tcmur_device: add priv lock support

When the tcmu-runner detect that the lock is lost, it will try to
queue a work event to reopen the image and at the same time queue
a work event to update the service status. While the reopen is not
atomic, and there has a gap between image close and image open,
during which the rbd image's state resource will be released and if
the update status event is fired, we will hit the crash bug.

This commit will add one rdev->priv_lock to protect the private data
in rdev struct. For the service status updating code just skip it
if it's in the reopen gap. And for all the other IOs just return
EBUSY to let the client try it again.

Signed-off-by: Xiubo Li <[email protected]>

main.c

@@ -1020,12 +1020,18 @@ static int dev_added(struct tcmu_device *dev)
 	tcmu_dev_dbg(dev, "Got block_size %d, size in bytes %"PRId64"\n",
 		     block_size, dev_size);
 
-	ret = pthread_spin_init(&rdev->cmds_list_lock, 0);
+	ret = pthread_mutex_init(&rdev->priv_lock, NULL);
 	if (ret) {
 		ret = -ret;
 		goto free_rdev;
 	}
 
+	ret = pthread_spin_init(&rdev->cmds_list_lock, 0);
+	if (ret) {
+		ret = -ret;
+		goto cleanup_priv_lock;
+	}
+
 	ret = pthread_mutex_init(&rdev->caw_lock, NULL);
 	if (ret) {
 		ret = -ret;
@@ -1096,6 +1102,8 @@ static int dev_added(struct tcmu_device *dev)
 	pthread_mutex_destroy(&rdev->caw_lock);
 cleanup_dev_lock:
 	pthread_spin_destroy(&rdev->cmds_list_lock);
+cleanup_priv_lock:
+	pthread_mutex_destroy(&rdev->priv_lock);
 free_rdev:
 	free(rdev);
 	return ret;
@@ -1146,6 +1154,10 @@ static void dev_removed(struct tcmu_device *dev)
 	if (ret != 0)
 		tcmu_err("could not cleanup mailbox lock %d\n", ret);
 
+	ret = pthread_mutex_destroy(&rdev->priv_lock);
+	if (ret != 0)
+		tcmu_err("could not cleanup priv lock %d\n", ret);
+
 	free(rdev);
 
 	tcmu_dev_dbg(dev, "removed from tcmu-runner\n");