md: support blocking writes to an array on device failure

Allows a userspace metadata handler to take action upon detecting a device
failure.

Based on an original patch by Neil Brown.

Changes:
-added blocked_wait waitqueue to rdev
-don't qualify Blocked with Faulty always let userspace block writes
-added md_wait_for_blocked_rdev to wait for the block device to be clear, if
 userspace misses the notification another one is sent every 5 seconds
-set MD_RECOVERY_NEEDED after clearing "blocked"
-kill DoBlock flag, just test mddev->external

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/drivers/md/md.c b/drivers/md/md.c
index bec00b2..83eb78b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1828,6 +1828,10 @@
 		len += sprintf(page+len, "%swrite_mostly",sep);
 		sep = ",";
 	}
+	if (test_bit(Blocked, &rdev->flags)) {
+		len += sprintf(page+len, "%sblocked", sep);
+		sep = ",";
+	}
 	if (!test_bit(Faulty, &rdev->flags) &&
 	    !test_bit(In_sync, &rdev->flags)) {
 		len += sprintf(page+len, "%sspare", sep);
@@ -1844,6 +1848,8 @@
 	 *  remove  - disconnects the device
 	 *  writemostly - sets write_mostly
 	 *  -writemostly - clears write_mostly
+	 *  blocked - sets the Blocked flag
+	 *  -blocked - clears the Blocked flag
 	 */
 	int err = -EINVAL;
 	if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
@@ -1866,6 +1872,16 @@
 	} else if (cmd_match(buf, "-writemostly")) {
 		clear_bit(WriteMostly, &rdev->flags);
 		err = 0;
+	} else if (cmd_match(buf, "blocked")) {
+		set_bit(Blocked, &rdev->flags);
+		err = 0;
+	} else if (cmd_match(buf, "-blocked")) {
+		clear_bit(Blocked, &rdev->flags);
+		wake_up(&rdev->blocked_wait);
+		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
+		md_wakeup_thread(rdev->mddev->thread);
+
+		err = 0;
 	}
 	return err ? err : len;
 }
@@ -2194,7 +2210,9 @@
 			goto abort_free;
 		}
 	}
+
 	INIT_LIST_HEAD(&rdev->same_set);
+	init_waitqueue_head(&rdev->blocked_wait);
 
 	return rdev;
 
@@ -4958,6 +4976,9 @@
 
 	if (!rdev || test_bit(Faulty, &rdev->flags))
 		return;
+
+	if (mddev->external)
+		set_bit(Blocked, &rdev->flags);
 /*
 	dprintk("md_error dev:%s, rdev:(%d:%d), (caller: %p,%p,%p,%p).\n",
 		mdname(mddev),
@@ -5760,7 +5781,7 @@
 
 	rdev_for_each(rdev, rtmp, mddev)
 		if (rdev->raid_disk >= 0 &&
-		    !mddev->external &&
+		    !test_bit(Blocked, &rdev->flags) &&
 		    (test_bit(Faulty, &rdev->flags) ||
 		     ! test_bit(In_sync, &rdev->flags)) &&
 		    atomic_read(&rdev->nr_pending)==0) {
@@ -5959,6 +5980,16 @@
 	}
 }
 
+void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
+{
+	sysfs_notify(&rdev->kobj, NULL, "state");
+	wait_event_timeout(rdev->blocked_wait,
+			   !test_bit(Blocked, &rdev->flags),
+			   msecs_to_jiffies(5000));
+	rdev_dec_pending(rdev, mddev);
+}
+EXPORT_SYMBOL(md_wait_for_blocked_rdev);
+
 static int md_notify_reboot(struct notifier_block *this,
 			    unsigned long code, void *x)
 {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 9fd473a..6778b7c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -773,7 +773,6 @@
 	r1bio_t *r1_bio;
 	struct bio *read_bio;
 	int i, targets = 0, disks;
-	mdk_rdev_t *rdev;
 	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
 	struct bio_list bl;
@@ -781,6 +780,7 @@
 	const int rw = bio_data_dir(bio);
 	const int do_sync = bio_sync(bio);
 	int do_barriers;
+	mdk_rdev_t *blocked_rdev;
 
 	/*
 	 * Register the new request and wait if the reconstruction
@@ -862,10 +862,17 @@
 	first = 0;
 	}
 #endif
+ retry_write:
+	blocked_rdev = NULL;
 	rcu_read_lock();
 	for (i = 0;  i < disks; i++) {
-		if ((rdev=rcu_dereference(conf->mirrors[i].rdev)) != NULL &&
-		    !test_bit(Faulty, &rdev->flags)) {
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			atomic_inc(&rdev->nr_pending);
+			blocked_rdev = rdev;
+			break;
+		}
+		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			atomic_inc(&rdev->nr_pending);
 			if (test_bit(Faulty, &rdev->flags)) {
 				rdev_dec_pending(rdev, mddev);
@@ -878,6 +885,20 @@
 	}
 	rcu_read_unlock();
 
+	if (unlikely(blocked_rdev)) {
+		/* Wait for this device to become unblocked */
+		int j;
+
+		for (j = 0; j < i; j++)
+			if (r1_bio->bios[j])
+				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
+
+		allow_barrier(conf);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_write;
+	}
+
 	BUG_ON(targets == 0); /* we never fail the last device */
 
 	if (targets < conf->raid_disks) {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 1e96aa3..5938fa9 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -790,6 +790,7 @@
 	const int do_sync = bio_sync(bio);
 	struct bio_list bl;
 	unsigned long flags;
+	mdk_rdev_t *blocked_rdev;
 
 	if (unlikely(bio_barrier(bio))) {
 		bio_endio(bio, -EOPNOTSUPP);
@@ -879,17 +880,23 @@
 	/*
 	 * WRITE:
 	 */
-	/* first select target devices under spinlock and
+	/* first select target devices under rcu_lock and
 	 * inc refcount on their rdev.  Record them by setting
 	 * bios[x] to bio
 	 */
 	raid10_find_phys(conf, r10_bio);
+ retry_write:
+	blocked_rdev = 0;
 	rcu_read_lock();
 	for (i = 0;  i < conf->copies; i++) {
 		int d = r10_bio->devs[i].devnum;
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[d].rdev);
-		if (rdev &&
-		    !test_bit(Faulty, &rdev->flags)) {
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			atomic_inc(&rdev->nr_pending);
+			blocked_rdev = rdev;
+			break;
+		}
+		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			atomic_inc(&rdev->nr_pending);
 			r10_bio->devs[i].bio = bio;
 		} else {
@@ -899,6 +906,22 @@
 	}
 	rcu_read_unlock();
 
+	if (unlikely(blocked_rdev)) {
+		/* Have to wait for this device to get unblocked, then retry */
+		int j;
+		int d;
+
+		for (j = 0; j < i; j++)
+			if (r10_bio->devs[j].bio) {
+				d = r10_bio->devs[j].devnum;
+				rdev_dec_pending(conf->mirrors[d].rdev, mddev);
+			}
+		allow_barrier(conf);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_write;
+	}
+
 	atomic_set(&r10_bio->remaining, 0);
 
 	bio_list_init(&bl);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 968daca..087eee0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2607,6 +2607,7 @@
 	}
 }
 
+
 /*
  * handle_stripe - do things to a stripe.
  *
@@ -2632,6 +2633,7 @@
 	struct stripe_head_state s;
 	struct r5dev *dev;
 	unsigned long pending = 0;
+	mdk_rdev_t *blocked_rdev = NULL;
 
 	memset(&s, 0, sizeof(s));
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
@@ -2691,6 +2693,11 @@
 		if (dev->written)
 			s.written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			blocked_rdev = rdev;
+			atomic_inc(&rdev->nr_pending);
+			break;
+		}
 		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
 			/* The ReadError flag will just be confusing now */
 			clear_bit(R5_ReadError, &dev->flags);
@@ -2705,6 +2712,11 @@
 	}
 	rcu_read_unlock();
 
+	if (unlikely(blocked_rdev)) {
+		set_bit(STRIPE_HANDLE, &sh->state);
+		goto unlock;
+	}
+
 	if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
 		sh->ops.count++;
 
@@ -2894,8 +2906,13 @@
 	if (sh->ops.count)
 		pending = get_stripe_work(sh);
 
+ unlock:
 	spin_unlock(&sh->lock);
 
+	/* wait for this device to become unblocked */
+	if (unlikely(blocked_rdev))
+		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
 	if (pending)
 		raid5_run_ops(sh, pending);
 
@@ -2912,6 +2929,7 @@
 	struct stripe_head_state s;
 	struct r6_state r6s;
 	struct r5dev *dev, *pdev, *qdev;
+	mdk_rdev_t *blocked_rdev = NULL;
 
 	r6s.qd_idx = raid6_next_disk(pd_idx, disks);
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
@@ -2975,6 +2993,11 @@
 		if (dev->written)
 			s.written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			blocked_rdev = rdev;
+			atomic_inc(&rdev->nr_pending);
+			break;
+		}
 		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
 			/* The ReadError flag will just be confusing now */
 			clear_bit(R5_ReadError, &dev->flags);
@@ -2989,6 +3012,11 @@
 			set_bit(R5_Insync, &dev->flags);
 	}
 	rcu_read_unlock();
+
+	if (unlikely(blocked_rdev)) {
+		set_bit(STRIPE_HANDLE, &sh->state);
+		goto unlock;
+	}
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
@@ -3094,8 +3122,13 @@
 	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
 		handle_stripe_expansion(conf, sh, &r6s);
 
+ unlock:
 	spin_unlock(&sh->lock);
 
+	/* wait for this device to become unblocked */
+	if (unlikely(blocked_rdev))
+		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
 	return_io(return_bi);
 
 	for (i=disks; i-- ;) {