mm: fix the racy mm->locked_vm change in

"mm->locked_vm += grow" and vm_stat_account() in acct_stack_growth() are
not safe; multiple threads using the same ->mm can do this at the same
time trying to expans different vma's under down_read(mmap_sem).  This
means that one of the "locked_vm += grow" changes can be lost and we can
miss munlock_vma_pages_all() later.

Move this code into the caller(s) under mm->page_table_lock.  All other
updates to ->locked_vm hold mmap_sem for writing.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mmap.c b/mm/mmap.c
index 3ec19b601be057574f72c7145ad0b4abef40330d..d1ac22485998ba6c2a5a5181280f80e4f17ef50b 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2138,10 +2138,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
        if (security_vm_enough_memory_mm(mm, grow))
                return -ENOMEM;
 
-       /* Ok, everything looks good - let it rip */
-       if (vma->vm_flags & VM_LOCKED)
-               mm->locked_vm += grow;
-       vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
        return 0;
 }
 
@@ -2202,6 +2198,10 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
                                 * against concurrent vma expansions.
                                 */
                                spin_lock(&vma->vm_mm->page_table_lock);
+                               if (vma->vm_flags & VM_LOCKED)
+                                       vma->vm_mm->locked_vm += grow;
+                               vm_stat_account(vma->vm_mm, vma->vm_flags,
+                                               vma->vm_file, grow);
                                anon_vma_interval_tree_pre_update_vma(vma);
                                vma->vm_end = address;
                                anon_vma_interval_tree_post_update_vma(vma);
@@ -2273,6 +2273,10 @@ int expand_downwards(struct vm_area_struct *vma,
                                 * against concurrent vma expansions.
                                 */
                                spin_lock(&vma->vm_mm->page_table_lock);
+                               if (vma->vm_flags & VM_LOCKED)
+                                       vma->vm_mm->locked_vm += grow;
+                               vm_stat_account(vma->vm_mm, vma->vm_flags,
+                                               vma->vm_file, grow);
                                anon_vma_interval_tree_pre_update_vma(vma);
                                vma->vm_start = address;
                                vma->vm_pgoff -= grow;