Commit Graph

2841 Commits

Author SHA1 Message Date
Alexander V. Chernikov
bdf942c3f0 Revert r234834 per luigi@ request.
Cleaner solution (e.g. adding another header) should be done here.

Original log:
  Move several enums and structures required for L2 filtering from ip_fw_private.h to ip_fw.h.
  Remove ipfw/ip_fw_private.h header from non-ipfw code.

Requested by:      luigi
Approved by:       kib(mentor)
2012-05-03 08:56:43 +00:00
Ed Maste
6107adc3f5 Relax restriction on direct tx to child ports
Lagg(4) restricts the type of packet that may be sent directly to a child
port, to avoid undesired output from accidental misconfiguration.
Previously only ETHERTYPE_PAE was permitted.

BPF writes to a lagg(4) child port are presumably intentional, so just
allow them, while still blocking other packets that should take the
aggregation path.

PR:		kern/138620
Approved by:	thompsa@
2012-05-03 01:41:12 +00:00
Alexander V. Chernikov
7bd5e9b143 Move several enums and structures required for L2 filtering from ip_fw_private.h to ip_fw.h.
Remove ipfw/ip_fw_private.h header from non-ipfw code.

Approved by:        ae(mentor)
MFC after:          2 weeks
2012-04-30 10:22:23 +00:00
Alexander V. Chernikov
c2508034a2 Do not require radix write lock to be held while dumping route table
via sysctl(4) interface. This permits router not to stop forwarding
packets while route table is being written to user-supplied buffer.

Reported by:        Pawel Tyll <ptyll@nitronet.pl>
Approved by:        kib(mentor)

MFC after:          1 week
2012-04-22 16:13:23 +00:00
Andrew Thompson
2885c19ebd Move the interface media check to a taskqueue, some interfaces (usb) sleep
during SIOCGIFMEDIA and we were holding locks.
2012-04-20 10:06:28 +00:00
Andrew Thompson
7702d4013b Add linkstate to bridge(4), set the link to up when at least one underlying
interface is up, otherwise the link is down.

This, among other things, allows carp to work on a bridge.

Prodded by:	glebius
Tested by:	Alexander Lunev
2012-04-20 09:55:50 +00:00
Andrew Thompson
ddf3201009 Remove KASSERTS, they do not add any value here since the pointer is about to
be derefernced anyway.
2012-04-18 01:39:14 +00:00
Luigi Rizzo
d76bf4ff7b A bit of cleanup in the names of fields of netmap-related structures.
Use the name 'ring' instead of 'queue' in all fields.
Bump NETMAP_API.
2012-04-13 16:03:07 +00:00
Luigi Rizzo
d5d42003f4 remove an unnecessary #define 2012-04-12 10:32:34 +00:00
Andrew Thompson
b517176ad9 Set the proto to LAGG_PROTO_NONE before calling the detach routine so packets
are discarded, this is an issue because lacp drops the lock which may allow
network threads to access freed memory. Expand the lock coverage so the
detach/attach happen atomically.

Submitted by:	Andrew Boyer (earlier version)
2012-04-12 01:07:17 +00:00
John Baldwin
19a3210a66 Add media types for 40G media that might be used with FreeBSD.
Reviewed by:	bz
MFC after:	2 weeks
2012-04-10 13:59:35 +00:00
Alexander V. Chernikov
9431cc1696 Fix build broken by r233938.
Pointed by:     David Wolfskill <david@catwhisker.org>
Approved by:    kib (mentor)
Pointy hat to:  melifaro
2012-04-06 13:34:19 +00:00
Alexander V. Chernikov
51ec1eb70d - Improve performace for writer-only BPF users.
Linux and Solaris (at least OpenSolaris) has PF_PACKET socket families to send
raw ethernet frames. The only FreeBSD interface that can be used to send raw frames
is BPF. As a result, many programs like cdpd, lldpd, various dhcp stuff uses
BPF only to send data. This leads us to the situation when software like cdpd,
being run on high-traffic-volume interface significantly reduces overall performance
since we have to acquire additional locks for every packet.

Here we add sysctl that changes BPF behavior in the following way:
If program came and opens BPF socket without explicitly specifyin read filter we
assume it to be write-only and add it to special writer-only per-interface list.
This makes bpf_peers_present() return 0, so no additional overhead is introduced.
After filter is supplied, descriptor is added to original per-interface list permitting
packets to be captured.

Unfortunately, pcap_open_live() sets catch-all filter itself for the purpose of
setting snap length.

Fortunately, most programs explicitly sets (event catch-all) filter after that.
tcpdump(1) is a good example.

So a bit hackis approach is taken: we upgrade description only after second
BIOCSETF is received.

Sysctl is named net.bpf.optimize_writers and is turned off by default.

- While here, document all sysctl variables in bpf.4

Sponsored by Yandex LLC

Reviewed by:    glebius (previous version)
Reviewed by:    silence on -net@
Approved by:    (mentor)

MFC after:      4 weeks
2012-04-06 06:55:21 +00:00
Alexander V. Chernikov
e4b3229aa5 - Improve BPF locking model.
Interface locks and descriptor locks are converted from mutex(9) to rwlock(9).
This greately improves performance: in most common case we need to acquire 1
reader lock instead of 2 mutexes.

- Remove filter(descriptor) (reader) lock in bpf_mtap[2]
This was suggested by glebius@. We protect filter by requesting interface
writer lock on filter change.

- Cover struct bpf_if under BPF_INTERNAL define. This permits including bpf.h
without including rwlock stuff. However, this is is temporary solution,
struct bpf_if should be made opaque for any external caller.

Found by:       Dmitrij Tejblum <tejblum@yandex-team.ru>
Sponsored by:   Yandex LLC

Reviewed by:    glebius (previous version)
Reviewed by:    silence on -net@
Approved by:    (mentor)

MFC after:      3 weeks
2012-04-06 06:53:58 +00:00
John Baldwin
02ed02af7b Retire the IF_ADDR_LOCK() and IF_ADDR_UNLOCK() compat macros from HEAD.
The new [RW]LOCK macros are merged back to 8.x so should be suitable for
new code in HEAD even if it is to be MFC'd.
2012-03-19 21:09:12 +00:00
Bjoern A. Zeeb
bfca216eb9 Hide kernel option ROUTETABLES evaluations in the implementation
rather than the header file.  With this also move RT_MAXFIBS and
RT_NUMFIBS into the implemantion to avoid further usage in other
code. rt_numfibs is all that should be needed.

This allows users to change the number of FIBs from 1..RT_MAXFIBS(16)
dynamically using the tunable without the need to change the kernel
config for the maximum anymore.  This means that thet multi-FIB
feature is now fully available with GENERIC kernels.
The kernel option ROUTETABLES can still be used to set the default
numbers of FIBs in absence of the tunable.

Ok.ed by:	julian, hrs, melifaro
MFC after:	2 weeks
2012-03-18 11:23:40 +00:00
Luigi Rizzo
a72505824c - remove an extra parenthesis in a closing brace;
- add the macro NETMAP_RING_FIRST_RESERVED() which returns
  the index of the first non-released buffer in the ring
  (this is useful for code that retains buffers for some time
  instead of processing them immediately)
2012-03-11 17:35:12 +00:00
Andrew Thompson
cd613b6351 Move the vlan buffer space into the union which also fixes an unused variable
warning with !INET & !INET6.

Spotted by:	pluknet
2012-03-07 07:22:53 +00:00
Andrew Thompson
86f67641a9 Add the ability to set which packet layers are used for the load balance hash
calculation.
2012-03-06 22:58:13 +00:00
Marko Zec
2db13e7575 Properly restore curvnet context when returning early from
ether_input_internal().

This change only affects options VIMAGE kernel builds.

PR:		kern/165643
Submitted by:	Vijay Singh
MFC after:	3 days
2012-03-04 11:11:03 +00:00
Juli Mallett
9624d94701 o) Add COMPAT_FREEBSD32 support for MIPS kernels using the n64 ABI with userlands
using the o32 ABI.  This mostly follows nwhitehorn's lead in implementing
   COMPAT_FREEBSD32 on powerpc64.
o) Add a new type to the freebsd32 compat layer, time32_t, which is time_t in the
   32-bit ABI being used.  Since the MIPS port is relatively-new, even the 32-bit
   ABIs use a 64-bit time_t.
o) Because time{spec,val}32 has the same size and layout as time{spec,val} on MIPS
   with 32-bit compatibility, then, disable some code which assumes otherwise
   wrongly when built for MIPS.  A more general macro to check in this case would
   seem like a good idea eventually.  If someone adds support for using n32
   userland with n64 kernels on MIPS, then they will have to add a variety of
   flags related to each piece of the ABI that can vary.  That's probably the
   right time to generalize further.
o) Add MIPS to the list of architectures which use PAD64_REQUIRED in the
   freebsd32 compat code.  Probably this should be generalized at some point.

Reviewed by:	gonzo
2012-03-03 08:19:18 +00:00
Andrew Thompson
70b23a4596 Use a more appropriate default for the maximum number of addresses in the
bridge forwarding table.

PR:		docs/164564
Discussed with:	brueffer
2012-02-29 20:58:21 +00:00
Luigi Rizzo
64ae02c365 A bunch of netmap fixes:
USERSPACE:
1. add support for devices with different number of rx and tx queues;

2. add better support for zero-copy operation, adding an extra field
   to the netmap ring to indicate how many buffers we have already processed
   but not yet released (with help from Eddie Kohler);

3. The two changes above unfortunately require an API change, so while
   at it add a version field and some spares to the ioctl() argument
   to help detect mismatches.

4. update the manual page for the two changes above;

5. update sample applications in tools/tools/netmap

KERNEL:

1. simplify the internal structures moving the global wait queues
   to the 'struct netmap_adapter';

2. simplify the functions that map kring<->nic ring indexes

3. normalize device-specific code, helps mainteinance;

4. start exploring the impact of micro-optimizations (prefetch etc.)
   in the ixgbe driver.
   Use 'legacy' descriptors on the tx ring and prefetch slots gives
   about 20% speedup at 900 MHz. Another 7-10% would come from removing
   the explict calls to bus_dmamap* in the core (they are effectively
   NOPs in this case, but it takes expensive load of the per-buffer
   dma maps to figure out that they are all NULL.

   Rx performance not investigated.

I am postponing the MFC so i can import a few more improvements
before merging.
2012-02-27 19:05:01 +00:00
Andrew Thompson
8d45bd6e80 Only look for a usable MAC address for the bridge ID from ports within our
bridge, this allows us to have more than one independent bridge in the same
STP domain.

PR:		kern/164369
Submitted by:	Nikos Vassiliadis (earlier version)
MFC after:	2 weeks
2012-02-24 17:50:36 +00:00
Andrew Thompson
3122b9120c Add a sysctl/tunable default value for the use_flowid sysctl in r232008. 2012-02-23 21:56:53 +00:00
Andrew Thompson
47190ea664 Indicate this function decrements the timer as well as testing for expiry. 2012-02-23 20:58:52 +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
Andrew Thompson
2ad65e315d Now that network interfaces advertise if they support linkstate notifications
we do not need to perform a media ioctl every 15 seconds.
2012-02-23 06:26:16 +00:00
Andrew Thompson
4661f8627c bstp_input() always consumes the packet so remove the mbuf handling dance
around it.

Obtained from:	OpenBSD (r1.37)
2012-02-23 00:59:21 +00:00
Andrew Thompson
0bf97ae271 Using the flowid in the mbuf assumes the network card is giving a good hash for
the traffic flow, this may not be the case giving poor traffic distribution.
Add a sysctl which allows us to fall back to our own flow hash code.

PR:		kern/164901
Submitted by:	Eugene Grosbein
MFC after:	1 week
2012-02-22 22:01:30 +00:00
Bjoern A. Zeeb
9dba179d5e IFC @231845
Sponsored by:	Cisco Systems, Inc.
2012-02-17 00:27:48 +00:00
Tijl Coosemans
265f940acc Change some headers such that lang/gcc* ports no longer patch them.
The lang/gcc* ports patch headers where they think something is
non-standard. These patched headers override the system headers which means
you have to rebuild these ports whenever you do installworld to make sure
they contain the latest changes.
2012-02-14 12:50:20 +00:00
Bjoern A. Zeeb
6d076ae8f7 Introduce a new NET_RT_IFLISTL API to query the address list. It works
on extended and extensible structs if_msghdrl and ifa_msghdrl.  This
will allow us to extend both the msghdrl structs and eventually if_data
in the future without breaking the ABI.

Bump __FreeBSD_version to allow ports to more easily detect the new API.

Reviewed by:	glebius, brooks
MFC after:	3 days
2012-02-11 06:02:16 +00:00
Bjoern A. Zeeb
e82cf13bfb Backout changes from r228571. Remove if_data from struct ifa_msghdr again.
While this breaks carp on HEAD temporary, it restores the upgrade path from
stable, and head before 20111215.

Reviewed by:	glebius, brooks
2012-02-11 05:59:54 +00:00
Sergey Kandaurov
4ecf274be7 g/c last bit of old ipv6 prefix management.
Reviewed by:	bz
Obtained from:	NetBSD, net/if.h, rev 1.80
2012-02-08 22:05:26 +00:00
Luigi Rizzo
5819da83ce - change the buffer size from a constant to a
TUNABLE variable (hw.netmap.buf_size) so we can experiment
  with values different from 2048 which may give better cache performance.

- rearrange the memory allocation code so it will be easier
  to replace it with a different implementation. The current code
  relies on a single large contiguous chunk of memory obtained through
  contigmalloc.
  The new implementation (not committed yet) uses multiple
  smaller chunks which are easier to fit in a fragmented address
  space.
2012-02-08 11:43:29 +00:00
Pawel Jakub Dawidek
50c8ec53f6 Allow to set if_bridge(4) sysctls from /boot/loader.conf.
MFC after:	3 days
2012-02-07 14:50:33 +00:00
Gleb Smirnoff
e8aa8bdd64 Fix typo in r231010.
Submitted by:	linimon
2012-02-05 12:52:28 +00:00
Gleb Smirnoff
cad582b753 Better comment for ifa_init(), ifa_ref(), ifa_free(). 2012-02-05 08:53:05 +00:00
Gleb Smirnoff
adc7231d5d In ifa_init() initialize if_data.ifi_datalen. This would be
required after upcoming changes from bz@.

Discussed with:	bz
2012-02-05 08:31:15 +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
Bjoern A. Zeeb
a84986256f Move a comment from rtinit1() to the top of the file where dealing with
the (maximum) number of FIBs trying to clarify that evetually FIBs
should probably attached to domain(9) specific storage. [1]

Add a comment on a limitimation on the rt_add_addr_allfibs option.

Use RT_DEFAULT_FIB instead of 0 where applicable.

Add empty line to functions without local variables per style.

Put public yet unused in-tree function rtinit_fib() under BURN_BRIDGES
to indicate that it might go away in the future.

No functional change.

Discussed with:	julian [1] (clarification on what the original one meant)
Sponsored by:	Cisco Systems, Inc.
2012-02-03 12:25:14 +00:00
Bjoern A. Zeeb
b3dd077152 Minor optimization doing input validation with a possible early return
before doing further work.

Sponsored by:	Cisco Systems, Inc.
2012-02-03 11:20:11 +00:00
Bjoern A. Zeeb
096f27864f Fix FLOWTABLE IPv6 handling in route.c missed in r205066.
While doing so, for consistency with the rtalloc_ign_fib(9) interface
called, remove the "in_" prefix from rtalloc_ign_wrapper() no longer
indicating that it would only handle the INET case.

Sponsored by:	Cisco Systems, Inc.
2012-02-03 10:17:34 +00:00
Bjoern A. Zeeb
b680a383a8 Allow for IPv6 to allocate (and in the VIMAGE case free) as many routing
tables (FIBs) as IPv4.
Prepare various general rt* functions for multi-FIB IPv6 handling in
addition to already existing multi-FIB IPv4 cases.

Sponsored by:	Cisco Systems, Inc.
2012-02-03 09:23:55 +00:00
Bjoern A. Zeeb
556d81ddd7 Rather than putting magic 0s as FIB argument into the rt* calls, provide
a macro RT_DEFAULT_FIB defined to 0 to more easily identify the cases
tied to the default FIB.

Sponsored by:	Cisco Systems, Inc.
2012-02-03 09:06:24 +00:00
Kip Macy
0fe48d670f A flowtable entry can continue referencing an llentry indefinitely if the entry is repeatedly
referenced within its timeout window. This change clears the LLE_VALID flag when an llentry
is removed from an interface's hash table and adds an extra check to the flowtable code
for the LLE_VALID flag in llentry to avoid retaining and using a stale reference.

Reviewed by:	qingli@
MFC after:	2 weeks
2012-01-26 20:02:40 +00:00
Bjoern A. Zeeb
8d74af3668 Replace random ARIN direct assignment legacy IPs with proper RFC 5735
TEST-NET1 block for use in documentation and example code addresses.

MFC after:	3 days
2012-01-24 15:20:31 +00:00
Eitan Adler
dde153da49 - Fix trivial typo
Approved by:	nwhitehorn
MFC after:	3 days
2012-01-14 17:07:52 +00:00
Robert Watson
7983103ae6 Clarify throughout the vlan(4) code the difference between a "tag" (the
802.1q-defined 16-bit VID, CFI, and PCP field in host by order) and a
VLAN ID (VID).  Tags go in packets.  VIDs identify VLANs.

No functional change is intended, so this should be safe to MFC.  Further
cleanup with functional changes will be committed separately (for example,
renaming vlan_tag/vlan_tag_p, which modify the KPI and KBI).

Reviewed by:	bz
Sponsored by:	ADARA Networks, Inc.
MFC after:	3 days
2012-01-12 18:39:37 +00:00