rbd: prevent kernel stack blow up on rbd map

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
Cc: stable@vger.kernel.org # 3.10+, needs backporting for < 4.2
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 028db28cb8a06f732a13bcedde2783514ee9e7ae..6f26cf38c6f9c732bfa3293c1b129919a6e245f3 100644 (file)
--- 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)
@@ -5131,7 +5133,12 @@ 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;
@@ -5139,6 +5146,12 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
        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) {
@@ -5153,7 +5166,7 @@ static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
        __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;
 
@@ -5282,7 +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;
 
@@ -5300,7 +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)
@@ -5321,7 +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);
@@ -5343,12 +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;
 
@@ -5359,7 +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);
@@ -5422,7 +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;