Extend the so far IPv4-only support for multiple routing tables (FIBs)
introduced in r178888 to IPv6 providing feature parity.
This includes an extended rtalloc(9) KPI for IPv6, the necessary
adjustments to the network stack, and user land support as in netstat.
Sponsored by: Cisco Systems, Inc.
Reviewed by: melifaro (basically)
MFC after: 10 days
M_NOWAIT. Currently, the code allows for sleeping in the ioctl path
to guarantee allocation. However code also handles ENOMEM gracefully, so
propagate this error back to user-space, rather than sleeping while
holding the global pf mutex.
Reviewed by: glebius
Discussed with: bz
- Define schednetisr() to swi_sched.
- In the swi handler check if there is some data prepared,
and if true, then call pfsync_sendout(), however tell it
not to schedule swi again.
- Since now we don't obtain the pfsync lock in the swi handler,
don't use ifqueue mutex to synchronize queue access.
revision 1.128
date: 2009/08/16 13:01:57; author: jsg; state: Exp; lines: +1 -5
remove prototypes of a bunch of functions that had their implementations
removed in pfsync v5.
o Make the pfsync.ko actually usable. Before this change loading it
didn't register protosw, so was a nop. However, a module /boot/kernel
did confused users.
o Rewrite the way we are joining multicast group:
- Move multicast initialization/destruction to separate functions.
- Don't allocate memory if we aren't going to join a multicast group.
- Use modern API for joining/leaving multicast group.
- Now the utterly wrong pfsync_ifdetach() isn't needed.
o Move module initialization from SYSINIT(9) to moduledata_t method.
o Refuse to unload module, unless asked forcibly.
o Improve a bit some FreeBSD porting code:
- Use separate malloc type.
- Simplify swi sheduling.
This change is probably wrong from VIMAGE viewpoint, however pfsync
wasn't VIMAGE-correct before this change, too.
Glanced at by: bz
destroyed prior to pfsync_uninit(). To do this, move all the
initialization to the module_t method, instead of SYSINIT(9).
o Fix another panic after module unload, due to not clearing the
m_addr_chg_pf_p pointer.
o Refuse to unload module, unless being unloaded forcibly.
o Revert the sub argument to MODULE_DECLARE, to the stable/8 value.
This change probably isn't correct from viewpoint of VIMAGE, but
the module wasn't VIMAGE-correct before the change, as well.
Glanced at by: bz
revision 1.170
date: 2011/10/30 23:04:38; author: mikeb; state: Exp; lines: +6 -7
Allow setting big MTU values on the pfsync interface but not larger
than the syncdev MTU. Prompted by the discussion with and tested
by Maxim Bourmistrov; ok dlg, mpf
Consistently use sc_ifp->if_mtu in the MTU check throughout the
module. This backs out r228813.
value used in sys/ofed/include/linux/netdevice.h), so there will be no
buffer overruns in the rest of the inline functions in this file.
Reviewed by: kmacy
MFC after: 1 week
revision 1.122
date: 2009/05/13 01:01:34; author: dlg; state: Exp; lines: +6 -4
only keep track of the number of updates on tcp connections. state sync on
all the other protocols is simply pushing the timeouts along which has a
resolution of 1 second, so it isnt going to be hurt by pfsync taking up
to a second to send it over.
keep track of updates on tcp still though, their windows need constant
attention.
revision 1.120
date: 2009/04/04 13:09:29; author: dlg; state: Exp; lines: +5 -5
use time_uptime instead of time_second internally. time_uptime isnt
affected by adjusting the clock.
revision 1.175
date: 2011/11/25 12:52:10; author: dlg; state: Exp; lines: +3 -3
use time_uptime to set state creation values as time_second can be
skewed at runtime by things like date(1) and ntpd. time_uptime is
monotonic and therefore more useful to compare against.
revision 1.118
date: 2009/03/23 06:19:59; author: dlg; state: Exp; lines: +8 -6
wait an appropriate amount of time before giving up on a bulk update,
rather than giving up after a hardcoded 5 seconds (which is generally much
too short an interval for a bulk update).
pointed out by david@, eyeballed by mcbride@
revision 1.171
date: 2011/10/31 22:02:52; author: mikeb; state: Exp; lines: +2 -1
Don't forget to cancel bulk update failure timeout when destroying an
interface. Problem report and fix from Erik Lax, thanks!
Start a brief note of revisions merged from OpenBSD.
7.x, 8.x and 9.x with pf(4) imports: pfsync(4) should suppress CARP
preemption, while it is running its bulk update.
However, reimplement the feature in more elegant manner, that is
partially inspired by newer OpenBSD:
- Rename term "suppression" to "demotion", to match with OpenBSD.
- Keep a global demotion factor, that can be raised by several
conditions, for now these are:
- interface goes down
- carp(4) has problems with ip_output() or ip6_output()
- pfsync performs bulk update
- Unlike in OpenBSD the demotion factor isn't a counter, but
is actual value added to advskew. The adjustment values for
particular error conditions are also configurable, and their
defaults are maximum advskew value, so a single failure bumps
demotion to maximum. This is for POLA compatibility, and should
satisfy most users.
- Demotion factor is a writable sysctl, so user can do
foot shooting, if he desires to.
of scheduling next run pfsync_bulk_update(), pfsync_bulk_fail()
was scheduled.
This lead to instant 100% state leak after first bulk update
request.
- After above fix, it appeared that pfsync_bulk_update() lacks
locking. To fix this, sc_bulk_tmo callout was converted to an
mtx one. Eventually, all pf/pfsync callouts should be converted
to mtx version, since it isn't possible to stop or drain a
non-mtx callout without risk of race.
- Add comment that callout_stop() in pfsync_clone_destroy() lacks
locking. Since pfsync0 can't be destroyed (yet), let it be here.
The root of problem is re-locking at the end of pfsync_sendout().
Several functions are calling pfsync_sendout() holding pointers
to pf data on stack, and these functions expect this data to be
consistent.
To fix this, the following approach was taken:
- The pfsync_sendout() doesn't call ip_output() directly, but
enqueues the mbuf on sc->sc_ifp's interfaces queue, that
is currently unused. Then pfsync netisr is scheduled. PF_LOCK
isn't dropped in pfsync_sendout().
- The netisr runs through queue and ip_output()s packets
on it.
Apart from fixing race, this also decouples stack, fixing
potential issues, that may happen, when sending pfsync(4)
packets on input path.
Reviewed by: eri (a quick review)
number of packets can be queued on sc, while we are in ip_output(), and then
we wipe the accumulated sc_len. On next pfsync_sendout() that would lead to
writing beyond our mbuf cluster.
to document where we are expecting to be called with a lock held to
more easily catch unnoticed code paths.
This does not neccessarily improve locking in pfsync, it just tries
to avoid the panics reported.
PR: kern/159390, kern/158873
Submitted by: pluknet (at least something that partly resembles
my patch ignoring other cleanup, which I only saw
too late on the 2nd PR)
MFC After: 3 days
and virtualization it is not helpful but complicates things.
Current state of art is to not virtualize these kinds of locks -
inp_group/hash/info/.. are all not virtualized either.
MFC after: 3 days