[ 3.5.y.z extended stable ] Patch "mm: prevent mmap_cache race in find_vma()" has been added to staging queue

[Luis Henriques]

This is a note to let you know that I have just added a patch titled

    mm: prevent mmap_cache race in find_vma()

to the linux-3.5.y-queue branch of the 3.5.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.5.y-queue

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.5.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Luis

------

>From 96ad26ddebee1acf3b75a096c855b02e48bc1ca9 Mon Sep 17 00:00:00 2001
From: Jan Stancek <jstancek at redhat.com>
Date: Thu, 4 Apr 2013 11:35:10 -0700
Subject: [PATCH] mm: prevent mmap_cache race in find_vma()

commit b6a9b7f6b1f21735a7456d534dc0e68e61359d2c upstream.

find_vma() can be called by multiple threads with read lock
held on mm->mmap_sem and any of them can update mm->mmap_cache.
Prevent compiler from re-fetching mm->mmap_cache, because other
readers could update it in the meantime:

               thread 1                             thread 2
                                        |
  find_vma()                            |  find_vma()
    struct vm_area_struct *vma = NULL;  |
    vma = mm->mmap_cache;               |
    if (!(vma && vma->vm_end > addr     |
        && vma->vm_start <= addr)) {    |
                                        |    mm->mmap_cache = vma;
    return vma;                         |
     ^^ compiler may optimize this      |
        local variable out and re-read  |
        mm->mmap_cache                  |

This issue can be reproduced with gcc-4.8.0-1 on s390x by running
mallocstress testcase from LTP, which triggers:

  kernel BUG at mm/rmap.c:1088!
    Call Trace:
     ([<000003d100c57000>] 0x3d100c57000)
      [<000000000023a1c0>] do_wp_page+0x2fc/0xa88
      [<000000000023baae>] handle_pte_fault+0x41a/0xac8
      [<000000000023d832>] handle_mm_fault+0x17a/0x268
      [<000000000060507a>] do_protection_exception+0x1e2/0x394
      [<0000000000603a04>] pgm_check_handler+0x138/0x13c
      [<000003fffcf1f07a>] 0x3fffcf1f07a
    Last Breaking-Event-Address:
      [<000000000024755e>] page_add_new_anon_rmap+0xc2/0x168

Thanks to Jakub Jelinek for his insight on gcc and helping to
track this down.

Signed-off-by: Jan Stancek <jstancek at redhat.com>
Acked-by: David Rientjes <rientjes at google.com>
Signed-off-by: Hugh Dickins <hughd at google.com>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 mm/mmap.c  | 2 +-
 mm/nommu.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/mmap.c b/mm/mmap.c
index fa1f274..5603d88 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1610,7 +1610,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)

 	/* Check the cache first. */
 	/* (Cache hit rate is typically around 35%.) */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
 		struct rb_node *rb_node;

diff --git a/mm/nommu.c b/mm/nommu.c
index d4b0c10..a60db99 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -807,7 +807,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;

 	/* check the cache first */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
 		return vma;

--
1.8.1.2