Commit Graph

46 Commits

Author SHA1 Message Date
mav
10741a6f2e Remove duplicate check.
Submitted by:	Dmitry Luhtionov <dmitryluhtionov@gmail.com>
2012-08-03 12:55:31 +00:00
glebius
6c78a88c3b Node constructor methods are supposed to be called in syscall
context always. Convert nodes to consistently use M_WAITOK flag
for memory allocation.

Reviewed by:	julian
2011-04-18 09:12:27 +00:00
mav
25d136f686 Remove alignment constraints. 2010-04-01 16:20:36 +00:00
des
66f807ed8b Retire the MALLOC and FREE macros. They are an abomination unto style(9).
MFC after:	3 months
2008-10-23 15:53:51 +00:00
mav
5b9ac353f2 Some minor code and math optimizations. 2008-03-26 21:19:03 +00:00
mav
9af7fc155d Rewrite node to support multiple hooks, alike to ng_l2tp, to use one pair
of pptpgre and ksocket nodes for all calls between two peers. This patch
modifies node's API by adding new "session_%04x" hook names support, while
keeping backward compatibility.

Together with appropriate user-level support (by latest mpd5) it gives
huge performance benefits for case of multiple active calls between
two peers because of avoiding data duplication and extra socket processing.
On my benchmarks I have got more then 10 times speedup for the 200
simultaneous PPTP calls between two peers.
In conclusion, it allows now to build effective "clients <=> PAC <=> PNS"
setups.
2008-03-24 22:55:22 +00:00
glebius
fd07387e04 Quoting Alexander:
Formulas described in RFC require high precision of floating point.
  Formulas of integer math implemented in ng_pptpgre give mistake in range
  of +0-7ms on RTT and +0-3ms on deviation. This leads to significant
  underestimation of real packet RTT.

  I have made a very simple patch to reduce mistake to +4-3ms on RTT and
  +2-1ms on deviation. Mistake in RTT is not good, but gets covered by
  deviation. To cover worst possible negative mistake in deviation I have
  added 2ms to it. Also this 2 ms cover the case when measured deviation
  is so small (about zero) that it can interfere with process scheduling
  delays or weather on Mars.

  My tests show decreasing of packet losses on 20ms RTT link from 2.5% to
  0.3% while speed increased un 1/3.

Reviewed by:	archie
2007-02-02 09:45:23 +00:00
glebius
0743267ea6 Rework locking, that I have introduced recently, since it was incorrect:
First, mutexed callouts are incompatible with netgraph nodes, because
  netgraph(4) can guarantee that the function will be called with mutex
  held.

  Second, nodes should not send data to their neighbor holding their
  mutex. A node does not know what stack can it enter sending data in
  some direction. May be executing will encounter a place to sleep.

New locking:

  - ng_pptpgre_recv() and ng_pptpgre_xmit() must be entered with mutex held.
  - ng_pptpgre_recv() and ng_pptpgre_xmit() unlock mutex before
    sending data and then return unlocked.
  - callout routines acquire mutex themselves.
2005-09-08 14:26:23 +00:00
glebius
d066ce1d4b Lock down PPTP node, since it has many data structures, that won't survive
parallel ng_pptp_rcvdata():

- Add a per-node mutex.
- Acquire mutex during all ng_pptp_rcvdata() method.
- Make callouts protected by mutex. Now callouts count as
  netgraph writers, but there are plans to allow reader callouts
  for nodes, that have internal locking.
- Acquire mutex in ng_pptp_reset(), which can be triggered
  by a message or node shutdown.

PR:		kern/80035
Tested by:	Deomid Ryabkov <myself rojer.pp.ru>
Reviewed by:	Deomid Ryabkov <myself rojer.pp.ru>
2005-08-30 09:51:54 +00:00
glebius
ab09c82551 Utilize callout_pending() macro 2005-01-11 12:20:28 +00:00
imp
a50ffc2912 /* -> /*- for license, minor formatting changes 2005-01-07 01:45:51 +00:00
glebius
ce23ffb82d Use ng_callout() and ng_uncallout() instead of home-grown
implementation.

Tested by:	Savchuk Taras
Reviewed by:	archie
Approved by:	julian (mentor)
2004-12-09 07:49:02 +00:00
glebius
f3d4554e29 Increase PPTP_MAX_TIMEOUT up to 3 seconds. 10 prooved too much for high packet
loss links, and 1 second appeared to be too small for high latency links.

If we will receive more complaints, we should make this parameter configurable.

PR:		kern/69536
Approved by:	archie, julian (mentor)
MFC after:	3 days
2004-09-06 19:53:58 +00:00
julian
c85e63d425 Switch to using C99 sparse initialisers for the type methods array.
Should make no binary difference.

Submitted by:	Gleb Smirnoff <glebius@cell.sick.ru>
Reviewed by:	Harti Brandt <harti@freebsd.org>
MFC after:	1 week
2004-05-29 00:51:19 +00:00
archie
590a18f52c Add 'enableWindowing' configuration knob to the ng_pptpgre(4) netgraph node.
Submitted by:	Michael Bretterklieber <mbretter@a-quadrat.at>
MFC after:	2 weeks
2004-04-26 14:26:54 +00:00
archie
7328a76791 Lower the maximum ACK timeout for GRE packets from 10 to 1 second.
In practice it seems that in situations of high packet loss the ACK
timeout seems to hit this maximum (perhaps inappropriately, but the
estimation algorithm is not perfect, so apparently it happens). In
any case, 10 seconds is way too high a value so lower to 1 second.

MFC after:	3 days
2003-11-18 20:43:23 +00:00
des
c011a79e99 Don't use ovbcopy(). 2003-04-04 12:12:34 +00:00
imp
cf874b345d Back out M_* changes, per decision of the TRB.
Approved by: trb
2003-02-19 05:47:46 +00:00
alfred
bf8e8a6e8f Remove M_TRYWAIT/M_WAITOK/M_WAIT. Callers should use 0.
Merge M_NOWAIT/M_DONTWAIT into a single flag M_NOWAIT.
2003-01-21 08:56:16 +00:00
bmilekic
514c635ee6 o Untangle the confusion with the malloc flags {M_WAITOK, M_NOWAIT} and
the mbuf allocator flags {M_TRYWAIT, M_DONTWAIT}.
o Fix a bpf_compat issue where malloc() was defined to just call
  bpf_alloc() and pass the 'canwait' flag(s) along.  It's been changed
  to call bpf_alloc() but pass the corresponding M_TRYWAIT or M_DONTWAIT
  flag (and only one of those two).

Submitted by: Hiten Pandya <hiten@unixdaemons.com> (hiten->commit_count++)
2002-12-19 22:58:27 +00:00
archie
8e0a543689 Relax checking of incoming PPTP GRE packets a bit: ignore a bogus payload
length field when there's no payload indicated by the header 'S' bit.
This works around semi-brokenness in the Mac OS X PPTP client.
2002-09-14 00:00:49 +00:00
archie
d14167a565 Const'ify variables to make it clear we're not writing to the mbuf data.
Reviewed by:	julian, brian
MFC after:	1 week
2002-06-05 23:35:31 +00:00
archie
b10887dc2b Fix GCC warnings caused by initializing a zero length array. In the process,
simply things a bit by getting rid of 'struct ng_parse_struct_info' which
was useless because it only contained one field.

MFC after:	2 weeks
2002-05-31 23:48:03 +00:00
archie
659c75a369 Use 'struct callout' instead of 'struct callout_handle' to avoid
exhausting the kernel timeout table. Perform the usual gymnastics to
avoid race conditions between node shutdown and timeouts occurring.

Also fix a bug in handling ack delays < PPTP_MIN_ACK_DELAY. Before,
we were ack'ing immediately. Instead, just impose a minimum ack delay
time, like the name of the macro implies.

MFC after:	1 week
2002-04-14 17:37:35 +00:00
obrien
7fd9a6a23a Update to C99, s/__FUNCTION__/__func__/,
also don't use ANSI string concatenation.
2001-12-10 08:09:49 +00:00
archie
94db785410 Don't reference a node after we dropped a reference to it
(same as in previous checkin, but in a different function).
2001-04-11 22:04:47 +00:00
julian
2b70619e17 netgraph.h:
Change a prototype.
  Add a function version of ng_ref_node() when debugging so
  a breakpoint can be set on it.
ng_base.c:
  add 'node' as an argument to ng_apply_item so that it is up
  to the caller to take over and release the item's reference on
  the node. If the release reports back that the node went away
  due to the reference going to 0, the caller should cease referencing
  the now defunct node. (e.g. the item was a 'kill node' message).
  Alter ng_unref_node to report back the residual references as a result.
ng_pptpgre.c:
  Don't reference a node after we dropped a reference to it.
  (What if it was the last?)
Fixes a node leak reported by Harti Brandt <brandt@fokus.gmd.de>
 which was due to an incorrect earlier attempt to fix the
 "accessing node after dropping the last reference" problem.
2001-03-10 16:31:00 +00:00
archie
4010cd1c76 Fix potential crash caused by packets with bogus ACK's.
Reported by:	Fabien THOMAS <fabient@netasq.com>
2001-03-08 20:10:02 +00:00
julian
ff86256bf7 Part 2 of the netgraph rewrite.
This is mostly cosmetic changes, (though I caught a bug or two while
makeing them)
Reviewed by:	archie@freebsd.org
2001-01-08 05:34:06 +00:00
julian
f0c46a9d00 Rewrite of netgraph to start getting ready for SMP.
This version is functional and is aproaching solid..
notice I said APROACHING. There are many node types I cannot test
I have tested: echo hole ppp socket vjc iface tee bpf async tty
The rest compile and "Look" right.  More changes to follow.
DEBUGGING is enabled in this code to help if people have problems.
2001-01-06 00:46:47 +00:00
julian
0c949560a1 Divorce the kernel binary ABI version number from the message
format version number. (userland programs should not need to be
recompiled when the netgraph kernel internal ABI is changed.

Also fix modules that don;t handle the fact that a caller may not supply
a return message pointer. (benign at the moment because the calling code
checks, but that will change)
2000-12-18 20:03:32 +00:00
julian
2d1192e612 Reviewed by: Archie@freebsd.org
This clears out my outstanding netgraph changes.
There is a netgraph change of design in the offing and this is to some
extent a superset of soem of the new functionality and some of the old
functionality that may be removed.

This code works as before, but allows some new features that I want to
work with and evaluate. It is the basis for a version of netgraph
with integral locking for SMP use.

This is running on my test machine with no new problems :-)
2000-12-12 18:52:14 +00:00
dwmalone
918549eb31 Add the use of M_ZERO to netgraph.
Submitted by:	josh@zipperup.org
Submitted by:	Robert Drehmel <robd@gmx.net>
Submitted by:	archie
Approved by:	archie
2000-11-18 15:17:43 +00:00
julian
bf2394b8d4 Since neither archie nor I work at Whistle any more, change our email
addresses to be the more usefu @freebsd.org ones
so we can keep getting bug-reports.
- man pages to follow..
2000-10-24 17:32:45 +00:00
archie
2eb0a98177 Calling untimeout(9) leads to a race window where memory could be leaked.
Close this window by simply not calling untimeout(9).
2000-10-11 20:29:12 +00:00
archie
63c14c2c25 Remove unnecessary #include's as reported by phk's script. 2000-09-22 16:51:14 +00:00
archie
1023c32e1a Allocate all memory (including within node constructors) with M_NOWAIT
instead of M_WAITOK, to allow for maximum flexibility.
2000-09-21 18:01:23 +00:00
archie
044c01152e Followup to previous commit..
- It's worthwhile to use untimeout(9), even though we must still protect
  against "false" timeouts, because most of the time it saves having to
  handle a dummy timeout event.
- Slight tweaks to the delayed ACK algorithm paramters.
2000-07-25 18:57:20 +00:00
archie
02b7ccf840 Several fixes:
- Fix slowness when operating over fast connections, where the timeout(9)
  granularity is on the same order of magnitude as the round trip time.
  timeout(9) can happen up to 1 tick early, which was causing receive
  ack timeouts to happen too early, causing bogus "lost" packets.
- Increase the local time counter to 64 bits to avoid roll-over.
- Keep statistics on memory allocation failures.
- Add a new option to always include the ack when sending data packets.
  Might be useful in high packet loss situations. Might not.
2000-07-25 00:23:19 +00:00
archie
9997aef57d Fix incorrectly implemented receive ACK timeout algorithm:
instead of bumping the recvAck counter by one, pretend that
all outstanding xmit packets are acknowleged, and restart
transmitting anew, with an empty (but halved) transmit window.

Put a lower bound on the adaptive timeout value.
2000-06-28 19:43:34 +00:00
archie
90a17e36f6 - Start sequence numbers at zero instead of one; the rest of the
world seems to interpret the spec this way
- Initialize transmit window to two instead of one; helps get things
  going initially when the first packet may get dropped
- Really fix the shutdown + timeout race condition this time
2000-06-26 19:43:24 +00:00
archie
67e7422842 Fix a couple of bugs:
- Properly handle 32 bit sequence numbers when they wrap around
- Don't drop GRE packets with stale ACK numbers, just ignore the ACK
- Close race between node being shutdown and timer going off
Also add support for lots of statistics, and control message ASCIIfication
2000-05-05 01:11:39 +00:00
julian
49604b4259 Two simple changes to the kernel internal API for netgraph modules,
to support future work in flow-control and 'packet reject/replace'
processing modes.

reviewed by: phk, archie
2000-04-28 17:09:00 +00:00
phk
6be1308ad1 Remove ~25 unneeded #include <sys/conf.h>
Remove ~60 unneeded #include <sys/malloc.h>
2000-04-19 14:58:28 +00:00
archie
4f702e355c Fix race condition caused by missing splnet()'s. 2000-01-04 22:06:08 +00:00
archie
086ca8f5bd New netgraph node type 'pptpgre': this performs GRE encapsulation
for the PPTP protocol as specified in RFC 2637.
1999-12-08 18:55:39 +00:00