[PATCH 4.2 052/110] rbd: prevent kernel stack blow up on rbd map

[Greg Kroah-Hartman]

4.2-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ilya Dryomov <idryomov@xxxxxxxxx>

commit 6d69bb536bac0d403d83db1ca841444981b280cd upstream.

Mapping an image with a long parent chain (e.g. image foo, whose parent
is bar, whose parent is baz, etc) currently leads to a kernel stack
overflow, due to the following recursion in the reply path:

  rbd_osd_req_callback()
    rbd_obj_request_complete()
      rbd_img_obj_callback()
        rbd_img_parent_read_callback()
          rbd_obj_request_complete()
            ...

Limit the parent chain to 16 images, which is ~5K worth of stack.  When
the above recursion is eliminated, this limit can be lifted.

Fixes: http://tracker.ceph.com/issues/12538

Signed-off-by: Ilya Dryomov <idryomov@xxxxxxxxx>
Reviewed-by: Josh Durgin <jdurgin@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 drivers/block/rbd.c |   33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -96,6 +96,8 @@ static int atomic_dec_return_safe(atomic
 #define RBD_MINORS_PER_MAJOR		256
 #define RBD_SINGLE_MAJOR_PART_SHIFT	4
 
+#define RBD_MAX_PARENT_CHAIN_LEN	16
+
 #define RBD_SNAP_DEV_NAME_PREFIX	"snap_"
 #define RBD_MAX_SNAP_NAME_LEN	\
 			(NAME_MAX - (sizeof (RBD_SNAP_DEV_NAME_PREFIX) - 1))
@@ -426,7 +428,7 @@ static ssize_t rbd_add_single_major(stru
 				    size_t count);
 static ssize_t rbd_remove_single_major(struct bus_type *bus, const char *buf,
 				       size_t count);
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth);
 static void rbd_spec_put(struct rbd_spec *spec);
 
 static int rbd_dev_id_to_minor(int dev_id)
@@ -5172,7 +5174,12 @@ out_err:
 	return ret;
 }
 
-static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
+/*
+ * @depth is rbd_dev_image_probe() -> rbd_dev_probe_parent() ->
+ * rbd_dev_image_probe() recursion depth, which means it's also the
+ * length of the already discovered part of the parent chain.
+ */
+static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth)
 {
 	struct rbd_device *parent = NULL;
 	int ret;
@@ -5180,6 +5187,12 @@ static int rbd_dev_probe_parent(struct r
 	if (!rbd_dev->parent_spec)
 		return 0;
 
+	if (++depth > RBD_MAX_PARENT_CHAIN_LEN) {
+		pr_info("parent chain is too long (%d)\n", depth);
+		ret = -EINVAL;
+		goto out_err;
+	}
+
 	parent = rbd_dev_create(rbd_dev->rbd_client, rbd_dev->parent_spec,
 				NULL);
 	if (!parent) {
@@ -5194,7 +5207,7 @@ static int rbd_dev_probe_parent(struct r
 	__rbd_get_client(rbd_dev->rbd_client);
 	rbd_spec_get(rbd_dev->parent_spec);
 
-	ret = rbd_dev_image_probe(parent, false);
+	ret = rbd_dev_image_probe(parent, depth);
 	if (ret < 0)
 		goto out_err;
 
@@ -5323,7 +5336,7 @@ static void rbd_dev_image_release(struct
  * parent), initiate a watch on its header object before using that
  * object to get detailed information about the rbd image.
  */
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 {
 	int ret;
 
@@ -5341,7 +5354,7 @@ static int rbd_dev_image_probe(struct rb
 	if (ret)
 		goto err_out_format;
 
-	if (mapping) {
+	if (!depth) {
 		ret = rbd_dev_header_watch_sync(rbd_dev);
 		if (ret) {
 			if (ret == -ENOENT)
@@ -5362,7 +5375,7 @@ static int rbd_dev_image_probe(struct rb
 	 * Otherwise this is a parent image, identified by pool, image
 	 * and snap ids - need to fill in names for those ids.
 	 */
-	if (mapping)
+	if (!depth)
 		ret = rbd_spec_fill_snap_id(rbd_dev);
 	else
 		ret = rbd_spec_fill_names(rbd_dev);
@@ -5384,12 +5397,12 @@ static int rbd_dev_image_probe(struct rb
 		 * Need to warn users if this image is the one being
 		 * mapped and has a parent.
 		 */
-		if (mapping && rbd_dev->parent_spec)
+		if (!depth && rbd_dev->parent_spec)
 			rbd_warn(rbd_dev,
 				 "WARNING: kernel layering is EXPERIMENTAL!");
 	}
 
-	ret = rbd_dev_probe_parent(rbd_dev);
+	ret = rbd_dev_probe_parent(rbd_dev, depth);
 	if (ret)
 		goto err_out_probe;
 
@@ -5400,7 +5413,7 @@ static int rbd_dev_image_probe(struct rb
 err_out_probe:
 	rbd_dev_unprobe(rbd_dev);
 err_out_watch:
-	if (mapping)
+	if (!depth)
 		rbd_dev_header_unwatch_sync(rbd_dev);
 out_header_name:
 	kfree(rbd_dev->header_name);
@@ -5463,7 +5476,7 @@ static ssize_t do_rbd_add(struct bus_typ
 	spec = NULL;		/* rbd_dev now owns this */
 	rbd_opts = NULL;	/* rbd_dev now owns this */
 
-	rc = rbd_dev_image_probe(rbd_dev, true);
+	rc = rbd_dev_image_probe(rbd_dev, 0);
 	if (rc < 0)
 		goto err_out_rbd_dev;
 


--
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/