md-cluster: gather resync infos and enable recv_thread after bitmap is ready

The in-memory bitmap is not ready when node joins cluster,
so it doesn't make sense to make gather_all_resync_info()
called so earlier, we need to call it after the node's
bitmap is setup. Also, recv_thread could be wake up after
node joins cluster, but it could cause problem if node
receives RESYNCING message without persionality since
mddev->pers->quiesce is called in process_suspend_info.

This commit introduces a new cluster interface load_bitmaps
to fix above problems, load_bitmaps is called in bitmap_load
where bitmap and persionality are ready, and load_bitmaps
does the following tasks:

1. call gather_all_resync_info to load all the node's
   bitmap info.
2. set MD_CLUSTER_ALREADY_IN_CLUSTER bit to recv_thread
   could be wake up, and wake up recv_thread if there is
   pending recv event.

Then ack_bast only wakes up recv_thread after IN_CLUSTER
bit is ready otherwise MD_CLUSTER_PENDING_RESYNC_EVENT is
set.

Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>

3 files changed, 28 insertions, 6 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index ad5a85847004..d8129ec93ebd 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1848,6 +1848,9 @@ int bitmap_load(struct mddev *mddev)
 	if (!bitmap)
 		goto out;
 
+	if (mddev_is_clustered(mddev))
+		md_cluster_ops->load_bitmaps(mddev, mddev->bitmap_info.nodes);
+
 	/* Clear out old bitmap info first:  Either there is none, or we
 	 * are resuming after someone else has possibly changed things,
 	 * so we should forget old cached info.
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index a55b5f4d0dbe..bef6a47b443f 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -61,6 +61,10 @@ struct resync_info {
  * the lock.
  */
 #define		MD_CLUSTER_SEND_LOCKED_ALREADY		5
+/* We should receive message after node joined cluster and
+ * set up all the related infos such as bitmap and personality */
+#define		MD_CLUSTER_ALREADY_IN_CLUSTER		6
+#define		MD_CLUSTER_PENDING_RECV_EVENT		7
 
 
 struct md_cluster_info {
@@ -376,8 +380,12 @@ static void ack_bast(void *arg, int mode)
 	struct dlm_lock_resource *res = arg;
 	struct md_cluster_info *cinfo = res->mddev->cluster_info;
 
-	if (mode == DLM_LOCK_EX)
-		md_wakeup_thread(cinfo->recv_thread);
+	if (mode == DLM_LOCK_EX) {
+		if (test_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state))
+			md_wakeup_thread(cinfo->recv_thread);
+		else
+			set_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state);
+	}
 }
 
 static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot)
@@ -846,10 +854,6 @@ static int join(struct mddev *mddev, int nodes)
 	if (!cinfo->resync_lockres)
 		goto err;
 
-	ret = gather_all_resync_info(mddev, nodes);
-	if (ret)
-		goto err;
-
 	return 0;
 err:
 	md_unregister_thread(&cinfo->recovery_thread);
@@ -867,6 +871,19 @@ err:
 	return ret;
 }
 
+static void load_bitmaps(struct mddev *mddev, int total_slots)
+{
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+
+	/* load all the node's bitmap info for resync */
+	if (gather_all_resync_info(mddev, total_slots))
+		pr_err("md-cluster: failed to gather all resyn infos\n");
+	set_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state);
+	/* wake up recv thread in case something need to be handled */
+	if (test_and_clear_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state))
+		md_wakeup_thread(cinfo->recv_thread);
+}
+
 static void resync_bitmap(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
@@ -1208,6 +1225,7 @@ static struct md_cluster_operations cluster_ops = {
 	.add_new_disk_cancel = add_new_disk_cancel,
 	.new_disk_ack = new_disk_ack,
 	.remove_disk = remove_disk,
+	.load_bitmaps = load_bitmaps,
 	.gather_bitmaps = gather_bitmaps,
 	.lock_all_bitmaps = lock_all_bitmaps,
 	.unlock_all_bitmaps = unlock_all_bitmaps,
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index 45ce6c97d8bd..e765499ba591 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -23,6 +23,7 @@ struct md_cluster_operations {
 	void (*add_new_disk_cancel)(struct mddev *mddev);
 	int (*new_disk_ack)(struct mddev *mddev, bool ack);
 	int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
+	void (*load_bitmaps)(struct mddev *mddev, int total_slots);
 	int (*gather_bitmaps)(struct md_rdev *rdev);
 	int (*lock_all_bitmaps)(struct mddev *mddev);
 	void (*unlock_all_bitmaps)(struct mddev *mddev);