:13:38 -07:00
|
|
|
preempt_enable();
|
2007-03-08 10:57:36 -07:00
|
|
|
}
|
|
|
|
}
|
2006-05-23 19:05:53 -06:00
|
|
|
#endif
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
do {
|
|
|
|
u32 offset;
|
|
|
|
|
|
|
|
/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
|
|
|
|
if (tp->urg_data && tp->urg_seq == *seq) {
|
|
|
|
if (copied)
|
|
|
|
break;
|
|
|
|
if (signal_pending(current)) {
|
|
|
|
copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Next get a buffer. */
|
|
|
|
|
2009-05-28 22:35:47 -06:00
|
|
|
skb_queue_walk(&sk->sk_receive_queue, skb) {
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Now that we have two receive queues this
|
|
|
|
* shouldn't happen.
|
|
|
|
*/
|
2009-11-13 14:56:33 -07:00
|
|
|
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
|
2010-10-30 05:08:53 -06:00
|
|
|
"recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
|
|
|
|
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
|
|
|
|
flags))
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
2009-11-13 14:56:33 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
offset = *seq - TCP_SKB_CB(skb)->seq;
|
2007-04-10 22:04:22 -06:00
|
|
|
if (tcp_hdr(skb)->syn)
|
2005-04-16 16:20:36 -06:00
|
|
|
offset--;
|
|
|
|
if (offset < skb->len)
|
|
|
|
goto found_ok_skb;
|
2007-04-10 22:04:22 -06:00
|
|
|
if (tcp_hdr(skb)->fin)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto found_fin_ok;
|
2010-10-30 05:08:53 -06:00
|
|
|
WARN(!(flags & MSG_PEEK),
|
|
|
|
"recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
|
|
|
|
*seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
|
2009-05-28 22:35:47 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* Well, if we have backlog, try to process it now yet. */
|
|
|
|
|
|
|
|
if (copied >= target && !sk->sk_backlog.tail)
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (copied) {
|
|
|
|
if (sk->sk_err ||
|
|
|
|
sk->sk_state == TCP_CLOSE ||
|
|
|
|
(sk->sk_shutdown & RCV_SHUTDOWN) ||
|
|
|
|
!timeo ||
|
2008-11-05 04:36:01 -07:00
|
|
|
signal_pending(current))
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
if (sock_flag(sk, SOCK_DONE))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (sk->sk_err) {
|
|
|
|
copied = sock_error(sk);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (sk->sk_shutdown & RCV_SHUTDOWN)
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (sk->sk_state == TCP_CLOSE) {
|
|
|
|
if (!sock_flag(sk, SOCK_DONE)) {
|
|
|
|
/* This occurs when user tries to read
|
|
|
|
* from never connected socket.
|
|
|
|
*/
|
|
|
|
copied = -ENOTCONN;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!timeo) {
|
|
|
|
copied = -EAGAIN;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (signal_pending(current)) {
|
|
|
|
copied = sock_intr_errno(timeo);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-05-23 19:00:16 -06:00
|
|
|
tcp_cleanup_rbuf(sk, copied);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2005-06-19 00:01:10 -06:00
|
|
|
if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Install new reader */
|
|
|
|
if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
|
|
|
|
user_recv = current;
|
|
|
|
tp->ucopy.task = user_recv;
|
|
|
|
tp->ucopy.iov = msg->msg_iov;
|
|
|
|
}
|
|
|
|
|
|
|
|
tp->ucopy.len = len;
|
|
|
|
|
2008-07-25 22:43:18 -06:00
|
|
|
WARN_ON(tp->copied_seq != tp->rcv_nxt &&
|
|
|
|
!(flags & (MSG_PEEK | MSG_TRUNC)));
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* Ugly... If prequeue is not empty, we have to
|
|
|
|
* process it before releasing socket, otherwise
|
|
|
|
* order will be broken at second iteration.
|
|
|
|
* More elegant solution is required!!!
|
|
|
|
*
|
|
|
|
* Look: we have the following (pseudo)queues:
|
|
|
|
*
|
|
|
|
* 1. packets in flight
|
|
|
|
* 2. backlog
|
|
|
|
* 3. prequeue
|
|
|
|
* 4. receive_queue
|
|
|
|
*
|
|
|
|
* Each queue can be processed only if the next ones
|
|
|
|
* are empty. At this point we have empty receive_queue.
|
|
|
|
* But prequeue _can_ be not empty after 2nd iteration,
|
|
|
|
* when we jumped to start of loop because backlog
|
|
|
|
* processing added something to receive_queue.
|
|
|
|
* We cannot release_sock(), because backlog contains
|
|
|
|
* packets arrived _after_ prequeued ones.
|
|
|
|
*
|
|
|
|
* Shortly, algorithm is clear --- to process all
|
|
|
|
* the queues in order. We could make it more directly,
|
|
|
|
* requeueing packets from backlog to prequeue, if
|
|
|
|
* is not empty. It is more elegant, but eats cycles,
|
|
|
|
* unfortunately.
|
|
|
|
*/
|
2005-07-08 15:57:23 -06:00
|
|
|
if (!skb_queue_empty(&tp->ucopy.prequeue))
|
2005-04-16 16:20:36 -06:00
|
|
|
goto do_prequeue;
|
|
|
|
|
|
|
|
/* __ Set realtime policy in scheduler __ */
|
|
|
|
}
|
|
|
|
|
2010-03-15 23:22:44 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
2012-09-13 22:59:52 -06:00
|
|
|
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
|
2012-11-08 02:59:54 -07:00
|
|
|
dma_async_issue_pending(tp->ucopy.dma_chan);
|
2012-09-13 22:59:52 -06:00
|
|
|
}
|
2010-03-15 23:22:44 -06:00
|
|
|
#endif
|
2005-04-16 16:20:36 -06:00
|
|
|
if (copied >= target) {
|
|
|
|
/* Do not sleep, just process backlog. */
|
|
|
|
release_sock(sk);
|
|
|
|
lock_sock(sk);
|
|
|
|
} else
|
|
|
|
sk_wait_data(sk, &timeo);
|
|
|
|
|
2006-05-23 19:05:53 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
2010-03-15 23:22:44 -06:00
|
|
|
tcp_service_net_dma(sk, false); /* Don't block */
|
2006-05-23 19:05:53 -06:00
|
|
|
tp->ucopy.wakeup = 0;
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (user_recv) {
|
|
|
|
int chunk;
|
|
|
|
|
|
|
|
/* __ Restore normal policy in scheduler __ */
|
|
|
|
|
|
|
|
if ((chunk = len - tp->ucopy.len) != 0) {
|
2008-07-16 21:32:45 -06:00
|
|
|
NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
|
2005-04-16 16:20:36 -06:00
|
|
|
len -= chunk;
|
|
|
|
copied += chunk;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (tp->rcv_nxt == tp->copied_seq &&
|
2005-07-08 15:57:23 -06:00
|
|
|
!skb_queue_empty(&tp->ucopy.prequeue)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
do_prequeue:
|
|
|
|
tcp_prequeue_process(sk);
|
|
|
|
|
|
|
|
if ((chunk = len - tp->ucopy.len) != 0) {
|
2008-07-16 21:32:45 -06:00
|
|
|
NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
|
2005-04-16 16:20:36 -06:00
|
|
|
len -= chunk;
|
|
|
|
copied += chunk;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2009-05-10 14:32:34 -06:00
|
|
|
if ((flags & MSG_PEEK) &&
|
|
|
|
(peek_seq - copied - urg_hole != tp->copied_seq)) {
|
2012-05-13 15:56:26 -06:00
|
|
|
net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
|
|
|
|
current->comm,
|
|
|
|
task_pid_nr(current));
|
2005-04-16 16:20:36 -06:00
|
|
|
peek_seq = tp->copied_seq;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
|
|
|
|
found_ok_skb:
|
|
|
|
/* Ok so how much can we use? */
|
|
|
|
used = skb->len - offset;
|
|
|
|
if (len < used)
|
|
|
|
used = len;
|
|
|
|
|
|
|
|
/* Do we have urgent data here? */
|
|
|
|
if (tp->urg_data) {
|
|
|
|
u32 urg_offset = tp->urg_seq - *seq;
|
|
|
|
if (urg_offset < used) {
|
|
|
|
if (!urg_offset) {
|
|
|
|
if (!sock_flag(sk, SOCK_URGINLINE)) {
|
|
|
|
++*seq;
|
2009-05-10 14:32:34 -06:00
|
|
|
urg_hole++;
|
2005-04-16 16:20:36 -06:00
|
|
|
offset++;
|
|
|
|
used--;
|
|
|
|
if (!used)
|
|
|
|
goto skip_copy;
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
used = urg_offset;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!(flags & MSG_TRUNC)) {
|
2006-05-23 19:05:53 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
|
|
|
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
|
2012-04-04 17:10:46 -06:00
|
|
|
tp->ucopy.dma_chan = net_dma_find_channel();
|
2006-05-23 19:05:53 -06:00
|
|
|
|
|
|
|
if (tp->ucopy.dma_chan) {
|
|
|
|
tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
|
|
|
|
tp->ucopy.dma_chan, skb, offset,
|
|
|
|
msg->msg_iov, used,
|
|
|
|
tp->ucopy.pinned_list);
|
|
|
|
|
|
|
|
if (tp->ucopy.dma_cookie < 0) {
|
|
|
|
|
2012-03-12 01:03:32 -06:00
|
|
|
pr_alert("%s: dma_cookie < 0\n",
|
|
|
|
__func__);
|
2006-05-23 19:05:53 -06:00
|
|
|
|
|
|
|
/* Exception. Bailout! */
|
|
|
|
if (!copied)
|
|
|
|
copied = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
2010-03-15 23:22:44 -06:00
|
|
|
|
2012-11-08 02:59:54 -07:00
|
|
|
dma_async_issue_pending(tp->ucopy.dma_chan);
|
2010-03-15 23:22:44 -06:00
|
|
|
|
2006-05-23 19:05:53 -06:00
|
|
|
if ((offset + used) == skb->len)
|
2012-05-16 16:48:15 -06:00
|
|
|
copied_early = true;
|
2006-05-23 19:05:53 -06:00
|
|
|
|
|
|
|
} else
|
|
|
|
#endif
|
|
|
|
{
|
|
|
|
err = skb_copy_datagram_iovec(skb, offset,
|
|
|
|
msg->msg_iov, used);
|
|
|
|
if (err) {
|
|
|
|
/* Exception. Bailout! */
|
|
|
|
if (!copied)
|
|
|
|
copied = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
*seq += used;
|
|
|
|
copied += used;
|
|
|
|
len -= used;
|
|
|
|
|
|
|
|
tcp_rcv_space_adjust(sk);
|
|
|
|
|
|
|
|
skip_copy:
|
|
|
|
if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
|
|
|
|
tp->urg_data = 0;
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
tcp_fast_path_check(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
if (used + offset < skb->len)
|
|
|
|
continue;
|
|
|
|
|
2007-04-10 22:04:22 -06:00
|
|
|
if (tcp_hdr(skb)->fin)
|
2005-04-16 16:20:36 -06:00
|
|
|
goto found_fin_ok;
|
2006-05-23 19:05:53 -06:00
|
|
|
if (!(flags & MSG_PEEK)) {
|
|
|
|
sk_eat_skb(sk, skb, copied_early);
|
2012-05-16 16:48:15 -06:00
|
|
|
copied_early = false;
|
2006-05-23 19:05:53 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
continue;
|
|
|
|
|
|
|
|
found_fin_ok:
|
|
|
|
/* Process the FIN. */
|
|
|
|
++*seq;
|
2006-05-23 19:05:53 -06:00
|
|
|
if (!(flags & MSG_PEEK)) {
|
|
|
|
sk_eat_skb(sk, skb, copied_early);
|
2012-05-16 16:48:15 -06:00
|
|
|
copied_early = false;
|
2006-05-23 19:05:53 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
} while (len > 0);
|
|
|
|
|
|
|
|
if (user_recv) {
|
2005-07-08 15:57:23 -06:00
|
|
|
if (!skb_queue_empty(&tp->ucopy.prequeue)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
int chunk;
|
|
|
|
|
|
|
|
tp->ucopy.len = copied > 0 ? len : 0;
|
|
|
|
|
|
|
|
tcp_prequeue_process(sk);
|
|
|
|
|
|
|
|
if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
|
2008-07-16 21:32:45 -06:00
|
|
|
NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
|
2005-04-16 16:20:36 -06:00
|
|
|
len -= chunk;
|
|
|
|
copied += chunk;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
tp->ucopy.task = NULL;
|
|
|
|
tp->ucopy.len = 0;
|
|
|
|
}
|
|
|
|
|
2006-05-23 19:05:53 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
2010-03-15 23:22:44 -06:00
|
|
|
tcp_service_net_dma(sk, true); /* Wait for queue to drain */
|
|
|
|
tp->ucopy.dma_chan = NULL;
|
2006-05-23 19:05:53 -06:00
|
|
|
|
|
|
|
if (tp->ucopy.pinned_list) {
|
|
|
|
dma_unpin_iovec_pages(tp->ucopy.pinned_list);
|
|
|
|
tp->ucopy.pinned_list = NULL;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* According to UNIX98, msg_name/msg_namelen are ignored
|
|
|
|
* on connected socket. I was just happy when found this 8) --ANK
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* Clean up data we have read: This will do ACK frames. */
|
2006-05-23 19:00:16 -06:00
|
|
|
tcp_cleanup_rbuf(sk, copied);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
release_sock(sk);
|
|
|
|
return copied;
|
|
|
|
|
|
|
|
out:
|
|
|
|
release_sock(sk);
|
|
|
|
return err;
|
|
|
|
|
|
|
|
recv_urg:
|
2009-03-31 15:43:17 -06:00
|
|
|
err = tcp_recv_urg(sk, msg, len, flags);
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2012-04-18 21:41:01 -06:00
|
|
|
|
|
|
|
recv_sndq:
|
|
|
|
err = tcp_peek_sndq(sk, msg, len);
|
|
|
|
goto out;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_recvmsg);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 04:17:20 -07:00
|
|
|
void tcp_set_state(struct sock *sk, int state)
|
|
|
|
{
|
|
|
|
int oldstate = sk->sk_state;
|
|
|
|
|
|
|
|
switch (state) {
|
|
|
|
case TCP_ESTABLISHED:
|
|
|
|
if (oldstate != TCP_ESTABLISHED)
|
2008-07-16 21:22:04 -06:00
|
|
|
TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 04:17:20 -07:00
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_CLOSE:
|
|
|
|
if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
|
2008-07-16 21:22:04 -06:00
|
|
|
TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS);
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 04:17:20 -07:00
|
|
|
|
|
|
|
sk->sk_prot->unhash(sk);
|
|
|
|
if (inet_csk(sk)->icsk_bind_hash &&
|
|
|
|
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
|
[SOCK] proto: Add hashinfo member to struct proto
This way we can remove TCP and DCCP specific versions of
sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port
sk->sk_prot->hash: inet_hash is directly used, only v6 need
a specific version to deal with mapped sockets
sk->sk_prot->unhash: both v4 and v6 use inet_hash directly
struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so
that inet_csk_get_port can find the per family routine.
Now only the lookup routines receive as a parameter a struct inet_hashtable.
With this we further reuse code, reducing the difference among INET transport
protocols.
Eventually work has to be done on UDP and SCTP to make them share this
infrastructure and get as a bonus inet_diag interfaces so that iproute can be
used with these protocols.
net-2.6/net/ipv4/inet_hashtables.c:
struct proto | +8
struct inet_connection_sock_af_ops | +8
2 structs changed
__inet_hash_nolisten | +18
__inet_hash | -210
inet_put_port | +8
inet_bind_bucket_create | +1
__inet_hash_connect | -8
5 functions changed, 27 bytes added, 218 bytes removed, diff: -191
net-2.6/net/core/sock.c:
proto_seq_show | +3
1 function changed, 3 bytes added, diff: +3
net-2.6/net/ipv4/inet_connection_sock.c:
inet_csk_get_port | +15
1 function changed, 15 bytes added, diff: +15
net-2.6/net/ipv4/tcp.c:
tcp_set_state | -7
1 function changed, 7 bytes removed, diff: -7
net-2.6/net/ipv4/tcp_ipv4.c:
tcp_v4_get_port | -31
tcp_v4_hash | -48
tcp_v4_destroy_sock | -7
tcp_v4_syn_recv_sock | -2
tcp_unhash | -179
5 functions changed, 267 bytes removed, diff: -267
net-2.6/net/ipv6/inet6_hashtables.c:
__inet6_hash | +8
1 function changed, 8 bytes added, diff: +8
net-2.6/net/ipv4/inet_hashtables.c:
inet_unhash | +190
inet_hash | +242
2 functions changed, 432 bytes added, diff: +432
vmlinux:
16 functions changed, 485 bytes added, 492 bytes removed, diff: -7
/home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c:
tcp_v6_get_port | -31
tcp_v6_hash | -7
tcp_v6_syn_recv_sock | -9
3 functions changed, 47 bytes removed, diff: -47
/home/acme/git/net-2.6/net/dccp/proto.c:
dccp_destroy_sock | -7
dccp_unhash | -179
dccp_hash | -49
dccp_set_state | -7
dccp_done | +1
5 functions changed, 1 bytes added, 242 bytes removed, diff: -241
/home/acme/git/net-2.6/net/dccp/ipv4.c:
dccp_v4_get_port | -31
dccp_v4_request_recv_sock | -2
2 functions changed, 33 bytes removed, diff: -33
/home/acme/git/net-2.6/net/dccp/ipv6.c:
dccp_v6_get_port | -31
dccp_v6_hash | -7
dccp_v6_request_recv_sock | +5
3 functions changed, 5 bytes added, 38 bytes removed, diff: -33
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 05:06:04 -07:00
|
|
|
inet_put_port(sk);
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 04:17:20 -07:00
|
|
|
/* fall through */
|
|
|
|
default:
|
2008-11-03 01:24:34 -07:00
|
|
|
if (oldstate == TCP_ESTABLISHED)
|
2008-07-16 21:22:46 -06:00
|
|
|
TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 04:17:20 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Change state AFTER socket is unhashed to avoid closed
|
|
|
|
* socket sitting in hash tables.
|
|
|
|
*/
|
|
|
|
sk->sk_state = state;
|
|
|
|
|
|
|
|
#ifdef STATE_TRACE
|
2008-11-03 01:24:34 -07:00
|
|
|
SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
|
[TCP]: Uninline tcp_set_state
net/ipv4/tcp.c:
tcp_close_state | -226
tcp_done | -145
tcp_close | -564
tcp_disconnect | -141
4 functions changed, 1076 bytes removed, diff: -1076
net/ipv4/tcp_input.c:
tcp_fin | -86
tcp_rcv_state_process | -164
2 functions changed, 250 bytes removed, diff: -250
net/ipv4/tcp_ipv4.c:
tcp_v4_connect | -209
1 function changed, 209 bytes removed, diff: -209
net/ipv4/arp.c:
arp_ignore | +5
1 function changed, 5 bytes added, diff: +5
net/ipv6/tcp_ipv6.c:
tcp_v6_connect | -158
1 function changed, 158 bytes removed, diff: -158
net/sunrpc/xprtsock.c:
xs_sendpages | -2
1 function changed, 2 bytes removed, diff: -2
net/dccp/ccids/ccid3.c:
ccid3_update_send_interval | +7
1 function changed, 7 bytes added, diff: +7
net/ipv4/tcp.c:
tcp_set_state | +238
1 function changed, 238 bytes added, diff: +238
built-in.o:
12 functions changed, 250 bytes added, 1695 bytes removed, diff: -1445
I've no explanation why some unrelated changes seem to occur
consistently as well (arp_ignore, ccid3_update_send_interval;
I checked the arp_ignore asm and it seems to be due to some
reordered of operation order causing some extra opcodes to be
generated). Still, the benefits are pretty obvious from the
codiff's results.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-12 04:17:20 -07:00
|
|
|
#endif
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_set_state);
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* State processing on a close. This implements the state shift for
|
|
|
|
* sending our FIN frame. Note that we only send a FIN for some
|
|
|
|
* states. A shutdown() may have already sent the FIN, or we may be
|
|
|
|
* closed.
|
|
|
|
*/
|
|
|
|
|
2005-11-29 17:21:38 -07:00
|
|
|
static const unsigned char new_state[16] = {
|
2005-04-16 16:20:36 -06:00
|
|
|
/* current state: new state: action: */
|
|
|
|
/* (Invalid) */ TCP_CLOSE,
|
|
|
|
/* TCP_ESTABLISHED */ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
|
|
|
|
/* TCP_SYN_SENT */ TCP_CLOSE,
|
|
|
|
/* TCP_SYN_RECV */ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
|
|
|
|
/* TCP_FIN_WAIT1 */ TCP_FIN_WAIT1,
|
|
|
|
/* TCP_FIN_WAIT2 */ TCP_FIN_WAIT2,
|
|
|
|
/* TCP_TIME_WAIT */ TCP_CLOSE,
|
|
|
|
/* TCP_CLOSE */ TCP_CLOSE,
|
|
|
|
/* TCP_CLOSE_WAIT */ TCP_LAST_ACK | TCP_ACTION_FIN,
|
|
|
|
/* TCP_LAST_ACK */ TCP_LAST_ACK,
|
|
|
|
/* TCP_LISTEN */ TCP_CLOSE,
|
|
|
|
/* TCP_CLOSING */ TCP_CLOSING,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int tcp_close_state(struct sock *sk)
|
|
|
|
{
|
|
|
|
int next = (int)new_state[sk->sk_state];
|
|
|
|
int ns = next & TCP_STATE_MASK;
|
|
|
|
|
|
|
|
tcp_set_state(sk, ns);
|
|
|
|
|
|
|
|
return next & TCP_ACTION_FIN;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Shutdown the sending side of a connection. Much like close except
|
2008-04-21 03:27:58 -06:00
|
|
|
* that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD).
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
|
|
|
|
|
|
|
void tcp_shutdown(struct sock *sk, int how)
|
|
|
|
{
|
|
|
|
/* We need to grab some memory, and put together a FIN,
|
|
|
|
* and then put it into the queue to be sent.
|
|
|
|
* Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92.
|
|
|
|
*/
|
|
|
|
if (!(how & SEND_SHUTDOWN))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/* If we've already sent a FIN, or it's a closed state, skip this. */
|
|
|
|
if ((1 << sk->sk_state) &
|
|
|
|
(TCPF_ESTABLISHED | TCPF_SYN_SENT |
|
|
|
|
TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
|
|
|
|
/* Clear out any half completed packets. FIN if needed. */
|
|
|
|
if (tcp_close_state(sk))
|
|
|
|
tcp_send_fin(sk);
|
|
|
|
}
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_shutdown);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-01-30 15:16:06 -07:00
|
|
|
bool tcp_check_oom(struct sock *sk, int shift)
|
|
|
|
{
|
|
|
|
bool too_many_orphans, out_of_socket_memory;
|
|
|
|
|
|
|
|
too_many_orphans = tcp_too_many_orphans(sk, shift);
|
|
|
|
out_of_socket_memory = tcp_out_of_memory(sk);
|
|
|
|
|
2012-05-13 15:56:26 -06:00
|
|
|
if (too_many_orphans)
|
|
|
|
net_info_ratelimited("too many orphaned sockets\n");
|
|
|
|
if (out_of_socket_memory)
|
|
|
|
net_info_ratelimited("out of memory -- consider tuning tcp_mem\n");
|
2012-01-30 15:16:06 -07:00
|
|
|
return too_many_orphans || out_of_socket_memory;
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
void tcp_close(struct sock *sk, long timeout)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb;
|
|
|
|
int data_was_unread = 0;
|
2006-05-04 00:31:35 -06:00
|
|
|
int state;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
sk->sk_shutdown = SHUTDOWN_MASK;
|
|
|
|
|
|
|
|
if (sk->sk_state == TCP_LISTEN) {
|
|
|
|
tcp_set_state(sk, TCP_CLOSE);
|
|
|
|
|
|
|
|
/* Special case. */
|
2005-08-09 21:11:41 -06:00
|
|
|
inet_csk_listen_stop(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
goto adjudge_to_death;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* We need to flush the recv. buffs. We do this only on the
|
|
|
|
* descriptor close, not protocol-sourced closes, because the
|
|
|
|
* reader process may not have drained the data yet!
|
|
|
|
*/
|
|
|
|
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
|
|
|
|
u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
|
2007-04-10 22:04:22 -06:00
|
|
|
tcp_hdr(skb)->fin;
|
2005-04-16 16:20:36 -06:00
|
|
|
data_was_unread += len;
|
|
|
|
__kfree_skb(skb);
|
|
|
|
}
|
|
|
|
|
2007-12-31 01:11:19 -07:00
|
|
|
sk_mem_reclaim(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
tcp: do not send reset to already closed sockets
i've found that tcp_close() can be called for an already closed
socket, but still sends reset in this case (tcp_send_active_reset())
which seems to be incorrect. Moreover, a packet with reset is sent
with different source port as original port number has been already
cleared on socket. Besides that incrementing stat counter for
LINUX_MIB_TCPABORTONCLOSE also does not look correct in this case.
Initially this issue was found on 2.6.18-x RHEL5 kernel, but the same
seems to be true for the current mainstream kernel (checked on
2.6.35-rc3). Please, correct me if i missed something.
How that happens:
1) the server receives a packet for socket in TCP_CLOSE_WAIT state
that triggers a tcp_reset():
Call Trace:
<IRQ> [<ffffffff8025b9b9>] tcp_reset+0x12f/0x1e8
[<ffffffff80046125>] tcp_rcv_state_process+0x1c0/0xa08
[<ffffffff8003eb22>] tcp_v4_do_rcv+0x310/0x37a
[<ffffffff80028bea>] tcp_v4_rcv+0x74d/0xb43
[<ffffffff8024ef4c>] ip_local_deliver_finish+0x0/0x259
[<ffffffff80037131>] ip_local_deliver+0x200/0x2f4
[<ffffffff8003843c>] ip_rcv+0x64c/0x69f
[<ffffffff80021d89>] netif_receive_skb+0x4c4/0x4fa
[<ffffffff80032eca>] process_backlog+0x90/0xec
[<ffffffff8000cc50>] net_rx_action+0xbb/0x1f1
[<ffffffff80012d3a>] __do_softirq+0xf5/0x1ce
[<ffffffff8001147a>] handle_IRQ_event+0x56/0xb0
[<ffffffff8006334c>] call_softirq+0x1c/0x28
[<ffffffff80070476>] do_softirq+0x2c/0x85
[<ffffffff80070441>] do_IRQ+0x149/0x152
[<ffffffff80062665>] ret_from_intr+0x0/0xa
<EOI> [<ffffffff80008a2e>] __handle_mm_fault+0x6cd/0x1303
[<ffffffff80008903>] __handle_mm_fault+0x5a2/0x1303
[<ffffffff80033a9d>] cache_free_debugcheck+0x21f/0x22e
[<ffffffff8006a263>] do_page_fault+0x49a/0x7dc
[<ffffffff80066487>] thread_return+0x89/0x174
[<ffffffff800c5aee>] audit_syscall_exit+0x341/0x35c
[<ffffffff80062e39>] error_exit+0x0/0x84
tcp_rcv_state_process()
... // (sk_state == TCP_CLOSE_WAIT here)
...
/* step 2: check RST bit */
if(th->rst) {
tcp_reset(sk);
goto discard;
}
...
---------------------------------
tcp_rcv_state_process
tcp_reset
tcp_done
tcp_set_state(sk, TCP_CLOSE);
inet_put_port
__inet_put_port
inet_sk(sk)->num = 0;
sk->sk_shutdown = SHUTDOWN_MASK;
2) After that the process (socket owner) tries to write something to
that socket and "inet_autobind" sets a _new_ (which differs from
the original!) port number for the socket:
Call Trace:
[<ffffffff80255a12>] inet_bind_hash+0x33/0x5f
[<ffffffff80257180>] inet_csk_get_port+0x216/0x268
[<ffffffff8026bcc9>] inet_autobind+0x22/0x8f
[<ffffffff80049140>] inet_sendmsg+0x27/0x57
[<ffffffff8003a9d9>] do_sock_write+0xae/0xea
[<ffffffff80226ac7>] sock_writev+0xdc/0xf6
[<ffffffff800680c7>] _spin_lock_irqsave+0x9/0xe
[<ffffffff8001fb49>] __pollwait+0x0/0xdd
[<ffffffff8008d533>] default_wake_function+0x0/0xe
[<ffffffff800a4f10>] autoremove_wake_function+0x0/0x2e
[<ffffffff800f0b49>] do_readv_writev+0x163/0x274
[<ffffffff80066538>] thread_return+0x13a/0x174
[<ffffffff800145d8>] tcp_poll+0x0/0x1c9
[<ffffffff800c56d3>] audit_syscall_entry+0x180/0x1b3
[<ffffffff800f0dd0>] sys_writev+0x49/0xe4
[<ffffffff800622dd>] tracesys+0xd5/0xe0
3) sendmsg fails at last with -EPIPE (=> 'write' returns -EPIPE in userspace):
F: tcp_sendmsg1 -EPIPE: sk=ffff81000bda00d0, sport=49847, old_state=7, new_state=7, sk_err=0, sk_shutdown=3
Call Trace:
[<ffffffff80027557>] tcp_sendmsg+0xcb/0xe87
[<ffffffff80033300>] release_sock+0x10/0xae
[<ffffffff8016f20f>] vgacon_cursor+0x0/0x1a7
[<ffffffff8026bd32>] inet_autobind+0x8b/0x8f
[<ffffffff8003a9d9>] do_sock_write+0xae/0xea
[<ffffffff80226ac7>] sock_writev+0xdc/0xf6
[<ffffffff800680c7>] _spin_lock_irqsave+0x9/0xe
[<ffffffff8001fb49>] __pollwait+0x0/0xdd
[<ffffffff8008d533>] default_wake_function+0x0/0xe
[<ffffffff800a4f10>] autoremove_wake_function+0x0/0x2e
[<ffffffff800f0b49>] do_readv_writev+0x163/0x274
[<ffffffff80066538>] thread_return+0x13a/0x174
[<ffffffff800145d8>] tcp_poll+0x0/0x1c9
[<ffffffff800c56d3>] audit_syscall_entry+0x180/0x1b3
[<ffffffff800f0dd0>] sys_writev+0x49/0xe4
[<ffffffff800622dd>] tracesys+0xd5/0xe0
tcp_sendmsg()
...
/* Wait for a connection to finish. */
if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
int old_state = sk->sk_state;
if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) {
if (f_d && (err == -EPIPE)) {
printk("F: tcp_sendmsg1 -EPIPE: sk=%p, sport=%u, old_state=%d, new_state=%d, "
"sk_err=%d, sk_shutdown=%d\n",
sk, ntohs(inet_sk(sk)->sport), old_state, sk->sk_state,
sk->sk_err, sk->sk_shutdown);
dump_stack();
}
goto out_err;
}
}
...
4) Then the process (socket owner) understands that it's time to close
that socket and does that (and thus triggers sending reset packet):
Call Trace:
...
[<ffffffff80032077>] dev_queue_xmit+0x343/0x3d6
[<ffffffff80034698>] ip_output+0x351/0x384
[<ffffffff80251ae9>] dst_output+0x0/0xe
[<ffffffff80036ec6>] ip_queue_xmit+0x567/0x5d2
[<ffffffff80095700>] vprintk+0x21/0x33
[<ffffffff800070f0>] check_poison_obj+0x2e/0x206
[<ffffffff80013587>] poison_obj+0x36/0x45
[<ffffffff8025dea6>] tcp_send_active_reset+0x15/0x14d
[<ffffffff80023481>] dbg_redzone1+0x1c/0x25
[<ffffffff8025dea6>] tcp_send_active_reset+0x15/0x14d
[<ffffffff8000ca94>] cache_alloc_debugcheck_after+0x189/0x1c8
[<ffffffff80023405>] tcp_transmit_skb+0x764/0x786
[<ffffffff8025df8a>] tcp_send_active_reset+0xf9/0x14d
[<ffffffff80258ff1>] tcp_close+0x39a/0x960
[<ffffffff8026be12>] inet_release+0x69/0x80
[<ffffffff80059b31>] sock_release+0x4f/0xcf
[<ffffffff80059d4c>] sock_close+0x2c/0x30
[<ffffffff800133c9>] __fput+0xac/0x197
[<ffffffff800252bc>] filp_close+0x59/0x61
[<ffffffff8001eff6>] sys_close+0x85/0xc7
[<ffffffff800622dd>] tracesys+0xd5/0xe0
So, in brief:
* a received packet for socket in TCP_CLOSE_WAIT state triggers
tcp_reset() which clears inet_sk(sk)->num and put socket into
TCP_CLOSE state
* an attempt to write to that socket forces inet_autobind() to get a
new port (but the write itself fails with -EPIPE)
* tcp_close() called for socket in TCP_CLOSE state sends an active
reset via socket with newly allocated port
This adds an additional check in tcp_close() for already closed
sockets. We do not want to send anything to closed sockets.
Signed-off-by: Konstantin Khorenko <khorenko@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-24 22:54:58 -06:00
|
|
|
/* If socket has been already reset (e.g. in tcp_reset()) - kill it. */
|
|
|
|
if (sk->sk_state == TCP_CLOSE)
|
|
|
|
goto adjudge_to_death;
|
|
|
|
|
2007-04-28 22:21:46 -06:00
|
|
|
/* As outlined in RFC 2525, section 2.17, we send a RST here because
|
|
|
|
* data was lost. To witness the awful effects of the old behavior of
|
|
|
|
* always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk
|
|
|
|
* GET in an FTP client, suspend the process, wait for the client to
|
|
|
|
* advertise a zero window, then kill -9 the FTP client, wheee...
|
|
|
|
* Note: timeout is always zero in such a case.
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
2012-04-18 21:40:39 -06:00
|
|
|
if (unlikely(tcp_sk(sk)->repair)) {
|
|
|
|
sk->sk_prot->disconnect(sk, 0);
|
|
|
|
} else if (data_was_unread) {
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Unread data was tossed, zap the connection. */
|
2008-07-16 21:31:39 -06:00
|
|
|
NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
|
2005-04-16 16:20:36 -06:00
|
|
|
tcp_set_state(sk, TCP_CLOSE);
|
2009-09-03 00:45:45 -06:00
|
|
|
tcp_send_active_reset(sk, sk->sk_allocation);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
|
|
|
|
/* Check zero linger _after_ checking for unread data. */
|
|
|
|
sk->sk_prot->disconnect(sk, 0);
|
2008-07-16 21:31:39 -06:00
|
|
|
NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else if (tcp_close_state(sk)) {
|
|
|
|
/* We FIN if the application ate all the data before
|
|
|
|
* zapping the connection.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* RED-PEN. Formally speaking, we have broken TCP state
|
|
|
|
* machine. State transitions:
|
|
|
|
*
|
|
|
|
* TCP_ESTABLISHED -> TCP_FIN_WAIT1
|
|
|
|
* TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible)
|
|
|
|
* TCP_CLOSE_WAIT -> TCP_LAST_ACK
|
|
|
|
*
|
|
|
|
* are legal only when FIN has been sent (i.e. in window),
|
|
|
|
* rather than queued out of window. Purists blame.
|
|
|
|
*
|
|
|
|
* F.e. "RFC state" is ESTABLISHED,
|
|
|
|
* if Linux state is FIN-WAIT-1, but FIN is still not sent.
|
|
|
|
*
|
|
|
|
* The visible declinations are that sometimes
|
|
|
|
* we enter time-wait state, when it is not required really
|
|
|
|
* (harmless), do not send active resets, when they are
|
|
|
|
* required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when
|
|
|
|
* they look as CLOSING or LAST_ACK for Linux)
|
|
|
|
* Probably, I missed some more holelets.
|
|
|
|
* --ANK
|
2012-08-31 06:29:12 -06:00
|
|
|
* XXX (TFO) - To start off we don't support SYN+ACK+FIN
|
|
|
|
* in a single packet! (May consider it later but will
|
|
|
|
* probably need API support or TCP_CORK SYN-ACK until
|
|
|
|
* data is written and socket is closed.)
|
2005-04-16 16:20:36 -06:00
|
|
|
*/
|
|
|
|
tcp_send_fin(sk);
|
|
|
|
}
|
|
|
|
|
|
|
|
sk_stream_wait_close(sk, timeout);
|
|
|
|
|
|
|
|
adjudge_to_death:
|
2006-05-04 00:31:35 -06:00
|
|
|
state = sk->sk_state;
|
|
|
|
sock_hold(sk);
|
|
|
|
sock_orphan(sk);
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* It is the last release_sock in its life. It will remove backlog. */
|
|
|
|
release_sock(sk);
|
|
|
|
|
|
|
|
|
|
|
|
/* Now socket is owned by kernel and we acquire BH lock
|
|
|
|
to finish close. No need to check for user refs.
|
|
|
|
*/
|
|
|
|
local_bh_disable();
|
|
|
|
bh_lock_sock(sk);
|
2008-07-25 22:43:18 -06:00
|
|
|
WARN_ON(sock_owned_by_user(sk));
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-12-30 00:04:08 -07:00
|
|
|
percpu_counter_inc(sk->sk_prot->orphan_count);
|
|
|
|
|
2006-05-04 00:31:35 -06:00
|
|
|
/* Have we already been destroyed by a softirq or backlog? */
|
|
|
|
if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
|
|
|
|
goto out;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* This is a (useful) BSD violating of the RFC. There is a
|
|
|
|
* problem with TCP as specified in that the other end could
|
|
|
|
* keep a socket open forever with no application left this end.
|
2014-02-09 15:30:32 -07:00
|
|
|
* We use a 1 minute timeout (about the same as BSD) then kill
|
2005-04-16 16:20:36 -06:00
|
|
|
* our end. If they send after that then tough - BUT: long enough
|
|
|
|
* that we won't make the old 4*rto = almost no time - whoops
|
|
|
|
* reset mistake.
|
|
|
|
*
|
|
|
|
* Nope, it was not mistake. It is really desired behaviour
|
|
|
|
* f.e. on http servers, when such sockets are useless, but
|
|
|
|
* consume significant resources. Let's do it with special
|
|
|
|
* linger2 option. --ANK
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (sk->sk_state == TCP_FIN_WAIT2) {
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
if (tp->linger2 < 0) {
|
|
|
|
tcp_set_state(sk, TCP_CLOSE);
|
|
|
|
tcp_send_active_reset(sk, GFP_ATOMIC);
|
2008-07-16 21:31:16 -06:00
|
|
|
NET_INC_STATS_BH(sock_net(sk),
|
|
|
|
LINUX_MIB_TCPABORTONLINGER);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
2005-08-09 21:10:42 -06:00
|
|
|
const int tmo = tcp_fin_time(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (tmo > TCP_TIMEWAIT_LEN) {
|
2006-07-31 23:32:09 -06:00
|
|
|
inet_csk_reset_keepalive_timer(sk,
|
|
|
|
tmo - TCP_TIMEWAIT_LEN);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
|
|
|
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (sk->sk_state != TCP_CLOSE) {
|
2007-12-31 01:11:19 -07:00
|
|
|
sk_mem_reclaim(sk);
|
2012-01-30 15:16:06 -07:00
|
|
|
if (tcp_check_oom(sk, 0)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
tcp_set_state(sk, TCP_CLOSE);
|
|
|
|
tcp_send_active_reset(sk, GFP_ATOMIC);
|
2008-07-16 21:31:16 -06:00
|
|
|
NET_INC_STATS_BH(sock_net(sk),
|
|
|
|
LINUX_MIB_TCPABORTONMEMORY);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-08-31 06:29:12 -06:00
|
|
|
if (sk->sk_state == TCP_CLOSE) {
|
|
|
|
struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
|
|
|
|
/* We could get here with a non-NULL req if the socket is
|
|
|
|
* aborted (e.g., closed with unread data) before 3WHS
|
|
|
|
* finishes.
|
|
|
|
*/
|
|
|
|
if (req != NULL)
|
|
|
|
reqsk_fastopen_remove(sk, req, false);
|
2005-08-09 21:11:41 -06:00
|
|
|
inet_csk_destroy_sock(sk);
|
2012-08-31 06:29:12 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Otherwise, socket is reprieved until protocol close. */
|
|
|
|
|
|
|
|
out:
|
|
|
|
bh_unlock_sock(sk);
|
|
|
|
local_bh_enable();
|
|
|
|
sock_put(sk);
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_close);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* These states need RST on ABORT according to RFC793 */
|
|
|
|
|
2012-05-16 17:15:34 -06:00
|
|
|
static inline bool tcp_need_reset(int state)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
return (1 << state) &
|
|
|
|
(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 |
|
|
|
|
TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
|
|
|
|
}
|
|
|
|
|
|
|
|
int tcp_disconnect(struct sock *sk, int flags)
|
|
|
|
{
|
|
|
|
struct inet_sock *inet = inet_sk(sk);
|
2005-08-09 21:10:42 -06:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
int err = 0;
|
|
|
|
int old_state = sk->sk_state;
|
|
|
|
|
|
|
|
if (old_state != TCP_CLOSE)
|
|
|
|
tcp_set_state(sk, TCP_CLOSE);
|
|
|
|
|
|
|
|
/* ABORT function of RFC793 */
|
|
|
|
if (old_state == TCP_LISTEN) {
|
2005-08-09 21:11:41 -06:00
|
|
|
inet_csk_listen_stop(sk);
|
2012-04-18 21:40:39 -06:00
|
|
|
} else if (unlikely(tp->repair)) {
|
|
|
|
sk->sk_err = ECONNABORTED;
|
2005-04-16 16:20:36 -06:00
|
|
|
} else if (tcp_need_reset(old_state) ||
|
|
|
|
(tp->snd_nxt != tp->write_seq &&
|
|
|
|
(1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
|
2005-11-10 18:13:47 -07:00
|
|
|
/* The last check adjusts for discrepancy of Linux wrt. RFC
|
2005-04-16 16:20:36 -06:00
|
|
|
* states
|
|
|
|
*/
|
|
|
|
tcp_send_active_reset(sk, gfp_any());
|
|
|
|
sk->sk_err = ECONNRESET;
|
|
|
|
} else if (old_state == TCP_SYN_SENT)
|
|
|
|
sk->sk_err = ECONNRESET;
|
|
|
|
|
|
|
|
tcp_clear_xmit_timers(sk);
|
|
|
|
__skb_queue_purge(&sk->sk_receive_queue);
|
2007-03-07 13:12:44 -07:00
|
|
|
tcp_write_queue_purge(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
__skb_queue_purge(&tp->out_of_order_queue);
|
2006-05-23 19:05:53 -06:00
|
|
|
#ifdef CONFIG_NET_DMA
|
|
|
|
__skb_queue_purge(&sk->sk_async_wait_queue);
|
|
|
|
#endif
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-10-15 00:30:45 -06:00
|
|
|
inet->inet_dport = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
|
|
|
|
inet_reset_saddr(sk);
|
|
|
|
|
|
|
|
sk->sk_shutdown = 0;
|
|
|
|
sock_reset_flag(sk, SOCK_DONE);
|
2014-02-26 15:02:48 -07:00
|
|
|
tp->srtt_us = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
if ((tp->write_seq += tp->max_window + 2) == 0)
|
|
|
|
tp->write_seq = 1;
|
2005-08-09 21:10:42 -06:00
|
|
|
icsk->icsk_backoff = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
tp->snd_cwnd = 2;
|
2005-08-10 01:03:31 -06:00
|
|
|
icsk->icsk_probes_out = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
tp->packets_out = 0;
|
2009-09-15 02:30:10 -06:00
|
|
|
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
|
2005-04-16 16:20:36 -06:00
|
|
|
tp->snd_cwnd_cnt = 0;
|
2009-11-30 13:53:30 -07:00
|
|
|
tp->window_clamp = 0;
|
2005-08-10 01:03:31 -06:00
|
|
|
tcp_set_ca_state(sk, TCP_CA_Open);
|
2005-04-16 16:20:36 -06:00
|
|
|
tcp_clear_retrans(tp);
|
2005-08-09 21:10:42 -06:00
|
|
|
inet_csk_delack_init(sk);
|
2007-03-07 13:12:44 -07:00
|
|
|
tcp_init_send_head(sk);
|
2007-05-03 18:32:28 -06:00
|
|
|
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
|
2005-04-16 16:20:36 -06:00
|
|
|
__sk_dst_reset(sk);
|
|
|
|
|
2009-10-15 00:30:45 -06:00
|
|
|
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
sk->sk_error_report(sk);
|
|
|
|
return err;
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_disconnect);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-09-18 08:19:23 -06:00
|
|
|
void tcp_sock_destruct(struct sock *sk)
|
|
|
|
{
|
|
|
|
inet_sock_destruct(sk);
|
|
|
|
|
|
|
|
kfree(inet_csk(sk)->icsk_accept_queue.fastopenq);
|
|
|
|
}
|
|
|
|
|
2012-05-16 17:15:34 -06:00
|
|
|
static inline bool tcp_can_repair_sock(const struct sock *sk)
|
2012-04-18 21:40:39 -06:00
|
|
|
{
|
net: Allow userns root to control ipv4
Allow an unpriviled user who has created a user namespace, and then
created a network namespace to effectively use the new network
namespace, by reducing capable(CAP_NET_ADMIN) and
capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns,
CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls.
Settings that merely control a single network device are allowed.
Either the network device is a logical network device where
restrictions make no difference or the network device is hardware NIC
that has been explicity moved from the initial network namespace.
In general policy and network stack state changes are allowed
while resource control is left unchanged.
Allow creating raw sockets.
Allow the SIOCSARP ioctl to control the arp cache.
Allow the SIOCSIFFLAG ioctl to allow setting network device flags.
Allow the SIOCSIFADDR ioctl to allow setting a netdevice ipv4 address.
Allow the SIOCSIFBRDADDR ioctl to allow setting a netdevice ipv4 broadcast address.
Allow the SIOCSIFDSTADDR ioctl to allow setting a netdevice ipv4 destination address.
Allow the SIOCSIFNETMASK ioctl to allow setting a netdevice ipv4 netmask.
Allow the SIOCADDRT and SIOCDELRT ioctls to allow adding and deleting ipv4 routes.
Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting gre tunnels.
Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting ipip tunnels.
Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL and SIOCDELTUNNEL ioctls for
adding, changing and deleting ipsec virtual tunnel interfaces.
Allow setting the MRT_INIT, MRT_DONE, MRT_ADD_VIF, MRT_DEL_VIF, MRT_ADD_MFC,
MRT_DEL_MFC, MRT_ASSERT, MRT_PIM, MRT_TABLE socket options on multicast routing
sockets.
Allow setting and receiving IPOPT_CIPSO, IP_OPT_SEC, IP_OPT_SID and
arbitrary ip options.
Allow setting IP_SEC_POLICY/IP_XFRM_POLICY ipv4 socket option.
Allow setting the IP_TRANSPARENT ipv4 socket option.
Allow setting the TCP_REPAIR socket option.
Allow setting the TCP_CONGESTION socket option.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-15 20:03:05 -07:00
|
|
|
return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
|
2012-04-18 21:40:39 -06:00
|
|
|
((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
|
|
|
|
}
|
|
|
|
|
2012-04-25 17:43:04 -06:00
|
|
|
static int tcp_repair_options_est(struct tcp_sock *tp,
|
|
|
|
struct tcp_repair_opt __user *optbuf, unsigned int len)
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
{
|
2012-04-25 17:43:04 -06:00
|
|
|
struct tcp_repair_opt opt;
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
|
2012-04-25 17:43:04 -06:00
|
|
|
while (len >= sizeof(opt)) {
|
|
|
|
if (copy_from_user(&opt, optbuf, sizeof(opt)))
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
optbuf++;
|
2012-04-25 17:43:04 -06:00
|
|
|
len -= sizeof(opt);
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
|
2012-04-25 17:43:04 -06:00
|
|
|
switch (opt.opt_code) {
|
|
|
|
case TCPOPT_MSS:
|
|
|
|
tp->rx_opt.mss_clamp = opt.opt_val;
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
break;
|
2012-04-25 17:43:04 -06:00
|
|
|
case TCPOPT_WINDOW:
|
2012-09-19 03:40:00 -06:00
|
|
|
{
|
|
|
|
u16 snd_wscale = opt.opt_val & 0xFFFF;
|
|
|
|
u16 rcv_wscale = opt.opt_val >> 16;
|
|
|
|
|
|
|
|
if (snd_wscale > 14 || rcv_wscale > 14)
|
|
|
|
return -EFBIG;
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
|
2012-09-19 03:40:00 -06:00
|
|
|
tp->rx_opt.snd_wscale = snd_wscale;
|
|
|
|
tp->rx_opt.rcv_wscale = rcv_wscale;
|
|
|
|
tp->rx_opt.wscale_ok = 1;
|
|
|
|
}
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
break;
|
|
|
|
case TCPOPT_SACK_PERM:
|
2012-04-25 17:43:04 -06:00
|
|
|
if (opt.opt_val != 0)
|
|
|
|
return -EINVAL;
|
|
|
|
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
tp->rx_opt.sack_ok |= TCP_SACK_SEEN;
|
|
|
|
if (sysctl_tcp_fack)
|
|
|
|
tcp_enable_fack(tp);
|
|
|
|
break;
|
|
|
|
case TCPOPT_TIMESTAMP:
|
2012-04-25 17:43:04 -06:00
|
|
|
if (opt.opt_val != 0)
|
|
|
|
return -EINVAL;
|
|
|
|
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
tp->rx_opt.tstamp_ok = 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* Socket option code for TCP.
|
|
|
|
*/
|
2006-03-20 23:45:21 -07:00
|
|
|
static int do_tcp_setsockopt(struct sock *sk, int level,
|
2009-09-30 17:12:20 -06:00
|
|
|
int optname, char __user *optval, unsigned int optlen)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
2005-08-09 21:10:42 -06:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
int val;
|
|
|
|
int err = 0;
|
|
|
|
|
2009-12-02 11:19:30 -07:00
|
|
|
/* These are data/string values, all the others are ints */
|
|
|
|
switch (optname) {
|
|
|
|
case TCP_CONGESTION: {
|
2005-06-23 21:37:36 -06:00
|
|
|
char name[TCP_CA_NAME_MAX];
|
|
|
|
|
|
|
|
if (optlen < 1)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
val = strncpy_from_user(name, optval,
|
2009-10-01 16:02:20 -06:00
|
|
|
min_t(long, TCP_CA_NAME_MAX-1, optlen));
|
2005-06-23 21:37:36 -06:00
|
|
|
if (val < 0)
|
|
|
|
return -EFAULT;
|
|
|
|
name[val] = 0;
|
|
|
|
|
|
|
|
lock_sock(sk);
|
2005-08-10 01:03:31 -06:00
|
|
|
err = tcp_set_congestion_control(sk, name);
|
2005-06-23 21:37:36 -06:00
|
|
|
release_sock(sk);
|
|
|
|
return err;
|
|
|
|
}
|
2009-12-02 11:19:30 -07:00
|
|
|
default:
|
|
|
|
/* fallthru */
|
|
|
|
break;
|
2010-05-14 04:58:26 -06:00
|
|
|
}
|
2005-06-23 21:37:36 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (optlen < sizeof(int))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (get_user(val, (int __user *)optval))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
lock_sock(sk);
|
|
|
|
|
|
|
|
switch (optname) {
|
|
|
|
case TCP_MAXSEG:
|
|
|
|
/* Values greater than interface MTU won't take effect. However
|
|
|
|
* at the point when this call is done we typically don't yet
|
|
|
|
* know which interface is going to be used */
|
2010-11-24 12:47:22 -07:00
|
|
|
if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
|
2005-04-16 16:20:36 -06:00
|
|
|
err = -EINVAL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
tp->rx_opt.user_mss = val;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_NODELAY:
|
|
|
|
if (val) {
|
|
|
|
/* TCP_NODELAY is weaker than TCP_CORK, so that
|
|
|
|
* this option on corked socket is remembered, but
|
|
|
|
* it is not activated until cork is cleared.
|
|
|
|
*
|
|
|
|
* However, when TCP_NODELAY is set we make
|
|
|
|
* an explicit push, which overrides even TCP_CORK
|
|
|
|
* for currently queued segments.
|
|
|
|
*/
|
|
|
|
tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
tcp_push_pending_frames(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
|
|
|
tp->nonagle &= ~TCP_NAGLE_OFF;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
2010-02-17 19:47:01 -07:00
|
|
|
case TCP_THIN_LINEAR_TIMEOUTS:
|
|
|
|
if (val < 0 || val > 1)
|
|
|
|
err = -EINVAL;
|
|
|
|
else
|
|
|
|
tp->thin_lto = val;
|
|
|
|
break;
|
|
|
|
|
2010-02-17 21:48:19 -07:00
|
|
|
case TCP_THIN_DUPACK:
|
|
|
|
if (val < 0 || val > 1)
|
|
|
|
err = -EINVAL;
|
2013-09-05 11:43:34 -06:00
|
|
|
else {
|
2010-02-17 21:48:19 -07:00
|
|
|
tp->thin_dupack = val;
|
2012-05-02 07:30:03 -06:00
|
|
|
if (tp->thin_dupack)
|
|
|
|
tcp_disable_early_retrans(tp);
|
2013-09-05 11:43:34 -06:00
|
|
|
}
|
2010-02-17 21:48:19 -07:00
|
|
|
break;
|
|
|
|
|
2012-04-18 21:40:39 -06:00
|
|
|
case TCP_REPAIR:
|
|
|
|
if (!tcp_can_repair_sock(sk))
|
|
|
|
err = -EPERM;
|
|
|
|
else if (val == 1) {
|
|
|
|
tp->repair = 1;
|
|
|
|
sk->sk_reuse = SK_FORCE_REUSE;
|
|
|
|
tp->repair_queue = TCP_NO_QUEUE;
|
|
|
|
} else if (val == 0) {
|
|
|
|
tp->repair = 0;
|
|
|
|
sk->sk_reuse = SK_NO_REUSE;
|
|
|
|
tcp_send_window_probe(sk);
|
|
|
|
} else
|
|
|
|
err = -EINVAL;
|
|
|
|
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_REPAIR_QUEUE:
|
|
|
|
if (!tp->repair)
|
|
|
|
err = -EPERM;
|
|
|
|
else if (val < TCP_QUEUES_NR)
|
|
|
|
tp->repair_queue = val;
|
|
|
|
else
|
|
|
|
err = -EINVAL;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_QUEUE_SEQ:
|
|
|
|
if (sk->sk_state != TCP_CLOSE)
|
|
|
|
err = -EPERM;
|
|
|
|
else if (tp->repair_queue == TCP_SEND_QUEUE)
|
|
|
|
tp->write_seq = val;
|
|
|
|
else if (tp->repair_queue == TCP_RECV_QUEUE)
|
|
|
|
tp->rcv_nxt = val;
|
|
|
|
else
|
|
|
|
err = -EINVAL;
|
|
|
|
break;
|
|
|
|
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
case TCP_REPAIR_OPTIONS:
|
|
|
|
if (!tp->repair)
|
|
|
|
err = -EINVAL;
|
|
|
|
else if (sk->sk_state == TCP_ESTABLISHED)
|
2012-04-25 17:43:04 -06:00
|
|
|
err = tcp_repair_options_est(tp,
|
|
|
|
(struct tcp_repair_opt __user *)optval,
|
|
|
|
optlen);
|
tcp: Repair connection-time negotiated parameters
There are options, which are set up on a socket while performing
TCP handshake. Need to resurrect them on a socket while repairing.
A new sockoption accepts a buffer and parses it. The buffer should
be CODE:VALUE sequence of bytes, where CODE is standard option
code and VALUE is the respective value.
Only 4 options should be handled on repaired socket.
To read 3 out of 4 of these options the TCP_INFO sockoption can be
used. An ability to get the last one (the mss_clamp) was added by
the previous patch.
Now the restore. Three of these options -- timestamp_ok, mss_clamp
and snd_wscale -- are just restored on a coket.
The sack_ok flags has 2 issues. First, whether or not to do sacks
at all. This flag is just read and set back. No other sack info is
saved or restored, since according to the standart and the code
dropping all sack-ed segments is OK, the sender will resubmit them
again, so after the repair we will probably experience a pause in
connection. Next, the fack bit. It's just set back on a socket if
the respective sysctl is set. No collected stats about packets flow
is preserved. As far as I see (plz, correct me if I'm wrong) the
fack-based congestion algorithm survives dropping all of the stats
and repairs itself eventually, probably losing the performance for
that period.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-18 21:41:57 -06:00
|
|
|
else
|
|
|
|
err = -EPERM;
|
|
|
|
break;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
case TCP_CORK:
|
|
|
|
/* When set indicates to always queue non-full frames.
|
|
|
|
* Later the user clears this option and we transmit
|
|
|
|
* any pending partial frames in the queue. This is
|
|
|
|
* meant to be used alongside sendfile() to get properly
|
|
|
|
* filled frames when the user (for example) must write
|
|
|
|
* out headers with a write() call first and then use
|
|
|
|
* sendfile to send out the data parts.
|
|
|
|
*
|
|
|
|
* TCP_CORK can be set together with TCP_NODELAY and it is
|
|
|
|
* stronger than TCP_NODELAY.
|
|
|
|
*/
|
|
|
|
if (val) {
|
|
|
|
tp->nonagle |= TCP_NAGLE_CORK;
|
|
|
|
} else {
|
|
|
|
tp->nonagle &= ~TCP_NAGLE_CORK;
|
|
|
|
if (tp->nonagle&TCP_NAGLE_OFF)
|
|
|
|
tp->nonagle |= TCP_NAGLE_PUSH;
|
[TCP]: Sed magic converts func(sk, tp, ...) -> func(sk, ...)
This is (mostly) automated change using magic:
sed -e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e '/struct sock \*sk/ N' -e '/struct sock \*sk/ N'
-e 's|struct sock \*sk,[\n\t ]*struct tcp_sock \*tp\([^{]*\n{\n\)|
struct sock \*sk\1\tstruct tcp_sock *tp = tcp_sk(sk);\n|g'
-e 's|struct sock \*sk, struct tcp_sock \*tp|
struct sock \*sk|g' -e 's|sk, tp\([^-]\)|sk\1|g'
Fixed four unused variable (tp) warnings that were introduced.
In addition, manually added newlines after local variables and
tweaked function arguments positioning.
$ gcc --version
gcc (GCC) 4.1.1 20060525 (Red Hat 4.1.1-1)
...
$ codiff -fV built-in.o.old built-in.o.new
net/ipv4/route.c:
rt_cache_flush | +14
1 function changed, 14 bytes added
net/ipv4/tcp.c:
tcp_setsockopt | -5
tcp_sendpage | -25
tcp_sendmsg | -16
3 functions changed, 46 bytes removed
net/ipv4/tcp_input.c:
tcp_try_undo_recovery | +3
tcp_try_undo_dsack | +2
tcp_mark_head_lost | -12
tcp_ack | -15
tcp_event_data_recv | -32
tcp_rcv_state_process | -10
tcp_rcv_established | +1
7 functions changed, 6 bytes added, 69 bytes removed, diff: -63
net/ipv4/tcp_output.c:
update_send_head | -9
tcp_transmit_skb | +19
tcp_cwnd_validate | +1
tcp_write_wakeup | -17
__tcp_push_pending_frames | -25
tcp_push_one | -8
tcp_send_fin | -4
7 functions changed, 20 bytes added, 63 bytes removed, diff: -43
built-in.o.new:
18 functions changed, 40 bytes added, 178 bytes removed, diff: -138
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-20 23:18:02 -06:00
|
|
|
tcp_push_pending_frames(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_KEEPIDLE:
|
|
|
|
if (val < 1 || val > MAX_TCP_KEEPIDLE)
|
|
|
|
err = -EINVAL;
|
|
|
|
else {
|
|
|
|
tp->keepalive_time = val * HZ;
|
|
|
|
if (sock_flag(sk, SOCK_KEEPOPEN) &&
|
|
|
|
!((1 << sk->sk_state) &
|
|
|
|
(TCPF_CLOSE | TCPF_LISTEN))) {
|
2010-04-26 12:33:27 -06:00
|
|
|
u32 elapsed = keepalive_time_elapsed(tp);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (tp->keepalive_time > elapsed)
|
|
|
|
elapsed = tp->keepalive_time - elapsed;
|
|
|
|
else
|
|
|
|
elapsed = 0;
|
2005-08-09 21:10:42 -06:00
|
|
|
inet_csk_reset_keepalive_timer(sk, elapsed);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case TCP_KEEPINTVL:
|
|
|
|
if (val < 1 || val > MAX_TCP_KEEPINTVL)
|
|
|
|
err = -EINVAL;
|
|
|
|
else
|
|
|
|
tp->keepalive_intvl = val * HZ;
|
|
|
|
break;
|
|
|
|
case TCP_KEEPCNT:
|
|
|
|
if (val < 1 || val > MAX_TCP_KEEPCNT)
|
|
|
|
err = -EINVAL;
|
|
|
|
else
|
|
|
|
tp->keepalive_probes = val;
|
|
|
|
break;
|
|
|
|
case TCP_SYNCNT:
|
|
|
|
if (val < 1 || val > MAX_TCP_SYNCNT)
|
|
|
|
err = -EINVAL;
|
|
|
|
else
|
2005-08-09 21:10:42 -06:00
|
|
|
icsk->icsk_syn_retries = val;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_LINGER2:
|
|
|
|
if (val < 0)
|
|
|
|
tp->linger2 = -1;
|
|
|
|
else if (val > sysctl_tcp_fin_timeout / HZ)
|
|
|
|
tp->linger2 = 0;
|
|
|
|
else
|
|
|
|
tp->linger2 = val * HZ;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_DEFER_ACCEPT:
|
2009-10-19 04:10:40 -06:00
|
|
|
/* Translate value in seconds to number of retransmits */
|
|
|
|
icsk->icsk_accept_queue.rskq_defer_accept =
|
|
|
|
secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
|
|
|
|
TCP_RTO_MAX / HZ);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_WINDOW_CLAMP:
|
|
|
|
if (!val) {
|
|
|
|
if (sk->sk_state != TCP_CLOSE) {
|
|
|
|
err = -EINVAL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
tp->window_clamp = 0;
|
|
|
|
} else
|
|
|
|
tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
|
|
|
|
SOCK_MIN_RCVBUF / 2 : val;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_QUICKACK:
|
|
|
|
if (!val) {
|
2005-08-09 21:10:42 -06:00
|
|
|
icsk->icsk_ack.pingpong = 1;
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
2005-08-09 21:10:42 -06:00
|
|
|
icsk->icsk_ack.pingpong = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
if ((1 << sk->sk_state) &
|
|
|
|
(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
|
2005-08-09 21:10:42 -06:00
|
|
|
inet_csk_ack_scheduled(sk)) {
|
|
|
|
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
|
2006-05-23 19:00:16 -06:00
|
|
|
tcp_cleanup_rbuf(sk, 1);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!(val & 1))
|
2005-08-09 21:10:42 -06:00
|
|
|
icsk->icsk_ack.pingpong = 1;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
2006-11-14 20:07:45 -07:00
|
|
|
#ifdef CONFIG_TCP_MD5SIG
|
|
|
|
case TCP_MD5SIG:
|
|
|
|
/* Read the IP->Key mappings from userspace */
|
|
|
|
err = tp->af_specific->md5_parse(sk, optval, optlen);
|
|
|
|
break;
|
|
|
|
#endif
|
tcp: Add TCP_USER_TIMEOUT socket option.
This patch provides a "user timeout" support as described in RFC793. The
socket option is also needed for the the local half of RFC5482 "TCP User
Timeout Option".
TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int,
when > 0, to specify the maximum amount of time in ms that transmitted
data may remain unacknowledged before TCP will forcefully close the
corresponding connection and return ETIMEDOUT to the application. If
0 is given, TCP will continue to use the system default.
Increasing the user timeouts allows a TCP connection to survive extended
periods without end-to-end connectivity. Decreasing the user timeouts
allows applications to "fail fast" if so desired. Otherwise it may take
upto 20 minutes with the current system defaults in a normal WAN
environment.
The socket option can be made during any state of a TCP connection, but
is only effective during the synchronized states of a connection
(ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK).
Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option,
TCP_USER_TIMEOUT will overtake keepalive to determine when to close a
connection due to keepalive failure.
The option does not change in anyway when TCP retransmits a packet, nor
when a keepalive probe will be sent.
This option, like many others, will be inherited by an acceptor from its
listener.
Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-27 13:13:28 -06:00
|
|
|
case TCP_USER_TIMEOUT:
|
|
|
|
/* Cap the max timeout in ms TCP will retry/retrans
|
|
|
|
* before giving up and aborting (ETIMEDOUT) a connection.
|
|
|
|
*/
|
2012-07-26 16:52:21 -06:00
|
|
|
if (val < 0)
|
|
|
|
err = -EINVAL;
|
|
|
|
else
|
|
|
|
icsk->icsk_user_timeout = msecs_to_jiffies(val);
|
tcp: Add TCP_USER_TIMEOUT socket option.
This patch provides a "user timeout" support as described in RFC793. The
socket option is also needed for the the local half of RFC5482 "TCP User
Timeout Option".
TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int,
when > 0, to specify the maximum amount of time in ms that transmitted
data may remain unacknowledged before TCP will forcefully close the
corresponding connection and return ETIMEDOUT to the application. If
0 is given, TCP will continue to use the system default.
Increasing the user timeouts allows a TCP connection to survive extended
periods without end-to-end connectivity. Decreasing the user timeouts
allows applications to "fail fast" if so desired. Otherwise it may take
upto 20 minutes with the current system defaults in a normal WAN
environment.
The socket option can be made during any state of a TCP connection, but
is only effective during the synchronized states of a connection
(ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK).
Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option,
TCP_USER_TIMEOUT will overtake keepalive to determine when to close a
connection due to keepalive failure.
The option does not change in anyway when TCP retransmits a packet, nor
when a keepalive probe will be sent.
This option, like many others, will be inherited by an acceptor from its
listener.
Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-27 13:13:28 -06:00
|
|
|
break;
|
2012-08-31 06:29:12 -06:00
|
|
|
|
|
|
|
case TCP_FASTOPEN:
|
|
|
|
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
|
|
|
|
TCPF_LISTEN)))
|
|
|
|
err = fastopen_init_queue(sk, val);
|
|
|
|
else
|
|
|
|
err = -EINVAL;
|
|
|
|
break;
|
2013-02-10 22:50:18 -07:00
|
|
|
case TCP_TIMESTAMP:
|
|
|
|
if (!tp->repair)
|
|
|
|
err = -EPERM;
|
|
|
|
else
|
|
|
|
tp->tsoffset = val - tcp_time_stamp;
|
|
|
|
break;
|
tcp: TCP_NOTSENT_LOWAT socket option
Idea of this patch is to add optional limitation of number of
unsent bytes in TCP sockets, to reduce usage of kernel memory.
TCP receiver might announce a big window, and TCP sender autotuning
might allow a large amount of bytes in write queue, but this has little
performance impact if a large part of this buffering is wasted :
Write queue needs to be large only to deal with large BDP, not
necessarily to cope with scheduling delays (incoming ACKS make room
for the application to queue more bytes)
For most workloads, using a value of 128 KB or less is OK to give
applications enough time to react to POLLOUT events in time
(or being awaken in a blocking sendmsg())
This patch adds two ways to set the limit :
1) Per socket option TCP_NOTSENT_LOWAT
2) A sysctl (/proc/sys/net/ipv4/tcp_notsent_lowat) for sockets
not using TCP_NOTSENT_LOWAT socket option (or setting a zero value)
Default value being UINT_MAX (0xFFFFFFFF), meaning this has no effect.
This changes poll()/select()/epoll() to report POLLOUT
only if number of unsent bytes is below tp->nosent_lowat
Note this might increase number of sendmsg()/sendfile() calls
when using non blocking sockets,
and increase number of context switches for blocking sockets.
Note this is not related to SO_SNDLOWAT (as SO_SNDLOWAT is
defined as :
Specify the minimum number of bytes in the buffer until
the socket layer will pass the data to the protocol)
Tested:
netperf sessions, and watching /proc/net/protocols "memory" column for TCP
With 200 concurrent netperf -t TCP_STREAM sessions, amount of kernel memory
used by TCP buffers shrinks by ~55 % (20567 pages instead of 45458)
lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols
TCPv6 1880 2 45458 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y
TCP 1696 508 45458 no 208 yes kernel y y y y y y y y y y y y y n y y y y y
lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols
TCPv6 1880 2 20567 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y
TCP 1696 508 20567 no 208 yes kernel y y y y y y y y y y y y y n y y y y y
Using 128KB has no bad effect on the throughput or cpu usage
of a single flow, although there is an increase of context switches.
A bonus is that we hold socket lock for a shorter amount
of time and should improve latencies of ACK processing.
lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3
OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf.
Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service
Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand
Size Size Size (sec) Util Util Util Util Demand Demand Units
Final Final % Method % Method
1651584 6291456 16384 20.00 17447.90 10^6bits/s 3.13 S -1.00 U 0.353 -1.000 usec/KB
Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3':
412,514 context-switches
200.034645535 seconds time elapsed
lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3
OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf.
Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service
Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand
Size Size Size (sec) Util Util Util Util Demand Demand Units
Final Final % Method % Method
1593240 6291456 16384 20.00 17321.16 10^6bits/s 3.35 S -1.00 U 0.381 -1.000 usec/KB
Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3':
2,675,818 context-switches
200.029651391 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-By: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-22 21:27:07 -06:00
|
|
|
case TCP_NOTSENT_LOWAT:
|
|
|
|
tp->notsent_lowat = val;
|
|
|
|
sk->sk_write_space(sk);
|
|
|
|
break;
|
2005-04-16 16:20:36 -06:00
|
|
|
default:
|
|
|
|
err = -ENOPROTOOPT;
|
|
|
|
break;
|
2007-04-20 18:09:22 -06:00
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
release_sock(sk);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2006-03-20 23:45:21 -07:00
|
|
|
int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
|
2009-09-30 17:12:20 -06:00
|
|
|
unsigned int optlen)
|
2006-03-20 23:45:21 -07:00
|
|
|
{
|
2011-10-21 03:22:42 -06:00
|
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
2006-03-20 23:45:21 -07:00
|
|
|
|
|
|
|
if (level != SOL_TCP)
|
|
|
|
return icsk->icsk_af_ops->setsockopt(sk, level, optname,
|
|
|
|
optval, optlen);
|
|
|
|
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_setsockopt);
|
2006-03-20 23:45:21 -07:00
|
|
|
|
|
|
|
#ifdef CONFIG_COMPAT
|
2006-03-20 23:48:35 -07:00
|
|
|
int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
|
2009-09-30 17:12:20 -06:00
|
|
|
char __user *optval, unsigned int optlen)
|
2006-03-20 23:45:21 -07:00
|
|
|
{
|
2006-03-20 23:46:16 -07:00
|
|
|
if (level != SOL_TCP)
|
|
|
|
return inet_csk_compat_setsockopt(sk, level, optname,
|
|
|
|
optval, optlen);
|
2006-03-20 23:45:21 -07:00
|
|
|
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
|
|
|
|
}
|
2006-03-20 23:48:35 -07:00
|
|
|
EXPORT_SYMBOL(compat_tcp_setsockopt);
|
2006-03-20 23:45:21 -07:00
|
|
|
#endif
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Return information about state of tcp endpoint in API format. */
|
2011-10-21 03:22:42 -06:00
|
|
|
void tcp_get_info(const struct sock *sk, struct tcp_info *info)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2011-10-21 03:22:42 -06:00
|
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
2005-08-09 21:10:42 -06:00
|
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
u32 now = tcp_time_stamp;
|
|
|
|
|
|
|
|
memset(info, 0, sizeof(*info));
|
|
|
|
|
|
|
|
info->tcpi_state = sk->sk_state;
|
2005-08-10 01:03:31 -06:00
|
|
|
info->tcpi_ca_state = icsk->icsk_ca_state;
|
2005-08-09 21:10:42 -06:00
|
|
|
info->tcpi_retransmits = icsk->icsk_retransmits;
|
2005-08-10 01:03:31 -06:00
|
|
|
info->tcpi_probes = icsk->icsk_probes_out;
|
2005-08-09 21:10:42 -06:00
|
|
|
info->tcpi_backoff = icsk->icsk_backoff;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (tp->rx_opt.tstamp_ok)
|
|
|
|
info->tcpi_options |= TCPI_OPT_TIMESTAMPS;
|
2007-08-09 06:14:46 -06:00
|
|
|
if (tcp_is_sack(tp))
|
2005-04-16 16:20:36 -06:00
|
|
|
info->tcpi_options |= TCPI_OPT_SACK;
|
|
|
|
if (tp->rx_opt.wscale_ok) {
|
|
|
|
info->tcpi_options |= TCPI_OPT_WSCALE;
|
|
|
|
info->tcpi_snd_wscale = tp->rx_opt.snd_wscale;
|
|
|
|
info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
|
2007-02-09 07:24:47 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2011-10-03 12:01:21 -06:00
|
|
|
if (tp->ecn_flags & TCP_ECN_OK)
|
2005-04-16 16:20:36 -06:00
|
|
|
info->tcpi_options |= TCPI_OPT_ECN;
|
2011-10-03 12:01:21 -06:00
|
|
|
if (tp->ecn_flags & TCP_ECN_SEEN)
|
|
|
|
info->tcpi_options |= TCPI_OPT_ECN_SEEN;
|
2012-10-19 09:14:44 -06:00
|
|
|
if (tp->syn_data_acked)
|
|
|
|
info->tcpi_options |= TCPI_OPT_SYN_DATA;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2005-08-09 21:10:42 -06:00
|
|
|
info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
|
|
|
|
info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
|
2005-07-05 16:24:38 -06:00
|
|
|
info->tcpi_snd_mss = tp->mss_cache;
|
2005-08-09 21:10:42 -06:00
|
|
|
info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2007-09-18 14:26:31 -06:00
|
|
|
if (sk->sk_state == TCP_LISTEN) {
|
|
|
|
info->tcpi_unacked = sk->sk_ack_backlog;
|
|
|
|
info->tcpi_sacked = sk->sk_max_ack_backlog;
|
|
|
|
} else {
|
|
|
|
info->tcpi_unacked = tp->packets_out;
|
|
|
|
info->tcpi_sacked = tp->sacked_out;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
info->tcpi_lost = tp->lost_out;
|
|
|
|
info->tcpi_retrans = tp->retrans_out;
|
|
|
|
info->tcpi_fackets = tp->fackets_out;
|
|
|
|
|
|
|
|
info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime);
|
2005-08-09 21:10:42 -06:00
|
|
|
info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime);
|
2005-04-16 16:20:36 -06:00
|
|
|
info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp);
|
|
|
|
|
2005-12-14 00:26:10 -07:00
|
|
|
info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
|
2005-04-16 16:20:36 -06:00
|
|
|
info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
|
2014-02-26 15:02:48 -07:00
|
|
|
info->tcpi_rtt = tp->srtt_us >> 3;
|
|
|
|
info->tcpi_rttvar = tp->mdev_us >> 2;
|
2005-04-16 16:20:36 -06:00
|
|
|
info->tcpi_snd_ssthresh = tp->snd_ssthresh;
|
|
|
|
info->tcpi_snd_cwnd = tp->snd_cwnd;
|
|
|
|
info->tcpi_advmss = tp->advmss;
|
|
|
|
info->tcpi_reordering = tp->reordering;
|
|
|
|
|
|
|
|
info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
|
|
|
|
info->tcpi_rcv_space = tp->rcvq_space.space;
|
|
|
|
|
|
|
|
info->tcpi_total_retrans = tp->total_retrans;
|
tcp: add pacing_rate information into tcp_info
Add two new fields to struct tcp_info, to report sk_pacing_rate
and sk_max_pacing_rate to monitoring applications, as ss from iproute2.
User exported fields are 64bit, even if kernel is currently using 32bit
fields.
lpaa5:~# ss -i
..
skmem:(r0,rb357120,t0,tb2097152,f1584,w1980880,o0,bl0) ts sack cubic
wscale:6,6 rto:400 rtt:0.875/0.75 mss:1448 cwnd:1 ssthresh:12 send
13.2Mbps pacing_rate 3336.2Mbps unacked:15 retrans:1/5448 lost:15
rcv_space:29200
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-13 15:27:40 -07:00
|
|
|
|
|
|
|
info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
|
|
|
|
sk->sk_pacing_rate : ~0ULL;
|
|
|
|
info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
|
|
|
|
sk->sk_max_pacing_rate : ~0ULL;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_get_info);
|
|
|
|
|
2006-03-20 23:45:21 -07:00
|
|
|
static int do_tcp_getsockopt(struct sock *sk, int level,
|
|
|
|
int optname, char __user *optval, int __user *optlen)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2005-08-09 21:11:56 -06:00
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
2005-04-16 16:20:36 -06:00
|
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
int val, len;
|
|
|
|
|
|
|
|
if (get_user(len, optlen))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
len = min_t(unsigned int, len, sizeof(int));
|
|
|
|
|
|
|
|
if (len < 0)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
switch (optname) {
|
|
|
|
case TCP_MAXSEG:
|
2005-07-05 16:24:38 -06:00
|
|
|
val = tp->mss_cache;
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
|
|
|
|
val = tp->rx_opt.user_mss;
|
2012-04-18 21:41:32 -06:00
|
|
|
if (tp->repair)
|
|
|
|
val = tp->rx_opt.mss_clamp;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case TCP_NODELAY:
|
|
|
|
val = !!(tp->nonagle&TCP_NAGLE_OFF);
|
|
|
|
break;
|
|
|
|
case TCP_CORK:
|
|
|
|
val = !!(tp->nonagle&TCP_NAGLE_CORK);
|
|
|
|
break;
|
|
|
|
case TCP_KEEPIDLE:
|
2009-08-29 00:48:54 -06:00
|
|
|
val = keepalive_time_when(tp) / HZ;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case TCP_KEEPINTVL:
|
2009-08-29 00:48:54 -06:00
|
|
|
val = keepalive_intvl_when(tp) / HZ;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case TCP_KEEPCNT:
|
2009-08-29 00:48:54 -06:00
|
|
|
val = keepalive_probes(tp);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case TCP_SYNCNT:
|
2005-08-09 21:11:56 -06:00
|
|
|
val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case TCP_LINGER2:
|
|
|
|
val = tp->linger2;
|
|
|
|
if (val >= 0)
|
|
|
|
val = (val ? : sysctl_tcp_fin_timeout) / HZ;
|
|
|
|
break;
|
|
|
|
case TCP_DEFER_ACCEPT:
|
2009-10-19 04:10:40 -06:00
|
|
|
val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
|
|
|
|
TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case TCP_WINDOW_CLAMP:
|
|
|
|
val = tp->window_clamp;
|
|
|
|
break;
|
|
|
|
case TCP_INFO: {
|
|
|
|
struct tcp_info info;
|
|
|
|
|
|
|
|
if (get_user(len, optlen))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
tcp_get_info(sk, &info);
|
|
|
|
|
|
|
|
len = min_t(unsigned int, len, sizeof(info));
|
|
|
|
if (put_user(len, optlen))
|
|
|
|
return -EFAULT;
|
|
|
|
if (copy_to_user(optval, &info, len))
|
|
|
|
return -EFAULT;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
case TCP_QUICKACK:
|
2005-08-09 21:11:56 -06:00
|
|
|
val = !icsk->icsk_ack.pingpong;
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
2005-06-23 21:37:36 -06:00
|
|
|
|
|
|
|
case TCP_CONGESTION:
|
|
|
|
if (get_user(len, optlen))
|
|
|
|
return -EFAULT;
|
|
|
|
len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
|
|
|
|
if (put_user(len, optlen))
|
|
|
|
return -EFAULT;
|
2005-08-10 01:03:31 -06:00
|
|
|
if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
|
2005-06-23 21:37:36 -06:00
|
|
|
return -EFAULT;
|
|
|
|
return 0;
|
2009-12-02 11:19:30 -07:00
|
|
|
|
2010-07-30 07:49:35 -06:00
|
|
|
case TCP_THIN_LINEAR_TIMEOUTS:
|
|
|
|
val = tp->thin_lto;
|
|
|
|
break;
|
|
|
|
case TCP_THIN_DUPACK:
|
|
|
|
val = tp->thin_dupack;
|
|
|
|
break;
|
tcp: Add TCP_USER_TIMEOUT socket option.
This patch provides a "user timeout" support as described in RFC793. The
socket option is also needed for the the local half of RFC5482 "TCP User
Timeout Option".
TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int,
when > 0, to specify the maximum amount of time in ms that transmitted
data may remain unacknowledged before TCP will forcefully close the
corresponding connection and return ETIMEDOUT to the application. If
0 is given, TCP will continue to use the system default.
Increasing the user timeouts allows a TCP connection to survive extended
periods without end-to-end connectivity. Decreasing the user timeouts
allows applications to "fail fast" if so desired. Otherwise it may take
upto 20 minutes with the current system defaults in a normal WAN
environment.
The socket option can be made during any state of a TCP connection, but
is only effective during the synchronized states of a connection
(ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK).
Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option,
TCP_USER_TIMEOUT will overtake keepalive to determine when to close a
connection due to keepalive failure.
The option does not change in anyway when TCP retransmits a packet, nor
when a keepalive probe will be sent.
This option, like many others, will be inherited by an acceptor from its
listener.
Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-27 13:13:28 -06:00
|
|
|
|
2012-04-18 21:40:39 -06:00
|
|
|
case TCP_REPAIR:
|
|
|
|
val = tp->repair;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_REPAIR_QUEUE:
|
|
|
|
if (tp->repair)
|
|
|
|
val = tp->repair_queue;
|
|
|
|
else
|
|
|
|
return -EINVAL;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case TCP_QUEUE_SEQ:
|
|
|
|
if (tp->repair_queue == TCP_SEND_QUEUE)
|
|
|
|
val = tp->write_seq;
|
|
|
|
else if (tp->repair_queue == TCP_RECV_QUEUE)
|
|
|
|
val = tp->rcv_nxt;
|
|
|
|
else
|
|
|
|
return -EINVAL;
|
|
|
|
break;
|
|
|
|
|
tcp: Add TCP_USER_TIMEOUT socket option.
This patch provides a "user timeout" support as described in RFC793. The
socket option is also needed for the the local half of RFC5482 "TCP User
Timeout Option".
TCP_USER_TIMEOUT is a TCP level socket option that takes an unsigned int,
when > 0, to specify the maximum amount of time in ms that transmitted
data may remain unacknowledged before TCP will forcefully close the
corresponding connection and return ETIMEDOUT to the application. If
0 is given, TCP will continue to use the system default.
Increasing the user timeouts allows a TCP connection to survive extended
periods without end-to-end connectivity. Decreasing the user timeouts
allows applications to "fail fast" if so desired. Otherwise it may take
upto 20 minutes with the current system defaults in a normal WAN
environment.
The socket option can be made during any state of a TCP connection, but
is only effective during the synchronized states of a connection
(ESTABLISHED, FIN-WAIT-1, FIN-WAIT-2, CLOSE-WAIT, CLOSING, or LAST-ACK).
Moreover, when used with the TCP keepalive (SO_KEEPALIVE) option,
TCP_USER_TIMEOUT will overtake keepalive to determine when to close a
connection due to keepalive failure.
The option does not change in anyway when TCP retransmits a packet, nor
when a keepalive probe will be sent.
This option, like many others, will be inherited by an acceptor from its
listener.
Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-08-27 13:13:28 -06:00
|
|
|
case TCP_USER_TIMEOUT:
|
|
|
|
val = jiffies_to_msecs(icsk->icsk_user_timeout);
|
|
|
|
break;
|
2014-04-16 10:25:01 -06:00
|
|
|
|
|
|
|
case TCP_FASTOPEN:
|
|
|
|
if (icsk->icsk_accept_queue.fastopenq != NULL)
|
|
|
|
val = icsk->icsk_accept_queue.fastopenq->max_qlen;
|
|
|
|
else
|
|
|
|
val = 0;
|
|
|
|
break;
|
|
|
|
|
2013-02-10 22:50:18 -07:00
|
|
|
case TCP_TIMESTAMP:
|
|
|
|
val = tcp_time_stamp + tp->tsoffset;
|
|
|
|
break;
|
tcp: TCP_NOTSENT_LOWAT socket option
Idea of this patch is to add optional limitation of number of
unsent bytes in TCP sockets, to reduce usage of kernel memory.
TCP receiver might announce a big window, and TCP sender autotuning
might allow a large amount of bytes in write queue, but this has little
performance impact if a large part of this buffering is wasted :
Write queue needs to be large only to deal with large BDP, not
necessarily to cope with scheduling delays (incoming ACKS make room
for the application to queue more bytes)
For most workloads, using a value of 128 KB or less is OK to give
applications enough time to react to POLLOUT events in time
(or being awaken in a blocking sendmsg())
This patch adds two ways to set the limit :
1) Per socket option TCP_NOTSENT_LOWAT
2) A sysctl (/proc/sys/net/ipv4/tcp_notsent_lowat) for sockets
not using TCP_NOTSENT_LOWAT socket option (or setting a zero value)
Default value being UINT_MAX (0xFFFFFFFF), meaning this has no effect.
This changes poll()/select()/epoll() to report POLLOUT
only if number of unsent bytes is below tp->nosent_lowat
Note this might increase number of sendmsg()/sendfile() calls
when using non blocking sockets,
and increase number of context switches for blocking sockets.
Note this is not related to SO_SNDLOWAT (as SO_SNDLOWAT is
defined as :
Specify the minimum number of bytes in the buffer until
the socket layer will pass the data to the protocol)
Tested:
netperf sessions, and watching /proc/net/protocols "memory" column for TCP
With 200 concurrent netperf -t TCP_STREAM sessions, amount of kernel memory
used by TCP buffers shrinks by ~55 % (20567 pages instead of 45458)
lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols
TCPv6 1880 2 45458 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y
TCP 1696 508 45458 no 208 yes kernel y y y y y y y y y y y y y n y y y y y
lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols
TCPv6 1880 2 20567 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y
TCP 1696 508 20567 no 208 yes kernel y y y y y y y y y y y y y n y y y y y
Using 128KB has no bad effect on the throughput or cpu usage
of a single flow, although there is an increase of context switches.
A bonus is that we hold socket lock for a shorter amount
of time and should improve latencies of ACK processing.
lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3
OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf.
Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service
Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand
Size Size Size (sec) Util Util Util Util Demand Demand Units
Final Final % Method % Method
1651584 6291456 16384 20.00 17447.90 10^6bits/s 3.13 S -1.00 U 0.353 -1.000 usec/KB
Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3':
412,514 context-switches
200.034645535 seconds time elapsed
lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat
lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3
OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf.
Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service
Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand
Size Size Size (sec) Util Util Util Util Demand Demand Units
Final Final % Method % Method
1593240 6291456 16384 20.00 17321.16 10^6bits/s 3.35 S -1.00 U 0.381 -1.000 usec/KB
Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3':
2,675,818 context-switches
200.029651391 seconds time elapsed
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-By: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-22 21:27:07 -06:00
|
|
|
case TCP_NOTSENT_LOWAT:
|
|
|
|
val = tp->notsent_lowat;
|
|
|
|
break;
|
2005-04-16 16:20:36 -06:00
|
|
|
default:
|
|
|
|
return -ENOPROTOOPT;
|
2007-04-20 18:09:22 -06:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (put_user(len, optlen))
|
|
|
|
return -EFAULT;
|
|
|
|
if (copy_to_user(optval, &val, len))
|
|
|
|
return -EFAULT;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-03-20 23:45:21 -07:00
|
|
|
int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
|
|
|
|
int __user *optlen)
|
|
|
|
{
|
|
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
|
|
|
|
if (level != SOL_TCP)
|
|
|
|
return icsk->icsk_af_ops->getsockopt(sk, level, optname,
|
|
|
|
optval, optlen);
|
|
|
|
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
|
|
|
|
}
|
2010-07-09 15:22:10 -06:00
|
|
|
EXPORT_SYMBOL(tcp_getsockopt);
|
2006-03-20 23:45:21 -07:00
|
|
|
|
|
|
|
#ifdef CONFIG_COMPAT
|
2006-03-20 23:48:35 -07:00
|
|
|
int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
|
|
|
|
char __user *optval, int __user *optlen)
|
2006-03-20 23:45:21 -07:00
|
|
|
{
|
2006-03-20 23:46:16 -07:00
|
|
|
if (level != SOL_TCP)
|
|
|
|
return inet_csk_compat_getsockopt(sk, level, optname,
|
|
|
|
optval, optlen);
|
2006-03-20 23:45:21 -07:00
|
|
|
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
|
|
|
|
}
|
2006-03-20 23:48:35 -07:00
|
|
|
EXPORT_SYMBOL(compat_tcp_getsockopt);
|
2006-03-20 23:45:21 -07:00
|
|
|
#endif
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-11-14 20:07:45 -07:00
|
|
|
#ifdef CONFIG_TCP_MD5SIG
|
2013-05-20 00:52:26 -06:00
|
|
|
static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
|
|
|
|
static DEFINE_MUTEX(tcp_md5sig_mutex);
|
2006-11-14 20:07:45 -07:00
|
|
|
|
2011-09-12 14:28:37 -06:00
|
|
|
static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
|
2006-11-14 20:07:45 -07:00
|
|
|
{
|
|
|
|
int cpu;
|
2011-09-12 14:28:37 -06:00
|
|
|
|
2006-11-14 20:07:45 -07:00
|
|
|
for_each_possible_cpu(cpu) {
|
2011-09-12 14:28:37 -06:00
|
|
|
struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu);
|
|
|
|
|
|
|
|
if (p->md5_desc.tfm)
|
|
|
|
crypto_free_hash(p->md5_desc.tfm);
|
2006-11-14 20:07:45 -07:00
|
|
|
}
|
|
|
|
free_percpu(pool);
|
|
|
|
}
|
|
|
|
|
2013-05-20 00:52:26 -06:00
|
|
|
static void __tcp_alloc_md5sig_pool(void)
|
2006-11-14 20:07:45 -07:00
|
|
|
{
|
|
|
|
int cpu;
|
2011-09-12 14:28:37 -06:00
|
|
|
struct tcp_md5sig_pool __percpu *pool;
|
2006-11-14 20:07:45 -07:00
|
|
|
|
2011-09-12 14:28:37 -06:00
|
|
|
pool = alloc_percpu(struct tcp_md5sig_pool);
|
2006-11-14 20:07:45 -07:00
|
|
|
if (!pool)
|
2013-05-20 00:52:26 -06:00
|
|
|
return;
|
2006-11-14 20:07:45 -07:00
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
struct crypto_hash *hash;
|
|
|
|
|
|
|
|
hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
|
2013-01-21 23:32:49 -07:00
|
|
|
if (IS_ERR_OR_NULL(hash))
|
2006-11-14 20:07:45 -07:00
|
|
|
goto out_free;
|
|
|
|
|
2011-09-12 14:28:37 -06:00
|
|
|
per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
|
2006-11-14 20:07:45 -07:00
|
|
|
}
|
2013-05-20 00:52:26 -06:00
|
|
|
/* before setting tcp_md5sig_pool, we must commit all writes
|
|
|
|
* to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool()
|
|
|
|
*/
|
|
|
|
smp_wmb();
|
|
|
|
tcp_md5sig_pool = pool;
|
|
|
|
return;
|
2006-11-14 20:07:45 -07:00
|
|
|
out_free:
|
|
|
|
__tcp_free_md5sig_pool(pool);
|
|
|
|
}
|
|
|
|
|
2013-05-20 00:52:26 -06:00
|
|
|
bool tcp_alloc_md5sig_pool(void)
|
2006-11-14 20:07:45 -07:00
|
|
|
{
|
2013-05-20 00:52:26 -06:00
|
|
|
if (unlikely(!tcp_md5sig_pool)) {
|
|
|
|
mutex_lock(&tcp_md5sig_mutex);
|
|
|
|
|
|
|
|
if (!tcp_md5sig_pool)
|
|
|
|
__tcp_alloc_md5sig_pool();
|
|
|
|
|
|
|
|
mutex_unlock(&tcp_md5sig_mutex);
|
2006-11-14 20:07:45 -07:00
|
|
|
}
|
2013-05-20 00:52:26 -06:00
|
|
|
return tcp_md5sig_pool != NULL;
|
2006-11-14 20:07:45 -07:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
|
|
|
|
|
2010-05-16 01:34:04 -06:00
|
|
|
|
|
|
|
/**
|
|
|
|
* tcp_get_md5sig_pool - get md5sig_pool for this user
|
|
|
|
*
|
|
|
|
* We use percpu structure, so if we succeed, we exit with preemption
|
|
|
|
* and BH disabled, to make sure another thread or softirq handling
|
|
|
|
* wont try to get same context.
|
|
|
|
*/
|
|
|
|
struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
|
2006-11-14 20:07:45 -07:00
|
|
|
{
|
2011-09-12 14:28:37 -06:00
|
|
|
struct tcp_md5sig_pool __percpu *p;
|
2010-05-16 01:34:04 -06:00
|
|
|
|
|
|
|
local_bh_disable();
|
2013-05-20 00:52:26 -06:00
|
|
|
p = ACCESS_ONCE(tcp_md5sig_pool);
|
2010-05-16 01:34:04 -06:00
|
|
|
if (p)
|
2013-05-20 00:52:26 -06:00
|
|
|
return __this_cpu_ptr(p);
|
2006-11-14 20:07:45 -07:00
|
|
|
|
2010-05-16 01:34:04 -06:00
|
|
|
local_bh_enable();
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_get_md5sig_pool);
|
2006-11-14 20:07:45 -07:00
|
|
|
|
2008-07-19 01:01:42 -06:00
|
|
|
int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
|
2011-10-23 23:52:35 -06:00
|
|
|
const struct tcphdr *th)
|
2008-07-19 01:01:42 -06:00
|
|
|
{
|
|
|
|
struct scatterlist sg;
|
2011-10-23 23:52:35 -06:00
|
|
|
struct tcphdr hdr;
|
2008-07-19 01:01:42 -06:00
|
|
|
int err;
|
|
|
|
|
2011-10-23 23:52:35 -06:00
|
|
|
/* We are not allowed to change tcphdr, make a local copy */
|
|
|
|
memcpy(&hdr, th, sizeof(hdr));
|
|
|
|
hdr.check = 0;
|
|
|
|
|
2008-07-19 01:01:42 -06:00
|
|
|
/* options aren't included in the hash */
|
2011-10-23 23:52:35 -06:00
|
|
|
sg_init_one(&sg, &hdr, sizeof(hdr));
|
|
|
|
err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(hdr));
|
2008-07-19 01:01:42 -06:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_md5_hash_header);
|
|
|
|
|
|
|
|
int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
|
2011-10-21 03:22:42 -06:00
|
|
|
const struct sk_buff *skb, unsigned int header_len)
|
2008-07-19 01:01:42 -06:00
|
|
|
{
|
|
|
|
struct scatterlist sg;
|
|
|
|
const struct tcphdr *tp = tcp_hdr(skb);
|
|
|
|
struct hash_desc *desc = &hp->md5_desc;
|
2012-04-14 23:58:06 -06:00
|
|
|
unsigned int i;
|
|
|
|
const unsigned int head_data_len = skb_headlen(skb) > header_len ?
|
|
|
|
skb_headlen(skb) - header_len : 0;
|
2008-07-19 01:01:42 -06:00
|
|
|
const struct skb_shared_info *shi = skb_shinfo(skb);
|
2010-05-17 14:40:51 -06:00
|
|
|
struct sk_buff *frag_iter;
|
2008-07-19 01:01:42 -06:00
|
|
|
|
|
|
|
sg_init_table(&sg, 1);
|
|
|
|
|
|
|
|
sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len);
|
|
|
|
if (crypto_hash_update(desc, &sg, head_data_len))
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
for (i = 0; i < shi->nr_frags; ++i) {
|
|
|
|
const struct skb_frag_struct *f = &shi->frags[i];
|
2013-05-13 15:25:52 -06:00
|
|
|
unsigned int offset = f->page_offset;
|
|
|
|
struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT);
|
|
|
|
|
|
|
|
sg_set_page(&sg, page, skb_frag_size(f),
|
|
|
|
offset_in_page(offset));
|
2011-10-18 15:00:24 -06:00
|
|
|
if (crypto_hash_update(desc, &sg, skb_frag_size(f)))
|
2008-07-19 01:01:42 -06:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2010-05-17 14:40:51 -06:00
|
|
|
skb_walk_frags(skb, frag_iter)
|
|
|
|
if (tcp_md5_hash_skb_data(hp, frag_iter, 0))
|
|
|
|
return 1;
|
|
|
|
|
2008-07-19 01:01:42 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_md5_hash_skb_data);
|
|
|
|
|
2011-10-21 03:22:42 -06:00
|
|
|
int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
|
2008-07-19 01:01:42 -06:00
|
|
|
{
|
|
|
|
struct scatterlist sg;
|
|
|
|
|
|
|
|
sg_init_one(&sg, key->key, key->keylen);
|
|
|
|
return crypto_hash_update(&hp->md5_desc, &sg, key->keylen);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(tcp_md5_hash_key);
|
|
|
|
|
2006-11-14 20:07:45 -07:00
|
|
|
#endif
|
|
|
|
|
2007-04-20 18:11:46 -06:00
|
|
|
void tcp_done(struct sock *sk)
|
|
|
|
{
|
2012-08-31 06:29:12 -06:00
|
|
|
struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
|
|
|
|
|
2008-11-03 01:24:34 -07:00
|
|
|
if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
|
2008-07-16 21:22:25 -06:00
|
|
|
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
|
2007-04-20 18:11:46 -06:00
|
|
|
|
|
|
|
tcp_set_state(sk, TCP_CLOSE);
|
|
|
|
tcp_clear_xmit_timers(sk);
|
2012-08-31 06:29:12 -06:00
|
|
|
if (req != NULL)
|
|
|
|
reqsk_fastopen_remove(sk, req, false);
|
2007-04-20 18:11:46 -06:00
|
|
|
|
|
|
|
sk->sk_shutdown = SHUTDOWN_MASK;
|
|
|
|
|
|
|
|
if (!sock_flag(sk, SOCK_DEAD))
|
|
|
|
sk->sk_state_change(sk);
|
|
|
|
else
|
|
|
|
inet_csk_destroy_sock(sk);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(tcp_done);
|
|
|
|
|
2005-06-23 21:37:36 -06:00
|
|
|
extern struct tcp_congestion_ops tcp_reno;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
static __initdata unsigned long thash_entries;
|
|
|
|
static int __init set_thash_entries(char *str)
|
|
|
|
{
|
2012-05-19 08:13:18 -06:00
|
|
|
ssize_t ret;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!str)
|
|
|
|
return 0;
|
2012-05-19 08:13:18 -06:00
|
|
|
|
|
|
|
ret = kstrtoul(str, 0, &thash_entries);
|
|
|
|
if (ret)
|
|
|
|
return 0;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
__setup("thash_entries=", set_thash_entries);
|
|
|
|
|
2013-10-19 17:25:36 -06:00
|
|
|
static void tcp_init_mem(void)
|
2012-01-29 18:20:17 -07:00
|
|
|
{
|
|
|
|
unsigned long limit = nr_free_buffer_pages() / 8;
|
|
|
|
limit = max(limit, 128UL);
|
2013-10-19 17:25:36 -06:00
|
|
|
sysctl_tcp_mem[0] = limit / 4 * 3;
|
|
|
|
sysctl_tcp_mem[1] = limit;
|
|
|
|
sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
|
2012-01-29 18:20:17 -07:00
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
void __init tcp_init(void)
|
|
|
|
{
|
|
|
|
struct sk_buff *skb = NULL;
|
2011-07-07 01:27:05 -06:00
|
|
|
unsigned long limit;
|
2012-05-01 20:28:41 -06:00
|
|
|
int max_rshare, max_wshare, cnt;
|
2012-02-08 13:39:07 -07:00
|
|
|
unsigned int i;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2007-12-11 03:12:04 -07:00
|
|
|
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-11-25 22:16:35 -07:00
|
|
|
percpu_counter_init(&tcp_sockets_allocated, 0);
|
2008-11-25 22:17:14 -07:00
|
|
|
percpu_counter_init(&tcp_orphan_count, 0);
|
2005-08-09 21:07:35 -06:00
|
|
|
tcp_hashinfo.bind_bucket_cachep =
|
|
|
|
kmem_cache_create("tcp_bind_bucket",
|
|
|
|
sizeof(struct inet_bind_bucket), 0,
|
2007-07-19 19:11:58 -06:00
|
|
|
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* Size and allocate the main established and bind bucket
|
|
|
|
* hash tables.
|
|
|
|
*
|
|
|
|
* The methodology is similar to that of the buffer cache.
|
|
|
|
*/
|
2005-08-09 21:07:35 -06:00
|
|
|
tcp_hashinfo.ehash =
|
2005-04-16 16:20:36 -06:00
|
|
|
alloc_large_system_hash("TCP established",
|
2005-08-09 20:59:44 -06:00
|
|
|
sizeof(struct inet_ehash_bucket),
|
2005-04-16 16:20:36 -06:00
|
|
|
thash_entries,
|
2012-11-30 03:08:52 -07:00
|
|
|
17, /* one slot per 128 KB of memory */
|
2006-11-07 00:10:51 -07:00
|
|
|
0,
|
2005-04-16 16:20:36 -06:00
|
|
|
NULL,
|
2009-10-08 18:16:19 -06:00
|
|
|
&tcp_hashinfo.ehash_mask,
|
2012-05-23 07:33:35 -06:00
|
|
|
0,
|
2007-10-30 01:59:25 -06:00
|
|
|
thash_entries ? 0 : 512 * 1024);
|
tcp/dccp: remove twchain
TCP listener refactoring, part 3 :
Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.
Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.
As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.
If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.
[ INET_TW_MATCH() is no longer needed ]
I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()
This way, SYN_RECV pseudo sockets will be supported the same.
A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].
Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()
Before patch :
dmesg | grep "TCP established"
TCP established hash table entries: 524288 (order: 11, 8388608 bytes)
After patch :
TCP established hash table entries: 524288 (order: 10, 4194304 bytes)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 01:22:02 -06:00
|
|
|
for (i = 0; i <= tcp_hashinfo.ehash_mask; i++)
|
2008-11-16 20:40:17 -07:00
|
|
|
INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
|
tcp/dccp: remove twchain
TCP listener refactoring, part 3 :
Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.
Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.
As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.
If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.
[ INET_TW_MATCH() is no longer needed ]
I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()
This way, SYN_RECV pseudo sockets will be supported the same.
A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].
Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()
Before patch :
dmesg | grep "TCP established"
TCP established hash table entries: 524288 (order: 11, 8388608 bytes)
After patch :
TCP established hash table entries: 524288 (order: 10, 4194304 bytes)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 01:22:02 -06:00
|
|
|
|
2007-11-07 03:40:20 -07:00
|
|
|
if (inet_ehash_locks_alloc(&tcp_hashinfo))
|
|
|
|
panic("TCP: failed to alloc ehash_locks");
|
2005-08-09 21:07:35 -06:00
|
|
|
tcp_hashinfo.bhash =
|
2005-04-16 16:20:36 -06:00
|
|
|
alloc_large_system_hash("TCP bind",
|
2005-08-09 20:59:44 -06:00
|
|
|
sizeof(struct inet_bind_hashbucket),
|
2009-10-08 18:16:19 -06:00
|
|
|
tcp_hashinfo.ehash_mask + 1,
|
2012-11-30 03:08:52 -07:00
|
|
|
17, /* one slot per 128 KB of memory */
|
2006-11-07 00:10:51 -07:00
|
|
|
0,
|
2005-08-09 21:07:35 -06:00
|
|
|
&tcp_hashinfo.bhash_size,
|
2005-04-16 16:20:36 -06:00
|
|
|
NULL,
|
2012-05-23 07:33:35 -06:00
|
|
|
0,
|
2005-04-16 16:20:36 -06:00
|
|
|
64 * 1024);
|
2012-02-08 13:39:07 -07:00
|
|
|
tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
|
2005-08-09 21:07:35 -06:00
|
|
|
for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
|
|
|
|
spin_lock_init(&tcp_hashinfo.bhash[i].lock);
|
|
|
|
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2010-08-26 00:02:17 -06:00
|
|
|
|
|
|
|
cnt = tcp_hashinfo.ehash_mask + 1;
|
|
|
|
|
|
|
|
tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
|
|
|
|
sysctl_tcp_max_orphans = cnt / 2;
|
|
|
|
sysctl_max_syn_backlog = max(128, cnt / 256);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2013-10-19 17:25:36 -06:00
|
|
|
tcp_init_mem();
|
2012-02-01 17:07:00 -07:00
|
|
|
/* Set per-socket limits to no more than 1/128 the pressure threshold */
|
2012-04-09 18:56:42 -06:00
|
|
|
limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
|
2012-05-01 20:28:41 -06:00
|
|
|
max_wshare = min(4UL*1024*1024, limit);
|
|
|
|
max_rshare = min(6UL*1024*1024, limit);
|
2006-03-25 02:34:07 -07:00
|
|
|
|
2007-12-31 01:11:19 -07:00
|
|
|
sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
|
2006-03-25 02:34:07 -07:00
|
|
|
sysctl_tcp_wmem[1] = 16*1024;
|
2012-05-01 20:28:41 -06:00
|
|
|
sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
|
2006-03-25 02:34:07 -07:00
|
|
|
|
2007-12-31 01:11:19 -07:00
|
|
|
sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
|
2006-03-25 02:34:07 -07:00
|
|
|
sysctl_tcp_rmem[1] = 87380;
|
2012-05-01 20:28:41 -06:00
|
|
|
sysctl_tcp_rmem[2] = max(87380, max_rshare);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2012-03-12 01:03:32 -06:00
|
|
|
pr_info("Hash tables configured (established %u bind %u)\n",
|
2012-03-11 12:36:11 -06:00
|
|
|
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
|
2005-06-23 13:19:55 -06:00
|
|
|
|
2012-07-10 01:49:14 -06:00
|
|
|
tcp_metrics_init();
|
|
|
|
|
2005-06-23 13:19:55 -06:00
|
|
|
tcp_register_congestion_control(&tcp_reno);
|
2009-12-02 11:12:09 -07:00
|
|
|
|
tcp: TCP Small Queues
This introduce TSQ (TCP Small Queues)
TSQ goal is to reduce number of TCP packets in xmit queues (qdisc &
device queues), to reduce RTT and cwnd bias, part of the bufferbloat
problem.
sk->sk_wmem_alloc not allowed to grow above a given limit,
allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a
given time.
TSO packets are sized/capped to half the limit, so that we have two
TSO packets in flight, allowing better bandwidth use.
As a side effect, setting the limit to 40000 automatically reduces the
standard gso max limit (65536) to 40000/2 : It can help to reduce
latencies of high prio packets, having smaller TSO packets.
This means we divert sock_wfree() to a tcp_wfree() handler, to
queue/send following frames when skb_orphan() [2] is called for the
already queued skbs.
Results on my dev machines (tg3/ixgbe nics) are really impressive,
using standard pfifo_fast, and with or without TSO/GSO.
Without reduction of nominal bandwidth, we have reduction of buffering
per bulk sender :
< 1ms on Gbit (instead of 50ms with TSO)
< 8ms on 100Mbit (instead of 132 ms)
I no longer have 4 MBytes backlogged in qdisc by a single netperf
session, and both side socket autotuning no longer use 4 Mbytes.
As skb destructor cannot restart xmit itself ( as qdisc lock might be
taken at this point ), we delegate the work to a tasklet. We use one
tasklest per cpu for performance reasons.
If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag.
This flag is tested in a new protocol method called from release_sock(),
to eventually send new segments.
[1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable
[2] skb_orphan() is usually called at TX completion time,
but some drivers call it in their start_xmit() handler.
These drivers should at least use BQL, or else a single TCP
session can still fill the whole NIC TX ring, since TSQ will
have no effect.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Dave Taht <dave.taht@bufferbloat.net>
Cc: Tom Herbert <therbert@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-10 23:50:31 -06:00
|
|
|
tcp_tasklet_init();
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|