rbd: prevent kernel stack blow up on rbd map

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@gmail.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
[idryomov@gmail.com: backport to 3.14: rbd_dev->opts, context]
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 75446991946871f12f96151207d2815740769cf3..eb3dff3500c233a3fe0fc04a5eb0178193fe8e03 100644 (file)
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -94,6 +94,8 @@ 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))
@@ -411,7 +413,7 @@ 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)
@@ -4822,7 +4824,12 @@ 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;
@@ -4830,6 +4837,12 @@ 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);
        if (!parent) {
                ret = -ENOMEM;
@@ -4843,7 +4856,7 @@ 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;
 
@@ -4970,7 +4983,7 @@ 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;
 
@@ -4990,7 +5003,7 @@ 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)
                        goto out_header_name;
@@ -5007,7 +5020,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
        if (ret)
                goto err_out_probe;
 
-       ret = rbd_dev_probe_parent(rbd_dev);
+       ret = rbd_dev_probe_parent(rbd_dev, depth);
        if (ret)
                goto err_out_probe;
 
@@ -5018,7 +5031,7 @@ 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);
@@ -5085,7 +5098,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
        rbdc = NULL;            /* rbd_dev now owns this */
        spec = 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;