2008-10-06 14:26:12 +04:00
|
|
|
#include <linux/bootmem.h>
|
|
|
|
#include <linux/compiler.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/init.h>
|
2009-09-22 04:02:01 +04:00
|
|
|
#include <linux/ksm.h>
|
2008-10-06 14:26:12 +04:00
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/mmzone.h>
|
2015-02-12 02:24:51 +03:00
|
|
|
#include <linux/huge_mm.h>
|
2008-10-06 14:26:12 +04:00
|
|
|
#include <linux/proc_fs.h>
|
|
|
|
#include <linux/seq_file.h>
|
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
|
|
|
#include <linux/hugetlb.h>
|
2015-09-10 01:35:38 +03:00
|
|
|
#include <linux/memcontrol.h>
|
mm: introduce idle page tracking
Knowing the portion of memory that is not used by a certain application or
memory cgroup (idle memory) can be useful for partitioning the system
efficiently, e.g. by setting memory cgroup limits appropriately.
Currently, the only means to estimate the amount of idle memory provided
by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the
access bit for all pages mapped to a particular process by writing 1 to
clear_refs, wait for some time, and then count smaps:Referenced. However,
this method has two serious shortcomings:
- it does not count unmapped file pages
- it affects the reclaimer logic
To overcome these drawbacks, this patch introduces two new page flags,
Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap.
A page's Idle flag can only be set from userspace by setting bit in
/sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page,
and it is cleared whenever the page is accessed either through page tables
(it is cleared in page_referenced() in this case) or using the read(2)
system call (mark_page_accessed()). Thus by setting the Idle flag for
pages of a particular workload, which can be found e.g. by reading
/proc/PID/pagemap, waiting for some time to let the workload access its
working set, and then reading the bitmap file, one can estimate the amount
of pages that are not used by the workload.
The Young page flag is used to avoid interference with the memory
reclaimer. A page's Young flag is set whenever the Access bit of a page
table entry pointing to the page is cleared by writing to the bitmap file.
If page_referenced() is called on a Young page, it will add 1 to its
return value, therefore concealing the fact that the Access bit was
cleared.
Note, since there is no room for extra page flags on 32 bit, this feature
uses extended page flags when compiled on 32 bit.
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: kpageidle requires an MMU]
[akpm@linux-foundation.org: decouple from page-flags rework]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 01:35:45 +03:00
|
|
|
#include <linux/mmu_notifier.h>
|
|
|
|
#include <linux/page_idle.h>
|
2009-12-16 14:19:59 +03:00
|
|
|
#include <linux/kernel-page-flags.h>
|
2008-10-06 14:26:12 +04:00
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include "internal.h"
|
|
|
|
|
|
|
|
#define KPMSIZE sizeof(u64)
|
|
|
|
#define KPMMASK (KPMSIZE - 1)
|
mm: introduce idle page tracking
Knowing the portion of memory that is not used by a certain application or
memory cgroup (idle memory) can be useful for partitioning the system
efficiently, e.g. by setting memory cgroup limits appropriately.
Currently, the only means to estimate the amount of idle memory provided
by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the
access bit for all pages mapped to a particular process by writing 1 to
clear_refs, wait for some time, and then count smaps:Referenced. However,
this method has two serious shortcomings:
- it does not count unmapped file pages
- it affects the reclaimer logic
To overcome these drawbacks, this patch introduces two new page flags,
Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap.
A page's Idle flag can only be set from userspace by setting bit in
/sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page,
and it is cleared whenever the page is accessed either through page tables
(it is cleared in page_referenced() in this case) or using the read(2)
system call (mark_page_accessed()). Thus by setting the Idle flag for
pages of a particular workload, which can be found e.g. by reading
/proc/PID/pagemap, waiting for some time to let the workload access its
working set, and then reading the bitmap file, one can estimate the amount
of pages that are not used by the workload.
The Young page flag is used to avoid interference with the memory
reclaimer. A page's Young flag is set whenever the Access bit of a page
table entry pointing to the page is cleared by writing to the bitmap file.
If page_referenced() is called on a Young page, it will add 1 to its
return value, therefore concealing the fact that the Access bit was
cleared.
Note, since there is no room for extra page flags on 32 bit, this feature
uses extended page flags when compiled on 32 bit.
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: kpageidle requires an MMU]
[akpm@linux-foundation.org: decouple from page-flags rework]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 01:35:45 +03:00
|
|
|
#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
|
2009-06-17 02:32:23 +04:00
|
|
|
|
2008-10-06 14:26:12 +04:00
|
|
|
/* /proc/kpagecount - an array exposing page counts
|
|
|
|
*
|
|
|
|
* Each entry is a u64 representing the corresponding
|
|
|
|
* physical page count.
|
|
|
|
*/
|
|
|
|
static ssize_t kpagecount_read(struct file *file, char __user *buf,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
u64 __user *out = (u64 __user *)buf;
|
|
|
|
struct page *ppage;
|
|
|
|
unsigned long src = *ppos;
|
|
|
|
unsigned long pfn;
|
|
|
|
ssize_t ret = 0;
|
|
|
|
u64 pcount;
|
|
|
|
|
|
|
|
pfn = src / KPMSIZE;
|
|
|
|
count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
|
|
|
|
if (src & KPMMASK || count & KPMMASK)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
while (count > 0) {
|
|
|
|
if (pfn_valid(pfn))
|
|
|
|
ppage = pfn_to_page(pfn);
|
2009-06-17 02:32:23 +04:00
|
|
|
else
|
|
|
|
ppage = NULL;
|
2011-01-13 04:00:34 +03:00
|
|
|
if (!ppage || PageSlab(ppage))
|
2008-10-06 14:26:12 +04:00
|
|
|
pcount = 0;
|
|
|
|
else
|
|
|
|
pcount = page_mapcount(ppage);
|
|
|
|
|
2009-06-17 02:32:23 +04:00
|
|
|
if (put_user(pcount, out)) {
|
2008-10-06 14:26:12 +04:00
|
|
|
ret = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2009-06-17 02:32:23 +04:00
|
|
|
pfn++;
|
|
|
|
out++;
|
2008-10-06 14:26:12 +04:00
|
|
|
count -= KPMSIZE;
|
2015-09-10 01:35:51 +03:00
|
|
|
|
|
|
|
cond_resched();
|
2008-10-06 14:26:12 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
*ppos += (char __user *)out - buf;
|
|
|
|
if (!ret)
|
|
|
|
ret = (char __user *)out - buf;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations proc_kpagecount_operations = {
|
|
|
|
.llseek = mem_lseek,
|
|
|
|
.read = kpagecount_read,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* /proc/kpageflags - an array exposing page flags
|
|
|
|
*
|
|
|
|
* Each entry is a u64 representing the corresponding
|
|
|
|
* physical page flags.
|
|
|
|
*/
|
|
|
|
|
2009-06-17 02:32:24 +04:00
|
|
|
static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
|
|
|
|
{
|
|
|
|
return ((kflags >> kbit) & 1) << ubit;
|
|
|
|
}
|
|
|
|
|
2009-12-16 14:19:59 +03:00
|
|
|
u64 stable_page_flags(struct page *page)
|
2009-06-17 02:32:24 +04:00
|
|
|
{
|
|
|
|
u64 k;
|
|
|
|
u64 u;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pseudo flag: KPF_NOPAGE
|
|
|
|
* it differentiates a memory hole from a page with no flags
|
|
|
|
*/
|
|
|
|
if (!page)
|
|
|
|
return 1 << KPF_NOPAGE;
|
|
|
|
|
|
|
|
k = page->flags;
|
|
|
|
u = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pseudo flags for the well known (anonymous) memory mapped pages
|
|
|
|
*
|
|
|
|
* Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
|
2016-01-16 03:53:46 +03:00
|
|
|
* simple test in page_mapcount() is not enough.
|
2009-06-17 02:32:24 +04:00
|
|
|
*/
|
2016-01-16 03:53:46 +03:00
|
|
|
if (!PageSlab(page) && page_mapcount(page))
|
2009-06-17 02:32:24 +04:00
|
|
|
u |= 1 << KPF_MMAP;
|
|
|
|
if (PageAnon(page))
|
|
|
|
u |= 1 << KPF_ANON;
|
2009-09-22 04:02:01 +04:00
|
|
|
if (PageKsm(page))
|
|
|
|
u |= 1 << KPF_KSM;
|
2009-06-17 02:32:24 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* compound pages: export both head/tail info
|
|
|
|
* they together define a compound page's start/end pos and order
|
|
|
|
*/
|
|
|
|
if (PageHead(page))
|
|
|
|
u |= 1 << KPF_COMPOUND_HEAD;
|
|
|
|
if (PageTail(page))
|
|
|
|
u |= 1 << KPF_COMPOUND_TAIL;
|
|
|
|
if (PageHuge(page))
|
|
|
|
u |= 1 << KPF_HUGE;
|
2012-10-09 03:33:47 +04:00
|
|
|
/*
|
|
|
|
* PageTransCompound can be true for non-huge compound pages (slab
|
|
|
|
* pages or pages allocated by drivers with __GFP_COMP) because it
|
2014-01-24 03:52:53 +04:00
|
|
|
* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
|
|
|
|
* to make sure a given page is a thp, not a non-huge compound page.
|
2012-10-09 03:33:47 +04:00
|
|
|
*/
|
2015-02-12 02:24:51 +03:00
|
|
|
else if (PageTransCompound(page)) {
|
|
|
|
struct page *head = compound_head(page);
|
|
|
|
|
|
|
|
if (PageLRU(head) || PageAnon(head))
|
|
|
|
u |= 1 << KPF_THP;
|
|
|
|
else if (is_huge_zero_page(head)) {
|
|
|
|
u |= 1 << KPF_ZERO_PAGE;
|
|
|
|
u |= 1 << KPF_THP;
|
|
|
|
}
|
|
|
|
} else if (is_zero_pfn(page_to_pfn(page)))
|
|
|
|
u |= 1 << KPF_ZERO_PAGE;
|
|
|
|
|
2009-06-17 02:32:24 +04:00
|
|
|
|
|
|
|
/*
|
2011-01-14 02:47:00 +03:00
|
|
|
* Caveats on high order pages: page->_count will only be set
|
|
|
|
* -1 on the head page; SLUB/SLQB do the same for PG_slab;
|
|
|
|
* SLOB won't set PG_slab at all on compound pages.
|
2009-06-17 02:32:24 +04:00
|
|
|
*/
|
2011-01-14 02:47:00 +03:00
|
|
|
if (PageBuddy(page))
|
|
|
|
u |= 1 << KPF_BUDDY;
|
|
|
|
|
2014-10-10 02:29:32 +04:00
|
|
|
if (PageBalloon(page))
|
|
|
|
u |= 1 << KPF_BALLOON;
|
|
|
|
|
2015-09-10 01:35:48 +03:00
|
|
|
if (page_is_idle(page))
|
|
|
|
u |= 1 << KPF_IDLE;
|
|
|
|
|
2011-01-14 02:47:00 +03:00
|
|
|
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
|
|
|
|
|
2009-06-17 02:32:24 +04:00
|
|
|
u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
|
|
|
|
|
|
|
|
u |= kpf_copy_bit(k, KPF_ERROR, PG_error);
|
|
|
|
u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty);
|
|
|
|
u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate);
|
|
|
|
u |= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback);
|
|
|
|
|
|
|
|
u |= kpf_copy_bit(k, KPF_LRU, PG_lru);
|
|
|
|
u |= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced);
|
|
|
|
u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
|
|
|
|
u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
|
|
|
|
|
|
|
|
u |= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache);
|
|
|
|
u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
|
|
|
|
|
|
|
|
u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);
|
|
|
|
u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked);
|
|
|
|
|
2009-10-08 03:32:27 +04:00
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
|
|
u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
|
|
|
|
#endif
|
|
|
|
|
2010-09-10 03:37:36 +04:00
|
|
|
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
|
2009-06-17 02:32:24 +04:00
|
|
|
u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
|
|
|
|
u |= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk);
|
|
|
|
u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private);
|
|
|
|
u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2);
|
|
|
|
u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1);
|
|
|
|
u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1);
|
|
|
|
|
|
|
|
return u;
|
|
|
|
};
|
2008-10-06 14:26:12 +04:00
|
|
|
|
|
|
|
static ssize_t kpageflags_read(struct file *file, char __user *buf,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
u64 __user *out = (u64 __user *)buf;
|
|
|
|
struct page *ppage;
|
|
|
|
unsigned long src = *ppos;
|
|
|
|
unsigned long pfn;
|
|
|
|
ssize_t ret = 0;
|
|
|
|
|
|
|
|
pfn = src / KPMSIZE;
|
|
|
|
count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
|
|
|
|
if (src & KPMMASK || count & KPMMASK)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
while (count > 0) {
|
|
|
|
if (pfn_valid(pfn))
|
|
|
|
ppage = pfn_to_page(pfn);
|
2009-06-17 02:32:23 +04:00
|
|
|
else
|
|
|
|
ppage = NULL;
|
2009-06-17 02:32:24 +04:00
|
|
|
|
2009-12-16 14:19:59 +03:00
|
|
|
if (put_user(stable_page_flags(ppage), out)) {
|
2008-10-06 14:26:12 +04:00
|
|
|
ret = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2009-06-17 02:32:23 +04:00
|
|
|
pfn++;
|
|
|
|
out++;
|
2008-10-06 14:26:12 +04:00
|
|
|
count -= KPMSIZE;
|
2015-09-10 01:35:51 +03:00
|
|
|
|
|
|
|
cond_resched();
|
2008-10-06 14:26:12 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
*ppos += (char __user *)out - buf;
|
|
|
|
if (!ret)
|
|
|
|
ret = (char __user *)out - buf;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations proc_kpageflags_operations = {
|
|
|
|
.llseek = mem_lseek,
|
|
|
|
.read = kpageflags_read,
|
|
|
|
};
|
|
|
|
|
2015-09-10 01:35:38 +03:00
|
|
|
#ifdef CONFIG_MEMCG
|
|
|
|
static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
u64 __user *out = (u64 __user *)buf;
|
|
|
|
struct page *ppage;
|
|
|
|
unsigned long src = *ppos;
|
|
|
|
unsigned long pfn;
|
|
|
|
ssize_t ret = 0;
|
|
|
|
u64 ino;
|
|
|
|
|
|
|
|
pfn = src / KPMSIZE;
|
|
|
|
count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
|
|
|
|
if (src & KPMMASK || count & KPMMASK)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
while (count > 0) {
|
|
|
|
if (pfn_valid(pfn))
|
|
|
|
ppage = pfn_to_page(pfn);
|
|
|
|
else
|
|
|
|
ppage = NULL;
|
|
|
|
|
|
|
|
if (ppage)
|
|
|
|
ino = page_cgroup_ino(ppage);
|
|
|
|
else
|
|
|
|
ino = 0;
|
|
|
|
|
|
|
|
if (put_user(ino, out)) {
|
|
|
|
ret = -EFAULT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
pfn++;
|
|
|
|
out++;
|
|
|
|
count -= KPMSIZE;
|
2015-09-10 01:35:51 +03:00
|
|
|
|
|
|
|
cond_resched();
|
2015-09-10 01:35:38 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
*ppos += (char __user *)out - buf;
|
|
|
|
if (!ret)
|
|
|
|
ret = (char __user *)out - buf;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations proc_kpagecgroup_operations = {
|
|
|
|
.llseek = mem_lseek,
|
|
|
|
.read = kpagecgroup_read,
|
|
|
|
};
|
|
|
|
#endif /* CONFIG_MEMCG */
|
|
|
|
|
2008-10-06 14:26:12 +04:00
|
|
|
static int __init proc_page_init(void)
|
|
|
|
{
|
|
|
|
proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
|
|
|
|
proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
|
2015-09-10 01:35:38 +03:00
|
|
|
#ifdef CONFIG_MEMCG
|
|
|
|
proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
|
|
|
|
#endif
|
2008-10-06 14:26:12 +04:00
|
|
|
return 0;
|
|
|
|
}
|
2014-01-24 03:55:45 +04:00
|
|
|
fs_initcall(proc_page_init);
|