linux/mm/pagewalk.c
Naoya Horiguchi d33b9f45bd mm: hugetlb: fix hugepage memory leak in walk_page_range()
Most callers of pmd_none_or_clear_bad() check whether the target page is
in a hugepage or not, but walk_page_range() do not check it.  So if we
read /proc/pid/pagemap for the hugepage on x86 machine, the hugepage
memory is leaked as shown below.  This patch fixes it.

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 (walk around the page tables),
 - munmap() and unlink() the file on hugetlbfs

Without my patches
------------------
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ./leak_pagemap
[snip output]
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:      900
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ls /hugetlbfs/
$

100 hugepages are accounted as used while there is no file on hugetlbfs.

With my patches
---------------
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ./leak_pagemap
[snip output]
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ls /hugetlbfs
$

No memory leaks.

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>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 08:53:24 -08:00

152 lines
3.5 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);
/* skip hugetlb vma to avoid hugepage PMD being cleared
* in pmd_none_or_clear_bad(). */
vma = find_vma(walk->mm, addr);
if (vma && is_vm_hugetlb_page(vma)) {
if (vma->vm_end < next)
next = vma->vm_end;
continue;
}
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;
}