Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932558AbZLQBkP (ORCPT ); Wed, 16 Dec 2009 20:40:15 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1758317AbZLQBib (ORCPT ); Wed, 16 Dec 2009 20:38:31 -0500 Received: from kroah.org ([198.145.64.141]:47959 "EHLO coco.kroah.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763621AbZLQBUZ (ORCPT ); Wed, 16 Dec 2009 20:20:25 -0500 X-Mailbox-Line: From gregkh@mini.kroah.org Wed Dec 16 17:16:03 2009 Message-Id: <20091217011603.095665584@mini.kroah.org> User-Agent: quilt/0.48-1 Date: Wed, 16 Dec 2009 17:14:51 -0800 From: Greg KH To: linux-kernel@vger.kernel.org, stable@kernel.org Cc: stable-review@kernel.org, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, Naoya Horiguchi , Andi Kleen , Wu Fengguang , Hugh Dickins , Mel Gorman , Lee Schermerhorn , Andy Whitcroft , David Rientjes Subject: [40/90] mm: hugetlb: fix hugepage memory leak in walk_page_range() In-Reply-To: <20091217011835.GA20434@kroah.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3702 Lines: 127 2.6.31-stable review patch. If anyone has any objections, please let us know. ------------------ From: Naoya Horiguchi commit d33b9f45bd24a6391bc05e2b5a13c1b5787ca9c2 upstream. 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 Cc: Andi Kleen Cc: Wu Fengguang Cc: Hugh Dickins Cc: Mel Gorman Cc: Lee Schermerhorn Cc: Andy Whitcroft Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/pagewalk.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -1,6 +1,7 @@ #include #include #include +#include static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -107,6 +108,7 @@ int walk_page_range(unsigned long addr, pgd_t *pgd; unsigned long next; int err = 0; + struct vm_area_struct *vma; if (addr >= end) return err; @@ -117,11 +119,22 @@ int walk_page_range(unsigned long addr, 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) @@ -131,7 +144,8 @@ int walk_page_range(unsigned long addr, err = walk_pud_range(pgd, addr, next, walk); if (err) break; - } while (pgd++, addr = next, addr != end); + pgd++; + } while (addr = next, addr != end); return err; } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/