Merge tag 'ceph-for-5.7-rc2' of git://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:

 - a set of patches for a deadlock on "rbd map" error path

 - a fix for invalid pointer dereference and uninitialized variable use
   on asynchronous create and unlink error paths.

* tag 'ceph-for-5.7-rc2' of git://github.com/ceph/ceph-client:
  ceph: fix potential bad pointer deref in async dirops cb's
  rbd: don't mess with a page vector in rbd_notify_op_lock()
  rbd: don't test rbd_dev->opts in rbd_dev_image_release()
  rbd: call rbd_dev_unprobe() after unwatching and flushing notifies
  rbd: avoid a deadlock on header_rwsem when flushing notifies

1 files changed, 19 insertions, 14 deletions

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 1e0a6b19ae0d..67d65ac785e9 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3754,11 +3754,7 @@ static int __rbd_notify_op_lock(struct rbd_device *rbd_dev,
 static void rbd_notify_op_lock(struct rbd_device *rbd_dev,
 			       enum rbd_notify_op notify_op)
 {
-	struct page **reply_pages;
-	size_t reply_len;
-
-	__rbd_notify_op_lock(rbd_dev, notify_op, &reply_pages, &reply_len);
-	ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len));
+	__rbd_notify_op_lock(rbd_dev, notify_op, NULL, NULL);
 }
 
 static void rbd_notify_acquired_lock(struct work_struct *work)
@@ -4527,6 +4523,10 @@ static void cancel_tasks_sync(struct rbd_device *rbd_dev)
 	cancel_work_sync(&rbd_dev->unlock_work);
 }
 
+/*
+ * header_rwsem must not be held to avoid a deadlock with
+ * rbd_dev_refresh() when flushing notifies.
+ */
 static void rbd_unregister_watch(struct rbd_device *rbd_dev)
 {
 	cancel_tasks_sync(rbd_dev);
@@ -6894,9 +6894,10 @@ static void rbd_print_dne(struct rbd_device *rbd_dev, bool is_snap)
 
 static void rbd_dev_image_release(struct rbd_device *rbd_dev)
 {
-	rbd_dev_unprobe(rbd_dev);
-	if (rbd_dev->opts)
+	if (!rbd_is_ro(rbd_dev))
 		rbd_unregister_watch(rbd_dev);
+
+	rbd_dev_unprobe(rbd_dev);
 	rbd_dev->image_format = 0;
 	kfree(rbd_dev->spec->image_id);
 	rbd_dev->spec->image_id = NULL;
@@ -6907,6 +6908,9 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
  * device.  If this image is the one being mapped (i.e., not a
  * parent), initiate a watch on its header object before using that
  * object to get detailed information about the rbd image.
+ *
+ * On success, returns with header_rwsem held for write if called
+ * with @depth == 0.
  */
 static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 {
@@ -6936,11 +6940,14 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 		}
 	}
 
+	if (!depth)
+		down_write(&rbd_dev->header_rwsem);
+
 	ret = rbd_dev_header_info(rbd_dev);
 	if (ret) {
 		if (ret == -ENOENT && !need_watch)
 			rbd_print_dne(rbd_dev, false);
-		goto err_out_watch;
+		goto err_out_probe;
 	}
 
 	/*
@@ -6985,10 +6992,11 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
 	return 0;
 
 err_out_probe:
-	rbd_dev_unprobe(rbd_dev);
-err_out_watch:
+	if (!depth)
+		up_write(&rbd_dev->header_rwsem);
 	if (need_watch)
 		rbd_unregister_watch(rbd_dev);
+	rbd_dev_unprobe(rbd_dev);
 err_out_format:
 	rbd_dev->image_format = 0;
 	kfree(rbd_dev->spec->image_id);
@@ -7050,12 +7058,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 		goto err_out_rbd_dev;
 	}
 
-	down_write(&rbd_dev->header_rwsem);
 	rc = rbd_dev_image_probe(rbd_dev, 0);
-	if (rc < 0) {
-		up_write(&rbd_dev->header_rwsem);
+	if (rc < 0)
 		goto err_out_rbd_dev;
-	}
 
 	if (rbd_dev->opts->alloc_size > rbd_dev->layout.object_size) {
 		rbd_warn(rbd_dev, "alloc_size adjusted to %u",