2008-02-04 23:29:01 -07:00
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/highmem.h>
|
|
|
|
#include <linux/sched.h>
|
2009-12-14 18:59:59 -07:00
|
|
|
#include <linux/hugetlb.h>
|
2008-02-04 23:29:01 -07:00
|
|
|
|
|
|
|
static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
|
2008-06-12 16:21:47 -06:00
|
|
|
struct mm_walk *walk)
|
2008-02-04 23:29:01 -07:00
|
|
|
{
|
|
|
|
pte_t *pte;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
pte = pte_offset_map(pmd, addr);
|
2008-04-28 03:11:47 -06:00
|
|
|
for (;;) {
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
2008-04-28 03:11:47 -06:00
|
|
|
addr += PAGE_SIZE;
|
|
|
|
if (addr == end)
|
|
|
|
break;
|
|
|
|
pte++;
|
|
|
|
}
|
2008-02-04 23:29:01 -07:00
|
|
|
|
|
|
|
pte_unmap(pte);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
|
2008-06-12 16:21:47 -06:00
|
|
|
struct mm_walk *walk)
|
2008-02-04 23:29:01 -07:00
|
|
|
{
|
|
|
|
pmd_t *pmd;
|
|
|
|
unsigned long next;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
|
|
do {
|
2011-03-22 17:32:56 -06:00
|
|
|
again:
|
2008-02-04 23:29:01 -07:00
|
|
|
next = pmd_addr_end(addr, end);
|
2011-03-22 17:32:56 -06:00
|
|
|
if (pmd_none(*pmd)) {
|
2008-02-04 23:29:01 -07:00
|
|
|
if (walk->pte_hole)
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pte_hole(addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
continue;
|
|
|
|
}
|
2011-03-22 17:32:56 -06:00
|
|
|
/*
|
|
|
|
* This implies that each ->pmd_entry() handler
|
|
|
|
* needs to know about pmd_trans_huge() pmds
|
|
|
|
*/
|
2008-02-04 23:29:01 -07:00
|
|
|
if (walk->pmd_entry)
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pmd_entry(pmd, addr, next, walk);
|
2011-03-22 17:32:56 -06:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check this here so we only break down trans_huge
|
|
|
|
* pages when we _need_ to
|
|
|
|
*/
|
|
|
|
if (!walk->pte_entry)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
split_huge_page_pmd(walk->mm, pmd);
|
|
|
|
if (pmd_none_or_clear_bad(pmd))
|
|
|
|
goto again;
|
|
|
|
err = walk_pte_range(pmd, addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
} while (pmd++, addr = next, addr != end);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
|
2008-06-12 16:21:47 -06:00
|
|
|
struct mm_walk *walk)
|
2008-02-04 23:29:01 -07:00
|
|
|
{
|
|
|
|
pud_t *pud;
|
|
|
|
unsigned long next;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
pud = pud_offset(pgd, addr);
|
|
|
|
do {
|
|
|
|
next = pud_addr_end(addr, end);
|
|
|
|
if (pud_none_or_clear_bad(pud)) {
|
|
|
|
if (walk->pte_hole)
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pte_hole(addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (walk->pud_entry)
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pud_entry(pud, addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (!err && (walk->pmd_entry || walk->pte_entry))
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk_pmd_range(pud, addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
} while (pud++, addr = next, addr != end);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2010-04-06 15:35:04 -06:00
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
|
|
|
|
unsigned long end)
|
|
|
|
{
|
|
|
|
unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
|
|
|
|
return boundary < end ? boundary : end;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int walk_hugetlb_range(struct vm_area_struct *vma,
|
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
struct mm_walk *walk)
|
|
|
|
{
|
|
|
|
struct hstate *h = hstate_vma(vma);
|
|
|
|
unsigned long next;
|
|
|
|
unsigned long hmask = huge_page_mask(h);
|
|
|
|
pte_t *pte;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
do {
|
|
|
|
next = hugetlb_entry_end(h, addr, end);
|
|
|
|
pte = huge_pte_offset(walk->mm, addr & hmask);
|
|
|
|
if (pte && walk->hugetlb_entry)
|
|
|
|
err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
} while (addr = next, addr != end);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2011-07-25 18:12:09 -06:00
|
|
|
|
|
|
|
static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk)
|
|
|
|
{
|
|
|
|
struct vm_area_struct *vma;
|
|
|
|
|
|
|
|
/* We don't need vma lookup at all. */
|
|
|
|
if (!walk->hugetlb_entry)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
|
|
|
|
vma = find_vma(walk->mm, addr);
|
|
|
|
if (vma && vma->vm_start <= addr && is_vm_hugetlb_page(vma))
|
|
|
|
return vma;
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
#else /* CONFIG_HUGETLB_PAGE */
|
|
|
|
static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int walk_hugetlb_range(struct vm_area_struct *vma,
|
|
|
|
unsigned long addr, unsigned long end,
|
|
|
|
struct mm_walk *walk)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* CONFIG_HUGETLB_PAGE */
|
|
|
|
|
|
|
|
|
2010-04-06 15:35:04 -06:00
|
|
|
|
2008-02-04 23:29:01 -07:00
|
|
|
/**
|
|
|
|
* walk_page_range - walk a memory map's page tables with a callback
|
2008-03-19 18:00:40 -06:00
|
|
|
* @mm: memory map to walk
|
|
|
|
* @addr: starting address
|
|
|
|
* @end: ending address
|
|
|
|
* @walk: set of callbacks to invoke for each level of the tree
|
2008-02-04 23:29:01 -07:00
|
|
|
*
|
|
|
|
* Recursively walk the page table for the memory area in a VMA,
|
|
|
|
* calling supplied callbacks. Callbacks are called in-order (first
|
|
|
|
* PGD, first PUD, first PMD, first PTE, second PTE... second PMD,
|
|
|
|
* etc.). If lower-level callbacks are omitted, walking depth is reduced.
|
|
|
|
*
|
2008-06-12 16:21:47 -06:00
|
|
|
* Each callback receives an entry pointer and the start and end of the
|
|
|
|
* associated range, and a copy of the original mm_walk for access to
|
|
|
|
* the ->private or ->mm fields.
|
2008-02-04 23:29:01 -07:00
|
|
|
*
|
2011-07-25 18:12:11 -06:00
|
|
|
* Usually no locks are taken, but splitting transparent huge page may
|
|
|
|
* take page table lock. And the bottom level iterator will map PTE
|
2008-02-04 23:29:01 -07:00
|
|
|
* directories from highmem if necessary.
|
|
|
|
*
|
|
|
|
* If any callback returns a non-zero value, the walk is aborted and
|
|
|
|
* the return value is propagated back to the caller. Otherwise 0 is returned.
|
2011-07-25 18:12:10 -06:00
|
|
|
*
|
|
|
|
* walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry
|
|
|
|
* is !NULL.
|
2008-02-04 23:29:01 -07:00
|
|
|
*/
|
2008-06-12 16:21:47 -06:00
|
|
|
int walk_page_range(unsigned long addr, unsigned long end,
|
|
|
|
struct mm_walk *walk)
|
2008-02-04 23:29:01 -07:00
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
unsigned long next;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
if (addr >= end)
|
|
|
|
return err;
|
|
|
|
|
2008-06-12 16:21:47 -06:00
|
|
|
if (!walk->mm)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
pgd = pgd_offset(walk->mm, addr);
|
2008-02-04 23:29:01 -07:00
|
|
|
do {
|
2011-07-25 18:12:09 -06:00
|
|
|
struct vm_area_struct *vma;
|
2010-11-24 13:57:10 -07:00
|
|
|
|
2008-02-04 23:29:01 -07:00
|
|
|
next = pgd_addr_end(addr, end);
|
2009-12-14 18:59:59 -07:00
|
|
|
|
mm hugetlb: add hugepage support to pagemap
This patch enables extraction of the pfn of a hugepage from
/proc/pid/pagemap in an architecture independent manner.
Details
-------
My test program (leak_pagemap) works as follows:
- creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,)
- read()/write() something on it,
- call page-types with option -p,
- munmap() and unlink() the file on hugetlbfs
Without my patches
------------------
$ ./leak_pagemap
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 1 0 __________________________________
0x0000000000000804 1 0 __R________M______________________ referenced,mmap
0x000000000000086c 81 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap
0x0000000000005808 5 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 101 0
The output of page-types don't show any hugepage.
With my patches
---------------
$ ./leak_pagemap
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 1 0 __________________________________
0x0000000000030000 51100 199 ________________TG________________ compound_tail,huge
0x0000000000028018 100 0 ___UD__________H_G________________ uptodate,dirty,compound_head,huge
0x0000000000000804 1 0 __R________M______________________ referenced,mmap
0x000000000000080c 1 0 __RU_______M______________________ referenced,uptodate,mmap
0x000000000000086c 80 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap
0x0000000000005808 4 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 51300 200
The output of page-types shows 51200 pages contributing to hugepages,
containing 100 head pages and 51100 tail pages as expected.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-14 19:00:01 -07:00
|
|
|
/*
|
|
|
|
* handle hugetlb vma individually because pagetable walk for
|
|
|
|
* the hugetlb page is dependent on the architecture and
|
|
|
|
* we can't handled it in the same manner as non-huge pages.
|
|
|
|
*/
|
2011-07-25 18:12:09 -06:00
|
|
|
vma = hugetlb_vma(addr, walk);
|
|
|
|
if (vma) {
|
2009-12-14 18:59:59 -07:00
|
|
|
if (vma->vm_end < next)
|
|
|
|
next = vma->vm_end;
|
2010-04-06 15:35:04 -06:00
|
|
|
/*
|
|
|
|
* Hugepage is very tightly coupled with vma, so
|
|
|
|
* walk through hugetlb entries within a given vma.
|
|
|
|
*/
|
|
|
|
err = walk_hugetlb_range(vma, addr, next, walk);
|
mm hugetlb: add hugepage support to pagemap
This patch enables extraction of the pfn of a hugepage from
/proc/pid/pagemap in an architecture independent manner.
Details
-------
My test program (leak_pagemap) works as follows:
- creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,)
- read()/write() something on it,
- call page-types with option -p,
- munmap() and unlink() the file on hugetlbfs
Without my patches
------------------
$ ./leak_pagemap
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 1 0 __________________________________
0x0000000000000804 1 0 __R________M______________________ referenced,mmap
0x000000000000086c 81 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap
0x0000000000005808 5 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 101 0
The output of page-types don't show any hugepage.
With my patches
---------------
$ ./leak_pagemap
flags page-count MB symbolic-flags long-symbolic-flags
0x0000000000000000 1 0 __________________________________
0x0000000000030000 51100 199 ________________TG________________ compound_tail,huge
0x0000000000028018 100 0 ___UD__________H_G________________ uptodate,dirty,compound_head,huge
0x0000000000000804 1 0 __R________M______________________ referenced,mmap
0x000000000000080c 1 0 __RU_______M______________________ referenced,uptodate,mmap
0x000000000000086c 80 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap
0x0000000000005808 4 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked
0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked
0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked
total 51300 200
The output of page-types shows 51200 pages contributing to hugepages,
containing 100 head pages and 51100 tail pages as expected.
[akpm@linux-foundation.org: build fix]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-14 19:00:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
2010-04-06 15:35:04 -06:00
|
|
|
pgd = pgd_offset(walk->mm, next);
|
2009-12-14 18:59:59 -07:00
|
|
|
continue;
|
|
|
|
}
|
2011-07-25 18:12:09 -06:00
|
|
|
|
2008-02-04 23:29:01 -07:00
|
|
|
if (pgd_none_or_clear_bad(pgd)) {
|
|
|
|
if (walk->pte_hole)
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pte_hole(addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
2009-12-14 18:59:59 -07:00
|
|
|
pgd++;
|
2008-02-04 23:29:01 -07:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (walk->pgd_entry)
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk->pgd_entry(pgd, addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (!err &&
|
|
|
|
(walk->pud_entry || walk->pmd_entry || walk->pte_entry))
|
2008-06-12 16:21:47 -06:00
|
|
|
err = walk_pud_range(pgd, addr, next, walk);
|
2008-02-04 23:29:01 -07:00
|
|
|
if (err)
|
|
|
|
break;
|
2009-12-14 18:59:59 -07:00
|
|
|
pgd++;
|
|
|
|
} while (addr = next, addr != end);
|
2008-02-04 23:29:01 -07:00
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|