[PATCH 1/2] mm,migration: Prevent rmap_walk_[anon|ksm] seeing the wrong VMA information

[Mel Gorman]

vma_adjust() is updating anon VMA information without locks being taken.
In contrast, file-backed mappings use the i_mmap_lock and this lack of
locking can result in races with users of rmap_walk such as page migration.
vma_address() can return -EFAULT for an address that will soon be valid.
For migration, this potentially leaves a dangling migration PTE behind
which can later cause a BUG_ON to trigger when the page is faulted in.

With the recent anon_vma changes, there can be more than one anon_vma->lock
to take in a anon_vma_chain but a second lock cannot be spinned upon in case
of deadlock. The rmap walker tries to take locks of different anon_vma's
but if the attempt fails, locks are released and the operation is restarted.

For vma_adjust(), the locking behaviour prior to the anon_vma is restored
so that rmap_walk() can be sure of the integrity of the VMA information and
lists when the anon_vma lock is held. With this patch, the vma->anon_vma->lock
is taken if

	a) If there is any overlap with the next VMA due to the adjustment
	b) If there is a new VMA is being inserted into the address space
	c) If the start of the VMA is being changed so that the
	   relationship between vm_start and vm_pgoff is preserved
	   for vma_address()

Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
---
 mm/ksm.c  |   22 ++++++++++++++++++++--
 mm/mmap.c |    9 +++++++++
 mm/rmap.c |   28 +++++++++++++++++++++++-----
 3 files changed, 52 insertions(+), 7 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c
index 3666d43..0c09927 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1668,15 +1668,28 @@ int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
 again:
 	hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) {
 		struct anon_vma *anon_vma = rmap_item->anon_vma;
+		struct anon_vma *locked_vma;
 		struct anon_vma_chain *vmac;
 		struct vm_area_struct *vma;
 
 		spin_lock(&anon_vma->lock);
 		list_for_each_entry(vmac, &anon_vma->head, same_anon_vma) {
 			vma = vmac->vma;
+
+			/* See comment in mm/rmap.c#rmap_walk_anon on locking */
+			locked_vma = NULL;
+			if (anon_vma != vma->anon_vma) {
+				locked_vma = vma->anon_vma;
+				if (!spin_trylock(&locked_vma->lock)) {
+					spin_unlock(&anon_vma->lock);
+					goto again;
+				}
+			}
+
 			if (rmap_item->address < vma->vm_start ||
 			    rmap_item->address >= vma->vm_end)
-				continue;
+				goto next_vma;
+
 			/*
 			 * Initially we examine only the vma which covers this
 			 * rmap_item; but later, if there is still work to do,
@@ -1684,9 +1697,14 @@ again:
 			 * were forked from the original since ksmd passed.
 			 */
 			if ((rmap_item->mm == vma->vm_mm) == search_new_forks)
-				continue;
+				goto next_vma;
 
 			ret = rmap_one(page, vma, rmap_item->address, arg);
+
+next_vma:
+			if (locked_vma)
+				spin_unlock(&locked_vma->lock);
+
 			if (ret != SWAP_AGAIN) {
 				spin_unlock(&anon_vma->lock);
 				goto out;
diff --git a/mm/mmap.c b/mm/mmap.c
index f90ea92..d635132 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -505,6 +505,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	struct vm_area_struct *next = vma->vm_next;
 	struct vm_area_struct *importer = NULL;
 	struct address_space *mapping = NULL;
+	struct anon_vma *anon_vma = NULL;
 	struct prio_tree_root *root = NULL;
 	struct file *file = vma->vm_file;
 	long adjust_next = 0;
@@ -578,6 +579,11 @@ again:			remove_next = 1 + (end > next->vm_end);
 		}
 	}
 
+	if (vma->anon_vma && (insert || importer || start != vma->vm_start)) {
+		anon_vma = vma->anon_vma;
+		spin_lock(&anon_vma->lock);
+	}
+
 	if (root) {
 		flush_dcache_mmap_lock(mapping);
 		vma_prio_tree_remove(vma, root);
@@ -620,6 +626,9 @@ again:			remove_next = 1 + (end > next->vm_end);
 	if (mapping)
 		spin_unlock(&mapping->i_mmap_lock);
 
+	if (anon_vma)
+		spin_unlock(&anon_vma->lock);
+
 	if (remove_next) {
 		if (file) {
 			fput(file);
diff --git a/mm/rmap.c b/mm/rmap.c
index 85f203e..f7ed89f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1358,7 +1358,7 @@ int try_to_munlock(struct page *page)
 static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
 		struct vm_area_struct *, unsigned long, void *), void *arg)
 {
-	struct anon_vma *anon_vma;
+	struct anon_vma *anon_vma, *locked_vma;
 	struct anon_vma_chain *avc;
 	int ret = SWAP_AGAIN;
 
@@ -1368,16 +1368,34 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
 	 * are holding mmap_sem. Users without mmap_sem are required to
 	 * take a reference count to prevent the anon_vma disappearing
 	 */
+retry:
 	anon_vma = page_anon_vma(page);
 	if (!anon_vma)
 		return ret;
 	spin_lock(&anon_vma->lock);
 	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
 		struct vm_area_struct *vma = avc->vma;
-		unsigned long address = vma_address(page, vma);
-		if (address == -EFAULT)
-			continue;
-		ret = rmap_one(page, vma, address, arg);
+		unsigned long address;
+
+		/*
+		 * Guard against deadlocks by not spinning against
+		 * vma->anon_vma->lock. On contention release and retry
+		 */
+		locked_vma = NULL;
+		if (anon_vma != vma->anon_vma) {
+			locked_vma = vma->anon_vma;
+			if (!spin_trylock(&locked_vma->lock)) {
+				spin_unlock(&anon_vma->lock);
+				goto retry;
+			}
+		}
+		address = vma_address(page, vma);
+		if (address != -EFAULT)
+			ret = rmap_one(page, vma, address, arg);
+
+		if (locked_vma)
+			spin_unlock(&locked_vma->lock);
+
 		if (ret != SWAP_AGAIN)
 			break;
 	}
-- 
1.6.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/