Commit Graph

113 Commits

Author SHA1 Message Date
Gleb Smirnoff
b8a6e03fac Widen NET_EPOCH coverage.
When epoch(9) was introduced to network stack, it was basically
dropped in place of existing locking, which was mutexes and
rwlocks. For the sake of performance mutex covered areas were
as small as possible, so became epoch covered areas.

However, epoch doesn't introduce any contention, it just delays
memory reclaim. So, there is no point to minimise epoch covered
areas in sense of performance. Meanwhile entering/exiting epoch
also has non-zero CPU usage, so doing this less often is a win.

Not the least is also code maintainability. In the new paradigm
we can assume that at any stage of processing a packet, we are
inside network epoch. This makes coding both input and output
path way easier.

On output path we already enter epoch quite early - in the
ip_output(), in the ip6_output().

This patch does the same for the input path. All ISR processing,
network related callouts, other ways of packet injection to the
network stack shall be performed in net_epoch. Any leaf function
that walks network configuration now asserts epoch.

Tricky part is configuration code paths - ioctls, sysctls. They
also call into leaf functions, so some need to be changed.

This patch would introduce more epoch recursions (see EPOCH_TRACE)
than we had before. They will be cleaned up separately, as several
of them aren't trivial. Note, that unlike a lock recursion the
epoch recursion is safe and just wastes a bit of resources.

Reviewed by:	gallatin, hselasky, cy, adrian, kristof
Differential Revision:	https://reviews.freebsd.org/D19111
2019-10-07 22:40:05 +00:00
Hans Petter Selasky
59854ecf55 Convert all IPv4 and IPv6 multicast memberships into using a STAILQ
instead of a linear array.

The multicast memberships for the inpcb structure are protected by a
non-sleepable lock, INP_WLOCK(), which needs to be dropped when
calling the underlying possibly sleeping if_ioctl() method. When using
a linear array to keep track of multicast memberships, the computed
memory location of the multicast filter may suddenly change, due to
concurrent insertion or removal of elements in the linear array. This
in turn leads to various invalid memory access issues and kernel
panics.

To avoid this problem, put all multicast memberships on a STAILQ based
list. Then the memory location of the IPv4 and IPv6 multicast filters
become fixed during their lifetime and use after free and memory leak
issues are easier to track, for example by: vmstat -m | grep multi

All list manipulation has been factored into inline functions
including some macros, to easily allow for a future hash-list
implementation, if needed.

This patch has been tested by pho@ .

Differential Revision: https://reviews.freebsd.org/D20080
Reviewed by:	markj @
MFC after:	1 week
Sponsored by:	Mellanox Technologies
2019-06-25 11:54:41 +00:00
Matt Macy
4f6c66cc9c UDP: further performance improvements on tx
Cumulative throughput while running 64
  netperf -H $DUT -t UDP_STREAM -- -m 1
on a 2x8x2 SKL went from 1.1Mpps to 2.5Mpps

Single stream throughput increases from 910kpps to 1.18Mpps

Baseline:
https://people.freebsd.org/~mmacy/2018.05.11/udpsender2.svg

- Protect read access to global ifnet list with epoch
https://people.freebsd.org/~mmacy/2018.05.11/udpsender3.svg

- Protect short lived ifaddr references with epoch
https://people.freebsd.org/~mmacy/2018.05.11/udpsender4.svg

- Convert if_afdata read lock path to epoch
https://people.freebsd.org/~mmacy/2018.05.11/udpsender5.svg

A fix for the inpcbhash contention is pending sufficient time
on a canary at LLNW.

Reviewed by:	gallatin
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15409
2018-05-23 21:02:14 +00:00
Matt Macy
d7c5a620e2 ifnet: Replace if_addr_lock rwlock with epoch + mutex
Run on LLNW canaries and tested by pho@

gallatin:
Using a 14-core, 28-HTT single socket E5-2697 v3 with a 40GbE MLX5
based ConnectX 4-LX NIC, I see an almost 12% improvement in received
packet rate, and a larger improvement in bytes delivered all the way
to userspace.

When the host receiving 64 streams of netperf -H $DUT -t UDP_STREAM -- -m 1,
I see, using nstat -I mce0 1 before the patch:

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
4.98   0.00   4.42   0.00 4235592     33   83.80 4720653 2149771   1235 247.32
4.73   0.00   4.20   0.00 4025260     33   82.99 4724900 2139833   1204 247.32
4.72   0.00   4.20   0.00 4035252     33   82.14 4719162 2132023   1264 247.32
4.71   0.00   4.21   0.00 4073206     33   83.68 4744973 2123317   1347 247.32
4.72   0.00   4.21   0.00 4061118     33   80.82 4713615 2188091   1490 247.32
4.72   0.00   4.21   0.00 4051675     33   85.29 4727399 2109011   1205 247.32
4.73   0.00   4.21   0.00 4039056     33   84.65 4724735 2102603   1053 247.32

After the patch

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
5.43   0.00   4.20   0.00 3313143     33   84.96 5434214 1900162   2656 245.51
5.43   0.00   4.20   0.00 3308527     33   85.24 5439695 1809382   2521 245.51
5.42   0.00   4.19   0.00 3316778     33   87.54 5416028 1805835   2256 245.51
5.42   0.00   4.19   0.00 3317673     33   90.44 5426044 1763056   2332 245.51
5.42   0.00   4.19   0.00 3314839     33   88.11 5435732 1792218   2499 245.52
5.44   0.00   4.19   0.00 3293228     33   91.84 5426301 1668597   2121 245.52

Similarly, netperf reports 230Mb/s before the patch, and 270Mb/s after the patch

Reviewed by:	gallatin
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15366
2018-05-18 20:13:34 +00:00
Matt Macy
b6f6f88018 r333175 introduced deferred deletion of multicast addresses in order to permit the driver ioctl
to sleep on commands to the NIC when updating multicast filters. More generally this permitted
driver's to use an sx as a softc lock. Unfortunately this change introduced a race whereby a
a multicast update would still be queued for deletion when ifconfig deleted the interface
thus calling down in to _purgemaddrs and synchronously deleting _all_ of the multicast addresses
on the interface.

Synchronously remove all external references to a multicast address before enqueueing for delete.

Reported by:	lwhsu
Approved by:	sbruno
2018-05-06 20:34:13 +00:00
Stephen Hurd
f3e1324b41 Separate list manipulation locking from state change in multicast
Multicast incorrectly calls in to drivers with a mutex held causing drivers
to have to go through all manner of contortions to use a non sleepable lock.
Serialize multicast updates instead.

Submitted by:	mmacy <mmacy@mattmacy.io>
Reviewed by:	shurd, sbruno
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D14969
2018-05-02 19:36:29 +00:00
Pedro F. Giffuni
51369649b0 sys: further adoption of SPDX licensing ID tags.
Mainly focus on files that use BSD 3-Clause license.

The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.

Special thanks to Wind River for providing access to "The Duke of
Highlander" tool: an older (2014) run over FreeBSD tree was useful as a
starting point.
2017-11-20 19:43:44 +00:00
Warner Losh
fbbd9655e5 Renumber copyright clause 4
Renumber cluase 4 to 3, per what everybody else did when BSD granted
them permission to remove clause 3. My insistance on keeping the same
numbering for legal reasons is too pedantic, so give up on that point.

Submitted by:	Jan Schaumann <jschauma@stevens.edu>
Pull Request:	https://github.com/freebsd/freebsd/pull/96
2017-02-28 23:42:47 +00:00
Eric van Gyzen
2d9db0bc63 Add GARP retransmit capability
A single gratuitous ARP (GARP) is always transmitted when an IPv4
address is added to an interface, and that is usually sufficient.
However, in some circumstances, such as when a shared address is
passed between cluster nodes, this single GARP may occasionally be
dropped or lost.  This can lead to neighbors on the network link
working with a stale ARP cache and sending packets destined for
that address to the node that previously owned the address, which
may not respond.

To avoid this situation, GARP retransmissions can be enabled by setting
the net.link.ether.inet.garp_rexmit_count sysctl to a value greater
than zero.  The setting represents the maximum number of retransmissions.
The interval between retransmissions is calculated using an exponential
backoff algorithm, doubling each time, so the retransmission intervals
are: {1, 2, 4, 8, 16, ...} (seconds).

Due to the exponential backoff algorithm used for the interval
between GARP retransmissions, the maximum number of retransmissions
is limited to 16 for sanity.  This limit corresponds to a maximum
interval between retransmissions of 2^16 seconds ~= 18 hours.
Increasing this limit is possible, but sending out GARPs spaced
days apart would be of little use.

Submitted by:	David A. Bright <david.a.bright@dell.com>
MFC after:	1 month
Relnotes:	yes
Sponsored by:	Dell EMC
Differential Revision:	https://reviews.freebsd.org/D7695
2016-10-02 01:42:45 +00:00
Bjoern A. Zeeb
89856f7e2d Get closer to a VIMAGE network stack teardown from top to bottom rather
than removing the network interfaces first. This change is rather larger
and convoluted as the ordering requirements cannot be separated.

Move the pfil(9) framework to SI_SUB_PROTO_PFIL, move Firewalls and
related modules to their own SI_SUB_PROTO_FIREWALL.
Move initialization of "physical" interfaces to SI_SUB_DRIVERS,
move virtual (cloned) interfaces to SI_SUB_PSEUDO.
Move Multicast to SI_SUB_PROTO_MC.

Re-work parts of multicast initialisation and teardown, not taking the
huge amount of memory into account if used as a module yet.

For interface teardown we try to do as many of them as we can on
SI_SUB_INIT_IF, but for some this makes no sense, e.g., when tunnelling
over a higher layer protocol such as IP. In that case the interface
has to go along (or before) the higher layer protocol is shutdown.

Kernel hhooks need to go last on teardown as they may be used at various
higher layers and we cannot remove them before we cleaned up the higher
layers.

For interface teardown there are multiple paths:
(a) a cloned interface is destroyed (inside a VIMAGE or in the base system),
(b) any interface is moved from a virtual network stack to a different
network stack ("vmove"), or (c) a virtual network stack is being shut down.
All code paths go through if_detach_internal() where we, depending on the
vmove flag or the vnet state, make a decision on how much to shut down;
in case we are destroying a VNET the individual protocol layers will
cleanup their own parts thus we cannot do so again for each interface as
we end up with, e.g., double-frees, destroying locks twice or acquiring
already destroyed locks.
When calling into protocol cleanups we equally have to tell them
whether they need to detach upper layer protocols ("ulp") or not
(e.g., in6_ifdetach()).

Provide or enahnce helper functions to do proper cleanup at a protocol
rather than at an interface level.

Approved by:		re (hrs)
Obtained from:		projects/vnet
Reviewed by:		gnn, jhb
Sponsored by:		The FreeBSD Foundation
MFC after:		2 weeks
Differential Revision:	https://reviews.freebsd.org/D6747
2016-06-21 13:48:49 +00:00
Alexander V. Chernikov
61eee0e202 MFP r287070,r287073: split radix implementation and route table structure.
There are number of radix consumers in kernel land (pf,ipfw,nfs,route)
  with different requirements. In fact, first 3 don't have _any_ requirements
  and first 2 does not use radix locking. On the other hand, routing
  structure do have these requirements (rnh_gen, multipath, custom
  to-be-added control plane functions, different locking).
Additionally, radix should not known anything about its consumers internals.

So, radix code now uses tiny 'struct radix_head' structure along with
  internal 'struct radix_mask_head' instead of 'struct radix_node_head'.
  Existing consumers still uses the same 'struct radix_node_head' with
  slight modifications: they need to pass pointer to (embedded)
  'struct radix_head' to all radix callbacks.

Routing code now uses new 'struct rib_head' with different locking macro:
  RADIX_NODE_HEAD prefix was renamed to RIB_ (which stands for routing
  information base).

New net/route_var.h header was added to hold routing subsystem internal
  data. 'struct rib_head' was placed there. 'struct rtentry' will also
  be moved there soon.
2016-01-25 06:33:15 +00:00
Alexander V. Chernikov
10e0e23528 Remove now-unused wrappers for various routing functions. 2016-01-14 08:54:44 +00:00
Steven Hartland
d6e82913c1 Revert r292275 & r292379
glebius has concerns about these changes so reverting those can be discussed
and addressed.

Sponsored by:	Multiplay
2015-12-17 14:41:30 +00:00
Steven Hartland
52e53e2de0 Fix lagg failover due to missing notifications
When using lagg failover mode neither Gratuitous ARP (IPv4) or Unsolicited
Neighbour Advertisements (IPv6) are sent to notify other nodes that the
address may have moved.

This results is slow failover, dropped packets and network outages for the
lagg interface when the primary link goes down.

We now use the new if_link_state_change_cond with the force param set to
allow lagg to force through link state changes and hence fire a
ifnet_link_event which are now monitored by rip and nd6.

Upon receiving these events each protocol trigger the relevant
notifications:
* inet4 => Gratuitous ARP
* inet6 => Unsolicited Neighbour Announce

This also fixes the carp IPv6 NA's that stopped working after r251584 which
added the ipv6_route__llma route.

The new behavour can be controlled using the sysctls:
* net.link.ether.inet.arp_on_link
* net.inet6.icmp6.nd6_on_link

Also removed unused param from lagg_port_state and added descriptions for the
sysctls while here.

PR:		156226
MFC after:	1 month
Sponsored by:	Multiplay
Differential Revision:	https://reviews.freebsd.org/D4111
2015-12-15 16:02:11 +00:00
George V. Neville-Neil
33872124a5 Replace the fastforward path with tryforward which does not require a
sysctl and will always be on. The former split between default and
fast forwarding is removed by this commit while preserving the ability
to use all network stack features.

Differential Revision:	https://reviews.freebsd.org/D4042
Reviewed by:	ae, melifaro, olivier, rwatson
MFC after:	1 month
Sponsored by:	Rubicon Communications (Netgate)
2015-11-05 07:26:32 +00:00
Alexander V. Chernikov
f221bcaa06 Remove several compat functions from pre-fib era. 2015-10-17 17:26:44 +00:00
Andrey V. Elsukov
cc0a3c8ca4 Convert in_ifaddr_lock and in6_ifaddr_lock to rmlock.
Both are used to protect access to IP addresses lists and they can be
acquired for reading several times per packet. To reduce lock contention
it is better to use rmlock here.

Reviewed by:	gnn (previous version)
Obtained from:	Yandex LLC
Sponsored by:	Yandex LLC
Differential Revision:	https://reviews.freebsd.org/D3149
2015-07-29 08:12:05 +00:00
Gleb Smirnoff
1dbefcc00d Move all code related to IP fragment reassembly to ip_reass.c. Some
function names have changed and comments are reformatted or added, but
there is no functional change.

Claim copyright for me and Adrian.

Sponsored by:	Nginx, Inc.
2015-04-10 06:02:37 +00:00
Gleb Smirnoff
26d50672d6 The last userland piece of in_var.h is now 'struct in_aliasreq'. Move
it to the top of the file, and ifdef _KERNEL the rest.
2015-02-19 23:59:27 +00:00
Gleb Smirnoff
e072c794ad Now that all users of _WANT_IFADDR are fixed, remove this crutch and
hide ifaddr, in_ifaddr and in6_ifaddr under _KERNEL.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2015-02-19 23:16:10 +00:00
Gleb Smirnoff
0d159406b6 - Rename 'struct igmp_ifinfo' into 'struct igmp_ifsoftc', since it really
represents a context.
- Preserve name 'struct igmp_ifinfo' for a new structure, that will be stable
  API between userland and kernel.
- Make sysctl_igmp_ifinfo() return the new 'struct igmp_ifinfo', instead of
  old one, which had a bunch of internal kernel structures in it.
- Move all above declarations from in_var.h to igmp_var.h, since they are
  private to IGMP code.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2015-02-19 22:35:23 +00:00
Gleb Smirnoff
fd1b2a7c57 Widen _KERNEL ifdef to hide more kernel network stack structures from userland. 2015-02-19 06:24:27 +00:00
Gleb Smirnoff
058e08bea9 Use new struct mbufq instead of struct ifqueue to manage packet queues in
IPv4 multicast code.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2015-02-19 01:21:02 +00:00
Alexander V. Chernikov
670e8b3b8c Kill custom in_matroute() radix mathing function removing one rte mutex lock.
Initially in_matrote() in_clsroute() in their current state was introduced by
r4105 20 years ago. Instead of deleting inactive routes immediately, we kept them
in route table, setting RTPRF_OURS flag and some expire time. After that, either
GC came or RTPRF_OURS got removed on first-packet. It was a good solution
in that days (and probably another decade after that) to keep TCP metrics.
However, after moving metrics to TCP hostcache in r122922, most of in_rmx
functionality became unused. It might had been used for flushing icmp-originated
routes before rte mutexes/refcounting, but I'm not sure about that.

So it looks like this is nearly impossible to make GC do its work nowadays:

in_rtkill() ignores non-RTPRF_OURS routes.
route can only become RTPRF_OURS after dropping last reference via rtfree()
which calls in_clsroute(), which, it turn, ignores UP and non-RTF_DYNAMIC routes.

Dynamic routes can still be installed via received redirect, but they
have default lifetime (no specific rt_expire) and no one has another trie walker
to call RTFREE() on them.

So, the changelist:
* remove custom rnh_match / rnh_close matching function.
* remove all GC functions
* partially revert r256695 (proto3 is no more used inside kernel,
  it is not possible to use rt_expire from user point of view, proto3 support
  is not complete)
* Finish r241884 (similar to this commit) and remove remaining IPv6 parts

MFC after:	1 month
2014-11-11 02:52:40 +00:00
Adrian Chadd
b8bc95cd49 Update the IPv4 input path to handle reassembled frames and incoming frames
with no RSS hash.

When doing RSS:

* Create a new IPv4 netisr which expects the frames to have been verified;
  it just directly dispatches to the IPv4 input path.
* Once IPv4 reassembly is done, re-calculate the RSS hash with the new
  IP and L3 header; then reinject it as appropriate.
* Update the IPv4 netisr to be a CPU affinity netisr with the RSS hash
  function (rss_soft_m2cpuid) - this will do a software hash if the
  hardware doesn't provide one.

NICs that don't implement hardware RSS hashing will now benefit from RSS
distribution - it'll inject into the correct destination netisr.

Note: the netisr distribution doesn't work out of the box - netisr doesn't
query RSS for how many CPUs and the affinity setup.  Yes, netisr likely
shouldn't really be doing CPU stuff anymore and should be "some kind of
'thing' that is a workqueue that may or may not have any CPU affinity";
that's for a later commit.

Differential Revision:	https://reviews.freebsd.org/D527
Reviewed by:	grehan
2014-09-09 04:18:20 +00:00
Gleb Smirnoff
586904c22e in_ifadown() can be void. 2013-11-01 10:29:10 +00:00
Gleb Smirnoff
237bf7f773 Cleanup in_ifscrub(), which is just an entry to in_scrubprefix(). 2013-11-01 10:18:41 +00:00
Gleb Smirnoff
8d7cf9b5d4 Uninline inm_lookup_locked(). Now in_var.h doesn't dereference
fields of struct ifnet.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2013-10-29 11:21:31 +00:00
Gleb Smirnoff
6ed910fabe Hide 'struct ifaddr' definition from userland. Two tools left that use it,
namely ipftest(1) and ifmcstat(1). These sniff structure definition using
_WANT_IFADDR define.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
2013-10-15 10:19:24 +00:00
Andre Oppermann
f89d4c3acf Back out r249318, r249320 and r249327 due to a heisenbug most
likely related to a race condition in the ipi_hash_lock with
the exact cause currently unknown but under investigation.
2013-05-06 16:42:18 +00:00
Gleb Smirnoff
18ba072a22 Fix build. 2013-04-10 08:09:25 +00:00
Alexander V. Chernikov
3c2824b9ef Do not check if found IPv4 rte is dynamic if net.inet.icmp.drop_redirect is
enabled. This eliminates one mtx_lock() per each routing lookup thus improving
performance in several cases (routing to directly connected interface or routing
to default gateway).

Icmp redirects should not be used to provide routing direction nowadays, even
for end hosts. Routers should not use them too (and this is explicitly restricted
in IPv6, see RFC 4861, clause 8.2).

Current commit changes rnh_machaddr function to 'stock' rn_match (and back) for every
AF_INET routing table in given VNET instance on drop_redirect sysctl change.

This change is part of bigger patch eliminating rte locking.

Sponsored by:	Yandex LLC
MFC after:	2 weeks
2012-10-10 19:06:11 +00:00
Gleb Smirnoff
b9abeb9d99 When traversing global in_ifaddr list in the IFP_TO_IA() macro, we need
to obtain IN_IFADDR_RLOCK().
2012-07-18 08:41:00 +00:00
Gleb Smirnoff
d294536082 Provide IA_MASKSIN() macro similar to IA_SIN() and IA_DSTSIN(). 2012-01-08 17:20:29 +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
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
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
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
Robert Watson
1e77c1056a Remove unused VNET_SET() and related macros; only VNET_GET() is
ever actually used.  Rename VNET_GET() to VNET() to shorten
variable references.

Discussed with:	bz, julian
Reviewed by:	bz
Approved by:	re (kensmith, kib)
2009-07-16 21:13:04 +00:00
Robert Watson
eddfbb763d Build on Jeff Roberson's linker-set based dynamic per-CPU allocator
(DPCPU), as suggested by Peter Wemm, and implement a new per-virtual
network stack memory allocator.  Modify vnet to use the allocator
instead of monolithic global container structures (vinet, ...).  This
change solves many binary compatibility problems associated with
VIMAGE, and restores ELF symbols for virtualized global variables.

Each virtualized global variable exists as a "reference copy", and also
once per virtual network stack.  Virtualized global variables are
tagged at compile-time, placing the in a special linker set, which is
loaded into a contiguous region of kernel memory.  Virtualized global
variables in the base kernel are linked as normal, but those in modules
are copied and relocated to a reserved portion of the kernel's vnet
region with the help of a the kernel linker.

Virtualized global variables exist in per-vnet memory set up when the
network stack instance is created, and are initialized statically from
the reference copy.  Run-time access occurs via an accessor macro, which
converts from the current vnet and requested symbol to a per-vnet
address.  When "options VIMAGE" is not compiled into the kernel, normal
global ELF symbols will be used instead and indirection is avoided.

This change restores static initialization for network stack global
variables, restores support for non-global symbols and types, eliminates
the need for many subsystem constructors, eliminates large per-subsystem
structures that caused many binary compatibility issues both for
monitoring applications (netstat) and kernel modules, removes the
per-function INIT_VNET_*() macros throughout the stack, eliminates the
need for vnet_symmap ksym(2) munging, and eliminates duplicate
definitions of virtualized globals under VIMAGE_GLOBALS.

Bump __FreeBSD_version and update UPDATING.

Portions submitted by:  bz
Reviewed by:            bz, zec
Discussed with:         gnn, jamie, jeff, jhb, julian, sam
Suggested by:           peter
Approved by:            re (kensmith)
2009-07-14 22:48:30 +00:00
Robert Watson
64aeca7b42 Initialize in_ifaddr_lock using RW_SYSINIT() instead of in ip_init(),
so that it doesn't run multiple times if VIMAGE is being used.

Discussed with:	bz
MFC after:	6 weeks
2009-06-25 14:44:00 +00:00
Robert Watson
2d9cfabad4 Add a new global rwlock, in_ifaddr_lock, which will synchronize use of the
in_ifaddrhead and INADDR_HASH address lists.

Previously, these lists were used unsynchronized as they were effectively
never changed in steady state, but we've seen increasing reports of
writer-writer races on very busy VPN servers as core count has gone up
(and similar configurations where address lists change frequently and
concurrently).

For the time being, use rwlocks rather than rmlocks in order to take
advantage of their better lock debugging support.  As a result, we don't
enable ip_input()'s read-locking of INADDR_HASH until an rmlock conversion
is complete and a performance analysis has been done.  This means that one
class of reader-writer races still exists.

MFC after:      6 weeks
Reviewed by:    bz
2009-06-25 11:52:33 +00:00
Robert Watson
8c0fec805f Modify most routines returning 'struct ifaddr *' to return references
rather than pointers, requiring callers to properly dispose of those
references.  The following routines now return references:

  ifaddr_byindex
  ifa_ifwithaddr
  ifa_ifwithbroadaddr
  ifa_ifwithdstaddr
  ifa_ifwithnet
  ifaof_ifpforaddr
  ifa_ifwithroute
  ifa_ifwithroute_fib
  rt_getifa
  rt_getifa_fib
  IFP_TO_IA
  ip_rtaddr
  in6_ifawithifp
  in6ifa_ifpforlinklocal
  in6ifa_ifpwithaddr
  in6_ifadd
  carp_iamatch6
  ip6_getdstifaddr

Remove unused macro which didn't have required referencing:

  IFP_TO_IA6

This closes many small races in which changes to interface
or address lists while an ifaddr was in use could lead to use of freed
memory (etc).  In a few cases, add missing if_addr_list locking
required to safely acquire references.

Because of a lack of deep copying support, we accept a race in which
an in6_ifaddr pointed to by mbuf tags and extracted with
ip6_getdstifaddr() doesn't hold a reference while in transmit.  Once
we have mbuf tag deep copy support, this can be fixed.

Reviewed by:	bz
Obtained from:	Apple, Inc. (portions)
MFC after:	6 weeks (portions)
2009-06-23 20:19:09 +00:00
Warner Losh
573a04c930 Remove bogus comment. 2009-05-09 18:50:01 +00:00
Kip Macy
582b6122ab make LLTABLE visible to netinet 2009-04-15 20:49:59 +00:00
Bruce M Simpson
d10910e6ce Merge IGMPv3 and Source-Specific Multicast (SSM) to the FreeBSD
IPv4 stack.

Diffs are minimized against p4.
PCS has been used for some protocol verification, more widespread
testing of recorded sources in Group-and-Source queries is needed.
sizeof(struct igmpstat) has changed.

__FreeBSD_version is bumped to 800070.
2009-03-09 17:53:05 +00:00
Qing Li
6e6b3f7cbc This main goals of this project are:
1. separating L2 tables (ARP, NDP) from the L3 routing tables
2. removing as much locking dependencies among these layers as
   possible to allow for some parallelism in the search operations
3. simplify the logic in the routing code,

The most notable end result is the obsolescent of the route
cloning (RTF_CLONING) concept, which translated into code reduction
in both IPv4 ARP and IPv6 NDP related modules, and size reduction in
struct rtentry{}. The change in design obsoletes the semantics of
RTF_CLONING, RTF_WASCLONE and RTF_LLINFO routing flags. The userland
applications such as "arp" and "ndp" have been modified to reflect
those changes. The output from "netstat -r" shows only the routing
entries.

Quite a few developers have contributed to this project in the
past: Glebius Smirnoff, Luigi Rizzo, Alessandro Cerri, and
Andre Oppermann. And most recently:

- Kip Macy revised the locking code completely, thus completing
  the last piece of the puzzle, Kip has also been conducting
  active functional testing
- Sam Leffler has helped me improving/refactoring the code, and
  provided valuable reviews
- Julian Elischer setup the perforce tree for me and has helped
  me maintaining that branch before the svn conversion
2008-12-15 06:10:57 +00:00
Bjoern A. Zeeb
1b193af610 Second round of putting global variables, which were virtualized
but formerly missed under VIMAGE_GLOBAL.

Put the extern declarations of the  virtualized globals
under VIMAGE_GLOBAL as the globals themsevles are already.
This will help by the time when we are going to remove the globals
entirely.

Sponsored by:	The FreeBSD Foundation
2008-12-13 19:13:03 +00:00
Marko Zec
44e33a0758 Change the initialization methodology for global variables scheduled
for virtualization.

Instead of initializing the affected global variables at instatiation,
assign initial values to them in initializer functions.  As a rule,
initialization at instatiation for such variables should never be
introduced again from now on.  Furthermore, enclose all instantiations
of such global variables in #ifdef VIMAGE_GLOBALS blocks.

Essentialy, this change should have zero functional impact.  In the next
phase of merging network stack virtualization infrastructure from
p4/vimage branch, the new initialization methology will allow us to
switch between using global variables and their counterparts residing in
virtualization containers with minimum code churn, and in the long run
allow us to intialize multiple instances of such container structures.

Discussed at:	devsummit Strassburg
Reviewed by:	bz, julian
Approved by:	julian (mentor)
Obtained from:	//depot/projects/vimage-commit2/...
X-MFC after:	never
Sponsored by:	NLnet Foundation, The FreeBSD Foundation
2008-11-19 09:39:34 +00:00
Julian Elischer
93fcb5a28d Revert a part of the MRT commit that proved un-needed.
rt_check() in its original form proved to be sufficient and
rt_check_fib() can go away (as can its evil twin in_rt_check()).

I believe this does NOT address the crashes people have been seeing
in rt_check.

MFC after:	1 week
2008-09-14 08:19:48 +00:00