md/raid1,raid10: Fix: Operation continuing on 0 devices.

Since commit 9a56784 ("md: allow last device to be forcibly
removed from RAID1/RAID10."), RAID1/10 arrays can now lose all rdevs.

Before that commit, losing the array last rdev or reaching the end of
the function without early return in raid{1,10}_error never occurred.
However, both situations can occur in the current implementation.

As a result, when mddev->fail_last_dev is set, a spurious pr_crit
message can be printed.

This patch prevents "Operation continuing" printed if the array
is not operational.

root@fedora:~# mdadm --create --verbose /dev/md0 --level=1 \
--raid-devices=2  /dev/loop0 /dev/loop1
mdadm: Note: this array has metadata at the start and
    may not be suitable as a boot device.  If you plan to
    store '/boot' on this device please ensure that
    your boot-loader understands md/v1.x metadata, or use
    --metadata=0.90
mdadm: size set to 1046528K
Continue creating array? y
mdadm: Defaulting to version 1.2 metadata
mdadm: array /dev/md0 started.
root@fedora:~# echo 1 > /sys/block/md0/md/fail_last_dev
root@fedora:~# mdadm --fail /dev/md0 loop0
mdadm: set loop0 faulty in /dev/md0
root@fedora:~# mdadm --fail /dev/md0 loop1
mdadm: set device faulty failed for loop1:  Device or resource busy
root@fedora:~# dmesg | tail -n 4
[ 1314.359674] md/raid1:md0: Disk failure on loop0, disabling device.
               md/raid1:md0: Operation continuing on 1 devices.
[ 1315.506633] md/raid1:md0: Disk failure on loop1, disabling device.
               md/raid1:md0: Operation continuing on 0 devices.
root@fedora:~#

Fixes: 9a56784 ("md: allow last device to be forcibly removed from RAID1/RAID10.")
Signed-off-by: Kenta Akagi <[email protected]>

Author: mgmlme

drivers/md/raid1.c

@@ -1785,17 +1785,18 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 	if (test_and_clear_bit(In_sync, &rdev->flags))
 		mddev->degraded++;
 	set_bit(Faulty, &rdev->flags);
+	if ((conf->raid_disks - mddev->degraded) > 0)
+		pr_crit("md/raid1:%s: Disk failure on %pg, disabling device.\n"
+			"md/raid1:%s: Operation continuing on %d devices.\n",
+			mdname(mddev), rdev->bdev,
+			mdname(mddev), conf->raid_disks - mddev->degraded);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_mask_bits(&mddev->sb_flags, 0,
 		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
-	pr_crit("md/raid1:%s: Disk failure on %pg, disabling device.\n"
-		"md/raid1:%s: Operation continuing on %d devices.\n",
-		mdname(mddev), rdev->bdev,
-		mdname(mddev), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(struct r1conf *conf)

drivers/md/raid10.c

@@ -2034,11 +2034,12 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 	set_bit(Faulty, &rdev->flags);
 	set_mask_bits(&mddev->sb_flags, 0,
 		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
+	if (enough(conf, -1))
+		pr_crit("md/raid10:%s: Disk failure on %pg, disabling device.\n"
+			"md/raid10:%s: Operation continuing on %d devices.\n",
+			mdname(mddev), rdev->bdev,
+			mdname(mddev), conf->geo.raid_disks - mddev->degraded);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
-	pr_crit("md/raid10:%s: Disk failure on %pg, disabling device.\n"
-		"md/raid10:%s: Operation continuing on %d devices.\n",
-		mdname(mddev), rdev->bdev,
-		mdname(mddev), conf->geo.raid_disks - mddev->degraded);
 }
 
 static void print_conf(struct r10conf *conf)