2005-01-07 01:45:51 +00:00
|
|
|
/*-
|
1994-05-24 10:09:53 +00:00
|
|
|
* Copyright (c) 1982, 1986, 1993
|
|
|
|
* The Regents of the University of California. All rights reserved.
|
|
|
|
*
|
|
|
|
* Redistribution and use in source and binary forms, with or without
|
|
|
|
* modification, are permitted provided that the following conditions
|
|
|
|
* are met:
|
|
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
|
|
* notice, this list of conditions and the following disclaimer.
|
|
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
|
|
* documentation and/or other materials provided with the distribution.
|
2017-02-28 23:42:47 +00:00
|
|
|
* 3. Neither the name of the University nor the names of its contributors
|
1994-05-24 10:09:53 +00:00
|
|
|
* may be used to endorse or promote products derived from this software
|
|
|
|
* without specific prior written permission.
|
|
|
|
*
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
|
|
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
|
|
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
|
|
* SUCH DAMAGE.
|
|
|
|
*
|
|
|
|
* @(#)tcp_timer.h 8.1 (Berkeley) 6/10/93
|
1999-08-28 01:08:13 +00:00
|
|
|
* $FreeBSD$
|
1994-05-24 10:09:53 +00:00
|
|
|
*/
|
|
|
|
|
1994-08-21 05:27:42 +00:00
|
|
|
#ifndef _NETINET_TCP_TIMER_H_
|
|
|
|
#define _NETINET_TCP_TIMER_H_
|
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
/*
|
|
|
|
* The TCPT_REXMT timer is used to force retransmissions.
|
|
|
|
* The TCP has the TCPT_REXMT timer set whenever segments
|
|
|
|
* have been sent for which ACKs are expected but not yet
|
|
|
|
* received. If an ACK is received which advances tp->snd_una,
|
|
|
|
* then the retransmit timer is cleared (if there are no more
|
|
|
|
* outstanding segments) or reset to the base value (if there
|
|
|
|
* are more ACKs expected). Whenever the retransmit timer goes off,
|
|
|
|
* we retransmit one unacknowledged segment, and do a backoff
|
|
|
|
* on the retransmit timer.
|
|
|
|
*
|
|
|
|
* The TCPT_PERSIST timer is used to keep window size information
|
|
|
|
* flowing even if the window goes shut. If all previous transmissions
|
|
|
|
* have been acknowledged (so that there are no retransmissions in progress),
|
|
|
|
* and the window is too small to bother sending anything, then we start
|
|
|
|
* the TCPT_PERSIST timer. When it expires, if the window is nonzero,
|
|
|
|
* we go to transmit state. Otherwise, at intervals send a single byte
|
|
|
|
* into the peer's window to force him to update our window information.
|
|
|
|
* We do this at most as often as TCPT_PERSMIN time intervals,
|
|
|
|
* but no more frequently than the current estimate of round-trip
|
|
|
|
* packet time. The TCPT_PERSIST timer is cleared whenever we receive
|
|
|
|
* a window update from the peer.
|
|
|
|
*
|
|
|
|
* The TCPT_KEEP timer is used to keep connections alive. If an
|
|
|
|
* connection is idle (no segments received) for TCPTV_KEEP_INIT amount of time,
|
|
|
|
* but not yet established, then we drop the connection. Once the connection
|
|
|
|
* is established, if the connection is idle for TCPTV_KEEP_IDLE time
|
|
|
|
* (and keepalives have been enabled on the socket), we begin to probe
|
|
|
|
* the connection. We force the peer to send us a segment by sending:
|
|
|
|
* <SEQ=SND.UNA-1><ACK=RCV.NXT><CTL=ACK>
|
|
|
|
* This segment is (deliberately) outside the window, and should elicit
|
|
|
|
* an ack segment in response from the peer. If, despite the TCPT_KEEP
|
|
|
|
* initiated segments we cannot elicit a response from a peer in TCPT_MAXIDLE
|
|
|
|
* amount of time probing, then we drop the connection.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Time constants.
|
|
|
|
*/
|
1999-08-30 21:17:07 +00:00
|
|
|
#define TCPTV_MSL ( 30*hz) /* max seg lifetime (hah!) */
|
1994-05-24 10:09:53 +00:00
|
|
|
#define TCPTV_SRTTBASE 0 /* base roundtrip time;
|
|
|
|
if 0, no idea yet */
|
1999-08-30 21:17:07 +00:00
|
|
|
#define TCPTV_RTOBASE ( 3*hz) /* assumed RTO if no info */
|
1994-05-24 10:09:53 +00:00
|
|
|
|
2016-01-26 16:33:38 +00:00
|
|
|
#define TCPTV_PERSMIN ( 5*hz) /* minimum persist interval */
|
1999-08-30 21:17:07 +00:00
|
|
|
#define TCPTV_PERSMAX ( 60*hz) /* maximum persist interval */
|
1994-05-24 10:09:53 +00:00
|
|
|
|
1999-08-30 21:17:07 +00:00
|
|
|
#define TCPTV_KEEP_INIT ( 75*hz) /* initial connect keepalive */
|
|
|
|
#define TCPTV_KEEP_IDLE (120*60*hz) /* dflt time before probing */
|
|
|
|
#define TCPTV_KEEPINTVL ( 75*hz) /* default probe interval */
|
1994-05-24 10:09:53 +00:00
|
|
|
#define TCPTV_KEEPCNT 8 /* max probes before drop */
|
|
|
|
|
2007-02-26 22:25:21 +00:00
|
|
|
#define TCPTV_FINWAIT2_TIMEOUT (60*hz) /* FIN_WAIT_2 timeout if no receiver */
|
|
|
|
|
2002-07-17 23:32:03 +00:00
|
|
|
/*
|
|
|
|
* Minimum retransmit timer is 3 ticks, for algorithmic stability.
|
2002-07-18 19:06:12 +00:00
|
|
|
* TCPT_RANGESET() will add another TCPTV_CPU_VAR to deal with
|
|
|
|
* the expected worst-case processing variances by the kernels
|
|
|
|
* representing the end points. Such variances do not always show
|
|
|
|
* up in the srtt because the timestamp is often calculated at
|
|
|
|
* the interface rather then at the TCP layer. This value is
|
|
|
|
* typically 50ms. However, it is also possible that delayed
|
|
|
|
* acks (typically 100ms) could create issues so we set the slop
|
|
|
|
* to 200ms to try to cover it. Note that, properly speaking,
|
|
|
|
* delayed-acks should not create a major issue for interactive
|
2004-08-16 18:32:07 +00:00
|
|
|
* environments which 'P'ush the last segment, at least as
|
2002-07-18 19:06:12 +00:00
|
|
|
* long as implementations do the required 'at least one ack
|
|
|
|
* for every two packets' for the non-interactive streaming case.
|
|
|
|
* (maybe the RTO calculation should use 2*RTT instead of RTT
|
|
|
|
* to handle the ack-every-other-packet case).
|
|
|
|
*
|
|
|
|
* The prior minimum of 1*hz (1 second) badly breaks throughput on any
|
|
|
|
* networks faster then a modem that has minor (e.g. 1%) packet loss.
|
2002-07-17 23:32:03 +00:00
|
|
|
*/
|
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
|
|
|
#define TCPTV_MIN ( hz/33 ) /* minimum allowable value */
|
2002-07-18 19:06:12 +00:00
|
|
|
#define TCPTV_CPU_VAR ( hz/5 ) /* cpu variance allowed (200ms) */
|
1999-08-30 21:17:07 +00:00
|
|
|
#define TCPTV_REXMTMAX ( 64*hz) /* max allowable REXMT value */
|
1994-05-24 10:09:53 +00:00
|
|
|
|
1995-02-08 20:18:48 +00:00
|
|
|
#define TCPTV_TWTRUNC 8 /* RTO factor to truncate TW */
|
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
#define TCP_LINGERTIME 120 /* linger at most 2 minutes */
|
|
|
|
|
|
|
|
#define TCP_MAXRXTSHIFT 12 /* maximum retransmits */
|
|
|
|
|
2012-10-29 12:17:02 +00:00
|
|
|
#define TCPTV_DELACK ( hz/10 ) /* 100ms timeout */
|
1999-08-30 21:17:07 +00:00
|
|
|
|
2017-02-11 17:05:08 +00:00
|
|
|
/*
|
|
|
|
* If we exceed this number of retransmits for a single segment, we'll consider
|
|
|
|
* the current srtt measurement no longer valid and will recalculate from
|
|
|
|
* scratch starting with the next ACK.
|
|
|
|
*/
|
|
|
|
#define TCP_RTT_INVALIDATE (TCP_MAXRXTSHIFT / 4)
|
|
|
|
|
1994-05-24 10:09:53 +00:00
|
|
|
#ifdef TCPTIMERS
|
2002-08-16 09:07:59 +00:00
|
|
|
static const char *tcptimers[] =
|
2012-11-27 19:07:28 +00:00
|
|
|
{ "REXMT", "PERSIST", "KEEP", "2MSL", "DELACK" };
|
1994-05-24 10:09:53 +00:00
|
|
|
#endif
|
|
|
|
|
2007-04-11 14:08:42 +00:00
|
|
|
/*
|
|
|
|
* Force a time value to be in a certain range.
|
|
|
|
*/
|
|
|
|
#define TCPT_RANGESET(tv, value, tvmin, tvmax) do { \
|
|
|
|
(tv) = (value) + tcp_rexmit_slop; \
|
|
|
|
if ((u_long)(tv) < (u_long)(tvmin)) \
|
|
|
|
(tv) = (tvmin); \
|
|
|
|
if ((u_long)(tv) > (u_long)(tvmax)) \
|
|
|
|
(tv) = (tvmax); \
|
|
|
|
} while(0)
|
|
|
|
|
|
|
|
#ifdef _KERNEL
|
|
|
|
|
2009-09-16 05:33:15 +00:00
|
|
|
struct xtcp_timer;
|
|
|
|
|
2007-09-24 05:26:24 +00:00
|
|
|
struct tcp_timer {
|
|
|
|
struct callout tt_rexmt; /* retransmit timer */
|
|
|
|
struct callout tt_persist; /* retransmit persistence */
|
|
|
|
struct callout tt_keep; /* keepalive */
|
|
|
|
struct callout tt_2msl; /* 2*msl TIME_WAIT timer */
|
|
|
|
struct callout tt_delack; /* delayed ACK timer */
|
2015-04-16 10:00:06 +00:00
|
|
|
uint32_t tt_flags; /* Timers flags */
|
2016-04-28 13:27:12 +00:00
|
|
|
uint32_t tt_draincnt; /* Count being drained */
|
2007-09-24 05:26:24 +00:00
|
|
|
};
|
2015-04-16 10:00:06 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags for the tt_flags field.
|
|
|
|
*/
|
|
|
|
#define TT_DELACK 0x0001
|
|
|
|
#define TT_REXMT 0x0002
|
|
|
|
#define TT_PERSIST 0x0004
|
|
|
|
#define TT_KEEP 0x0008
|
|
|
|
#define TT_2MSL 0x0010
|
|
|
|
#define TT_MASK (TT_DELACK|TT_REXMT|TT_PERSIST|TT_KEEP|TT_2MSL)
|
|
|
|
|
2015-08-30 13:44:39 +00:00
|
|
|
#define TT_DELACK_RST 0x0100
|
|
|
|
#define TT_REXMT_RST 0x0200
|
|
|
|
#define TT_PERSIST_RST 0x0400
|
|
|
|
#define TT_KEEP_RST 0x0800
|
|
|
|
#define TT_2MSL_RST 0x1000
|
|
|
|
|
2015-04-16 10:00:06 +00:00
|
|
|
#define TT_STOPPED 0x00010000
|
2007-04-11 09:45:16 +00:00
|
|
|
|
2012-02-05 16:53:02 +00:00
|
|
|
#define TP_KEEPINIT(tp) ((tp)->t_keepinit ? (tp)->t_keepinit : tcp_keepinit)
|
|
|
|
#define TP_KEEPIDLE(tp) ((tp)->t_keepidle ? (tp)->t_keepidle : tcp_keepidle)
|
|
|
|
#define TP_KEEPINTVL(tp) ((tp)->t_keepintvl ? (tp)->t_keepintvl : tcp_keepintvl)
|
|
|
|
#define TP_KEEPCNT(tp) ((tp)->t_keepcnt ? (tp)->t_keepcnt : tcp_keepcnt)
|
|
|
|
#define TP_MAXIDLE(tp) (TP_KEEPCNT(tp) * TP_KEEPINTVL(tp))
|
|
|
|
|
2016-01-26 16:33:38 +00:00
|
|
|
extern int tcp_persmin; /* minimum persist interval */
|
|
|
|
extern int tcp_persmax; /* maximum persist interval */
|
1996-09-13 23:51:44 +00:00
|
|
|
extern int tcp_keepinit; /* time to establish connection */
|
1994-05-24 10:09:53 +00:00
|
|
|
extern int tcp_keepidle; /* time before keepalive probes begin */
|
1999-08-30 21:17:07 +00:00
|
|
|
extern int tcp_keepintvl; /* time between keepalive probes */
|
2012-02-05 16:53:02 +00:00
|
|
|
extern int tcp_keepcnt; /* number of keepalives */
|
1999-08-30 21:17:07 +00:00
|
|
|
extern int tcp_delacktime; /* time before sending a delayed ACK */
|
|
|
|
extern int tcp_maxpersistidle;
|
2002-07-18 19:06:12 +00:00
|
|
|
extern int tcp_rexmit_min;
|
|
|
|
extern int tcp_rexmit_slop;
|
1999-08-30 21:17:07 +00:00
|
|
|
extern int tcp_msl;
|
1994-05-24 10:09:53 +00:00
|
|
|
extern int tcp_ttl; /* time to live for TCP segs */
|
|
|
|
extern int tcp_backoff[];
|
2012-10-28 19:02:07 +00:00
|
|
|
extern int tcp_syn_backoff[];
|
1994-08-21 05:27:42 +00:00
|
|
|
|
2007-02-26 22:25:21 +00:00
|
|
|
extern int tcp_finwait2_timeout;
|
|
|
|
extern int tcp_fast_finwait2_recycle;
|
|
|
|
|
2017-10-06 20:33:40 +00:00
|
|
|
VNET_DECLARE(int, tcp_pmtud_blackhole_detect);
|
|
|
|
#define V_tcp_pmtud_blackhole_detect VNET(tcp_pmtud_blackhole_detect)
|
|
|
|
VNET_DECLARE(int, tcp_pmtud_blackhole_mss);
|
|
|
|
#define V_tcp_pmtud_blackhole_mss VNET(tcp_pmtud_blackhole_mss)
|
|
|
|
VNET_DECLARE(int, tcp_v6pmtud_blackhole_mss);
|
|
|
|
#define V_tcp_v6pmtud_blackhole_mss VNET(tcp_v6pmtud_blackhole_mss)
|
|
|
|
|
2016-08-16 12:40:56 +00:00
|
|
|
int tcp_inpinfo_lock_add(struct inpcb *inp);
|
|
|
|
void tcp_inpinfo_lock_del(struct inpcb *inp, struct tcpcb *tp);
|
|
|
|
|
2003-03-08 22:06:20 +00:00
|
|
|
void tcp_timer_init(void);
|
2007-09-07 09:19:22 +00:00
|
|
|
void tcp_timer_2msl(void *xtp);
|
2016-04-28 13:27:12 +00:00
|
|
|
void tcp_timer_discard(void *);
|
2007-05-16 17:14:25 +00:00
|
|
|
struct tcptw *
|
2014-10-30 08:53:56 +00:00
|
|
|
tcp_tw_2msl_scan(int reuse); /* XXX temporary? */
|
2007-09-07 09:19:22 +00:00
|
|
|
void tcp_timer_keep(void *xtp);
|
|
|
|
void tcp_timer_persist(void *xtp);
|
|
|
|
void tcp_timer_rexmt(void *xtp);
|
|
|
|
void tcp_timer_delack(void *xtp);
|
1999-08-30 21:17:07 +00:00
|
|
|
|
1999-12-29 04:46:21 +00:00
|
|
|
#endif /* _KERNEL */
|
1999-08-30 21:17:07 +00:00
|
|
|
|
|
|
|
#endif /* !_NETINET_TCP_TIMER_H_ */
|