mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 20:51:44 +00:00
5dc37642cb
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>
168 lines
3.9 KiB
C
168 lines
3.9 KiB
C
#include <linux/mm.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/hugetlb.h>
|
|
|
|
static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pte_t *pte;
|
|
int err = 0;
|
|
|
|
pte = pte_offset_map(pmd, addr);
|
|
for (;;) {
|
|
err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
|
|
if (err)
|
|
break;
|
|
addr += PAGE_SIZE;
|
|
if (addr == end)
|
|
break;
|
|
pte++;
|
|
}
|
|
|
|
pte_unmap(pte);
|
|
return err;
|
|
}
|
|
|
|
static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
int err = 0;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
next = pmd_addr_end(addr, end);
|
|
if (pmd_none_or_clear_bad(pmd)) {
|
|
if (walk->pte_hole)
|
|
err = walk->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
if (walk->pmd_entry)
|
|
err = walk->pmd_entry(pmd, addr, next, walk);
|
|
if (!err && walk->pte_entry)
|
|
err = walk_pte_range(pmd, addr, next, walk);
|
|
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,
|
|
struct mm_walk *walk)
|
|
{
|
|
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)
|
|
err = walk->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
if (walk->pud_entry)
|
|
err = walk->pud_entry(pud, addr, next, walk);
|
|
if (!err && (walk->pmd_entry || walk->pte_entry))
|
|
err = walk_pmd_range(pud, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
} while (pud++, addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|
|
|
|
/**
|
|
* walk_page_range - walk a memory map's page tables with a callback
|
|
* @mm: memory map to walk
|
|
* @addr: starting address
|
|
* @end: ending address
|
|
* @walk: set of callbacks to invoke for each level of the tree
|
|
*
|
|
* 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.
|
|
*
|
|
* 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.
|
|
*
|
|
* No locks are taken, but the bottom level iterator will map PTE
|
|
* 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.
|
|
*/
|
|
int walk_page_range(unsigned long addr, unsigned long end,
|
|
struct mm_walk *walk)
|
|
{
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
int err = 0;
|
|
struct vm_area_struct *vma;
|
|
|
|
if (addr >= end)
|
|
return err;
|
|
|
|
if (!walk->mm)
|
|
return -EINVAL;
|
|
|
|
pgd = pgd_offset(walk->mm, addr);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
vma = find_vma(walk->mm, addr);
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
if (vma && is_vm_hugetlb_page(vma)) {
|
|
pte_t *pte;
|
|
struct hstate *hs;
|
|
|
|
if (vma->vm_end < next)
|
|
next = vma->vm_end;
|
|
hs = hstate_vma(vma);
|
|
pte = huge_pte_offset(walk->mm,
|
|
addr & huge_page_mask(hs));
|
|
if (pte && !huge_pte_none(huge_ptep_get(pte))
|
|
&& walk->hugetlb_entry)
|
|
err = walk->hugetlb_entry(pte, addr,
|
|
next, walk);
|
|
if (err)
|
|
break;
|
|
continue;
|
|
}
|
|
#endif
|
|
if (pgd_none_or_clear_bad(pgd)) {
|
|
if (walk->pte_hole)
|
|
err = walk->pte_hole(addr, next, walk);
|
|
if (err)
|
|
break;
|
|
pgd++;
|
|
continue;
|
|
}
|
|
if (walk->pgd_entry)
|
|
err = walk->pgd_entry(pgd, addr, next, walk);
|
|
if (!err &&
|
|
(walk->pud_entry || walk->pmd_entry || walk->pte_entry))
|
|
err = walk_pud_range(pgd, addr, next, walk);
|
|
if (err)
|
|
break;
|
|
pgd++;
|
|
} while (addr = next, addr != end);
|
|
|
|
return err;
|
|
}
|