[PATCH v2 2/3] md-cluster: propagate update_size() errors to callers

[ghuicao]

From: Cao Guanghui <caoguanghui@xxxxxxxxxx>

update_size() in md-cluster.c has a void return type, so the caller in
md.c cannot detect cluster resize failures.  A capacity revert or
message delivery failure is silently lost, and the MD layer reports
success to userspace even when the cluster operation failed.

Change the update_size() callback in struct md_cluster_ops and its
implementation to return int, and propagate the error at the call sites
in md.c.

Fixes: 818da59f97d6 ("md-cluster: add the support for resize")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Cao Guanghui <caoguanghui@xxxxxxxxxx>
---
 drivers/md/md-cluster.c | 11 ++++++-----
 drivers/md/md-cluster.h |  2 +-
 drivers/md/md.c        |  7 +++++--
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1292,7 +1292,7 @@ static int cluster_check_sync_size(struct mddev *mddev)
  *    let other nodes to perform it. If one node can't update sync_size
  *    accordingly, we need to revert to previous value.
  */
-static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
+static int update_size(struct mddev *mddev, sector_t old_dev_sectors)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	struct cluster_msg cmsg;
@@ -1303,7 +1303,7 @@ static int update_size(struct mddev *mddev, sector_t old_dev_sectors)
 	md_update_sb(mddev, 1);
 	if (lock_comm(cinfo, 1)) {
 		pr_err("%s: lock_comm failed\n", __func__);
-		return;
+		return -1;
 	}
 
 	memset(&cmsg, 0, sizeof(cmsg));
@@ -1325,12 +1325,12 @@ static int update_size(struct mddev *mddev, sector_t old_dev_sectors)
 			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
 			       __func__, __LINE__);
 			unlock_comm(cinfo);
-			return;
+			return ret;
 		}
 	} else {
 		pr_err("md-cluster: No good device id found to send\n");
 		unlock_comm(cinfo);
-		return;
+		return -1;
 	}
 
 	/*
@@ -1355,6 +1355,7 @@ static int update_size(struct mddev *mddev, sector_t old_dev_sectors)
 			       __func__, __LINE__);
 	}
 	unlock_comm(cinfo);
+	return ret;
 }
 
 static int resync_start(struct mddev *mddev)
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -34,7 +34,7 @@ struct md_cluster_operations {
 	int (*resize_bitmaps)(struct mddev *mddev, sector_t newsize, sector_t oldsize);
 	int (*lock_all_bitmaps)(struct mddev *mddev);
 	void (*unlock_all_bitmaps)(struct mddev *mddev);
-	void (*update_size)(struct mddev *mddev, sector_t old_dev_sectors);
+	int (*update_size)(struct mddev *mddev, sector_t old_dev_sectors);
 };
 
 extern int md_setup_cluster(struct mddev *mddev, int nodes);
diff --git a/drivers/md/md.c b/drivers/md/md.c
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8023,7 +8023,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	rv = mddev->pers->resize(mddev, num_sectors);
 	if (!rv) {
 		if (mddev_is_clustered(mddev))
-			mddev->cluster_ops->update_size(mddev, old_dev_sectors);
+			rv = mddev->cluster_ops->update_size(mddev, old_dev_sectors);
 		else if (!mddev_is_dm(mddev))
 			set_capacity_and_notify(mddev->gendisk,
 						mddev->array_sectors);
@@ -10615,8 +10615,12 @@ void md_reap_sync_thread(struct mddev *mddev)
 	 */
 	if (mddev_is_clustered(mddev) && is_reshaped &&
 	    mddev->pers->finish_reshape &&
-	    !test_bit(MD_CLOSING, &mddev->flags))
-		mddev->cluster_ops->update_size(mddev, old_dev_sectors);
+	    !test_bit(MD_CLOSING, &mddev->flags)) {
+		int ret = mddev->cluster_ops->update_size(mddev, old_dev_sectors);
+
+		if (ret)
+			pr_warn("md: cluster update_size failed after reshape: %d\n", ret);
+	}
 	/* flag recovery needed just to double check */
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	sysfs_notify_dirent_safe(mddev->sysfs_completed);
-- 
2.34.1