md: Introduction : patchbomb for 2.6.27 merge window

diff .prev/drivers/md/raid10.c ./drivers/md/raid10.c
@@ -2137,6 +2137,8 @@ static int run(mddev_t *mddev)
 		    !test_bit(In_sync, &disk->rdev->flags)) {
 			disk->head_position = 0;
 			mddev->degraded++;
+			if (disk->rdev)
+				conf->fullsync = 1;
 		}
 	}
 

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -4305,7 +4305,9 @@ static int run(mddev_t *mddev)
 				" disk %d\n", bdevname(rdev->bdev,b),
 				raid_disk);
 			working_disks++;
-		}
+		} else
+			/* Cannot rely on bitmap to complete recovery */
+			conf->fullsync = 1;
 	}
 
 	/*

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -2898,6 +2898,8 @@ static void handle_stripe5(struct stripe
 
 		for (i = conf->raid_disks; i--; ) {
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
+			set_bit(R5_LOCKED, &dev->flags);
+			s.locked++;
 			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
 				sh->ops.count++;
 		}

@@ -2911,6 +2913,7 @@ static void handle_stripe5(struct stripe
 			conf->raid_disks);
 		s.locked += handle_write_operations5(sh, 1, 1);
 	} else if (s.expanded &&
+		   s.locked == 0 &&
 		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -3897,8 +3897,10 @@ static void autorun_devices(int part)
 
 		md_probe(dev, NULL, NULL);
 		mddev = mddev_find(dev);
-		if (!mddev) {
-			printk(KERN_ERR 
+		if (!mddev || !mddev->gendisk) {
+			if (mddev)
+				mddev_put(mddev);
+			printk(KERN_ERR
 				"md: cannot allocate memory for md drive.\n");
 			break;
 		}

diff .prev/drivers/md/linear.c ./drivers/md/linear.c
@@ -126,7 +126,7 @@ static linear_conf_t *linear_conf(mddev_
 		int j = rdev->raid_disk;
 		dev_info_t *disk = conf->disks + j;
 
-		if (j < 0 || j > raid_disks || disk->rdev) {
+		if (j < 0 || j >= raid_disks || disk->rdev) {
 			printk("linear: disk numbering problem. Aborting!\n");
 			goto out;
 		}

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -115,9 +115,7 @@ static void return_io(struct bio *return
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
 		bi->bi_size = 0;
-		bi->bi_end_io(bi,
-			      test_bit(BIO_UPTODATE, &bi->bi_flags)
-			        ? 0 : -EIO);
+		bio_endio(bi, 0);
 		bi = return_bi;
 	}
 }

@@ -3700,9 +3698,7 @@ static int make_request(struct request_q
 		if ( rw == WRITE )
 			md_write_end(mddev);
 
-		bi->bi_end_io(bi,
-			      test_bit(BIO_UPTODATE, &bi->bi_flags)
-			        ? 0 : -EIO);
+		bio_endio(bi, 0);
 	}
 	return 0;
 }

@@ -4005,12 +4001,8 @@ static int  retry_aligned_read(raid5_con
 	spin_lock_irq(&conf->device_lock);
 	remaining = --raid_bio->bi_phys_segments;
 	spin_unlock_irq(&conf->device_lock);
-	if (remaining == 0) {
-
-		raid_bio->bi_end_io(raid_bio,
-			      test_bit(BIO_UPTODATE, &raid_bio->bi_flags)
-			        ? 0 : -EIO);
-	}
+	if (remaining == 0)
+		bio_endio(raid_bio, 0);
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_stripe);
 	return handled;

diff .prev/drivers/md/bitmap.c ./drivers/md/bitmap.c
@@ -454,8 +454,11 @@ void bitmap_update_sb(struct bitmap *bit
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
 	sb->events = cpu_to_le64(bitmap->mddev->events);
-	if (!bitmap->mddev->degraded)
-		sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	if (bitmap->mddev->events < bitmap->events_cleared) {
+		/* rocking back to read-only */
+		bitmap->events_cleared = bitmap->mddev->events;
+		sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
+	}
 	kunmap_atomic(sb, KM_USER0);
 	write_page(bitmap, bitmap->sb_page, 1);
 }

@@ -1085,9 +1088,19 @@ void bitmap_daemon_work(struct bitmap *b
 			} else
 				spin_unlock_irqrestore(&bitmap->lock, flags);
 			lastpage = page;
-/*
-			printk("bitmap clean at page %lu\n", j);
-*/
+
+			/* We are possibly going to clear some bits, so make
+			 * sure that events_cleared is up-to-date.
+			 */
+			if (bitmap->need_sync) {
+				bitmap_super_t *sb;
+				bitmap->need_sync = 0;
+				sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+				sb->events_cleared =
+					cpu_to_le64(bitmap->events_cleared);
+				kunmap_atomic(sb, KM_USER0);
+				write_page(bitmap, bitmap->sb_page, 1);
+			}
 			spin_lock_irqsave(&bitmap->lock, flags);
 			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}

@@ -1257,6 +1270,12 @@ void bitmap_endwrite(struct bitmap *bitm
 			return;
 		}
 
+		if (success &&
+		    bitmap->events_cleared < bitmap->mddev->events) {
+			bitmap->events_cleared = bitmap->mddev->events;
+			bitmap->need_sync = 1;
+		}
+
 		if (!success && ! (*bmc & NEEDED_MASK))
 			*bmc |= NEEDED_MASK;
 

diff .prev/include/linux/raid/bitmap.h ./include/linux/raid/bitmap.h
@@ -221,6 +221,7 @@ struct bitmap {
 	unsigned long syncchunk;
 
 	__u64	events_cleared;
+	int need_sync;
 
 	/* bitmap spinlock */
 	spinlock_t lock;

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -278,6 +278,7 @@ static mddev_t * mddev_find(dev_t unit)
 	init_waitqueue_head(&new->sb_wait);
 	init_waitqueue_head(&new->recovery_wait);
 	new->reshape_position = MaxSector;
+	new->resync_min = 0;
 	new->resync_max = MaxSector;
 	new->level = LEVEL_NONE;
 

@@ -3075,6 +3076,36 @@ sync_completed_show(mddev_t *mddev, char
 static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);
 
 static ssize_t
+min_sync_show(mddev_t *mddev, char *page)
+{
+	return sprintf(page, "%llu\n",
+		       (unsigned long long)mddev->resync_min);
+}
+static ssize_t
+min_sync_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	unsigned long long min;
+	if (strict_strtoull(buf, 10, &min))
+		return -EINVAL;
+	if (min > mddev->resync_max)
+		return -EINVAL;
+	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		return -EBUSY;
+
+	/* Must be a multiple of chunk_size */
+	if (mddev->chunk_size) {
+		if (min & (sector_t)((mddev->chunk_size>>9)-1))
+			return -EINVAL;
+	}
+	mddev->resync_min = min;
+
+	return len;
+}
+
+static struct md_sysfs_entry md_min_sync =
+__ATTR(sync_min, S_IRUGO|S_IWUSR, min_sync_show, min_sync_store);
+
+static ssize_t
 max_sync_show(mddev_t *mddev, char *page)
 {
 	if (mddev->resync_max == MaxSector)

@@ -3089,9 +3120,10 @@ max_sync_store(mddev_t *mddev, const cha
 	if (strncmp(buf, "max", 3) == 0)
 		mddev->resync_max = MaxSector;
 	else {
-		char *ep;
-		unsigned long long max = simple_strtoull(buf, &ep, 10);
-		if (ep == buf || (*ep != 0 && *ep != '\n'))
+		unsigned long long max;
+		if (strict_strtoull(buf, 10, &max))
+			return -EINVAL;
+		if (max < mddev->resync_min)
 			return -EINVAL;
 		if (max < mddev->resync_max &&
 		    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))

@@ -3222,6 +3254,7 @@ static struct attribute *md_redundancy_a
 	&md_sync_speed.attr,
 	&md_sync_force_parallel.attr,
 	&md_sync_completed.attr,
+	&md_min_sync.attr,
 	&md_max_sync.attr,
 	&md_suspend_lo.attr,
 	&md_suspend_hi.attr,

@@ -3777,6 +3810,7 @@ static int do_md_stop(mddev_t * mddev, i
 		mddev->size = 0;
 		mddev->raid_disks = 0;
 		mddev->recovery_cp = 0;
+		mddev->resync_min = 0;
 		mddev->resync_max = MaxSector;
 		mddev->reshape_position = MaxSector;
 		mddev->external = 0;

@@ -5625,9 +5659,11 @@ void md_do_sync(mddev_t *mddev)
 		max_sectors = mddev->resync_max_sectors;
 		mddev->resync_mismatches = 0;
 		/* we don't use the checkpoint if there's a bitmap */
-		if (!mddev->bitmap &&
-		    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+		if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+			j = mddev->resync_min;
+		else if (!mddev->bitmap)
 			j = mddev->recovery_cp;
+
 	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		max_sectors = mddev->size << 1;
 	else {

@@ -5796,6 +5832,7 @@ void md_do_sync(mddev_t *mddev)
 
  skip:
 	mddev->curr_resync = 0;
+	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 	wake_up(&resync_wait);

diff .prev/include/linux/raid/md_k.h ./include/linux/raid/md_k.h
@@ -227,6 +227,8 @@ struct mddev_s
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
 	sector_t			recovery_cp;
+	sector_t			resync_min;	/* user requested sync
+							 * starts here */
 	sector_t			resync_max;	/* resync should pause
 							 * when it gets here */
 

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -3359,9 +3359,9 @@ static struct kobject *md_probe(dev_t de
 	disk->queue = mddev->queue;
 	add_disk(disk);
 	mddev->gendisk = disk;
-	mutex_unlock(&disks_mutex);
 	error = kobject_init_and_add(&mddev->kobj, &md_ktype, &disk->dev.kobj,
 				     "%s", "md");
+	mutex_unlock(&disks_mutex);
 	if (error)
 		printk(KERN_WARNING "md: cannot register %s/md - name in use\n",
 		       disk->disk_name);

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -5536,6 +5536,8 @@ void md_allow_write(mddev_t *mddev)
 		return;
 	if (mddev->ro)
 		return;
+	if (!mddev->pers->sync_request)
+		return;
 
 	spin_lock_irq(&mddev->write_lock);
 	if (mddev->in_sync) {

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -1984,7 +1984,7 @@ offset_store(mdk_rdev_t *rdev, const cha
 	unsigned long long offset = simple_strtoull(buf, &e, 10);
 	if (e==buf || (*e && *e != '\n'))
 		return -EINVAL;
-	if (rdev->mddev->pers)
+	if (rdev->mddev->pers && rdev->raid_disk >= 0)
 		return -EBUSY;
 	if (rdev->size && rdev->mddev->external)
 		/* Must set offset before size, so overlap checks

@@ -2023,7 +2023,7 @@ rdev_size_store(mdk_rdev_t *rdev, const 
 
 	if (e==buf || (*e && *e != '\n'))
 		return -EINVAL;
-	if (my_mddev->pers)
+	if (my_mddev->pers && rdev->raid_disk >= 0)
 		return -EBUSY;
 	rdev->size = size;
 	if (size > oldsize && rdev->mddev->external) {

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -1932,7 +1932,7 @@ slot_store(mdk_rdev_t *rdev, const char 
 		slot = -1;
 	else if (e==buf || (*e && *e!= '\n'))
 		return -EINVAL;
-	if (rdev->mddev->pers) {
+	if (rdev->mddev->pers && slot == -1) {
 		/* Setting 'slot' on an active array requires also
 		 * updating the 'rd%d' link, and communicating
 		 * with the personality with ->hot_*_disk.

@@ -1940,8 +1940,6 @@ slot_store(mdk_rdev_t *rdev, const char 
 		 * failed/spare devices.  This normally happens automatically,
 		 * but not when the metadata is externally managed.
 		 */
-		if (slot != -1)
-			return -EBUSY;
 		if (rdev->raid_disk == -1)
 			return -EEXIST;
 		/* personality does all needed checks */

@@ -1955,6 +1953,44 @@ slot_store(mdk_rdev_t *rdev, const char 
 		sysfs_remove_link(&rdev->mddev->kobj, nm);
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
+	} else if (rdev->mddev->pers) {
+		mdk_rdev_t *rdev2;
+		struct list_head *tmp;
+		/* Activating a spare .. or possibly reactivating
+		 * if we every get bitmaps working here.
+		 */
+
+		if (rdev->raid_disk != -1)
+			return -EBUSY;
+
+		if (rdev->mddev->pers->hot_add_disk == NULL)
+			return -EINVAL;
+
+		rdev_for_each(rdev2, tmp, rdev->mddev)
+			if (rdev2->raid_disk == slot)
+				return -EEXIST;
+
+		rdev->raid_disk = slot;
+		if (test_bit(In_sync, &rdev->flags))
+			rdev->saved_raid_disk = slot;
+		else
+			rdev->saved_raid_disk = -1;
+		err = rdev->mddev->pers->
+			hot_add_disk(rdev->mddev, rdev);
+		if (err != 1) {
+			rdev->raid_disk = -1;
+			if (err == 0)
+				return -EEXIST;
+			return err;
+		}
+		sprintf(nm, "rd%d", rdev->raid_disk);
+		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
+			printk(KERN_WARNING
+			       "md: cannot register "
+			       "%s for %s\n",
+			       nm, mdname(rdev->mddev));
+
+		/* don't wakeup anyone, leave that to userspace. */
 	} else {
 		if (slot >= rdev->mddev->raid_disks)
 			return -ENOSPC;

diff .prev/drivers/md/multipath.c ./drivers/md/multipath.c
@@ -284,10 +284,15 @@ static int multipath_add_disk(mddev_t *m
 	int found = 0;
 	int path;
 	struct multipath_info *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	print_multipath_conf(conf);
 
-	for (path=0; path<mddev->raid_disks; path++) 
+	for (path = first; path <= last; path++)
 		if ((p=conf->multipaths+path)->rdev == NULL) {
 			q = rdev->bdev->bd_disk->queue;
 			blk_queue_stack_limits(mddev->queue, q);

diff .prev/drivers/md/raid10.c ./drivers/md/raid10.c
@@ -1116,6 +1116,8 @@ static int raid10_add_disk(mddev_t *mdde
 	int found = 0;
 	int mirror;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is

@@ -1125,12 +1127,16 @@ static int raid10_add_disk(mddev_t *mdde
 	if (!enough(conf))
 		return 0;
 
+	if (rdev->raid_disk)
+		first = last = rdev->raid_disk;
+
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
 	else
-		mirror = 0;
-	for ( ; mirror < mddev->raid_disks; mirror++)
+		mirror = first;
+	for ( ; mirror <= last ; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,

diff .prev/drivers/md/raid1.c ./drivers/md/raid1.c
@@ -1103,8 +1103,13 @@ static int raid1_add_disk(mddev_t *mddev
 	int found = 0;
 	int mirror = 0;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
-	for (mirror=0; mirror < mddev->raid_disks; mirror++)
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
+
+	for (mirror = first; mirror <= last; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -4607,21 +4607,27 @@ static int raid5_add_disk(mddev_t *mddev
 	int found = 0;
 	int disk;
 	struct disk_info *p;
+	int first = 0;
+	int last = conf->raid_disks - 1;
 
 	if (mddev->degraded > conf->max_degraded)
 		/* no point adding a device */
 		return 0;
 
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
+
 	/*
 	 * find the disk ... but prefer rdev->saved_raid_disk
 	 * if possible.
 	 */
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->disks[rdev->saved_raid_disk].rdev == NULL)
 		disk = rdev->saved_raid_disk;
 	else
-		disk = 0;
-	for ( ; disk < conf->raid_disks; disk++)
+		disk = first;
+	for ( ; disk <= last ; disk++)
 		if ((p=conf->disks + disk)->rdev == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = disk;

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -1977,10 +1977,8 @@ slot_store(mdk_rdev_t *rdev, const char 
 			rdev->saved_raid_disk = -1;
 		err = rdev->mddev->pers->
 			hot_add_disk(rdev->mddev, rdev);
-		if (err != 1) {
+		if (err) {
 			rdev->raid_disk = -1;
-			if (err == 0)
-				return -EEXIST;
 			return err;
 		}
 		sprintf(nm, "rd%d", rdev->raid_disk);

@@ -5920,7 +5918,8 @@ static int remove_and_add_spares(mddev_t
 			if (rdev->raid_disk < 0
 			    && !test_bit(Faulty, &rdev->flags)) {
 				rdev->recovery_offset = 0;
-				if (mddev->pers->hot_add_disk(mddev,rdev)) {
+				if (mddev->pers->
+				    hot_add_disk(mddev, rdev) == 0) {
 					char nm[20];
 					sprintf(nm, "rd%d", rdev->raid_disk);
 					if (sysfs_create_link(&mddev->kobj,

diff .prev/drivers/md/multipath.c ./drivers/md/multipath.c
@@ -281,7 +281,7 @@ static int multipath_add_disk(mddev_t *m
 {
 	multipath_conf_t *conf = mddev->private;
 	struct request_queue *q;
-	int found = 0;
+	int err = -EEXIST;
 	int path;
 	struct multipath_info *p;
 	int first = 0;

@@ -312,11 +312,13 @@ static int multipath_add_disk(mddev_t *m
 			rdev->raid_disk = path;
 			set_bit(In_sync, &rdev->flags);
 			rcu_assign_pointer(p->rdev, rdev);
-			found = 1;
+			err = 0;
+			break;
 		}
 
 	print_multipath_conf(conf);
-	return found;
+
+	return err;
 }
 
 static int multipath_remove_disk(mddev_t *mddev, int number)

diff .prev/drivers/md/raid10.c ./drivers/md/raid10.c
@@ -1113,7 +1113,7 @@ static int raid10_spare_active(mddev_t *
 static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror;
 	mirror_info_t *p;
 	int first = 0;

@@ -1123,9 +1123,9 @@ static int raid10_add_disk(mddev_t *mdde
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
-		return 0;
+		return -EBUSY;
 	if (!enough(conf))
-		return 0;
+		return -EINVAL;
 
 	if (rdev->raid_disk)
 		first = last = rdev->raid_disk;

@@ -1151,7 +1151,7 @@ static int raid10_add_disk(mddev_t *mdde
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != mirror)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);

@@ -1159,7 +1159,7 @@ static int raid10_add_disk(mddev_t *mdde
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid10_remove_disk(mddev_t *mddev, int number)

diff .prev/drivers/md/raid1.c ./drivers/md/raid1.c
@@ -1100,7 +1100,7 @@ static int raid1_spare_active(mddev_t *m
 static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror = 0;
 	mirror_info_t *p;
 	int first = 0;

@@ -1124,7 +1124,7 @@ static int raid1_add_disk(mddev_t *mddev
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */

@@ -1135,7 +1135,7 @@ static int raid1_add_disk(mddev_t *mddev
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid1_remove_disk(mddev_t *mddev, int number)

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -4604,7 +4604,7 @@ abort:
 static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	raid5_conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int disk;
 	struct disk_info *p;
 	int first = 0;

@@ -4612,7 +4612,7 @@ static int raid5_add_disk(mddev_t *mddev
 
 	if (mddev->degraded > conf->max_degraded)
 		/* no point adding a device */
-		return 0;
+		return -EINVAL;
 
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;

@@ -4631,14 +4631,14 @@ static int raid5_add_disk(mddev_t *mddev
 		if ((p=conf->disks + disk)->rdev == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = disk;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != disk)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
 			break;
 		}
 	print_raid5_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid5_resize(mddev_t *mddev, sector_t sectors)

@@ -4739,7 +4739,7 @@ static int raid5_start_reshape(mddev_t *
 	rdev_for_each(rdev, rtmp, mddev)
 		if (rdev->raid_disk < 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
-			if (raid5_add_disk(mddev, rdev)) {
+			if (raid5_add_disk(mddev, rdev) == 0) {
 				char nm[20];
 				set_bit(In_sync, &rdev->flags);
 				added_devices++;

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -4300,9 +4300,6 @@ static int hot_remove_disk(mddev_t * mdd
 	char b[BDEVNAME_SIZE];
 	mdk_rdev_t *rdev;
 
-	if (!mddev->pers)
-		return -ENODEV;
-
 	rdev = find_rdev(mddev, dev);
 	if (!rdev)
 		return -ENXIO;

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -2716,8 +2716,10 @@ array_state_store(mddev_t *mddev, const 
 	}
 	if (err)
 		return err;
-	else
+	else {
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
 		return len;
+	}
 }
 static struct md_sysfs_entry md_array_state =
 __ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);

@@ -3408,7 +3410,11 @@ static void md_safemode_timeout(unsigned
 {
 	mddev_t *mddev = (mddev_t *) data;
 
-	mddev->safemode = 1;
+	if (!atomic_read(&mddev->writes_pending)) {
+		mddev->safemode = 1;
+		if (mddev->external)
+			sysfs_notify(&mddev->kobj, NULL, "array_state");
+	}
 	md_wakeup_thread(mddev->thread);
 }
 

@@ -3675,6 +3681,7 @@ static int do_md_run(mddev_t * mddev)
 
 	mddev->changed = 1;
 	md_new_event(mddev);
+	sysfs_notify(&mddev->kobj, NULL, "array_state");
 	kobject_uevent(&mddev->gendisk->dev.kobj, KOBJ_CHANGE);
 	return 0;
 }

@@ -3709,6 +3716,8 @@ static int restart_array(mddev_t *mddev)
 		md_wakeup_thread(mddev->thread);
 		md_wakeup_thread(mddev->sync_thread);
 		err = 0;
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
+
 	} else
 		err = -EINVAL;
 

@@ -3879,6 +3888,7 @@ static int do_md_stop(mddev_t * mddev, i
 			mdname(mddev));
 	err = 0;
 	md_new_event(mddev);
+	sysfs_notify(&mddev->kobj, NULL, "array_state");
 out:
 	return err;
 }

@@ -4876,8 +4886,9 @@ static int md_ioctl(struct inode *inode,
 	    mddev->ro && mddev->pers) {
 		if (mddev->ro == 2) {
 			mddev->ro = 0;
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-		md_wakeup_thread(mddev->thread);
+			sysfs_notify(&mddev->kobj, NULL, "array_state");
+			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			md_wakeup_thread(mddev->thread);
 
 		} else {
 			err = -EROFS;

@@ -5516,6 +5527,7 @@ void md_done_sync(mddev_t *mddev, int bl
  */
 void md_write_start(mddev_t *mddev, struct bio *bi)
 {
+	int did_change = 0;
 	if (bio_data_dir(bi) != WRITE)
 		return;
 

@@ -5526,6 +5538,7 @@ void md_write_start(mddev_t *mddev, stru
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		md_wakeup_thread(mddev->sync_thread);
+		did_change = 1;
 	}
 	atomic_inc(&mddev->writes_pending);
 	if (mddev->safemode == 1)

@@ -5536,10 +5549,12 @@ void md_write_start(mddev_t *mddev, stru
 			mddev->in_sync = 0;
 			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			md_wakeup_thread(mddev->thread);
+			did_change = 1;
 		}
 		spin_unlock_irq(&mddev->write_lock);
-		sysfs_notify(&mddev->kobj, NULL, "array_state");
 	}
+	if (did_change)
+		sysfs_notify(&mddev->kobj, NULL, "array_state");
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));

@@ -5991,18 +6006,22 @@ void md_check_recovery(mddev_t *mddev)
 		int spares = 0;
 
 		if (!mddev->external) {
+			int did_change = 0;
 			spin_lock_irq(&mddev->write_lock);
 			if (mddev->safemode &&
 			    !atomic_read(&mddev->writes_pending) &&
 			    !mddev->in_sync &&
 			    mddev->recovery_cp == MaxSector) {
 				mddev->in_sync = 1;
+				did_change = 1;
 				if (mddev->persistent)
 					set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			}
 			if (mddev->safemode == 1)
 				mddev->safemode = 0;
 			spin_unlock_irq(&mddev->write_lock);
+			if (did_change)
+				sysfs_notify(&mddev->kobj, NULL, "array_state");
 		}
 
 		if (mddev->flags)

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -169,7 +169,6 @@ void md_new_event(mddev_t *mddev)
 {
 	atomic_inc(&md_event_count);
 	wake_up(&md_event_waiters);
-	sysfs_notify(&mddev->kobj, NULL, "sync_action");
 }
 EXPORT_SYMBOL_GPL(md_new_event);
 

@@ -2936,7 +2935,7 @@ action_show(mddev_t *mddev, char *page)
 				type = "check";
 			else
 				type = "repair";
-		} else
+		} else if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
 			type = "recover";
 	}
 	return sprintf(page, "%s\n", type);

@@ -2958,9 +2957,12 @@ action_store(mddev_t *mddev, const char 
 	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
 		return -EBUSY;
-	else if (cmd_match(page, "resync") || cmd_match(page, "recover"))
+	else if (cmd_match(page, "resync"))
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	else if (cmd_match(page, "recover")) {
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	else if (cmd_match(page, "reshape")) {
+	} else if (cmd_match(page, "reshape")) {
 		int err;
 		if (mddev->pers->start_reshape == NULL)
 			return -EINVAL;

@@ -2977,6 +2979,7 @@ action_store(mddev_t *mddev, const char 
 	}
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
+	sysfs_notify(&mddev->kobj, NULL, "sync_action");
 	return len;
 }
 

@@ -3682,6 +3685,7 @@ static int do_md_run(mddev_t * mddev)
 	mddev->changed = 1;
 	md_new_event(mddev);
 	sysfs_notify(&mddev->kobj, NULL, "array_state");
+	sysfs_notify(&mddev->kobj, NULL, "sync_action");
 	kobject_uevent(&mddev->gendisk->dev.kobj, KOBJ_CHANGE);
 	return 0;
 }

@@ -4252,6 +4256,8 @@ static int add_new_disk(mddev_t * mddev,
 			export_rdev(rdev);
 
 		md_update_sb(mddev, 1);
+		if (mddev->degraded)
+			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
 		return err;

@@ -5105,6 +5111,8 @@ void md_error(mddev_t *mddev, mdk_rdev_t
 	if (!mddev->pers->error_handler)
 		return;
 	mddev->pers->error_handler(mddev,rdev);
+	if (mddev->degraded)
+		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);

@@ -6055,13 +6063,18 @@ void md_check_recovery(mddev_t *mddev)
 			mddev->recovery = 0;
 			/* flag recovery needed just to double check */
 			set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			sysfs_notify(&mddev->kobj, NULL, "sync_action");
 			md_new_event(mddev);
 			goto unlock;
 		}
+		/* Set RUNNING before clearing NEEDED to avoid
+		 * any transients in the value of "sync_action".
+		 */
+		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		/* Clear some bits that don't mean anything, but
 		 * might be left set
 		 */
-		clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 

@@ -6079,17 +6092,19 @@ void md_check_recovery(mddev_t *mddev)
 				/* Cannot proceed */
 				goto unlock;
 			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if ((spares = remove_and_add_spares(mddev))) {
 			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if (mddev->recovery_cp < MaxSector) {
 			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
 			/* nothing to be done ... */
 			goto unlock;
 
 		if (mddev->pers->sync_request) {
-			set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 			if (spares && mddev->bitmap && ! mddev->bitmap->file) {
 				/* We are adding a device or devices to an array
 				 * which has the bitmap stored on all devices.

@@ -6108,9 +6123,16 @@ void md_check_recovery(mddev_t *mddev)
 				mddev->recovery = 0;
 			} else
 				md_wakeup_thread(mddev->sync_thread);
+			sysfs_notify(&mddev->kobj, NULL, "sync_action");
 			md_new_event(mddev);
 		}
 	unlock:
+		if (!mddev->sync_thread) {
+			clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
+					       &mddev->recovery))
+				sysfs_notify(&mddev->kobj, NULL, "sync_action");
+		}
 		mddev_unlock(mddev);
 	}
 }

diff .prev/include/linux/raid/md_k.h ./include/linux/raid/md_k.h
@@ -188,6 +188,7 @@ struct mddev_s
 	 * NEEDED:   we might need to start a resync/recover
 	 * RUNNING:  a thread is running, or about to be started
 	 * SYNC:     actually doing a resync, not a recovery
+	 * RECOVER:  doing recovery, or need to try it.
 	 * INTR:     resync needs to be aborted for some reason
 	 * DONE:     thread is done and is waiting to be reaped
 	 * REQUEST:  user-space has requested a sync (used with SYNC)

@@ -198,6 +199,7 @@ struct mddev_s
 	 */
 #define	MD_RECOVERY_RUNNING	0
 #define	MD_RECOVERY_SYNC	1
+#define	MD_RECOVERY_RECOVER	2
 #define	MD_RECOVERY_INTR	3
 #define	MD_RECOVERY_DONE	4
 #define	MD_RECOVERY_NEEDED	5

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -2969,6 +2969,7 @@ action_store(mddev_t *mddev, const char 
 		err = mddev->pers->start_reshape(mddev);
 		if (err)
 			return err;
+		sysfs_notify(&mddev->kobj, NULL, "degraded");
 	} else {
 		if (cmd_match(page, "check"))
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);

@@ -3686,6 +3687,7 @@ static int do_md_run(mddev_t * mddev)
 	md_new_event(mddev);
 	sysfs_notify(&mddev->kobj, NULL, "array_state");
 	sysfs_notify(&mddev->kobj, NULL, "sync_action");
+	sysfs_notify(&mddev->kobj, NULL, "degraded");
 	kobject_uevent(&mddev->gendisk->dev.kobj, KOBJ_CHANGE);
 	return 0;
 }

@@ -6049,7 +6051,9 @@ void md_check_recovery(mddev_t *mddev)
 			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 				/* success...*/
 				/* activate any spares */
-				mddev->pers->spare_active(mddev);
+				if (mddev->pers->spare_active(mddev))
+					sysfs_notify(&mddev->kobj, NULL,
+						     "degraded");
 			}
 			md_update_sb(mddev, 1);
 

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -1886,6 +1886,8 @@ state_store(mdk_rdev_t *rdev, const char
 
 		err = 0;
 	}
+	if (!err)
+		sysfs_notify(&rdev->kobj, NULL, "state");
 	return err ? err : len;
 }
 static struct rdev_sysfs_entry rdev_state =

@@ -1979,7 +1981,8 @@ slot_store(mdk_rdev_t *rdev, const char 
 		if (err) {
 			rdev->raid_disk = -1;
 			return err;
-		}
+		} else
+			sysfs_notify(&rdev->kobj, NULL, "state");
 		sprintf(nm, "rd%d", rdev->raid_disk);
 		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
 			printk(KERN_WARNING

@@ -1996,6 +1999,7 @@ slot_store(mdk_rdev_t *rdev, const char 
 		clear_bit(Faulty, &rdev->flags);
 		clear_bit(WriteMostly, &rdev->flags);
 		set_bit(In_sync, &rdev->flags);
+		sysfs_notify(&rdev->kobj, NULL, "state");
 	}
 	return len;
 }

@@ -3525,6 +3529,7 @@ static int do_md_run(mddev_t * mddev)
 				return -EINVAL;
 			}
 		}
+		sysfs_notify(&rdev->kobj, NULL, "state");
 	}
 
 	md_probe(mddev->unit, NULL, NULL);

@@ -4256,6 +4261,8 @@ static int add_new_disk(mddev_t * mddev,
 		}
 		if (err)
 			export_rdev(rdev);
+		else
+			sysfs_notify(&rdev->kobj, NULL, "state");
 
 		md_update_sb(mddev, 1);
 		if (mddev->degraded)

@@ -5115,6 +5122,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t
 	mddev->pers->error_handler(mddev,rdev);
 	if (mddev->degraded)
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
+	set_bit(StateChanged, &rdev->flags);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);

@@ -6037,6 +6045,10 @@ void md_check_recovery(mddev_t *mddev)
 		if (mddev->flags)
 			md_update_sb(mddev, 0);
 
+		rdev_for_each(rdev, rtmp, mddev)
+			if (test_and_clear_bit(StateChanged, &rdev->flags))
+				sysfs_notify(&rdev->kobj, NULL, "state");
+
 
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
 		    !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {

diff .prev/include/linux/raid/md_k.h ./include/linux/raid/md_k.h
@@ -87,6 +87,9 @@ struct mdk_rdev_s
 #define Blocked		8		/* An error occured on an externally
 					 * managed array, don't allow writes
 					 * until it is cleared */
+#define StateChanged	9		/* Faulty or Blocked has changed during
+					 * interrupt, so it needs to be
+					 * notified by the thread */
 	wait_queue_head_t blocked_wait;
 
 	int desc_nr;			/* descriptor index in the superblock */

diff .prev/drivers/md/md.c ./drivers/md/md.c
@@ -658,11 +658,14 @@ static unsigned int calc_sb_csum(mdp_sup
  */
 
 struct super_type  {
-	char 		*name;
-	struct module	*owner;
-	int		(*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version);
-	int		(*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev);
-	void		(*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
+	char		    *name;
+	struct module	    *owner;
+	int		    (*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev,
+					  int minor_version);
+	int		    (*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev);
+	void		    (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev);
+	unsigned long long  (*rdev_size_change)(mdk_rdev_t *rdev,
+						unsigned long long size);
 };
 
 /*

@@ -1004,6 +1007,27 @@ static void super_90_sync(mddev_t *mddev
 }
 
 /*
+ * rdev_size_change for 0.90.0
+ */
+static unsigned long long
+super_90_rdev_size_change(mdk_rdev_t *rdev, unsigned long long size)
+{
+	if (size && size < rdev->mddev->size)
+		return 0; /* component must fit device */
+	size *= 2; /* convert to sectors */
+	if (rdev->mddev->bitmap_offset)
+		return 0; /* can't move bitmap */
+	rdev->sb_offset = calc_dev_sboffset(rdev->bdev);
+	if (!size || size > rdev->sb_offset*2)
+		size = rdev->sb_offset*2;
+	md_super_write(rdev->mddev, rdev, rdev->sb_offset << 1, rdev->sb_size,
+		       rdev->sb_page);
+	md_super_wait(rdev->mddev);
+	return size/2; /* kB for sysfs */
+}
+
+
+/*
  * version 1 superblock
  */
 

@@ -1328,21 +1352,59 @@ static void super_1_sync(mddev_t *mddev,
 	sb->sb_csum = calc_sb_1_csum(sb);
 }
 
+static unsigned long long
+super_1_rdev_size_change(mdk_rdev_t *rdev, unsigned long long size)
+{
+	struct mdp_superblock_1 *sb;
+	unsigned long long max_size;
+	if (size && size < rdev->mddev->size)
+		return 0; /* component must fit device */
+	size *= 2; /* convert to sectors */
+	if (rdev->sb_offset < rdev->data_offset/2) {
+		/* minor versions 1 and 2; superblock before data */
+		max_size = (rdev->bdev->bd_inode->i_size >> 9);
+		max_size -= rdev->data_offset;
+		if (!size || size > max_size)
+			size = max_size;
+	} else if (rdev->mddev->bitmap_offset) {
+		/* minor version 0 with bitmap we can't move */
+		return 0;
+	} else {
+		/* minor version 0; superblock after data */
+		sector_t sb_offset;
+		sb_offset = (rdev->bdev->bd_inode->i_size >> 9) - 8*2;
+		sb_offset &= ~(sector_t)(4*2 - 1);
+		max_size = rdev->size*2 + sb_offset - rdev->sb_offset*2;
+		if (!size || size > max_size)
+			size = max_size;
+		rdev->sb_offset = sb_offset/2;
+	}
+	sb = (struct mdp_superblock_1 *) page_address(rdev->sb_page);
+	sb->data_size = cpu_to_le64(size);
+	sb->super_offset = rdev->sb_offset*2;
+	sb->sb_csum = calc_sb_1_csum(sb);
+	md_super_write(rdev->mddev, rdev, rdev->sb_offset << 1, rdev->sb_size,
+		       rdev->sb_page);
+	md_super_wait(rdev->mddev);
+	return size/2; /* kB for sysfs */
+}
 
 static struct super_type super_types[] = {
 	[0] = {
 		.name	= "0.90.0",
 		.owner	= THIS_MODULE,
-		.load_super	= super_90_load,
-		.validate_super	= super_90_validate,
-		.sync_super	= super_90_sync,
+		.load_super	    = super_90_load,
+		.validate_super	    = super_90_validate,
+		.sync_super	    = super_90_sync,
+		.rdev_size_change   = super_90_rdev_size_change,
 	},
 	[1] = {
 		.name	= "md-1",
 		.owner	= THIS_MODULE,
-		.load_super	= super_1_load,
-		.validate_super	= super_1_validate,
-		.sync_super	= super_1_sync,
+		.load_super	    = super_1_load,
+		.validate_super	    = super_1_validate,
+		.sync_super	    = super_1_sync,
+		.rdev_size_change   = super_1_rdev_size_change,
 	},
 };
 

@@ -2060,8 +2122,20 @@ rdev_size_store(mdk_rdev_t *rdev, const 
 
 	if (e==buf || (*e && *e != '\n'))
 		return -EINVAL;
-	if (my_mddev->pers && rdev->raid_disk >= 0)
-		return -EBUSY;
+	if (my_mddev->pers && rdev->raid_disk >= 0) {
+		if (rdev->mddev->persistent) {
+			size = super_types[rdev->mddev->major_version].
+				rdev_size_change(rdev, size);
+			if (!size)
+				return -EBUSY;
+		} else if (!size) {
+			size = (rdev->bdev->bd_inode->i_size >> 10);
+			size -= rdev->data_offset/2;
+		}
+		if (size < rdev->mddev->size)
+			return -EINVAL; /* component must fit device */
+	}
+
 	rdev->size = size;
 	if (size > oldsize && rdev->mddev->external) {
 		/* need to check that all other rdevs with the same ->bdev

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -837,15 +837,10 @@ ops_run_postxor(struct stripe_head *sh, 
 static void ops_complete_check(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	int pd_idx = sh->pd_idx;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
-		sh->ops.zero_sum_result == 0)
-		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-
 	set_bit(STRIPE_OP_CHECK, &sh->ops.complete);
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);

@@ -873,11 +868,6 @@ static void ops_run_check(struct stripe_
 	tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
 		&sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
 
-	if (tx)
-		set_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-	else
-		clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-
 	atomic_inc(&sh->count);
 	tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
 		ops_complete_check, sh);

diff .prev/include/linux/raid/raid5.h ./include/linux/raid/raid5.h
@@ -267,10 +267,8 @@ struct r6_state {
 
 /* modifiers to the base operations
  * STRIPE_OP_MOD_REPAIR_PD - compute the parity block and write it back
- * STRIPE_OP_MOD_DMA_CHECK - parity is not corrupted by the check
  */
 #define STRIPE_OP_MOD_REPAIR_PD 7
-#define STRIPE_OP_MOD_DMA_CHECK 8
 
 /*
  * Plugging:

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -373,8 +373,6 @@ static unsigned long get_stripe_work(str
 	test_and_ack_op(STRIPE_OP_BIODRAIN, pending);
 	test_and_ack_op(STRIPE_OP_POSTXOR, pending);
 	test_and_ack_op(STRIPE_OP_CHECK, pending);
-	if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending))
-		ack++;
 
 	sh->ops.count -= ack;
 	if (unlikely(sh->ops.count < 0)) {

@@ -399,7 +397,6 @@ static void ops_run_io(struct stripe_hea
 
 	might_sleep();
 
-	set_bit(STRIPE_IO_STARTED, &sh->state);
 	for (i = disks; i--; ) {
 		int rw;
 		struct bio *bi;

@@ -433,6 +430,8 @@ static void ops_run_io(struct stripe_hea
 				test_bit(STRIPE_EXPAND_READY, &sh->state))
 				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
 
+			set_bit(STRIPE_IO_STARTED, &sh->state);
+
 			bi->bi_bdev = rdev->bdev;
 			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
 				__func__, (unsigned long long)sh->sector,

@@ -900,9 +899,6 @@ static void raid5_run_ops(struct stripe_
 	if (test_bit(STRIPE_OP_CHECK, &pending))
 		ops_run_check(sh);
 
-	if (test_bit(STRIPE_OP_IO, &pending))
-		ops_run_io(sh);
-
 	if (overlap_clear)
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];

@@ -2013,8 +2009,6 @@ static int __handle_issuing_new_read_req
 			 */
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantread, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			s->locked++;
 			pr_debug("Reading block %d (sync=%d)\n", disk_idx,
 				s->syncing);

@@ -2208,9 +2202,6 @@ static void handle_issuing_new_write_req
 						"%d for r-m-w\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
-					if (!test_and_set_bit(
-						STRIPE_OP_IO, &sh->ops.pending))
-						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);

@@ -2234,9 +2225,6 @@ static void handle_issuing_new_write_req
 						"%d for Reconstruct\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
-					if (!test_and_set_bit(
-						STRIPE_OP_IO, &sh->ops.pending))
-						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);

@@ -2444,8 +2432,6 @@ static void handle_parity_checks5(raid5_
 
 		set_bit(R5_LOCKED, &dev->flags);
 		set_bit(R5_Wantwrite, &dev->flags);
-		if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-			sh->ops.count++;
 
 		clear_bit(STRIPE_DEGRADED, &sh->state);
 		s->locked++;

@@ -2801,9 +2787,6 @@ static void handle_stripe5(struct stripe
 				(i == sh->pd_idx || dev->written)) {
 				pr_debug("Writing block %d\n", i);
 				set_bit(R5_Wantwrite, &dev->flags);
-				if (!test_and_set_bit(
-				    STRIPE_OP_IO, &sh->ops.pending))
-					sh->ops.count++;
 				if (prexor)
 					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||

@@ -2857,16 +2840,12 @@ static void handle_stripe5(struct stripe
 		dev = &sh->dev[s.failed_num];
 		if (!test_bit(R5_ReWrite, &dev->flags)) {
 			set_bit(R5_Wantwrite, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			set_bit(R5_ReWrite, &dev->flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		} else {
 			/* let's read it back */
 			set_bit(R5_Wantread, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		}

@@ -2884,13 +2863,10 @@ static void handle_stripe5(struct stripe
 		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
 		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
 
-		for (i = conf->raid_disks; i--; ) {
+		for (i = conf->raid_disks; i--; )
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
-		}
 	}
 
 	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&

@@ -2926,6 +2902,8 @@ static void handle_stripe5(struct stripe
 	if (pending)
 		raid5_run_ops(sh, pending);
 
+	ops_run_io(sh);
+
 	return_io(return_bi);
 
 }

diff .prev/include/linux/raid/raid5.h ./include/linux/raid/raid5.h
@@ -263,7 +263,6 @@ struct r6_state {
 #define STRIPE_OP_BIODRAIN	3
 #define STRIPE_OP_POSTXOR	4
 #define STRIPE_OP_CHECK	5
-#define STRIPE_OP_IO		6
 
 /* modifiers to the base operations
  * STRIPE_OP_MOD_REPAIR_PD - compute the parity block and write it back

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -390,7 +390,7 @@ raid5_end_read_request(struct bio *bi, i
 static void
 raid5_end_write_request(struct bio *bi, int error);
 
-static void ops_run_io(struct stripe_head *sh)
+static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int i, disks = sh->disks;

@@ -425,9 +425,7 @@ static void ops_run_io(struct stripe_hea
 		rcu_read_unlock();
 
 		if (rdev) {
-			if (test_bit(STRIPE_SYNCING, &sh->state) ||
-				test_bit(STRIPE_EXPAND_SOURCE, &sh->state) ||
-				test_bit(STRIPE_EXPAND_READY, &sh->state))
+			if (s->syncing || s->expanding || s->expanded)
 				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
 
 			set_bit(STRIPE_IO_STARTED, &sh->state);

@@ -2902,10 +2900,9 @@ static void handle_stripe5(struct stripe
 	if (pending)
 		raid5_run_ops(sh, pending);
 
-	ops_run_io(sh);
+	ops_run_io(sh, &s);
 
 	return_io(return_bi);
-
 }
 
 static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -3114,68 +3114,9 @@ static void handle_stripe6(struct stripe
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
-	return_io(return_bi);
-
-	for (i=disks; i-- ;) {
-		int rw;
-		struct bio *bi;
-		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
-			rw = READ;
-		else
-			continue;
-
-		set_bit(STRIPE_IO_STARTED, &sh->state);
-
-		bi = &sh->dev[i].req;
-
-		bi->bi_rw = rw;
-		if (rw == WRITE)
-			bi->bi_end_io = raid5_end_write_request;
-		else
-			bi->bi_end_io = raid5_end_read_request;
+	ops_run_io(sh, &s);
 
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (rdev && test_bit(Faulty, &rdev->flags))
-			rdev = NULL;
-		if (rdev)
-			atomic_inc(&rdev->nr_pending);
-		rcu_read_unlock();
-
-		if (rdev) {
-			if (s.syncing || s.expanding || s.expanded)
-				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
-
-			bi->bi_bdev = rdev->bdev;
-			pr_debug("for %llu schedule op %ld on disc %d\n",
-				(unsigned long long)sh->sector, bi->bi_rw, i);
-			atomic_inc(&sh->count);
-			bi->bi_sector = sh->sector + rdev->data_offset;
-			bi->bi_flags = 1 << BIO_UPTODATE;
-			bi->bi_vcnt = 1;
-			bi->bi_max_vecs = 1;
-			bi->bi_idx = 0;
-			bi->bi_io_vec = &sh->dev[i].vec;
-			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
-			bi->bi_io_vec[0].bv_offset = 0;
-			bi->bi_size = STRIPE_SIZE;
-			bi->bi_next = NULL;
-			if (rw == WRITE &&
-			    test_bit(R5_ReWrite, &sh->dev[i].flags))
-				atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
-			generic_make_request(bi);
-		} else {
-			if (rw == WRITE)
-				set_bit(STRIPE_DEGRADED, &sh->state);
-			pr_debug("skip op %ld on disc %d for sector %llu\n",
-				bi->bi_rw, i, (unsigned long long)sh->sector);
-			clear_bit(R5_LOCKED, &sh->dev[i].flags);
-			set_bit(STRIPE_HANDLE, &sh->state);
-		}
-	}
+	return_io(return_bi);
 }
 
 static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -605,7 +605,11 @@ static void ops_complete_compute5(void *
 	set_bit(R5_UPTODATE, &tgt->flags);
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 	clear_bit(R5_Wantcompute, &tgt->flags);
-	set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
+	clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
+	if (sh->check_state == check_state_compute_run)
+		sh->check_state = check_state_compute_result;
+	else
+		set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }

@@ -838,7 +842,7 @@ static void ops_complete_check(void *str
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	set_bit(STRIPE_OP_CHECK, &sh->ops.complete);
+	sh->check_state = check_state_check_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }

@@ -870,7 +874,8 @@ static void ops_run_check(struct stripe_
 		ops_complete_check, sh);
 }
 
-static void raid5_run_ops(struct stripe_head *sh, unsigned long pending)
+static void raid5_run_ops(struct stripe_head *sh, unsigned long pending,
+			  unsigned long ops_request)
 {
 	int overlap_clear = 0, i, disks = sh->disks;
 	struct dma_async_tx_descriptor *tx = NULL;

@@ -880,7 +885,8 @@ static void raid5_run_ops(struct stripe_
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending))
+	if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending) ||
+	    test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request))
 		tx = ops_run_compute5(sh, pending);
 
 	if (test_bit(STRIPE_OP_PREXOR, &pending))

@@ -894,7 +900,7 @@ static void raid5_run_ops(struct stripe_
 	if (test_bit(STRIPE_OP_POSTXOR, &pending))
 		ops_run_postxor(sh, tx, pending);
 
-	if (test_bit(STRIPE_OP_CHECK, &pending))
+	if (test_bit(STRIPE_OP_CHECK, &ops_request))
 		ops_run_check(sh);
 
 	if (overlap_clear)

@@ -1961,8 +1967,7 @@ static int __handle_issuing_new_read_req
 	/* don't schedule compute operations or reads on the parity block while
 	 * a check is in flight
 	 */
-	if ((disk_idx == sh->pd_idx) &&
-	     test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
+	if (disk_idx == sh->pd_idx && sh->check_state)
 		return ~0;
 
 	/* is the data in this block needed, and can we get it? */

@@ -1983,9 +1988,8 @@ static int __handle_issuing_new_read_req
 		 * 3/ We hold off parity block re-reads until check operations
 		 * have quiesced.
 		 */
-		if ((s->uptodate == disks - 1) &&
-		    (s->failed && disk_idx == s->failed_num) &&
-		    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
+		if ((s->uptodate == disks - 1) && !sh->check_state &&
+		    (s->failed && disk_idx == s->failed_num)) {
 			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
 			set_bit(R5_Wantcompute, &dev->flags);
 			sh->ops.target = disk_idx;

@@ -2021,12 +2025,8 @@ static void handle_issuing_new_read_requ
 {
 	int i;
 
-	/* Clear completed compute operations.  Parity recovery
-	 * (STRIPE_OP_MOD_REPAIR_PD) implies a write-back which is handled
-	 * later on in this routine
-	 */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-		!test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
+	/* Clear completed compute operations */
+	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete)) {
 		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
 		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
 		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);

@@ -2350,90 +2350,85 @@ static void handle_issuing_new_write_req
 static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks)
 {
-	int canceled_check = 0;
+	struct r5dev *dev = NULL;
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 
-	/* complete a check operation */
-	if (test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
+	switch (sh->check_state) {
+	case check_state_idle:
+		/* start a new check operation if there are no failures */
 		if (s->failed == 0) {
-			if (sh->ops.zero_sum_result == 0)
-				/* parity is correct (on disc,
-				 * not in buffer any more)
-				 */
-				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
-				conf->mddev->resync_mismatches +=
-					STRIPE_SECTORS;
-				if (test_bit(
-				     MD_RECOVERY_CHECK, &conf->mddev->recovery))
-					/* don't try to repair!! */
-					set_bit(STRIPE_INSYNC, &sh->state);
-				else {
-					set_bit(STRIPE_OP_COMPUTE_BLK,
-						&sh->ops.pending);
-					set_bit(STRIPE_OP_MOD_REPAIR_PD,
-						&sh->ops.pending);
-					set_bit(R5_Wantcompute,
-						&sh->dev[sh->pd_idx].flags);
-					sh->ops.target = sh->pd_idx;
-					sh->ops.count++;
-					s->uptodate++;
-				}
-			}
-		} else
-			canceled_check = 1; /* STRIPE_INSYNC is not set */
-	}
-
-	/* start a new check operation if there are no failures, the stripe is
-	 * not insync, and a repair is not in flight
-	 */
-	if (s->failed == 0 &&
-	    !test_bit(STRIPE_INSYNC, &sh->state) &&
-	    !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-		if (!test_and_set_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
 			BUG_ON(s->uptodate != disks);
+			sh->check_state = check_state_run;
+			set_bit(STRIPE_OP_CHECK, &s->ops_request);
 			clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
-			sh->ops.count++;
 			s->uptodate--;
+			break;
 		}
-	}
-
-	/* check if we can clear a parity disk reconstruct */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-	    test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-
-		clear_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
+		dev = &sh->dev[s->failed_num];
+		/* fall through */
+	case check_state_compute_result:
+		sh->check_state = check_state_idle;
+		if (!dev)
+			dev = &sh->dev[sh->pd_idx];
 
+		/* check that a write has not made the stripe insync */
+		if (test_bit(STRIPE_INSYNC, &sh->state))
+			break;
 
-	/* Wait for check parity and compute block operations to complete
-	 * before write-back.  If a failure occurred while the check operation
-	 * was in flight we need to cycle this stripe through handle_stripe
-	 * since the parity block may not be uptodate
-	 */
-	if (!canceled_check && !test_bit(STRIPE_INSYNC, &sh->state) &&
-	    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending) &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) {
-		struct r5dev *dev;
 		/* either failed parity check, or recovery is happening */
-		if (s->failed == 0)
-			s->failed_num = sh->pd_idx;
-		dev = &sh->dev[s->failed_num];
 		BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
 		BUG_ON(s->uptodate != disks);
 
 		set_bit(R5_LOCKED, &dev->flags);
+		s->locked++;
 		set_bit(R5_Wantwrite, &dev->flags);
 
 		clear_bit(STRIPE_DEGRADED, &sh->state);
-		s->locked++;
 		set_bit(STRIPE_INSYNC, &sh->state);
+		break;
+	case check_state_run:
+		break; /* we will be called again upon completion */
+	case check_state_check_result:
+		sh->check_state = check_state_idle;
+
+		/* if a failure occurred during the check operation, leave
+		 * STRIPE_INSYNC not set and let the stripe be handled again
+		 */
+		if (s->failed)
+			break;
+
+		/* handle a successful check operation, if parity is correct
+		 * we are done.  Otherwise update the mismatch count and repair
+		 * parity if !MD_RECOVERY_CHECK
+		 */
+		if (sh->ops.zero_sum_result == 0)
+			/* parity is correct (on disc,
+			 * not in buffer any more)
+			 */
+			set_bit(STRIPE_INSYNC, &sh->state);
+		else {
+			conf->mddev->resync_mismatches += STRIPE_SECTORS;
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+				/* don't try to repair!! */
+				set_bit(STRIPE_INSYNC, &sh->state);
+			else {
+				sh->check_state = check_state_compute_run;
+				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+				set_bit(R5_Wantcompute,
+					&sh->dev[sh->pd_idx].flags);
+				sh->ops.target = sh->pd_idx;
+				s->uptodate++;
+			}
+		}
+		break;
+	case check_state_compute_run:
+		break;
+	default:
+		printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+		       __func__, sh->check_state,
+		       (unsigned long long) sh->sector);
+		BUG();
 	}
 }
 

@@ -2807,7 +2802,7 @@ static void handle_stripe5(struct stripe
 	 *    block.
 	 */
 	if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) &&
-			  !test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
+	    !sh->check_state)
 		handle_issuing_new_write_requests5(conf, sh, &s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe

@@ -2815,11 +2810,10 @@ static void handle_stripe5(struct stripe
 	 * data is available.  The parity check is held off while parity
 	 * dependent operations are in flight.
 	 */
-	if ((s.syncing && s.locked == 0 &&
+	if (sh->check_state ||
+	    (s.syncing && s.locked == 0 &&
 	     !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
-	     !test_bit(STRIPE_INSYNC, &sh->state)) ||
-	      test_bit(STRIPE_OP_CHECK, &sh->ops.pending) ||
-	      test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending))
+	     !test_bit(STRIPE_INSYNC, &sh->state)))
 		handle_parity_checks5(conf, sh, &s, disks);
 
 	if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {

@@ -2897,8 +2891,8 @@ static void handle_stripe5(struct stripe
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
-	if (pending)
-		raid5_run_ops(sh, pending);
+	if (pending || s.ops_request)
+		raid5_run_ops(sh, pending, s.ops_request);
 
 	ops_run_io(sh, &s);
 

77 lines not on this page · raw message

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -523,38 +523,34 @@ static void ops_complete_biofill(void *s
 		(unsigned long long)sh->sector);
 
 	/* clear completed biofills */
+	spin_lock_irq(&conf->device_lock);
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
 		/* acknowledge completion of a biofill operation */
 		/* and check if we need to reply to a read request,
 		 * new R5_Wantfill requests are held off until
-		 * !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending)
+		 * !STRIPE_BIOFILL_RUN
 		 */
 		if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
 			struct bio *rbi, *rbi2;
 
-			/* The access to dev->read is outside of the
-			 * spin_lock_irq(&conf->device_lock), but is protected
-			 * by the STRIPE_OP_BIOFILL pending bit
-			 */
 			BUG_ON(!dev->read);
 			rbi = dev->read;
 			dev->read = NULL;
 			while (rbi && rbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
-				spin_lock_irq(&conf->device_lock);
 				if (--rbi->bi_phys_segments == 0) {
 					rbi->bi_next = return_bi;
 					return_bi = rbi;
 				}
-				spin_unlock_irq(&conf->device_lock);
 				rbi = rbi2;
 			}
 		}
 	}
-	set_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
+	spin_unlock_irq(&conf->device_lock);
+	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
 	return_io(return_bi);
 

@@ -880,7 +876,7 @@ static void raid5_run_ops(struct stripe_
 	int overlap_clear = 0, i, disks = sh->disks;
 	struct dma_async_tx_descriptor *tx = NULL;
 
-	if (test_bit(STRIPE_OP_BIOFILL, &pending)) {
+	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
 	}

@@ -2630,15 +2626,8 @@ static void handle_stripe5(struct stripe
 	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
 	s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
-	/* Now to look around and see what can be done */
-
-	/* clean-up completed biofill operations */
-	if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
-	}
 
+	/* Now to look around and see what can be done */
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;

@@ -2652,10 +2641,10 @@ static void handle_stripe5(struct stripe
 		/* maybe we can request a biofill operation
 		 *
 		 * new wantfill requests are only permitted while
-		 * STRIPE_OP_BIOFILL is clear
+		 * ops_complete_biofill is guaranteed to be inactive
 		 */
 		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
-			!test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+		    !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
 			set_bit(R5_Wantfill, &dev->flags);
 
 		/* now count some things */

@@ -2699,8 +2688,10 @@ static void handle_stripe5(struct stripe
 		goto unlock;
 	}
 
-	if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
-		sh->ops.count++;
+	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+		set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+		set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+	}
 
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 		" to_write=%d failed=%d failed_num=%d\n",

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -604,8 +604,6 @@ static void ops_complete_compute5(void *
 	clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
 	if (sh->check_state == check_state_compute_run)
 		sh->check_state = check_state_compute_result;
-	else
-		set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }

@@ -881,8 +879,7 @@ static void raid5_run_ops(struct stripe_
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending) ||
-	    test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request))
+	if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request))
 		tx = ops_run_compute5(sh, pending);
 
 	if (test_bit(STRIPE_OP_PREXOR, &pending))

@@ -1960,12 +1957,6 @@ static int __handle_issuing_new_read_req
 	struct r5dev *dev = &sh->dev[disk_idx];
 	struct r5dev *failed_dev = &sh->dev[s->failed_num];
 
-	/* don't schedule compute operations or reads on the parity block while
-	 * a check is in flight
-	 */
-	if (disk_idx == sh->pd_idx && sh->check_state)
-		return ~0;
-
 	/* is the data in this block needed, and can we get it? */
 	if (!test_bit(R5_LOCKED, &dev->flags) &&
 	    !test_bit(R5_UPTODATE, &dev->flags) && (dev->toread ||

@@ -1974,23 +1965,16 @@ static int __handle_issuing_new_read_req
 	     (failed_dev->toread || (failed_dev->towrite &&
 	     !test_bit(R5_OVERWRITE, &failed_dev->flags)
 	     ))))) {
-		/* 1/ We would like to get this block, possibly by computing it,
-		 * but we might not be able to.
-		 *
-		 * 2/ Since parity check operations potentially make the parity
-		 * block !uptodate it will need to be refreshed before any
-		 * compute operations on data disks are scheduled.
-		 *
-		 * 3/ We hold off parity block re-reads until check operations
-		 * have quiesced.
+		/* We would like to get this block, possibly by computing it,
+		 * otherwise read it if the backing disk is insync
 		 */
-		if ((s->uptodate == disks - 1) && !sh->check_state &&
+		if ((s->uptodate == disks - 1) &&
 		    (s->failed && disk_idx == s->failed_num)) {
-			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
+			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
 			set_bit(R5_Wantcompute, &dev->flags);
 			sh->ops.target = disk_idx;
 			s->req_compute = 1;
-			sh->ops.count++;
 			/* Careful: from this point on 'uptodate' is in the eye
 			 * of raid5_run_ops which services 'compute' operations
 			 * before writes. R5_Wantcompute flags a block that will

@@ -1999,12 +1983,7 @@ static int __handle_issuing_new_read_req
 			 */
 			s->uptodate++;
 			return 0; /* uptodate + compute == disks */
-		} else if ((s->uptodate < disks - 1) &&
-			test_bit(R5_Insync, &dev->flags)) {
-			/* Note: we hold off compute operations while checks are
-			 * in flight, but we still prefer 'compute' over 'read'
-			 * hence we only read if (uptodate < * disks-1)
-			 */
+		} else if (test_bit(R5_Insync, &dev->flags)) {
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantread, &dev->flags);
 			s->locked++;

@@ -2021,20 +2000,13 @@ static void handle_issuing_new_read_requ
 {
 	int i;
 
-	/* Clear completed compute operations */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
-
 	/* look for blocks to read/compute, skip this if a compute
 	 * is already in flight, or if the stripe contents are in the
 	 * midst of changing due to a write
 	 */
-	if (!test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
-		!test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+	    !test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
+	    !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
 		for (i = disks; i--; )
 			if (__handle_issuing_new_read_requests5(
 				sh, s, i, disks) == 0)

@@ -2236,10 +2208,9 @@ static void handle_issuing_new_write_req
 	 * simultaneously.  If this is not the case then new writes need to be
 	 * held off until the compute completes.
 	 */
-	if ((s->req_compute ||
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) &&
-		(s->locked == 0 && (rcw == 0 || rmw == 0) &&
-		!test_bit(STRIPE_BIT_DELAY, &sh->state)))
+	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+	    (s->locked == 0 && (rcw == 0 || rmw == 0) &&
+	    !test_bit(STRIPE_BIT_DELAY, &sh->state)))
 		s->locked += handle_write_operations5(sh, rcw == 0, 0);
 }
 

@@ -2410,6 +2381,7 @@ static void handle_parity_checks5(raid5_
 				set_bit(STRIPE_INSYNC, &sh->state);
 			else {
 				sh->check_state = check_state_compute_run;
+				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
 				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
 				set_bit(R5_Wantcompute,
 					&sh->dev[sh->pd_idx].flags);

@@ -2725,8 +2697,7 @@ static void handle_stripe5(struct stripe
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite ||
-	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding ||
-	    test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
 		handle_issuing_new_read_requests5(sh, &s, disks);
 
 	/* Now we check to see if any write operations have recently

@@ -2803,7 +2774,7 @@ static void handle_stripe5(struct stripe
 	 */
 	if (sh->check_state ||
 	    (s.syncing && s.locked == 0 &&
-	     !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
+	     !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
 	     !test_bit(STRIPE_INSYNC, &sh->state)))
 		handle_parity_checks5(conf, sh, &s, disks);
 

@@ -2869,7 +2840,7 @@ static void handle_stripe5(struct stripe
 	}
 
 	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
 		handle_stripe_expansion(conf, sh, NULL);
 
 	if (sh->ops.count)

@@ -3089,7 +3060,7 @@ static void handle_stripe6(struct stripe
 	}
 
 	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
 		handle_stripe_expansion(conf, sh, &r6s);
 
  unlock:

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
@@ -122,6 +122,13 @@ static void return_io(struct bio *return
 
 static void print_raid5_conf (raid5_conf_t *conf);
 
+static int stripe_operations_active(struct stripe_head *sh)
+{
+	return sh->check_state || sh->reconstruct_state ||
+	       test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
+	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
+}
+
 static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 {
 	if (atomic_dec_and_test(&sh->count)) {

@@ -141,7 +148,7 @@ static void __release_stripe(raid5_conf_
 			}
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
-			BUG_ON(sh->ops.pending);
+			BUG_ON(stripe_operations_active(sh));
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 				atomic_dec(&conf->preread_active_stripes);
 				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)

@@ -243,7 +250,7 @@ static void init_stripe(struct stripe_he
 
 	BUG_ON(atomic_read(&sh->count) != 0);
 	BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
-	BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete);
+	BUG_ON(stripe_operations_active(sh));
 
 	CHECK_DEVLOCK();
 	pr_debug("init_stripe called, stripe %llu\n",

@@ -344,47 +351,6 @@ static struct stripe_head *get_active_st
 	return sh;
 }
 
-/* test_and_ack_op() ensures that we only dequeue an operation once */
-#define test_and_ack_op(op, pend) \
-do {							\
-	if (test_bit(op, &sh->ops.pending) &&		\
-		!test_bit(op, &sh->ops.complete)) {	\
-		if (test_and_set_bit(op, &sh->ops.ack)) \
-			clear_bit(op, &pend);		\
-		else					\
-			ack++;				\
-	} else						\
-		clear_bit(op, &pend);			\
-} while (0)
-
-/* find new work to run, do not resubmit work that is already
- * in flight
- */
-static unsigned long get_stripe_work(struct stripe_head *sh)
-{
-	unsigned long pending;
-	int ack = 0;
-
-	pending = sh->ops.pending;
-
-	test_and_ack_op(STRIPE_OP_BIOFILL, pending);
-	test_and_ack_op(STRIPE_OP_COMPUTE_BLK, pending);
-	test_and_ack_op(STRIPE_OP_PREXOR, pending);
-	test_and_ack_op(STRIPE_OP_BIODRAIN, pending);
-	test_and_ack_op(STRIPE_OP_POSTXOR, pending);
-	test_and_ack_op(STRIPE_OP_CHECK, pending);
-
-	sh->ops.count -= ack;
-	if (unlikely(sh->ops.count < 0)) {
-		printk(KERN_ERR "pending: %#lx ops.pending: %#lx ops.ack: %#lx "
-			"ops.complete: %#lx\n", pending, sh->ops.pending,
-			sh->ops.ack, sh->ops.complete);
-		BUG();
-	}
-
-	return pending;
-}
-
 static void
 raid5_end_read_request(struct bio *bi, int error);
 static void

@@ -609,7 +575,7 @@ static void ops_complete_compute5(void *
 }
 
 static struct dma_async_tx_descriptor *
-ops_run_compute5(struct stripe_head *sh, unsigned long pending)
+ops_run_compute5(struct stripe_head *sh, unsigned long ops_request)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;

@@ -640,7 +606,7 @@ ops_run_compute5(struct stripe_head *sh,
 			ops_complete_compute5, sh);
 
 	/* ack now if postxor is not set to be run */
-	if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending))
+	if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
 		async_tx_ack(tx);
 
 	return tx;

@@ -652,8 +618,6 @@ static void ops_complete_prexor(void *st
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
-
-	set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
 }
 
 static struct dma_async_tx_descriptor *

@@ -686,7 +650,7 @@ ops_run_prexor(struct stripe_head *sh, s
 
 static struct dma_async_tx_descriptor *
 ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		 unsigned long pending)
+		 unsigned long ops_request)
 {
 	int disks = sh->disks;
 	int pd_idx = sh->pd_idx, i;

@@ -694,7 +658,7 @@ ops_run_biodrain(struct stripe_head *sh,
 	/* check if prexor is active which means only process blocks
 	 * that are part of a read-modify-write (Wantprexor)
 	 */
-	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
+	int prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);

@@ -744,7 +708,7 @@ static void ops_complete_postxor(void *s
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
+	sh->reconstruct_state = reconstruct_state_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }

@@ -763,16 +727,14 @@ static void ops_complete_write(void *str
 			set_bit(R5_UPTODATE, &dev->flags);
 	}
 
-	set_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
-	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-
+	sh->reconstruct_state = reconstruct_state_drain_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
 
 static void
 ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		unsigned long pending)
+		unsigned long ops_request)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;

@@ -780,7 +742,7 @@ ops_run_postxor(struct stripe_head *sh, 
 
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest;
-	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
+	int prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
 	unsigned long flags;
 	dma_async_tx_callback callback;
 

@@ -807,7 +769,7 @@ ops_run_postxor(struct stripe_head *sh, 
 	}
 
 	/* check whether this postxor is part of a write */
-	callback = test_bit(STRIPE_OP_BIODRAIN, &pending) ?
+	callback = test_bit(STRIPE_OP_BIODRAIN, &ops_request) ?
 		ops_complete_write : ops_complete_postxor;
 
 	/* 1/ if we prexor'd then the dest is reused as a source

@@ -868,8 +830,7 @@ static void ops_run_check(struct stripe_
 		ops_complete_check, sh);
 }
 
-static void raid5_run_ops(struct stripe_head *sh, unsigned long pending,
-			  unsigned long ops_request)
+static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
 {
 	int overlap_clear = 0, i, disks = sh->disks;
 	struct dma_async_tx_descriptor *tx = NULL;

@@ -880,18 +841,18 @@ static void raid5_run_ops(struct stripe_
 	}
 
 	if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request))
-		tx = ops_run_compute5(sh, pending);
+		tx = ops_run_compute5(sh, ops_request);
 
-	if (test_bit(STRIPE_OP_PREXOR, &pending))
+	if (test_bit(STRIPE_OP_PREXOR, &ops_request))
 		tx = ops_run_prexor(sh, tx);
 
-	if (test_bit(STRIPE_OP_BIODRAIN, &pending)) {
-		tx = ops_run_biodrain(sh, tx, pending);
+	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
+		tx = ops_run_biodrain(sh, tx, ops_request);
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_POSTXOR, &pending))
-		ops_run_postxor(sh, tx, pending);
+	if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
+		ops_run_postxor(sh, tx, ops_request);
 
 	if (test_bit(STRIPE_OP_CHECK, &ops_request))
 		ops_run_check(sh);

@@ -1684,11 +1645,11 @@ static void compute_block_2(struct strip
 	}
 }
 
-static int
-handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
+static void
+handle_write_operations5(struct stripe_head *sh, struct stripe_head_state *s,
+			 int rcw, int expand)
 {
 	int i, pd_idx = sh->pd_idx, disks = sh->disks;
-	int locked = 0;
 
 	if (rcw) {
 		/* if we are not expanding this is a proper write request, and

@@ -1696,12 +1657,12 @@ handle_write_operations5(struct stripe_h
 		 * stripe cache
 		 */
 		if (!expand) {
-			set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-			sh->ops.count++;
-		}
+			sh->reconstruct_state = reconstruct_state_drain_run;
+			set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		} else
+			sh->reconstruct_state = reconstruct_state_run;
 
-		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-		sh->ops.count++;
+		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];

@@ -1710,21 +1671,20 @@ handle_write_operations5(struct stripe_h
 				set_bit(R5_LOCKED, &dev->flags);
 				if (!expand)
 					clear_bit(R5_UPTODATE, &dev->flags);
-				locked++;
+				s->locked++;
 			}
 		}
-		if (locked + 1 == disks)
+		if (s->locked + 1 == disks)
 			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
 				atomic_inc(&sh->raid_conf->pending_full_writes);
 	} else {
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
-		set_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-		set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-
-		sh->ops.count += 3;
+		sh->reconstruct_state = reconstruct_state_drain_run;
+		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];

@@ -1742,7 +1702,7 @@ handle_write_operations5(struct stripe_h
 				set_bit(R5_Wantprexor, &dev->flags);
 				set_bit(R5_LOCKED, &dev->flags);
 				clear_bit(R5_UPTODATE, &dev->flags);
-				locked++;
+				s->locked++;
 			}
 		}
 	}

@@ -1752,13 +1712,11 @@ handle_write_operations5(struct stripe_h
 	 */
 	set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
 	clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-	locked++;
+	s->locked++;
 
-	pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
+	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
 		__func__, (unsigned long long)sh->sector,
-		locked, sh->ops.pending);
-
-	return locked;
+		s->locked, s->ops_request);
 }
 
 /*

@@ -2005,8 +1963,7 @@ static void handle_issuing_new_read_requ
 	 * midst of changing due to a write
 	 */
 	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
-	    !test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
-	    !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+	    !sh->reconstruct_state) {
 		for (i = disks; i--; )
 			if (__handle_issuing_new_read_requests5(
 				sh, s, i, disks) == 0)

@@ -2211,7 +2168,7 @@ static void handle_issuing_new_write_req
 	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
 	    (s->locked == 0 && (rcw == 0 || rmw == 0) &&
 	    !test_bit(STRIPE_BIT_DELAY, &sh->state)))
-		s->locked += handle_write_operations5(sh, rcw == 0, 0);
+		handle_write_operations5(sh, s, rcw == 0, 0);
 }
 
 static void handle_issuing_new_write_requests6(raid5_conf_t *conf,

@@ -2581,15 +2538,14 @@ static void handle_stripe5(struct stripe
 	struct bio *return_bi = NULL;
 	struct stripe_head_state s;
 	struct r5dev *dev;
-	unsigned long pending = 0;
 	mdk_rdev_t *blocked_rdev = NULL;
 	int prexor;
 
 	memset(&s, 0, sizeof(s));
-	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
-		"ops=%lx:%lx:%lx\n", (unsigned long long)sh->sector, sh->state,
-		atomic_read(&sh->count), sh->pd_idx,
-		sh->ops.pending, sh->ops.ack, sh->ops.complete);
+	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
+		 "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state,
+		 atomic_read(&sh->count), sh->pd_idx, sh->check_state,
+		 sh->reconstruct_state);
 
 	spin_lock(&sh->lock);
 	clear_bit(STRIPE_HANDLE, &sh->state);

@@ -2703,34 +2659,12 @@ static void handle_stripe5(struct stripe
 	/* Now we check to see if any write operations have recently
 	 * completed
 	 */
-
-	/* leave prexor set until postxor is done, allows us to distinguish
-	 * a rmw from a rcw during biodrain
-	 */
 	prexor = 0;
-	if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
-		prexor = 1;
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-
+	if (sh->reconstruct_state == reconstruct_state_drain_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
 		for (i = disks; i--; )
-			clear_bit(R5_Wantprexor, &sh->dev[i].flags);
-	}
-
-	/* if only POSTXOR is set then this is an 'expand' postxor */
-	if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+			prexor += test_and_clear_bit(R5_Wantprexor,
+						     &sh->dev[i].flags);
 
 		/* All the 'written' buffers and the parity block are ready to
 		 * be written back to disk

@@ -2763,8 +2697,7 @@ static void handle_stripe5(struct stripe
 	 * 2/ A 'check' operation is in flight, as it may clobber the parity
 	 *    block.
 	 */
-	if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) &&
-	    !sh->check_state)
+	if (s.to_write && !sh->reconstruct_state && !sh->check_state)
 		handle_issuing_new_write_requests5(conf, sh, &s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe

@@ -2805,18 +2738,10 @@ static void handle_stripe5(struct stripe
 		}
 	}
 
-	/* Finish postxor operations initiated by the expansion
-	 * process
-	 */
-	if (test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete) &&
-		!test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending)) {
-
+	/* Finish reconstruct operations initiated by the expansion process */
+	if (sh->reconstruct_state == reconstruct_state_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
 		clear_bit(STRIPE_EXPANDING, &sh->state);
-
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-
 		for (i = conf->raid_disks; i--; )
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
 			set_bit(R5_LOCKED, &dev->flags);