Commit Graph

63 Commits

Author SHA1 Message Date
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
Andre Oppermann
97d8d152c2 Introduce tcp_hostcache and remove the tcp specific metrics from
the routing table.  Move all usage and references in the tcp stack
from the routing table metrics to the tcp hostcache.

It caches measured parameters of past tcp sessions to provide better
initial start values for following connections from or to the same
source or destination.  Depending on the network parameters to/from
the remote host this can lead to significant speedups for new tcp
connections after the first one because they inherit and shortcut
the learning curve.

tcp_hostcache is designed for multiple concurrent access in SMP
environments with high contention and is hash indexed by remote
ip address.

It removes significant locking requirements from the tcp stack with
regard to the routing table.

Reviewed by:	sam (mentor), bms
Reviewed by:	-net, -current, core@kame.net (IPv6 parts)
Approved by:	re (scottl)
2003-11-20 20:07:39 +00:00
Sam Leffler
2a0746208b use local values instead of chasing pointers
Supported by:	FreeBSD Foundation
2003-11-08 22:57:13 +00:00
Jeffrey Hsu
9d11646de7 Unify the "send high" and "recover" variables as specified in the
lastest rev of the spec.  Use an explicit flag for Fast Recovery. [1]

Fix bug with exiting Fast Recovery on a retransmit timeout
diagnosed by Lu Guohan. [2]

Reviewed by:		Thomas Henderson <thomas.r.henderson@boeing.com>
Reported and tested by:	Lu Guohan <lguohan00@mails.tsinghua.edu.cn> [2]
Approved by:		Thomas Henderson <thomas.r.henderson@boeing.com>,
			Sally Floyd <floyd@acm.org> [1]
2003-07-15 21:49:53 +00:00
Jeffrey Hsu
f058535deb Compensate for decreasing the minimum retransmit timeout.
Reviewed by:	jlemon
2003-06-04 10:03:55 +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
Jonathan Lemon
7990938421 Convert tcp_fillheaders(tp, ...) -> tcpip_fillheaders(inp, ...) so the
routine does not require a tcpcb to operate.  Since we no longer keep
template mbufs around, move pseudo checksum out of this routine, and
merge it with the length update.

Sponsored by: DARPA, NAI Labs
2003-02-19 22:18:06 +00:00
Jeffrey Hsu
cb942153c8 Fix NewReno.
Reviewed by: Tom Henderson <thomas.r.henderson@boeing.com>
2003-01-13 11:01:20 +00:00
Jeffrey Hsu
abe239cfe2 Validate inp to prevent an use after free. 2002-12-24 21:00:31 +00:00
Bruce Evans
c74af4fac1 Include <sys/mutex.h> and its prerequisite <sys/lock.h> instead of depending
on namespace pollution 4 layers deep in <netinet/in_pcb.h>.

Removed unused includes.  Sorted includes.
2002-09-05 15:33:30 +00:00
John Polstra
8ea8a6804b Fix overflows in intermediate calculations in sysctl_msec_to_ticks().
At hz values of 1000 and above the overflows caused net.inet.tcp.keepidle
to be reported as negative.

MFC after:	3 days
2002-07-20 23:48:59 +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
Jeffrey Hsu
f76fcf6d4c Lock up inpcb.
Submitted by:	Jennifer Yang <yangjihui@yahoo.com>
2002-06-10 20:05:46 +00:00
Seigo Tanimura
4cc20ab1f0 Back out my lats commit of locking down a socket, it conflicts with hsu's work.
Requested by:	hsu
2002-05-31 11:52:35 +00:00
Seigo Tanimura
243917fe3b Lock down a socket, milestone 1.
o Add a mutex (sb_mtx) to struct sockbuf. This protects the data in a
  socket buffer. The mutex in the receive buffer also protects the data
  in struct socket.

o Determine the lock strategy for each members in struct socket.

o Lock down the following members:

  - so_count
  - so_options
  - so_linger
  - so_state

o Remove *_locked() socket APIs.  Make the following socket APIs
  touching the members above now require a locked socket:

 - sodisconnect()
 - soisconnected()
 - soisconnecting()
 - soisdisconnected()
 - soisdisconnecting()
 - sofree()
 - soref()
 - sorele()
 - sorwakeup()
 - sotryfree()
 - sowakeup()
 - sowwakeup()

Reviewed by:	alfred
2002-05-20 05:41:09 +00:00
Robert Watson
c39a614e0d o Our currenty userland boot code (due to rc.conf and rc.network) always
enables TCP keepalives using the net.inet.tcp.always_keepalive by default.
  Synchronize the kernel default with the userland default.
2001-12-07 17:01:28 +00:00
Mike Silbersack
b0e3ad758b Much delayed but now present: RFC 1948 style sequence numbers
In order to ensure security and functionality, RFC 1948 style
initial sequence number generation has been implemented.  Barring
any major crypographic breakthroughs, this algorithm should be
unbreakable.  In addition, the problems with TIME_WAIT recycling
which affect our currently used algorithm are not present.

Reviewed by: jesper
2001-08-22 00:58:16 +00:00
Mike Silbersack
2d610a5028 Temporary feature: Runtime tuneable tcp initial sequence number
generation scheme.  Users may now select between the currently used
OpenBSD algorithm and the older random positive increment method.

While the OpenBSD algorithm is more secure, it also breaks TIME_WAIT
handling; this is causing trouble for an increasing number of folks.

To switch between generation schemes, one sets the sysctl
net.inet.tcp.tcp_seq_genscheme.  0 = random positive increments,
1 = the OpenBSD algorithm.  1 is still the default.

Once a secure _and_ compatible algorithm is implemented, this sysctl
will be removed.

Reviewed by: jlemon
Tested by: numerous subscribers of -net
2001-07-08 02:20:47 +00:00
Mike Silbersack
08517d530e Eliminate the allocation of a tcp template structure for each
connection.  The information contained in a tcptemp can be
reconstructed from a tcpcb when needed.

Previously, tcp templates required the allocation of one
mbuf per connection.  On large systems, this change should
free up a large number of mbufs.

Reviewed by:	bmilekic, jlemon, ru
MFC after: 2 weeks
2001-06-23 03:21:46 +00:00
Jesper Skriver
7ceb778366 Disable rfc1323 and rfc1644 TCP extensions if we havn't got
any response to our third SYN to work-around some broken
terminal servers (most of which have hopefully been retired)
that have bad VJ header compression code which trashes TCP
segments containing unknown-to-them TCP options.

PR:		kern/1689
Submitted by:	jesper
Reviewed by:	wollman
MFC after:	2 weeks
2001-05-31 19:24:49 +00:00
Jesper Skriver
d1745f454d Say goodbye to TCP_COMPAT_42
Reviewed by:	wollman
Requested by:	wollman
2001-04-20 11:58:56 +00:00
Kris Kennaway
f0a04f3f51 Randomize the TCP initial sequence numbers more thoroughly.
Obtained from:	OpenBSD
Reviewed by:	jesper, peter, -developers
2001-04-17 18:08:01 +00:00
Jonathan Lemon
7d42e30c2e Use more aggressive retransmit timeouts for the initial SYN packet.
As we currently drop the connection after 4 retransmits + 2 ICMP errors,
this allows initial connection attempts to be dropped much faster.
2001-02-26 21:33:55 +00:00
Jonathan Lemon
d17e895b5f If TCPDEBUG is defined, we could dereference a tp which was freed. 2000-10-02 15:00:13 +00:00
Jonathan Lemon
af1270f87f It is possible for a TCP callout to be removed from the timing wheel,
but have a network interrupt arrive and deactivate the timeout before
the callout routine runs.  Check for this case in the callout routine;
it should only run if the callout is active and not on the wheel.
2000-09-16 00:53:53 +00:00
Poul-Henning Kamp
77978ab8bc Previous commit changing SYSCTL_HANDLER_ARGS violated KNF.
Pointed out by:	bde
2000-07-04 11:25:35 +00:00
Poul-Henning Kamp
82d9ae4e32 Style police catches up with rev 1.26 of src/sys/sys/sysctl.h:
Sanitize SYSCTL_HANDLER_ARGS so that simplistic tools can grog our
sources:

        -sysctl_vm_zone SYSCTL_HANDLER_ARGS
        +sysctl_vm_zone (SYSCTL_HANDLER_ARGS)
2000-07-03 09:35:31 +00:00
Jonathan Lemon
46f5848237 Implement TCP NewReno, as documented in RFC 2582. This allows
better recovery for multiple packet losses in a single window.
The algorithm can be toggled via the sysctl net.inet.tcp.newreno,
which defaults to "on".

Submitted by:  Jayanth Vijayaraghavan <jayanth@yahoo-inc.com>
2000-05-06 03:31:09 +00:00
Yoshinobu Inoue
fb59c426ff tcp updates to support IPv6.
also a small patch to sys/nfs/nfs_socket.c, as max_hdr size change.

Reviewed by: freebsd-arch, cvs-committers
Obtained from: KAME project
2000-01-09 19:17:30 +00:00
Jonathan Lemon
9fc2bcf662 Simplify, and return an error if the user attempts to set a TCP
time value which results in < 1 tick.

Suggested by: 	bde
1999-08-31 16:34:20 +00:00
Jonathan Lemon
ccb4d0c653 Add a SYSCTL_PROC so that TCP timer values are now expressed to
the user in ms, while they are stored internally as ticks. Note
that there probably are rounding bogons here, especially on the
alpha.
1999-08-31 03:40:24 +00:00
Jonathan Lemon
9b8b58e033 Restructure TCP timeout handling:
- eliminate the fast/slow timeout lists for TCP and instead use a
    callout entry for each timer.
  - increase the TCP timer granularity to HZ
  - implement "bad retransmit" recovery, as presented in
    "On Estimating End-to-End Network Path Properties", by Allman and Paxson.

Submitted by:	jlemon, wollmann
1999-08-30 21:17:07 +00:00
Peter Wemm
c3aac50f28 $Id$ -> $FreeBSD$ 1999-08-28 01:08:13 +00:00
Bill Fumerola
3d177f465a Add sysctl descriptions to many SYSCTL_XXXs
PR:		kern/11197
Submitted by:	Adrian Chadd <adrian@FreeBSD.org>
Reviewed by:	billf(spelling/style/minor nits)
Looked at by:	bde(style)
1999-05-03 23:57:32 +00:00
David Greenman
552b7df4c1 Ensure that TCP_REXMTVAL doesn't return a value less than t_rttmin. This
is believed to have been broken with the Brakmo/Peterson srtt
calculation changes. The result of this bug is that TCP connections
could time out extremely quickly (in 12 seconds).
Also backed out jdp's partial fix for this problem in rev 1.17 of
tcp_timer.c as it is obsoleted by this commit.
Bug was pointed out by Kevin Lehey <kml@roller.nas.nasa.gov>.

PR:	6068
1998-04-24 09:25:39 +00:00
Poul-Henning Kamp
8e5db87cdb Remove the last traces of TUBA.
Inspired by:	PR kern/3317
1998-04-06 06:52:47 +00:00
David Greenman
f498eeeead Changes to support the addition of a new sysctl variable:
net.inet.tcp.delack_enabled
Which defaults to 1 and can be set to 0 to disable TCP delayed-ack
processing (i.e. all acks are immediate).
1998-02-26 05:25:39 +00:00
Eivind Eklund
92252381f3 Make TCP_COMPAT_42 a new style option. 1998-01-25 04:23:33 +00:00
Joerg Wunsch
0cc12cc57e Make TCPDEBUG a new-style option. 1997-09-16 18:36:06 +00:00
Bruce Evans
1fd0b0588f Removed unused #includes. 1997-08-02 14:33:27 +00:00
Peter Wemm
6875d25465 Back out part 1 of the MCFH that changed $Id$ to $FreeBSD$. We are not
ready for it yet.
1997-02-22 09:48:43 +00:00
Jordan K. Hubbard
1130b656e5 Make the long-awaited change from $Id$ to $FreeBSD$
This will make a number of things easier in the future, as well as (finally!)
avoiding the Id-smashing problem which has plagued developers for so long.

Boy, I'm glad we're not using sup anymore.  This update would have been
insane otherwise.
1997-01-14 07:20:47 +00:00
Paul Traina
7b40aa327d Make the misnamed tcp initial keepalive timer value (which is really the
time, in seconds, that state for non-established TCP sessions stays about)
a sysctl modifyable variable.

[part 1 of two commits, I just realized I can't play with the indices as
 I was typing this commit message.]
1996-09-13 23:51:44 +00:00
David Greenman
af7a299930 Fixed two bugs in previous commit: be sure to include tcp_debug.h when
TCPDEBUG is defined, and fix typo in TCPDEBUG2() macro.
1996-07-12 17:28:47 +00:00
Garrett Wollman
2c37256e5a Modify the kernel to use the new pr_usrreqs interface rather than the old
pr_usrreq mechanism which was poorly designed and error-prone.  This
commit renames pr_usrreq to pr_ousrreq so that old code which depended on it
would break in an obvious manner.  This commit also implements the new
interface for TCP, although the old function is left as an example
(#ifdef'ed out).  This commit ALSO fixes a longstanding bug in the
TCP timer processing (introduced by davidg on 1995/04/12) which caused
timer processing on a TCB to always stop after a single timer had
expired (because it misinterpreted the return value from tcp_usrreq()
to indicate that the TCB had been deleted).  Finally, some code
related to polling has been deleted from if.c because it is not
relevant t -current and doesn't look at all like my current code.
1996-07-11 16:32:50 +00:00
John Polstra
588c92252f Fix a bug in the handling of the "persist" state which, under certain
circumstances, caused perfectly good connections to be dropped.  This
happened for connections over a LAN, where the retransmit timer
calculation TCP_REXMTVAL(tp) returned 0.  If sending was blocked by flow
control for long enough, the old code dropped the connection, even
though timely replies were being received for all window probes.

Reviewed by:	W. Richard Stevens <rstevens@noao.edu>
1996-06-03 15:37:52 +00:00
David Greenman
2d8266af5c Two fixes from Rich Stevens:
1) Set the persist timer to help time-out connections in the CLOSING state.
2) Honor the keep-alive timer in the CLOSING state.

   This fixes problems with connections getting "stuck" due to incompletion
of the final connection shutdown which can be a BIG problem on busy WWW
servers.
1996-04-15 03:46:33 +00:00
Poul-Henning Kamp
34be9bf3ce Add a sysctl (net.inet.tcp.always_keepalive: 0) that when set will force
keepalive on all tcp sessions.  Setsockopt(2) cannot override this setting.
Maybe another one is needed that just changes the default for SO_KEEPALIVE ?
Requested by: Joe Greco <jgreco@brasil.moneng.mei.com>
1996-04-04 11:17:04 +00:00
David Greenman
2ee45d7d28 Move or add #include <queue.h> in preparation for upcoming struct socket
changes.
1996-03-11 15:13:58 +00:00