ƒ·.265370
157
205
282
133
113
119
261
396
162
130
152
113
117
143
151
194
581
716
267
3065
364
277
209
164
265
175
678
203
207
170
430
355
280
186
198
112
441
230
502
369
871
649
291
460
417
976
158
158
163
1198
698
180
301
193
444
1711
956
494
517
161
161
142
142
169
177
322
181
391
211
181
311
202
238
265
140
1089
195
227
167
292
749
749
182
194
586
399
295
510
150
431
168
217
115
184
532
366
219
334
130
408
364
277
270
635
299
362
153
958
666
1252
423
1085
935
622
153
204
391
276
229
202
202
243
173
234
335
272
370
291
219
346
164
201
204
241
216
228
190
213
300
285
282
211
578
226
211
156
188
174
289
213
155
234
211
168
226
623
156
376

K 10
svn:author
V 6
adrian
K 8
svn:date
V 27
2014-05-05T17:06:40.106906Z
K 7
svn:log
V 109
Wake up the hardware before calling ath_mode_init() in the ioctl() path.

Tested:

* AR5416, STA + powersave

END
K 10
svn:author
V 6
tuexen
K 8
svn:date
V 27
2014-05-05T17:30:05.430043Z
K 7
svn:log
V 186
Fill in csum_data only for UDP or TCP packets. This fixes a bug where
SCTP were reported to have always a correct checksum if they don't
contain any ethernet padding.

MFC after: 3 days

END
K 10
svn:author
V 7
delphij
K 8
svn:date
V 27
2014-05-05T17:51:27.756386Z
K 7
svn:log
V 37
Publish previously released patches.

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T17:56:10.252707Z
K 7
svn:log
V 21
Leverage bsd.opts.mk

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T17:58:00.389476Z
K 7
svn:log
V 27
Update to latest versions.

END
K 10
svn:author
V 3
pfg
K 8
svn:date
V 27
2014-05-05T18:04:57.080140Z
K 7
svn:log
V 168
Revert r265367:
Use of calloc instead of malloc in regex (from OpenBSD).

In this case the change makes no sense since we are using realloc() later.

Reported by:	ache

END
K 10
svn:author
V 4
neel
K 8
svn:date
V 27
2014-05-05T18:06:35.680803Z
K 7
svn:log
V 302
Modify the "-p" option to be more flexible when associating a 'vcpu' with
a 'hostcpu'. The new format of the argument string is "vcpu:hostcpu".

This allows pinning a subset of the vcpus if desired.

It also allows pinning a vcpu to more than a single 'hostcpu'.

Submitted by:	novel (initial version)

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T18:15:18.966988Z
K 7
svn:log
V 70
Avoid /etc/make.conf
and make it easier to deal with compiler updates

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T18:16:15.942314Z
K 7
svn:log
V 38
WITHOUT always wins

Reviewed by:	imp

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T18:17:26.306019Z
K 7
svn:log
V 60
If doing destroy-all and at top-level whack stage tree too.

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T18:18:23.977104Z
K 7
svn:log
V 21
Leverage bsd.opts.mk

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T18:31:00.655418Z
K 7
svn:log
V 25
New/updated dependencies

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T18:32:24.376115Z
K 7
svn:log
V 51
If building WITH_META_FILES we do not want STAGING

END
K 10
svn:author
V 5
peter
K 8
svn:date
V 27
2014-05-05T19:35:02.779383Z
K 7
svn:log
V 57
MFC r250916: coexist with /etc/localtime being a symlink

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T19:35:32.199776Z
K 7
svn:log
V 101
Sadly there is at least on lib we need to build for host (libdwarf)
else we cannot build ctfconvert.

END
K 10
svn:author
V 7
asomers
K 8
svn:date
V 27
2014-05-05T19:38:29.934067Z
K 7
svn:log
V 484
Remove the ifconfig test added in rev 263445.  After discussion with
melifaro, we agreed that ifconfig's behavior was not a bug.  The main
motivation for bin/187551 was to partially resolve kern/187549, but we
resolved kern/187549 in a different way instead.

ObsoleteFiles.inc
etc/mtree/BSD.tests.dist
sbin/ifconfig/tests/fibs_test.sh
sbin/ifconfig/tests/Makefile
sbin/ifconfig/Makefile
	Remove /usr/tests/sbin/ifconfig

PR:		bin/187551
MFC after:	3 days
Sponsored by:	Spectra Logic

END
K 10
svn:author
V 3
ken
K 8
svn:date
V 27
2014-05-05T19:53:03.481128Z
K 7
svn:log
V 623
Adjust #if statements inside mprsas_send_smpcmd() to more accurately
reflect when unmapped I/O support was added.

For FreeBSD 10, it arrived just prior to __FreeBSD_version 1000028.
For FreeBSD 9, it arrived just prior to __FreeBSD_version 902001.

Also, fix compiler warnings in mprsas_send_smpcmd() that happen in the
i386 PAE build for non-unmapped I/O builds.  These were fixed in mps(4)
in revision 241145, but didn't make it into the mpr(4) driver.  This
change should only affect FreeBSD versions outside the above revisions,
and thus doesn't affect head.

MFC after:	3 days
Sponsored by:	Spectra Logic Corporation

END
K 10
svn:author
V 7
dchagin
K 8
svn:date
V 27
2014-05-05T20:13:25.413556Z
K 7
svn:log
V 170
hecking epoll fd against fd is useless as different fds could
resolve to the same file.
Instead of checking of file descriptors compare file pointers.

Suggested by: mjg

END
K 10
svn:author
V 3
ken
K 8
svn:date
V 27
2014-05-05T20:35:35.481355Z
K 7
svn:log
V 2971
MFC the mpr(4) driver for LSI's 12Gb SAS cards.

This includes r265236, r265237, r265241 and r265261:

  ------------------------------------------------------------------------
  r265236 | ken | 2014-05-02 14:25:09 -0600 (Fri, 02 May 2014) | 51 lines

  Bring in the mpr(4) driver for LSI's MPT3 12Gb SAS controllers.

  This is derived from the mps(4) driver, but it supports only the 12Gb
  IT and IR hardware including the SAS 3004, SAS 3008 and SAS 3108.

  Some notes about this driver:
   o The 12Gb hardware can do "FastPath" I/O, and that capability is included in
     this driver.

   o WarpDrive functionality has been removed, since it isn't supported in
     the 12Gb driver interface.

   o The Scatter/Gather list handling code is significantly different between
     the 6Gb and 12Gb hardware.  The 12Gb boards support IEEE Scatter/Gather
     lists.

  Thanks to LSI for developing and testing this driver for FreeBSD.

  share/man/man4/mpr.4:
  	mpr(4) man page.

  sys/dev/mpr/*:
  	mpr(4) driver files.

  sys/modules/Makefile,
  sys/modules/mpr/Makefile:
  	Add a module Makefile for the mpr(4) driver.

  sys/conf/files:
  	Add the mpr(4) driver.

  sys/amd64/conf/GENERIC,
  sys/i386/conf/GENERIC,
  sys/mips/conf/OCTEON1,
  sys/sparc64/conf/GENERIC:
  	Add the mpr(4) driver to all config files that currently
  	have the mps(4) driver.

  sys/ia64/conf/GENERIC:
  	Add the mps(4) and mpr(4) drivers to the ia64 GENERIC
  	config file.

  sys/i386/conf/XEN:
  	Exclude the mpr module from building here.

  Submitted by:	Steve McConnell <Stephen.McConnell@lsi.com>
  Tested by:	Chris Reeves <chrisr@spectralogic.com>
  Sponsored by:	LSI, Spectra Logic
  Relnotes:	LSI 12Gb SAS driver mpr(4) added

  ------------------------------------------------------------------------
  ------------------------------------------------------------------------
  r265237 | ken | 2014-05-02 14:36:20 -0600 (Fri, 02 May 2014) | 8 lines

  Add the mpr(4) man page to the man4 Makefile.

  This should have been included in r265236.

  Submitted by:	Steve McConnell <Stephen.McConnell@lsi.com>
  MFC after:	3 days
  Sponsored by:	LSI, Spectra Logic

  ------------------------------------------------------------------------
  ------------------------------------------------------------------------
  r265241 | brueffer | 2014-05-02 15:14:28 -0600 (Fri, 02 May 2014) | 2 lines

  Use our standard SYNOPSIS wording; perform some cleanup while here.

  ------------------------------------------------------------------------
  ------------------------------------------------------------------------
  r265261 | brueffer | 2014-05-03 05:15:28 -0600 (Sat, 03 May 2014) | 2 lines

  Add a missing colon.

  ------------------------------------------------------------------------

Submitted by:	Steve McConnell <Stephen.McConnell@lsi.com>
Tested by:	Chris Reeves <chrisr@spectralogic.com>
Sponsored by:	LSI, Spectra Logic
Relnotes:	LSI 12Gb SAS driver mpr(4) added

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-05T20:48:36.322978Z
K 7
svn:log
V 266
MFC: r264705, r264749
Modify the NFSv4 client create/mkdir RPC so that it acquires
post-create/mkdir directory attributes. This allows the RPC to
name cache the newly created directory and reduces the lookup RPC
count for applications creating a lot of directories.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-05T20:55:37.708690Z
K 7
svn:log
V 179
MFC: r264738
For an NFSv4 mount with the "nocto" option, don't get the
up to date file attributes upon close. This reduces the
Getattr RPC count by about 65% for software builds.

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T21:29:56.982574Z
K 7
svn:log
V 116
Define a new method for probing vt(4) driver before attach it at early stage.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T21:31:00.736231Z
K 7
svn:log
V 72
Create dataset for vt(4) drivers.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 7
glebius
K 8
svn:date
V 27
2014-05-05T21:33:20.671399Z
K 7
svn:log
V 168
The tcp_log_addrs() uses th pointer, which points into the mbuf, thus we
can not free the mbuf before tcp_log_addrs().

Sponsored by:	Nginx, Inc.
Sponsored by:	Netflix

END
K 10
svn:author
V 8
brueffer
K 8
svn:date
V 27
2014-05-05T21:34:10.492747Z
K 7
svn:log
V 78
MFC: r265242

Generate hardware notes for mpr(4) and bump copyright for 2014.

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T21:44:53.810555Z
K 7
svn:log
V 585
Set of updates to vt(4) core part.
o Declare vt(4) drivers dataset.
o Create single static structures for all early drivers.
o Add vt(4) to be by default in the kernel consoles list.
o Create one more sysinit point, to be able to initialize memory and lock
	requirement of early drivers.
o Implement early drivers select. (Only best available will be selected).
o Fix one missed "return (0)" for VTYLOCK.
o Improve locking for cases when one driver replace another.
o Make driver replacement notification less debug-look-like.

Minor spell fixes.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 7
rwatson
K 8
svn:date
V 27
2014-05-05T21:46:10.164557Z
K 7
svn:log
V 106
Garbage collect two more unused sysinit subsystems: SI_SUB_KVM_RSRC and
SI_SUB_CLISTS.

MFC after:	3 days

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T21:48:19.381843Z
K 7
svn:log
V 114
Switch fb and efifb drivers to use names and new vt(4) driver probe method.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T21:49:31.549016Z
K 7
svn:log
V 78
Add vt(4) driver name for ofwfb driver.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-05T22:02:48.009324Z
K 7
svn:log
V 337
[1] Make WITHOUT_FOO alway trump WITH_FOO, regardless of the system
    default. This restores more of the historical expectations that
    were broken when we started disallowing both WITH_FOO and
    WITHOUT_FOO to be defined.
[2] Document this new behavior, and improve the documentation in
    general here.

Submitted by: sjg@ [1].

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-05T22:03:01.316725Z
K 7
svn:log
V 262
Introduce CWARNFLAGS.${COMPILER_TYPE} and use that to simplify the
thicket of .if ${COMPILER_TYPE} == "clang" that controls
warnings. Also, use CFLAGS.clang in a couple places in preference to
having a similar construct that's related to the CWARNFLAGS changes.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-05T22:03:08.905100Z
K 7
svn:log
V 187
Simplify use of the semi-bogus EARLY_BUILD variable. Also, simplify
use of semi-bogus NO_WARNS variable. Both of these, in this case,
should collapse to WITHOUT_WARNS in a future commit.

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T22:10:31.580743Z
K 7
svn:log
V 94
Revert r264997 and r265026. It is not required anymore.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-05T22:12:46.851759Z
K 7
svn:log
V 105
Switch vga drivers to use names and new vt(4) driver probe method.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
sjg
K 8
svn:date
V 27
2014-05-05T22:55:42.140925Z
K 7
svn:log
V 20
Need to stage_files

END
K 10
svn:author
V 3
gjb
K 8
svn:date
V 27
2014-05-05T23:01:01.091707Z
K 7
svn:log
V 348
Add a helper script for parsing 'svn log' for the
'Relnotes:' tag in case 'yes' is not explicitly
the first string value following the tab.

As it turns out, a number of commits have bypassed
my filters (both email and 'svn log --search'), and
this script returns the results I want when doing
these searches.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
gjb
K 8
svn:date
V 27
2014-05-05T23:36:46.117249Z
K 7
svn:log
V 137
Use 'return' instead of 'exit' in main(), since the script exits
with the last returned exit code.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 4
neel
K 8
svn:date
V 27
2014-05-05T23:54:13.473589Z
K 7
svn:log
V 408
Disable the 'uart_drain()' callback when the emulated receive FIFO is full.

Failing to do this will cause the kevent(2) notification to trigger
continuously and the bhyve(8) mevent thread will hog the cpu until the
characters on the backend tty device are drained.

Also, make the uart backend file descriptor non-blocking to avoid a
select(2) before every byte read from that backend.

Reviewed by:	grehan

END
K 10
svn:author
V 7
glebius
K 8
svn:date
V 27
2014-05-06T00:00:07.234089Z
K 7
svn:log
V 272
- Remove net.inet.tcp.reass.overflows sysctl. It counts exactly
  same events that tcpstat's tcps_rcvmemdrop counter counts.
- Rename tcps_rcvmemdrop to tcps_rcvreassfull and improve its
  description in netstat(1) output.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.

END
K 10
svn:author
V 6
adrian
K 8
svn:date
V 27
2014-05-06T01:15:42.102644Z
K 7
svn:log
V 775
Modify the RX path to keep the previous RX descriptor around once it's
used.

It turns out that the RX DMA engine does the same last-descriptor-link-
pointer-re-reading trick that the TX DMA engine.  That is, the hardware
re-reads the link pointer before it moves onto the next descriptor.
Thus we can't free a descriptor before we move on; it's possible the
hardware will need to re-read the link pointer before we overwrite
it with a new one.

Tested:

* AR5416, STA mode

TODO:

* more thorough AP and STA mode testing!
* test on other pre-AR9380 NICs, just to be sure.
* Break out the RX descriptor grabbing bits from the RX completion
  bits, like what is done in the RX EDMA code, so ..
* .. the RX lock can be held during ath_rx_proc(), but not across
  packet input.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T02:22:52.685119Z
K 7
svn:log
V 557
MFC r261533, r261536, r261537, and r263457.

r261533:
cxgbe(4): Use the port's tx channel to identify it to t4_clr_port_stats.

r261536:
cxgbe(4): The T5 allows for a different freelist starvation threshold
for queues with buffer packing.  Use the correct value to calculate a
freelist's low water mark.

r261537:
cxgbe(4): Use the rx channel map (instead of the tx channel map) as the
congestion channel map.

r263457:
cxgbe(4):  Recognize the "spider" configuration where a T5 card's 40G
QSFP port is presented as 4 distinct 10G SFP+ ports to the driver.

END
K 10
svn:author
V 7
davidcs
K 8
svn:date
V 27
2014-05-06T02:32:27.457358Z
K 7
svn:log
V 194
Modify Copyright information to reflect Qlogic Corporation's purchase
of Broadcom's NetXtreme business

Submitted by:David C Somayajulu (davidcs@freebsd.org) QLogic Corporation
MFC after:5 days

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T02:44:01.741965Z
K 7
svn:log
V 362
MFC: r264469, r264498
Lagg did not set the value of if_hw_tsomax, so when lagg
was stacked on top of network interfaces that set if_hw_tsomax,
tcp_output() would see the default value instead of the value
set by the network interface(s). This patch modifies lagg so that
it sets if_hw_tsomax to the minimum of the value(s) for the
underlying network interfaces.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T02:49:31.249529Z
K 7
svn:log
V 319
MFC: r264517
Vlan did not set the value of if_hw_tsomax, so when vlan
was stacked on top of a network interface that set if_hw_tsomax,
tcp_output() would see the default value instead of the value
set by the network interface. This patch modifies vlan so that
it sets if_hw_tsomax to the value of the parent interface.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T02:54:59.302786Z
K 7
svn:log
V 878
MFC: r264630
For NFS mounts using rsize,wsize=65536 over TSO enabled
network interfaces limited to 32 transmit segments, there
are two known issues.
The more serious one is that for an I/O of slightly less than 64K,
the net device driver prepends an ethernet header, resulting in a
TSO segment slightly larger than 64K. Since m_defrag() copies this
into 33 mbuf clusters, the transmit fails with EFBIG.
A tester indicated observing a similar failure using iSCSI.

The second less critical problem is that the network
device driver must copy the mbuf chain via m_defrag()
(m_collapse() is not sufficient), resulting in measurable overhead.

This patch reduces the default size of if_hw_tsomax
slightly, so that the first issue is avoided.
Fixing the second issue will require a way for the
network device driver to inform tcp_output() that it
is limited to 32 transmit segments.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T03:02:02.028755Z
K 7
svn:log
V 67
MFC r261534:
cxgbetool: Display the congestion channel map in hex.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T03:05:14.551744Z
K 7
svn:log
V 67
MFC r261804:
Provide additional information in some panic strings.

END
K 10
svn:author
V 6
bryanv
K 8
svn:date
V 27
2014-05-06T03:38:04.888739Z
K 7
svn:log
V 68
MFC r265287:

  Fix SYNOPSIS ("device if_vtnet" -> "device vtnet").

END
K 10
svn:author
V 3
alc
K 8
svn:date
V 27
2014-05-06T03:42:04.859798Z
K 7
svn:log
V 1104
Prior to r254304, a separate function, vm_pageout_page_stats(), was used to
periodically update the reference status of the active pages.  This function
was called, instead of vm_pageout_scan(), when memory was not scarce.  The
objective was to provide up to date reference status for active pages in
case memory did become scarce and active pages needed to be deactivated.

The active page queue scan performed by vm_pageout_page_stats() was
virtually identical to that performed by vm_pageout_scan(), and so r254304
eliminated vm_pageout_page_stats().  Instead, vm_pageout_scan() is
called with the parameter "pass" set to zero.  The intention was that when
pass is zero, vm_pageout_scan() would only scan the active queue.  However,
the variable page_shortage can still be greater than zero when memory is not
scarce and vm_pageout_scan() is called with pass equal to zero.
Consequently, the inactive queue may be scanned and dirty pages laundered
even though that was not intended by r254304.  This revision fixes that.

Reported by:	avg
MFC after:	1 week
Sponsored by:	EMC / Isilon Storage Division

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T04:21:48.674785Z
K 7
svn:log
V 605
Move the /usr/src specific options to src.opts.mk. Move inclusion of
/etc/src.conf to this file as well. Now, it will only affect builds of
/usr/src and not others that use the bsd.*.mk files. Specifically
don't install src.opts.mk so we can catch when it 'leaks' into
bsd.*.mk again and have there be errors when this happens. Future
commits will move to including src.opts.mk instead of bsd.own.mk when
all that's needed is one of the MK_FOO options from src.opts.mk.
Future options should be placed here, unless they directly affect a
bsd.*.mk file, in which case they should be placed in bsd.opts.mk.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T04:22:01.054886Z
K 7
svn:log
V 88
Use src.opts.mk in preference to bsd.own.mk except where we need stuff
from the latter.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T04:22:06.156809Z
K 7
svn:log
V 209
MFC r260210 (by adrian@):
Add an option to enable or disable the small RX packet copying that
is done to improve performance of small frames.

When doing RX packing, the RX copying isn't necessarily required.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T04:22:29.970407Z
K 7
svn:log
V 100
Document src.opts.mk changes and the decoupling of /etc/src.conf from
anything but the source tree.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T04:22:37.633123Z
K 7
svn:log
V 351
Remove support for WITHOUT_BMAKE. bmake is now the only make that can
build world, so it is the only make we build or install. fmake is
still in the tree, but disconnected, and upgrades from older systems
that still have bmake has not been removed, but its state has not been
tested (it should work given how minimal the work to upgrade to bmake
is).

END
K 10
svn:author
V 3
ken
K 8
svn:date
V 27
2014-05-06T06:18:43.581857Z
K 7
svn:log
V 1617
Fix a problem with async notifications in the mpr(4) driver.

This problem only occurs on versions of FreeBSD prior to the recent CAM
locking changes.  (i.e. stable/9 and older versions of stable/10)  This
change should be a no-op for head and stable/10.

If a path isn't specified, xpt_register_async() will create a fully
wildcarded path and acquire a lock (the XPT lock in older versions,
and via xpt_path_lock() in newer versions) to call xpt_action() for the
XPT_SASYNC_CB CCB.  It will then drop the lock and if the requested event
includes AC_FOUND_DEVICE or AC_PATH_REGISTERED, it will get the caller up
to date with any device arrivals or path registrations.

The issue is that before the locking changes, each SIM lock would get
acquired in turn during the EDT tree traversal process.  If a path is
specified for xpt_register_async(), it won't acquire and drop its own lock,
but instead expects the caller to hold its own SIM lock.  That works for
the first part of xpt_register_async(), but causes a recursive lock
acquisition once the EDT traversal happens and it comes to the SIM in
question.  And it isn't possible to call xpt_action() without holding a SIM
lock.

The locking changes fix this by using the XPT topology lock for EDT
traversal, so it is no longer an issue to hold the SIM lock while calling
xpt_register_async().

The solution for FreeBSD versions before the locking changes is to request
notification of all device arrivals (so we pass a NULL path into
xpt_register_async()) and then filter out the arrivals that are not ours.

MFC After:	3 days
Sponsored by:	Spectra Logic Corporation

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T06:49:39.127922Z
K 7
svn:log
V 864
MFC r263317, r263412, and r263451.

r263317:
cxgbe(4): significant rx rework.

- More flexible cluster size selection, including the ability to fall
  back to a safe cluster size (PAGE_SIZE from zone_jumbop by default) in
  case an allocation of a larger size fails.
- A single get_fl_payload() function that assembles the payload into an
  mbuf chain for any kind of freelist.  This replaces two variants: one
  for freelists with buffer packing enabled and another for those without.
- Buffer packing with any sized cluster.  It was limited to 4K clusters
  only before this change.
- Enable buffer packing for TOE rx queues as well.
- Statistics and tunables to go with all these changes.  The driver's
  man page will be updated separately.

r263412:
cxgbe(4): if_iqdrops statistic should include tunnel congestion drops.

r263451:
cxgbe(4): man page updates.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T07:21:50.150705Z
K 7
svn:log
V 402
MFC r259382:

Read card capabilities after firmware initialization, instead of setting
them up as part of firmware initialization (which the driver gets to do
only if it's the master driver).

Read the range of tids available for the ETHOFLD functionality if it's
enabled.

New is_ftid() and is_etid() functions to test whether a tid falls within
the range of filter tids or ETHOFLD tids respectively.

END
K 10
svn:author
V 8
hselasky
K 8
svn:date
V 27
2014-05-06T09:12:32.525534Z
K 7
svn:log
V 419
Reduce the number of interrupts in USB host mode for the DWC OTG
controller driver by piggybacking the SOF interrupt when issuing new
and checking old transfers. Number of interrupts was reduced by 30%
when doing Isochronous transfers.

Use correct GINTMSK_XXX macros when accessing the DWC OTG interrupt
mask register.

Add code to adjust the frame interval register which influences the
SOF rate.

MFC after:	2 weeks

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2014-05-06T09:51:15.637662Z
K 7
svn:log
V 69
MFC r260830:
Add ID for one more ASMedia AHCI-compatible controller.

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2014-05-06T09:52:37.747907Z
K 7
svn:log
V 69
MFC r260830:
Add ID for one more ASMedia AHCI-compatible controller.

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2014-05-06T09:54:24.974099Z
K 7
svn:log
V 50
MFC r264610:
Correct AMD chipsets identification.

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2014-05-06T09:55:49.384652Z
K 7
svn:log
V 50
MFC r264610:
Correct AMD chipsets identification.

END
K 10
svn:author
V 7
rwatson
K 8
svn:date
V 27
2014-05-06T10:53:51.897216Z
K 7
svn:log
V 73
Spell raccdt in a more conventional way in a comment.

MFC after:	3 days

END
K 10
svn:author
V 2
se
K 8
svn:date
V 27
2014-05-06T11:12:56.021690Z
K 7
svn:log
V 86
Fix buildkernel breakage, which was fall-out from the move of options to
src.opts.mk.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T12:15:05.023797Z
K 7
svn:log
V 224
MFC: r264672
Modify the Lookup RPC for NFSv4 so that it acquires directory
attributes. This allows the client to cache directory names
when they are looked up, reducing the Lookup RPC count by
about 40% for software builds.

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2014-05-06T12:20:07.949565Z
K 7
svn:log
V 89
MFC r265100:
Fix the comparision for the end of range in vm_phys_fictitious_reg_range().

END
K 10
svn:author
V 2
se
K 8
svn:date
V 27
2014-05-06T12:31:17.504967Z
K 7
svn:log
V 299
Fix include statement to accept src.opts.mk from a source directory
instead of from /usr/share/mk.

I'm not sure that this will let buildworld complete on a system with
no installed src.opts.mk (make buildworld is still running), but the
tinderbox builds are all failing earlyon without this patch.

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2014-05-06T12:31:25.248287Z
K 7
svn:log
V 118
MFC r265102:
Fix two cases of recursive acquisitions of the vm object lock, only
possible in rare failure situations.

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2014-05-06T12:35:19.506615Z
K 7
svn:log
V 89
MFC r265100:
Fix the comparision for the end of range in vm_phys_fictitious_reg_range().

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2014-05-06T12:39:23.652586Z
K 7
svn:log
V 218
MFC r265102:
Fix one cases of recursive acquisitions of the vm object lock, only
possible in rare failure situations.  The second part of r265102 is
not applicable to stable/9 since vm_page_insert() cannot fail there.

END
K 10
svn:author
V 3
ian
K 8
svn:date
V 27
2014-05-06T13:38:34.869248Z
K 7
svn:log
V 109
Move the pl310.enabled tunable to hw.pl310.enabled.  Clean up a few minor
style(9) nits.  Use DEVMETHOD_END.

END
K 10
svn:author
V 3
ian
K 8
svn:date
V 27
2014-05-06T13:46:36.261121Z
K 7
svn:log
V 145
Break out the code that figures out the L2 cache geometry to its own
routine, so that it can be called from multiple places in upcoming changes.

END
K 10
svn:author
V 3
ray
K 8
svn:date
V 27
2014-05-06T13:52:13.929980Z
K 7
svn:log
V 172
Implement KDMKTONE ioctl.

Submitted by:	Matthew D.Fuller <fullermd@over-yonder.net> (original version)
MFC:		7 days
PR:		kern/189170

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 2
se
K 8
svn:date
V 27
2014-05-06T14:01:48.743832Z
K 7
svn:log
V 49
Revert r265436, since it is not the correct fix.

END
K 10
svn:author
V 3
ian
K 8
svn:date
V 27
2014-05-06T14:03:35.049060Z
K 7
svn:log
V 996
Call platform_pl310_init() before enabling the controller, and handle the
case where the controller is already enabled.

Some of the pl310 configuration registers cannot be changed while the
controller is active, so if there is any platform-specific init to be done
it must happen before enabling the controller.

The controller should not be enabled upon entry to the kernel, but u-boot
has recently developed the bad habit of leaving caches enabled when
launching the kernel, and since we have no control over that source code
we have to do our best to cope with it.  The PL310 manual doesn't document
a safe sequence for disabling the controller, but the sequence used here
(force write-through mode and disable linefill allocations, then clean and
invalidate the current contents before disabling the hardware) appears to
be sound both by analysis and empirical testing.

These changes were developed and tested in collaboration with
Svatopluk Kraus <onwahe@gmail.com>.

Reviewed by:	cognet@

END
K 10
svn:author
V 3
ian
K 8
svn:date
V 27
2014-05-06T14:08:42.700411Z
K 7
svn:log
V 102
Add defines for the bits in the PL310 debug control register.

This should have been part of r265444.

END
K 10
svn:author
V 3
ian
K 8
svn:date
V 27
2014-05-06T14:19:54.782479Z
K 7
svn:log
V 134
Add a public routine to set the L2 cache ram latencies.  This can be
called by platform init routines to fine-tune cache performance.

END
K 10
svn:author
V 3
ian
K 8
svn:date
V 27
2014-05-06T14:26:24.357437Z
K 7
svn:log
V 75
Enable PL310 power-saving modes and tune the cache ram latencies for imx6.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T14:33:18.304163Z
K 7
svn:log
V 199
Fix the upgrade path for fmake by allowing the include of src.opts.mk
to fail and falling back on the conservative testing of variables
already in place. This should stop the tide of tinderbox mail.

END
K 10
svn:author
V 6
brooks
K 8
svn:date
V 27
2014-05-06T14:38:03.958963Z
K 7
svn:log
V 653
MFC r265097:

Merge from CheriBSD:

commit 1d1b908107255ffdff4d17f015d8f057d73cc6cb
Author: Brooks Davis <brooks@one-eyed-alien.net>
Date:   Fri Mar 28 16:24:45 2014 +0000

    Add a long needed seatbelt.

    Exit with an error when make is called without a target at the top level
    rather than poluting the source tree and causing use confusion in future
    builds.

commit a9d9aa341b2f4308a227ab460ba85f1f287ad028
Author: Brooks Davis <brooks@one-eyed-alien.net>
Date:   Tue Apr 29 16:06:12 2014 +0000

    Simplify seatbelt added in 1d1b908 based in feedback.

    Discussed with:     imp@FreeBSD.org

Reviewed by:	imp
Sponsored by:	DARPA, AFRL

END
K 10
svn:author
V 6
brooks
K 8
svn:date
V 27
2014-05-06T15:38:44.921862Z
K 7
svn:log
V 653
MFC: r265097

Merge from CheriBSD:

commit 1d1b908107255ffdff4d17f015d8f057d73cc6cb
Author: Brooks Davis <brooks@one-eyed-alien.net>
Date:   Fri Mar 28 16:24:45 2014 +0000

    Add a long needed seatbelt.

    Exit with an error when make is called without a target at the top level
    rather than poluting the source tree and causing use confusion in future
    builds.

commit a9d9aa341b2f4308a227ab460ba85f1f287ad028
Author: Brooks Davis <brooks@one-eyed-alien.net>
Date:   Tue Apr 29 16:06:12 2014 +0000

    Simplify seatbelt added in 1d1b908 based in feedback.

    Discussed with:     imp@FreeBSD.org

Reviewed by:	imp
Sponsored by:	DARPA, AFRL

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T15:44:34.152621Z
K 7
svn:log
V 90
Add helpful note about possible workarounds for (as yet) unknown
breakage. Also fix typo.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T15:44:41.943168Z
K 7
svn:log
V 101
Time to prune entries for RELENG_7 and stable/8. They are still in
svn, for the historically minded.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2014-05-06T15:44:46.620766Z
K 7
svn:log
V 493
No need to install man pages for bootstrapping new make. Some
environments (that I can't reproduce locally, but that others have
reported) seem to get tripped up by this man page install. There's
really no need to do it, so turn off the man pages using the most
portable method. We can't just directly set MK_MAN=no here because
we're bootstrapping in the host environment and such a setting was
forbidden until very recently. NO_MAN= can produce a warning, but for
now the warning is benign.

END
K 10
svn:author
V 6
marius
K 8
svn:date
V 27
2014-05-06T16:29:02.172529Z
K 7
svn:log
V 303
- Allow foot shooting with the resetconfig command via the -f option.
- Fix typos preventing -f to actually work with the create command.
- Initialize flags to zero rather than using stack garbage when handling
  the grow command.

MFC after:	3 days
Sponsored by:	Bally Wulff Games & Entertainment GmbH

END
K 10
svn:author
V 6
tuexen
K 8
svn:date
V 27
2014-05-06T16:51:07.637985Z
K 7
svn:log
V 199
Remove unused code. This is triggered by the bugreport of Sylvestre Ledru
which deal with useless code in the user land stack:
https://bugzilla.mozilla.org/show_bug.cgi?id=1003929

MFC after: 3 days

END
K 10
svn:author
V 5
markj
K 8
svn:date
V 27
2014-05-06T18:07:58.797709Z
K 7
svn:log
V 415
Add a postinit debugger hook to rtld. This will be used by dtrace(1) to halt
the victim process before its entry point is called, at which point probes
and DOF data are registered with the kernel. The r_debug_state hook cannot
be used for this purpose, as it is called before the program's init routines
are invoked and in particular before DOF data is registered (via drti.o).

Reviewed by:	kib
MFC after:	2 weeks

END
K 10
svn:author
V 5
markm
K 8
svn:date
V 27
2014-05-06T18:42:24.674125Z
K 7
svn:log
V 56
MFC - tracking commit.
Merging r265354 through r265456.

END
K 10
svn:author
V 7
delphij
K 8
svn:date
V 27
2014-05-06T19:03:04.315142Z
K 7
svn:log
V 334
Import George Wilson's change for Illumos #4730:

	4730 metaslab group taskq should be destroyed in metaslab_group_destroy()
	Reviewed by: Alex Reece <alex.reece@delphix.com>
	Reviewed by: Matthew Ahrens <mahrens@delphix.com>
	Reviewed by: Sebastien Roy <sebastien.roy@delphix.com>

	Original author: George Wilson

MFC after:	3 days

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-06T19:18:20.826238Z
K 7
svn:log
V 77
r253688:
Reserve room for ioctls that aren't in this copy of the driver yet.

END
K 10
svn:author
V 7
dchagin
K 8
svn:date
V 27
2014-05-06T19:38:16.239496Z
K 7
svn:log
V 120
Change linux clock_gettime, clock_settime, clock_getres,
clock_nanosleep syscalls definition to match actual linux one.

END
K 10
svn:author
V 7
dchagin
K 8
svn:date
V 27
2014-05-06T19:39:57.589871Z
K 7
svn:log
V 19
Regen for r265460.

END
K 10
svn:author
V 6
marcel
K 8
svn:date
V 27
2014-05-06T20:34:21.465698Z
K 7
svn:log
V 89
In apm_write(), both fd and imgsz are referenced, so don't mark the
arguments as unused.

END
K 10
svn:author
V 6
scottl
K 8
svn:date
V 27
2014-05-06T20:40:16.018062Z
K 7
svn:log
V 436
Due to reasons unknown at this time, the system can be forced to write
a journal block even when there are no journal entries to be written.
Until the root cause is found, handle this case by ensuring that a
valid journal segment is always written.

Second, the data buffer used for writing journal entries was never
being scrubbed of old data.  Fix this.

Submitted by:	Takehara Mikihito
Obtained from:	Netflix, Inc.
MFC after:	3 days

END
K 10
svn:author
V 7
delphij
K 8
svn:date
V 27
2014-05-06T21:30:58.758857Z
K 7
svn:log
V 269
Sort .ALLSRC before concatenating files together.  This makes sure that the
file are always built the same.

(Note that Header and Localstuff must appear first and in that order, the
sorting does not affect as a coincident effect).

Submitted by:	sjg
MFC after:	3 days

END
K 10
svn:author
V 7
delphij
K 8
svn:date
V 27
2014-05-06T21:34:01.826781Z
K 7
svn:log
V 122
Don't reply monlist request when it's not enabled.

No objection from:	roberto (but all bugs are mine)
MFC after:	2 weeks

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T21:47:43.632960Z
K 7
svn:log
V 236
MFC: r264681
Modify the NFSv4 client open/create RPC so that it acquires
post-open/create directory attributes. This allows the RPC to
name cache the newly created file and reduces the lookup RPC
count by about 10% for software builds.

END
K 10
svn:author
V 6
marcel
K 8
svn:date
V 27
2014-05-06T21:51:16.171539Z
K 7
svn:log
V 35
Add missing svn:keywords property.

END
K 10
svn:author
V 6
marcel
K 8
svn:date
V 27
2014-05-06T21:54:05.361320Z
K 7
svn:log
V 312
Add mkimg_write() which combines lseek(2) and write(2) and uses
sector granularity for both offset and length. Have all schemes
use mkimg_write() instead of mkimg_seek() followed by write(2).

Now that schemes don't use lseek(2) nor write(2) directly, it's
easier to support output formats other than raw disks.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T21:54:52.216024Z
K 7
svn:log
V 266
MFC: r264705, r264749
Modify the NFSv4 client create/mkdir RPC so that it acquires
post-create/mkdir directory attributes. This allows the RPC to
name cache the newly created directory and reduces the lookup RPC
count for applications creating a lot of directories.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T21:59:48.891621Z
K 7
svn:log
V 179
MFC: r264738
For an NFSv4 mount with the "nocto" option, don't get the
up to date file attributes upon close. This reduces the
Getattr RPC count by about 65% for software builds.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2014-05-06T22:04:50.338930Z
K 7
svn:log
V 172
MFC: r264739
Add {} braces so that the code conforms to the indentation.
Fortunately, I don't think doing the assignment of cap->tsomax
unconditionally causes any problem.

END
K 10
svn:author
V 7
asomers
K 8
svn:date
V 27
2014-05-06T22:06:39.082830Z
K 7
svn:log
V 538
dd(1) uses gettimeofday(2) to compute the throughput statistics.  However,
gettimeofday returns the system clock, which may jump forward or back,
especially if NTP is in use.  If the time jumps backwards, then dd will see
negative elapsed time, round it up to 1usec, and print an absurdly fast
transfer rate.

The solution is to use clock_gettime(2) with CLOCK_MONOTONIC_PRECISE as the
clock_id.  That clock advances steadily, regardless of changes to the system
clock.

Reviewed by:	delphij
MFC after:	3 days
Sponsored by:	Spectra Logic

END
K 10
svn:author
V 3
ken
K 8
svn:date
V 27
2014-05-06T22:13:38.583402Z
K 7
svn:log
V 206
Change the device name for mpr(4) from /dev/mpr_N to /dev/mprN.

This is more consistent with the existing mps(4) behavior.

Reviewed by:	Steve McConnell <stephen.mcconnell@avagotech.com>
MFC after:	3 days

END
K 10
svn:author
V 6
adrian
K 8
svn:date
V 27
2014-05-06T23:28:37.532714Z
K 7
svn:log
V 266
Bump the default C-state to Cmax, rather than the kernel default
of C1.

This may not stay through 11.0-RELEASE, but at least having it
on by default in -HEAD will expose (more) issues with broken hardware.

Note: I have no plans or desire to MFC this to stable/10.

END
K 10
svn:author
V 6
emaste
K 8
svn:date
V 27
2014-05-06T23:28:48.164548Z
K 7
svn:log
V 58
MFC r261908 by ian: Fix a typo, C_ALSOLUTE -> C_ABSOLUTE.

END
K 10
svn:author
V 3
alc
K 8
svn:date
V 27
2014-05-07T00:32:49.262095Z
K 7
svn:log
V 865
MFC r262338
  When the kernel is running in a virtual machine, it cannot rely upon the
  processor family to determine if the workaround for AMD Family 10h Erratum
  383 should be enabled.  To enable virtual machine migration among a
  heterogeneous collection of physical machines, the hypervisor may have
  been configured to report an older processor family with a reduced feature
  set.  Effectively, the reported processor family and its features are like
  a "least common denominator" for the collection of machines.

  Therefore, when the kernel is running in a virtual machine, instead of
  relying upon the processor family, we now test for features that prove
  that the underlying processor is not affected by the erratum.  (The
  features that we test for are unlikely to ever be emulated in software
  on an affected physical processor.)

PR:		186061

END
K 10
svn:author
V 6
emaste
K 8
svn:date
V 27
2014-05-07T00:51:24.376540Z
K 7
svn:log
V 570
Merge -fstandalone-debug from Clang r198655:

  Implement a new -fstandalone-debug option. rdar://problem/15685848
  It controls everything that -flimit-debug-info used to, plus the
  vtable type optimization. The old -fno-limit-debug-info option is now an
  alias to -fstandalone-debug and vice versa.

  Standalone is the default on Darwin until dtrace is updated to work with
  non-standalone debug info (rdar://problem/15758808).

  Note: I kept the LimitedDebugInfo name in CodeGenOptions::DebugInfoKind
  because NoStandaloneDebugInfo sounded even more confusing.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-07T02:13:55.551227Z
K 7
svn:log
V 1159
MFC r253701, r253829, r253873, r253889, r253890, r254577, r254727, and r254933.

r253701:
Display a string instead of a numeric code in the linkdnrc sysctl.

r253829:
Display SGE tunables in the sysctl tree.

dev.t5nex.0.fl_pktshift: payload DMA offset in rx buffer (bytes)
dev.t5nex.0.fl_pad: payload pad boundary (bytes)
dev.t5nex.0.spg_len: status page size (bytes)
dev.t5nex.0.cong_drop: congestion drop setting

r253873:
Set up congestion manager context properly for T5 based cards.

r253889:
Fix previous commit (r253873).  "cong" has one bit per channel but the
congestion channel map has 1 nibble per channel.  So bits wxyz need to
be blown up into 000w000x000y000z.

r253890:
Display temperature sensor data.  Shows -1 if sensor not
available on the card.

# sysctl dev.t4nex.0.temperature
# sysctl dev.t5nex.0.temperature

r254577:
Display P/N information in the description.

r254727:
There is no need to hold the freelist lock around alloc/free of
software descriptors.  This also silences WITNESS warnings when
the software descriptors are allocated with M_WAITOK.

r254933:
Use correct mailbox and PCIe PF number when querying RDMA parameters.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-07T03:06:50.060294Z
K 7
svn:log
V 331
MFC r255047 (with a manual tweak to match the ext_free in stable/9):

Add a routine for attaching an mbuf to a buffer with an external
refcount.  This one is willing to work with buffers that may already be
referenced.  MEXTADD/m_extadd are suitable only for the first attachment
to a cluster -- they initialize the refcount to 1.

END
K 10
svn:author
V 6
bryanv
K 8
svn:date
V 27
2014-05-07T03:17:21.929619Z
K 7
svn:log
V 989
MFC r255111, r255112, r255131, r255167, r256066, r261150, r261151,
    r261164, r261166, r261167, r261168, r261394, r261395:

This updates the network driver to support multiple queues, and several bug
fixes. Note that multiqueue support is not compiled in by default since that
would change ALTQ behavior.

  - Sync VirtIO net device header file from recent Linux
  - Import multiqueue VirtIO net driver
  - Fix build with gcc
  - Do not hold the vtnet Rx queue lock when calling up into the stack
  - Read and write the MAC address in the config space byte by byte
  - Also include the mbuf's csum_flags in an assert message
  - Remove stray space
  - Move duplicated transmit start code into a single function
  - Avoid queue unlock followed by relock when the enable interrupt race is
    lost
  - Check for a full virtqueue in the multiqueue transmit path
  - Do not place the sglist used for Rx/Tx on the stack
  - Use m_defrag() instead of m_collapse() to compact a long mbuf chain

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-07T04:00:05.448441Z
K 7
svn:log
V 843
MFC r255050, r255052.

r255050:
Implement support for rx buffer packing.  Enable it by default for T5
cards.

This is a T4 and T5 chip feature which lets the chip deliver multiple
Ethernet frames in a single buffer.  This is more efficient within the
chip, in the driver, and reduces wastage of space in rx buffers.

- Always allocate rx buffers from the jumbop zone, no matter what the
  MTU is.  Do not use the normal cluster refcounting mechanism.
- Reserve space for an mbuf and a refcount in the cluster itself and let
  the chip DMA multiple frames in the rest.
- Use the embedded mbuf for the first frame and allocate mbufs on the
  fly for any additional frames delivered in the cluster.  Each of these
  mbufs has a reference on the underlying cluster.

r255052:
Fix the sysctl that displays whether buffer packing is enabled
or not.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-07T04:21:07.176375Z
K 7
svn:log
V 530
MFC r255198, r255410, and r255411.

r255198:
For TOE connections, the window scale factor in CPL_PASS_ACCEPT_REQ is
set to 15 to indicate that the peer did not send a window scale option
with its SYN.  Do not send a window scale option in the SYN|ACK reply
in that case.

r255410:
Fix a miscalculation that caused cxgbe/tom to auto-increment
a TOE socket's tx buffer size too aggressively.

r255411:
Rework the tx credit mechanism between the cxgbe/tom driver
and the card.  This helps smooth out some burstiness in the
exchange.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-07T05:06:55.919094Z
K 7
svn:log
V 62
MFC r256459:
cxgbe(4): Update T4 and T5 firmwares to 1.9.12.0

END
K 10
svn:author
V 3
ken
K 8
svn:date
V 27
2014-05-07T05:11:16.197394Z
K 7
svn:log
V 111
Remove some debugging code.

Submitted by:	Steve McConnell <stephen.mcconnell@avagotech.com>
MFC after:	3 days

END
K 10
svn:author
V 3
ken
K 8
svn:date
V 27
2014-05-07T05:14:48.564665Z
K 7
svn:log
V 298
Hold the SIM lock when calling xpt_create_path() and xpt_action() in
mprsas_SSU_to_SATA_devices().

This fixes an assertion on shutdown with INVARIANTS enabled with SATA
drives present on an IR firmware controller.

Reviewed by:	Steve McConnell <stephen.mcconnell@avagotech.com>.
MFC after:	3 days

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2014-05-07T05:28:23.514669Z
K 7
svn:log
V 184
MFC r256477:
cxgbe(4): Store the log2 of the # of doorbells per BAR2 page for both
ingress and egress queues, and for both T4 and T5.  These values are
used by the T4/T5 iWARP driver.

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:10:55.185792Z
K 7
svn:log
V 134
MFC r263742:

Fix harmless warning after reconnecting a session and not doing anything
with it.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:12:59.789358Z
K 7
svn:log
V 107
MFC r263743:

Move the ic_outstanding_count under #ifdef DIAGNOSTIC.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:14:41.774634Z
K 7
svn:log
V 107
MFC r263745:

Target Transfer Tag is opaque; no need to htonl(3) it.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:18:03.251644Z
K 7
svn:log
V 148
MFC r263810:

Rework cfiscsi_datamove_in() to obey expected data transfer length
received from the initiator.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:20:35.674971Z
K 7
svn:log
V 79
MFC r263811:

Remove ctl_mem_pool.{c,h}.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:22:51.073242Z
K 7
svn:log
V 139
MFC r263978:

Make it possible to have multiple CTL worker threads.  Leave the default
of 1 for now.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:24:46.450916Z
K 7
svn:log
V 240
MFC r263979:

Hide CTL messages about SCSI error responses.  Too many users take
them for actual target errors.  They can be enabled back by setting
kern.cam.ctl.verbose=1, or booting with bootverbose.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:26:34.193069Z
K 7
svn:log
V 177
MFC r264020:

Remove the homegrown ctl_be_block_io allocator, replacing it with UMA.
There is no performance difference.

Reviewed by:	mav@
Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:29:01.681171Z
K 7
svn:log
V 275
MFC r264022:

Get rid of ICL lock; use upper-layer (initiator or target) lock instead.
This avoids extra locking in icl_pdu_queue(); the upper layer needs to call
it while holding its own lock anyway, to avoid sending PDUs out of order.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:31:45.229459Z
K 7
svn:log
V 196
MFC r264023:

Instead of "icltx" and "iclrx", use thread names with prefix from upper
layer, so that one can see which side of the stack the threads are for.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:34:03.429664Z
K 7
svn:log
V 124
MFC r264024:

Use atomic ops instead of mutexes where appropriate.

Submitted by:	mav@
Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:38:19.810784Z
K 7
svn:log
V 251
MFC r264025:

Get rid of the "autoscaling", instead just set socket buffer sizes
in the usual way.  The only thing the old code did was making things
less predictable.

MFC r264058:

Fix build, broken by r264025.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:41:33.871000Z
K 7
svn:log
V 70
MFC r264026:

Enable a KASSERT.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:44:19.141667Z
K 7
svn:log
V 106
MFC r264109:

We don't need TAILQ for iSCSI PDUs; STAILQ is enough.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T06:46:59.566456Z
K 7
svn:log
V 109
MFC r264110:

All the iSCSI sysctls are also tunables; advertise that.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:17:11.403134Z
K 7
svn:log
V 146
MFC r264122:

Rework the iSCSI PDU transmit code to avoid lock contention and coalesce
PDUs before sending.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:18:38.823085Z
K 7
svn:log
V 121
MFC r264163:

Remove hack to pass STAILQ to a function and do it properly instead.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:20:02.381967Z
K 7
svn:log
V 133
MFC r264264 by mav@:

Wakeup only one thread of added in r263978i at a time.

This slightly reduces lock congestion between threads.

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:25:47.689359Z
K 7
svn:log
V 96
MFC r263740:

Use a less unusual syntax in debug printfs.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:28:23.981850Z
K 7
svn:log
V 118
MFC r264500:

Stop treating LUN 0 as mandatory.  There is no reason to do that.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:29:39.989383Z
K 7
svn:log
V 205
MFC r264524:

Make it possible for the iSCSI target side to operate in both normal
and ICL_KERNEL_PROXY mode, and fix some bit rot so the latter actually
works again.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:31:25.099304Z
K 7
svn:log
V 190
MFC r264525:

Add some stuff to make it easier to figure out for the system administrator
whether the ICL_KERNEL_PROXY stuff got compiled in correctly.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:32:45.551722Z
K 7
svn:log
V 187
MFC r264526:

Properly identify target portal when running in proxy mode.  While here,
remove CTL_ISCSI_CLOSE, it wasn't used or implemented anyway.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:33:56.718016Z
K 7
svn:log
V 116
MFC r264527:

Make it possible to interrupt login when running in proxy mode.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:35:21.089060Z
K 7
svn:log
V 483
MFC r264528:

Rework the way we enable CTL iSCSI port.  Previously conf_apply()
needed it to be already enabled, because listening in proxy mode
requires it; however, it's conf_apply() that opens pidfiles,
so it resulted in port being enabled before pidfile was opened.
This was not so bad, but it was also disabled when pidfile couldn't
be opened due to ctld already running; this means that starting
second ctld instance screwed up the first.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:36:46.570344Z
K 7
svn:log
V 131
MFC r264529:

Use socket address from accept(2) instead of retrieving it via
getpeername(2).

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:37:55.152449Z
K 7
svn:log
V 116
MFC r264530:

Properly pass the initiator address when running in proxy mode.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:39:16.946252Z
K 7
svn:log
V 62
MFC r264531:

Constify.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:40:45.867180Z
K 7
svn:log
V 94
MFC r264532:

Use proper terminology in debug messages.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:41:58.177663Z
K 7
svn:log
V 80
MFC r264533:

Use consistent punctuation.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 7
dchagin
K 8
svn:date
V 27
2014-05-07T07:42:47.806093Z
K 7
svn:log
V 192
Be a bit secure. To avoid a double fp lookup add a kern_kevent_fp
counterpart for kern_kevent with file pointer parameter instead
of file descriptor an pass the buck to it.

Suggested by: mjg

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:43:13.008204Z
K 7
svn:log
V 118
MFC r264534:

If we fail to create LUN, try again on next configuration reload.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:44:17.752949Z
K 7
svn:log
V 61
MFC r264535:

English.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:45:22.074584Z
K 7
svn:log
V 139
MFC r264536:

Get rid of ISCSIDCLOSE; it wasn't used and is redundant anyway,
because of ISCSIDFAIL.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:46:23.610807Z
K 7
svn:log
V 116
MFC r264537:

Be more strict with locking for is_waiting_for_iscsid variable.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:47:29.277254Z
K 7
svn:log
V 74
MFC r264538:

Remove useless debug.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:48:32.896744Z
K 7
svn:log
V 131
MFC r264544:

Add kern.iscsi.fail_on_disconnection; this is required for gmultipath
to work.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:53:24.690764Z
K 7
svn:log
V 528
MFC r264348 by mav@:

Improve use of socket buffer upcalls.

Use soreadable()/sowriteable() in socket upcalls to avoid extra wakeups
until we have enough data to read or space to write.

Increase partial receive len from 1K to 128K to not wake up on every
received packet.

This significantly reduces locks congestion and CPU usage and improves
throughput for large I/Os on NICs without TSO and LRO.

MFC r264552 by mav@:

Close the race in older code, that caused connection stuck after r264348.

Sponsored by:	iXsystems, Inc.

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:54:47.833970Z
K 7
svn:log
V 62
MFC r264545:

Fix typo.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2014-05-07T07:56:36.280487Z
K 7
svn:log
V 281
MFC r264549:

Make it possible for the initiator side to operate in both proxy
and normal mode; this makes it possible to compile with the former
by default, but use it only when neccessary.  That's especially
important for the userland part.

Sponsored by:	The FreeBSD Foundation

END