Commit d33b9f45 authored by Naoya Horiguchi's avatar Naoya Horiguchi Committed by Linus Torvalds

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: default avatarNaoya 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 4f16fc10
#include <linux/mm.h> #include <linux/mm.h>
#include <linux/highmem.h> #include <linux/highmem.h>
#include <linux/sched.h> #include <linux/sched.h>
#include <linux/hugetlb.h>
static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk) struct mm_walk *walk)
...@@ -107,6 +108,7 @@ int walk_page_range(unsigned long addr, unsigned long end, ...@@ -107,6 +108,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
pgd_t *pgd; pgd_t *pgd;
unsigned long next; unsigned long next;
int err = 0; int err = 0;
struct vm_area_struct *vma;
if (addr >= end) if (addr >= end)
return err; return err;
...@@ -117,11 +119,22 @@ int walk_page_range(unsigned long addr, unsigned long end, ...@@ -117,11 +119,22 @@ int walk_page_range(unsigned long addr, unsigned long end,
pgd = pgd_offset(walk->mm, addr); pgd = pgd_offset(walk->mm, addr);
do { do {
next = pgd_addr_end(addr, end); 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 (pgd_none_or_clear_bad(pgd)) {
if (walk->pte_hole) if (walk->pte_hole)
err = walk->pte_hole(addr, next, walk); err = walk->pte_hole(addr, next, walk);
if (err) if (err)
break; break;
pgd++;
continue; continue;
} }
if (walk->pgd_entry) if (walk->pgd_entry)
...@@ -131,7 +144,8 @@ int walk_page_range(unsigned long addr, unsigned long end, ...@@ -131,7 +144,8 @@ int walk_page_range(unsigned long addr, unsigned long end,
err = walk_pud_range(pgd, addr, next, walk); err = walk_pud_range(pgd, addr, next, walk);
if (err) if (err)
break; break;
} while (pgd++, addr = next, addr != end); pgd++;
} while (addr = next, addr != end);
return err; return err;
} }
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment