Commit Graph

5949 Commits

Author SHA1 Message Date
Mark Johnston
9f78e2b83d Initialize the dumper struct before calling set_dumper().
Fields owned by the generic code were being left uninitialized,
causing problems in clear_dumper() if an error occurred.

Coverity CID:	1391200
X-MFC with:	r333283
2018-05-22 16:01:56 +00:00
Matt Macy
f42a83f2a6 inpcb: revert deferred inpcb free pending further review 2018-05-21 16:13:43 +00:00
Michael Tuexen
c692df45fc Only fillin data srucuture when actually stored. 2018-05-21 14:53:22 +00:00
Michael Tuexen
d3132db2b5 Do the appropriate accounting when ip_output() fails. 2018-05-21 14:52:18 +00:00
Michael Tuexen
95844fce7d Make clear why there is an assignment, which is not necessary. 2018-05-21 14:51:20 +00:00
Ed Maste
3b9b6b1704 Pair CURVNET_SET and CURVNET_RESTORE in a block
Per vnet(9), CURVNET_SET and CURVNET_RESTORE cannot be used as a single
statement for a conditional and CURVNET_RESTORE must be in the same
block as CURVNET_SET (or a subblock).

Reviewed by:	andrew
Sponsored by:	The FreeBSD Foundation
2018-05-21 13:08:44 +00:00
Ed Maste
15f8acc53f Revert r333968, it broke all archs but i386 and amd64 2018-05-21 11:56:07 +00:00
Matt Macy
ed6bb714b2 in(6)_mcast: Expand out vnet set / restore macro so that they work in a conditional block
Reported by:	zec at fer.hr
2018-05-21 08:34:10 +00:00
Matt Macy
06b15160e1 ensure that vnet is set when doing in_leavegroup 2018-05-21 07:12:06 +00:00
Matt Macy
1a3d880c26 in(s)_moptions: free before tearing down inpcb 2018-05-20 20:08:21 +00:00
Matt Macy
47d2a58560 inpcb: defer destruction of inpcb until after a grace period has elapsed
in_pcbfree will remove the incpb from the list and release the rtentry
while the vnet is set, but the actual destruction will be deferred
until any threads in a (not yet used) epoch section, no longer potentially
have references.
2018-05-20 04:38:04 +00:00
Matt Macy
056b40e29c inpcb: consolidate possible deletion in pcblist functions in to epoch
deferred context.
2018-05-20 02:27:58 +00:00
Matt Macy
ddece765f3 in_pcb: add helper for deferring inpcb rele calls from list functions 2018-05-20 02:17:30 +00:00
Matt Macy
cb6bb2303e ip(6)_freemoptions: defer imo destruction to epoch callback task
Avoid the ugly unlock / lock of the inpcbinfo where we need to
figure out what kind of lock we hold by simply deferring the
operation to another context. (Also a small dependency for
converting the pcbinfo read lock to epoch)
2018-05-20 00:22:28 +00:00
Matt Macy
f6960e207e netinet silence warnings 2018-05-19 05:56:21 +00:00
Matt Macy
7a3c5b05e4 tcp sysctl fix may be uninitialized 2018-05-19 05:55:31 +00:00
Matt Macy
21f6fe2d7c tcp fastopen: fix may be uninitialized 2018-05-19 05:55:00 +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
Mark Johnston
b35822d9d0 Fix netdump configuration when VIMAGE is enabled.
We need to set the current vnet before iterating over the global
interface list. Because the dump device may only be set from the host,
only proceed with configuration if the thread belongs to the default
vnet. [1]

Also fix a resource leak that occurs if the priv_check() in set_dumper()
fails.

Reported by:	mmacy, sbruno [1]
Reviewed by:	sbruno
X-MFC with:	r333283
Differential Revision:	https://reviews.freebsd.org/D15449
2018-05-17 04:08:57 +00:00
Lawrence Stewart
9891578a40 Plug a memory leak and potential NULL-pointer dereference introduced in r331214.
Each TCP connection that uses the system default cc_newreno(4) congestion
control algorithm module leaks a "struct newreno" (8 bytes of memory) at
connection initialisation time. The NULL-pointer dereference is only germane
when using the ABE feature, which is disabled by default.

While at it:

- Defer the allocation of memory until it is actually needed given that ABE is
  optional and disabled by default.

- Document the ENOMEM errno in getsockopt(2)/setsockopt(2).

- Document ENOMEM and ENOBUFS in tcp(4) as being synonymous given that they are
  used interchangeably throughout the code.

- Fix a few other nits also accidentally omitted from the original patch.

Reported by:	Harsh Jain on freebsd-net@
Tested by:	tjh@
Differential Revision:	https://reviews.freebsd.org/D15358
2018-05-17 02:46:27 +00:00
Brooks Davis
514ef08caf Unwrap a line that no longer requires wrapping. 2018-05-15 20:14:38 +00:00
Brooks Davis
423349f696 Remove stray tabs from in_lltable_dump_entry(). 2018-05-15 20:13:00 +00:00
Stephen Hurd
f2cf90e264 Check that ifma_protospec != NULL in inm_lookup
If ifma_protospec is NULL when inm_lookup() is called, there
is a dereference in a NULL struct pointer. This ensures that struct is
not NULL before comparing the address.

Reported by:	dumbbell
Reviewed by:	sbruno
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15440
2018-05-15 16:54:41 +00:00
Michael Tuexen
482d420926 sctp_get_mbuf_for_msg() should honor the allinone parameter.
When it is not required that the buffer is not a chain, return
a chain. This is based on a patch provided by Irene Ruengeler.
2018-05-14 15:16:51 +00:00
Michael Tuexen
589c42c2c8 Ensure that the MTU's used are multiple of 4.
The length of SCTP packets is always a multiple of 4. Therefore,
ensure that the MTUs used are also a multiple of 4.

Thanks to Irene Ruengeler for providing an earlier version of this
patch.

MFC after:	1 week
2018-05-14 13:50:17 +00:00
Stephen Hurd
b69888c28f Fix LORs in in6?_leave_group()
r333175 updated the join_group functions, but not the leave_group ones.

Reviewed by:	sbruno
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15393
2018-05-11 21:42:27 +00:00
Warner Losh
33123867af Use the full year, for real this time. 2018-05-09 20:26:37 +00:00
Warner Losh
603bbd0631 Minor style nits
Use full copyright year.
Remove 'All Rights Reserved' from new file (rights holder OK'd)
Minor #ifdef motion and #endif tagging
Remove __FBSDID macro from comments

Sponsored by: Netflix
OK'd by: rrs@
2018-05-09 14:11:35 +00:00
Michael Tuexen
45d41de5e6 Fix two typos reported by N. J. Mann, which were introduced in
https://svnweb.freebsd.org/changeset/base/333382 by me.

MFC after:	3 days
2018-05-08 20:39:35 +00:00
Michael Tuexen
9669e724d1 When reporting ERROR or ABORT chunks, don't use more data
that is guaranteed to be contigous.
Thanks to Felix Weinrank for finding and reporting this bug
by fuzzing the usrsctp stack.

MFC after:	3 days
2018-05-08 18:48:51 +00:00
Matt Macy
10d20c84ed Fix spurious retransmit recovery on low latency networks
TCP's smoothed RTT (SRTT) can be much larger than an actual observed RTT. This can be either because of hz restricting the calculable RTT to 10ms in VMs or 1ms using the default 1000hz or simply because SRTT recently incorporated a larger value.

If an ACK arrives before the calculated badrxtwin (now + SRTT):
tp->t_badrxtwin = ticks + (tp->t_srtt >> (TCP_RTT_SHIFT + 1));

We'll erroneously reset snd_una to snd_max. If multiple segments were dropped and this happens repeatedly the transmit rate will be limited to 1MSS per RTO until we've retransmitted all drops.

Reported by:	rstone
Reviewed by:	hiren, transport
Approved by:	sbruno
MFC after:	1 month
Differential Revision:	https://reviews.freebsd.org/D8556
2018-05-08 02:22:34 +00:00
Alexander Motin
167a34407c Keep CARP state as INIT when net.inet.carp.allow=0.
Currently when net.inet.carp.allow=0 CARP state remains as MASTER, which is
not very useful (if there are other masters -- it can lead to split brain,
if there are none -- it makes no sense).  Having it as INIT makes it clear
that carp packets are disabled.

Submitted by:	wg
MFC after:	1 month
Relnotes:	yes
Sponsored by:	iXsystems, Inc.
Differential Revision:	https://reviews.freebsd.org/D14477
2018-05-07 14:44:55 +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
Michael Tuexen
67e8b08bbe Ensure we are not dereferencing a NULL pointer.
This was found by Coverity scanning the usrsctp stack (CID 203808).

MFC after:	3 days
2018-05-06 14:19:50 +00:00
Mark Johnston
e505460228 Import the netdump client code.
This is a component of a system which lets the kernel dump core to
a remote host after a panic, rather than to a local storage device.
The server component is available in the ports tree. netdump is
particularly useful on diskless systems.

The netdump(4) man page contains some details describing the protocol.
Support for configuring netdump will be added to dumpon(8) in a future
commit. To use netdump, the kernel must have been compiled with the
NETDUMP option.

The initial revision of netdump was written by Darrell Anderson and
was integrated into Sandvine's OS, from which this version was derived.

Reviewed by:	bdrewery, cem (earlier versions), julian, sbruno
MFC after:	1 month
X-MFC note:	use a spare field in struct ifnet
Sponsored by:	Dell EMC Isilon
Differential Revision:	https://reviews.freebsd.org/D15253
2018-05-06 00:38:29 +00:00
Matt Macy
28c001002a Currently in_pcbfree will unconditionally wunlock the pcbinfo lock
to avoid a LOR on the multicast list lock in the freemoptions routines.
As it turns out, tcp_usr_detach can acquire the tcbinfo lock readonly.
Trying to wunlock the pcbinfo lock in that context has caused a number
of reported crashes.

This change unclutters in_pcbfree and moves the handling of wunlock vs
runlock of pcbinfo to the freemoptions routine.

Reported by:	mjg@, bde@, o.hartmann at walstatt.org
Approved by:	sbruno
2018-05-05 22:40:40 +00:00
Andrey V. Elsukov
5ada542398 Immediately propagate EACCES error code to application from tcp_output.
In r309610 and r315514 the behavior of handling EACCES was changed, and
tcp_output() now returns zero when EACCES happens. The reason of this
change was a hesitation that applications that use TCP-MD5 will be
affected by changes in project/ipsec.

TCP-MD5 code returns EACCES when security assocition for given connection
is not configured. But the same error code can return pfil(9), and this
change has affected connections blocked by pfil(9). E.g. application
doesn't return immediately when SYN segment is blocked, instead it waits
when several tries will be failed.

Actually, for TCP-MD5 application it doesn't matter will it get EACCES
after first SYN, or after several tries. Security associtions must be
configured before initiating TCP connection.

I left the EACCES in the switch() to show that it has special handling.

Reported by:	Andreas Longwitz <longwitz at incore dot de>
MFC after:	10 days
2018-05-04 09:28:12 +00:00
Sean Bruno
68ff29affa cc_cubic:
- Update cubic parameters to draft-ietf-tcpm-cubic-04

Submitted by:	Matt Macy <mmacy@mattmacy.io>
Reviewed by:	lstewart
Differential Revision:	https://reviews.freebsd.org/D10556
2018-05-03 15:01:27 +00:00
Michael Tuexen
4c6a10903f SImplify the call to tcp_drop(), since the handling of soft error
is also done in tcp_drop(). No functional change.

Sponsored by:	Netflix, Inc.
2018-05-02 20:04:31 +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
Randall Stewart
803a230592 This change re-arranges the fields within the tcp-pcb so that
they are more in order of cache line use as one passes
through the tcp_input/output paths (non-errors most likely path). This
helps speed up cache line optimization so that the tcp stack runs
a bit more efficently.

Sponsored by:	Netflix Inc.
Differential Revision:	https://reviews.freebsd.org/D15136
2018-04-26 21:41:16 +00:00
Sean Bruno
7875017ca9 Revert r332894 at the request of the submitter.
Submitted by:	Johannes Lundberg <johalun0_gmail.com>
Sponsored by:	Limelight Networks
2018-04-24 19:55:12 +00:00
Sean Bruno
7b7796eea5 Load balance sockets with new SO_REUSEPORT_LB option
This patch adds a new socket option, SO_REUSEPORT_LB, which allow multiple
programs or threads to bind to the same port and incoming connections will be
load balanced using a hash function.

Most of the code was copied from a similar patch for DragonflyBSD.

However, in DragonflyBSD, load balancing is a global on/off setting and can not
be set per socket. This patch allows for simultaneous use of both the current
SO_REUSEPORT and the new SO_REUSEPORT_LB options on the same system.

Required changes to structures
Globally change so_options from 16 to 32 bit value to allow for more options.
Add hashtable in pcbinfo to hold all SO_REUSEPORT_LB sockets.

Limitations
As DragonflyBSD, a load balance group is limited to 256 pcbs
(256 programs or threads sharing the same socket).

Submitted by:	Johannes Lundberg <johanlun0@gmail.com>
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D11003
2018-04-23 19:51:00 +00:00
Randall Stewart
fd389e7cd5 These two modules need the tcp_hpts.h file for
when the option is enabled (not sure how LINT/build-universe
missed this) opps.

Sponsored by:	Netflix Inc
2018-04-19 15:03:48 +00:00
Randall Stewart
3ee9c3c4eb This commit brings in the TCP high precision timer system (tcp_hpts).
It is the forerunner/foundational work of bringing in both Rack and BBR
which use hpts for pacing out packets. The feature is optional and requires
the TCPHPTS option to be enabled before the feature will be active. TCP
modules that use it must assure that the base component is compile in
the kernel in which they are loaded.

MFC after:	Never
Sponsored by:	Netflix Inc.
Differential Revision:	https://reviews.freebsd.org/D15020
2018-04-19 13:37:59 +00:00
Brooks Davis
3a4fc8a8a1 Remove support for the Arcnet protocol.
While Arcnet has some continued deployment in industrial controls, the
lack of drivers for any of the PCI, USB, or PCIe NICs on the market
suggests such users aren't running FreeBSD.

Evidence in the PR database suggests that the cm(4) driver (our sole
Arcnet NIC) was broken in 5.0 and has not worked since.

PR:		182297
Reviewed by:	jhibbits, vangyzen
Relnotes:	yes
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D15057
2018-04-13 21:18:04 +00:00
Brooks Davis
0437c8e3b1 Remove support for FDDI networks.
Defines in net/if_media.h remain in case code copied from ifconfig is in
use elsewere (supporting non-existant media type is harmless).

Reviewed by:	kib, jhb
Sponsored by:	DARPA, AFRL
Differential Revision:	https://reviews.freebsd.org/D15017
2018-04-11 17:28:24 +00:00
Jonathan T. Looney
f897951965 Add missing header change from r332381.
Sponsored by:	Netflix, Inc.
Pointy hat:	jtl
2018-04-10 17:00:37 +00:00
Jonathan T. Looney
8b8718b5b0 Modify the net.inet.tcp.function_ids sysctl introduced in r331347.
Export additional information which may be helpful to userspace
consumers and rename the sysctl to net.inet.tcp.function_info.

Sponsored by:	Netflix, Inc.
2018-04-10 16:59:36 +00:00
Jonathan T. Looney
dcaffbd6fb Move the TCP Blackbox Recorder probe in tcp_output.c to be with the
other tracing/debugging code.

Sponsored by:	Netflix, Inc.
2018-04-10 15:54:29 +00:00