13 Jan, 2012
1 commit
-
This patch adds a lightweight sync migrate operation MIGRATE_SYNC_LIGHT
mode that avoids writing back pages to backing storage. Async compaction
maps to MIGRATE_ASYNC while sync compaction maps to MIGRATE_SYNC_LIGHT.
For other migrate_pages users such as memory hotplug, MIGRATE_SYNC is
used.This avoids sync compaction stalling for an excessive length of time,
particularly when copying files to a USB stick where there might be a
large number of dirty pages backed by a filesystem that does not support
->writepages.[aarcange@redhat.com: This patch is heavily based on Andrea's work]
[akpm@linux-foundation.org: fix fs/nfs/write.c build]
[akpm@linux-foundation.org: fix fs/btrfs/disk-io.c build]
Signed-off-by: Mel Gorman
Reviewed-by: Rik van Riel
Cc: Andrea Arcangeli
Cc: Minchan Kim
Cc: Dave Jones
Cc: Jan Kara
Cc: Andy Isaacson
Cc: Nai Xia
Cc: Johannes Weiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
11 Jan, 2012
1 commit
-
mpol_equal() logically returns a boolean. Use a bool type to slightly
improve readability.Signed-off-by: KOSAKI Motohiro
Cc: Stephen Wilson
Acked-by: David Rientjes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
30 Dec, 2011
1 commit
-
commit 8aacc9f550 ("mm/mempolicy.c: fix pgoff in mbind vma merge") is the
slightly incorrect fix.Why? Think following case.
1. map 4 pages of a file at offset 0
[0123]
2. map 2 pages just after the first mapping of the same file but with
page offset 2[0123][23]
3. mbind() 2 pages from the first mapping at offset 2.
mbind_range() should treat new vma is,[0123][23]
|23|
mbind vmabut it does
[0123][23]
|01|
mbind vmaOops. then, it makes wrong vma merge and splitting ([01][0123] or similar).
This patch fixes it.
[testcase]
test result - before the patchcase4: 126: test failed. expect '2,4', actual '2,2,2'
case5: passed
case6: passed
case7: passed
case8: passed
case_n: 246: test failed. expect '4,2', actual '1,4'------------[ cut here ]------------
kernel BUG at mm/filemap.c:135!
invalid opcode: 0000 [#4] SMP DEBUG_PAGEALLOC(snip long bug on messages)
test result - after the patch
case4: passed
case5: passed
case6: passed
case7: passed
case8: passed
case_n: passedsource: mbind_vma_test.c
============================================================
#include
#include
#include
#include
#include
#include
#includestatic unsigned long pagesize;
void* mmap_addr;
struct bitmask *nmask;
char buf[1024];
FILE *file;
char retbuf[10240] = "";
int mapped_fd;char *rubysrc = "ruby -e '\
pid = %d; \
vstart = 0x%llx; \
vend = 0x%llx; \
s = `pmap -q #{pid}`; \
rary = []; \
s.each_line {|line|; \
ary=line.split(\" \"); \
addr = ary[0].to_i(16); \
if(vstart < vend) then \
rary.push(ary[1].to_i()/4); \
end; \
}; \
print rary.join(\",\"); \
'";void init(void)
{
void* addr;
char buf[128];nmask = numa_allocate_nodemask();
numa_bitmask_setbit(nmask, 0);pagesize = getpagesize();
sprintf(buf, "%s", "mbind_vma_XXXXXX");
mapped_fd = mkstemp(buf);
if (mapped_fd == -1)
perror("mkstemp "), exit(1);
unlink(buf);if (lseek(mapped_fd, pagesize*8, SEEK_SET) < 0)
perror("lseek "), exit(1);
if (write(mapped_fd, "\0", 1) < 0)
perror("write "), exit(1);addr = mmap(NULL, pagesize*8, PROT_NONE,
MAP_SHARED, mapped_fd, 0);
if (addr == MAP_FAILED)
perror("mmap "), exit(1);if (mprotect(addr+pagesize, pagesize*6, PROT_READ|PROT_WRITE) < 0)
perror("mprotect "), exit(1);mmap_addr = addr + pagesize;
/* make page populate */
memset(mmap_addr, 0, pagesize*6);
}void fin(void)
{
void* addr = mmap_addr - pagesize;
munmap(addr, pagesize*8);memset(buf, 0, sizeof(buf));
memset(retbuf, 0, sizeof(retbuf));
}void mem_bind(int index, int len)
{
int err;err = mbind(mmap_addr+pagesize*index, pagesize*len,
MPOL_BIND, nmask->maskp, nmask->size, 0);
if (err)
perror("mbind "), exit(err);
}void mem_interleave(int index, int len)
{
int err;err = mbind(mmap_addr+pagesize*index, pagesize*len,
MPOL_INTERLEAVE, nmask->maskp, nmask->size, 0);
if (err)
perror("mbind "), exit(err);
}void mem_unbind(int index, int len)
{
int err;err = mbind(mmap_addr+pagesize*index, pagesize*len,
MPOL_DEFAULT, NULL, 0, 0);
if (err)
perror("mbind "), exit(err);
}void Assert(char *expected, char *value, char *name, int line)
{
if (strcmp(expected, value) == 0) {
fprintf(stderr, "%s: passed\n", name);
return;
}
else {
fprintf(stderr, "%s: %d: test failed. expect '%s', actual '%s'\n",
name, line,
expected, value);
// exit(1);
}
}/*
AAAA
PPPPPPNNNNNN
might become
PPNNNNNNNNNN
case 4 below
*/
void case4(void)
{
init();
sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);mem_bind(0, 4);
mem_unbind(2, 2);file = popen(buf, "r");
fread(retbuf, sizeof(retbuf), 1, file);
Assert("2,4", retbuf, "case4", __LINE__);fin();
}/*
AAAA
PPPPPPNNNNNN
might become
PPPPPPPPPPNN
case 5 below
*/
void case5(void)
{
init();
sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);mem_bind(0, 2);
mem_bind(2, 2);file = popen(buf, "r");
fread(retbuf, sizeof(retbuf), 1, file);
Assert("4,2", retbuf, "case5", __LINE__);fin();
}/*
AAAA
PPPPNNNNXXXX
might become
PPPPPPPPPPPP 6
*/
void case6(void)
{
init();
sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);mem_bind(0, 2);
mem_bind(4, 2);
mem_bind(2, 2);file = popen(buf, "r");
fread(retbuf, sizeof(retbuf), 1, file);
Assert("6", retbuf, "case6", __LINE__);fin();
}/*
AAAA
PPPPNNNNXXXX
might become
PPPPPPPPXXXX 7
*/
void case7(void)
{
init();
sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);mem_bind(0, 2);
mem_interleave(4, 2);
mem_bind(2, 2);file = popen(buf, "r");
fread(retbuf, sizeof(retbuf), 1, file);
Assert("4,2", retbuf, "case7", __LINE__);fin();
}/*
AAAA
PPPPNNNNXXXX
might become
PPPPNNNNNNNN 8
*/
void case8(void)
{
init();
sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);mem_bind(0, 2);
mem_interleave(4, 2);
mem_interleave(2, 2);file = popen(buf, "r");
fread(retbuf, sizeof(retbuf), 1, file);
Assert("2,4", retbuf, "case8", __LINE__);fin();
}void case_n(void)
{
init();
sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);/* make redundunt mappings [0][1234][34][7] */
mmap(mmap_addr + pagesize*4, pagesize*2, PROT_READ|PROT_WRITE,
MAP_FIXED|MAP_SHARED, mapped_fd, pagesize*3);/* Expect to do nothing. */
mem_unbind(2, 2);file = popen(buf, "r");
fread(retbuf, sizeof(retbuf), 1, file);
Assert("4,2", retbuf, "case_n", __LINE__);fin();
}int main(int argc, char** argv)
{
case4();
case5();
case6();
case7();
case8();
case_n();return 0;
}
=============================================================Signed-off-by: KOSAKI Motohiro
Acked-by: Johannes Weiner
Cc: Minchan Kim
Cc: Caspar Zhang
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: Hugh Dickins
Cc: Mel Gorman
Cc: Lee Schermerhorn
Cc: [3.1.x]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
07 Nov, 2011
1 commit
-
* 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux: (230 commits)
Revert "tracing: Include module.h in define_trace.h"
irq: don't put module.h into irq.h for tracking irqgen modules.
bluetooth: macroize two small inlines to avoid module.h
ip_vs.h: fix implicit use of module_get/module_put from module.h
nf_conntrack.h: fix up fallout from implicit moduleparam.h presence
include: replace linux/module.h with "struct module" wherever possible
include: convert various register fcns to macros to avoid include chaining
crypto.h: remove unused crypto_tfm_alg_modname() inline
uwb.h: fix implicit use of asm/page.h for PAGE_SIZE
pm_runtime.h: explicitly requires notifier.h
linux/dmaengine.h: fix implicit use of bitmap.h and asm/page.h
miscdevice.h: fix up implicit use of lists and types
stop_machine.h: fix implicit use of smp.h for smp_processor_id
of: fix implicit use of errno.h in include/linux/of.h
of_platform.h: delete needless include
acpi: remove module.h include from platform/aclinux.h
miscdevice.h: delete unnecessary inclusion of module.h
device_cgroup.h: delete needless include
net: sch_generic remove redundant use of
net: inet_timewait_sock doesnt need
...Fix up trivial conflicts (other header files, and removal of the ab3550 mfd driver) in
- drivers/media/dvb/frontends/dibx000_common.c
- drivers/media/video/{mt9m111.c,ov6650.c}
- drivers/mfd/ab3550-core.c
- include/linux/dmaengine.h
01 Nov, 2011
1 commit
-
Quiet the spares noise:
warning: symbol 'default_policy' was not declared. Should it be static?
Signed-off-by: H Hartley Sweeten
Cc: KOSAKI Motohiro
Cc: Stephen Wilson
Cc: Andrea Arcangeli
Cc: Mel Gorman
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
31 Oct, 2011
1 commit
-
The files changed within are only using the EXPORT_SYMBOL
macro variants. They are not using core modular infrastructure
and hence don't need module.h but only the export.h header.Signed-off-by: Paul Gortmaker
15 Sep, 2011
2 commits
-
When compiling mm/mempolicy.c with struct user copy checks the following
warning is shown:In file included from arch/x86/include/asm/uaccess.h:572,
from include/linux/uaccess.h:5,
from include/linux/highmem.h:7,
from include/linux/pagemap.h:10,
from include/linux/mempolicy.h:70,
from mm/mempolicy.c:68:
In function `copy_from_user',
inlined from `compat_sys_get_mempolicy' at mm/mempolicy.c:1415:
arch/x86/include/asm/uaccess_64.h:64: warning: call to `copy_from_user_overflow' declared with attribute warning: copy_from_user() buffer size is not provably correct
LD mm/built-in.oFix this by passing correct buffer size value.
Signed-off-by: KAMEZAWA Hiroyuki
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
commit 9d8cebd4bcd7 ("mm: fix mbind vma merge problem") didn't really
fix the mbind vma merge problem due to wrong pgoff value passing to
vma_merge(), which made vma_merge() always return NULL.Before the patch applied, we are getting a result like:
addr = 0x7fa58f00c000
[snip]
7fa58f00c000-7fa58f00d000 rw-p 00000000 00:00 0
7fa58f00d000-7fa58f00e000 rw-p 00000000 00:00 0
7fa58f00e000-7fa58f00f000 rw-p 00000000 00:00 0here 7fa58f00c000->7fa58f00f000 we get 3 VMAs which are expected to be
merged described as described in commit 9d8cebd.Re-testing the patched kernel with the reproducer provided in commit
9d8cebd, we get the correct result:addr = 0x7ffa5aaa2000
[snip]
7ffa5aaa2000-7ffa5aaa6000 rw-p 00000000 00:00 0
7fffd556f000-7fffd5584000 rw-p 00000000 00:00 0 [stack]Signed-off-by: Caspar Zhang
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: Hugh Dickins
Cc: Mel Gorman
Cc: Lee Schermerhorn
Cc: Minchan Kim
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
27 Jul, 2011
1 commit
-
[ This patch has already been accepted as commit 0ac0c0d0f837 but later
reverted (commit 35926ff5fba8) because it itroduced arch specific
__node_random which was defined only for x86 code so it broke other
archs. This is a followup without any arch specific code. Other than
that there are no functional changes.]Some workloads that create a large number of small files tend to assign
too many pages to node 0 (multi-node systems). Part of the reason is
that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts
at node 0 for newly created tasks.This patch changes the rotor to be initialized to a random node number
of the cpuset.[akpm@linux-foundation.org: fix layout]
[Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration]
[mhocko@suse.cz: Make it arch independent]
[akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build]
Signed-off-by: Jack Steiner
Signed-off-by: Lee Schermerhorn
Signed-off-by: Michal Hocko
Reviewed-by: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: Pekka Enberg
Cc: Paul Menage
Cc: Jack Steiner
Cc: Robin Holt
Cc: David Rientjes
Cc: Christoph Lameter
Cc: David Rientjes
Cc: Jack Steiner
Cc: KOSAKI Motohiro
Cc: Lee Schermerhorn
Cc: Michal Hocko
Cc: Paul Menage
Cc: Pekka Enberg
Cc: Robin Holt
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
25 May, 2011
6 commits
-
Moving show_numa_map() from mempolicy.c to task_mmu.c solves several
issues.- Having the show() operation "miles away" from the corresponding
seq_file iteration operations is a maintenance burden.- The need to export ad hoc info like struct proc_maps_private is
eliminated.- The implementation of show_numa_map() can be improved in a simple
manner by cooperating with the other seq_file operations (start,
stop, etc) -- something that would be messy to do without this
change.Signed-off-by: Stephen Wilson
Reviewed-by: KOSAKI Motohiro
Cc: Hugh Dickins
Cc: David Rientjes
Cc: Lee Schermerhorn
Cc: Alexey Dobriyan
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This function has been superseded by gather_hugetbl_stats() and is no
longer needed.Signed-off-by: Stephen Wilson
Reviewed-by: KOSAKI Motohiro
Cc: Hugh Dickins
Cc: David Rientjes
Cc: Lee Schermerhorn
Cc: Alexey Dobriyan
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Improve the prototype of gather_stats() to take a struct numa_maps as
argument instead of a generic void *. Update all callers to make the
required type explicit.Since gather_stats() is not needed before its definition and is scheduled
to be moved out of mempolicy.c the declaration is removed as well.Signed-off-by: Stephen Wilson
Reviewed-by: KOSAKI Motohiro
Cc: Hugh Dickins
Cc: David Rientjes
Cc: Lee Schermerhorn
Cc: Alexey Dobriyan
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Mapping statistics in a NUMA environment is now computed using the generic
walk_page_range() logic. Remove the old/equivalent functionality.Signed-off-by: Stephen Wilson
Reviewed-by: KOSAKI Motohiro
Cc: Hugh Dickins
Cc: David Rientjes
Cc: Lee Schermerhorn
Cc: Alexey Dobriyan
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Converting show_numa_map() to use the generic routine decouples the
function from mempolicy.c, allowing it to be moved out of the mm subsystem
and into fs/proc.Also, include KSM pages in /proc/pid/numa_maps statistics. The pagewalk
logic implemented by check_pte_range() failed to account for such pages as
they were not applicable to the page migration case.Signed-off-by: Stephen Wilson
Reviewed-by: KOSAKI Motohiro
Cc: Hugh Dickins
Cc: David Rientjes
Cc: Lee Schermerhorn
Cc: Alexey Dobriyan
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
In commit 48fce3429d ("mempolicies: unexport get_vma_policy()")
get_vma_policy() was marked static as all clients were local to
mempolicy.c.However, the decision to generate /proc/pid/numa_maps in the numa memory
policy code and outside the procfs subsystem introduces an artificial
interdependency between the two systems. Exporting get_vma_policy() once
again is the first step to clean up this interdependency.Signed-off-by: Stephen Wilson
Reviewed-by: KOSAKI Motohiro
Cc: Hugh Dickins
Cc: David Rientjes
Cc: Lee Schermerhorn
Cc: Alexey Dobriyan
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
23 Mar, 2011
1 commit
-
The 'flags' field is already checked, no need to do it again.
Signed-off-by: Namhyung Kim
Cc: Bob Liu
Cc: Lee Schermerhorn
Reviewed-by: Minchan Kim
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
19 Mar, 2011
1 commit
-
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (47 commits)
doc: CONFIG_UNEVICTABLE_LRU doesn't exist anymore
Update cpuset info & webiste for cgroups
dcdbas: force SMI to happen when expected
arch/arm/Kconfig: remove one to many l's in the word.
asm-generic/user.h: Fix spelling in comment
drm: fix printk typo 'sracth'
Remove one to many n's in a word
Documentation/filesystems/romfs.txt: fixing link to genromfs
drivers:scsi Change printk typo initate -> initiate
serial, pch uart: Remove duplicate inclusion of linux/pci.h header
fs/eventpoll.c: fix spelling
mm: Fix out-of-date comments which refers non-existent functions
drm: Fix printk typo 'failled'
coh901318.c: Change initate to initiate.
mbox-db5500.c Change initate to initiate.
edac: correct i82975x error-info reported
edac: correct i82975x mci initialisation
edac: correct commented info
fs: update comments to point correct document
target: remove duplicate include of target/target_core_device.h from drivers/target/target_core_hba.c
...Trivial conflict in fs/eventpoll.c (spelling vs addition)
05 Mar, 2011
2 commits
-
Pass down the correct node for a transparent hugepage allocation. Most
callers continue to use the current node, however the hugepaged daemon
now uses the previous node of the first to be collapsed page instead.
This ensures that khugepaged does not mess up local memory for an
existing process which uses local policy.The choice of node is somewhat primitive currently: it just uses the
node of the first page in the pmd range. An alternative would be to
look at multiple pages and use the most popular node. I used the
simplest variant for now which should work well enough for the case of
all pages being on the same node.[akpm@linux-foundation.org: coding-style fixes]
Acked-by: Andrea Arcangeli
Signed-off-by: Andi Kleen
Reviewed-by: KAMEZAWA Hiroyuki
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Currently alloc_pages_vma() always uses the local node as policy node for
the LOCAL policy. Pass this node down as an argument instead.No behaviour change from this patch, but will be needed for followons.
Acked-by: Andrea Arcangeli
Signed-off-by: Andi Kleen
Reviewed-by: KAMEZAWA Hiroyuki
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
01 Mar, 2011
1 commit
-
Signed-off-by: Justin P. Mattock
Signed-off-by: Jiri Kosina
26 Feb, 2011
1 commit
-
The THP code didn't pass the correct interleaving shift to the memory
policy code. Fix this here by adjusting for the order.Signed-off-by: Andi Kleen
Reviewed-by: Christoph Lameter
Acked-by: Andrea Arcangeli
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
14 Jan, 2011
5 commits
-
It's mostly a matter of replacing alloc_pages with alloc_pages_vma after
introducing alloc_pages_vma. khugepaged needs special handling as the
allocation has to happen inside collapse_huge_page where the vma is known
and an error has to be returned to the outer loop to sleep
alloc_sleep_millisecs in case of failure. But it retains the more
efficient logic of handling allocation failures in khugepaged in case of
CONFIG_NUMA=n.Signed-off-by: Andrea Arcangeli
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
split_huge_page_pmd compat code. Each one of those would need to be
expanded to hundred of lines of complex code without a fully reliable
split_huge_page_pmd design.Signed-off-by: Andrea Arcangeli
Acked-by: Rik van Riel
Acked-by: Mel Gorman
Signed-off-by: Johannes Weiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Today, tasklist_lock in migrate_pages doesn't protect anything.
rcu_read_lock() provide enough protection from pid hash walk.Signed-off-by: KOSAKI Motohiro
Reported-by: Peter Zijlstra
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
With the introduction of the boolean sync parameter, the API looks a
little inconsistent as offlining is still an int. Convert offlining to a
bool for the sake of being tidy.Signed-off-by: Mel Gorman
Cc: Andrea Arcangeli
Cc: KOSAKI Motohiro
Cc: Rik van Riel
Acked-by: Johannes Weiner
Cc: Andy Whitcroft
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
…ompaction in the faster path
Migration synchronously waits for writeback if the initial passes fails.
Callers of memory compaction do not necessarily want this behaviour if the
caller is latency sensitive or expects that synchronous migration is not
going to have a significantly better success rate.This patch adds a sync parameter to migrate_pages() allowing the caller to
indicate if wait_on_page_writeback() is allowed within migration or not.
For reclaim/compaction, try_to_compact_pages() is first called
asynchronously, direct reclaim runs and then try_to_compact_pages() is
called synchronously as there is a greater expectation that it'll succeed.[akpm@linux-foundation.org: build/merge fix]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
03 Dec, 2010
1 commit
-
find_task_by_vpid() should be protected by rcu_read_lock(), to prevent
free_pid() reclaiming pid.Signed-off-by: Zeng Zhaoming
Cc: "Paul E. McKenney"
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
29 Oct, 2010
1 commit
-
When a node contains only HighMem memory, slab_node(MPOL_BIND)
dereferences a NULL pointer.[ This code seems to go back all the way to commit 19770b32609b: "mm:
filter based on a nodemask as well as a gfp_mask". Which was back in
April 2008, and it got merged into 2.6.26. - Linus ]Signed-off-by: Eric Dumazet
Cc: Mel Gorman
Cc: Christoph Lameter
Cc: Lee Schermerhorn
Cc: Andrew Morton
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds
27 Oct, 2010
2 commits
-
Function check_range may return ERR_PTR(...). Check for it.
Signed-off-by: Vasiliy Kulikov
Acked-by: David Rientjes
Reviewed-by: Christoph Lameter
Reviewed-by: KOSAKI Motohiro
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Presently update_nr_listpages() doesn't have a role. That's because lists
passed is always empty just after calling migrate_pages. The
migrate_pages cleans up page list which have failed to migrate before
returning by aaa994b3.[PATCH] page migration: handle freeing of pages in migrate_pages()
Do not leave pages on the lists passed to migrate_pages(). Seems that we will
not need any postprocessing of pages. This will simplify the handling of
pages by the callers of migrate_pages().At that time, we thought we don't need any postprocessing of pages. But
the situation is changed. The compaction need to know the number of
failed to migrate for COMPACTPAGEFAILED statThis patch makes new rule for caller of migrate_pages to call
putback_lru_pages. So caller need to clean up the lists so it has a
chance to postprocess the pages. [suggested by Christoph Lameter]Signed-off-by: Minchan Kim
Cc: Hugh Dickins
Cc: Andi Kleen
Reviewed-by: Mel Gorman
Reviewed-by: Wu Fengguang
Acked-by: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
10 Aug, 2010
2 commits
-
migrate_pages() is using >500 bytes stack. Reduce it.
mm/mempolicy.c: In function 'sys_migrate_pages':
mm/mempolicy.c:1344: warning: the frame size of 528 bytes is larger than 512 bytes[akpm@linux-foundation.org: don't play with a might-be-NULL pointer]
Signed-off-by: KOSAKI Motohiro
Reviewed-by: KAMEZAWA Hiroyuki
Reviewed-by: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The oom killer presently kills current whenever there is no more memory
free or reclaimable on its mempolicy's nodes. There is no guarantee that
current is a memory-hogging task or that killing it will free any
substantial amount of memory, however.In such situations, it is better to scan the tasklist for nodes that are
allowed to allocate on current's set of nodes and kill the task with the
highest badness() score. This ensures that the most memory-hogging task,
or the one configured by the user with /proc/pid/oom_adj, is always
selected in such scenarios.Signed-off-by: David Rientjes
Reviewed-by: KOSAKI Motohiro
Cc: KAMEZAWA Hiroyuki
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
30 Jun, 2010
1 commit
-
My patch to "Factor out duplicate put/frees in mpol_shared_policy_init()
to a common return path"; and Dan Carpenter's fix thereto both left a
dangling reference to the incoming tmpfs superblock mempolicy structure.
A similar leak was introduced earlier when the nodemask was moved offstack
to the scratch area despite the note in the comment block regarding the
incoming ref.Move the remaining 'put of the incoming "mpol" to the common exit path to
drop the reference.Signed-off-by: Lee Schermerhorn
Acked-by: Dan Carpenter
Cc: KOSAKI Motohiro
Cc: David Rientjes
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
26 May, 2010
1 commit
-
The original code called mpol_put(new) while "new" was an ERR_PTR.
Signed-off-by: Dan Carpenter
Cc: Lee Schermerhorn
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Acked-by: David Rientjes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
25 May, 2010
6 commits
-
Use mm->task_size instead of TASK_SIZE to ensure that the entire user
address space is migrated. mm->task_size is independent of the calling
task context. TASK SIZE may be dependant on the address space size of the
calling process. Usage of TASK_SIZE can lead to partial address space
migration if the calling process was 32 bit and the migrating process was
64 bit.Here is the test script used on 64 system with a 32 bit echo process:
mount -t cgroup none /cgroup -o cpuset
cd /cgroupmkdir 0
echo 1 > 0/cpuset.cpus
echo 0 > 0/cpuset.mems
echo 1 > 0/cpuset.memory_migratemkdir 1
echo 1 > 1/cpuset.cpus
echo 1 > 1/cpuset.mems
echo 1 > 1/cpuset.memory_migrateecho $$ > 0/tasks
64_bit_process &
pid=$!echo $pid > 1/tasks # This does not migrate all process pages without
# this patch. If 64 bit echo is used or this patch is
# applied, then the full address space of $pid is
# migrated.To check memory migration, I watched:
grep MemUsed /sys/devices/system/node/node*/meminfoSigned-off-by: Greg Thelen
Acked-by: Christoph Lameter
Reviewed-by: KOSAKI Motohiro
Cc: Mel Gorman
Cc: KAMEZAWA Hiroyuki
Cc: Daisuke Nishimura
Cc: Balbir Singh
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Before applying this patch, cpuset updates task->mems_allowed and
mempolicy by setting all new bits in the nodemask first, and clearing all
old unallowed bits later. But in the way, the allocator may find that
there is no node to alloc memory.The reason is that cpuset rebinds the task's mempolicy, it cleans the
nodes which the allocater can alloc pages on, for example:(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oomThis patch fixes this problem by expanding the nodes range first(set newly
allowed bits) and shrink it lazily(clear newly disallowed bits). So we
use a variable to tell the write-side task that read-side task is reading
nodemask, and the write-side task clears newly disallowed nodes after
read-side task ends the current memory allocation.[akpm@linux-foundation.org: fix spello]
Signed-off-by: Miao Xie
Cc: David Rientjes
Cc: Nick Piggin
Cc: Paul Menage
Cc: Lee Schermerhorn
Cc: Hugh Dickins
Cc: Ravikiran Thirumalai
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Nick Piggin reported that the allocator may see an empty nodemask when
changing cpuset's mems[1]. It happens only on the kernel that do not do
atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG)But I found that there is also a problem on the kernel that can do atomic
nodemask_t stores. The problem is that the allocator can't find a node to
alloc page when changing cpuset's mems though there is a lot of free
memory. The reason is like this:(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oomI can use the attached program reproduce it by the following step:
# mkdir /dev/cpuset
# mount -t cpuset cpuset /dev/cpuset
# mkdir /dev/cpuset/1
# echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus
# echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems
# echo $$ > /dev/cpuset/1/tasks
# numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog &
= max(nr_cpus - 1, 1)
# killall -s SIGUSR1 cpuset_mem_hog
# ./change_mems.shseveral hours later, oom will happen though there is a lot of free memory.
This patchset fixes this problem by expanding the nodes range first(set
newly allowed bits) and shrink it lazily(clear newly disallowed bits). So
we use a variable to tell the write-side task that read-side task is
reading nodemask, and the write-side task clears newly disallowed nodes
after read-side task ends the current memory allocation.This patch:
In order to fix no node to alloc memory, when we want to update mempolicy
and mems_allowed, we expand the set of nodes first (set all the newly
nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the
mempolicy's rebind functions may breaks the expanding.So we restructure the mempolicy's rebind functions and split the rebind
work to two steps, just like the update of cpuset's mems: The 1st step:
expand the set of the mempolicy's nodes. The 2nd step: shrink the set of
the mempolicy's nodes. It is used when there is no real lock to protect
the mempolicy in the read-side. Otherwise we can do rebind work at once.In order to implement it, we define
enum mpol_rebind_step {
MPOL_REBIND_ONCE,
MPOL_REBIND_STEP1,
MPOL_REBIND_STEP2,
MPOL_REBIND_NSTEP,
};If the mempolicy needn't be updated by two steps, we can pass
MPOL_REBIND_ONCE to the rebind functions. Or we can pass
MPOL_REBIND_STEP1 to do the first step of the rebind work and pass
MPOL_REBIND_STEP2 to do the second step work.Besides that, it maybe long time between these two step and we have to
release the lock that protects mempolicy and mems_allowed. If we hold the
lock once again, we must check whether the current mempolicy is under the
rebinding (the first step has been done) or not, because the task may
alloc a new mempolicy when we don't hold the lock. So we defined the
following flag to identify it:#define MPOL_F_REBINDING (1 << 2)
The new functions will be used in the next patch.
Signed-off-by: Miao Xie
Cc: David Rientjes
Cc: Nick Piggin
Cc: Paul Menage
Cc: Lee Schermerhorn
Cc: Hugh Dickins
Cc: Ravikiran Thirumalai
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Factor out duplicate put/frees in mpol_shared_policy_init() to a common
return path.Signed-off-by: Lee Schermerhorn
Cc: Hugh Dickins
Cc: Ravikiran Thirumalai
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: David Rientjes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Rename 'policy_types[]' to 'policy_modes[]' to better match the array
contents.Use designated intializer syntax for policy_modes[].
Signed-off-by: Lee Schermerhorn
Cc: Hugh Dickins
Cc: Ravikiran Thirumalai
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: David Rientjes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
We don't really need the extra variable 'i' in mpol_parse_str(). The only
use is as the the loop variable. Then, it's assigned to 'mode'. Just use
mode, and loose the 'uninitialized_var()' macro.Signed-off-by: Lee Schermerhorn
Cc: Hugh Dickins
Cc: Ravikiran Thirumalai
Cc: KOSAKI Motohiro
Cc: Christoph Lameter
Cc: David Rientjes
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
