1
0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-23 11:18:54 +00:00
Commit Graph

138261 Commits

Author SHA1 Message Date
Alan Cox
7630c26507 Reintroduce UMA_SLAB_KMAP; however, change its spelling to
UMA_SLAB_KERNEL for consistency with its sibling UMA_SLAB_KMEM.
(UMA_SLAB_KMAP met its original demise in revision 1.30 of
vm/uma_core.c.)  UMA_SLAB_KERNEL is now required by the jumbo frame
allocators.  Without it, UMA cannot correctly return pages from the
jumbo frame zones to the VM system because it resets the pages' object
field to NULL instead of the kernel object.  In more detail, the jumbo
frame zones are created with the option UMA_ZONE_REFCNT.  This causes
UMA to overwrite the pages' object field with the address of the slab.
However, when UMA wants to release these pages, it doesn't know how to
restore the object field, so it sets it to NULL.  This change teaches
UMA how to reset the object field to the kernel object.

Crashes reported by: kris
Fix tested by: kris
Fix discussed with: jeff
MFC after: 6 weeks
2008-04-04 18:41:12 +00:00
Warner Losh
1ff6c09714 Fix stupid typo 2008-04-04 18:22:16 +00:00
Alan Cox
2addc03d04 Eliminate an unnecessary test and its misleading comment from pmap_enter(). 2008-04-04 18:00:22 +00:00
Rafal Jaworowski
367bbd3833 Make kernel.tramp build properly on ARM9E.
Reviewed by:	imp
Approved by:	cognet (mentor)
2008-04-04 17:35:24 +00:00
Warner Losh
043b496b8d Add note about PZERO being obsolete, because so much code uses it.
Feel free to improve the verbage, since this was a compromise between
conflicting feedback I got on my original version.
2008-04-04 16:59:58 +00:00
Jeff Roberson
00ca09449d - Add sysctls at debug.rwlock to control the behavior of the speculative
spinning when readers hold a lock.  This spinning is speculative because,
   unlike the write case, we can not test whether the owners are running.
 - Add speculative read spinning for readers who are blocked by pending
   writers while a read lock is still held.  This allows the thread to
   spin until the write lock succeeds after which it may spin until the
   writer has released the lock.  This prevents excessive context switches
   when readers and writers both hold the lock for brief periods.

Sponsored by:	Nokia
2008-04-04 10:00:46 +00:00
Doug Rabson
aea15cbc62 Add some compatibility code so that software which is built to use the new
struct flock with l_sysid member can work properly on an an old kernel which
doesn't support l_sysid.

Sponsored by:	Isilon Systems
2008-04-04 09:43:03 +00:00
Konstantin Belousov
8eb6b6ecb6 The temporary workaround for the call to the vget() without lock type in
the fdesc_allocvp(). The caller of the fdesc_allocvp() expects that the
returned vnode is not reclaimed. Do lock the vnode exclusive and drop
the lock after.

Reported by:	pho
Reviewed by:	jeff
2008-04-04 09:37:57 +00:00
Ruslan Ermilov
85018ba57b - Normalize usage(), add "ddb pathname" syntax.
- Revise the manpage.
2008-04-04 07:31:43 +00:00
Ruslan Ermilov
5ffbd51eb0 - Add -D to usage().
- Bump document date for the addition of the -D option.
- Reformat a sentence to look like a real sentence.
2008-04-04 05:55:42 +00:00
Greg Lehey
2269fa5765 Add -D option to specify exact format of date and time output with ls -l. 2008-04-04 03:57:46 +00:00
Craig Rodrigues
205e074f2c Add comment about specifying "ro" mount option when
doing an update mount on a read-only file system.

Requested by:	yar
2008-04-04 01:50:58 +00:00
Jeff Roberson
3bc8c68d9f - Add a Nokia copyright to cpuset to reflect their generous
contribution to this work.
2008-04-04 01:22:04 +00:00
Jeff Roberson
0502fe2e43 - Allow static_boost to specify no boost with '0', traditional kernel
fixed pri boost with '1' or any priority less than the current thread's
   priority with a value greater than two.  Default the boost to
   PRI_MIN_TIMESHARE to prevent regular user-space threads from starving
   threads in the kernel.  This prevents these user-threads from also
   being scheduled as if they are high fixed-priority kernel threads.
 - Restore the setting of lowpri in tdq_choose().  It has to be either here
   or in sched_switch().  I accidentally removed it from both places.

Tested by:	kris
2008-04-04 01:16:18 +00:00
Jeff Roberson
03d17db7d5 - Don't check for the ITHD pri class in tdq_load_add and rem. 4BSD doesn't
do this either.  Simply check P_NOLOAD.  It'd be nice if this was
   in a thread flag so we didn't have an extra cache miss every time we
   add and remove a thread from the run-queue.
2008-04-04 01:04:43 +00:00
Jeff Roberson
e4b1aa6210 - Fix a mis-merge that crept in during the softclock changes.
Spotted by:	jhb
2008-04-04 01:03:23 +00:00
Ed Maste
77cd5850c8 Allow crashdumps on machines with >4GB of RAM as long as the adapter can
do 64-bit S/G.

Submitted by:	Alex Bencz
Reviewed by:	scottl
2008-04-03 23:29:31 +00:00
Jack F Vogel
8cecae251c Fix the build breakage, need the | between dependencies, I didn't
realize that :(
2008-04-03 20:58:18 +00:00
Warner Losh
ecf899b423 Always build kernel.tramp. This should be helpful for a lot of
people, as well making sure it doesn't break.
2008-04-03 20:42:36 +00:00
Warner Losh
52b370fe8e Use safer string handling.
Reviewed by: security-team
2008-04-03 20:37:38 +00:00
Warner Losh
22e5baf782 Minor style(9) nit: move to using ANSI definition of functions. 2008-04-03 20:36:44 +00:00
Rafal Jaworowski
15898edac1 Now really add the bus_space_generic.c file...
Reviewed by:	sam
Approved by:	cognet (mentor)
2008-04-03 18:28:34 +00:00
Rafal Jaworowski
47e972c91a Refactor certain ARM bus space methods: instead of having multiple copies of
the same code introduce sys/arm/arm/bus_space_generic.c for a shared set of
routines.

Reviewed by:	sam
Approved by:	cognet (mentor)
2008-04-03 18:22:08 +00:00
Rafal Jaworowski
b7170e5c34 Fix AVILA build.
Reviewed by:	sam
Approved by:	cognet(mentor)
2008-04-03 18:20:39 +00:00
Marcel Moolenaar
7256cdffc9 Align functions to 16-byte boundaries due to profiling granularity. 2008-04-03 17:40:20 +00:00
Marcel Moolenaar
66821a4c67 Set sc_psim so that the openpic core can correct the off-by-one
error in the number of IRQs that PSIM gives us.
2008-04-03 17:38:27 +00:00
Warner Losh
aa037d58ea Take the first baby step towards unifying and cleaning up arminit():
- Pull all the code to deal with the trampoline stuff into one
	  centeralized place and use it from everywhere.
	- Some minor style tidiness

Reviewed by: tinguely
2008-04-03 16:44:50 +00:00
Ruslan Ermilov
c3ee8ebcbc Fix descriptions of "struct msqid_ds and "struct ipc_perm" to match
harsh reality.
2008-04-03 16:21:43 +00:00
Scott Long
942adee743 Don't force a reset at driver attach time. It doesn't work on some
adapters, apparently.
2008-04-03 14:39:48 +00:00
David Xu
44253336b6 let umtxq_busy() only spin on mp machine. make function name
do_rwlock_unlock to be consistent with others.
2008-04-03 11:49:20 +00:00
Yaroslav Tykhiy
61f3d0ccf7 Put back the quote from Chinggis Khan removed in rev. 1.259.
The quote predated rev. 1.232, which rev. 1.259 was to correct;
therefore it was protected by the "Don't remove fortunes" rule.

Noticed by:	ceri
Pointy hat to:	yar
2008-04-03 10:22:56 +00:00
Jack F Vogel
ab78c99d94 Another build fix 2008-04-03 06:45:38 +00:00
Jack F Vogel
f413cc200e Fix a lint issue in the build. 2008-04-03 06:17:16 +00:00
David Schultz
c79a26333b Add some tests for fma(), fmaf(), and fmal(). 2008-04-03 06:15:58 +00:00
David Schultz
92a1a6e169 Fix some corner cases:
- fma(x, y, z) returns z, not NaN, if z is infinite, x and y are finite,
  x*y overflows, and x*y and z have opposite signs.
- fma(x, y, z) doesn't generate an overflow, underflow, or inexact exception
  if z is NaN or infinite, as per IEEE 754R.
- If the rounding mode is set to FE_DOWNWARD, fma(1.0, 0.0, -0.0) is -0.0,
  not +0.0.
2008-04-03 06:14:51 +00:00
Warner Losh
d93b192e7a KERNBASE + 0x00200000 is the same thing as KERNVIRTADDR on this
platform, so use the latter in preference to the former.  This makes
the fake_preload setup be the same between kb920x_machdep.c and
avila_machdep.c....
2008-04-03 06:14:23 +00:00
Warner Losh
e5a11098e8 Remove unnecessary #define. 2008-04-03 06:07:45 +00:00
George V. Neville-Neil
6d5a24c513 Add a manual page and a Makefile.
Add code to reflect packets back from the sink so that we can measure
round trip at the source.
2008-04-03 05:26:54 +00:00
David Xu
caad30a422 put THR_CRITICAL_LEAVE into do .. while statement. 2008-04-03 02:47:35 +00:00
Kevin Lo
6cec2e4b55 style(9) cleanup 2008-04-03 02:41:54 +00:00
David Xu
a6cba9400a add __hidden suffix to _umtx_op_err, this eliminates PLT. 2008-04-03 02:13:51 +00:00
Jack F Vogel
4809e4fa4d Fix minor bug in last checkin, NO_STRICT_ALIGNMENT code. 2008-04-03 00:25:09 +00:00
Jack F Vogel
e9d8b9c383 This update primarily addresses the ability to have both the em
and the igb driver static in the kernel. But it also reflects
some other bug fixes in my development stream at Intel.
PR 122373 is also fixed in this code.
2008-04-02 22:00:36 +00:00
Doug Barton
53eb99795c Back out revision 1.6, the addition of "BEFORE: mountcritremote".
mountcritremote REQUIREs FILESYSTEMS, and that script REQUIREs zfs,
so this change is a noop. By removing it we make life a little easier
both for rcorder(8) and for debugging down the road.

Approved by:	2 weeks of silence from pjd
2008-04-02 19:29:16 +00:00
David E. O'Brien
20c46652dc PR ports/121363 (& ports/73797) has been committed, so we can now go back
to JB's revision 1.96 change to remove -fno-strict-aliasing from CFLAGS.

This makes the default CFLAGS to match the simple defaults that the
tinderboxes use.  By using -fno-strict-aliasing by default we are
choosing to ignore problems in code which had the potential to
shoot ourselves in the foot.
2008-04-02 17:24:22 +00:00
Warner Losh
8a4cd00ae3 Add zyd, ural, and rum. They were missing. 2008-04-02 16:17:19 +00:00
Andrew Gallatin
e5062938d1 Initialize if_baudrate using IF_Gbps() macro.
Note that if_baudrate is a long, and 32-bits isn't enough to properly
represent 10Gb/s.

Pointed out by: dwhite
2008-04-02 13:59:43 +00:00
David Xu
7abb97dcd8 Non-portable functions are in pthread_np.h, fix compiling problem. 2008-04-02 11:41:12 +00:00
Jeff Roberson
e8245292a7 - Convert two timeout users to the new callout_reset_curcpu() api.
Sponsored by:	Nokia
2008-04-02 11:21:42 +00:00
Jeff Roberson
8d809d5061 Implement per-cpu callout threads, wheels, and locks.
- Move callout thread creation from kern_intr.c to kern_timeout.c
 - Call callout_tick() on every processor via hardclock_cpu() rather than
   inspecting callout internal details in kern_clock.c.
 - Remove callout implementation details from callout.h
 - Package up all of the global variables into a per-cpu callout structure.
 - Start one thread per-cpu.  Threads are not strictly bound.  They prefer
   to execute on the native cpu but may migrate temporarily if interrupts
   are starving callout processing.
 - Run all callouts by default in the thread for cpu0 to maintain current
   ordering and concurrency guarantees.  Many consumers may not properly
   handle concurrent execution.
 - The new callout_reset_on() api allows specifying a particular cpu to
   execute the callout on.  This may migrate a callout to a new cpu.
   callout_reset() schedules on the last assigned cpu while
   callout_reset_curcpu() schedules on the current cpu.

Reviewed by:	phk
Sponsored by:	Nokia
2008-04-02 11:20:30 +00:00