raid5: introduce MD_BROKEN

commit 57668f0 upstream.

Raid456 module had allowed to achieve failed state. It was fixed by
fb73b35 ("raid5: block failing device if raid will be failed").
This fix introduces a bug, now if raid5 fails during IO, it may result
with a hung task without completion. Faulty flag on the device is
necessary to process all requests and is checked many times, mainly in
analyze_stripe().
Allow to set faulty on drive again and set MD_BROKEN if raid is failed.

As a result, this level is allowed to achieve failed state again, but
communication with userspace (via -EBUSY status) will be preserved.

This restores possibility to fail array via #mdadm --set-faulty command
and will be fixed by additional verification on mdadm side.

Reproduction steps:
 mdadm -CR imsm -e imsm -n 3 /dev/nvme[0-2]n1
 mdadm -CR r5 -e imsm -l5 -n3 /dev/nvme[0-2]n1 --assume-clean
 mkfs.xfs /dev/md126 -f
 mount /dev/md126 /mnt/root/

 fio --filename=/mnt/root/file --size=5GB --direct=1 --rw=randrw
--bs=64k --ioengine=libaio --iodepth=64 --runtime=240 --numjobs=4
--time_based --group_reporting --name=throughput-test-job
--eta-newline=1 &

 echo 1 > /sys/block/nvme2n1/device/device/remove
 echo 1 > /sys/block/nvme1n1/device/device/remove

 [ 1475.787779] Call Trace:
 [ 1475.793111] __schedule+0x2a6/0x700
 [ 1475.799460] schedule+0x38/0xa0
 [ 1475.805454] raid5_get_active_stripe+0x469/0x5f0 [raid456]
 [ 1475.813856] ? finish_wait+0x80/0x80
 [ 1475.820332] raid5_make_request+0x180/0xb40 [raid456]
 [ 1475.828281] ? finish_wait+0x80/0x80
 [ 1475.834727] ? finish_wait+0x80/0x80
 [ 1475.841127] ? finish_wait+0x80/0x80
 [ 1475.847480] md_handle_request+0x119/0x190
 [ 1475.854390] md_make_request+0x8a/0x190
 [ 1475.861041] generic_make_request+0xcf/0x310
 [ 1475.868145] submit_bio+0x3c/0x160
 [ 1475.874355] iomap_dio_submit_bio.isra.20+0x51/0x60
 [ 1475.882070] iomap_dio_bio_actor+0x175/0x390
 [ 1475.889149] iomap_apply+0xff/0x310
 [ 1475.895447] ? iomap_dio_bio_actor+0x390/0x390
 [ 1475.902736] ? iomap_dio_bio_actor+0x390/0x390
 [ 1475.909974] iomap_dio_rw+0x2f2/0x490
 [ 1475.916415] ? iomap_dio_bio_actor+0x390/0x390
 [ 1475.923680] ? atime_needs_update+0x77/0xe0
 [ 1475.930674] ? xfs_file_dio_aio_read+0x6b/0xe0 [xfs]
 [ 1475.938455] xfs_file_dio_aio_read+0x6b/0xe0 [xfs]
 [ 1475.946084] xfs_file_read_iter+0xba/0xd0 [xfs]
 [ 1475.953403] aio_read+0xd5/0x180
 [ 1475.959395] ? _cond_resched+0x15/0x30
 [ 1475.965907] io_submit_one+0x20b/0x3c0
 [ 1475.972398] __x64_sys_io_submit+0xa2/0x180
 [ 1475.979335] ? do_io_getevents+0x7c/0xc0
 [ 1475.986009] do_syscall_64+0x5b/0x1a0
 [ 1475.992419] entry_SYSCALL_64_after_hwframe+0x65/0xca
 [ 1476.000255] RIP: 0033:0x7f11fc27978d
 [ 1476.006631] Code: Bad RIP value.
 [ 1476.073251] INFO: task fio:3877 blocked for more than 120 seconds.

Cc: [email protected]
Fixes: fb73b35 ("raid5: block failing device if raid will be failed")
Reviewd-by: Xiao Ni <[email protected]>
Signed-off-by: Mariusz Tkaczyk <[email protected]>
Signed-off-by: Song Liu <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: mtkaczyk

drivers/md/raid5.c

@@ -686,17 +686,17 @@ int raid5_calc_degraded(struct r5conf *conf)
 	return degraded;
 }
 
-static int has_failed(struct r5conf *conf)
+static bool has_failed(struct r5conf *conf)
 {
-	int degraded;
+	int degraded = conf->mddev->degraded;
 
-	if (conf->mddev->reshape_position == MaxSector)
-		return conf->mddev->degraded > conf->max_degraded;
+	if (test_bit(MD_BROKEN, &conf->mddev->flags))
+		return true;
 
-	degraded = raid5_calc_degraded(conf);
-	if (degraded > conf->max_degraded)
-		return 1;
-	return 0;
+	if (conf->mddev->reshape_position != MaxSector)
+		degraded = raid5_calc_degraded(conf);
+
+	return degraded > conf->max_degraded;
 }
 
 struct stripe_head *
@@ -2877,34 +2877,31 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 	unsigned long flags;
 	pr_debug("raid456: error called\n");
 
+	pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n",
+		mdname(mddev), bdevname(rdev->bdev, b));
+
 	spin_lock_irqsave(&conf->device_lock, flags);
+	set_bit(Faulty, &rdev->flags);
+	clear_bit(In_sync, &rdev->flags);
+	mddev->degraded = raid5_calc_degraded(conf);
 
-	if (test_bit(In_sync, &rdev->flags) &&
-	    mddev->degraded == conf->max_degraded) {
-		/*
-		 * Don't allow to achieve failed state
-		 * Don't try to recover this device
-		 */
+	if (has_failed(conf)) {
+		set_bit(MD_BROKEN, &conf->mddev->flags);
 		conf->recovery_disabled = mddev->recovery_disabled;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		return;
+
+		pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n",
+			mdname(mddev), mddev->degraded, conf->raid_disks);
+	} else {
+		pr_crit("md/raid:%s: Operation continuing on %d devices.\n",
+			mdname(mddev), conf->raid_disks - mddev->degraded);
 	}
 
-	set_bit(Faulty, &rdev->flags);
-	clear_bit(In_sync, &rdev->flags);
-	mddev->degraded = raid5_calc_degraded(conf);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
 	set_bit(Blocked, &rdev->flags);
 	set_mask_bits(&mddev->sb_flags, 0,
 		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
-	pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n"
-		"md/raid:%s: Operation continuing on %d devices.\n",
-		mdname(mddev),
-		bdevname(rdev->bdev, b),
-		mdname(mddev),
-		conf->raid_disks - mddev->degraded);
 	r5c_update_on_rdev_error(mddev, rdev);
 }