25818f0f28 (memblock: Make MEMBLOCK_ERROR be 0) thankfully made
MEMBLOCK_ERROR 0 and there already are codes which expect error return
to be 0. There's no point in keeping MEMBLOCK_ERROR around. End its
misery.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-6-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
After node affine allocation fails, memblock_alloc_try_nid() calls
memblock_alloc_base() with @max_addr set to MEMBLOCK_ALLOC_ANYWHERE.
This is inconsistent with memblock_alloc() and what the function's
sole user - sparc/mm/init_64 - expects, although it doesn't make any
difference as sparc64 doesn't have highmem and ACCESSIBLE equals
ANYWHERE.
This patch makes memblock_alloc_try_nid() use ACCESSIBLE instead of
ANYWHERE. This isn't complete as node affine allocation doesn't
consider memblock.current_limit. It will be handled with future
changes.
This patch doesn't introduce any behavior difference.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-4-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
a226f6c899 (FRV: Clean up bootmem allocator's page freeing algorithm)
separated out __free_pages_bootmem() from free_all_bootmem_core().
__free_pages_bootmem() takes @order argument but it assumes @order is
either 0 or ilog2(BITS_PER_LONG). Note that all the current users
match that assumption and this doesn't cause actual problems.
Fix it by using 1 << order instead of BITS_PER_LONG.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-3-git-send-email-tj@kernel.org
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
The return value of memblock_x86_check_reserved_size() doesn't
indicate whether there's an overlapping reservatoin or not. It
indicates whether the caller needs to iterate further to discover all
reserved portions of the specified area.
efi_reserve_boot_esrvices() wants to check whether the boot services
area overlaps with other reservations but incorrectly used
membloc_x86_check_reserved_size(). Use memblock_is_region_reserved()
instead.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/1310457490-3356-2-git-send-email-tj@kernel.org
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
SPARSEMEM w/o VMEMMAP and DISCONTIGMEM, both used only on 32bit, use
sections array to map pfn to nid which is limited in granularity. If
NUMA nodes are laid out such that the mapping cannot be accurate, boot
will fail triggering BUG_ON() in mminit_verify_page_links().
On 32bit, it's 512MiB w/ PAE and SPARSEMEM. This seems to have been
granular enough until commit 2706a0bf7b (x86, NUMA: Enable
CONFIG_AMD_NUMA on 32bit too). Apparently, there is a machine which
aligns NUMA nodes to 128MiB and has only AMD NUMA but not SRAT. This
led to the following BUG_ON().
On node 0 totalpages: 2096615
DMA zone: 32 pages used for memmap
DMA zone: 0 pages reserved
DMA zone: 3927 pages, LIFO batch:0
Normal zone: 1740 pages used for memmap
Normal zone: 220978 pages, LIFO batch:31
HighMem zone: 16405 pages used for memmap
HighMem zone: 1853533 pages, LIFO batch:31
BUG: Int 6: CR2 (null)
EDI (null) ESI 00000002 EBP 00000002 ESP c1543ecc
EBX f2400000 EDX 00000006 ECX (null) EAX 00000001
err (null) EIP c16209aa CS 00000060 flg 00010002
Stack: f2400000 00220000 f7200800 c1620613 00220000 01000000 04400000 00238000
(null) f7200000 00000002 f7200b58 f7200800 c1620929 000375fe (null)
f7200b80 c16395f0 00200a02 f7200a80 (null) 000375fe 00000002 (null)
Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00181-g2706a0b #17
Call Trace:
[<c136b1e5>] ? early_fault+0x2e/0x2e
[<c16209aa>] ? mminit_verify_page_links+0x12/0x42
[<c1620613>] ? memmap_init_zone+0xaf/0x10c
[<c1620929>] ? free_area_init_node+0x2b9/0x2e3
[<c1607e99>] ? free_area_init_nodes+0x3f2/0x451
[<c1601d80>] ? paging_init+0x112/0x118
[<c15f578d>] ? setup_arch+0x791/0x82f
[<c15f43d9>] ? start_kernel+0x6a/0x257
This patch implements node_map_pfn_alignment() which determines
maximum internode alignment and update numa_register_memblks() to
reject NUMA configuration if alignment exceeds the pfn -> nid mapping
granularity of the memory model as determined by PAGES_PER_SECTION.
This makes the problematic machine boot w/ flatmem by rejecting the
NUMA config and provides protection against crazy NUMA configurations.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20110712074534.GB2872@htj.dyndns.org
LKML-Reference: <20110628174613.GP478@escobedo.osrc.amd.com>
Reported-and-Tested-by: Hans Rosenfeld <hans.rosenfeld@amd.com>
Cc: Conny Seidel <conny.seidel@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
DISCONTIGMEM on x86-32 implements pfn -> nid mapping similarly to
SPARSEMEM; however, it calls each mapping unit ELEMENT instead of
SECTION. This patch renames it to SECTION so that PAGES_PER_SECTION
is valid for both DISCONTIGMEM and SPARSEMEM. This will be used by
the next patch to implement mapping granularity check.
This patch is trivial constant rename.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20110712074422.GA2872@htj.dyndns.org
Cc: Hans Rosenfeld <hans.rosenfeld@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
That file harkens back to the days of the big 2.4 -> 2.6 version jump,
and was based even then on older versions. Some of it is just obsolete,
and Jesper Juhl points out that it talks about kernel versions 2.6 and
should be updated to 3.0.
Remove some obsolete text, and re-phrase some other to not be 2.6-specific.
Reported-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6:
[media] msp3400: fill in v4l2_tuner based on vt->type field
[media] tuner-core.c: don't change type field in g_tuner or g_frequency
[media] cx18/ivtv: fix g_tuner support
[media] tuner-core: power up tuner when called with s_power(1)
[media] v4l2-ioctl.c: check for valid tuner type in S_HW_FREQ_SEEK
[media] tuner-core: simplify the standard fixup
[media] tuner-core/v4l2-subdev: document that the type field has to be filled in
[media] v4l2-subdev.h: remove unused s_mode tuner op
[media] feature-removal-schedule: change in how radio device nodes are handled
[media] bttv: fix s_tuner for radio
[media] pvrusb2: fix g/s_tuner support
[media] v4l2-ioctl.c: prefill tuner type for g_frequency and g/s_tuner
[media] tuner-core: fix tuner_resume: use t->mode instead of t->type
[media] tuner-core: fix s_std and s_tuner
* git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6:
cifs: drop spinlock before calling cifs_put_tlink
cifs: fix expand_dfs_referral
cifs: move bdi_setup_and_register outside of CONFIG_CIFS_DFS_UPCALL
cifs: factor smb_vol allocation out of cifs_setup_volume_info
cifs: have cifs_cleanup_volume_info not take a double pointer
cifs: fix build_unc_path_to_root to account for a prefixpath
cifs: remove bogus call to cifs_cleanup_volume_info
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86:
hp-wmi: fix use after free
dell-laptop - using buffer without mutex_lock
Revert: "dell-laptop: Toggle the unsupported hardware killswitch"
platform-drivers-x86: set backlight type to BACKLIGHT_PLATFORM
thinkpad-acpi: handle HKEY 0x4010, 0x4011 events
drivers/platform/x86: Fix memory leak
thinkpad-acpi: handle some new HKEY 0x60xx events
acer-wmi: fix bitwise bug when set device state
acer-wmi: Only update rfkill status for associated hotkey events
Since we removed sti()/cli() and related, how about removing it from
Documentation/spinlocks.txt?
Signed-off-by: Muthukumar R <muthur@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[ 191.310008] WARNING: kmemcheck: Caught 32-bit read from freed memory (f0d25f14)
[ 191.310011] c056d2f088000000105fd2f00000000050415353040000000000000000000000
[ 191.310020] i i i i f f f f f f f f f f f f f f f f f f f f f f f f f f f f
[ 191.310027] ^
[ 191.310029]
[ 191.310032] Pid: 737, comm: modprobe Not tainted 3.0.0-rc5+ #268 Hewlett-Packard HP Compaq 6005 Pro SFF PC/3047h
[ 191.310036] EIP: 0060:[<f80b3104>] EFLAGS: 00010286 CPU: 0
[ 191.310039] EIP is at hp_wmi_perform_query+0x104/0x150 [hp_wmi]
[ 191.310041] EAX: f0d25601 EBX: f0d25f00 ECX: 000121cf EDX: 000121ce
[ 191.310043] ESI: f0d25f10 EDI: f0f97ea8 EBP: f0f97ec4 ESP: c173f34c
[ 191.310045] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
[ 191.310046] CR0: 8005003b CR2: f540c000 CR3: 30f30000 CR4: 000006d0
[ 191.310048] DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
[ 191.310050] DR6: ffff4ff0 DR7: 00000400
[ 191.310051] [<f80b317b>] hp_wmi_dock_state+0x2b/0x40 [hp_wmi]
[ 191.310054] [<f80b6093>] hp_wmi_init+0x93/0x1a8 [hp_wmi]
[ 191.310057] [<c10011f0>] do_one_initcall+0x30/0x170
[ 191.310061] [<c107ab9f>] sys_init_module+0xef/0x1a60
[ 191.310064] [<c149f998>] sysenter_do_call+0x12/0x28
[ 191.310067] [<ffffffff>] 0xffffffff
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Matthew Garrett <mjg@redhat.com>
This reverts commit a3d77411e8,
as it causes a mess in the wireless rfkill status on some models.
It is probably a bad idea to toggle the rfkill for all dell models
without the respect to the claim that it is hardware-controlled.
Cc: stable@kernel.org
Signed-off-by: Keng-Yu Lin <kengyu@canonical.com>
Signed-off-by: Matthew Garrett <mjg@redhat.com>
Patch 2e711c04db
(PM: Remove sysdev suspend, resume and shutdown operations)
deleted sysdev_suspend(), which was being relied on to call
check_wakeup_irqs() in suspend. If check_wakeup_irqs() is not
called, wake interrupts that are pending when suspend is
entered may be lost. It also breaks IRQCHIP_MASK_ON_SUSPEND,
which is handled in check_wakeup_irqs().
This patch adds a call to check_wakeup_irqs() in syscore_suspend(),
similar to what was deleted in sysdev_suspend().
Signed-off-by: Colin Cross <ccross@android.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
I came across a memory leak during a cyclic cpu-online-offline test.
Signed-off-by: Yu Luming <luming.yu@intel.com>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dave Jones <davej@redhat.com>
* 'hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/groeck/staging:
hwmon: (pmbus) Improve auto-detection of temperature status register
hwmon: (lm95241) Fix negative temperature results
hwmon: (lm95241) Fix chip detection code
It is possible that a PMBus device supports the READ_TEMPERATURE2 and/or
READ_TEMPERATURE3 registers but does not support READ_TEMPERATURE1.
Improve temperature status register detection to address this condition.
Reported-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Guenter Roeck <guenter.roeck@ericsson.com>
Acked-by: Jean Delvare <khali@linux-fr.org>
Cc: stable@kernel.org # 2.6.39+
Negative temperatures were returned in degrees C instead of milli-Degrees C.
Also, negative temperatures were reported for remote temperature sensors even
if the chip was configured for positive-only results.
Fix by detecting temperature modes, and by treating negative temperatures
similar to positive temperatures, with appropriate sign extension.
Signed-off-by: Guenter Roeck <guenter.roeck@ericsson.com>
Acked-by: Jean Delvare <khali@linux-fr.org>
Cc: stable@kernel.org # 2.6.30+
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6:
ALSA: hda - Fix a copmile warning
ASoC: ak4642: fixup snd_soc_update_bits mask for PW_MGMT2
ALSA: hda - Change all ADCs for dual-adc switching mode for Realtek
ASoC: Manage WM8731 ACTIVE bit as a supply widget
ASoC: Don't set invalid name string to snd_card->driver field
ASoC: Ensure we delay long enough for WM8994 FLL to lock when starting
ASoC: Tegra: I2S: Ensure clock is enabled when writing regs
ASoC: Fix Blackfin I2S _pointer() implementation return in bounds values
ASoC: tlv320aic3x: Do soft reset to codec when going to bias off state
ASoC: tlv320aic3x: Don't sync first two registers from register cache
audio: tlv320aic26: fix PLL register configuration
* 'fixes' of master.kernel.org:/home/rmk/linux-2.6-arm:
ARM: 6994/1: smp_twd: Fix typo in 'twd_timer_rate' printing
ARM: 6987/1: l2x0: fix disabling function to avoid deadlock
ARM: 6966/1: ep93xx: fix inverted RTS/DTR signals on uart1
ARM: 6980/1: mmci: use StartBitErr to detect bad connections
ARM: 6979/1: mach-vt8500: add forgotten irq_data conversion
ARM: move memory layout sanity checking before meminfo initialization
ARM: 6990/1: MAINTAINERS: add entry for ARM PMU profiling and debugging
ARM: 6989/1: perf: do not start the PMU when no events are present
ARM: dmabounce: fix map_single() error return value
When firewire-ohci is bound to a Pinnacle MovieBoard, eventually a
"Register access failure" is logged and an interrupt storm or a kernel
panic happens. https://bugzilla.kernel.org/show_bug.cgi?id=36622
Until this is sorted out (if that is going to succeed at all), let's
just prevent firewire-ohci from touching these devices.
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Cc: <stable@kernel.org>
Regression introduced in commit 724d9f1cfb.
Prior to that, expand_dfs_referral would regenerate the mount data string
and then call cifs_parse_mount_options to re-parse it (klunky, but it
worked). The above commit moved cifs_parse_mount_options out of cifs_mount,
so the re-parsing of the new mount options no longer occurred. Fix it by
making expand_dfs_referral re-parse the mount options.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
This needs to be done regardless of whether that KConfig option is set
or not.
Reported-by: Sven-Haegar Koch <haegar@sdinet.de>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
It's harmless but annyoing.
sound/pci/hda/patch_realtek.c: In function ‘alc_cap_getput_caller’:
sound/pci/hda/patch_realtek.c:2722:9: warning: ‘err’ may be used uninitialized in this function
Signed-off-by: Takashi Iwai <tiwai@suse.de>
* 's5p-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/kgene/linux-samsung:
ARM: S3C2440: fix section mismatch on mini2440
ARM: S3C24XX: drop return codes in void function of dma.c
ARM: S3C24XX: don't use uninitialized variable in dma.c
ARM: EXYNOS4: Set appropriate I2C device variant
ARM: S5PC100: Fix for compilation error
spi/s3c64xx: Bug fix for SPI with different FIFO level
ARM: SAMSUNG: Add tx_st_done variable
ARM: EXYNOS4: Address a section mismatch w/ suspend issue.
ARM: S5P: Fix bug on init of PWMTimers for HRTimer
ARM: SAMSUNG: header file revised to prevent declaring duplicated
ARM: EXYNOS4: fix improper gpio configuration
ARM: EXYNOS4: Fix card detection for sdhci 0 and 2
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/lrg/voltage-2.6:
regulator: max8997: Fix setting inappropriate value for ramp_delay variable
regulator: db8500-prcmu: small fixes
regulator: max8997: remove dependency on platform_data pointer
regulator: MAX8997: Fix for divide by zero error
regulator: max8952 - fix wrong gpio valid check
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
btrfs: fix oops when doing space balance
Btrfs: don't panic if we get an error while balancing V2
btrfs: add missing options displayed in mount output
This driver handles the variants pca9530-pca9533, so it chose the name
"pca953x". However, there is a gpio driver which decided on the same
name. As a result, those two can't be loaded at the same time. Add a
subsystem prefix to make the driver name unique. Device matching will not
suffer, because both are I2C drivers which match using a
i2c_device_id-table which is not altered.
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Jean Delvare <khali@linux-fr.org>
Cc: Richard Purdie <richard.purdie@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
remap_pfn_range() means map physical address pfn<<PAGE_SHIFT to user addr.
For nommu arch it's implemented by vma->vm_start = pfn << PAGE_SHIFT which
is wrong acroding the original meaning of this function. And some driver
developer using remap_pfn_range() with correct parameter will get
unexpected result because vm_start is changed. It should be implementd
like addr = pfn << PAGE_SHIFT but which is meanless on nommu arch, this
patch just make it simply return.
Parameter name and setting of vma->vm_flags also be fixed.
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Greg Ungerer <gerg@uclinux.org>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Bob Liu <lliubbo@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes a regression in 3.0 reported by Paul Parsons regarding the
removal of the msleep(1) in the ds1wm_reset() function:
: The linux-3.0-rc4 DS1WM 1-wire driver is logging "bus error, retrying"
: error messages on an HP iPAQ hx4700 PDA (XScale-PXA270):
:
: <snip>
: Driver for 1-wire Dallas network protocol.
: DS1WM w1 busmaster driver - (c) 2004 Szabolcs Gyurko
: 1-Wire driver for the DS2760 battery monitor chip - (c) 2004-2005, Szabolcs Gyurko
: ds1wm ds1wm: pass: 1 bus error, retrying
: ds1wm ds1wm: pass: 2 bus error, retrying
: ds1wm ds1wm: pass: 3 bus error, retrying
: ds1wm ds1wm: pass: 4 bus error, retrying
: ds1wm ds1wm: pass: 5 bus error, retrying
: ...
:
: The visible result is that the battery charging LED is erratic; sometimes
: it works, mostly it doesn't.
:
: The linux-2.6.39 DS1WM 1-wire driver worked OK. I haven't tried 3.0-rc1,
: 3.0-rc2, or 3.0-rc3.
This sleep should not be required on normal circuitry provided the
pull-ups on the bus are correctly adapted to the slaves. Unfortunately,
this is not always the case. The sleep is restored but as a parameter to
the probe function in the pdata.
[akpm@linux-foundation.org: coding-style fixes]
Reported-by: Paul Parsons <lost.distance@yahoo.com>
Tested-by: Paul Parsons <lost.distance@yahoo.com>
Signed-off-by: Jean-François Dagenais <dagenaisj@sonatest.com>
Cc: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
commit 889976dbcb ("memcg: reclaim memory from nodes in round-robin
order") adds an numa node round-robin for memcg. But the information is
updated once per 10sec.
This patch changes the update trigger from jiffies to memcg's event count.
After this patch, numa scan information will be updated when we see 1024
events of pagein/pageout under a memcg.
[akpm@linux-foundation.org: attempt to repair code layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now, in mem_cgroup_hierarchical_reclaim(), mem_cgroup_local_usage() is
used for checking whether the memcg contains reclaimable pages or not. If
no pages in it, the routine skips it.
But, mem_cgroup_local_usage() contains Unevictable pages and cannot handle
"noswap" condition correctly. This doesn't work on a swapless system.
This patch adds test_mem_cgroup_reclaimable() and replaces
mem_cgroup_local_usage(). test_mem_cgroup_reclaimable() see LRU counter
and returns correct answer to the caller. And this new function has
"noswap" argument and can see only FILE LRU if necessary.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix kerneldoc layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__tlb_remove_page() switches to a new batch page, but still checks space
in the old batch. This check always fails, and causes a forced tlb flush.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour. Unfortunately, if the highest zone is small, a
problem occurs.
When balance_pgdat() returns, it may be at a lower classzone_idx than it
started because the highest zone was unreclaimable. Before checking if it
should go to sleep though, it checks pgdat->classzone_idx which when there
is no other activity will be MAX_NR_ZONES-1. It interprets this as it has
been woken up while reclaiming, skips scheduling and reclaims again. As
there is no useful reclaim work to do, it enters into a loop of shrinking
slab consuming loads of CPU until the highest zone becomes reclaimable for
a long period of time.
There are two problems here. 1) If the returned classzone or order is
lower, it'll continue reclaiming without scheduling. 2) if the highest
zone was marked unreclaimable but balance_pgdat() returns immediately at
DEF_PRIORITY, the new lower classzone is not communicated back to kswapd()
for sleeping.
This patch does two things that are related. If the end_zone is
unreclaimable, this information is communicated back. Second, if the
classzone or order was reduced due to failing to reclaim, new information
is not read from pgdat and instead an attempt is made to go to sleep. Due
to this, it is also necessary that pgdat->classzone_idx be initialised
each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as
wakeups.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When deciding if kswapd is sleeping prematurely, the classzone is taken
into account but this is different to what balance_pgdat() and the
allocator are doing. Specifically, the DMA zone will be checked based on
the classzone used when waking kswapd which could be for a GFP_KERNEL or
GFP_HIGHMEM request. The lowmem reserve limit kicks in, the watermark is
not met and kswapd thinks it's sleeping prematurely keeping kswapd awake in
error.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour.
When kswapd applies pressure to zones during node balancing, it checks if
the zone is above a high+balance_gap threshold. If it is, it does not
apply pressure but it unconditionally shrinks slab on a global basis which
is excessive. In the event kswapd is being kept awake due to a high small
unreclaimable zone, it skips zone shrinking but still calls shrink_slab().
Once pressure has been applied, the check for zone being unreclaimable is
being made before the check is made if all_unreclaimable should be set.
This miss of unreclaimable can cause has_under_min_watermark_zone to be
set due to an unreclaimable zone preventing kswapd backing off on
congestion_wait().
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour. Unfortunately, if the highest zone is small, a
problem occurs.
This seems to happen most with recent sandybridge laptops but it's
probably a co-incidence as some of these laptops just happen to have a
small Normal zone. The reproduction case is almost always during copying
large files that kswapd pegs at 100% CPU until the file is deleted or
cache is dropped.
The problem is mostly down to sleeping_prematurely() keeping kswapd awake
when the highest zone is small and unreclaimable and compounded by the
fact we shrink slabs even when not shrinking zones causing a lot of time
to be spent in shrinkers and a lot of memory to be reclaimed.
Patch 1 corrects sleeping_prematurely to check the zones matching
the classzone_idx instead of all zones.
Patch 2 avoids shrinking slab when we are not shrinking a zone.
Patch 3 notes that sleeping_prematurely is checking lower zones against
a high classzone which is not what allocators or balance_pgdat()
is doing leading to an artifical belief that kswapd should be
still awake.
Patch 4 notes that when balance_pgdat() gives up on a high zone that the
decision is not communicated to sleeping_prematurely()
This problem affects 2.6.38.8 for certain and is expected to affect 2.6.39
and 3.0-rc4 as well. If accepted, they need to go to -stable to be picked
up by distros and this series is against 3.0-rc4. I've cc'd people that
reported similar problems recently to see if they still suffer from the
problem and if this fixes it.
This patch: correct the check for kswapd sleeping in sleeping_prematurely()
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour.
A problem occurs if the highest zone is small. balance_pgdat() only
considers unreclaimable zones when priority is DEF_PRIORITY but
sleeping_prematurely considers all zones. It's possible for this sequence
to occur
1. kswapd wakes up and enters balance_pgdat()
2. At DEF_PRIORITY, marks highest zone unreclaimable
3. At DEF_PRIORITY-1, ignores highest zone setting end_zone
4. At DEF_PRIORITY-1, calls shrink_slab freeing memory from
highest zone, clearing all_unreclaimable. Highest zone
is still unbalanced
5. kswapd returns and calls sleeping_prematurely
6. sleeping_prematurely looks at *all* zones, not just the ones
being considered by balance_pgdat. The highest small zone
has all_unreclaimable cleared but the zone is not
balanced. all_zones_ok is false so kswapd stays awake
This patch corrects the behaviour of sleeping_prematurely to check the
zones balance_pgdat() checked.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
