summaryrefslogtreecommitdiff
path: root/mm/mincore.c
diff options
context:
space:
mode:
authorNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>2009-12-14 17:59:58 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-15 08:53:24 -0800
commit4f16fc107d9c9b8a72aa19b189a9216e90a7aaef (patch)
tree7d2cd426ab80a30d3fc7584605738ad39a8b24be /mm/mincore.c
parent536240f2bde98216feac87b4891d19a536b8884a (diff)
downloadlwn-4f16fc107d9c9b8a72aa19b189a9216e90a7aaef.tar.gz
lwn-4f16fc107d9c9b8a72aa19b189a9216e90a7aaef.zip
mm: hugetlb: fix hugepage memory leak in mincore()
Most callers of pmd_none_or_clear_bad() check whether the target page is in a hugepage or not, but mincore() and walk_page_range() do not check it. So if we use mincore() on a hugepage on x86 machine, the hugepage memory is leaked as shown below. This patch fixes it by extending mincore() system call to support hugepages. Details ======= My test program (leak_mincore) works as follows: - creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,) - read()/write() something on it, - call mincore() for first ten pages and printf() the values of *vec - munmap() and unlink() the file on hugetlbfs Without my patch ---------------- $ cat /proc/meminfo| grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ./leak_mincore vec[0] 0 vec[1] 0 vec[2] 0 vec[3] 0 vec[4] 0 vec[5] 0 vec[6] 0 vec[7] 0 vec[8] 0 vec[9] 0 $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 999 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ls /hugetlbfs/ $ Return values in *vec from mincore() are set to 0, while the hugepage should be in memory, and 1 hugepage is still accounted as used while there is no file on hugetlbfs. With my patch ------------- $ cat /proc/meminfo| grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ./leak_mincore vec[0] 1 vec[1] 1 vec[2] 1 vec[3] 1 vec[4] 1 vec[5] 1 vec[6] 1 vec[7] 1 vec[8] 1 vec[9] 1 $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ls /hugetlbfs/ $ Return value in *vec set to 1 and no memory leaks. [akpm@linux-foundation.org: cleanup] [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> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mincore.c')
-rw-r--r--mm/mincore.c37
1 files changed, 37 insertions, 0 deletions
diff --git a/mm/mincore.c b/mm/mincore.c
index 8cb508f84ea4..7a3436ef39eb 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -14,6 +14,7 @@
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/hugetlb.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -72,6 +73,42 @@ static long do_mincore(unsigned long addr, unsigned char *vec, unsigned long pag
if (!vma || addr < vma->vm_start)
return -ENOMEM;
+#ifdef CONFIG_HUGETLB_PAGE
+ if (is_vm_hugetlb_page(vma)) {
+ struct hstate *h;
+ unsigned long nr_huge;
+ unsigned char present;
+
+ i = 0;
+ nr = min(pages, (vma->vm_end - addr) >> PAGE_SHIFT);
+ h = hstate_vma(vma);
+ nr_huge = ((addr + pages * PAGE_SIZE - 1) >> huge_page_shift(h))
+ - (addr >> huge_page_shift(h)) + 1;
+ nr_huge = min(nr_huge,
+ (vma->vm_end - addr) >> huge_page_shift(h));
+ while (1) {
+ /* hugepage always in RAM for now,
+ * but generally it needs to be check */
+ ptep = huge_pte_offset(current->mm,
+ addr & huge_page_mask(h));
+ present = !!(ptep &&
+ !huge_pte_none(huge_ptep_get(ptep)));
+ while (1) {
+ vec[i++] = present;
+ addr += PAGE_SIZE;
+ /* reach buffer limit */
+ if (i == nr)
+ return nr;
+ /* check hugepage border */
+ if (!((addr & ~huge_page_mask(h))
+ >> PAGE_SHIFT))
+ break;
+ }
+ }
+ return nr;
+ }
+#endif
+
/*
* Calculate how many pages there are left in the last level of the
* PTE array for our address.