Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph fixes from Sage Weil:
 "Two fixes.

  One is a stopgap to prevent a stack blowout when users have a deep
  chain of image clones.  (We'll rewrite this code to be non-recursive
  for the next window, but in the meantime this is a simple fix that
  avoids a crash.)

  The second fixes a refcount underflow"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  rbd: prevent kernel stack blow up on rbd map
  rbd: don't leak parent_spec in rbd_dev_probe_parent()

1 files changed, 39 insertions, 30 deletions

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index f5e49b6..6f26cf3 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -96,6 +96,8 @@ static int atomic_dec_return_safe(atomic_t *v)
 #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(struct bus_type *bus, const char *buf,
 				    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)
@@ -5131,44 +5133,51 @@ 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;
-	struct rbd_spec *parent_spec;
-	struct rbd_client *rbdc;
 	int ret;
 
 	if (!rbd_dev->parent_spec)
 		return 0;
-	/*
-	 * We need to pass a reference to the client and the parent
-	 * spec when creating the parent rbd_dev.  Images related by
-	 * parent/child relationships always share both.
-	 */
-	parent_spec = rbd_spec_get(rbd_dev->parent_spec);
-	rbdc = __rbd_get_client(rbd_dev->rbd_client);
 
-	ret = -ENOMEM;
-	parent = rbd_dev_create(rbdc, parent_spec, NULL);
-	if (!parent)
+	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) {
+		ret = -ENOMEM;
 		goto out_err;
+	}
+
+	/*
+	 * Images related by parent/child relationships always share
+	 * rbd_client and spec/parent_spec, so bump their refcounts.
+	 */
+	__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;
+
 	rbd_dev->parent = parent;
 	atomic_set(&rbd_dev->parent_ref, 1);
-
 	return 0;
+
 out_err:
-	if (parent) {
-		rbd_dev_unparent(rbd_dev);
+	rbd_dev_unparent(rbd_dev);
+	if (parent)
 		rbd_dev_destroy(parent);
-	} else {
-		rbd_put_client(rbdc);
-		rbd_spec_put(parent_spec);
-	}
-
 	return ret;
 }
 
@@ -5286,7 +5295,7 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
  * 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;
 
@@ -5304,7 +5313,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 	if (ret)
 		goto err_out_format;
 
-	if (mapping) {
+	if (!depth) {
 		ret = rbd_dev_header_watch_sync(rbd_dev);
 		if (ret) {
 			if (ret == -ENOENT)
@@ -5325,7 +5334,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 	 * 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);
@@ -5347,12 +5356,12 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 		 * 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;
 
@@ -5363,7 +5372,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
 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);
@@ -5426,7 +5435,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	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;