Commit Graph

69 Commits

Author SHA1 Message Date
Richard Scheffenegger
d7ca3f780d Reduce default TCP delayed ACK timeout to 40ms.
Reviewed by:	kbowling, tuexen
Approved by:	tuexen (mentor)
MFC after:	2 weeks
Sponsored by:	NetApp, Inc.
Differential Revision:	https://reviews.freebsd.org/D23281
2020-04-16 15:59:23 +00:00
Randall Stewart
481be5de9d White space cleanup -- remove trailing tab's or spaces
from any line.

Sponsored by:	Netflix Inc.
2020-02-12 13:31:36 +00:00
Bjoern A. Zeeb
334fc5822b vnet: virtualise more network stack sysctls.
Virtualise tcp_always_keepalive, TCP and UDP log_in_vain.  All three are
set in the netoptions startup script, which we would love to run for VNETs
as well [1].

While virtualising the log_in_vain sysctls seems pointles at first for as
long as the kernel message buffer is not virtualised, it at least allows
an administrator to debug the base system or an individual jail if needed
without turning the logging on for all jails running on a system.

PR:		243193 [1]
MFC after:	2 weeks
2020-01-08 23:30:26 +00:00
Michael Tuexen
0999766ddf Add sysctl variable net.inet.tcp.rexmit_initial for setting RTO.Initial
used by TCP.

Reviewed by:		rrs@, 0mp@
Sponsored by:		Netflix, Inc.
Differential Revision:	https://reviews.freebsd.org/D19355
2019-03-23 21:36:59 +00:00
Michael Tuexen
3b853844d7 Reduce the TCP initial retransmission timeout from 3 seconds to
1 second as allowed by RFC 6298.

Reviewed by:		kbowling@, Richard Scheffenegger
Sponsored by:		Netflix, Inc.
Differential Revision:	https://reviews.freebsd.org/D18941
2019-02-20 18:03:43 +00:00
Michael Tuexen
c6dcb64b18 Use exponential backoff for retransmitting SYN segments as specified
in the TCP RFCs.

Reviewed by:		rrs@, Richard Scheffenegger
Sponsored by:		Netflix, Inc.
Differential Revision:	https://reviews.freebsd.org/D18974
2019-02-20 17:56:38 +00:00
Matt Macy
6573d7580b epoch(9): allow preemptible epochs to compose
- Add tracker argument to preemptible epochs
- Inline epoch read path in kernel and tied modules
- Change in_epoch to take an epoch as argument
- Simplify tfb_tcp_do_segment to not take a ti_locked argument,
  there's no longer any benefit to dropping the pcbinfo lock
  and trying to do so just adds an error prone branchfest to
  these functions
- Remove cases of same function recursion on the epoch as
  recursing is no longer free.
- Remove the the TAILQ_ENTRY and epoch_section from struct
  thread as the tracker field is now stack or heap allocated
  as appropriate.

Tested by: pho and Limelight Networks
Reviewed by: kbowling at llnw dot com
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D16066
2018-07-04 02:47:16 +00:00
Randall Stewart
89e560f441 This commit brings in a new refactored TCP stack called Rack.
Rack includes the following features:
 - A different SACK processing scheme (the old sack structures are not used).
 - RACK (Recent acknowledgment) where counting dup-acks is no longer done
        instead time is used to knwo when to retransmit. (see the I-D)
 - TLP (Tail Loss Probe) where we will probe for tail-losses to attempt
        to try not to take a retransmit time-out. (see the I-D)
 - Burst mitigation using TCPHTPS
 - PRR (partial rate reduction) see the RFC.

Once built into your kernel, you can select this stack by either
socket option with the name of the stack is "rack" or by setting
the global sysctl so the default is rack.

Note that any connection that does not support SACK will be kicked
back to the "default" base  FreeBSD stack (currently known as "default").

To build this into your kernel you will need to enable in your
kernel:
   makeoptions WITH_EXTRA_TCP_STACKS=1
   options TCPHPTS

Sponsored by:	Netflix Inc.
Differential Revision:		https://reviews.freebsd.org/D15525
2018-06-07 18:18:13 +00:00
John Baldwin
f17985319d Export tcp_always_keepalive for use by the Chelsio TOM module.
This used to work by accident with ld.bfd even though always_keepalive
was marked as static. LLD honors static more correctly, so export this
variable properly (including moving it into the tcp_* namespace).

Reviewed by:	bz, emaste
MFC after:	2 weeks
Sponsored by:	Chelsio Communications
Differential Revision:	https://reviews.freebsd.org/D14129
2018-01-30 23:01:37 +00:00
Pedro F. Giffuni
51369649b0 sys: further adoption of SPDX licensing ID tags.
Mainly focus on files that use BSD 3-Clause license.

The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.

Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
2017-11-20 19:43:44 +00:00
Gleb Smirnoff
e29c55e4bb Declare pmtud_blackhole global variables in tcp_timer.h, so that
alternative TCP stacks can legally use them.
2017-10-06 20:33:40 +00:00
Gleb Smirnoff
cc65eb4e79 Hide struct inpcb, struct tcpcb from the userland.
This is a painful change, but it is needed.  On the one hand, we avoid
modifying them, and this slows down some ideas, on the other hand we still
eventually modify them and tools like netstat(1) never work on next version of
FreeBSD.  We maintain a ton of spares in them, and we already got some ifdef
hell at the end of tcpcb.

Details:
- Hide struct inpcb, struct tcpcb under _KERNEL || _WANT_FOO.
- Make struct xinpcb, struct xtcpcb pure API structures, not including
  kernel structures inpcb and tcpcb inside.  Export into these structures
  the fields from inpcb and tcpcb that are known to be used, and put there
  a ton of spare space.
- Make kernel and userland utilities compilable after these changes.
- Bump __FreeBSD_version.

Reviewed by:	rrs, gnn
Differential Revision:	D10018
2017-03-21 06:39:49 +00:00
Warner Losh
fbbd9655e5 Renumber copyright clause 4
Renumber cluase 4 to 3, per what everybody else did when BSD granted
them permission to remove clause 3. My insistance on keeping the same
numbering for legal reasons is too pedantic, so give up on that point.

Submitted by:	Jan Schaumann <jschauma@stevens.edu>
Pull Request:	https://github.com/freebsd/freebsd/pull/96
2017-02-28 23:42:47 +00:00
Ryan Stone
5ede40dcf2 Don't zero out srtt after excess retransmits
If the TCP stack has retransmitted more than 1/4 of the total
number of retransmits before a connection drop, it decides that
its current RTT estimate is hopelessly out of date and decides
to recalculate it from scratch starting with the next ACK.

Unfortunately, it implements this by zeroing out the current RTT
estimate.  Drop this hack entirely, as it makes it significantly more
difficult to debug connection issues.  Instead check for excessive
retransmits at the point where srtt is updated from an ACK being
received.  If we've exceeded 1/4 of the maximum retransmits,
discard the previous srtt estimate and replace it with the latest
rtt measurement.

Differential Revision:	https://reviews.freebsd.org/D9519
Reviewed by:	gnn
Sponsored by:	Dell EMC Isilon
2017-02-11 17:05:08 +00:00
Randall Stewart
b07fef500b This cleans up the timer code in TCP and also makes it so we do not
take the INFO lock *unless* we are really going to delete the TCB.

Differential Revision:	D7136
2016-08-16 12:40:56 +00:00
Randall Stewart
e5ad64562a This cleans up the timers code in TCP to start using the new
async_drain functionality. This as been tested in NF as well as
by Verisign. Still to do in here is to remove all the old flags. They
are currently left being maintained but probably are no longer needed.

Sponsored by:	Netflix Inc.
Differential Revision:	http://reviews.freebsd.org/D5924
2016-04-28 13:27:12 +00:00
Hiren Panchasara
0645c6049d Persist timers TCPTV_PERSMIN and TCPTV_PERSMAX are hardcoded with 5 seconds and
60 seconds, respectively. Turn them into sysctls that can be tuned live. The
default values of 5 seconds and 60 seconds have been retained.

Submitted by:		Jason Wolfe (j at nitrology dot com)
Reviewed by:		gnn, rrs, hiren, bz
MFC after:		1 week
Sponsored by:		Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D5024
2016-01-26 16:33:38 +00:00
Julien Charbon
d6de19ac2f Put r284245 back in place: If at first this fix was seen as a temporary
workaround for a callout(9) issue, it turns out it is instead the right
way to use callout in mpsafe mode without using callout_drain().

r284245 commit message:

Fix a callout race condition introduced in TCP timers callouts with r281599.
In TCP timer context, it is not enough to check callout_stop() return value
to decide if a callout is still running or not, previous callout_reset()
return values have also to be checked.

Differential Revision:	https://reviews.freebsd.org/D2763
2015-08-30 13:44:39 +00:00
Julien Charbon
bcf9b91395 Revert r284245: "Fix a callout race condition introduced in TCP
timers callouts with r281599."

r281599 fixed a TCP timer race condition, but due a callout(9) bug
it also introduced another race condition workaround-ed with r284245.
The callout(9) bug being fixed with r286880, we can now revert the
workaround (r284245).

Differential Revision:	https://reviews.freebsd.org/D2079 (Initial change)
Differential Revision:	https://reviews.freebsd.org/D2763 (Workaround)
Differential Revision:	https://reviews.freebsd.org/D3078 (Fix)
Sponsored by:		Verisign, Inc.
MFC after:		2 weeks
2015-08-24 09:30:27 +00:00
Hiren Panchasara
ad389a8c3b Remove unused TCPTV_SRTTDFLT. We initialize srtt with TCPTV_SRTTBASE when we
don't have any rtt estimate.

Differential Revision:	D3334
Sponsored by:		Limelight Networks
2015-08-12 16:08:37 +00:00
Julien Charbon
cad814eedf Fix a callout race condition introduced in TCP timers callouts with r281599.
In TCP timer context, it is not enough to check callout_stop() return value
to decide if a callout is still running or not, previous callout_reset()
return values have also to be checked.

Differential Revision:	https://reviews.freebsd.org/D2763
Reviewed by:		hiren
Approved by:		hiren
MFC after:		1 day
Sponsored by:		Verisign, Inc.
2015-06-10 20:43:07 +00:00
Julien Charbon
5571f9cf81 Fix an old and well-documented use-after-free race condition in
TCP timers:
 - Add a reference from tcpcb to its inpcb
 - Defer tcpcb deletion until TCP timers have finished

Differential Revision:	https://reviews.freebsd.org/D2079
Submitted by:		jch, Marc De La Gueronniere <mdelagueronniere@verisign.com>
Reviewed by:		imp, rrs, adrian, jhb, bz
Approved by:		jhb
Sponsored by:		Verisign, Inc.
2015-04-16 10:00:06 +00:00
Julien Charbon
cea40c4888 Fix a race condition in TCP timewait between tcp_tw_2msl_reuse() and
tcp_tw_2msl_scan().  This race condition drives unplanned timewait
timeout cancellation.  Also simplify implementation by holding inpcb
reference and removing tcptw reference counting.

Differential Revision:	https://reviews.freebsd.org/D826
Submitted by:		Marc De la Gueronniere <mdelagueronniere@verisign.com>
Submitted by:		jch
Reviewed By:		jhb (mentor), adrian, rwatson
Sponsored by:		Verisign, Inc.
MFC after:		2 weeks
X-MFC-With:		r264321
2014-10-30 08:53:56 +00:00
John Baldwin
66eefb1eae Currently, the TCP slow timer can starve TCP input processing while it
walks the list of connections in TIME_WAIT closing expired connections
due to contention on the global TCP pcbinfo lock.

To remediate, introduce a new global lock to protect the list of
connections in TIME_WAIT.  Only acquire the TCP pcbinfo lock when
closing an expired connection.  This limits the window of time when
TCP input processing is stopped to the amount of time needed to close
a single connection.

Submitted by:	Julien Charbon <jcharbon@verisign.com>
Reviewed by:	rwatson, rrs, adrian
MFC after:	2 months
2014-04-10 18:15:35 +00:00
Andre Oppermann
13feab8286 Add DELACK to list of timers.
MFC after:	1 week
2012-11-27 19:07:28 +00:00
Andre Oppermann
8d045dbdf3 Define the delayed ACK timeout value directly as hz/10 instead of
obfuscating it by going through PR_FASTHZ.  No functional change.

MFC after:	2 weeks
2012-10-29 12:17:02 +00:00
Andre Oppermann
024fd5b6bb For retransmits of SYN|ACK from the syncache use the slightly more
aggressive special tcp_syn_backoff[] retransmit schedule instead of
the normal tcp_backoff[] schedule for established connections.

MFC after:	2 weeks
2012-10-28 19:02:07 +00:00
Gleb Smirnoff
9077f38738 Add new socket options: TCP_KEEPINIT, TCP_KEEPIDLE, TCP_KEEPINTVL and
TCP_KEEPCNT, that allow to control initial timeout, idle time, idle
re-send interval and idle send count on a per-socket basis.

Reviewed by:	andre, bz, lstewart
2012-02-05 16:53:02 +00:00
Andre Oppermann
1c18314d17 Remove the TCP inflight bandwidth limiter as announced in r211315
to give way for the pluggable congestion control framework.  It is
the task of the congestion control algorithm to set the congestion
window and amount of inflight data without external interference.

In 'struct tcpcb' the variables previously used by the inflight
limiter are renamed to spares to keep the ABI intact and to have
some more space for future extensions.

In 'struct tcp_info' the variable 'tcpi_snd_bwnd' is not removed to
preserve the ABI.  It is always set to 0.

In siftr.c in 'struct pkt_node' the variable 'snd_bwnd' is not removed
to preserve the ABI.  It is always set to 0.

These unused variable in the various structures may be reused in the
future or garbage collected before the next release or at some other
point when an ABI change happens anyway for other reasons.

No MFC is planned.  The inflight bandwidth limiter stays disabled by
default in the other branches but remains available.
2010-09-16 21:06:45 +00:00
Mike Silbersack
b8614722ff Add the ability to see TCP timers via netstat -x. This can be a useful
feature when you have a seemingly stuck socket and want to figure
out why it has not been closed yet.

No plans to MFC this, as it changes the netstat sysctl ABI.

Reviewed by:	andre, rwatson, Eric Van Gyzen
2009-09-16 05:33:15 +00:00
Mike Silbersack
e2f2059f68 Two changes:
- Reintegrate the ANSI C function declaration change
  from tcp_timer.c rev 1.92

- Reorganize the tcpcb structure so that it has a single
  pointer to the "tcp_timer" structure which contains all
  of the tcp timer callouts.  This change means that when
  the single tcp timer change is reintegrated, tcpcb will
  not change in size, and therefore the ABI between
  netstat and the kernel will not change.

Neither of these changes should have any functional
impact.

Reviewed by: bmah, rrs
Approved by: re (bmah)
2007-09-24 05:26:24 +00:00
Robert Watson
85d9437250 Back out tcp_timer.c:1.93 and associated changes that reimplemented the many
TCP timers as a single timer, but retain the API changes necessary to
reintroduce this change.  This will back out the source of at least two
reported problems: lock leaks in certain timer edge cases, and TCP timers
continuing to fire after a connection has closed (a bug previously fixed and
then reintroduced with the timer rewrite).

In a follow-up commit, some minor restylings and comment changes performed
after the TCP timer rewrite will be reapplied, and a further change to allow
the TCP timer rewrite to be added back without disturbing the ABI.  The new
design is believed to be a good thing, but the outstanding issues are
leading to significant stability/correctness problems that are holding
up 7.0.

This patch was generated by silby, but is being committed by proxy due to
poor network connectivity for silby this week.

Approved by:	re (kensmith)
Submitted by:	silby
Tested by:	rwatson, kris
Problems reported by:	peter, kris, others
2007-09-07 09:19:22 +00:00
Peter Wemm
c4a184bdc4 Change TCPTV_MIN to be independent of HZ. While it was documented to
be in ticks "for algorithm stability" when originally committed, it turns
out that it has a significant impact in timing out connections.  When we
changed HZ from 100 to 1000, this had a big effect on reducing the time
before dropping connections.

To demonstrate, boot with kern.hz=100.  ssh to a box on local ethernet
and establish a reliable round-trip-time (ie: type a few commands).
Then unplug the ethernet and press a key.  Time how long it takes to
drop the connection.

The old behavior (with hz=100) caused the connection to typically drop
between 90 and 110 seconds of getting no response.

Now boot with kern.hz=1000 (default).  The same test causes the ssh session
to drop after just 9-10 seconds.  This is a big deal on a wifi connection.

With kern.hz=1000, change sysctl net.inet.tcp.rexmit_min from 3 to 30.
Note how it behaves the same as when HZ was 100.  Also, note that when
booting with hz=100, net.inet.tcp.rexmit_min *used* to be 30.

This commit changes TCPTV_MIN to be scaled with hz.  rexmit_min should
always be about 30.  If you set hz to Really Slow(TM), there is a safety
feature to prevent a value of 0 being used.

This may be revised in the future, but for the time being, it restores the
old, pre-hz=1000 behavior, which is significantly less annoying.

As a workaround, to avoid rebooting or rebuilding a kernel, you can run
"sysctl net.inet.tcp.rexmit_min=30" and add "net.inet.tcp.rexmit_min=30"
to /etc/sysctl.conf.  This is safe to run from 6.0 onwards.

Approved by:  re (rwatson)
Reviewed by:  andre, silby
2007-07-31 22:11:55 +00:00
Andre Oppermann
abb91d889a Remove now unused stuff forgotten in the previous commit. 2007-05-16 17:55:22 +00:00
Andre Oppermann
2104448fe7 Move TIME_WAIT related functions and timer handling from files
other than repo copied tcp_subr.c into tcp_timewait.c#1.284:

 tcp_input.c#1.350 tcp_timewait() -> tcp_twcheck()

 tcp_timer.c#1.92 tcp_timer_2msl_reset() -> tcp_tw_2msl_reset()
 tcp_timer.c#1.92 tcp_timer_2msl_stop() -> tcp_tw_2msl_stop()
 tcp_timer.c#1.92 tcp_timer_2msl_tw() -> tcp_tw_2msl_scan()

This is a mechanical move with appropriate renames and making
them static if used only locally.

The tcp_tw_2msl_scan() cleanup function is still run from the
tcp_slowtimo() in tcp_timer.c.
2007-05-16 17:14:25 +00:00
Ruslan Ermilov
7480de4305 Make "struct tcp_timer" visible only to the kernel, and unbreak world. 2007-04-11 14:08:42 +00:00
Andre Oppermann
b8152ba793 Change the TCP timer system from using the callout system five times
directly to a merged model where only one callout, the next to fire,
is registered.

Instead of callout_reset(9) and callout_stop(9) the new function
tcp_timer_activate() is used which then internally manages the callout.

The single new callout is a mutex callout on inpcb simplifying the
locking a bit.

tcp_timer() is the called function which handles all race conditions
in one place and then dispatches the individual timer functions.

Reviewed by:	rwatson (earlier version)
2007-04-11 09:45:16 +00:00
Mohan Srinivasan
7c72af8770 Reap FIN_WAIT_2 connections marked SOCANTRCVMORE faster. This mitigate
potential issues where the peer does not close, potentially leaving
thousands of connections in FIN_WAIT_2. This is controlled by a new sysctl
fast_finwait2_recycle, which is disabled by default.

Reviewed by: gnn, silby.
2007-02-26 22:25:21 +00:00
John-Mark Gurney
4dc630cdd2 if min is greater than max, prefer max over min... I managed to get a
retransmit timer that was going to take 19 days to trigger...

Reviewed by:	silby
2006-09-25 07:22:39 +00:00
Ruslan Ermilov
751dea2935 Back when we had T/TCP support, we used to apply different
timeouts for TCP and T/TCP connections in the TIME_WAIT
state, and we had two separate timed wait queues for them.
Now that is has gone, the timeout is always 2*MSL again,
and there is no reason to keep two queues (the first was
unused anyway!).

Also, reimplement the remaining queue using a TAILQ (it
was technically impossible before, with two queues).
2006-09-07 13:06:00 +00:00
Mohan Srinivasan
464469c713 Fixes an edge case bug in timewait handling where ticks rolling over causing
the timewait expiry to be exactly 0 corrupts the timewait queues (and that entry).
Reviewed by:	silby
2006-08-11 21:15:23 +00:00
Andre Oppermann
eaf80179e2 Have TCP Inflight disable itself if the RTT is below a certain
threshold.  Inflight doesn't make sense on a LAN as it has
trouble figuring out the maximal bandwidth because of the coarse
tick granularity.

The sysctl net.inet.tcp.inflight.rttthresh specifies the threshold
in milliseconds below which inflight will disengage.  It defaults
to 10ms.

Tested by:	Joao Barros <joao.barros-at-gmail.com>,
		Rich Murphey <rich-at-whiteoaklabs.com>
Sponsored by:	TCP/IP Optimization Fundraise 2005
2006-02-16 19:38:07 +00:00
Warner Losh
c398230b64 /* -> /*- for license, minor formatting changes 2005-01-07 01:45:51 +00:00
Robert Watson
a4f757cd5d White space cleanup for netinet before branch:
- Trailing tab/space cleanup
- Remove spurious spaces between or before tabs

This change avoids touching files that Andre likely has in his working
set for PFIL hooks changes for IPFW/DUMMYNET.

Approved by:	re (scottl)
Submitted by:	Xin LI <delphij@frontfree.net>
2004-08-16 18:32:07 +00:00
Warner Losh
f36cfd49ad Remove advertising clause from University of California Regent's
license, per letter dated July 22, 1999 and email from Peter Wemm,
Alan Cox and Robert Watson.

Approved by: core, peter, alc, rwatson
2004-04-07 20:46:16 +00:00
Jonathan Lemon
607b0b0cc9 Remove a panic(); if the zone allocator can't provide more timewait
structures, reuse the oldest one.  Also move the expiry timer from
a per-structure callout to the tcp slow timer.

Sponsored by: DARPA, NAI Labs
2003-03-08 22:06:20 +00:00
Jonathan Lemon
340c35de6a Add a TCP TIMEWAIT state which uses less space than a fullblown TCP
control block.  Allow the socket and tcpcb structures to be freed
earlier than inpcb.  Update code to understand an inp w/o a socket.

Reviewed by: hsu, silby, jayanth
Sponsored by: DARPA, NAI Labs
2003-02-19 22:32:43 +00:00
Alfred Perlstein
e88894d39a make the strings for tcptimers, tanames and prurequests const to silence
warnings.
2002-08-16 09:07:59 +00:00
Matthew Dillon
701bec5a38 Introduce two new sysctl's:
net.inet.tcp.rexmit_min (default 3 ticks equiv)

    This sysctl is the retransmit timer RTO minimum,
    specified in milliseconds.  This value is
    designed for algorithmic stability only.

net.inet.tcp.rexmit_slop (default 200ms)

    This sysctl is the retransmit timer RTO slop
    which is added to every retransmit timeout and
    is designed to handle protocol stack overheads
    and delayed ack issues.

Note that the *original* code applied a 1-second
RTO minimum but never applied real slop to the RTO
calculation, so any RTO calculation over one second
would have no slop and thus not account for
protocol stack overheads (TCP timestamps are not
a measure of protocol turnaround!).  Essentially,
the original code made the RTO calculation almost
completely irrelevant.

Please note that the 200ms slop is debateable.
This commit is not meant to be a line in the sand,
and if the community winds up deciding that increasing
it is the correct solution then it's easy to do.
Note that larger values will destroy performance
on lossy networks while smaller values may result in
a greater number of unnecessary retransmits.
2002-07-18 19:06:12 +00:00
Matthew Dillon
22fd54d461 I don't know how the minimum retransmit timeout managed to get set to
one second but it badly breaks throughput on networks with minor packet
loss.

Complaints by: at least two people tracked down to this.
MFC after:	3 days
2002-07-17 23:32:03 +00:00