From 7c9d5c54fb72d92fe3fd7d3a3eb58b5200e454c4 Mon Sep 17 00:00:00 2001
From: Zhao Heming <heming.zhao@suse.com>
Date: Tue, 21 Jul 2020 02:08:52 +0800
Subject: [PATCH] md-cluster: fix safemode_delay value when converting to
 clustered bitmap
Git-commit: 7c9d5c54fb72d92fe3fd7d3a3eb58b5200e454c4
Patch-mainline: v5.9-rc1
References: bsc#1163727

When array convert to clustered bitmap, the safe_mode_delay doesn't
clean and vice versa. the /sys/block/mdX/md/safe_mode_delay keep original
value after changing bitmap type. In safe_delay_store(), the code forbids
setting mddev->safemode_delay when array is clustered. So in cluster-md
env, the expected safemode_delay value should be 0.

Reproducible steps:
```
node1 # mdadm --zero-superblock /dev/sd{b,c,d}
node1 # mdadm -C /dev/md0 -b internal -e 1.2 -n 2 -l mirror /dev/sdb /dev/sdc
node1 # cat /sys/block/md0/md/safe_mode_delay
0.204
node1 # mdadm -G /dev/md0 -b none
node1 # mdadm --grow /dev/md0 --bitmap=clustered
node1 # cat /sys/block/md0/md/safe_mode_delay
0.204  <== doesn't change, should ZERO for cluster-md

node1 # mdadm --zero-superblock /dev/sd{b,c,d}
node1 # mdadm -C /dev/md0 -b clustered -e 1.2 -n 2 -l mirror /dev/sdb /dev/sdc
node1 # cat /sys/block/md0/md/safe_mode_delay
0.000
node1 # mdadm -G /dev/md0 -b none
node1 # cat /sys/block/md0/md/safe_mode_delay
0.000  <== doesn't change, should default value
```

Reviewed-by: NeilBrown <neilb@suse.de>
Signed-off-by: Zhao Heming <heming.zhao@suse.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 drivers/md/md.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9d740e4181ff..79a6b2f423dd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -101,6 +101,8 @@ static int remove_and_add_spares(struct mddev *mddev,
  * count by 2 for every hour elapsed between read errors.
  */
 #define MD_DEFAULT_MAX_CORRECTED_READ_ERRORS 20
+/* Default safemode delay: 200 msec */
+#define DEFAULT_SAFEMODE_DELAY ((200 * HZ)/1000 +1)
 /*
  * Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
  * is 1000 KB/sec, so the extra system load does not show up that much.
@@ -6034,7 +6036,7 @@ int md_run(struct mddev *mddev)
 	if (mddev_is_clustered(mddev))
 		mddev->safemode_delay = 0;
 	else
-		mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
+		mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 	mddev->in_sync = 1;
 	smp_wmb();
 	spin_lock(&mddev->lock);
@@ -7413,6 +7415,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 
 				mddev->bitmap_info.nodes = 0;
 				md_cluster_ops->leave(mddev);
+				mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY;
 			}
 			mddev_suspend(mddev);
 			md_bitmap_destroy(mddev);
@@ -8408,6 +8411,7 @@ int unregister_md_cluster_operations(void)
 
 int md_setup_cluster(struct mddev *mddev, int nodes)
 {
+	int ret;
 	if (!md_cluster_ops)
 		request_module("md-cluster");
 	spin_lock(&pers_lock);
@@ -8419,7 +8423,10 @@ int md_setup_cluster(struct mddev *mddev, int nodes)
 	}
 	spin_unlock(&pers_lock);
 
-	return md_cluster_ops->join(mddev, nodes);
+	ret = md_cluster_ops->join(mddev, nodes);
+	if (!ret)
+		mddev->safemode_delay = 0;
+	return ret;
 }
 
 void md_cluster_stop(struct mddev *mddev)
-- 
1.8.3.1