Го211753
198
830
157
480
204
109
298
231
176
143
805
308
479
263
197
160
160
238
486
390
331
232
336
125
267
401
117
125
122
273
163
133
177
256
157
125
109
433
191
197
463
140
252
162
389
162
115
141
327
177
294
158
217
116
122
111
156
257
158
424
252
177
358
321
229
127
329
218
516
181
237
297
198
290
311
667
175
165
259
121
195
178
291
174
119
158
150
180
112
160
149
271
252
164
326
204
832
141
267
182
336
426
365
165
230
309
657
141
177
230
190
131
249
211
133
216
171
216
790
790
258
436
234
209
213
254
280
241
243
276
404
211
255
386
240
212
161
379
379
442
442
901
249
202
244
230
234
245
142
347
183
347
227
162
164
176
254
353
157
262
249
629
833
141
100
184
162
308
280
403
252
202
317
180
190
408
194
151
594
698
1386
229
214
230
168
160
373
373
143
649
122
122
330
118
480
195
207
163
200

K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-24T13:21:05.656264Z
K 7
svn:log
V 734
Enable fasttrap and make dtraceall depend on fasttrap when building i386
or amd64.

Sponsored by:	The FreeBSD Foundation
> Description of fields to fill in above:                     76 columns --|
> PR:            If a GNATS PR is affected by the change.
> Submitted by:  If someone else sent in the change.
> Reviewed by:   If someone else reviewed your modification.
> Approved by:   If you needed approval for this commit.
> Obtained from: If the change is from a third party.
> MFC after:     N [day[s]|week[s]|month[s]].  Request a reminder email.
> Security:      Vulnerability reference (one per line) or description.
> Empty fields above will be automatically removed.

M    dtrace/dtraceall/dtraceall.c
M    dtrace/Makefile

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-24T13:22:01.619628Z
K 7
svn:log
V 61
Fix a bug with the different filename.

Submitted by:	emaste

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-24T13:38:53.062345Z
K 7
svn:log
V 384
Some fixes so we can build libstdc++ with clang:
o Make the value_type, vector_type, iterator, __mutex_type types of
free_list class so we can access them
o In some cases template keywords must be inserted to treat classes as
dependent template names
o Remove two 'inline' keywords where they do not make sense

Submitted by:	Dimitry Andric <dimitry at andric.com>
Reviewed by:	trema

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2010-08-24T16:08:01.709943Z
K 7
svn:log
V 111
Enable timer interrupt before starting timer. This allows to handle very
short periods without interrupt loss.

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-24T16:11:12.457137Z
K 7
svn:log
V 13
MFC @ 211755

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T16:29:09.326074Z
K 7
svn:log
V 205
The order was correct before.  I'd talked to Nathan about this before,
so this must have been mismerged into tbemd before I merged it back to
head.  This unbreaks this on powerpc64

Submitted by:	nathanw@

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T16:35:26.412238Z
K 7
svn:log
V 138
Change the logic here to match Makefile.inc1.  Having it in two places
suggests an opportunity for refactoring :)

Submitted by:	nathanw@

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2010-08-24T17:46:43.059724Z
K 7
svn:log
V 82
MFC r210448:

Fix alignment for the 'flags' label, and make more room for 'tdev'.

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2010-08-24T17:47:52.809818Z
K 7
svn:log
V 49
MFC r210447:

Add P_HASTHREADS flag description.

END
K 10
svn:author
V 3
avg
K 8
svn:date
V 27
2010-08-24T17:48:22.036323Z
K 7
svn:log
V 712
zfs arc_reclaim_thread: no need to call arc_reclaim_needed when
resetting needfree

needfree is checked at the very start of arc_reclaim_needed.
This change makes code easier to follow and maintain in face of
potential changed in arc_reclaim_needed.

Also, put the whole sub-block under _KERNEL because needfree can be set
only in kernel code.

To do: rename needfree to something else to aovid confusion with
OpenSolaris global variable of the same name which is used in the same
code, but has different meaning (page deficit).

Note: I have an impression that locking around accesses to this variable
as well as mutual notifications between arc_reclaim_thread and
arc_lowmem are not proper.

MFC after:	1 week

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2010-08-24T18:07:59.652053Z
K 7
svn:log
V 215
When ACPI reports current battery consumption rate in mAmps, print it also
in mWatts. Values in mAmps are not always suitable, because they depend on
battery voltage, which depends on battery type and charge level.

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-24T18:17:40.229107Z
K 7
svn:log
V 382
Add PNP id for Compex RL2000.
I'm not sure whether adding this logical id is correct or not
because Compex RL2000 is in the list of supported hardware list.
I guess the Compex RL2000 could be PCI variant while the controller
in question is ISA controller. It seems PNP compat id didn't match
or it had multiple compat ids so isa_pnp_probe() seemed to return
ENOENT.

PR:	kern/80853

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-24T18:40:11.249510Z
K 7
svn:log
V 166
Remove unnecessary controller reinitialization.
CAM filter handling was rewritten long time ago so it should not
require controller reinitialization.

PR:	kern/87506

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-24T18:44:12.979549Z
K 7
svn:log
V 100
vr_init_locked() will stop and reset the controller. Remove
unnecessary vr_stop()/vr_reset() calls.

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-24T18:52:24.641995Z
K 7
svn:log
V 64
Remove unnecessary controller reinitialization.

PR:	kern/87506

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-24T19:41:15.686669Z
K 7
svn:log
V 64
Remove unnecessary controller reinitialization.

PR:	kern/87506

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-24T20:38:01.597576Z
K 7
svn:log
V 144
 - Re-enable umem_write_mtt so we actually write the userspace mappings
   to the card.

Sponsored by:	Isilon Systems, iX Systems, and Panasas.

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-24T20:40:12.354392Z
K 7
svn:log
V 392
 - Provide a mmap_single interface as well as mmap.  mmap_single gives
   the device pager an offset based on the physical address returned by
   the linux mmap handler so that the normal mmap handler can simply
   return the offset as the paddr when a fault happens and we no longer
   have the context required to resolve the address.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-24T20:41:05.163641Z
K 7
svn:log
V 296
 - Zero all locks before calling the appropriate init function as linux
   passes uninitialized memory in when locks are created and bsd expects
   it to be zeroed.  This is much more reliable than converting all
   necessary sites to zero.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-24T20:45:21.145124Z
K 7
svn:log
V 237
 - Use __LP64__ as a mostly correct check for 64bit architectures rather
   than SIZEOF_LONG.  We can't simply use sizeof(long) here as that is not
   available to the preprocessor.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-24T20:50:08.588592Z
K 7
svn:log
V 131
Unify 32-bit and 64-bit PowerPC libthr support. This reduces code
duplication, and simplifies the TBEMD import.

Requested by:	imp

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T20:54:43.602037Z
K 7
svn:log
V 243
Powerpc is special here.  powerpc and powerpc64 use different ABIs, so
their implementations aren't in the same files.  Introduce LIBC_ARCH
and use that in preference to MACHINE_CPUARCH.  Tested by amd64 and
powerpc64 builds (thanks nathanw@)

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T21:16:37.352133Z
K 7
svn:log
V 33
Loopback changes in head @211774

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-24T21:25:58.923617Z
K 7
svn:log
V 173
 - Fix the ibdev_path, it is not used to open the actual device as I had
   thought.  The sysctl path is appropriate.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-24T21:27:02.281774Z
K 7
svn:log
V 307
 - Port the test programs to bsd and allow them to use an inet4 socket
   to communicate parameters before establishing an actual infiniband
   connection.  This works around not having ipoib yet.
 - Add a Makefile to complile the various verbs tests.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T21:28:34.767408Z
K 7
svn:log
V 25
Fix an accidental sed...

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T21:33:32.495973Z
K 7
svn:log
V 33
Loopback changes in head @211778

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2010-08-24T21:38:44.857098Z
K 7
svn:log
V 28
s/ithread/interrupt thread/

END
K 10
svn:author
V 5
edwin
K 8
svn:date
V 27
2010-08-24T22:02:47.054939Z
K 7
svn:log
V 178
See if I can make it working with calendars not synced to the
Gregorian calendar start. The easiest way is to add a year-field
to the calendar and just have a lot of repetition.

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-24T23:14:02.830791Z
K 7
svn:log
V 68
Remove this directory for an attempt to merge from the vendor tree.

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-24T23:16:21.169806Z
K 7
svn:log
V 37
Fix manpage.

Submitted by:	brueffer

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-24T23:17:30.118556Z
K 7
svn:log
V 82
Merge dtracetoolkit/dtruss from the vendor.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-24T23:19:14.139767Z
K 7
svn:log
V 155
Make RTLD work on powerpc64 again. If there is a sub-directory named
MACHINE_ARCH, use that specific one, otherwise use MACHINE_CPUARCH.

Reviewed by:	imp

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-24T23:24:43.479624Z
K 7
svn:log
V 62
Port dtruss to FreeBSD.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-24T23:34:13.426016Z
K 7
svn:log
V 33
Loopback changes in head @211786

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-25T00:05:14.703865Z
K 7
svn:log
V 13
MFC @ 211787

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2010-08-25T00:35:58.411147Z
K 7
svn:log
V 335
If the first iteration of the do loop in replay_prune()
succeeded and a subsequent interation failed to find an
entry to prune, it could loop infinitely, since the
"freed" variable wasn't reset to FALSE. This patch moves
setting freed FALSE to inside the loop to fix the problem.

Tested by:	alan.bryan at yahoo.com
MFC after:	2 weeks

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-25T00:36:06.505945Z
K 7
svn:log
V 98
 - Add missing subdirs to the lib makefile

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-25T01:50:12.787449Z
K 7
svn:log
V 103
 - Add an implementation of mthca_map_user_db()

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-25T02:03:48.299111Z
K 7
svn:log
V 370
Prodded by Yongari, add support for Holtek HT80232.  Add the device
ID, plus the ability to force '16-bit mode' which really means NE-2000
mode.  Other open source drivers suggest that the Holtek misbehaves if
you allow the 8-bit probe.  Also, all of the PCI chips emulate
NE-2000ish cards, so always force 16-bit mode for memory transfers.

PR:		84202 (patch not used)

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-25T02:09:07.541051Z
K 7
svn:log
V 48
On second thought, we need to force 16-bit mode

END
K 10
svn:author
V 7
davidxu
K 8
svn:date
V 27
2010-08-25T03:14:32.502131Z
K 7
svn:log
V 155
If a thread is removed from umtxq while sleeping, reset error code
to zero, this gives userland a better indication that a thread needn't
to be cancelled.

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-25T06:42:47.346740Z
K 7
svn:log
V 67
Update how syscalls are handled to use syscallenter and syscallret

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-25T07:24:52.087143Z
K 7
svn:log
V 293
Add the start of the OABI syscalls. These will be used when the kernel is
built for EABI but the userland is built for OABI.

The syscalls that have been implemented allow me boot FreeBSD into
multi-user mode and allow me to log in. Not all syscalls that need to be
implemented have been yet.

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-25T07:30:33.526074Z
K 7
svn:log
V 67
We are not building this on PowerPC so don't define PAD64_REQUIRED

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-25T07:31:18.673023Z
K 7
svn:log
V 20
Add generated files

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-25T07:33:35.143746Z
K 7
svn:log
V 44
Sync up XLR tick.c with the new MIPS tick.c

END
K 10
svn:author
V 8
netchild
K 8
svn:date
V 27
2010-08-25T08:09:42.276201Z
K 7
svn:log
V 229
- Change the threshold from 'running next scrub the <value+1>th day after the
  last one' to 'running next scrub the <value>th day after the last one'.
- Improve wording.

Requested by:	jhell <jhell@DataIX.net>
MFC after:	1 week

END
K 10
svn:author
V 5
maxim
K 8
svn:date
V 27
2010-08-25T08:37:18.807135Z
K 7
svn:log
V 83
o Correct typo.

Submitted by:	Bojidara Marinchovska via -stable
MFC after:	1 week

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-25T08:48:54.442500Z
K 7
svn:log
V 196
RMI XLR platform code clean-up.

- move PIC code to xlr_machdep.c
- move fast message ring code completely to on_chip.c
- move memory initialization to a new function xlr_mem_init()
- style fixes

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2010-08-25T08:49:21.601018Z
K 7
svn:log
V 66
MFC r211455:
Remove bintime_cmp() function, unused since r200086.

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-25T09:10:32.456385Z
K 7
svn:log
V 121
Call the necessary DTrace function pointers when we have different kinds
of traps.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-25T09:30:48.793427Z
K 7
svn:log
V 20
Fix copyright note.

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-25T09:32:12.481660Z
K 7
svn:log
V 26
Add the $FreeBSD$ ID tag.

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-25T09:34:34.419178Z
K 7
svn:log
V 15
Tweak comment.

END
K 10
svn:author
V 5
gabor
K 8
svn:date
V 27
2010-08-25T09:48:21.066106Z
K 7
svn:log
V 62
- Regen after adding WITH_BSD_GREP and removing WITH_GNU_GREP

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-25T09:53:00.165273Z
K 7
svn:log
V 159
Rename on_chip.c to fmn.c, as the file has just the fast messaging network
code.  The iodi.c has the bus for SoC devices, so the name on_chip.c is
misleading.

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2010-08-25T11:11:14.991621Z
K 7
svn:log
V 66
MFC r211455:
Remove bintime_cmp() function, unused since r200086.

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-25T11:49:48.279987Z
K 7
svn:log
V 326
XLR PIC code update and style(9) fixes.

- style(9) fixes to mips/rmi platform files
- update pic.h to add pic_setup_intr() and use pic_setup_intr() for setting
  up interrupts which are routed thru PIC.
- remove rmi_spin_mutex_safe and haslock, and make sure that the functions
  are called only after mutexes are available.

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-25T12:10:20.954108Z
K 7
svn:log
V 154
XLR PIC code update.
- Fix a bug in xlr_pic_init (use irq in PIC_IRQ_IS_EDGE_TRIGGERED)
- use new macro PIC_INTR_TO_IRQ() and PIC_IRT_x() in xlr_pic_init

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-25T12:35:36.393638Z
K 7
svn:log
V 82
Add the necessary DTrace function pointers.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-25T13:37:55.068162Z
K 7
svn:log
V 260
Provide timecounter based on XLR PIC timer.

- Use timer 7 in XLR PIC as a 32 counter
- provide pic_init_timer(), pic_set_timer(), pic_timer_count32() and
  pic_timer_count() PIC timer operations.
- register this timer as platform_timecounter on rmi platform.

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-25T15:21:26.921561Z
K 7
svn:log
V 224
With the current code the the client and the server must be in the same
subnet.
Specify a new parameter for passing the gateway and allow client and
server not being in the same subnet.

Obtained from:	Sandvine Incorporated

END
K 10
svn:author
V 2
jh
K 8
svn:date
V 27
2010-08-25T15:29:12.989348Z
K 7
svn:log
V 137
Call devfs_populate_vp() from devfs_getattr(). It was possible that
fstat(2) returned stale information through an open file descriptor.

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-25T16:23:50.470586Z
K 7
svn:log
V 27
Fix build of ppc32 loader.

END
K 10
svn:author
V 5
brian
K 8
svn:date
V 27
2010-08-25T18:09:51.894155Z
K 7
svn:log
V 234
If we read zero bytes from the directory, early out with ENOENT
rather than forging ahead and interpreting garbage buffer content
and dirent structures.

This change backs out r211684 which was essentially a no-op.

MFC after:	1 week

END
K 10
svn:author
V 3
osa
K 8
svn:date
V 27
2010-08-25T18:11:01.996282Z
K 7
svn:log
V 125
Add one more new memory day for Russian Federation: the end of Second World War.

Obtained from:	http://kremlin.ru/acts/8444

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-25T19:12:05.222282Z
K 7
svn:log
V 423
Intel QPI chipsets actually provide two extra "non-core" PCI buses that
provide PCI devices for various hardware such as memory controllers, etc.
These PCI buses are not enumerated via ACPI however.  Add qpi(4) psuedo
bus and Host-PCI bridge drivers to enumerate these buses.  Currently the
driver uses the CPU ID to determine the bridges' presence.

In collaboration with:	Joseph Golio @ Isilon Systems
MFC after:	2 weeks

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-25T20:37:58.105781Z
K 7
svn:log
V 89
Correctly ensure that the CPU family is 0x6, not non-zero.

Submitted by:	Dimitry Andric

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-25T20:48:24.176072Z
K 7
svn:log
V 136
Allow ABIs to provide their own LIBC_ARCH in a more generic way. As a side
effect, this fixes the build on powerpc64.

Reviewed by:	imp

END
K 10
svn:author
V 4
jkim
K 8
svn:date
V 27
2010-08-25T20:52:40.067283Z
K 7
svn:log
V 203
Check opcode for short jump as well.  Some option ROMs do short jumps
(e.g., some NVIDIA video cards) and we were not able to do POST while
resuming because we only honored long jump.

MFC after:	3 days

END
K 10
svn:author
V 4
jkim
K 8
svn:date
V 27
2010-08-25T21:03:50.412799Z
K 7
svn:log
V 104
Add x86bios_set_intr() to set interrupt vectors for real mode and simplify
x86bios_get_intr() a little.

END
K 10
svn:author
V 4
jkim
K 8
svn:date
V 27
2010-08-25T21:13:23.818082Z
K 7
svn:log
V 196
Increase maximum number of page table entries per VM86 context from 8 to 24
pages, yet again.  Now we can allocate a whole segment, which is required
for shadowing option ROM images, for example.

END
K 10
svn:author
V 5
trasz
K 8
svn:date
V 27
2010-08-25T21:32:08.795770Z
K 7
svn:log
V 216
Revert r210194, adding a comment explaining why calls to chgproccnt()
in unionfs are actually needed.  I have a better fix in trasz_hrl p4 branch,
but now is not a good moment to commit it.

Reported by:	Alex Kozlov

END
K 10
svn:author
V 4
jkim
K 8
svn:date
V 27
2010-08-25T22:09:02.745026Z
K 7
svn:log
V 573
Add an experimental feature to shadow video BIOS.  Long ago, this trick was
supported by many BIOSes to improve performance of VESA BIOS calls for real
mode OSes but it is not our intention here.  However, this may help some
platforms where the video ROMs are inaccessible after suspend, for example.
Note it may consume up to 64K bytes of contiguous memory depending on video
controller model when it is enabled.  This feature can be disabled by
setting zero to 'debug.vesa.shadow_rom' loader tunable via loader(8) or
loader.conf(5).  The default is 1 (enabled), for now.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2010-08-25T22:19:52.154506Z
K 7
svn:log
V 78
MFC: r210834
Add some mutex locking on the nfsnode to the regular NFS client.

END
K 10
svn:author
V 4
jkim
K 8
svn:date
V 27
2010-08-25T22:48:18.077987Z
K 7
svn:log
V 72
Fix a debugging message under bootverbose.  This address is not linear.

END
K 10
svn:author
V 8
rmacklem
K 8
svn:date
V 27
2010-08-25T23:23:00.568489Z
K 7
svn:log
V 161
Add mutex locking for the call to replay_prune() in
replay_setsize(), since replay_prune() expects the
rc_lock to be held when it is called.

MFC after:	2 weeks

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-26T05:16:00.897692Z
K 7
svn:log
V 29
Rescue doesn't work for n64.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-26T05:25:51.691514Z
K 7
svn:log
V 102
Ugly kludge to paper over some kind of ld bug and/or misuse: don't
build uathload on mips n64 either.

END
K 10
svn:author
V 7
davidxu
K 8
svn:date
V 27
2010-08-26T07:09:48.573172Z
K 7
svn:log
V 82
Decrease rdlock count only when thread unlocked a reader lock.

MFC after:	3 days

END
K 10
svn:author
V 5
edwin
K 8
svn:date
V 27
2010-08-26T07:44:54.271746Z
K 7
svn:log
V 196
Instead of being able to handle the Judiac Calendar properly (Lunar
calendar, so the dates never match the Gregorian calendars), we
make calendar(1) support years in the definition in the events.

END
K 10
svn:author
V 5
edwin
K 8
svn:date
V 27
2010-08-26T07:57:45.965895Z
K 7
svn:log
V 80
Do only the years once :-)

Add a note to the man-page on how to use the years.

END
K 10
svn:author
V 7
davidxu
K 8
svn:date
V 27
2010-08-26T09:04:27.428440Z
K 7
svn:log
V 23
eliminate unused code.

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-26T10:27:45.679641Z
K 7
svn:log
V 63
Fix for style(9) by removing a space at the start of each line

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-26T11:20:57.668998Z
K 7
svn:log
V 58
Fix typo.

Submitted by:	Ben Kaduk <minimarmot gmail com>

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-26T11:22:12.638143Z
K 7
svn:log
V 85
Sync DTrace bits with amd64 and fix the build.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-26T11:25:09.023299Z
K 7
svn:log
V 20
MFC r211704:
Style.

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-26T11:45:39.218366Z
K 7
svn:log
V 65
Add a man page for dtruss.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-26T11:46:38.349005Z
K 7
svn:log
V 54
Install dtruss.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-26T13:00:29.279537Z
K 7
svn:log
V 175
Mark __JCR_LIST__, __DTOR_END__, __JCR_END__, __FRAME_END__ as used to
avoid segfaults when building with clang.

Permission to backport given by Jan hubicka <jh at suse.cz>.

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-26T13:04:16.275590Z
K 7
svn:log
V 156
Mark __DTOR_LIST__, __EH_FRAME_BEGIN__ and __CTOR_END__ as used to avoid
segfaults when building with clang.

This comes (partly) from the LLVM svn r41105.

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-26T14:54:12.005253Z
K 7
svn:log
V 72
Guard against TARGET_ABI being undefined (TARGET_ABI will go away soon)

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-26T15:49:52.257754Z
K 7
svn:log
V 233
Make sure TARGET_ABI is defined.  TARGET_ABI will die a horrible death
after we get all of TBEMD merged back into head, and make mips64 imply
n64, so don't bother to make this 100% pretty.  You'll have to settle
for only 64% pretty.

END
K 10
svn:author
V 2
jh
K 8
svn:date
V 27
2010-08-26T16:01:29.985084Z
K 7
svn:log
V 112
Set de_dir for user created symbolic links. This will be needed to be
able to resolve their parent directories.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2010-08-26T19:55:03.228719Z
K 7
svn:log
V 740
MFC r208887, r209115-209116, r209839-209841, r211345-211347

r208887
tunable to control mc5 partition

r209115
make format string a string literal.

r209116
Add knob to get packet timestamps from the hardware.

r209839
Fix bufsize calculation so that cxgbtool can display information for the
last I/O queue too.

r209840
Eliminate ext_intr_task.  The "slow" interrupt handler is already
running on the adapter's task queue.  Just do what the task does
instead of enqueueing it.

r209841
Improved link detection.

r211345
wakeup is required if the adapter lock is released anywhere during
init and not just for the may_sleep case.

r211346
Always reset the XGMAC's XAUI PCS on a link up.

r211347
Fix tx pause quanta and timer calculations.

END
K 10
svn:author
V 3
uqs
K 8
svn:date
V 27
2010-08-26T20:44:12.302954Z
K 7
svn:log
V 49
MFC r204111: Fix common misspelling of hierarchy

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-26T21:37:20.890076Z
K 7
svn:log
V 173
 - Import qperf from git://git.openfabrics.org/~johann/qperf.git/.git rev
   b81434ec094694bae55e20dd1af5f5057d8e5f82

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-26T21:42:45.655218Z
K 7
svn:log
V 89
 - Merge in qperf from ofed base.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 4
jeff
K 8
svn:date
V 27
2010-08-26T22:07:27.073032Z
K 7
svn:log
V 242
 - Re-enable mthca_reset() for pci-e devices.  Warn on pci-x devices and
   skip the reset.  The cards seem to work fine without anyway.
 - Disable debug output for all hardware drivers.

Sponsored by:	Isilon Systems, iX Systems, and Panasas

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-26T23:33:04.258850Z
K 7
svn:log
V 333
- Check the result of malloc(M_NOWAIT) in replay_alloc(). The caller
  (replay_alloc()) knows how to handle replay_alloc() failure.
- Eliminate 'freed_one' variable, it is not needed - when no entry is found
  rce will be NULL.
- Add locking assertions where we expect a rc_lock to be held.

Reviewed by:	rmacklem
MFC after:	2 weeks

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-26T23:41:40.490953Z
K 7
svn:log
V 272
- When VFS_VGET() is not supported, switch to VOP_LOOKUP().
- We are fine by only share-locking the vnode.
- Remove assertion that doesn't hold for ZFS where we cross mount points
  boundaries by going into .zfs/snapshot/<name>/.

Reviewed by:	rmacklem
MFC after:	1 month

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-26T23:44:32.315783Z
K 7
svn:log
V 73
Update comment now that I finally committed r211854.

MFC after:	1 month

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2010-08-27T02:14:02.358367Z
K 7
svn:log
V 138
MFC r204348, r206109

r204348
Support IFCAP_VLAN_HWTSO capability.

r206109
Bump response queue size to 2K, add statistic for starvation.

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2010-08-27T02:29:16.505922Z
K 7
svn:log
V 217
MFC r207643, r207687, r208887, r209115

r207643
T3 hardware filters.

r207687
Do not hold the T3 firmware in memory all the time.

r208887
tunable to control mc5 partition

r209115
make format string a string literal

END
K 10
svn:author
V 2
np
K 8
svn:date
V 27
2010-08-27T02:46:21.335932Z
K 7
svn:log
V 565
MFC r209839-209841, r211345-211347

r209839
Fix bufsize calculation so that cxgbtool can display information for the
last I/O queue too.

r209840
Eliminate ext_intr_task.  The "slow" interrupt handler is already
running on the adapter's task queue.  Just do what the task does
instead of enqueueing it.

r209841
Improved link detection.

r211345
wakeup is required if the adapter lock is released anywhere during
init and not just for the may_sleep case.

r211346
Always reset the XGMAC's XAUI PCS on a link up.

r211347
Fix tx pause quanta and timer calculations.

END
K 10
svn:author
V 7
davidxu
K 8
svn:date
V 27
2010-08-27T03:23:07.249812Z
K 7
svn:log
V 45
clear lock to zero state if it is destroyed.

END
K 10
svn:author
V 7
davidxu
K 8
svn:date
V 27
2010-08-27T05:20:22.794803Z
K 7
svn:log
V 81
Unregister thread specific data destructor when a corresponding dso
is unloaded.

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-27T05:29:59.523957Z
K 7
svn:log
V 129
pmap_mapdev() does not appear to actually need GIANT to be held here,
and asserting that is held breaks drm.

MFC after:	2 weeks

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-27T07:45:50.457188Z
K 7
svn:log
V 93
Whitespace fixes in mips/include, remove unused 'struct tlb' from locore.h

PR:		misc/147471

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-27T08:05:44.273373Z
K 7
svn:log
V 39
MFC r211750:
Remove extra FreeBSD tag.

END
K 10
svn:author
V 5
brian
K 8
svn:date
V 27
2010-08-27T08:54:40.482458Z
K 7
svn:log
V 154
Fix an off-by-one error where we try to split a path name that's
more than 100 characters long and the 101th last character is a
'/'.

MFC after:	3 weeks

END
K 10
svn:author
V 3
uqs
K 8
svn:date
V 27
2010-08-27T09:33:26.722382Z
K 7
svn:log
V 118
MFC r205208:

- Use `Va' for variables instead of `Dv'.
- Correctly spell negative values.
- Also fixes make manlint.

END
K 10
svn:author
V 3
uqs
K 8
svn:date
V 27
2010-08-27T09:35:05.181729Z
K 7
svn:log
V 41
MFC r206615: remove .Pp where not needed

END
K 10
svn:author
V 5
andre
K 8
svn:date
V 27
2010-08-27T09:36:02.660109Z
K 7
svn:log
V 121
MFC r211462:

  Untangle the net.inet.tcp.log_in_vain and net.inet.tcp.log_debug
  sysctl's and remove any side effects.

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-27T09:55:51.889740Z
K 7
svn:log
V 79
Use private namespace for visibility keyword.

Noted by:	bde
MFC after:	3 days

END
K 10
svn:author
V 5
andre
K 8
svn:date
V 27
2010-08-27T09:59:51.277598Z
K 7
svn:log
V 121
MFC r211462:

  Untangle the net.inet.tcp.log_in_vain and net.inet.tcp.log_debug
  sysctl's and remove any side effects.

END
K 10
svn:author
V 5
andre
K 8
svn:date
V 27
2010-08-27T10:15:45.849010Z
K 7
svn:log
V 695
MFC r211464:

  If a TCP connection has been idle for one retransmit timeout or more
  it must reset its congestion window back to the initial window.

  RFC3390 has increased the initial window from 1 segment to up to
  4 segments.

  The initial window increase of RFC3390 wasn't reflected into the
  restart window which remained at its original defaults of 4 segments
  for local and 1 segment for all other connections.  Both values are
  controllable through sysctl net.inet.tcp.local_slowstart_flightsize
  and net.inet.tcp.slowstart_flightsize.

  The increase helps TCP's slow start algorithm to open up the congestion
  window much faster.

  Reviewed by:	lstewart
  MFC after:	1 week

END
K 10
svn:author
V 5
andre
K 8
svn:date
V 27
2010-08-27T10:16:32.204275Z
K 7
svn:log
V 695
MFC r211464:

  If a TCP connection has been idle for one retransmit timeout or more
  it must reset its congestion window back to the initial window.

  RFC3390 has increased the initial window from 1 segment to up to
  4 segments.

  The initial window increase of RFC3390 wasn't reflected into the
  restart window which remained at its original defaults of 4 segments
  for local and 1 segment for all other connections.  Both values are
  controllable through sysctl net.inet.tcp.local_slowstart_flightsize
  and net.inet.tcp.slowstart_flightsize.

  The increase helps TCP's slow start algorithm to open up the congestion
  window much faster.

  Reviewed by:	lstewart
  MFC after:	1 week

END
K 10
svn:author
V 3
uqs
K 8
svn:date
V 27
2010-08-27T10:47:17.453842Z
K 7
svn:log
V 165
MFC r206622,207939,208593,208732,209031: mdoc cleanup

- order prologue by Dd/Dt/Os
- fix prologue
- remove empty lines and other garbage
- uppercase document title

END
K 10
svn:author
V 2
jh
K 8
svn:date
V 27
2010-08-27T11:08:11.565730Z
K 7
svn:log
V 344
Don't attempt to write label with GEOM_BSD based method if the class is
not available. This improves error reporting when bsdlabel(8) is unable
to open a device for writing. If GEOM_BSD was unavailable, only a rather
obscure error message "Class not found" was printed.

PR:		bin/58390
Reviewed by:	ae
Discussed with:	marcel
MFC after:	1 month

END
K 10
svn:author
V 5
andre
K 8
svn:date
V 27
2010-08-27T12:34:53.491613Z
K 7
svn:log
V 139
Use timestamp modulo comparison macro for automatic receive buffer
scaling to correctly handle wrapping of ticks value.

MFC after:	1 week

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T13:54:17.017956Z
K 7
svn:log
V 116
Make comment more readable.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T13:58:38.003531Z
K 7
svn:log
V 120
Add mtx_owned() implementation.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:01:28.261942Z
K 7
svn:log
V 161
Add QUEUE_INSERT() and QUEUE_TAKE() macros that simplify the code a bit.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:06:00.461609Z
K 7
svn:log
V 187
We have sync_start() function to start synchronization, introduce sync_stop()
function to stop it.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:08:10.191557Z
K 7
svn:log
V 148
Log that synchronization was interrupted in a proper place.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:10:25.239908Z
K 7
svn:log
V 150
Don't increase number synchronized bytes in case of an error.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:12:53.116633Z
K 7
svn:log
V 183
- Remove redundant and incorrect 'old' word from debug message.
- Log disconnects as warnings.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:26:37.798093Z
K 7
svn:log
V 311
Implement keepalive mechanism inside HAST protocol so we can detect secondary
node failures quickly for HAST resources that are rarely modified.

Remove XXX from a comment now that the guard thread never sleeps infinitely.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:28:39.263374Z
K 7
svn:log
V 118
Reduce indent where possible.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:35:39.210786Z
K 7
svn:log
V 162
When logging to stdout/stderr don't close those descriptors after fork().

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T14:38:12.982877Z
K 7
svn:log
V 293
- Run hooks in background - don't block waiting for them to finish.
- Keep all hooks we're running in a global list, so we can report when
  they finish and also report when they are running for too long.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T15:16:52.136272Z
K 7
svn:log
V 147
Allow to execute specified program on various HAST events.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T15:20:31.496280Z
K 7
svn:log
V 119
Document new 'exec' parameter.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-27T18:17:46.975772Z
K 7
svn:log
V 69
Simplify the tcp pcblist estimate logic slightly.

MFC after:	3 days

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-27T18:50:12.131574Z
K 7
svn:log
V 286
MFC 211433:
Ensure a minimum "slop" of 10 extra pcb structures when providing a
memory size estimate to userland for pcb list sysctls.  The previous
behavior of a "slop" of n/8 does not work well for small values of n
(e.g. no slop at all if you have less than 8 open UDP connections).

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-27T18:50:32.696082Z
K 7
svn:log
V 286
MFC 211433:
Ensure a minimum "slop" of 10 extra pcb structures when providing a
memory size estimate to userland for pcb list sysctls.  The previous
behavior of a "slop" of n/8 does not work well for small values of n
(e.g. no slop at all if you have less than 8 open UDP connections).

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-27T18:55:24.307070Z
K 7
svn:log
V 349
MFC 210774,210935:
- Tweak the logic to disable CLFLUSH in virtual environments to work around
  problems with flushing the local APIC register range so that it checks
  vm_guest directly.
- Add Xen to the list of virtual vendors.  In the non PV (HVM) case this
  fixes the virtualization detection successfully disabling the CLFLUSH
  instruction.

END
K 10
svn:author
V 3
jhb
K 8
svn:date
V 27
2010-08-27T18:55:48.417328Z
K 7
svn:log
V 349
MFC 210774,210935:
- Tweak the logic to disable CLFLUSH in virtual environments to work around
  problems with flushing the local APIC register range so that it checks
  vm_guest directly.
- Add Xen to the list of virtual vendors.  In the non PV (HVM) case this
  fixes the virtualization detection successfully disabling the CLFLUSH
  instruction.

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-27T19:53:57.069148Z
K 7
svn:log
V 803
Revamp XLR interrupt handling, the previous scheme does not work well on
SMP.

We used to route all PIC based interrupts to cpu 0, and used the per-CPU
interrupt mask to enable/disable interrupts. But the interrupt threads can
run on any cpu on SMP, and the interrupt thread will re-enable the interrupts
on the CPU it runs on when it is done, and not on cpu0 where the PIC will
still send interrupts to.

The fix is move the disable/enable for PIC based interrupts to PIC, we will
ack on PIC only when the interrupt thread is done, and we do not use the
per-CPU interrupt mask.

The changes also introduce a way for subsystems to add a function that
will be called to clear the interrupt on the subsystem. Currently This is
used by the PCI/PCIe for doing additional work during the interrupt
handling.

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-27T19:57:17.243629Z
K 7
svn:log
V 156
Do not call __pthread_cxa_finalize with invalid struct dl_phdr_info.

Reported and tested by:	Fabian Keil <freebsd-listen fabiankeil de>
MFC after:	17 days

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T20:48:12.838268Z
K 7
svn:log
V 109
Add hooks execution.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T20:49:06.534897Z
K 7
svn:log
V 151
Check if no signals were delivered just before going to sleep.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T21:20:32.219822Z
K 7
svn:log
V 137
Correct when we log interrupted synchronization.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T21:26:55.566363Z
K 7
svn:log
V 141
When logging to stdout/stderr, flush after each log.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T21:28:02.048274Z
K 7
svn:log
V 152
When SIGTERM or SIGINT is received, terminate worker processes.

MFC after:	2 weeks
Obtained from:	Wheel Systems Sp. z o.o. http://www.wheelsystems.com

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-27T21:31:15.060976Z
K 7
svn:log
V 50
Use ZFS_CTLDIR_NAME instead of hardcoding ".zfs".

END
K 10
svn:author
V 2
bz
K 8
svn:date
V 27
2010-08-27T21:52:05.446447Z
K 7
svn:log
V 255
MFC r211451:

  When calculating the expected memory size for userspace, also take the
  number of syncache entries into account for the surplus we add to account
  for a possible increase of records in the re-entry window.

  Discussed with:		jhb, silby

END
K 10
svn:author
V 7
attilio
K 8
svn:date
V 27
2010-08-27T21:52:27.560847Z
K 7
svn:log
V 87
Rework the padding by having a 32 bits object and clearing to 0.

Requested by:	emaste

END
K 10
svn:author
V 2
bz
K 8
svn:date
V 27
2010-08-27T21:52:54.510754Z
K 7
svn:log
V 255
MFC r211451:

  When calculating the expected memory size for userspace, also take the
  number of syncache entries into account for the surplus we add to account
  for a possible increase of records in the re-entry window.

  Discussed with:		jhb, silby

END
K 10
svn:author
V 2
bz
K 8
svn:date
V 27
2010-08-27T23:22:58.118157Z
K 7
svn:log
V 135
MFp4 CH=182972:

Add explicit linkstate UP/DOWN for the epair.  This is needed by carp(4)
and other things to work.

MFC after:	5 days

END
K 10
svn:author
V 3
jfv
K 8
svn:date
V 27
2010-08-27T23:24:08.980021Z
K 7
svn:log
V 70
Add support for Intel Cougar Point SMBus controller.

MFC afer 1 week

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-27T23:50:13.874274Z
K 7
svn:log
V 68
Make sure not to access unallocated stats memory.

Reviewed by:	jfv

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-28T00:09:19.185199Z
K 7
svn:log
V 80
Do not call voluntary panic(9) in case of if_alloc() failure.

Reviewed by:	jfv

END
K 10
svn:author
V 3
jfv
K 8
svn:date
V 27
2010-08-28T00:09:46.813154Z
K 7
svn:log
V 161
Add Intel Cougar Point PCH LPC Controller Device IDs
for watchdog support. Also add additional Intel Ibex
Peak (5 Series/3400 Series) PCH IDs.

MFC after a week

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-28T00:16:49.840634Z
K 7
svn:log
V 256
If em(4) failed to allocate RX buffers, do not call panic(9).
Just showing some buffer allocation error is more appropriate
action for drivers. This should fix occasional panic reported on
em(4) when driver encountered resource shortage.

Reviewed by:	jfv

END
K 10
svn:author
V 3
jfv
K 8
svn:date
V 27
2010-08-28T00:23:13.080882Z
K 7
svn:log
V 65
Add Intel Cougar Point PCH HD Audio Controller ID

MFC in a week

END
K 10
svn:author
V 8
mckusick
K 8
svn:date
V 27
2010-08-28T00:27:47.959541Z
K 7
svn:log
V 164
MFC of -r210382 to note that foreground fsck should be run after
a filesystem related panic. Also -r210933 and -r211397 by joel
to fix typos and spelling mistakes.

END
K 10
svn:author
V 8
mckusick
K 8
svn:date
V 27
2010-08-28T00:30:57.072401Z
K 7
svn:log
V 151
MFC of -r210382 to note that foreground fsck should be run after
a filesystem related panic. Also -r210933 by joel to fix typos
and spelling mistakes.

END
K 10
svn:author
V 7
yongari
K 8
svn:date
V 27
2010-08-28T00:34:22.582785Z
K 7
svn:log
V 532
Do not allocate multicast array memory in multicast filter
configuration function. For failed memory allocations, em(4)/lem(4)
called panic(9) which is not acceptable on production box.
igb(4)/ixgb(4)/ix(4) allocated the required memory in stack which
consumed 768 bytes of stack memory which looks too big.

To address these issues, allocate multicast array memory in device
attach time and make multicast configuration success under any
conditions. This change also removes the excessive use of memory in
stack.

Reviewed by:	jfv

END
K 10
svn:author
V 7
delphij
K 8
svn:date
V 27
2010-08-28T00:48:40.570506Z
K 7
svn:log
V 736
MFC r210624 and r210833:

Improve cputemp(4) driver wrt newer Intel processors, especially
Xeon 5500/5600 series:

 - Utilize IA32_TEMPERATURE_TARGET, a.k.a. Tj(target) in place
   of Tj(max) when a sane value is available, as documented
   in Intel whitepaper "CPU Monitoring With DTS/PECI"; (By sane
   value we mean 70C - 100C for now);
 - Print the probe results when booting verbose;
 - Replace cpu_mask with cpu_stepping;
 - Use CPUID_* macros instead of rolling our own.

Catch known CPUs before using IA32_TEMPERATURE_TARGET.
This way we would have an opportunity to hide the
Tj(target) value doesn't seem right stuff if we know
it's not working there.

Add temperature value for Core2 Duo Extreme Mobile that
I have access to.

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-28T06:25:08.353015Z
K 7
svn:log
V 46
Use struct timespec_oabi over struct timespec

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-28T06:25:57.471775Z
K 7
svn:log
V 6
Regen

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-28T06:28:02.973780Z
K 7
svn:log
V 89
Create the functions from syscalls.master. They'll panic to remind me to
implement them.

END
K 10
svn:author
V 6
andrew
K 8
svn:date
V 27
2010-08-28T06:31:15.058248Z
K 7
svn:log
V 67
Attach the sys/compat/arm to the build with the COMPAT_OABI option

END
K 10
svn:author
V 2
jh
K 8
svn:date
V 27
2010-08-28T06:33:01.242969Z
K 7
svn:log
V 216
MFC r204636:

In reallocf(3), free the memory only when size != 0. Otherwise, when the
System V compatibility option (malloc "V" flag) is in effect a zero sized
reallocf() could cause a double free.

PR:		bin/141753

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2010-08-28T07:10:51.761431Z
K 7
svn:log
V 187
Add Intel Cougar Point PCH SATA Controller DeviceIDs. Correct some existing
entries for Intel Ibex Peak (5 Series/3400 Series) PCH SATA controllers.

Submitted by:	jfv@
MFC after:	1 week

END
K 10
svn:author
V 8
bschmidt
K 8
svn:date
V 27
2010-08-28T07:21:15.378822Z
K 7
svn:log
V 305
MFC r211295,211314,211546:
Introduce IEEE80211_C_RATECTL, drivers which use the ratectl framework
should set this capability. Initialize ni_txrate after txparams have
been setup. Some drivers calculate various things prior to association
based on ni_txrate and rely on it being nonzero.

PR:		kern/149185

END
K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2010-08-28T07:24:45.193779Z
K 7
svn:log
V 159
MFata(4):
Add Intel Cougar Point PCH SATA Controller DeviceIDs. Correct some existing
entries for Intel Ibex Peak (5 Series/3400 Series) PCH SATA controllers.

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-28T07:58:10.730210Z
K 7
svn:log
V 104
Initial code for XLR CompactFlash driver.

Submitted by:	Sreekanth M. S. <kanthms at netlogicmicro com>

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-28T08:03:29.322141Z
K 7
svn:log
V 221
Register an interrupt vector for DTrace return probes. There is some
code missing in lapic to make sure that we don't overwrite this entry,
but this will be done on a sequent commit.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-28T08:13:38.605542Z
K 7
svn:log
V 85
Replace a memory barrier with a mutex barrier.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-28T08:18:20.235447Z
K 7
svn:log
V 95
Add the path necessary to find fasttrap_isa.h to CFLAGS.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-28T08:30:20.528667Z
K 7
svn:log
V 315
Correct offset conversion to little endian. It was implemented in version 2,
but because of a bug it was a no-op, so we were still using offsets in native
byte order for the host. Do it properly this time, bump version to 4 and set
the G_ELI_FLAG_NATIVE_BYTE_ORDER flag when version is under 4.

MFC after:	2 weeks

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-28T08:38:03.912648Z
K 7
svn:log
V 101
Run all tasks from a proper context, with proper priority, etc.

Reviewed by:	jhb
MFC after:	1 month

END
K 10
svn:author
V 6
rpaulo
K 8
svn:date
V 27
2010-08-28T08:39:37.166910Z
K 7
svn:log
V 56
Remove debugging.

Sponsored by:	The FreeBSD Foundation

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-28T08:57:15.276411Z
K 7
svn:log
V 501
There is a bug in vfs_allocate_syncvnode() failure handling in mount code.
Actually it is hard to properly handle such a failure, especially in MNT_UPDATE
case. The only reason for the vfs_allocate_syncvnode() function to fail is
getnewvnode() failure. Fortunately it is impossible for current implementation
of getnewvnode() to fail, so we can assert this and make
vfs_allocate_syncvnode() void. This in turn free us from handling its failures
in the mount code.

Reviewed by:	kib
MFC after:	1 month

END
K 10
svn:author
V 2
mm
K 8
svn:date
V 27
2010-08-28T08:59:55.556956Z
K 7
svn:log
V 606
Update ZFS metaslab code from OpenSolaris.
This provides a noticeable write speedup, especially on pools with
less than 30% of free space.

Detailed information (OpenSolaris onnv changesets and Bug IDs):

11146:7e58f40bcb1c
6826241	Sync write IOPS drops dramatically during TXG sync
6869229	zfs should switch to shiny new metaslabs more frequently

11728:59fdb3b856f6
6918420	zdb -m has issues printing metaslab statistics

12047:7c1fcc8419ca
6917066	zfs block picking can be improved

Approved by:	delphij (mentor)
Obtained from:	OpenSolaris (Bug ID 6826241, 6869229, 6918420, 6917066)
MFC after:	2 weeks

END
K 10
svn:author
V 2
mm
K 8
svn:date
V 27
2010-08-28T09:24:11.197801Z
K 7
svn:log
V 1293
Import changes from OpenSolaris that provide
- better ACL caching and speedup of ACL permission checks
- faster handling of stat()
- lowered mutex contention in the read/writer lock (rrwlock)
- several related bugfixes

Detailed information (OpenSolaris onnv changesets and Bug IDs):

9749:105f407a2680
6802734	Support for Access Based Enumeration (not used on FreeBSD)
6844861	inconsistent xattr readdir behavior with too-small buffer

9866:ddc5f1d8eb4e
6848431	zfs with rstchown=0 or file_chown_self privilege allows user to "take" ownership

9981:b4907297e740
6775100	stat() performance on files on zfs should be improved
6827779	rrwlock is overly protective of its counters

10143:d2d432dfe597
6857433	memory leaks found at: zfs_acl_alloc/zfs_acl_node_alloc
6860318	truncate() on zfsroot succeeds when file has a component of its path set without access permission

10232:f37b85f7e03e
6865875	zfs sometimes incorrectly giving search access to a dir

10250:b179ceb34b62
6867395	zpool_upgrade_007_pos testcase panic'd with BAD TRAP: type=e (#pf Page fault)

10269:2788675568fd
6868276	zfs_rezget() can be hazardous when znode has a cached ACL

10295:f7a18a1e9610
6870564	panic in zfs_getsecattr

Approved by:	delphij (mentor)
Obtained from:	OpenSolaris (multiple Bug IDs)
MFC after:	2 weeks

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-28T14:15:18.298527Z
K 7
svn:log
V 128
projects/ppc64 is now completely merged to HEAD and has served its purpose
well. Now it shall go to the great Attic in the sky.

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-28T15:03:11.405589Z
K 7
svn:log
V 113
Repair some build breakage introduced in r211725 and garbage collect some
code made obsolete in the same commit.

END
K 10
svn:author
V 10
nwhitehorn
K 8
svn:date
V 27
2010-08-28T15:04:53.984282Z
K 7
svn:log
V 129
Fix breakage introduced in r211725 and improve functionality of truss on
64-bit powerpc by adding 32-bit compatibility features.

END
K 10
svn:author
V 6
brucec
K 8
svn:date
V 27
2010-08-28T16:32:01.738757Z
K 7
svn:log
V 73
Fix incorrect usage of 'assure' and 'insure'.

Approved by: rrs (mentor)

END
K 10
svn:author
V 3
alc
K 8
svn:date
V 27
2010-08-28T16:57:07.142724Z
K 7
svn:log
V 68
Add the MAP_PREFAULT_READ option to mmap(2).

Reviewed by:	jhb, kib

END
K 10
svn:author
V 3
ume
K 8
svn:date
V 27
2010-08-28T17:06:22.487201Z
K 7
svn:log
V 280
MFC r211276:
- When there is no room for returning the result, nss backend
  have to return ERANGE and terminate with NS_RETURN.
- When gethostbyname_r(3) and the friends end with an error,
  set errno to the value nss backend returns, and return errno
  value.

PR:		kern/131623

END
K 10
svn:author
V 3
ume
K 8
svn:date
V 27
2010-08-28T17:12:52.826274Z
K 7
svn:log
V 280
MFC r211276:
- When there is no room for returning the result, nss backend
  have to return ERANGE and terminate with NS_RETURN.
- When gethostbyname_r(3) and the friends end with an error,
  set errno to the value nss backend returns, and return errno
  value.

PR:		kern/131623

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-28T17:38:40.194500Z
K 7
svn:log
V 51
Test the poll(2) return value.

MFC after:	2 weeks

END
K 10
svn:author
V 3
kib
K 8
svn:date
V 27
2010-08-28T17:42:08.429600Z
K 7
svn:log
V 556
For some file types, select code registers two selfd structures. E.g.,
for socket, when specified POLLIN|POLLOUT in events, you would have one
selfd registered for receiving socket buffer, and one for sending. Now,
if both events are not ready to fire at the time of the initial scan,
but are simultaneously ready after the sleep, pollrescan() would iterate
over the pollfd struct twice. Since both times revents is not zero,
returned value would be off by one.

Fix this by recalculating the return value in pollout().

PR:	kern/143029
MFC after:	2 weeks

END
K 10
svn:author
V 3
ume
K 8
svn:date
V 27
2010-08-28T17:52:53.204785Z
K 7
svn:log
V 30
Record mergeinfo for r211276.

END
K 10
svn:author
V 3
ume
K 8
svn:date
V 27
2010-08-28T17:54:17.568570Z
K 7
svn:log
V 30
Record mergeinfo for r211276.

END
K 10
svn:author
V 6
tuexen
K 8
svn:date
V 27
2010-08-28T17:59:51.205912Z
K 7
svn:log
V 234
Fix the switching on/off of CMT using sysctl and socket option.
Fix the switching on/off of PF and NR-SACKs using sysctl.
Add minor improvement in handling malloc failures.
Improve the address checks when sending.

MFC after: 4 weeks

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-28T18:49:51.239770Z
K 7
svn:log
V 26
Merge from head at 211943

END
K 10
svn:author
V 8
jchandra
K 8
svn:date
V 27
2010-08-28T19:02:51.932080Z
K 7
svn:log
V 382
New driver nlge for XLR/XLS Network Accelerator. This will support the XGMAC
and XAUI 10G interfaces in addition RGMII/SGMII 1G interfaces.  This driver
is work in progress.

board.c and board.h expanded to include more info.

Only one of rge and nlge can be enabled at a time, rge will be deprecated
when nlge stabilizes.

Submitted by:	Sriram Gorti <srgorti at netlogicmicro com>

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-28T19:28:12.333632Z
K 7
svn:log
V 102
Move ZUT_OBJS in the same place that is used in vendor code.

Obtained from:	//depot/user/pjd/zfs/...

END
K 10
svn:author
V 3
pjd
K 8
svn:date
V 27
2010-08-28T19:29:06.360408Z
K 7
svn:log
V 114
Return NULL pointer instead of B_FALSE as it is done in the vendor code.

Obtained from:	//depot/user/pjd/zfs/...

END
K 10
svn:author
V 3
imp
K 8
svn:date
V 27
2010-08-28T21:06:13.377512Z
K 7
svn:log
V 71
Now that we default to the proper endian, we don't need these for mips

END
K 10
svn:author
V 6
tuexen
K 8
svn:date
V 27
2010-08-28T21:15:00.680164Z
K 7
svn:log
V 104
Bugfix: Do not send a packet drop report in response to a received
        INIT-ACK with incorrect CRC.

END