summaryrefslogtreecommitdiffstats
path: root/sys/netinet/tcp_timer.c
Commit message (Collapse)AuthorAgeFilesLines
* Introduce tcp_hostcache and remove the tcp specific metrics fromandre2003-11-201-5/+2
| | | | | | | | | | | | | | | | | | | | | | | 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)
* use local values instead of chasing pointerssam2003-11-081-3/+2
| | | | Supported by: FreeBSD Foundation
* Unify the "send high" and "recover" variables as specified in thehsu2003-07-151-2/+7
| | | | | | | | | | | | 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]
* Compensate for decreasing the minimum retransmit timeout.hsu2003-06-041-2/+2
| | | | Reviewed by: jlemon
* Remove a panic(); if the zone allocator can't provide more timewaitjlemon2003-03-081-22/+61
| | | | | | | 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
* Add a TCP TIMEWAIT state which uses less space than a fullblown TCPjlemon2003-02-191-0/+27
| | | | | | | | 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
* Convert tcp_fillheaders(tp, ...) -> tcpip_fillheaders(inp, ...) so thejlemon2003-02-191-1/+1
| | | | | | | | 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
* Fix NewReno.hsu2003-01-131-5/+2
| | | | Reviewed by: Tom Henderson <thomas.r.henderson@boeing.com>
* Validate inp to prevent an use after free.hsu2002-12-241-0/+25
|
* Include <sys/mutex.h> and its prerequisite <sys/lock.h> instead of dependingbde2002-09-051-8/+6
| | | | | | on namespace pollution 4 layers deep in <netinet/in_pcb.h>. Removed unused includes. Sorted includes.
* Fix overflows in intermediate calculations in sysctl_msec_to_ticks().jdp2002-07-201-2/+2
| | | | | | | At hz values of 1000 and above the overflows caused net.inet.tcp.keepidle to be reported as negative. MFC after: 3 days
* Introduce two new sysctl's:dillon2002-07-181-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
* Lock up inpcb.hsu2002-06-101-0/+51
| | | | Submitted by: Jennifer Yang <yangjihui@yahoo.com>
* Back out my lats commit of locking down a socket, it conflicts with hsu's work.tanimura2002-05-311-51/+17
| | | | Requested by: hsu
* Lock down a socket, milestone 1.tanimura2002-05-201-17/+51
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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
* o Our currenty userland boot code (due to rc.conf and rc.network) alwaysrwatson2001-12-071-1/+1
| | | | | enables TCP keepalives using the net.inet.tcp.always_keepalive by default. Synchronize the kernel default with the userland default.
* Much delayed but now present: RFC 1948 style sequence numberssilby2001-08-221-2/+0
| | | | | | | | | | 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
* Temporary feature: Runtime tuneable tcp initial sequence numbersilby2001-07-081-0/+2
| | | | | | | | | | | | | | | | | | 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
* Eliminate the allocation of a tcp template structure for eachsilby2001-06-231-3/+9
| | | | | | | | | | | | 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
* Disable rfc1323 and rfc1644 TCP extensions if we havn't gotjesper2001-05-311-0/+9
| | | | | | | | | | | | 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
* Say goodbye to TCP_COMPAT_42jesper2001-04-201-15/+0
| | | | | Reviewed by: wollman Requested by: wollman
* Randomize the TCP initial sequence numbers more thoroughly.kris2001-04-171-1/+1
| | | | | Obtained from: OpenBSD Reviewed by: jesper, peter, -developers
* Use more aggressive retransmit timeouts for the initial SYN packet.jlemon2001-02-261-1/+7
| | | | | As we currently drop the connection after 4 retransmits + 2 ICMP errors, this allows initial connection attempts to be dropped much faster.
* If TCPDEBUG is defined, we could dereference a tp which was freed.jlemon2000-10-021-1/+1
|
* It is possible for a TCP callout to be removed from the timing wheel,jlemon2000-09-161-5/+5
| | | | | | 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.
* Previous commit changing SYSCTL_HANDLER_ARGS violated KNF.phk2000-07-041-1/+1
| | | | Pointed out by: bde
* Style police catches up with rev 1.26 of src/sys/sys/sysctl.h:phk2000-07-031-1/+1
| | | | | | | | Sanitize SYSCTL_HANDLER_ARGS so that simplistic tools can grog our sources: -sysctl_vm_zone SYSCTL_HANDLER_ARGS +sysctl_vm_zone (SYSCTL_HANDLER_ARGS)
* Implement TCP NewReno, as documented in RFC 2582. This allowsjlemon2000-05-061-0/+5
| | | | | | | | 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>
* tcp updates to support IPv6.shin2000-01-091-7/+18
| | | | | | | 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
* Simplify, and return an error if the user attempts to set a TCPjlemon1999-08-311-7/+3
| | | | | | time value which results in < 1 tick. Suggested by: bde
* Add a SYSCTL_PROC so that TCP timer values are now expressed tojlemon1999-08-311-10/+35
| | | | | | the user in ms, while they are stored internally as ticks. Note that there probably are rounding bogons here, especially on the alpha.
* Restructure TCP timeout handling:jlemon1999-08-301-223/+287
| | | | | | | | | | - 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
* $Id$ -> $FreeBSD$peter1999-08-281-1/+1
|
* Add sysctl descriptions to many SYSCTL_XXXsbillf1999-05-031-3/+3
| | | | | | | PR: kern/11197 Submitted by: Adrian Chadd <adrian@FreeBSD.org> Reviewed by: billf(spelling/style/minor nits) Looked at by: bde(style)
* Ensure that TCP_REXMTVAL doesn't return a value less than t_rttmin. Thisdg1998-04-241-12/+7
| | | | | | | | | | | 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
* Remove the last traces of TUBA.phk1998-04-061-8/+1
| | | | Inspired by: PR kern/3317
* Changes to support the addition of a new sysctl variable:dg1998-02-261-11/+12
| | | | | | 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).
* Make TCP_COMPAT_42 a new style option.eivind1998-01-251-1/+2
|
* Make TCPDEBUG a new-style option.joerg1997-09-161-1/+3
|
* Removed unused #includes.bde1997-08-021-7/+1
|
* Back out part 1 of the MCFH that changed $Id$ to $FreeBSD$. We are notpeter1997-02-221-1/+1
| | | | ready for it yet.
* Make the long-awaited change from $Id$ to $FreeBSD$jkh1997-01-141-1/+1
| | | | | | | | 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.
* Make the misnamed tcp initial keepalive timer value (which is really thepst1996-09-131-1/+5
| | | | | | | | 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.]
* Fixed two bugs in previous commit: be sure to include tcp_debug.h whendg1996-07-121-1/+4
| | | | TCPDEBUG is defined, and fix typo in TCPDEBUG2() macro.
* Modify the kernel to use the new pr_usrreqs interface rather than the oldwollman1996-07-111-4/+16
| | | | | | | | | | | | | | 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.
* Fix a bug in the handling of the "persist" state which, under certainjdp1996-06-031-7/+12
| | | | | | | | | | 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>
* Two fixes from Rich Stevens:dg1996-04-151-2/+2
| | | | | | | | | 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.
* Add a sysctl (net.inet.tcp.always_keepalive: 0) that when set will forcephk1996-04-041-2/+7
| | | | | | 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>
* Move or add #include <queue.h> in preparation for upcoming struct socketdg1996-03-111-2/+2
| | | | changes.
* Reverse the modification which caused the annoying m_copydata crash: setolah1996-01-041-1/+5
| | | | | | the TF_ACKNOW flag when the REXMT timer goes off to force a retransmission. In certain situations pulling snd_nxt back to snd_una is not sufficient.
OpenPOWER on IntegriCloud