Lee Schermerhorn [Mon, 10 Mar 2008 18:43:45 +0000 (11:43 -0700)]
mempolicy: fix reference counting bugs
Address 3 known bugs in the current memory policy reference counting method.
I have a series of patches to rework the reference counting to reduce overhead
in the allocation path. However, that series will require testing in -mm once
I repost it.
1) alloc_page_vma() does not release the extra reference taken for
vma/shared mempolicy when the mode == MPOL_INTERLEAVE. This can result in
leaking mempolicy structures. This is probably occurring, but not being
noticed.
Fix: add the conditional release of the reference.
2) hugezonelist unconditionally releases a reference on the mempolicy when
mode == MPOL_INTERLEAVE. This can result in decrementing the reference
count for system default policy [should have no ill effect] or premature
freeing of task policy. If this occurred, the next allocation using task
mempolicy would use the freed structure and probably BUG out.
Fix: add the necessary check to the release.
3) The current reference counting method assumes that vma 'get_policy()'
methods automatically add an extra reference a non-NULL returned mempolicy.
This is true for shmem_get_policy() used by tmpfs mappings, including
regular page shm segments. However, SHM_HUGETLB shm's, backed by
hugetlbfs, just use the vma policy without the extra reference. This
results in freeing of the vma policy on the first allocation, with reuse of
the freed mempolicy structure on subsequent allocations.
Fix: Rather than add another condition to the conditional reference
release, which occur in the allocation path, just add a reference when
returning the vma policy in shm_get_policy() to match the assumptions.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Greg KH <greg@kroah.com> Cc: Andi Kleen <ak@suse.de> Cc: Christoph Lameter <clameter@sgi.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: David Rientjes <rientjes@google.com> Cc: <eric.whitney@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Alex Dubov [Mon, 10 Mar 2008 18:43:40 +0000 (11:43 -0700)]
tifm: fix memorystick host initialization code
Instead of assuming that host is powered on only once at card insertion, allow
for the possibility that memstick layer may need to cycle card's power to get
it out from some unhealthy states.
Signed-off-by: Alex Dubov <oakad@yahoo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Alex Dubov [Mon, 10 Mar 2008 18:43:40 +0000 (11:43 -0700)]
tifm: fix the MemoryStick host fifo handling code
Additional input received from JMicron on MemoryStick host interfaces showed
that some assumtions in fifo handling code were incorrect. This patch also
fixes data corruption used to occure during PIO transfers.
Signed-off-by: Alex Dubov <oakad@yahoo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Krzysztof Helt [Mon, 10 Mar 2008 18:43:37 +0000 (11:43 -0700)]
tridentfb: fix memory size detection
Fix memory size multiplier during detection.
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: "Antonino A. Daplas" <adaplas@pol.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Krzysztof Helt [Mon, 10 Mar 2008 18:43:36 +0000 (11:43 -0700)]
tridentfb: register should be left in non-locked state
Remove locking registers after they are unlocked during switch to/from MMIO
mode. This fixes regression on the Blade3D (Trident 9880) caused by the
previous patch (probe fixes).
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl> Cc: "Antonino A. Daplas" <adaplas@pol.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Josh Boyer [Mon, 10 Mar 2008 18:43:35 +0000 (11:43 -0700)]
of_serial: fix section mismatch warnings
Fix the following section mismatches:
WARNING: drivers/built-in.o(.exit.text+0x5a): Section mismatch in reference from the function of_platform_serial_exit() to the variable .devinit.data:of_platform_serial_driver
The function __exit of_platform_serial_exit() references
a variable __devinitdata of_platform_serial_driver.
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/tglx/linux-2.6-hrt:
time: remove obsolete CLOCK_TICK_ADJUST
time: don't touch an offlined CPU's ts->tick_stopped in tick_cancel_sched_timer()
time: prevent the loop in timespec_add_ns() from being optimised away
ntp: use unsigned input for do_div()
Ivan Kokshaysky [Sun, 9 Mar 2008 13:31:17 +0000 (16:31 +0300)]
alpha: fix iommu-related boot panic
This fixes a boot panic due to a typo in the recent iommu patchset from
FUJITA Tomonori <tomof@acm.org> - the code used dma_get_max_seg_size()
instead of dma_get_seg_boundary().
It also removes a couple of unnecessary BUG_ON() and ALIGN() macros.
Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Reported-and-tested-by: Bob Tracy <rct@frus.com> Acked-by: FUJITA Tomonori <tomof@acm.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Gregory Haskins [Sat, 8 Mar 2008 05:10:15 +0000 (00:10 -0500)]
cpu hotplug: adjust root-domain->online span in response to hotplug event
We currently set the root-domain online span automatically when the
domain is added to the cpu if the cpu is already a member of
cpu_online_map.
This was done as a hack/bug-fix for s2ram, but it also causes a problem
with hotplug CPU_DOWN transitioning. The right way to fix the original
problem is to actually respond to CPU_UP events, instead of CPU_ONLINE,
which is already too late.
This solves the hung reboot regression reported by Andrew Morton and
others.
While the fix did greatly improve the situation, it was correctly pointed out
by Roman that it does have a small bug: If the users change clocksources after
the system has been running and NTP has made corrections, the correctoins made
against the old clocksource will be applied against the new clocksource,
causing error.
The second attempt, which corrects the issue in the NTP_INTERVAL_LENGTH
definition has also made it up-stream as commit e13a2e61dd5152f5499d2003470acf9c838eab84
Roman has correctly pointed out that CLOCK_TICK_ADJUST is calculated
based on the PIT's frequency, and isn't really relevant to non-PIT
driven clocksources (that is, clocksources other then jiffies and pit).
This patch reverts both of those changes, and simply removes
CLOCK_TICK_ADJUST.
This does remove the granularity error correction for users of PIT and Jiffies
clocksource users, but the granularity error but for the majority of users, it
should be within the 500ppm range NTP can accommodate for.
For systems that have granularity errors greater then 500ppm, the
"ntp_tick_adj=" boot option can be used to compensate.
[johnstul@us.ibm.com: provided changelog]
[mattilinnanvuori@yahoo.com: maek ntp_tick_adj static] Signed-off-by: Roman Zippel <zippel@linux-m68k.org> Acked-by: john stultz <johnstul@us.ibm.com> Signed-off-by: Matti Linnanvuori <mattilinnanvuori@yahoo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: mingo@elte.hu Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Karsten Wiese [Tue, 4 Mar 2008 22:59:55 +0000 (14:59 -0800)]
time: don't touch an offlined CPU's ts->tick_stopped in tick_cancel_sched_timer()
Silences WARN_ONs in rcu_enter_nohz() and rcu_exit_nohz(), which appeared
before caused by (repeated) calls to:
$ echo 0 > /sys/devices/system/cpu/cpu1/online
$ echo 1 > /sys/devices/system/cpu/cpu1/online
Signed-off-by: Karsten Wiese <fzu@wemgehoertderstaat.de> Cc: johnstul@us.ibm.com Cc: Rafael Wysocki <rjw@sisk.pl> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
David Howells [Mon, 25 Feb 2008 17:31:57 +0000 (18:31 +0100)]
ntp: use unsigned input for do_div()
The kernel NTP code shouldn't hand 64-bit *signed* values to do_div(). Make it
instead hand 64-bit unsigned values. This gets rid of a couple of warnings.
Signed-off-by: David Howells <dhowells@redhat.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Roland McGrath [Sat, 8 Mar 2008 19:41:22 +0000 (11:41 -0800)]
Fix waitid si_code regression
In commit ee7c82da830ea860b1f9274f1f0cdf99f206e7c2 ("wait_task_stopped:
simplify and fix races with SIGCONT/SIGKILL/untrace"), the magic (short)
cast when storing si_code was lost in wait_task_stopped. This leaks the
in-kernel CLD_* values that do not match what userland expects.
Herbert Xu [Sat, 8 Mar 2008 12:29:43 +0000 (20:29 +0800)]
[CRYPTO] skcipher: Fix section mismatches
The previous patch to move chainiv and eseqiv into blkcipher created
a section mismatch for the chainiv exit function which was also called
from __init. This patch removes the __exit marking on it.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Roland McGrath [Fri, 7 Mar 2008 22:56:02 +0000 (14:56 -0800)]
x86_64: make ptrace always sign-extend orig_ax to 64 bits
This makes 64-bit ptrace calls setting the 64-bit orig_ax field for a
32-bit task sign-extend the low 32 bits up to 64. This matches what a
64-bit debugger expects when tracing a 32-bit task.
This follows on my "x86_64 ia32 syscall restart fix". This didn't
matter until that was fixed.
The debugger ignores or zeros the high half of every register slot it
sets (including the orig_rax pseudo-register) uniformly. It expects
that the setting of the low 32 bits always has the same meaning as a
32-bit debugger setting those same 32 bits with native 32-bit
facilities.
This never arose before because the syscall restart check never
matched any -ERESTART* values due to lack of sign extension. Before
that fix, even 32-bit ptrace setting orig_eax to -1 failed to trigger
the restart check anyway. So this was never noticed as a regression
of 64-bit debuggers vs 32-bit debuggers on the same 64-bit kernel.
Signed-off-by: Roland McGrath <roland@redhat.com>
[ Changed to just do the sign-extension unconditionally on x86-64,
since orig_ax is always just a small integer and doesn't need
the full 64-bit range ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Linus Torvalds [Fri, 7 Mar 2008 21:49:32 +0000 (13:49 -0800)]
Merge branch 'slab-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/christoph/vm
* 'slab-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/christoph/vm:
slub: fix typo in Documentation/vm/slub.txt
slab: NUMA slab allocator migration bugfix
slub: Do not cross cacheline boundaries for very small objects
slab - use angle brackets for include of kmalloc_sizes.h
slab numa fallback logic: Do not pass unfiltered flags to page allocator
slub statistics: Fix check for DEACTIVATE_REMOTE_FREES
* git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6:
ide: update references to Documentation/ide/ide.txt (v2)
ide: move ide.txt to Documentation/ide/
ide: fix buggy code in ide_register_hw()
ide: fix enabling DMA on it821x in "smart" mode
ide-cd: mark REQ_TYPE_ATA_PC write requests with REQ_RW flag
ide-cd: mark REQ_TYPE_ATA_PC write requests with REQ_RW flag
On Thursday 06 March 2008, walt wrote:
> For me, this commit causes the problem it's intended to fix:
>
> commit 9f10d9ee0ac6d79d7bc8b9a158bf4a29322d84d3
> Author: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
> Date: Tue Feb 26 21:50:35 2008 +0100
>
> ide-cd: fix 'ireason' handling for REQ_TYPE_ATA_PC requests
>
> This fixes some hangs caused by not finishing the transfer before ending
> the request and also makes use of 'ireason == 1' quirk for spurious IRQs.
>
> When I mount a CD there is a long delay, and I see this error message:
>
> hdc: ide_cd_check_ireason: wrong transfer direction!
> cdrom: failed setting lba address space
> hdc: status error: status=0x58 { DriveReady SeekComplete DataRequest }
> ide: failed opcode was: unknown
> hdc: drive not ready for command
> <repeated many times>
>
> When I revert this commit everything works properly again, including
> CD burning.
It turned out that REQ_TYPE_ATA_PC write requests were not marked as such
(the previous commit assumed them to be).
Reported-by: walt <w41ter@gmail.com> Tested-by: walt <w41ter@gmail.com> Reviewed-by: Borislav Petkov <petkovbb@googlemail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Linus Torvalds [Fri, 7 Mar 2008 20:08:07 +0000 (12:08 -0800)]
Merge branch 'hotfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6
* 'hotfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
NFS: Fix dentry revalidation for NFSv4 referrals and mountpoint crossings
NFS: Fix the fsid revalidation in nfs_update_inode()
SUNRPC: Fix a nfs4 over rdma transport oops
NFS: Fix an f_mode/f_flags confusion in fs/nfs/write.c
Trond Myklebust [Thu, 6 Mar 2008 17:34:59 +0000 (12:34 -0500)]
NFS: Fix dentry revalidation for NFSv4 referrals and mountpoint crossings
As long as the directory contents haven't changed, we should just let the
path walk proceed to cross the mountpoint. Apart from being an optimisation
in the case of 'nohide' mountpoint traversals, it also fixes an issue with
referrals: referral inodes don't have valid filehandles, so calling
nfs_revalidate_inode() on them is a bug.
Trond Myklebust [Thu, 6 Mar 2008 17:34:50 +0000 (12:34 -0500)]
NFS: Fix the fsid revalidation in nfs_update_inode()
When we detect that we've crossed a mountpoint on the remote server, we
must take care not to use that inode to revalidate the fsid on our
current superblock. To do so, we label the inode as a remote mountpoint,
and check for that in nfs_update_inode().
Tilman Schmidt [Fri, 7 Mar 2008 18:47:08 +0000 (19:47 +0100)]
gigaset: fix Oops on module unload regression
The card state mutex was only initialized when a device was connected,
but used during unload unconditionally, leading to an Oops if a driver
was loaded and unloaded again without ever connecting a device.
Fix this by initializing the mutex as soon as the structure is allocated.
Also add a missing mutex unlock revealed in the same execution path.
Linus Torvalds [Fri, 7 Mar 2008 18:08:17 +0000 (10:08 -0800)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel:
sched: don't allow rt_runtime_us to be zero for groups having rt tasks
sched: rt-group: fixup schedulability constraints calculation
sched: fix the wrong time slice value for SCHED_FIFO tasks
sched: export task_nice
sched: balance RT task resched only on runqueue
sched: retain vruntime
Ingo Molnar [Fri, 7 Mar 2008 09:47:43 +0000 (10:47 +0100)]
drivers/char/esp.c: fix bootup lockup
randconfig testing found a bootup lockup in drivers/char/esp.c because
of a spinlock that wasn't correctly initialized.
I'm not sure why it became more prominent in 2.6.25-rc4, the bug seems
rather old and i've been doing allyesconfig bootups for ages with
CONFIG_ESP enabled.
This fixes this bootup lockup:
PM: Adding info for No Bus:ttyP63
ttyP32 at 0x0240 (irq = 0) is an ESP primary port
BUG: spinlock lockup on CPU#0, swapper/1, f56dd004
Pid: 1, comm: swapper Not tainted 2.6.25-rc4-sched-devel.git-x86-latest.git #402 [<c03ac6f4>] _raw_spin_lock+0x134/0x140
[<c08649be>] _spin_lock_irqsave+0x5e/0x80
[<c0b9fbfe>] ? espserial_init+0x2be/0x6e0
[<c0b9fbfe>] espserial_init+0x2be/0x6e0
[<c0b877a3>] kernel_init+0x83/0x260
[<c0b9f940>] ? espserial_init+0x0/0x6e0
[<c010416a>] ? restore_nocheck_notrace+0x0/0xe
[<c0b87720>] ? kernel_init+0x0/0x260
[<c0b87720>] ? kernel_init+0x0/0x260
[<c0104507>] kernel_thread_helper+0x7/0x10
=======================
kzalloc() is not the way to initialize spinlocks anymore.
Dhaval Giani [Thu, 28 Feb 2008 09:51:56 +0000 (15:21 +0530)]
sched: don't allow rt_runtime_us to be zero for groups having rt tasks
This patch checks if we can set the rt_runtime_us to 0. If there is a
realtime task in the group, we don't want to set the rt_runtime_us as 0
or bad things will happen. (that task wont get any CPU time despite
being TASK_RUNNNG)
it was only possible to configure the rt-group scheduling parameters
beyond the default value in a very small range.
that's because div64_64() has a different calling convention than
do_div() :/
fix a few untidies while we are here; sysctl_sched_rt_period may overflow
due to that multiplication, so cast to u64 first. Also that RUNTIME_INF
juggling makes little sense although its an effective NOP.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
this is due to a place that can reschedule a task without holding
the tasks runqueue lock. This was caused by the RT balancing code
that pulls RT tasks to the current run queue and will reschedule the
current task.
There's a slight chance that the pulling of the RT tasks will release
the current runqueue's lock and retake it (in the double_lock_balance).
During this time that the runqueue is released, the current task can
migrate to another runqueue.
In the prio_changed_rt code, after the pull, if the current task is of
lesser priority than one of the RT tasks pulled, resched_task is called
on the current task. If the current task had migrated in that small
window, resched_task will be called without holding the runqueue lock
for the runqueue that the task is on.
This race condition also exists in the mainline kernel and this patch
adds a check to make sure the task hasn't migrated before calling
resched_task.
Signed-off-by: Steven Rostedt <srostedt@redhat.com> Tested-by: Sripathi Kodi <sripathik@in.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra [Fri, 29 Feb 2008 20:21:01 +0000 (15:21 -0500)]
sched: retain vruntime
Kei Tokunaga reported an interactivity problem when moving tasks
between control groups.
Tasks would retain their old vruntime when moved between groups, this
can cause funny lags. Re-set the vruntime on group move to fit within
the new tree.
Peter Korsgaard [Thu, 6 Mar 2008 09:56:45 +0000 (10:56 +0100)]
x86-boot: don't request VBE2 information
The new x86 setup code (4fd06960f120) broke booting on an old P3/500MHz
with an onboard Voodoo3 of mine. After debugging it, it turned out
to be caused by the fact that the vesa probing now asks for VBE2 data.
Disassembing the video BIOS shows that it overflows the vesa_general_info
structure when VBE2 data is requested because the source addresses for the
information strings which get strcpy'ed to the buffer lie outside the 32K
BIOS code (and hence contain long sequences of 0xff's).
(The full BIOS can be found at http://peter.korsgaard.com/vgabios.bin
if interested).
The old setup code didn't ask for VBE2 info, and the new code doesn't
actually do anything with the extra information, so the fix is to simply
not request it. Other BIOS'es might have the same problem.
Signed-off-by: Peter Korsgaard <jacmet@sunsite.dk> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Jan Beulich [Wed, 5 Mar 2008 08:35:14 +0000 (08:35 +0000)]
x86: fix merge mistake in i387.c
convert_fxsr_to_user() in 2.6.24's i387_32.c did this, and
convert_to_fxsr() also does the inverse, so I assume it's an oversight
that it is no longer being done.
[ mingo@elte.hu:
we encode it this way because there's no space for the 'FPU Last
Instruction Opcode' (->fop) field in the legacy user_i387_ia32_struct
that PTRACE_GETFPREGS/PTRACE_SETFPREGS uses.
it's probably pure legacy - i'd be surprised if any user-space relied on
the FPU Last Opcode in any way. But indeed we used to do it previously
so the most conservative thing is to preserve that piece of information.
]
Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Aurelien Jarno [Wed, 5 Mar 2008 18:14:24 +0000 (19:14 +0100)]
x86: clear DF before calling signal handler
The Linux kernel currently does not clear the direction flag before
calling a signal handler, whereas the x86/x86-64 ABI requires that.
Linux had this behavior/bug forever, but this becomes a real problem
with gcc version 4.3, which assumes that the direction flag is
correctly cleared at the entry of a function.
This patches changes the setup_frame() functions to clear the
direction before entering the signal handler.
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net> Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: H. Peter Anvin <hpa@zytor.com>
Linus Torvalds [Fri, 7 Mar 2008 03:32:05 +0000 (19:32 -0800)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/blackfin-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/blackfin-2.6:
[Blackfin] arch: current_l1_stack_save is a pointer, so use NULL rather than 0
[Blackfin] arch: fix atomic and32/xor32 comments and ENDPROC markings
[Blackfin] arch: fix bug - allow SDH driver to be used as module
[Blackfin] arch: to kill syscalls missing warning by adding new timerfd syscalls
Linus Torvalds [Fri, 7 Mar 2008 03:31:34 +0000 (19:31 -0800)]
Merge branch 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6
* 'release' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6:
[IA64] kprobes arch consolidation build fix
[IA64] update efi region debugging to use MB, GB and TB as well as KB
[IA64] use dev_printk in video quirk
[IA64] remove remaining __FUNCTION__ occurrences
[IA64] remove unnecessary nfs includes from sys_ia32.c
[IA64] remove CONFIG_SMP ifdef in ia64_send_ipi()
[IA64] arch_ptrace() cleanup
[IA64] remove duplicate code from arch_ptrace()
[IA64] convert sys_ptrace to arch_ptrace
[IA64] remove find_thread_for_addr()
[IA64] do not sync RBS when changing PT_AR_BSP or PT_CFM
[IA64] access user RBS directly
Joe Korty [Wed, 5 Mar 2008 23:04:59 +0000 (15:04 -0800)]
slab: NUMA slab allocator migration bugfix
NUMA slab allocator cpu migration bugfix
The NUMA slab allocator (specifically, cache_alloc_refill)
is not refreshing its local copies of what cpu and what
numa node it is on, when it drops and reacquires the irq
block that it inherited from its caller. As a result
those values become invalid if an attempt to migrate the
process to another numa node occured while the irq block
had been dropped.
The solution is to make cache_alloc_refill reload these
variables whenever it drops and reacquires the irq block.
The error is very difficult to hit. When it does occur,
one gets the following oops + stack traceback bits in
check_spinlock_acquired:
kernel BUG at mm/slab.c:2417
cache_alloc_refill+0xe6
kmem_cache_alloc+0xd0
...
This patch was developed against 2.6.23, ported to and
compiled-tested only against 2.6.25-rc4.
Signed-off-by: Joe Korty <joe.korty@ccur.com> Signed-off-by: Christoph Lameter <clameter@sgi.com>
Nick Piggin [Wed, 5 Mar 2008 22:05:56 +0000 (14:05 -0800)]
slub: Do not cross cacheline boundaries for very small objects
SLUB should pack even small objects nicely into cachelines if that is what
has been asked for. Use the same algorithm as SLAB for this.
The effect of this patch for a system with a cacheline size of 64
bytes is that the 24 byte sized slab caches will now put exactly
2 objects into a cacheline instead of 3 with some overlap into
the next cacheline. This reduces the object density in a 4k slab
from 170 to 128 objects (same as SLAB).
Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Christoph Lameter <clameter@sgi.com>
Harvey Harrison [Thu, 6 Mar 2008 17:49:01 +0000 (09:49 -0800)]
[IA64] kprobes arch consolidation build fix
ia64 named their handler kprobes_fault_handler while all other
arches used kprobe_fault_handler. Change the function definition
and header declaration.
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
Simon Horman [Tue, 26 Feb 2008 06:24:04 +0000 (15:24 +0900)]
[IA64] update efi region debugging to use MB, GB and TB as well as KB
When EFI_DEBUG is defined to a non-zero value in arch/ia64/kernel/efi.c,
the efi memory regions are displayed. This patch enhances the
display code in a few ways:
1. Use TB, GB and MB as well as KB as units.
Although this introduces rounding errors (KB doesn't as
size is always a multiple of 4Kb), it does make
things a lot more readable.
Also as the range is also shown, it is possible to note the exact size
if it is important. In my experience, the size field is mostly useful
for getting a general idea of the size of a region.
On the rx2620 that I use, there actually is an 8TB region (though not
backed by physical memory, and 8TB really is a lot more readable than
8589934592KB.
2. pad the size field with leading spaces to further improve readability
...
... ( 8MB)
... ( 928MB)
... ( 3MB)
...
vs
...
... (8MB)
... (928MB)
... (3MB)
...
3. Pad the attr field out to 64bits using leading zeros,
to further improve readability.
Harvey Harrison [Tue, 4 Mar 2008 23:15:00 +0000 (15:15 -0800)]
[IA64] remove remaining __FUNCTION__ occurrences
__FUNCTION__ is gcc-specific, use __func__
Long lines have been kept where they exist, some small spacing changes
have been done.
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Tony Luck <tony.luck@intel.com>
KOSAKI Motohiro [Tue, 4 Mar 2008 23:45:42 +0000 (15:45 -0800)]
[IA64] remove unnecessary nfs includes from sys_ia32.c
Compilation of 2.6.25-rc2-mm1 on ia64 generates many warnings.
IA64 support 2 ELF format (IA64 binary and IA32 binary),
thus if 2 elf related header included, cause many warning or error.
about 2 week ago, J. Bruce Fields proposed this problem fixed patch.
(http://marc.info/?l=linux-ia64&m=120329313305695&w=2)
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Tony Luck <tony.luck@intel.com>
However, it was redundantly listed in asm-mn10300/Kbuild and
asm-x86/Kbuild too. Remove those as well, so it really stops being
exported on those architectures. Also remove the redundant listing of
ptrace.h and termios.h from mn10300.
Signed-off-by: David Woodhouse <dwmw2@infradead.org> Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joy Latten [Thu, 6 Mar 2008 11:28:44 +0000 (19:28 +0800)]
[CRYPTO] xcbc: Fix crash with IPsec
When using aes-xcbc-mac for authentication in IPsec,
the kernel crashes. It seems this algorithm doesn't
account for the space IPsec may make in scatterlist for authtag.
Thus when crypto_xcbc_digest_update2() gets called,
nbytes may be less than sg[i].length.
Since nbytes is an unsigned number, it wraps
at the end of the loop allowing us to go back
into loop and causing crash in memcpy.
I used update function in digest.c to model this fix.
Please let me know if it looks ok.
Signed-off-by: Joy Latten <latten@austin.ibm.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The XTS blockmode uses a copy of the IV which is saved on the stack
and may or may not be properly aligned. If it is not, it will break
hardware cipher like the geode or padlock.
This patch encrypts the IV in place so we don't have to worry about
alignment.
Signed-off-by: Sebastian Siewior <sebastian@breakpoint.cc> Tested-by: Stefan Hellermann <stefan@the2masters.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Paul Mundt [Thu, 6 Mar 2008 07:08:00 +0000 (16:08 +0900)]
sh: Fix up SH7710 VoIP-GW build.
The only board-specific bits that existed here were for setting up the
IRQs, which are now handled by the SH7710 CPU support code instead. As
there's nothing else to do for setup, kill off the board support code
and have the defconfig use the generic machvec instead.
David Chinner [Thu, 6 Mar 2008 02:49:43 +0000 (13:49 +1100)]
[XFS] fix inode leak in xfs_iget_core()
If the radix_tree_preload() fails, we need to destroy the inode we just
read in before trying again. This could leak xfs_vnode structures when
there is memory pressure. Noticed by Christoph Hellwig.
David Chinner [Thu, 6 Mar 2008 02:45:10 +0000 (13:45 +1100)]
[XFS] 977545 977545 977545 977545 977545 977545 xfsaild causing too many
wakeups
Idle state is not being detected properly by the xfsaild push code. The
current idle state is detected by an empty list which may never happen
with mostly idle filesystem or one using lazy superblock counters. A
single dirty item in the list that exists beyond the push target can
result repeated looping attempting to push up to the target because it
fails to check if the push target has been acheived or not.
Fix by considering a dirty list with everything past the target as an idle
state and set the timeout appropriately.
hitfb presently has probe using __init whilst remove uses __devexit.
As this device can't possibly be hotplugged, switch to __exit and
__exit_p() instead.
Paul Mundt [Thu, 6 Mar 2008 04:39:18 +0000 (13:39 +0900)]
fb: pvr2fb: Fix up remaining section mismatch.
Building with CONFIG_DEBUG_SECTION_MISMATCH=y reports:
CC drivers/video/pvr2fb.o
LD drivers/video/built-in.o
WARNING: drivers/video/built-in.o(.text+0xb9b0): Section mismatch in reference from the function pvr2fb_check_var() to the variable .devinit.data:pvr2_fix
The function pvr2fb_check_var() references
the variable __devinitdata pvr2_fix.
This is often because pvr2fb_check_var lacks a __devinitdata
annotation or the annotation of pvr2_fix is wrong.
This is obviously crap as no such reference exists, but it's a bit
closer to reality from older versions which blamed the PCI table. The
real problem was a reference to pvr2_var.vmode from pvr2fb_check_var(),
as pvr2_var is flagged as __devinitdata (pvr2_fix is also, so at least
that part is right).
pvr2_var.vmode is just a fancy way of saying FB_VMODE_NONINTERLACED, so
we just reference that explicitly instead.
This patch fixes the old non-verbose hp6xx apm code and enables some
very basic apm output. We now get percentage (battery) output
and basic time estimate.
Signed-off-by: Kristoffer Ericson <kristoffer.ericson@gmail.com> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Harvey Harrison [Tue, 4 Mar 2008 23:23:47 +0000 (15:23 -0800)]
sh: replace remaining __FUNCTION__ occurrences
__FUNCTION__ is gcc-specific, use __func__
Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Adrian Bunk [Mon, 3 Mar 2008 18:07:42 +0000 (20:07 +0200)]
sh/mm/pg-sh7705.c must #include <linux/fs.h>
This patch fixes the following compile error:
<-- snip -->
...
CC arch/sh/mm/pg-sh7705.o
/home/bunk/linux/kernel-2.6/git/linux-2.6/arch/sh/mm/pg-sh7705.c: In function 'ptep_get_and_clear':
/home/bunk/linux/kernel-2.6/git/linux-2.6/arch/sh/mm/pg-sh7705.c:130: error: implicit declaration of function 'mapping_writably_mapped'
make[2]: *** [arch/sh/mm/pg-sh7705.o] Error 1
<-- snip -->
Signed-off-by: Adrian Bunk <adrian.bunk@movial.fi> Signed-off-by: Paul Mundt <lethal@linux-sh.org>
David Rientjes [Wed, 5 Mar 2008 07:32:38 +0000 (23:32 -0800)]
cpusets: fix obsolete comment
mm migration is no longer done in cpuset_update_task_memory_state() so it
can no longer take current->mm->mmap_sem, so fix the obsolete comment.
[ This changed in commit 04c19fa6f16047abff2288ddbc1f0798ede5a849
("cpuset: migrate all tasks in cpuset at once") when the mm migration
was moved from cpuset_update_task_memory_state() to update_nodemask() ]
Signed-off-by: David Rientjes <rientjes@google.com> Cc: Paul Jackson <pj@sgi.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / karo-tx-linux.git / log