Commit Graph

203 Commits

Author SHA1 Message Date
Gleb Smirnoff
90b357f6ec M_DONTWAIT is a flag from historical mbuf(9)
allocator, not malloc(9) or uma(9) flag.
2012-04-10 06:52:39 +00:00
Kip Macy
a93cda789a When using flowtable llentrys can outlive the interface with which they're associated
at which the lle_tbl pointer points to freed memory and the llt_free pointer is no longer
valid.

Move the free pointer in to the llentry itself and update the initalization sites.

MFC after:	2 weeks
2012-02-23 18:21:37 +00:00
Bjoern A. Zeeb
81d5d46b3c Add multi-FIB IPv6 support to the core network stack supplementing
the original IPv4 implementation from r178888:

- Use RT_DEFAULT_FIB in the IPv4 implementation where noticed.
- Use rt*fib() KPI with explicit RT_DEFAULT_FIB where applicable in
  the NFS code.
- Use the new in6_rt* KPI in TCP, gif(4), and the IPv6 network stack
  where applicable.
- Split in6_rtqtimo() and in6_mtutimo() as done in IPv4 and equally
  prevent multiple initializations of callouts in in6_inithead().
- Use wrapper functions where needed to preserve the current KPI to
  ease MFCs.  Use BURN_BRIDGES to indicate expected future cleanup.
- Fix (related) comments (both technical or style).
- Convert to rtinit() where applicable and only use custom loops where
  currently not possible otherwise.
- Multicast group, most neighbor discovery address actions and faith(4)
  are locked to the default FIB.  Individual IPv6 addresses will only
  appear in the default FIB, however redirect information and prefixes
  of connected subnets are automatically propagated to all FIBs by
  default (mimicking IPv4 behavior as closely as possible).

Sponsored by:	Cisco Systems, Inc.
2012-02-03 13:08:44 +00:00
Gleb Smirnoff
56cf9dc1f6 Drop support for SIOCSIFADDR, SIOCSIFNETMASK, SIOCSIFBRDADDR, SIOCSIFDSTADDR
ioctl commands.

PR:		163524
Reviewed by:	net
2012-01-16 09:53:24 +00:00
John Baldwin
137f91e80f Convert all users of IF_ADDR_LOCK to use new locking macros that specify
either a read lock or write lock.

Reviewed by:	bz
MFC after:	2 weeks
2012-01-05 19:00:36 +00:00
John Baldwin
0f188ebb1d Use a helper variable to wrap a long line. 2012-01-04 13:29:26 +00:00
John Baldwin
56d6e1292d In the handling of the SIOC[DG]LIFADDR icotls in in_lifaddr_ioctl(), add
missing interface address list locking and grab a reference on the
matching interface address after dropping the lock while it is used to
avoid a potential use after free.

Reviewed by:	bz
MFC after:	1 week
2012-01-04 13:26:56 +00:00
John Baldwin
0823c29b81 Fix the SIOC[DG]LIFADDR ioctls in in_lifaddr_ioctl() to work with IPv4
interface address rather than IPv6.

Submitted by:	hrs
Reviewed by:	bz
MFC after:	1 week
2012-01-04 13:23:51 +00:00
Gleb Smirnoff
7121247312 Provide ABI compatibility shim to enable configuring of addresses
with ifconfig(8) prior to r228571.

Requested by:	brooks
2011-12-21 12:39:08 +00:00
Gleb Smirnoff
92ed4e1a24 Since size of struct in_aliasreq has just been changed in r228571,
and thus ifconfig(8) needs recompile, it is a good chance to make
parameter checks on SIOCAIFADDR arguments more strict.
2011-12-16 13:30:17 +00:00
Gleb Smirnoff
08b68b0e4c A major overhaul of the CARP implementation. The ip_carp.c was started
from scratch, copying needed functionality from the old implemenation
on demand, with a thorough review of all code. The main change is that
interface layer has been removed from the CARP. Now redundant addresses
are configured exactly on the interfaces, they run on.

The CARP configuration itself is, as before, configured and read via
SIOCSVH/SIOCGVH ioctls. A new prefix created with SIOCAIFADDR or
SIOCAIFADDR_IN6 may now be configured to a particular virtual host id,
which makes the prefix redundant.

ifconfig(8) semantics has been changed too: now one doesn't need
to clone carpXX interface, he/she should directly configure a vhid
on a Ethernet interface.

To supply vhid data from the kernel to an application the getifaddrs(8)
function had been changed to pass ifam_data with each address. [1]

The new implementation definitely closes all PRs related to carp(4)
being an interface, and may close several others. It also allows
to run a single redundant IP per interface.

Big thanks to Bjoern Zeeb for his help with inet6 part of patch, for
idea on using ifam_data and for several rounds of reviewing!

PR:		kern/117000, kern/126945, kern/126714, kern/120130, kern/117448
Reviewed by:	bz
Submitted by:	bz [1]
2011-12-16 12:16:56 +00:00
Gleb Smirnoff
55174c34ef Belatedly catch up with r151555. in_scrubprefix() also needs this fix. We
should compare not only addresses, but their masks, too, when searching
for matching prefix.
2011-12-13 06:56:43 +00:00
Gleb Smirnoff
f769e5b0fa Fix a very special case when SIOCAIFADDR supplies mask of 0.0.0.0,
don't overwrite the mask with autoguessing based on classes.
2011-12-06 20:55:20 +00:00
Gleb Smirnoff
89b9325530 Fix one more fallout from r227791: do not overwrite trimmed sa_len
on the ia_sockmask when doing SIOCSIFNETMASK.

Reported by:	Stefan Bethke <stb lassitu.de>, gonzo
Pointy hat to:	glebius
2011-11-28 13:30:14 +00:00
Gleb Smirnoff
c6e5c71116 Remove superfluous check: SIOCAIFADDR must have ifra_addr supplied. 2011-11-24 22:46:11 +00:00
Gleb Smirnoff
bd47ae58a6 Fix stupid typo in r227830.
PR:		162806
Pointy hat to:	glebius
2011-11-24 22:43:48 +00:00
Gleb Smirnoff
e278f44bb5 style(9) nit 2011-11-22 19:39:27 +00:00
Gleb Smirnoff
bbaa3f944e Fix SIOCDIFADDR semantics: if no address is specified, then delete first one. 2011-11-22 19:37:57 +00:00
Gleb Smirnoff
cf00e5c6b7 This check isn't needed now, sanity checking done in the beginning.
Missed it in last commit.
2011-11-21 20:07:12 +00:00
Gleb Smirnoff
6d00fd9c2d Historically in_control() did not check sockaddrs supplied with
structs ifreq/in_aliasreq and there've been several panics due
to that problem. All these panics were fixed just a couple of
lines above the panicing code.

Take a more general approach: sanity check sockaddrs supplied
with SIOCAIFADDR and SIOCSIF*ADDR at the beggining of the
function and drop all checks below.

One check is now disabled due to strange code in ifconfig(8)
that I've removed recently. I'm going to enable it with next
__FreeBSD_version bump.

Historically in_ifinit() was able to recover from an error
and restore old address. Nowadays this feature isn't working
for all error cases, but for some of them. I suppose no software
relies on this behavior, so I'd like to remove it, since this
simplifies code a lot.

Also, move if_scrub() earlier in the in_ifinit(). It is more
correct to wipe routes before removing address from local
address list, and interface address list.

Silence from:	bz, brooks, andre, rwatson, 3 weeks
2011-11-21 14:10:13 +00:00
Qing Li
b3664a14cc Exclude host routes when checking for prefix coverage on multiple
interfaces. A host route has a NULL mask so check for that condition.
I have also been told by developers who customize the packet output
path with direct manipulation of the route entry (or the outgoing
interface to be specific). This patch checks for the route mask
explicitly to make sure custom code will not panic.

PR:		kern/161805
MFC after:	3 days
2011-10-25 04:06:29 +00:00
Gleb Smirnoff
53883e0c24 Add support for IPv4 /31 prefixes, as described in RFC3021.
To run a /31 network, participating hosts MUST drop support
for directed broadcasts, and treat the first and last addresses
on subnet as unicast. The broadcast address for the prefix
should be the link local broadcast address, INADDR_BROADCAST.
2011-10-15 18:41:25 +00:00
Gleb Smirnoff
b365d954cc Remove last remnants of classful addressing:
- Remove ia_net, ia_netmask, ia_netbroadcast from struct in_ifaddr.
- Remove net.inet.ip.subnetsarelocal, I bet no one need it in 2011.
- fix bug when we were not forwarding to a host which matches classful
  net address. For example router having 192.168.x.y/16 network attached,
  would not forward traffic to 192.168.*.0, which are legal IPs in
  CIDR world.
- For compatibility, leave autoguessing of mask based on class.

Reviewed by:	andre, bz, rwatson
2011-10-15 16:28:06 +00:00
Gleb Smirnoff
a0b5928b29 De-spl(9). 2011-10-13 13:30:41 +00:00
Qing Li
15d2521975 All indirect routes will fail the rtcheck, except for a special host
route where the destination IP and the gateway IP is the same. This
special case handling is only meant for backward compatibility reason.
The last commit introduced a bug in the route check logic, where a
valid special case is treated as an error. This patch fixes that bug
along with some code cleanup.

Suggested by:	gleb
Reviewed by:	kmacy, discussed with gleb
MFC after:	1 day
2011-10-10 17:41:11 +00:00
Qing Li
6703e7ea10 Do not try removing an ARP entry associated with a given interface
address if that interface does not support ARP. Otherwise the
system will generate error messages unnecessarily due to the missing
entry.

PR:		kern/159602
Submitted by:	pluknet
MFC after:	3 days
2011-10-07 22:22:19 +00:00
Qing Li
41b210c6f6 Remove the reference held on the loopback route when the interface
address is being deleted. Only the last reference holder deletes the
loopback route. All other delete operations just clear the IFA_RTSELF
flag.

PR:		kern/159601
Submitted by:	pluknet
Reviewed by:	discussed on net@
MFC after:	3 days
2011-10-07 18:01:34 +00:00
Qing Li
db92413e6a A system may have multiple physical interfaces, all of which are on the
same prefix. Since a single route entry is installed for the prefix
(without RADIX_MPATH), incoming packets on the interfaces that are not
associated with the prefix route may trigger an error message about
unable to allocation LLE entry, and fails L2. This patch makes sure a
valid route is present in the system, and allow the aforementioned
condition to exist and treats as valid.

Reviewed by:	bz
MFC after:	5 days
2011-10-03 19:51:18 +00:00
Qing Li
6cf8e3300e This patch allows ARP to work properly in the presence of
self-referencing routes. This patch is a rework of r223862.

Reviewed by:	bz, zec
MFC after:	5 days
2011-10-03 19:06:55 +00:00
Qing Li
1184509858 When an interface address route is removed from the system, another
route with the same prefix is searched for as a replacement. The
current code did not bypass routes that have non-operational
interfaces. This patch fixes that bug and will find a replacement
route with an active interface.

PR:		kern/159603
Submitted by:	pluknet, ambrisko at ambrisko dot com
Reviewed by:	discussed on net@
Approved by:	re (bz)
MFC after:	3 days
2011-08-28 00:14:40 +00:00
Kevin Lo
7236660627 If RTF_HOST flag is specified, then we are interested in destination
address.

PR:		kern/159600
Submitted by:	Svatopluk Kraus <onwahe at gmail dot com>
Approved by:	re (hrs)
2011-08-10 06:17:06 +00:00
Marko Zec
13e255fab7 Permit ARP to proceed for IPv4 host routes for which the gateway is the
same as the host address.  This already works fine for INET6 and ND6.

While here, remove two function pointers from struct lltable which are
only initialized but never used.

MFC after:	3 days
2011-07-08 09:38:33 +00:00
Qing Li
92322284cd Supply the LLE_STATIC flag bit to in_ifscurb() when scrubbing interface
address so that proper clean up will take place in the routing code.
This patch fixes the bootp panic on startup problem. Also, added more
error handling and logging code in function in_scrubprefix().

MFC after:	5 days
2011-05-29 02:21:35 +00:00
Qing Li
5b84dc789a The statically configured (permanent) ARP entries are removed when an
interface is brought down, even though the interface address is still
valid. This patch maintains the permanent ARP entries as long as the
interface address (having the same prefix as that of the ARP entries)
is valid.

Reviewed by:	delphij
MFC after:	5 days
2011-05-20 19:12:20 +00:00
Sergey Kandaurov
79d514355c Reference ifaddr object before unlocking as it can be freed
from another context at the moment of later access.

PR:		kern/155555
Submitted by:	Andrew Boyer <aboyer att averesystems.com>
Approved by:	avg (mentor)
MFC after:	2 weeks
2011-03-21 14:19:40 +00:00
Gleb Smirnoff
a98c06f1c8 Use time_uptime instead of non-monotonic time_second to drive ARP
timeouts.

Suggested by:	bde
2010-11-30 15:57:00 +00:00
Dimitry Andric
3e288e6238 After some off-list discussion, revert a number of changes to the
DPCPU_DEFINE and VNET_DEFINE macros, as these cause problems for various
people working on the affected files.  A better long-term solution is
still being considered.  This reversal may give some modules empty
set_pcpu or set_vnet sections, but these are harmless.

Changes reverted:

------------------------------------------------------------------------
r215318 | dim | 2010-11-14 21:40:55 +0100 (Sun, 14 Nov 2010) | 4 lines

Instead of unconditionally emitting .globl's for the __start_set_xxx and
__stop_set_xxx symbols, only emit them when the set_vnet or set_pcpu
sections are actually defined.

------------------------------------------------------------------------
r215317 | dim | 2010-11-14 21:38:11 +0100 (Sun, 14 Nov 2010) | 3 lines

Apply the STATIC_VNET_DEFINE and STATIC_DPCPU_DEFINE macros throughout
the tree.

------------------------------------------------------------------------
r215316 | dim | 2010-11-14 21:23:02 +0100 (Sun, 14 Nov 2010) | 2 lines

Add macros to define static instances of VNET_DEFINE and DPCPU_DEFINE.
2010-11-22 19:32:54 +00:00
Dimitry Andric
31c6a0037e Apply the STATIC_VNET_DEFINE and STATIC_DPCPU_DEFINE macros throughout
the tree.
2010-11-14 20:38:11 +00:00
George V. Neville-Neil
e162ea60d4 Add a queue to hold packets while we await an ARP reply.
When a fast machine first brings up some non TCP networking program
it is quite possible that we will drop packets due to the fact that
only one packet can be held per ARP entry.  This leads to packets
being missed when a program starts or restarts if the ARP data is
not currently in the ARP cache.

This code adds a new sysctl, net.link.ether.inet.maxhold, which defines
a system wide maximum number of packets to be held in each ARP entry.
Up to maxhold packets are queued until an ARP reply is received or
the ARP times out.  The default setting is the old value of 1
which has been part of the BSD networking code since time
immemorial.

Expose the time we hold an incomplete ARP entry by adding
the sysctl net.link.ether.inet.wait, which defaults to 20
seconds, the value used when the new ARP code was added..

Reviewed by:	bz, rpaulo
MFC after: 3 weeks
2010-11-12 22:03:02 +00:00
Bjoern A. Zeeb
12112cf676 MfP4 CH182763 (original version):
Make it harder to exploit certain in_control() related races between the
intiial lookup at the beginning and the time we will remove the entry
from the lists by re-checking that entry is still in the list before
trying to remove it.

(*) It is believed that with the current code and locking strategy we
    cannot completely fix all race.

Reported by:	Nima Misaghian (nima_misa hotmail.com) on net@ 20100817
Tested by:	Nima Misaghian (nima_misa hotmail.com) (original version)
PR:		kern/146250
Submitted by:	Mikolaj Golub (to.my.trociny gmail.com) (different version)
MFC after:	1 week
2010-10-16 19:53:22 +00:00
Bjoern A. Zeeb
42db1b87d6 In case of RADIX_MPATH do not leak the IN_IFADDR read lock on
early return.

MFC after:	3 days
2010-09-04 16:06:01 +00:00
Will Andrews
54bfbd5153 Allow carp(4) to be loaded as a kernel module. Follow precedent set by
bridge(4), lagg(4) etc. and make use of function pointers and
pf_proto_register() to hook carp into the network stack.

Currently, because of the uncertainty about whether the unload path is free
of race condition panics, unloads are disallowed by default.  Compiling with
CARPMOD_CAN_UNLOAD in CFLAGS removes this anti foot shooting measure.

This commit requires IP6PROTOSPACER, introduced in r211115.

Reviewed by:	bz, simon
Approved by:	ken (mentor)
MFC after:	2 weeks
2010-08-11 00:51:50 +00:00
Qing Li
0ed6142b31 This patch fixes the problem where proxy ARP entries cannot be added
over the if_ng interface.

MFC after:	3 days
2010-05-25 20:42:35 +00:00
Bjoern A. Zeeb
82cea7e6f3 MFP4: @176978-176982, 176984, 176990-176994, 177441
"Whitspace" churn after the VIMAGE/VNET whirls.

Remove the need for some "init" functions within the network
stack, like pim6_init(), icmp_init() or significantly shorten
others like ip6_init() and nd6_init(), using static initialization
again where possible and formerly missed.

Move (most) variables back to the place they used to be before the
container structs and VIMAGE_GLOABLS (before r185088) and try to
reduce the diff to stable/7 and earlier as good as possible,
to help out-of-tree consumers to update from 6.x or 7.x to 8 or 9.

This also removes some header file pollution for putatively
static global variables.

Revert VIMAGE specific changes in ipfilter::ip_auth.c, that are
no longer needed.

Reviewed by:	jhb
Discussed with:	rwatson
Sponsored by:	The FreeBSD Foundation
Sponsored by:	CK Software GmbH
MFC after:	6 days
2010-04-29 11:52:42 +00:00
Bjoern A. Zeeb
becba438d2 Plug reference leaks in the link-layer code ("new-arp") that previously
prevented the link-layer entry from being freed.

In both in.c and in6.c (though that code path seems to be basically dead)
plug a reference leak in case of a pending callout being drained.

In if_ether.c consistently add a reference before resetting the callout
and in case we canceled a pending one remove the reference for that.
In the final case in arptimer, before freeing the expired entry, remove
the reference again and explicitly call callout_stop() to clear the active
flag.

In nd6.c:nd6_free() we are only ever called from the callout function and
thus need to remove the reference there as well before calling into
llentry_free().

In if_llatbl.c when freeing entire tables make sure that in case we cancel
a pending callout to remove the reference as well.

Reviewed by:		qingli (earlier version)
MFC after:		10 days
Problem observed, patch tested by: simon on ipv6gw.f.o,
			Christian Kratzer (ck cksoft.de),
			Evgenii Davidov (dado korolev-net.ru)
PR:			kern/144564
Configurations still affected:	with options FLOWTABLE
2010-04-11 16:04:08 +00:00
Qing Li
c7ea0aa648 One of the advantages of enabling ECMP (a.k.a RADIX_MPATH) is to
allow for connection load balancing across interfaces. Currently
the address alias handling method is colliding with the ECMP code.
For example, when two interfaces are configured on the same prefix,
only one prefix route is installed. So connection load balancing
among the available interfaces is not possible.

The other advantage of ECMP is for failover. The issue with the
current code, is that the interface link-state is not reflected
in the route entry. For example, if there are two interfaces on
the same prefix, the cable on one interface is unplugged, new and
existing connections should switch over to the other interface.
This is not done today and packets go into a black hole.

Also, there is a small bug in the kernel where deleting ECMP routes
in the userland will always return an error even though the command
is successfully executed.

MFC after:	5 days
2010-03-09 01:11:45 +00:00
Qing Li
d577d18a00 Some of the existing ppp and vpn related scripts create and set
the IP addresses of the tunnel end points to the same value. In
these cases the loopback route is not installed for the local
end.

Verified by:	avg
MFC after:	5 days
2010-02-02 20:38:30 +00:00
Qing Li
646c800540 Ensure an address is removed from the interface address
list when the installation of that address fails.

PR:		139559
2010-01-08 17:49:24 +00:00
Qing Li
ccbb9c359d Consolidate the route message generation code for when address
aliases were added or deleted. The announced route entry for
an address alias is no longer empty because this empty route
entry was causing some route daemon to fail and exit abnormally.

MFC after:	5 days
2009-12-30 22:13:01 +00:00
Qing Li
c7ab66020f The proxy arp entries could not be added into the system over the
IFF_POINTOPOINT link types. The reason was due to the routing
entry returned from the kernel covering the remote end is of an
interface type that does not support ARP. This patch fixes this
problem by providing a hint to the kernel routing code, which
indicates the prefix route instead of the PPP host route should
be returned to the caller. Since a host route to the local end
point is also added into the routing table, and there could be
multiple such instantiations due to multiple PPP links can be
created with the same local end IP address, this patch also fixes
the loopback route installation failure problem observed prior to
this patch. The reference count of loopback route to local end would
be either incremented or decremented. The first instantiation would
create the entry and the last removal would delete the route entry.

MFC after:	5 days
2009-12-30 21:35:34 +00:00