2005-04-17 02:20:36 +04:00
|
|
|
/* internal.h: mm/ internal definitions
|
|
|
|
*
|
|
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*/
|
2006-03-22 11:08:33 +03:00
|
|
|
#ifndef __MM_INTERNAL_H
|
|
|
|
#define __MM_INTERNAL_H
|
|
|
|
|
|
|
|
#include <linux/mm.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2008-07-24 08:27:10 +04:00
|
|
|
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
|
|
|
|
unsigned long floor, unsigned long ceiling);
|
|
|
|
|
2006-03-22 11:08:40 +03:00
|
|
|
static inline void set_page_count(struct page *page, int v)
|
2006-01-06 11:10:57 +03:00
|
|
|
{
|
2006-03-22 11:08:40 +03:00
|
|
|
atomic_set(&page->_count, v);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Turn a non-refcounted page (->_count == 0) into refcounted with
|
|
|
|
* a count of one.
|
|
|
|
*/
|
|
|
|
static inline void set_page_refcounted(struct page *page)
|
|
|
|
{
|
2008-02-05 09:29:27 +03:00
|
|
|
VM_BUG_ON(PageTail(page));
|
2006-09-26 10:30:55 +04:00
|
|
|
VM_BUG_ON(atomic_read(&page->_count));
|
2006-01-06 11:10:57 +03:00
|
|
|
set_page_count(page, 1);
|
|
|
|
}
|
|
|
|
|
2006-03-22 11:08:33 +03:00
|
|
|
static inline void __put_page(struct page *page)
|
|
|
|
{
|
|
|
|
atomic_dec(&page->_count);
|
|
|
|
}
|
|
|
|
|
2011-11-03 00:36:59 +04:00
|
|
|
static inline void __get_page_tail_foll(struct page *page,
|
|
|
|
bool get_page_head)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* If we're getting a tail page, the elevated page->_count is
|
|
|
|
* required only in the head page and we will elevate the head
|
|
|
|
* page->_count and tail page->_mapcount.
|
|
|
|
*
|
|
|
|
* We elevate page_tail->_mapcount for tail pages to force
|
|
|
|
* page_tail->_count to be zero at all times to avoid getting
|
|
|
|
* false positives from get_page_unless_zero() with
|
|
|
|
* speculative page access (like in
|
|
|
|
* page_cache_get_speculative()) on tail pages.
|
|
|
|
*/
|
|
|
|
VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
|
|
|
|
VM_BUG_ON(atomic_read(&page->_count) != 0);
|
|
|
|
VM_BUG_ON(page_mapcount(page) < 0);
|
|
|
|
if (get_page_head)
|
|
|
|
atomic_inc(&page->first_page->_count);
|
|
|
|
atomic_inc(&page->_mapcount);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is meant to be called as the FOLL_GET operation of
|
|
|
|
* follow_page() and it must be called while holding the proper PT
|
|
|
|
* lock while the pte (or pmd_trans_huge) is still mapping the page.
|
|
|
|
*/
|
|
|
|
static inline void get_page_foll(struct page *page)
|
|
|
|
{
|
|
|
|
if (unlikely(PageTail(page)))
|
|
|
|
/*
|
|
|
|
* This is safe only because
|
|
|
|
* __split_huge_page_refcount() can't run under
|
|
|
|
* get_page_foll() because we hold the proper PT lock.
|
|
|
|
*/
|
|
|
|
__get_page_tail_foll(page, true);
|
|
|
|
else {
|
|
|
|
/*
|
|
|
|
* Getting a normal page or the head of a compound page
|
|
|
|
* requires to already have an elevated page->_count.
|
|
|
|
*/
|
|
|
|
VM_BUG_ON(atomic_read(&page->_count) <= 0);
|
|
|
|
atomic_inc(&page->_count);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2009-09-22 04:03:35 +04:00
|
|
|
extern unsigned long highest_memmap_pfn;
|
|
|
|
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:39 +04:00
|
|
|
/*
|
|
|
|
* in mm/vmscan.c:
|
|
|
|
*/
|
vmscan: move isolate_lru_page() to vmscan.c
On large memory systems, the VM can spend way too much time scanning
through pages that it cannot (or should not) evict from memory. Not only
does it use up CPU time, but it also provokes lock contention and can
leave large systems under memory presure in a catatonic state.
This patch series improves VM scalability by:
1) putting filesystem backed, swap backed and unevictable pages
onto their own LRUs, so the system only scans the pages that it
can/should evict from memory
2) switching to two handed clock replacement for the anonymous LRUs,
so the number of pages that need to be scanned when the system
starts swapping is bound to a reasonable number
3) keeping unevictable pages off the LRU completely, so the
VM does not waste CPU time scanning them. ramfs, ramdisk,
SHM_LOCKED shared memory segments and mlock()ed VMA pages
are keept on the unevictable list.
This patch:
isolate_lru_page logically belongs to be in vmscan.c than migrate.c.
It is tough, because we don't need that function without memory migration
so there is a valid argument to have it in migrate.c. However a
subsequent patch needs to make use of it in the core mm, so we can happily
move it to vmscan.c.
Also, make the function a little more generic by not requiring that it
adds an isolated page to a given list. Callers can do that.
Note that we now have '__isolate_lru_page()', that does
something quite different, visible outside of vmscan.c
for use with memory controller. Methinks we need to
rationalize these names/purposes. --lts
[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:09 +04:00
|
|
|
extern int isolate_lru_page(struct page *page);
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:39 +04:00
|
|
|
extern void putback_lru_page(struct page *page);
|
vmscan: move isolate_lru_page() to vmscan.c
On large memory systems, the VM can spend way too much time scanning
through pages that it cannot (or should not) evict from memory. Not only
does it use up CPU time, but it also provokes lock contention and can
leave large systems under memory presure in a catatonic state.
This patch series improves VM scalability by:
1) putting filesystem backed, swap backed and unevictable pages
onto their own LRUs, so the system only scans the pages that it
can/should evict from memory
2) switching to two handed clock replacement for the anonymous LRUs,
so the number of pages that need to be scanned when the system
starts swapping is bound to a reasonable number
3) keeping unevictable pages off the LRU completely, so the
VM does not waste CPU time scanning them. ramfs, ramdisk,
SHM_LOCKED shared memory segments and mlock()ed VMA pages
are keept on the unevictable list.
This patch:
isolate_lru_page logically belongs to be in vmscan.c than migrate.c.
It is tough, because we don't need that function without memory migration
so there is a valid argument to have it in migrate.c. However a
subsequent patch needs to make use of it in the core mm, so we can happily
move it to vmscan.c.
Also, make the function a little more generic by not requiring that it
adds an isolated page to a given list. Callers can do that.
Note that we now have '__isolate_lru_page()', that does
something quite different, visible outside of vmscan.c
for use with memory controller. Methinks we need to
rationalize these names/purposes. --lts
[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:09 +04:00
|
|
|
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:39 +04:00
|
|
|
/*
|
|
|
|
* in mm/page_alloc.c
|
|
|
|
*/
|
2008-04-28 13:13:34 +04:00
|
|
|
extern void __free_pages_bootmem(struct page *page, unsigned int order);
|
mm: introduce PageHuge() for testing huge/gigantic pages
A series of patches to enhance the /proc/pagemap interface and to add a
userspace executable which can be used to present the pagemap data.
Export 10 more flags to end users (and more for kernel developers):
11. KPF_MMAP (pseudo flag) memory mapped page
12. KPF_ANON (pseudo flag) memory mapped page (anonymous)
13. KPF_SWAPCACHE page is in swap cache
14. KPF_SWAPBACKED page is swap/RAM backed
15. KPF_COMPOUND_HEAD (*)
16. KPF_COMPOUND_TAIL (*)
17. KPF_HUGE hugeTLB pages
18. KPF_UNEVICTABLE page is in the unevictable LRU list
19. KPF_HWPOISON hardware detected corruption
20. KPF_NOPAGE (pseudo flag) no page frame at the address
(*) For compound pages, exporting _both_ head/tail info enables
users to tell where a compound page starts/ends, and its order.
a simple demo of the page-types tool
# ./page-types -h
page-types [options]
-r|--raw Raw mode, for kernel developers
-a|--addr addr-spec Walk a range of pages
-b|--bits bits-spec Walk pages with specified bits
-l|--list Show page details in ranges
-L|--list-each Show page details one by one
-N|--no-summary Don't show summay info
-h|--help Show this usage message
addr-spec:
N one page at offset N (unit: pages)
N+M pages range from N to N+M-1
N,M pages range from N to M-1
N, pages range from N to end
,M pages range from 0 to M
bits-spec:
bit1,bit2 (flags & (bit1|bit2)) != 0
bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1
bit1,~bit2 (flags & (bit1|bit2)) == bit1
=bit1,bit2 flags == (bit1|bit2)
bit-names:
locked error referenced uptodate
dirty lru active slab
writeback reclaim buddy mmap
anonymous swapcache swapbacked compound_head
compound_tail huge unevictable hwpoison
nopage reserved(r) mlocked(r) mappedtodisk(r)
private(r) private_2(r) owner_private(r) arch(r)
uncached(r) readahead(o) slob_free(o) slub_frozen(o)
slub_debug(o)
(r) raw mode bits (o) overloaded bits
# ./page-types
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 487369 1903 _________________________________
0x0000000000000014 5 0 __R_D____________________________ referenced,dirty
0x0000000000000020 1 0 _____l___________________________ lru
0x0000000000000024 34 0 __R__l___________________________ referenced,lru
0x0000000000000028 3838 14 ___U_l___________________________ uptodate,lru
0x0001000000000028 48 0 ___U_l_______________________I___ uptodate,lru,readahead
0x000000000000002c 6478 25 __RU_l___________________________ referenced,uptodate,lru
0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead
0x0000000000000040 8344 32 ______A__________________________ active
0x0000000000000060 1 0 _____lA__________________________ lru,active
0x0000000000000068 348 1 ___U_lA__________________________ uptodate,lru,active
0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead
0x000000000000006c 988 3 __RU_lA__________________________ referenced,uptodate,lru,active
0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead
0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked
0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400 503 1 __________B______________________ buddy
0x0000000000000804 1 0 __R________M_____________________ referenced,mmap
0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap
0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead
0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap
0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead
0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap
0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead
0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap
0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000 492 1 ____________a____________________ anonymous
0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 30 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 513968 2007
# ./page-types -r
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 468002 1828 _________________________________
0x0000000100000000 19102 74 _____________________r___________ reserved
0x0000000000008000 41 0 _______________H_________________ compound_head
0x0000000000010000 188 0 ________________T________________ compound_tail
0x0000000000008014 1 0 __R_D__________H_________________ referenced,dirty,compound_head
0x0000000000010014 4 0 __R_D___________T________________ referenced,dirty,compound_tail
0x0000000000000020 1 0 _____l___________________________ lru
0x0000000800000024 34 0 __R__l__________________P________ referenced,lru,private
0x0000000000000028 3794 14 ___U_l___________________________ uptodate,lru
0x0001000000000028 46 0 ___U_l_______________________I___ uptodate,lru,readahead
0x0000000400000028 44 0 ___U_l_________________d_________ uptodate,lru,mappedtodisk
0x0001000400000028 2 0 ___U_l_________________d_____I___ uptodate,lru,mappedtodisk,readahead
0x000000000000002c 6434 25 __RU_l___________________________ referenced,uptodate,lru
0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead
0x000000040000002c 14 0 __RU_l_________________d_________ referenced,uptodate,lru,mappedtodisk
0x000000080000002c 30 0 __RU_l__________________P________ referenced,uptodate,lru,private
0x0000000800000040 8124 31 ______A_________________P________ active,private
0x0000000000000040 219 0 ______A__________________________ active
0x0000000800000060 1 0 _____lA_________________P________ lru,active,private
0x0000000000000068 322 1 ___U_lA__________________________ uptodate,lru,active
0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead
0x0000000400000068 13 0 ___U_lA________________d_________ uptodate,lru,active,mappedtodisk
0x0000000800000068 12 0 ___U_lA_________________P________ uptodate,lru,active,private
0x000000000000006c 977 3 __RU_lA__________________________ referenced,uptodate,lru,active
0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead
0x000000040000006c 5 0 __RU_lA________________d_________ referenced,uptodate,lru,active,mappedtodisk
0x000000080000006c 3 0 __RU_lA_________________P________ referenced,uptodate,lru,active,private
0x0000000c0000006c 3 0 __RU_lA________________dP________ referenced,uptodate,lru,active,mappedtodisk,private
0x0000000c00000068 1 0 ___U_lA________________dP________ uptodate,lru,active,mappedtodisk,private
0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked
0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400 538 2 __________B______________________ buddy
0x0000000000000804 1 0 __R________M_____________________ referenced,mmap
0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap
0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead
0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap
0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead
0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap
0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead
0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap
0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000 492 1 ____________a____________________ anonymous
0x0000000000005008 2 0 ___U________a_b__________________ uptodate,anonymous,swapbacked
0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked
0x000000000000580c 1 0 __RU_______Ma_b__________________ referenced,uptodate,mmap,anonymous,swapbacked
0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 29 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 513968 2007
# ./page-types --raw --list --no-summary --bits reserved
offset count flags
0 15 _____________________r___________
31 4 _____________________r___________
159 97 _____________________r___________
4096 2067 _____________________r___________
6752 2390 _____________________r___________
9355 3 _____________________r___________
9728 14526 _____________________r___________
This patch:
Introduce PageHuge(), which identifies huge/gigantic pages by their
dedicated compound destructor functions.
Also move prep_compound_gigantic_page() to hugetlb.c and make
__free_pages_ok() non-static.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 02:32:22 +04:00
|
|
|
extern void prep_compound_page(struct page *page, unsigned long order);
|
2009-12-16 14:19:58 +03:00
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
|
|
extern bool is_free_buddy_page(struct page *page);
|
|
|
|
#endif
|
mm: introduce PageHuge() for testing huge/gigantic pages
A series of patches to enhance the /proc/pagemap interface and to add a
userspace executable which can be used to present the pagemap data.
Export 10 more flags to end users (and more for kernel developers):
11. KPF_MMAP (pseudo flag) memory mapped page
12. KPF_ANON (pseudo flag) memory mapped page (anonymous)
13. KPF_SWAPCACHE page is in swap cache
14. KPF_SWAPBACKED page is swap/RAM backed
15. KPF_COMPOUND_HEAD (*)
16. KPF_COMPOUND_TAIL (*)
17. KPF_HUGE hugeTLB pages
18. KPF_UNEVICTABLE page is in the unevictable LRU list
19. KPF_HWPOISON hardware detected corruption
20. KPF_NOPAGE (pseudo flag) no page frame at the address
(*) For compound pages, exporting _both_ head/tail info enables
users to tell where a compound page starts/ends, and its order.
a simple demo of the page-types tool
# ./page-types -h
page-types [options]
-r|--raw Raw mode, for kernel developers
-a|--addr addr-spec Walk a range of pages
-b|--bits bits-spec Walk pages with specified bits
-l|--list Show page details in ranges
-L|--list-each Show page details one by one
-N|--no-summary Don't show summay info
-h|--help Show this usage message
addr-spec:
N one page at offset N (unit: pages)
N+M pages range from N to N+M-1
N,M pages range from N to M-1
N, pages range from N to end
,M pages range from 0 to M
bits-spec:
bit1,bit2 (flags & (bit1|bit2)) != 0
bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1
bit1,~bit2 (flags & (bit1|bit2)) == bit1
=bit1,bit2 flags == (bit1|bit2)
bit-names:
locked error referenced uptodate
dirty lru active slab
writeback reclaim buddy mmap
anonymous swapcache swapbacked compound_head
compound_tail huge unevictable hwpoison
nopage reserved(r) mlocked(r) mappedtodisk(r)
private(r) private_2(r) owner_private(r) arch(r)
uncached(r) readahead(o) slob_free(o) slub_frozen(o)
slub_debug(o)
(r) raw mode bits (o) overloaded bits
# ./page-types
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 487369 1903 _________________________________
0x0000000000000014 5 0 __R_D____________________________ referenced,dirty
0x0000000000000020 1 0 _____l___________________________ lru
0x0000000000000024 34 0 __R__l___________________________ referenced,lru
0x0000000000000028 3838 14 ___U_l___________________________ uptodate,lru
0x0001000000000028 48 0 ___U_l_______________________I___ uptodate,lru,readahead
0x000000000000002c 6478 25 __RU_l___________________________ referenced,uptodate,lru
0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead
0x0000000000000040 8344 32 ______A__________________________ active
0x0000000000000060 1 0 _____lA__________________________ lru,active
0x0000000000000068 348 1 ___U_lA__________________________ uptodate,lru,active
0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead
0x000000000000006c 988 3 __RU_lA__________________________ referenced,uptodate,lru,active
0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead
0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked
0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400 503 1 __________B______________________ buddy
0x0000000000000804 1 0 __R________M_____________________ referenced,mmap
0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap
0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead
0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap
0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead
0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap
0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead
0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap
0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000 492 1 ____________a____________________ anonymous
0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 30 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 513968 2007
# ./page-types -r
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 468002 1828 _________________________________
0x0000000100000000 19102 74 _____________________r___________ reserved
0x0000000000008000 41 0 _______________H_________________ compound_head
0x0000000000010000 188 0 ________________T________________ compound_tail
0x0000000000008014 1 0 __R_D__________H_________________ referenced,dirty,compound_head
0x0000000000010014 4 0 __R_D___________T________________ referenced,dirty,compound_tail
0x0000000000000020 1 0 _____l___________________________ lru
0x0000000800000024 34 0 __R__l__________________P________ referenced,lru,private
0x0000000000000028 3794 14 ___U_l___________________________ uptodate,lru
0x0001000000000028 46 0 ___U_l_______________________I___ uptodate,lru,readahead
0x0000000400000028 44 0 ___U_l_________________d_________ uptodate,lru,mappedtodisk
0x0001000400000028 2 0 ___U_l_________________d_____I___ uptodate,lru,mappedtodisk,readahead
0x000000000000002c 6434 25 __RU_l___________________________ referenced,uptodate,lru
0x000100000000002c 47 0 __RU_l_______________________I___ referenced,uptodate,lru,readahead
0x000000040000002c 14 0 __RU_l_________________d_________ referenced,uptodate,lru,mappedtodisk
0x000000080000002c 30 0 __RU_l__________________P________ referenced,uptodate,lru,private
0x0000000800000040 8124 31 ______A_________________P________ active,private
0x0000000000000040 219 0 ______A__________________________ active
0x0000000800000060 1 0 _____lA_________________P________ lru,active,private
0x0000000000000068 322 1 ___U_lA__________________________ uptodate,lru,active
0x0001000000000068 12 0 ___U_lA______________________I___ uptodate,lru,active,readahead
0x0000000400000068 13 0 ___U_lA________________d_________ uptodate,lru,active,mappedtodisk
0x0000000800000068 12 0 ___U_lA_________________P________ uptodate,lru,active,private
0x000000000000006c 977 3 __RU_lA__________________________ referenced,uptodate,lru,active
0x000100000000006c 48 0 __RU_lA______________________I___ referenced,uptodate,lru,active,readahead
0x000000040000006c 5 0 __RU_lA________________d_________ referenced,uptodate,lru,active,mappedtodisk
0x000000080000006c 3 0 __RU_lA_________________P________ referenced,uptodate,lru,active,private
0x0000000c0000006c 3 0 __RU_lA________________dP________ referenced,uptodate,lru,active,mappedtodisk,private
0x0000000c00000068 1 0 ___U_lA________________dP________ uptodate,lru,active,mappedtodisk,private
0x0000000000004078 1 0 ___UDlA_______b__________________ uptodate,dirty,lru,active,swapbacked
0x000000000000407c 34 0 __RUDlA_______b__________________ referenced,uptodate,dirty,lru,active,swapbacked
0x0000000000000400 538 2 __________B______________________ buddy
0x0000000000000804 1 0 __R________M_____________________ referenced,mmap
0x0000000000000828 1029 4 ___U_l_____M_____________________ uptodate,lru,mmap
0x0001000000000828 43 0 ___U_l_____M_________________I___ uptodate,lru,mmap,readahead
0x000000000000082c 382 1 __RU_l_____M_____________________ referenced,uptodate,lru,mmap
0x000100000000082c 12 0 __RU_l_____M_________________I___ referenced,uptodate,lru,mmap,readahead
0x0000000000000868 192 0 ___U_lA____M_____________________ uptodate,lru,active,mmap
0x0001000000000868 12 0 ___U_lA____M_________________I___ uptodate,lru,active,mmap,readahead
0x000000000000086c 800 3 __RU_lA____M_____________________ referenced,uptodate,lru,active,mmap
0x000100000000086c 31 0 __RU_lA____M_________________I___ referenced,uptodate,lru,active,mmap,readahead
0x0000000000004878 2 0 ___UDlA____M__b__________________ uptodate,dirty,lru,active,mmap,swapbacked
0x0000000000001000 492 1 ____________a____________________ anonymous
0x0000000000005008 2 0 ___U________a_b__________________ uptodate,anonymous,swapbacked
0x0000000000005808 4 0 ___U_______Ma_b__________________ uptodate,mmap,anonymous,swapbacked
0x000000000000580c 1 0 __RU_______Ma_b__________________ referenced,uptodate,mmap,anonymous,swapbacked
0x0000000000005868 2839 11 ___U_lA____Ma_b__________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 29 0 __RU_lA____Ma_b__________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 513968 2007
# ./page-types --raw --list --no-summary --bits reserved
offset count flags
0 15 _____________________r___________
31 4 _____________________r___________
159 97 _____________________r___________
4096 2067 _____________________r___________
6752 2390 _____________________r___________
9355 3 _____________________r___________
9728 14526 _____________________r___________
This patch:
Introduce PageHuge(), which identifies huge/gigantic pages by their
dedicated compound destructor functions.
Also move prep_compound_gigantic_page() to hugetlb.c and make
__free_pages_ok() non-static.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-17 02:32:22 +04:00
|
|
|
|
2011-12-29 16:09:50 +04:00
|
|
|
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
|
|
|
|
|
|
|
|
/*
|
|
|
|
* in mm/compaction.c
|
|
|
|
*/
|
|
|
|
/*
|
|
|
|
* compact_control is used to track pages being migrated and the free pages
|
|
|
|
* they are being migrated to during memory compaction. The free_pfn starts
|
|
|
|
* at the end of a zone and migrate_pfn begins at the start. Movable pages
|
|
|
|
* are moved to the end of a zone during a compaction run and the run
|
|
|
|
* completes when free_pfn <= migrate_pfn
|
|
|
|
*/
|
|
|
|
struct compact_control {
|
|
|
|
struct list_head freepages; /* List of free pages to migrate to */
|
|
|
|
struct list_head migratepages; /* List of pages being migrated */
|
|
|
|
unsigned long nr_freepages; /* Number of isolated free pages */
|
|
|
|
unsigned long nr_migratepages; /* Number of pages to migrate */
|
|
|
|
unsigned long free_pfn; /* isolate_freepages search base */
|
|
|
|
unsigned long migrate_pfn; /* isolate_migratepages search base */
|
2012-06-04 07:05:57 +04:00
|
|
|
bool sync; /* Synchronous migration */
|
2011-12-29 16:09:50 +04:00
|
|
|
|
|
|
|
int order; /* order a direct compactor needs */
|
|
|
|
int migratetype; /* MOVABLE, RECLAIMABLE etc */
|
|
|
|
struct zone *zone;
|
|
|
|
};
|
|
|
|
|
|
|
|
unsigned long
|
|
|
|
isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn);
|
|
|
|
unsigned long
|
|
|
|
isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
|
|
|
|
unsigned long low_pfn, unsigned long end_pfn);
|
|
|
|
|
|
|
|
#endif
|
2006-03-22 11:08:33 +03:00
|
|
|
|
2007-10-16 12:26:10 +04:00
|
|
|
/*
|
|
|
|
* function for dealing with page's order in buddy system.
|
|
|
|
* zone->lock is already acquired when we use these.
|
|
|
|
* So, we don't need atomic page->flags operations here.
|
|
|
|
*/
|
|
|
|
static inline unsigned long page_order(struct page *page)
|
|
|
|
{
|
2010-10-27 01:22:08 +04:00
|
|
|
/* PageBuddy() must be checked by the caller */
|
2007-10-16 12:26:10 +04:00
|
|
|
return page_private(page);
|
|
|
|
}
|
2008-02-24 02:24:06 +03:00
|
|
|
|
mm: nommu: sort mm->mmap list properly
When I was reading nommu code, I found that it handles the vma list/tree
in an unusual way. IIUC, because there can be more than one
identical/overrapped vmas in the list/tree, it sorts the tree more
strictly and does a linear search on the tree. But it doesn't applied to
the list (i.e. the list could be constructed in a different order than
the tree so that we can't use the list when finding the first vma in that
order).
Since inserting/sorting a vma in the tree and link is done at the same
time, we can easily construct both of them in the same order. And linear
searching on the tree could be more costly than doing it on the list, it
can be converted to use the list.
Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly
linked") made the list be doubly linked, there were a couple of code need
to be fixed to construct the list properly.
Patch 1/6 is a preparation. It maintains the list sorted same as the tree
and construct doubly-linked list properly. Patch 2/6 is a simple
optimization for the vma deletion. Patch 3/6 and 4/6 convert tree
traversal to list traversal and the rest are simple fixes and cleanups.
This patch:
@vma added into @mm should be sorted by start addr, end addr and VMA
struct addr in that order because we may get identical VMAs in the @mm.
However this was true only for the rbtree, not for the list.
This patch fixes this by remembering 'rb_prev' during the tree traversal
like find_vma_prepare() does and linking the @vma via __vma_link_list().
After this patch, we can iterate the whole VMAs in correct order simply by
using @mm->mmap list.
[akpm@linux-foundation.org: avoid duplicating __vma_link_list()]
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Acked-by: Greg Ungerer <gerg@uclinux.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 04:11:22 +04:00
|
|
|
/* mm/util.c */
|
|
|
|
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
|
|
struct vm_area_struct *prev, struct rb_node *rb_parent);
|
|
|
|
|
2009-12-15 04:58:59 +03:00
|
|
|
#ifdef CONFIG_MMU
|
|
|
|
extern long mlock_vma_pages_range(struct vm_area_struct *vma,
|
|
|
|
unsigned long start, unsigned long end);
|
|
|
|
extern void munlock_vma_pages_range(struct vm_area_struct *vma,
|
|
|
|
unsigned long start, unsigned long end);
|
|
|
|
static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
|
|
|
|
}
|
|
|
|
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
/*
|
|
|
|
* Called only in fault path via page_evictable() for a new page
|
|
|
|
* to determine if it's being mapped into a LOCKED vma.
|
|
|
|
* If so, mark page as mlocked.
|
|
|
|
*/
|
2012-05-30 02:06:25 +04:00
|
|
|
static inline int mlocked_vma_newpage(struct vm_area_struct *vma,
|
|
|
|
struct page *page)
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
{
|
|
|
|
VM_BUG_ON(PageLRU(page));
|
|
|
|
|
|
|
|
if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
|
|
|
|
return 0;
|
|
|
|
|
2008-10-19 07:26:51 +04:00
|
|
|
if (!TestSetPageMlocked(page)) {
|
|
|
|
inc_zone_page_state(page, NR_MLOCK);
|
|
|
|
count_vm_event(UNEVICTABLE_PGMLOCKED);
|
|
|
|
}
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2009-12-15 04:59:22 +03:00
|
|
|
* must be called with vma's mmap_sem held for read or write, and page locked.
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
*/
|
|
|
|
extern void mlock_vma_page(struct page *page);
|
2009-12-15 04:59:22 +03:00
|
|
|
extern void munlock_vma_page(struct page *page);
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Clear the page's PageMlocked(). This can be useful in a situation where
|
|
|
|
* we want to unconditionally remove a page from the pagecache -- e.g.,
|
|
|
|
* on truncation or freeing.
|
|
|
|
*
|
|
|
|
* It is legal to call this function for any page, mlocked or not.
|
|
|
|
* If called for a page that is still mapped by mlocked vmas, all we do
|
|
|
|
* is revert to lazy LRU behaviour -- semantics are not broken.
|
|
|
|
*/
|
|
|
|
extern void __clear_page_mlock(struct page *page);
|
|
|
|
static inline void clear_page_mlock(struct page *page)
|
|
|
|
{
|
|
|
|
if (unlikely(TestClearPageMlocked(page)))
|
|
|
|
__clear_page_mlock(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* mlock_migrate_page - called only from migrate_page_copy() to
|
2008-10-19 07:26:51 +04:00
|
|
|
* migrate the Mlocked page flag; update statistics.
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
*/
|
|
|
|
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
|
|
|
|
{
|
2008-10-19 07:26:51 +04:00
|
|
|
if (TestClearPageMlocked(page)) {
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
__dec_zone_page_state(page, NR_MLOCK);
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
SetPageMlocked(newpage);
|
2008-10-19 07:26:51 +04:00
|
|
|
__inc_zone_page_state(newpage, NR_MLOCK);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
}
|
|
|
|
|
thp: transparent hugepage core
Lately I've been working to make KVM use hugepages transparently without
the usual restrictions of hugetlbfs. Some of the restrictions I'd like to
see removed:
1) hugepages have to be swappable or the guest physical memory remains
locked in RAM and can't be paged out to swap
2) if a hugepage allocation fails, regular pages should be allocated
instead and mixed in the same vma without any failure and without
userland noticing
3) if some task quits and more hugepages become available in the
buddy, guest physical memory backed by regular pages should be
relocated on hugepages automatically in regions under
madvise(MADV_HUGEPAGE) (ideally event driven by waking up the
kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes
not null)
4) avoidance of reservation and maximization of use of hugepages whenever
possible. Reservation (needed to avoid runtime fatal faliures) may be ok for
1 machine with 1 database with 1 database cache with 1 database cache size
known at boot time. It's definitely not feasible with a virtualization
hypervisor usage like RHEV-H that runs an unknown number of virtual machines
with an unknown size of each virtual machine with an unknown amount of
pagecache that could be potentially useful in the host for guest not using
O_DIRECT (aka cache=off).
hugepages in the virtualization hypervisor (and also in the guest!) are
much more important than in a regular host not using virtualization,
becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24
to 19 in case only the hypervisor uses transparent hugepages, and they
decrease the tlb-miss cacheline accesses from 19 to 15 in case both the
linux hypervisor and the linux guest both uses this patch (though the
guest will limit the addition speedup to anonymous regions only for
now...). Even more important is that the tlb miss handler is much slower
on a NPT/EPT guest than for a regular shadow paging or no-virtualization
scenario. So maximizing the amount of virtual memory cached by the TLB
pays off significantly more with NPT/EPT than without (even if there would
be no significant speedup in the tlb-miss runtime).
The first (and more tedious) part of this work requires allowing the VM to
handle anonymous hugepages mixed with regular pages transparently on
regular anonymous vmas. This is what this patch tries to achieve in the
least intrusive possible way. We want hugepages and hugetlb to be used in
a way so that all applications can benefit without changes (as usual we
leverage the KVM virtualization design: by improving the Linux VM at
large, KVM gets the performance boost too).
The most important design choice is: always fallback to 4k allocation if
the hugepage allocation fails! This is the _very_ opposite of some large
pagecache patches that failed with -EIO back then if a 64k (or similar)
allocation failed...
Second important decision (to reduce the impact of the feature on the
existing pagetable handling code) is that at any time we can split an
hugepage into 512 regular pages and it has to be done with an operation
that can't fail. This way the reliability of the swapping isn't decreased
(no need to allocate memory when we are short on memory to swap) and it's
trivial to plug a split_huge_page* one-liner where needed without
polluting the VM. Over time we can teach mprotect, mremap and friends to
handle pmd_trans_huge natively without calling split_huge_page*. The fact
it can't fail isn't just for swap: if split_huge_page would return -ENOMEM
(instead of the current void) we'd need to rollback the mprotect from the
middle of it (ideally including undoing the split_vma) which would be a
big change and in the very wrong direction (it'd likely be simpler not to
call split_huge_page at all and to teach mprotect and friends to handle
hugepages instead of rolling them back from the middle). In short the
very value of split_huge_page is that it can't fail.
The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and
incremental and it'll just be an "harmless" addition later if this initial
part is agreed upon. It also should be noted that locking-wise replacing
regular pages with hugepages is going to be very easy if compared to what
I'm doing below in split_huge_page, as it will only happen when
page_count(page) matches page_mapcount(page) if we can take the PG_lock
and mmap_sem in write mode. collapse_huge_page will be a "best effort"
that (unlike split_huge_page) can fail at the minimal sign of trouble and
we can try again later. collapse_huge_page will be similar to how KSM
works and the madvise(MADV_HUGEPAGE) will work similar to
madvise(MADV_MERGEABLE).
The default I like is that transparent hugepages are used at page fault
time. This can be changed with
/sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set
to three values "always", "madvise", "never" which mean respectively that
hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions,
or never used. /sys/kernel/mm/transparent_hugepage/defrag instead
controls if the hugepage allocation should defrag memory aggressively
"always", only inside "madvise" regions, or "never".
The pmd_trans_splitting/pmd_trans_huge locking is very solid. The
put_page (from get_user_page users that can't use mmu notifier like
O_DIRECT) that runs against a __split_huge_page_refcount instead was a
pain to serialize in a way that would result always in a coherent page
count for both tail and head. I think my locking solution with a
compound_lock taken only after the page_first is valid and is still a
PageHead should be safe but it surely needs review from SMP race point of
view. In short there is no current existing way to serialize the O_DIRECT
final put_page against split_huge_page_refcount so I had to invent a new
one (O_DIRECT loses knowledge on the mapping status by the time gup_fast
returns so...). And I didn't want to impact all gup/gup_fast users for
now, maybe if we change the gup interface substantially we can avoid this
locking, I admit I didn't think too much about it because changing the gup
unpinning interface would be invasive.
If we ignored O_DIRECT we could stick to the existing compound refcounting
code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM
(and any other mmu notifier user) would call it without FOLL_GET (and if
FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the
current task mmu notifier list yet). But O_DIRECT is fundamental for
decent performance of virtualized I/O on fast storage so we can't avoid it
to solve the race of put_page against split_huge_page_refcount to achieve
a complete hugepage feature for KVM.
Swap and oom works fine (well just like with regular pages ;). MMU
notifier is handled transparently too, with the exception of the young bit
on the pmd, that didn't have a range check but I think KVM will be fine
because the whole point of hugepages is that EPT/NPT will also use a huge
pmd when they notice gup returns pages with PageCompound set, so they
won't care of a range and there's just the pmd young bit to check in that
case.
NOTE: in some cases if the L2 cache is small, this may slowdown and waste
memory during COWs because 4M of memory are accessed in a single fault
instead of 8k (the payoff is that after COW the program can run faster).
So we might want to switch the copy_huge_page (and clear_huge_page too) to
not temporal stores. I also extensively researched ways to avoid this
cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k
up to 1M (I can send those patches that fully implemented prefault) but I
concluded they're not worth it and they add an huge additional complexity
and they remove all tlb benefits until the full hugepage has been faulted
in, to save a little bit of memory and some cache during app startup, but
they still don't improve substantially the cache-trashing during startup
if the prefault happens in >4k chunks. One reason is that those 4k pte
entries copied are still mapped on a perfectly cache-colored hugepage, so
the trashing is the worst one can generate in those copies (cow of 4k page
copies aren't so well colored so they trashes less, but again this results
in software running faster after the page fault). Those prefault patches
allowed things like a pte where post-cow pages were local 4k regular anon
pages and the not-yet-cowed pte entries were pointing in the middle of
some hugepage mapped read-only. If it doesn't payoff substantially with
todays hardware it will payoff even less in the future with larger l2
caches, and the prefault logic would blot the VM a lot. If one is
emebdded transparent_hugepage can be disabled during boot with sysfs or
with the boot commandline parameter transparent_hugepage=0 (or
transparent_hugepage=2 to restrict hugepages inside madvise regions) that
will ensure not a single hugepage is allocated at boot time. It is simple
enough to just disable transparent hugepage globally and let transparent
hugepages be allocated selectively by applications in the MADV_HUGEPAGE
region (both at page fault time, and if enabled with the
collapse_huge_page too through the kernel daemon).
This patch supports only hugepages mapped in the pmd, archs that have
smaller hugepages will not fit in this patch alone. Also some archs like
power have certain tlb limits that prevents mixing different page size in
the same regions so they will not fit in this framework that requires
"graceful fallback" to basic PAGE_SIZE in case of physical memory
fragmentation. hugetlbfs remains a perfect fit for those because its
software limits happen to match the hardware limits. hugetlbfs also
remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped
to be found not fragmented after a certain system uptime and that would be
very expensive to defragment with relocation, so requiring reservation.
hugetlbfs is the "reservation way", the point of transparent hugepages is
not to have any reservation at all and maximizing the use of cache and
hugepages at all times automatically.
Some performance result:
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep
ages3
memset page fault 1566023
memset tlb miss 453854
memset second tlb miss 453321
random access tlb miss 41635
random access second tlb miss 41658
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3
memset page fault 1566471
memset tlb miss 453375
memset second tlb miss 453320
random access tlb miss 41636
random access second tlb miss 41637
vmx andrea # ./largepages3
memset page fault 1566642
memset tlb miss 453417
memset second tlb miss 453313
random access tlb miss 41630
random access second tlb miss 41647
vmx andrea # ./largepages3
memset page fault 1566872
memset tlb miss 453418
memset second tlb miss 453315
random access tlb miss 41618
random access second tlb miss 41659
vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage
vmx andrea # ./largepages3
memset page fault 2182476
memset tlb miss 460305
memset second tlb miss 460179
random access tlb miss 44483
random access second tlb miss 44186
vmx andrea # ./largepages3
memset page fault 2182791
memset tlb miss 460742
memset second tlb miss 459962
random access tlb miss 43981
random access second tlb miss 43988
============
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#define SIZE (3UL*1024*1024*1024)
int main()
{
char *p = malloc(SIZE), *p2;
struct timeval before, after;
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset page fault %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
return 0;
}
============
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 02:46:52 +03:00
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
extern unsigned long vma_address(struct page *page,
|
|
|
|
struct vm_area_struct *vma);
|
|
|
|
#endif
|
2009-12-15 04:58:59 +03:00
|
|
|
#else /* !CONFIG_MMU */
|
2012-05-30 02:06:25 +04:00
|
|
|
static inline int mlocked_vma_newpage(struct vm_area_struct *v, struct page *p)
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:44 +04:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
static inline void clear_page_mlock(struct page *page) { }
|
|
|
|
static inline void mlock_vma_page(struct page *page) { }
|
|
|
|
static inline void mlock_migrate_page(struct page *new, struct page *old) { }
|
|
|
|
|
2009-12-15 04:58:59 +03:00
|
|
|
#endif /* !CONFIG_MMU */
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:39 +04:00
|
|
|
|
2008-11-06 23:53:26 +03:00
|
|
|
/*
|
|
|
|
* Return the mem_map entry representing the 'offset' subpage within
|
|
|
|
* the maximally aligned gigantic page 'base'. Handle any discontiguity
|
|
|
|
* in the mem_map at MAX_ORDER_NR_PAGES boundaries.
|
|
|
|
*/
|
|
|
|
static inline struct page *mem_map_offset(struct page *base, int offset)
|
|
|
|
{
|
|
|
|
if (unlikely(offset >= MAX_ORDER_NR_PAGES))
|
|
|
|
return pfn_to_page(page_to_pfn(base) + offset);
|
|
|
|
return base + offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2011-03-31 05:57:33 +04:00
|
|
|
* Iterator over all subpages within the maximally aligned gigantic
|
2008-11-06 23:53:26 +03:00
|
|
|
* page 'base'. Handle any discontiguity in the mem_map.
|
|
|
|
*/
|
|
|
|
static inline struct page *mem_map_next(struct page *iter,
|
|
|
|
struct page *base, int offset)
|
|
|
|
{
|
|
|
|
if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
|
|
|
|
unsigned long pfn = page_to_pfn(base) + offset;
|
|
|
|
if (!pfn_valid(pfn))
|
|
|
|
return NULL;
|
|
|
|
return pfn_to_page(pfn);
|
|
|
|
}
|
|
|
|
return iter + 1;
|
|
|
|
}
|
|
|
|
|
2008-02-24 02:24:06 +03:00
|
|
|
/*
|
|
|
|
* FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
|
|
|
|
* so all functions starting at paging_init should be marked __init
|
|
|
|
* in those cases. SPARSEMEM, however, allows for memory hotplug,
|
|
|
|
* and alloc_bootmem_node is not used.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_SPARSEMEM
|
|
|
|
#define __paginginit __meminit
|
|
|
|
#else
|
|
|
|
#define __paginginit __init
|
|
|
|
#endif
|
|
|
|
|
2008-07-24 08:26:49 +04:00
|
|
|
/* Memory initialisation debug and verification */
|
|
|
|
enum mminit_level {
|
|
|
|
MMINIT_WARNING,
|
|
|
|
MMINIT_VERIFY,
|
|
|
|
MMINIT_TRACE
|
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef CONFIG_DEBUG_MEMORY_INIT
|
|
|
|
|
|
|
|
extern int mminit_loglevel;
|
|
|
|
|
|
|
|
#define mminit_dprintk(level, prefix, fmt, arg...) \
|
|
|
|
do { \
|
|
|
|
if (level < mminit_loglevel) { \
|
|
|
|
printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
|
|
|
|
printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
|
|
|
|
} \
|
|
|
|
} while (0)
|
|
|
|
|
2008-07-24 08:26:51 +04:00
|
|
|
extern void mminit_verify_pageflags_layout(void);
|
|
|
|
extern void mminit_verify_page_links(struct page *page,
|
|
|
|
enum zone_type zone, unsigned long nid, unsigned long pfn);
|
2008-07-24 08:26:52 +04:00
|
|
|
extern void mminit_verify_zonelist(void);
|
2008-07-24 08:26:51 +04:00
|
|
|
|
2008-07-24 08:26:49 +04:00
|
|
|
#else
|
|
|
|
|
|
|
|
static inline void mminit_dprintk(enum mminit_level level,
|
|
|
|
const char *prefix, const char *fmt, ...)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2008-07-24 08:26:51 +04:00
|
|
|
static inline void mminit_verify_pageflags_layout(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void mminit_verify_page_links(struct page *page,
|
|
|
|
enum zone_type zone, unsigned long nid, unsigned long pfn)
|
|
|
|
{
|
|
|
|
}
|
2008-07-24 08:26:52 +04:00
|
|
|
|
|
|
|
static inline void mminit_verify_zonelist(void)
|
|
|
|
{
|
|
|
|
}
|
2008-07-24 08:26:49 +04:00
|
|
|
#endif /* CONFIG_DEBUG_MEMORY_INIT */
|
2008-07-24 08:26:52 +04:00
|
|
|
|
|
|
|
/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
|
|
|
|
#if defined(CONFIG_SPARSEMEM)
|
|
|
|
extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
|
|
|
|
unsigned long *end_pfn);
|
|
|
|
#else
|
|
|
|
static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
|
|
|
|
unsigned long *end_pfn)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_SPARSEMEM */
|
|
|
|
|
2009-06-17 02:33:22 +04:00
|
|
|
#define ZONE_RECLAIM_NOSCAN -2
|
|
|
|
#define ZONE_RECLAIM_FULL -1
|
|
|
|
#define ZONE_RECLAIM_SOME 0
|
|
|
|
#define ZONE_RECLAIM_SUCCESS 1
|
2006-03-22 11:08:33 +03:00
|
|
|
#endif
|
2009-12-16 14:19:59 +03:00
|
|
|
|
2009-12-16 14:19:59 +03:00
|
|
|
extern int hwpoison_filter(struct page *p);
|
|
|
|
|
2009-12-16 14:19:59 +03:00
|
|
|
extern u32 hwpoison_filter_dev_major;
|
|
|
|
extern u32 hwpoison_filter_dev_minor;
|
2009-12-16 14:19:59 +03:00
|
|
|
extern u64 hwpoison_filter_flags_mask;
|
|
|
|
extern u64 hwpoison_filter_flags_value;
|
2009-12-16 14:19:59 +03:00
|
|
|
extern u64 hwpoison_filter_memcg;
|
2009-12-16 14:19:59 +03:00
|
|
|
extern u32 hwpoison_filter_enable;
|
2012-05-31 04:17:35 +04:00
|
|
|
|
|
|
|
extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
|
|
|
|
unsigned long, unsigned long,
|
|
|
|
unsigned long, unsigned long);
|