mm: validate_mm browse_rb SMP race condition

The mmap_sem for reading in validate_mm called from expand_stack is not
enough to prevent the argumented rbtree rb_subtree_gap information to
change from under us because expand_stack may be running from other
threads concurrently which will hold the mmap_sem for reading too.

The argumented rbtree is updated with vma_gap_update under the
page_table_lock so use it in browse_rb() too to avoid false positives.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 2 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index cfc0cdc..918c9ec 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -390,8 +390,9 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma)
 }
 
 #ifdef CONFIG_DEBUG_VM_RB
-static int browse_rb(struct rb_root *root)
+static int browse_rb(struct mm_struct *mm)
 {
+	struct rb_root *root = &mm->mm_rb;
 	int i = 0, j, bug = 0;
 	struct rb_node *nd, *pn = NULL;
 	unsigned long prev = 0, pend = 0;
@@ -414,12 +415,14 @@ static int browse_rb(struct rb_root *root)
 				  vma->vm_start, vma->vm_end);
 			bug = 1;
 		}
+		spin_lock(&mm->page_table_lock);
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
 			pr_emerg("free gap %lx, correct %lx\n",
 			       vma->rb_subtree_gap,
 			       vma_compute_subtree_gap(vma));
 			bug = 1;
 		}
+		spin_unlock(&mm->page_table_lock);
 		i++;
 		pn = nd;
 		prev = vma->vm_start;
@@ -475,7 +478,7 @@ static void validate_mm(struct mm_struct *mm)
 			  mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
-	i = browse_rb(&mm->mm_rb);
+	i = browse_rb(mm);
 	if (i != mm->map_count) {
 		if (i != -1)
 			pr_emerg("map_count %d rb %d\n", mm->map_count, i);