After memory pressure has forced it to dip into the reserves, 2.6.32's
5f8dcc2121 "page-allocator: split per-cpu
list into one-list-per-migrate-type" has been returning MIGRATE_RESERVE
pages to the MIGRATE_MOVABLE free_list: in some sense depleting reserves.
Fix that in the most straightforward way (which, considering the overheads
of alternative approaches, is Mel's preference): the right migratetype is
already in page_private(page), but free_pcppages_bulk() wasn't using it.
How did this bug show up? As a 20% slowdown in my tmpfs loop kbuild
swapping tests, on PowerMac G5 with SLUB allocator. Bisecting to that
commit was easy, but explaining the magnitude of the slowdown not easy.
The same effect appears, but much less markedly, with SLAB, and even
less markedly on other machines (the PowerMac divides into fewer zones
than x86, I think that may be a factor). We guess that lumpy reclaim
of short-lived high-order pages is implicated in some way, and probably
this bug has been tickling a poor decision somewhere in page reclaim.
But instrumentation hasn't told me much, I've run out of time and
imagination to determine exactly what's going on, and shouldn't hold up
the fix any longer: it's valid, and might even fix other misbehaviours.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: check total number of devices when removing missing
Btrfs: check return value of open_bdev_exclusive properly
Btrfs: do not mark the chunk as readonly if in degraded mode
Btrfs: run orphan cleanup on default fs root
Btrfs: fix a memory leak in btrfs_init_acl
Btrfs: Use correct values when updating inode i_size on fallocate
Btrfs: remove tree_search() in extent_map.c
Btrfs: Add mount -o compress-force
Convert CONFIG_ARCH_OMAP34XX to CONFIG_ARCH_OMAP3, and
CONFIG_ARCH_OMAP24XX to CONFIG_ARCH_OMAP2, in preparation for Tony's
multi-OMAP patches.
While here, update some copyrights, convert instances of "34xx" to
"3xxx" where applicable, and convert preprocessor directives of the
form
#if defined(CONFIG_ARCH_OMAP2) | defined(CONFIG_ARCH_OMAP3)
to
#if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3)
for standardization.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Tony Lindgren <tony@atomide.com>
The macros defining the shift bits in registers for various
register bit fields are defined as 1 << n.
Instead define them as n. They can then be used as val << n.
The changes are generated by updating the script which autogenerates
the files modifed in the patch.
Signed-off-by: Rajendra Nayak <rnayak@ti.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Rename the omap2_clk_init() in the OMAP2, 3, and 4 clock code to be
omap2xxx_clk_init(), omap3xxx_clk_init(), etc. Remove all traces of
the (commented) old virt_prcm_set code from omap3xxx_clk_init() and
omap4xxx_clk_init(), since this will be handled with the OPP code that
is cooking in the PM branch.
After this patch, there should be very little else in the clock code
that blocks a multi-OMAP 2+3 kernel. (OMAP2420+OMAP2430 still has some
outstanding issues that need to be resolved; this is pending on some
additions to the hwmod data.)
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Move all static functions up to the top of the file to match the
practice in other OMAP clock code. Make omap3_noncore_dpll_program()
static (noted by sparse) and prepend an underscore to the function
name to mark that it is file-local.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
omap2_clk_prepare_for_reboot() is only applicable to OMAP2xxx chips,
so rename it to omap2xxx_clk_prepare_for_reboot() and only call it when
running on OMAP2xxx chips. Remove the old stub in the OMAP3 clock code.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Now that almost all of the code has been removed from clock2xxx.c and
clock34xx.c, many of the includes are now unnecessary and can be removed.
While we're here, standardize the initial comment blocks.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Richard Woodruff <r-woodruff2@ti.com>
Cc: Jouni Högander <jouni.hogander@nokia.com>
In the OMAP3xxx clock code, remove the #ifdef CONFIG_ARCH_OMAP3 in
clock34xx.c, since this file is only compiled for OMAP3xxx builds. Also,
rename omap2_clk_arch_init in this file to omap3xxx_clk_arch_init() to
pave the way for multi-OMAP kernels. Ensure that it is not executed
on non-OMAP3xxx systems.
In the OMAP2xxx clock code, rename omap2_clk_arch_init in this file to
omap2xxx_clk_arch_init() to pave the way for multi-OMAP kernels.
Ensure that it is not executed on non-OMAP2xxx systems.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Here are the sparc bits to remove TIF_ABI_PENDING now that
set_personality() is called at the appropriate place in exec.
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that the previous commit made it possible to do the personality
setting at the point of no return, we do just that for ELF binaries.
And suddenly all the reasons for that insane TIF_ABI_PENDING bit go
away, and we can just make SET_PERSONALITY() just do the obvious thing
for a 32-bit compat process.
Everything becomes much more straightforward this way.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
'flush_old_exec()' is the point of no return when doing an execve(), and
it is pretty badly misnamed. It doesn't just flush the old executable
environment, it also starts up the new one.
Which is very inconvenient for things like setting up the new
personality, because we want the new personality to affect the starting
of the new environment, but at the same time we do _not_ want the new
personality to take effect if flushing the old one fails.
As a result, the x86-64 '32-bit' personality is actually done using this
insane "I'm going to change the ABI, but I haven't done it yet" bit
(TIF_ABI_PENDING), with SET_PERSONALITY() not actually setting the
personality, but just the "pending" bit, so that "flush_thread()" can do
the actual personality magic.
This patch in no way changes any of that insanity, but it does split the
'flush_old_exec()' function up into a preparatory part that can fail
(still called flush_old_exec()), and a new part that will actually set
up the new exec environment (setup_new_exec()). All callers are changed
to trivially comply with the new world order.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 761c9d45 (ASoC: Fix build of OMAP sound drivers) changes
CONFIG_MACH_OMAP3517EVM -> CONFIG_SND_OMAP_SOC_OMAP3517EVM in the
Makefile. Whereas the config option defined in Kconfig is
SND_OMAP_SOC_AM3517EVM. Because of this, ASoC driver for AM3517
was not getting compiled.
Signed-off-by: Anuj Aggarwal <anuj.aggarwal@ti.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Commit e9ff5eb2 (Fixing infinite loop in resume path) uses wrong AIC23
register in resume function because of which register writes happen
on some non-existing registers.
Signed-off-by: Anuj Aggarwal <anuj.aggarwal@ti.com>
Acked-by: Liam Girdwood <lrg@slimlogic.co.uk>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
This patch documents a new ABS_MT parameter and adds further text to
clarify some points around the MT protocol.
Requested-by: Yoonyoung Shim <jy0922.shim@samsung.com>
Requested-by: Mika Kuoppala <mika.kuoppala@nokia.com>
Requested-by: Peter Hutterer <peter.hutterer@who-t.net>
Signed-off-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
For pressure-based multi-touch devices, a direct way to send sensor
intensity data per finger is needed. This patch adds the ABS_MT_PRESSURE
event to the MT protocol.
Requested-by: Yoonyoung Shim <jy0922.shim@samsung.com>
Requested-by: Mika Kuoppala <mika.kuoppala@nokia.com>
Requested-by: Peter Hutterer <peter.hutterer@who-t.net>
Signed-off-by: Henrik Rydberg <rydberg@euromail.se>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
I missed converting one dev_info call to deb_dbg before submitting the driver.
Without this change, a message will be printed to dmesg for each button press
if a RC6 remote is used.
Signed-off-by: David Härdeman <david@hardeman.nu>
Cc: stable <stable@kernel.org>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Some of the newer 4xx pci cores need an explicit bit set to send
type 1 transactions instead of just comparing the bus numbers.
This patch enables type 1 transations for pcix nodes, thus enabling
devices behind PCI bridges.
Signed-off-by: Stef van Os <stef.van.os@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Add missing call to pci_fixup_device(pci_fixup_early, ...) when
building the pci_dev from scratch off the Open Firmware device-tree
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Add missing hookup to existing pci_slot when building the pci_dev from
scratch off the Open Firmware device-tree
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We are missing these when building the pci_dev from scratch off
the Open Firmware device-tree
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Commit 37e8273cd3 ("usbnet: Set link down
initially for drivers that update link state") changed the initial link
state in cdc_ether and other drivers based on the understanding that the
devices they support generate link change interrupts. However, this is
optional in the CDC Ethernet protocol, and two users have reported in
<http://bugzilla.kernel.org/show_bug.cgi?id=14791> that the link state
for their devices remains down. Therefore, revert the change in
cdc_ether.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Tested-by: Avi Rozen <avi.rozen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
Fix failure exit in ipathfs
fix oops in fs/9p late mount failure
fix leak in romfs_fill_super()
get rid of pointless checks after simple_pin_fs()
Fix failure exits in bfs_fill_super()
fix affs parse_options()
Fix remount races with symlink handling in affs
Fix a leak in affs_fill_super()
Split the DPLL3 M2 divider clock functions out of clock34xx.c and move
them into mach-omap2/clkt34xx_dpll3m2.c. This is intended to make the
clock code easier to understand, since all of the functions needed to
manage the OMAP3 DPLL3 M2 divider are now located in their own file,
rather than being mixed with other, unrelated functions.
Clock debugging is also now more finely-grained, since the DEBUG macro
can now be defined for the DPLL3 M2 clock alone. This should reduce
unnecessary console noise when debugging DVFS.
Also, if at some future point the mach-omap2/ directory is split
into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap34xx/
directory, rather than shared with other chip types that don't use this
clock type.
This patch also lays the groundwork to skip compilation of this
code on OMAP3 chips that don't support DVFS (e.g., AM35xx) via
the Makefile, rather than via #ifdefs.
Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to
improve the patch description.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Jouni Högander <jouni.hogander@nokia.com>
Cc: Alexander Shishkin <virtuoso@slind.org>
omap2430_clk_i2chs_find_idlest() doesn't need to be compiled in on
non-2430 builds, so skip it in those cases to save memory.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Move the sys_clk clock functions from clock2xxx.c to
mach-omap2/clkt2xxx_sys.c. This is intended to make the clock code
easier to understand, since all of the functions needed to manage the
sys_clk are now located in their own file, rather than being mixed
with other, unrelated functions.
Clock debugging is also now more finely-grained, since the DEBUG
macro can now be defined for the sys_clk clock alone. This
should reduce unnecessary console noise when debugging.
Also, if at some future point the mach-omap2/ directory is split into
OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/
directory, rather than shared with other chip types that don't use
this clock type.
Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to
improve the patch description.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Alexander Shishkin <virtuoso@slind.org>
Move the osc_clk clock functions from clock2xxx.c to
mach-omap2/clkt2xxx_osc. This is intended to make the clock code
easier to understand, since all of the functions needed to manage the
osc_clk are now located in their own file, rather than being mixed
with other, unrelated functions.
Clock debugging is also now more finely-grained, since the DEBUG
macro can now be defined for osc_clk clocks alone. This
should reduce unnecessary console noise when debugging.
Also, if at some future point the mach-omap2/ directory is split
into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/
directory, rather than shared with other chip types that don't use this
clock type.
Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to
improve the patch description.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Alexander Shishkin <virtuoso@slind.org>
Move the APLL-related clock functions from clock2xxx.c to
mach-omap2/clkt2xxx_apll.c. This is intended to make the clock code
easier to understand, since all of the functions needed to manage APLLs
are now located in their own file, rather than being mixed with other,
unrelated functions.
Clock debugging is also now more finely-grained, since the DEBUG
macro can now be defined for APLL clocks alone. This
should reduce unnecessary console noise when debugging.
Also, if at some future point the mach-omap2/ directory is split
into OMAP2/3/4 variants, this clkt file can be placed in the mach-omap2xxx/
directory, rather than shared with other chip types that don't use this
clock type.
Thanks to Alexander Shishkin <virtuoso@slind.org> for his comments to
improve the patch description.
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Richard Woodruff <r-woodruff2@ti.com>
Cc: Alexander Shishkin <virtuoso@slind.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6:
x86/PCI: remove IOH range fetching
PCI: fix nested spinlock hang in aer_inject
* master.kernel.org:/home/rmk/linux-2.6-arm:
[ARM] Update mach-types
[ARM] orion5x: D-link DNS-323 rev. B1 power-off
[ARM] Orion5x: add GPIO LED and buttons for wrt350n v2
[ARM] pxa: fix irq suspend/resume for pxa25x
[ARM] pxa: fix the incorrect naming of AC97 reset pin config for pxa26x
[ARM] pxa/corgi: fix incorrect default GPIO for UDC Vbus
[ARM] Kirkwood: drive USB VBUS pin on rd88f6192-nas high on boot
[ARM] Orion: fix PCIe inbound window programming when RAM size is not a power of two
If you have a disk failure in RAID1 and then add a new disk to the
array, and then try to remove the missing volume, it will fail. The
reason is the sanity check only looks at the total number of rw devices,
which is just 2 because we have 2 good disks and 1 bad one. Instead
check the total number of devices in the array to make sure we can
actually remove the device. Tested this with a failed disk setup and
with this test we can now run
btrfs-vol -r missing /mount/point
and it works fine.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Hit this problem while testing RAID1 failure stuff. open_bdev_exclusive
returns ERR_PTR(), not NULL. So change the return value properly. This
is important if you accidently specify a device that doesn't exist when
trying to add a new device to an array, you will panic the box
dereferencing bdev.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If a RAID setup has chunks that span multiple disks, and one of those
disks has failed, btrfs_chunk_readonly will return 1 since one of the
disks in that chunk's stripes is dead and therefore not writeable. So
instead if we are in degraded mode, return 0 so we can go ahead and
allocate stuff. Without this patch all of the block groups in a RAID1
setup will end up read-only, which will mean we can't add new disks to
the array since we won't be able to make allocations.
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch revert's commit
6c090a11e1
Since it introduces this problem where we can run orphan cleanup on a
volume that can have orphan entries re-added. Instead of my original
fix, Yan Zheng pointed out that we can just revert my original fix and
then run the orphan cleanup in open_ctree after we look up the fs_root.
I have tested this with all the tests that gave me problems and this
patch fixes both problems. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
In btrfs_init_acl() cloned acl is not released
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
commit f2bc9dd07e3424c4ec5f3949961fe053d47bc825
Author: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Date: Wed Jan 20 12:57:53 2010 +0530
Btrfs: Use correct values when updating inode i_size on fallocate
Even though we allocate more, we should be updating inode i_size
as per the arguments passed
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch removes tree_search() in extent_map.c because it is not called by
anything.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The default btrfs mount -o compress mode will quickly back off
compressing a file if it notices that compression does not reduce the
size of the data being written. This can save considerable CPU because
all future writes to the file go through uncompressed.
But some files are both very large and have mixed data stored in
them. In that case, we want to add the ability to always try
compressing data before writing it.
This commit adds mount -o compress-force. A later commit will add
a new inode flag that does the same thing.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus:
MIPS: PowerTV: Fix support for timer interrupts with > 64 external IRQs
MIPS: PowerTV: Streamline access to platform device registers
MIPS: Fix vmlinuz build for 32bit-only math shells
MIPS: Add support of LZO-compressed kernels
Turned out to cause trouble on single IOH machines, and is superceded by
_CRS on multi-IOH machines with production BIOSes.
Signed-off-by: Jeff Garrett <jeff@jgarrett.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
We have to properly decrease bi_size in order to merge_bvec_fn return
right result. Otherwise this result in false merge rejects for two
absolutely valid bio_vecs. This may cause significant performance
penalty for example fs_block_size == 1k and block device is raid0 with
small chunk_size = 8k. Then it is impossible to merge 7-th fs-block in
to bio which already has 6 fs-blocks.
Cc: <stable@kernel.org>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
