11 files changed, 856 insertions, 241 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 41df4cda66e2..2fba2bbe72d8 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -270,19 +270,20 @@ static struct page *read_sb_page(mddev_t *mddev, long offset, unsigned long inde
 
 	if (!page)
 		return ERR_PTR(-ENOMEM);
-	do {
-		ITERATE_RDEV(mddev, rdev, tmp)
-			if (rdev->in_sync && !rdev->faulty)
-				goto found;
-		return ERR_PTR(-EIO);
 
-	found:
+	ITERATE_RDEV(mddev, rdev, tmp) {
+		if (! rdev->in_sync || rdev->faulty)
+			continue;
+
 		target = (rdev->sb_offset << 1) + offset + index * (PAGE_SIZE/512);
 
-	} while (!sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ));
+		if (sync_page_io(rdev->bdev, target, PAGE_SIZE, page, READ)) {
+			page->index = index;
+			return page;
+		}
+	}
+	return ERR_PTR(-EIO);
 
-	page->index = index;
-	return page;
 }
 
 static int write_sb_page(mddev_t *mddev, long offset, struct page *page, int wait)
@@ -437,6 +438,7 @@ void bitmap_print_sb(struct bitmap *bitmap)
 	printk(KERN_DEBUG "  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
 	printk(KERN_DEBUG "     sync size: %llu KB\n",
 			(unsigned long long)le64_to_cpu(sb->sync_size)/2);
+	printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind));
 	kunmap(bitmap->sb_page);
 }
 
@@ -445,7 +447,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 {
 	char *reason = NULL;
 	bitmap_super_t *sb;
-	unsigned long chunksize, daemon_sleep;
+	unsigned long chunksize, daemon_sleep, write_behind;
 	unsigned long bytes_read;
 	unsigned long long events;
 	int err = -EINVAL;
@@ -474,6 +476,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 
 	chunksize = le32_to_cpu(sb->chunksize);
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep);
+	write_behind = le32_to_cpu(sb->write_behind);
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -485,7 +488,9 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	else if ((1 << ffz(~chunksize)) != chunksize)
 		reason = "bitmap chunksize not a power of 2";
 	else if (daemon_sleep < 1 || daemon_sleep > 15)
-		reason = "daemon sleep period out of range";
+		reason = "daemon sleep period out of range (1-15s)";
+	else if (write_behind > COUNTER_MAX)
+		reason = "write-behind limit out of range (0 - 16383)";
 	if (reason) {
 		printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",
 			bmname(bitmap), reason);
@@ -518,8 +523,12 @@ success:
 	/* assign fields using values from superblock */
 	bitmap->chunksize = chunksize;
 	bitmap->daemon_sleep = daemon_sleep;
+	bitmap->daemon_lastrun = jiffies;
+	bitmap->max_write_behind = write_behind;
 	bitmap->flags |= sb->state;
 	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
+	if (sb->state & BITMAP_STALE)
+		bitmap->events_cleared = bitmap->mddev->events;
 	err = 0;
 out:
 	kunmap(bitmap->sb_page);
@@ -617,7 +626,7 @@ static void bitmap_file_unmap(struct bitmap *bitmap)
 		page_cache_release(sb_page);
 }
 
-static void bitmap_stop_daemons(struct bitmap *bitmap);
+static void bitmap_stop_daemon(struct bitmap *bitmap);
 
 /* dequeue the next item in a page list -- don't call from irq context */
 static struct page_list *dequeue_page(struct bitmap *bitmap)
@@ -659,7 +668,7 @@ static void bitmap_file_put(struct bitmap *bitmap)
 	bitmap->file = NULL;
 	spin_unlock_irqrestore(&bitmap->lock, flags);
 
-	bitmap_stop_daemons(bitmap);
+	bitmap_stop_daemon(bitmap);
 
 	drain_write_queues(bitmap);
 
@@ -818,7 +827,7 @@ int bitmap_unplug(struct bitmap *bitmap)
 	return 0;
 }
 
-static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset);
+static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
 /* * bitmap_init_from_disk -- called at bitmap_create time to initialize
  * the in-memory bitmap from the on-disk bitmap -- also, sets up the
  * memory mapping of the bitmap file
@@ -826,8 +835,11 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset);
  *   if there's no bitmap file, or if the bitmap file had been
  *   previously kicked from the array, we mark all the bits as
  *   1's in order to cause a full resync.
+ *
+ * We ignore all bits for sectors that end earlier than 'start'.
+ * This is used when reading an out-of-date bitmap...
  */
-static int bitmap_init_from_disk(struct bitmap *bitmap)
+static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
 {
 	unsigned long i, chunks, index, oldindex, bit;
 	struct page *page = NULL, *oldpage = NULL;
@@ -914,7 +926,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap)
 			 	 * whole page and write it out
 				 */
 				memset(page_address(page) + offset, 0xff,
-					PAGE_SIZE - offset);
+				       PAGE_SIZE - offset);
 				ret = write_page(bitmap, page, 1);
 				if (ret) {
 					kunmap(page);
@@ -928,8 +940,11 @@ static int bitmap_init_from_disk(struct bitmap *bitmap)
 		}
 		if (test_bit(bit, page_address(page))) {
 			/* if the disk bit is set, set the memory bit */
-			bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap));
+			bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
+					       ((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
+				);
 			bit_cnt++;
+			set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
 		}
 	}
 
@@ -1141,6 +1156,9 @@ static void bitmap_writeback_daemon(mddev_t *mddev)
 		err = -EINTR;
 		goto out;
 	}
+	if (bitmap == NULL)
+		/* about to be stopped. */
+		return;
 
 	PRINTK("%s: bitmap writeback daemon woke up...\n", bmname(bitmap));
 	/* wait on bitmap page writebacks */
@@ -1170,21 +1188,12 @@ static void bitmap_writeback_daemon(mddev_t *mddev)
 	}
 }
 
-static int bitmap_start_daemon(struct bitmap *bitmap, mdk_thread_t **ptr,
+static mdk_thread_t *bitmap_start_daemon(struct bitmap *bitmap,
 				void (*func)(mddev_t *), char *name)
 {
 	mdk_thread_t *daemon;
-	unsigned long flags;
 	char namebuf[32];
 
-	spin_lock_irqsave(&bitmap->lock, flags);
-	*ptr = NULL;
-
-	if (!bitmap->file) /* no need for daemon if there's no backing file */
-		goto out_unlock;
-
-	spin_unlock_irqrestore(&bitmap->lock, flags);
-
 #ifdef INJECT_FATAL_FAULT_2
 	daemon = NULL;
 #else
@@ -1194,47 +1203,32 @@ static int bitmap_start_daemon(struct bitmap *bitmap, mdk_thread_t **ptr,
 	if (!daemon) {
 		printk(KERN_ERR "%s: failed to start bitmap daemon\n",
 			bmname(bitmap));
-		return -ECHILD;
+		return ERR_PTR(-ECHILD);
 	}
 
-	spin_lock_irqsave(&bitmap->lock, flags);
-	*ptr = daemon;
-
 	md_wakeup_thread(daemon); /* start it running */
 
 	PRINTK("%s: %s daemon (pid %d) started...\n",
 		bmname(bitmap), name, daemon->tsk->pid);
-out_unlock:
-	spin_unlock_irqrestore(&bitmap->lock, flags);
-	return 0;
-}
 
-static int bitmap_start_daemons(struct bitmap *bitmap)
-{
-	int err = bitmap_start_daemon(bitmap, &bitmap->writeback_daemon,
-					bitmap_writeback_daemon, "bitmap_wb");
-	return err;
+	return daemon;
 }
 
-static void bitmap_stop_daemon(struct bitmap *bitmap, mdk_thread_t **ptr)
+static void bitmap_stop_daemon(struct bitmap *bitmap)
 {
-	mdk_thread_t *daemon;
-	unsigned long flags;
-
-	spin_lock_irqsave(&bitmap->lock, flags);
-	daemon = *ptr;
-	*ptr = NULL;
-	spin_unlock_irqrestore(&bitmap->lock, flags);
-	if (daemon)
-		md_unregister_thread(daemon); /* destroy the thread */
-}
+	/* the daemon can't stop itself... it'll just exit instead... */
+	if (bitmap->writeback_daemon && ! IS_ERR(bitmap->writeback_daemon) &&
+	    current->pid != bitmap->writeback_daemon->tsk->pid) {
+		mdk_thread_t *daemon;
+		unsigned long flags;
 
-static void bitmap_stop_daemons(struct bitmap *bitmap)
-{
-	/* the daemons can't stop themselves... they'll just exit instead... */
-	if (bitmap->writeback_daemon &&
-	    current->pid != bitmap->writeback_daemon->tsk->pid)
-		bitmap_stop_daemon(bitmap, &bitmap->writeback_daemon);
+		spin_lock_irqsave(&bitmap->lock, flags);
+		daemon = bitmap->writeback_daemon;
+		bitmap->writeback_daemon = NULL;
+		spin_unlock_irqrestore(&bitmap->lock, flags);
+		if (daemon && ! IS_ERR(daemon))
+			md_unregister_thread(daemon); /* destroy the thread */
+	}
 }
 
 static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
@@ -1274,9 +1268,16 @@ static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
 	}
 }
 
-int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors)
+int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
 {
 	if (!bitmap) return 0;
+
+	if (behind) {
+		atomic_inc(&bitmap->behind_writes);
+		PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n",
+		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
+	}
+
 	while (sectors) {
 		int blocks;
 		bitmap_counter_t *bmc;
@@ -1311,9 +1312,15 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
 }
 
 void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
-		     int success)
+		     int success, int behind)
 {
 	if (!bitmap) return;
+	if (behind) {
+		atomic_dec(&bitmap->behind_writes);
+		PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
+		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
+	}
+
 	while (sectors) {
 		int blocks;
 		unsigned long flags;
@@ -1424,7 +1431,7 @@ void bitmap_close_sync(struct bitmap *bitmap)
 	}
 }
 
-static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset)
+static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
 {
 	/* For each chunk covered by any of these sectors, set the
 	 * counter to 1 and set resync_needed.  They should all
@@ -1441,7 +1448,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset)
 	}
 	if (! *bmc) {
 		struct page *page;
-		*bmc = 1 | NEEDED_MASK;
+		*bmc = 1 | (needed?NEEDED_MASK:0);
 		bitmap_count_page(bitmap, offset, 1);
 		page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
 		set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
@@ -1476,17 +1483,14 @@ void bitmap_flush(mddev_t *mddev)
 /*
  * free memory that was allocated
  */
-void bitmap_destroy(mddev_t *mddev)
+static void bitmap_free(struct bitmap *bitmap)
 {
 	unsigned long k, pages;
 	struct bitmap_page *bp;
-	struct bitmap *bitmap = mddev->bitmap;
 
 	if (!bitmap) /* there was no bitmap */
 		return;
 
-	mddev->bitmap = NULL; /* disconnect from the md device */
-
 	/* release the bitmap file and kill the daemon */
 	bitmap_file_put(bitmap);
 
@@ -1504,6 +1508,17 @@ void bitmap_destroy(mddev_t *mddev)
 	kfree(bp);
 	kfree(bitmap);
 }
+void bitmap_destroy(mddev_t *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	if (!bitmap) /* there was no bitmap */
+		return;
+
+	mddev->bitmap = NULL; /* disconnect from the md device */
+
+	bitmap_free(bitmap);
+}
 
 /*
  * initialize the bitmap structure
@@ -1517,6 +1532,7 @@ int bitmap_create(mddev_t *mddev)
 	unsigned long pages;
 	struct file *file = mddev->bitmap_file;
 	int err;
+	sector_t start;
 
 	BUG_ON(sizeof(bitmap_super_t) != 256);
 
@@ -1533,15 +1549,15 @@ int bitmap_create(mddev_t *mddev)
 
 	spin_lock_init(&bitmap->lock);
 	bitmap->mddev = mddev;
-	mddev->bitmap = bitmap;
 
 	spin_lock_init(&bitmap->write_lock);
 	INIT_LIST_HEAD(&bitmap->complete_pages);
 	init_waitqueue_head(&bitmap->write_wait);
 	bitmap->write_pool = mempool_create(WRITE_POOL_SIZE, write_pool_alloc,
 				write_pool_free, NULL);
+	err = -ENOMEM;
 	if (!bitmap->write_pool)
-		return -ENOMEM;
+		goto error;
 
 	bitmap->file = file;
 	bitmap->offset = mddev->bitmap_offset;
@@ -1549,7 +1565,7 @@ int bitmap_create(mddev_t *mddev)
 	/* read superblock from bitmap file (this sets bitmap->chunksize) */
 	err = bitmap_read_sb(bitmap);
 	if (err)
-		return err;
+		goto error;
 
 	bitmap->chunkshift = find_first_bit(&bitmap->chunksize,
 					sizeof(bitmap->chunksize));
@@ -1573,27 +1589,44 @@ int bitmap_create(mddev_t *mddev)
 #else
 	bitmap->bp = kmalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL);
 #endif
+	err = -ENOMEM;
 	if (!bitmap->bp)
-		return -ENOMEM;
+		goto error;
 	memset(bitmap->bp, 0, pages * sizeof(*bitmap->bp));
 
 	bitmap->flags |= BITMAP_ACTIVE;
 
 	/* now that we have some pages available, initialize the in-memory
 	 * bitmap from the on-disk bitmap */
-	err = bitmap_init_from_disk(bitmap);
+	start = 0;
+	if (mddev->degraded == 0
+	    || bitmap->events_cleared == mddev->events)
+		/* no need to keep dirty bits to optimise a re-add of a missing device */
+		start = mddev->recovery_cp;
+	err = bitmap_init_from_disk(bitmap, start);
 
 	if (err)
-		return err;
+		goto error;
 
 	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
 		pages, bmname(bitmap));
 
-	/* kick off the bitmap daemons */
-	err = bitmap_start_daemons(bitmap);
-	if (err)
-		return err;
+	mddev->bitmap = bitmap;
+
+	if (file)
+		/* kick off the bitmap writeback daemon */
+		bitmap->writeback_daemon =
+			bitmap_start_daemon(bitmap,
+					    bitmap_writeback_daemon,
+					    "bitmap_wb");
+
+	if (IS_ERR(bitmap->writeback_daemon))
+		return PTR_ERR(bitmap->writeback_daemon);
 	return bitmap_update_sb(bitmap);
+
+ error:
+	bitmap_free(bitmap);
+	return err;
 }
 
 /* the bitmap API -- for raid personalities */
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index 17212b4201a1..cc07bbebbb16 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -568,12 +568,9 @@ int dm_create_persistent(struct exception_store *store, uint32_t chunk_size)
 
       bad:
 	dm_io_put(sectors_to_pages(chunk_size));
-	if (ps) {
-		if (ps->area)
-			free_area(ps);
-
-		kfree(ps);
-	}
+	if (ps && ps->area)
+		free_area(ps);
+	kfree(ps);
 	return r;
 }
 
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index b08df8b9b2ca..863282513753 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -375,16 +375,18 @@ static void rh_inc(struct region_hash *rh, region_t region)
 
 	read_lock(&rh->hash_lock);
 	reg = __rh_find(rh, region);
+
+	atomic_inc(&reg->pending);
+
+	spin_lock_irq(&rh->region_lock);
 	if (reg->state == RH_CLEAN) {
 		rh->log->type->mark_region(rh->log, reg->key);
 
-		spin_lock_irq(&rh->region_lock);
 		reg->state = RH_DIRTY;
 		list_del_init(&reg->list);	/* take off the clean list */
-		spin_unlock_irq(&rh->region_lock);
 	}
+	spin_unlock_irq(&rh->region_lock);
 
-	atomic_inc(&reg->pending);
 	read_unlock(&rh->hash_lock);
 }
 
@@ -408,6 +410,10 @@ static void rh_dec(struct region_hash *rh, region_t region)
 
 	if (atomic_dec_and_test(&reg->pending)) {
 		spin_lock_irqsave(&rh->region_lock, flags);
+		if (atomic_read(&reg->pending)) { /* check race */
+			spin_unlock_irqrestore(&rh->region_lock, flags);
+			return;
+		}
 		if (reg->state == RH_RECOVERING) {
 			list_add_tail(&reg->list, &rh->quiesced_regions);
 		} else {
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 8d740013d74d..bb279fad2fd2 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -38,7 +38,8 @@ static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
 	/*
 	 * sector_div(a,b) returns the remainer and sets a to a/b
 	 */
-	(void)sector_div(block, conf->smallest->size);
+	block >>= conf->preshift;
+	(void)sector_div(block, conf->hash_spacing);
 	hash = conf->hash_table[block];
 
 	while ((sector>>1) >= (hash->size + hash->offset))
@@ -47,7 +48,7 @@ static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
 }
 
 /**
- *	linear_mergeable_bvec -- tell bio layer if a two requests can be merged
+ *	linear_mergeable_bvec -- tell bio layer if two requests can be merged
  *	@q: request queue
  *	@bio: the buffer head that's been built up so far
  *	@biovec: the request that could be merged to it.
@@ -116,7 +117,7 @@ static int linear_run (mddev_t *mddev)
 	dev_info_t **table;
 	mdk_rdev_t *rdev;
 	int i, nb_zone, cnt;
-	sector_t start;
+	sector_t min_spacing;
 	sector_t curr_offset;
 	struct list_head *tmp;
 
@@ -127,11 +128,6 @@ static int linear_run (mddev_t *mddev)
 	memset(conf, 0, sizeof(*conf) + mddev->raid_disks*sizeof(dev_info_t));
 	mddev->private = conf;
 
-	/*
-	 * Find the smallest device.
-	 */
-
-	conf->smallest = NULL;
 	cnt = 0;
 	mddev->array_size = 0;
 
@@ -159,8 +155,6 @@ static int linear_run (mddev_t *mddev)
 		disk->size = rdev->size;
 		mddev->array_size += rdev->size;
 
-		if (!conf->smallest || (disk->size < conf->smallest->size))
-			conf->smallest = disk;
 		cnt++;
 	}
 	if (cnt != mddev->raid_disks) {
@@ -168,6 +162,36 @@ static int linear_run (mddev_t *mddev)
 		goto out;
 	}
 
+	min_spacing = mddev->array_size;
+	sector_div(min_spacing, PAGE_SIZE/sizeof(struct dev_info *));
+
+	/* min_spacing is the minimum spacing that will fit the hash
+	 * table in one PAGE.  This may be much smaller than needed.
+	 * We find the smallest non-terminal set of consecutive devices
+	 * that is larger than min_spacing as use the size of that as
+	 * the actual spacing
+	 */
+	conf->hash_spacing = mddev->array_size;
+	for (i=0; i < cnt-1 ; i++) {
+		sector_t sz = 0;
+		int j;
+		for (j=i; i<cnt-1 && sz < min_spacing ; j++)
+			sz += conf->disks[j].size;
+		if (sz >= min_spacing && sz < conf->hash_spacing)
+			conf->hash_spacing = sz;
+	}
+
+	/* hash_spacing may be too large for sector_div to work with,
+	 * so we might need to pre-shift
+	 */
+	conf->preshift = 0;
+	if (sizeof(sector_t) > sizeof(u32)) {
+		sector_t space = conf->hash_spacing;
+		while (space > (sector_t)(~(u32)0)) {
+			space >>= 1;
+			conf->preshift++;
+		}
+	}
 	/*
 	 * This code was restructured to work around a gcc-2.95.3 internal
 	 * compiler error.  Alter it with care.
@@ -177,39 +201,52 @@ static int linear_run (mddev_t *mddev)
 		unsigned round;
 		unsigned long base;
 
-		sz = mddev->array_size;
-		base = conf->smallest->size;
+		sz = mddev->array_size >> conf->preshift;
+		sz += 1; /* force round-up */
+		base = conf->hash_spacing >> conf->preshift;
 		round = sector_div(sz, base);
-		nb_zone = conf->nr_zones = sz + (round ? 1 : 0);
+		nb_zone = sz + (round ? 1 : 0);
 	}
-			
-	conf->hash_table = kmalloc (sizeof (dev_info_t*) * nb_zone,
+	BUG_ON(nb_zone > PAGE_SIZE / sizeof(struct dev_info *));
+
+	conf->hash_table = kmalloc (sizeof (struct dev_info *) * nb_zone,
 					GFP_KERNEL);
 	if (!conf->hash_table)
 		goto out;
 
 	/*
 	 * Here we generate the linear hash table
+	 * First calculate the device offsets.
 	 */
+	conf->disks[0].offset = 0;
+	for (i=1; i<mddev->raid_disks; i++)
+		conf->disks[i].offset =
+			conf->disks[i-1].offset +
+			conf->disks[i-1].size;
+
 	table = conf->hash_table;
-	start = 0;
 	curr_offset = 0;
-	for (i = 0; i < cnt; i++) {
-		dev_info_t *disk = conf->disks + i;
+	i = 0;
+	for (curr_offset = 0;
+	     curr_offset < mddev->array_size;
+	     curr_offset += conf->hash_spacing) {
 
-		disk->offset = curr_offset;
-		curr_offset += disk->size;
+		while (i < mddev->raid_disks-1 &&
+		       curr_offset >= conf->disks[i+1].offset)
+			i++;
 
-		/* 'curr_offset' is the end of this disk
-		 * 'start' is the start of table
+		*table ++ = conf->disks + i;
+	}
+
+	if (conf->preshift) {
+		conf->hash_spacing >>= conf->preshift;
+		/* round hash_spacing up so that when we divide by it,
+		 * we err on the side of "too-low", which is safest.
 		 */
-		while (start < curr_offset) {
-			*table++ = disk;
-			start += conf->smallest->size;
-		}
+		conf->hash_spacing++;
 	}
-	if (table-conf->hash_table != nb_zone)
-		BUG();
+
+	BUG_ON(table - conf->hash_table > nb_zone);
 
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
 	mddev->queue->unplug_fn = linear_unplug;
@@ -238,6 +275,11 @@ static int linear_make_request (request_queue_t *q, struct bio *bio)
 	dev_info_t *tmp_dev;
 	sector_t block;
 
+	if (unlikely(bio_barrier(bio))) {
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	if (bio_data_dir(bio)==WRITE) {
 		disk_stat_inc(mddev->gendisk, writes);
 		disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio));
@@ -294,7 +336,7 @@ static void linear_status (struct seq_file *seq, mddev_t *mddev)
 	sector_t s = 0;
   
 	seq_printf(seq, "      ");
-	for (j = 0; j < conf->nr_zones; j++)
+	for (j = 0; j < mddev->raid_disks; j++)
 	{
 		char b[BDEVNAME_SIZE];
 		s += conf->smallest_size;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 20ca80b7dc20..2897df90df44 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -34,6 +34,7 @@
 
 #include <linux/module.h>
 #include <linux/config.h>
+#include <linux/kthread.h>
 #include <linux/linkage.h>
 #include <linux/raid/md.h>
 #include <linux/raid/bitmap.h>
@@ -73,7 +74,7 @@ static DEFINE_SPINLOCK(pers_lock);
  * Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
  * is 1000 KB/sec, so the extra system load does not show up that much.
  * Increase it if you want to have more _guaranteed_ speed. Note that
- * the RAID driver will use the maximum available bandwith if the IO
+ * the RAID driver will use the maximum available bandwidth if the IO
  * subsystem is idle. There is also an 'absolute maximum' reconstruction
  * speed limit - in case reconstruction slows down your system despite
  * idle IO detection.
@@ -393,7 +394,7 @@ int sync_page_io(struct block_device *bdev, sector_t sector, int size,
 	return ret;
 }
 
-static int read_disk_sb(mdk_rdev_t * rdev)
+static int read_disk_sb(mdk_rdev_t * rdev, int size)
 {
 	char b[BDEVNAME_SIZE];
 	if (!rdev->sb_page) {
@@ -404,7 +405,7 @@ static int read_disk_sb(mdk_rdev_t * rdev)
 		return 0;
 
 
-	if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, MD_SB_BYTES, rdev->sb_page, READ))
+	if (!sync_page_io(rdev->bdev, rdev->sb_offset<<1, size, rdev->sb_page, READ))
 		goto fail;
 	rdev->sb_loaded = 1;
 	return 0;
@@ -531,7 +532,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 	sb_offset = calc_dev_sboffset(rdev->bdev);
 	rdev->sb_offset = sb_offset;
 
-	ret = read_disk_sb(rdev);
+	ret = read_disk_sb(rdev, MD_SB_BYTES);
 	if (ret) return ret;
 
 	ret = -EINVAL;
@@ -564,6 +565,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 
 	rdev->preferred_minor = sb->md_minor;
 	rdev->data_offset = 0;
+	rdev->sb_size = MD_SB_BYTES;
 
 	if (sb->level == LEVEL_MULTIPATH)
 		rdev->desc_nr = -1;
@@ -623,6 +625,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 		mddev->size = sb->size;
 		mddev->events = md_event(sb);
 		mddev->bitmap_offset = 0;
+		mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
 
 		if (sb->state & (1<<MD_SB_CLEAN))
 			mddev->recovery_cp = MaxSector;
@@ -643,12 +646,12 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 
 		if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
 		    mddev->bitmap_file == NULL) {
-			if (mddev->level != 1) {
+			if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6) {
 				/* FIXME use a better test */
 				printk(KERN_WARNING "md: bitmaps only support for raid1\n");
 				return -EINVAL;
 			}
-			mddev->bitmap_offset = (MD_SB_BYTES >> 9);
+			mddev->bitmap_offset = mddev->default_bitmap_offset;
 		}
 
 	} else if (mddev->pers == NULL) {
@@ -669,6 +672,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 
 	if (mddev->level != LEVEL_MULTIPATH) {
 		rdev->faulty = 0;
+		rdev->flags = 0;
 		desc = sb->disks + rdev->desc_nr;
 
 		if (desc->state & (1<<MD_DISK_FAULTY))
@@ -678,6 +682,8 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 			rdev->in_sync = 1;
 			rdev->raid_disk = desc->raid_disk;
 		}
+		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
+			set_bit(WriteMostly, &rdev->flags);
 	} else /* MULTIPATH are always insync */
 		rdev->in_sync = 1;
 	return 0;
@@ -706,6 +712,8 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 	int i;
 	int active=0, working=0,failed=0,spare=0,nr_disks=0;
 
+	rdev->sb_size = MD_SB_BYTES;
+
 	sb = (mdp_super_t*)page_address(rdev->sb_page);
 
 	memset(sb, 0, sizeof(*sb));
@@ -776,6 +784,8 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 			spare++;
 			working++;
 		}
+		if (test_bit(WriteMostly, &rdev2->flags))
+			d->state |= (1<<MD_DISK_WRITEMOSTLY);
 	}
 	
 	/* now set the "removed" and "faulty" bits on any missing devices */
@@ -831,6 +841,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	int ret;
 	sector_t sb_offset;
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+	int bmask;
 
 	/*
 	 * Calculate the position of the superblock.
@@ -859,7 +870,10 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	}
 	rdev->sb_offset = sb_offset;
 
-	ret = read_disk_sb(rdev);
+	/* superblock is rarely larger than 1K, but it can be larger,
+	 * and it is safe to read 4k, so we do that
+	 */
+	ret = read_disk_sb(rdev, 4096);
 	if (ret) return ret;
 
 
@@ -869,7 +883,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	    sb->major_version != cpu_to_le32(1) ||
 	    le32_to_cpu(sb->max_dev) > (4096-256)/2 ||
 	    le64_to_cpu(sb->super_offset) != (rdev->sb_offset<<1) ||
-	    sb->feature_map != 0)
+	    (le32_to_cpu(sb->feature_map) & ~MD_FEATURE_ALL) != 0)
 		return -EINVAL;
 
 	if (calc_sb_1_csum(sb) != sb->sb_csum) {
@@ -885,6 +899,11 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 	rdev->preferred_minor = 0xffff;
 	rdev->data_offset = le64_to_cpu(sb->data_offset);
 
+	rdev->sb_size = le32_to_cpu(sb->max_dev) * 2 + 256;
+	bmask = queue_hardsect_size(rdev->bdev->bd_disk->queue)-1;
+	if (rdev->sb_size & bmask)
+		rdev-> sb_size = (rdev->sb_size | bmask)+1;
+
 	if (refdev == 0)
 		return 1;
 	else {
@@ -939,13 +958,15 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 		mddev->size = le64_to_cpu(sb->size)/2;
 		mddev->events = le64_to_cpu(sb->events);
 		mddev->bitmap_offset = 0;
+		mddev->default_bitmap_offset = 0;
+		mddev->default_bitmap_offset = 1024;
 		
 		mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
 		memcpy(mddev->uuid, sb->set_uuid, 16);
 
 		mddev->max_disks =  (4096-256)/2;
 
-		if ((le32_to_cpu(sb->feature_map) & 1) &&
+		if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
 		    mddev->bitmap_file == NULL ) {
 			if (mddev->level != 1) {
 				printk(KERN_WARNING "md: bitmaps only supported for raid1\n");
@@ -986,6 +1007,9 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 			rdev->raid_disk = role;
 			break;
 		}
+		rdev->flags = 0;
+		if (sb->devflags & WriteMostly1)
+			set_bit(WriteMostly, &rdev->flags);
 	} else /* MULTIPATH are always insync */
 		rdev->in_sync = 1;
 
@@ -1017,7 +1041,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 
 	if (mddev->bitmap && mddev->bitmap_file == NULL) {
 		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
-		sb->feature_map = cpu_to_le32(1);
+		sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
 	}
 
 	max_dev = 0;
@@ -1363,7 +1387,7 @@ repeat:
 		dprintk("%s ", bdevname(rdev->bdev,b));
 		if (!rdev->faulty) {
 			md_super_write(mddev,rdev,
-				       rdev->sb_offset<<1, MD_SB_BYTES,
+				       rdev->sb_offset<<1, rdev->sb_size,
 				       rdev->sb_page);
 			dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
 				bdevname(rdev->bdev,b),
@@ -2073,6 +2097,8 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
 	info.state         = 0;
 	if (mddev->in_sync)
 		info.state = (1<<MD_SB_CLEAN);
+	if (mddev->bitmap && mddev->bitmap_offset)
+		info.state = (1<<MD_SB_BITMAP_PRESENT);
 	info.active_disks  = active;
 	info.working_disks = working;
 	info.failed_disks  = failed;
@@ -2087,7 +2113,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
 	return 0;
 }
 
-static int get_bitmap_file(mddev_t * mddev, void * arg)
+static int get_bitmap_file(mddev_t * mddev, void __user * arg)
 {
 	mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */
 	char *ptr, *buf = NULL;
@@ -2146,6 +2172,8 @@ static int get_disk_info(mddev_t * mddev, void __user * arg)
 			info.state |= (1<<MD_DISK_ACTIVE);
 			info.state |= (1<<MD_DISK_SYNC);
 		}
+		if (test_bit(WriteMostly, &rdev->flags))
+			info.state |= (1<<MD_DISK_WRITEMOSTLY);
 	} else {
 		info.major = info.minor = 0;
 		info.raid_disk = -1;
@@ -2210,8 +2238,11 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 			       mdname(mddev));
 			return -EINVAL;
 		}
-		rdev = md_import_device(dev, mddev->major_version,
-					mddev->minor_version);
+		if (mddev->persistent)
+			rdev = md_import_device(dev, mddev->major_version,
+						mddev->minor_version);
+		else
+			rdev = md_import_device(dev, -1, -1);
 		if (IS_ERR(rdev)) {
 			printk(KERN_WARNING 
 				"md: md_import_device returned %ld\n",
@@ -2231,6 +2262,9 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		rdev->saved_raid_disk = rdev->raid_disk;
 
 		rdev->in_sync = 0; /* just to be sure */
+		if (info->state & (1<<MD_DISK_WRITEMOSTLY))
+			set_bit(WriteMostly, &rdev->flags);
+
 		rdev->raid_disk = -1;
 		err = bind_rdev_to_array(rdev, mddev);
 		if (err)
@@ -2271,6 +2305,9 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		else
 			rdev->in_sync = 0;
 
+		if (info->state & (1<<MD_DISK_WRITEMOSTLY))
+			set_bit(WriteMostly, &rdev->flags);
+
 		err = bind_rdev_to_array(rdev, mddev);
 		if (err) {
 			export_rdev(rdev);
@@ -2430,25 +2467,51 @@ static int set_bitmap_file(mddev_t *mddev, int fd)
 {
 	int err;
 
-	if (mddev->pers)
-		return -EBUSY;
+	if (mddev->pers) {
+		if (!mddev->pers->quiesce)
+			return -EBUSY;
+		if (mddev->recovery || mddev->sync_thread)
+			return -EBUSY;
+		/* we should be able to change the bitmap.. */
+	}
 
-	mddev->bitmap_file = fget(fd);
 
-	if (mddev->bitmap_file == NULL) {
-		printk(KERN_ERR "%s: error: failed to get bitmap file\n",
-			mdname(mddev));
-		return -EBADF;
-	}
+	if (fd >= 0) {
+		if (mddev->bitmap)
+			return -EEXIST; /* cannot add when bitmap is present */
+		mddev->bitmap_file = fget(fd);
 
-	err = deny_bitmap_write_access(mddev->bitmap_file);
-	if (err) {
-		printk(KERN_ERR "%s: error: bitmap file is already in use\n",
-			mdname(mddev));
-		fput(mddev->bitmap_file);
-		mddev->bitmap_file = NULL;
-	} else
+		if (mddev->bitmap_file == NULL) {
+			printk(KERN_ERR "%s: error: failed to get bitmap file\n",
+			       mdname(mddev));
+			return -EBADF;
+		}
+
+		err = deny_bitmap_write_access(mddev->bitmap_file);
+		if (err) {
+			printk(KERN_ERR "%s: error: bitmap file is already in use\n",
+			       mdname(mddev));
+			fput(mddev->bitmap_file);
+			mddev->bitmap_file = NULL;
+			return err;
+		}
 		mddev->bitmap_offset = 0; /* file overrides offset */
+	} else if (mddev->bitmap == NULL)
+		return -ENOENT; /* cannot remove what isn't there */
+	err = 0;
+	if (mddev->pers) {
+		mddev->pers->quiesce(mddev, 1);
+		if (fd >= 0)
+			err = bitmap_create(mddev);
+		if (fd < 0 || err)
+			bitmap_destroy(mddev);
+		mddev->pers->quiesce(mddev, 0);
+	} else if (fd < 0) {
+		if (mddev->bitmap_file)
+			fput(mddev->bitmap_file);
+		mddev->bitmap_file = NULL;
+	}
+
 	return err;
 }
 
@@ -2528,6 +2591,11 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
 {
 	int rv = 0;
 	int cnt = 0;
+	int state = 0;
+
+	/* calculate expected state,ignoring low bits */
+	if (mddev->bitmap && mddev->bitmap_offset)
+		state |= (1 << MD_SB_BITMAP_PRESENT);
 
 	if (mddev->major_version != info->major_version ||
 	    mddev->minor_version != info->minor_version ||
@@ -2536,12 +2604,16 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
 	    mddev->level         != info->level         ||
 /*	    mddev->layout        != info->layout        || */
 	    !mddev->persistent	 != info->not_persistent||
-	    mddev->chunk_size    != info->chunk_size    )
+	    mddev->chunk_size    != info->chunk_size    ||
+	    /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
+	    ((state^info->state) & 0xfffffe00)
+		)
 		return -EINVAL;
 	/* Check there is only one change */
 	if (mddev->size != info->size) cnt++;
 	if (mddev->raid_disks != info->raid_disks) cnt++;
 	if (mddev->layout != info->layout) cnt++;
+	if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) cnt++;
 	if (cnt == 0) return 0;
 	if (cnt > 1) return -EINVAL;
 
@@ -2620,6 +2692,35 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
 			}
 		}
 	}
+	if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) {
+		if (mddev->pers->quiesce == NULL)
+			return -EINVAL;
+		if (mddev->recovery || mddev->sync_thread)
+			return -EBUSY;
+		if (info->state & (1<<MD_SB_BITMAP_PRESENT)) {
+			/* add the bitmap */
+			if (mddev->bitmap)
+				return -EEXIST;
+			if (mddev->default_bitmap_offset == 0)
+				return -EINVAL;
+			mddev->bitmap_offset = mddev->default_bitmap_offset;
+			mddev->pers->quiesce(mddev, 1);
+			rv = bitmap_create(mddev);
+			if (rv)
+				bitmap_destroy(mddev);
+			mddev->pers->quiesce(mddev, 0);
+		} else {
+			/* remove the bitmap */
+			if (!mddev->bitmap)
+				return -ENOENT;
+			if (mddev->bitmap->file)
+				return -EINVAL;
+			mddev->pers->quiesce(mddev, 1);
+			bitmap_destroy(mddev);
+			mddev->pers->quiesce(mddev, 0);
+			mddev->bitmap_offset = 0;
+		}
+	}
 	md_update_sb(mddev);
 	return rv;
 }
@@ -2781,7 +2882,7 @@ static int md_ioctl(struct inode *inode, struct file *file,
 			goto done_unlock;
 
 		case GET_BITMAP_FILE:
-			err = get_bitmap_file(mddev, (void *)arg);
+			err = get_bitmap_file(mddev, argp);
 			goto done_unlock;
 
 		case GET_DISK_INFO:
@@ -2950,18 +3051,6 @@ static int md_thread(void * arg)
 {
 	mdk_thread_t *thread = arg;
 
-	lock_kernel();
-
-	/*
-	 * Detach thread
-	 */
-
-	daemonize(thread->name, mdname(thread->mddev));
-
-	current->exit_signal = SIGCHLD;
-	allow_signal(SIGKILL);
-	thread->tsk = current;
-
 	/*
 	 * md_thread is a 'system-thread', it's priority should be very
 	 * high. We avoid resource deadlocks individually in each
@@ -2973,14 +3062,14 @@ static int md_thread(void * arg)
 	 * bdflush, otherwise bdflush will deadlock if there are too
 	 * many dirty RAID5 blocks.
 	 */
-	unlock_kernel();
 
 	complete(thread->event);
-	while (thread->run) {
+	while (!kthread_should_stop()) {
 		void (*run)(mddev_t *);
 
 		wait_event_interruptible_timeout(thread->wqueue,
-						 test_bit(THREAD_WAKEUP, &thread->flags),
+						 test_bit(THREAD_WAKEUP, &thread->flags)
+						 || kthread_should_stop(),
 						 thread->timeout);
 		try_to_freeze();
 
@@ -2989,11 +3078,8 @@ static int md_thread(void * arg)
 		run = thread->run;
 		if (run)
 			run(thread->mddev);
-
-		if (signal_pending(current))
-			flush_signals(current);
 	}
-	complete(thread->event);
+
 	return 0;
 }
 
@@ -3010,11 +3096,9 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev,
 				 const char *name)
 {
 	mdk_thread_t *thread;
-	int ret;
 	struct completion event;
 
-	thread = (mdk_thread_t *) kmalloc
-				(sizeof(mdk_thread_t), GFP_KERNEL);
+	thread = kmalloc(sizeof(mdk_thread_t), GFP_KERNEL);
 	if (!thread)
 		return NULL;
 
@@ -3027,8 +3111,8 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev,
 	thread->mddev = mddev;
 	thread->name = name;
 	thread->timeout = MAX_SCHEDULE_TIMEOUT;
-	ret = kernel_thread(md_thread, thread, 0);
-	if (ret < 0) {
+	thread->tsk = kthread_run(md_thread, thread, mdname(thread->mddev));
+	if (IS_ERR(thread->tsk)) {
 		kfree(thread);
 		return NULL;
 	}
@@ -3038,21 +3122,9 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev,
 
 void md_unregister_thread(mdk_thread_t *thread)
 {
-	struct completion event;
-
-	init_completion(&event);
-
-	thread->event = &event;
-
-	/* As soon as ->run is set to NULL, the task could disappear,
-	 * so we need to hold tasklist_lock until we have sent the signal
-	 */
 	dprintk("interrupting MD-thread pid %d\n", thread->tsk->pid);
-	read_lock(&tasklist_lock);
-	thread->run = NULL;
-	send_sig(SIGKILL, thread->tsk, 1);
-	read_unlock(&tasklist_lock);
-	wait_for_completion(&event);
+
+	kthread_stop(thread->tsk);
 	kfree(thread);
 }
 
@@ -3259,10 +3331,13 @@ static int md_seq_show(struct seq_file *seq, void *v)
 			char b[BDEVNAME_SIZE];
 			seq_printf(seq, " %s[%d]",
 				bdevname(rdev->bdev,b), rdev->desc_nr);
+			if (test_bit(WriteMostly, &rdev->flags))
+				seq_printf(seq, "(W)");
 			if (rdev->faulty) {
 				seq_printf(seq, "(F)");
 				continue;
-			}
+			} else if (rdev->raid_disk < 0)
+				seq_printf(seq, "(S)"); /* spare */
 			size += rdev->size;
 		}
 
@@ -3274,6 +3349,15 @@ static int md_seq_show(struct seq_file *seq, void *v)
 				seq_printf(seq, "\n      %llu blocks",
 					(unsigned long long)size);
 		}
+		if (mddev->persistent) {
+			if (mddev->major_version != 0 ||
+			    mddev->minor_version != 90) {
+				seq_printf(seq," super %d.%d",
+					   mddev->major_version,
+					   mddev->minor_version);
+			}
+		} else
+			seq_printf(seq, " super non-persistent");
 
 		if (mddev->pers) {
 			mddev->pers->status (seq, mddev);
@@ -3416,7 +3500,6 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok)
  */
 void md_write_start(mddev_t *mddev, struct bio *bi)
 {
-	DEFINE_WAIT(w);
 	if (bio_data_dir(bi) != WRITE)
 		return;
 
@@ -3533,7 +3616,7 @@ static void md_do_sync(mddev_t *mddev)
 	printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev));
 	printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:"
 		" %d KB/sec/disc.\n", sysctl_speed_limit_min);
-	printk(KERN_INFO "md: using maximum available idle IO bandwith "
+	printk(KERN_INFO "md: using maximum available idle IO bandwidth "
 	       "(but not more than %d KB/sec) for reconstruction.\n",
 	       sysctl_speed_limit_max);
 
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 2d2ca7fa0265..286342375fb7 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -169,6 +169,11 @@ static int multipath_make_request (request_queue_t *q, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
+	if (unlikely(bio_barrier(bio))) {
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
 
 	mp_bh->master_bio = bio;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 2120710172c5..f6757259ce7f 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -404,6 +404,11 @@ static int raid0_make_request (request_queue_t *q, struct bio *bio)
 	unsigned long chunk;
 	sector_t block, rsect;
 
+	if (unlikely(bio_barrier(bio))) {
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	if (bio_data_dir(bio)==WRITE) {
 		disk_stat_inc(mddev->gendisk, writes);
 		disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio));
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 51d9645ed09c..a93ca478142a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -222,8 +222,17 @@ static void raid_end_bio_io(r1bio_t *r1_bio)
 {
 	struct bio *bio = r1_bio->master_bio;
 
-	bio_endio(bio, bio->bi_size,
-		test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
+	/* if nobody has done the final endio yet, do it now */
+	if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+		PRINTK(KERN_DEBUG "raid1: sync end %s on sectors %llu-%llu\n",
+			(bio_data_dir(bio) == WRITE) ? "write" : "read",
+			(unsigned long long) bio->bi_sector,
+			(unsigned long long) bio->bi_sector +
+				(bio->bi_size >> 9) - 1);
+
+		bio_endio(bio, bio->bi_size,
+			test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
+	}
 	free_r1bio(r1_bio);
 }
 
@@ -292,7 +301,7 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
-	int mirror;
+	int mirror, behind;
 	conf_t *conf = mddev_to_conf(r1_bio->mddev);
 
 	if (bio->bi_size)
@@ -323,16 +332,46 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 
 	update_head_pos(mirror, r1_bio);
 
+	behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
+	if (behind) {
+		if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+			atomic_dec(&r1_bio->behind_remaining);
+
+		/* In behind mode, we ACK the master bio once the I/O has safely
+		 * reached all non-writemostly disks. Setting the Returned bit
+		 * ensures that this gets done only once -- we don't ever want to
+		 * return -EIO here, instead we'll wait */
+
+		if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
+		    test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+			/* Maybe we can return now */
+			if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+				struct bio *mbio = r1_bio->master_bio;
+				PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
+				       (unsigned long long) mbio->bi_sector,
+				       (unsigned long long) mbio->bi_sector +
+				       (mbio->bi_size >> 9) - 1);
+				bio_endio(mbio, mbio->bi_size, 0);
+			}
+		}
+	}
 	/*
 	 *
 	 * Let's see if all mirrored write operations have finished
 	 * already.
 	 */
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
+		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+			/* free extra copy of the data pages */
+			int i = bio->bi_vcnt;
+			while (i--)
+				__free_page(bio->bi_io_vec[i].bv_page);
+		}
 		/* clear the bitmap if all writes complete successfully */
 		bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
 				r1_bio->sectors,
-				!test_bit(R1BIO_Degraded, &r1_bio->state));
+				!test_bit(R1BIO_Degraded, &r1_bio->state),
+				behind);
 		md_write_end(r1_bio->mddev);
 		raid_end_bio_io(r1_bio);
 	}
@@ -360,13 +399,14 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 {
 	const unsigned long this_sector = r1_bio->sector;
 	int new_disk = conf->last_used, disk = new_disk;
+	int wonly_disk = -1;
 	const int sectors = r1_bio->sectors;
 	sector_t new_distance, current_distance;
-	mdk_rdev_t *new_rdev, *rdev;
+	mdk_rdev_t *rdev;
 
 	rcu_read_lock();
 	/*
-	 * Check if it if we can balance. We can balance on the whole
+	 * Check if we can balance. We can balance on the whole
 	 * device if no resync is going on, or below the resync window.
 	 * We take the first readable disk when above the resync window.
 	 */
@@ -376,11 +416,16 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 		/* Choose the first operation device, for consistancy */
 		new_disk = 0;
 
-		while ((new_rdev=conf->mirrors[new_disk].rdev) == NULL ||
-		       !new_rdev->in_sync) {
-			new_disk++;
-			if (new_disk == conf->raid_disks) {
-				new_disk = -1;
+		for (rdev = conf->mirrors[new_disk].rdev;
+		     !rdev || !rdev->in_sync
+			     || test_bit(WriteMostly, &rdev->flags);
+		     rdev = conf->mirrors[++new_disk].rdev) {
+
+			if (rdev && rdev->in_sync)
+				wonly_disk = new_disk;
+
+			if (new_disk == conf->raid_disks - 1) {
+				new_disk = wonly_disk;
 				break;
 			}
 		}
@@ -389,16 +434,26 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 
 
 	/* make sure the disk is operational */
-	while ((new_rdev=conf->mirrors[new_disk].rdev) == NULL ||
-	       !new_rdev->in_sync) {
+	for (rdev = conf->mirrors[new_disk].rdev;
+	     !rdev || !rdev->in_sync ||
+		     test_bit(WriteMostly, &rdev->flags);
+	     rdev = conf->mirrors[new_disk].rdev) {
+
+		if (rdev && rdev->in_sync)
+			wonly_disk = new_disk;
+
 		if (new_disk <= 0)
 			new_disk = conf->raid_disks;
 		new_disk--;
 		if (new_disk == disk) {
-			new_disk = -1;
-			goto rb_out;
+			new_disk = wonly_disk;
+			break;
 		}
 	}
+
+	if (new_disk < 0)
+		goto rb_out;
+
 	disk = new_disk;
 	/* now disk == new_disk == starting point for search */
 
@@ -419,37 +474,41 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 			disk = conf->raid_disks;
 		disk--;
 
-		if ((rdev=conf->mirrors[disk].rdev) == NULL ||
-		    !rdev->in_sync)
+		rdev = conf->mirrors[disk].rdev;
+
+		if (!rdev ||
+		    !rdev->in_sync ||
+		    test_bit(WriteMostly, &rdev->flags))
 			continue;
 
 		if (!atomic_read(&rdev->nr_pending)) {
 			new_disk = disk;
-			new_rdev = rdev;
 			break;
 		}
 		new_distance = abs(this_sector - conf->mirrors[disk].head_position);
 		if (new_distance < current_distance) {
 			current_distance = new_distance;
 			new_disk = disk;
-			new_rdev = rdev;
 		}
 	} while (disk != conf->last_used);
 
-rb_out:
+ rb_out:
 
 
 	if (new_disk >= 0) {
-		conf->next_seq_sect = this_sector + sectors;
-		conf->last_used = new_disk;
-		atomic_inc(&new_rdev->nr_pending);
-		if (!new_rdev->in_sync) {
+		rdev = conf->mirrors[new_disk].rdev;
+		if (!rdev)
+			goto retry;
+		atomic_inc(&rdev->nr_pending);
+		if (!rdev->in_sync) {
 			/* cannot risk returning a device that failed
 			 * before we inc'ed nr_pending
 			 */
-			atomic_dec(&new_rdev->nr_pending);
+			atomic_dec(&rdev->nr_pending);
 			goto retry;
 		}
+		conf->next_seq_sect = this_sector + sectors;
+		conf->last_used = new_disk;
 	}
 	rcu_read_unlock();
 
@@ -542,6 +601,39 @@ static void device_barrier(conf_t *conf, sector_t sect)
 	spin_unlock_irq(&conf->resync_lock);
 }
 
+/* duplicate the data pages for behind I/O */
+static struct page **alloc_behind_pages(struct bio *bio)
+{
+	int i;
+	struct bio_vec *bvec;
+	struct page **pages = kmalloc(bio->bi_vcnt * sizeof(struct page *),
+					GFP_NOIO);
+	if (unlikely(!pages))
+		goto do_sync_io;
+
+	memset(pages, 0, bio->bi_vcnt * sizeof(struct page *));
+
+	bio_for_each_segment(bvec, bio, i) {
+		pages[i] = alloc_page(GFP_NOIO);
+		if (unlikely(!pages[i]))
+			goto do_sync_io;
+		memcpy(kmap(pages[i]) + bvec->bv_offset,
+			kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len);
+		kunmap(pages[i]);
+		kunmap(bvec->bv_page);
+	}
+
+	return pages;
+
+do_sync_io:
+	if (pages)
+		for (i = 0; i < bio->bi_vcnt && pages[i]; i++)
+			__free_page(pages[i]);
+	kfree(pages);
+	PRINTK("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
+	return NULL;
+}
+
 static int make_request(request_queue_t *q, struct bio * bio)
 {
 	mddev_t *mddev = q->queuedata;
@@ -554,7 +646,12 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
 	struct bio_list bl;
+	struct page **behind_pages = NULL;
 
+	if (unlikely(bio_barrier(bio))) {
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
 
 	/*
 	 * Register the new request and wait if the reconstruction
@@ -589,8 +686,6 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	r1_bio->mddev = mddev;
 	r1_bio->sector = bio->bi_sector;
 
-	r1_bio->state = 0;
-
 	if (bio_data_dir(bio) == READ) {
 		/*
 		 * read balancing logic:
@@ -651,13 +746,22 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	}
 	rcu_read_unlock();
 
+	BUG_ON(targets == 0); /* we never fail the last device */
+
 	if (targets < conf->raid_disks) {
 		/* array is degraded, we will not clear the bitmap
 		 * on I/O completion (see raid1_end_write_request) */
 		set_bit(R1BIO_Degraded, &r1_bio->state);
 	}
 
+	/* do behind I/O ? */
+	if (bitmap &&
+	    atomic_read(&bitmap->behind_writes) < bitmap->max_write_behind &&
+	    (behind_pages = alloc_behind_pages(bio)) != NULL)
+		set_bit(R1BIO_BehindIO, &r1_bio->state);
+
 	atomic_set(&r1_bio->remaining, 0);
+	atomic_set(&r1_bio->behind_remaining, 0);
 
 	bio_list_init(&bl);
 	for (i = 0; i < disks; i++) {
@@ -674,12 +778,31 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		mbio->bi_rw = WRITE;
 		mbio->bi_private = r1_bio;
 
+		if (behind_pages) {
+			struct bio_vec *bvec;
+			int j;
+
+			/* Yes, I really want the '__' version so that
+			 * we clear any unused pointer in the io_vec, rather
+			 * than leave them unchanged.  This is important
+			 * because when we come to free the pages, we won't
+			 * know the originial bi_idx, so we just free
+			 * them all
+			 */
+			__bio_for_each_segment(bvec, mbio, j, 0)
+				bvec->bv_page = behind_pages[j];
+			if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
+				atomic_inc(&r1_bio->behind_remaining);
+		}
+
 		atomic_inc(&r1_bio->remaining);
 
 		bio_list_add(&bl, mbio);
 	}
+	kfree(behind_pages); /* the behind pages are attached to the bios now */
 
-	bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors);
+	bitmap_startwrite(bitmap, bio->bi_sector, r1_bio->sectors,
+				test_bit(R1BIO_BehindIO, &r1_bio->state));
 	spin_lock_irqsave(&conf->device_lock, flags);
 	bio_list_merge(&conf->pending_bio_list, &bl);
 	bio_list_init(&bl);
@@ -1105,6 +1228,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	sector_t max_sector, nr_sectors;
 	int disk;
 	int i;
+	int wonly;
 	int write_targets = 0;
 	int sync_blocks;
 	int still_degraded = 0;
@@ -1160,14 +1284,21 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	 */
 	disk = conf->last_used;
 	/* make sure disk is operational */
-
+	wonly = disk;
 	while (conf->mirrors[disk].rdev == NULL ||
-	       !conf->mirrors[disk].rdev->in_sync) {
+	       !conf->mirrors[disk].rdev->in_sync ||
+	       test_bit(WriteMostly, &conf->mirrors[disk].rdev->flags)
+		) {
+		if (conf->mirrors[disk].rdev  &&
+		    conf->mirrors[disk].rdev->in_sync)
+			wonly = disk;
 		if (disk <= 0)
 			disk = conf->raid_disks;
 		disk--;
-		if (disk == conf->last_used)
+		if (disk == conf->last_used) {
+			disk = wonly;
 			break;
+		}
 	}
 	conf->last_used = disk;
 	atomic_inc(&conf->mirrors[disk].rdev->nr_pending);
@@ -1439,6 +1570,17 @@ out:
 static int stop(mddev_t *mddev)
 {
 	conf_t *conf = mddev_to_conf(mddev);
+	struct bitmap *bitmap = mddev->bitmap;
+	int behind_wait = 0;
+
+	/* wait for behind writes to complete */
+	while (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		behind_wait++;
+		printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait);
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule_timeout(HZ); /* wait a second */
+		/* need to kick something here to make sure I/O goes? */
+	}
 
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
@@ -1561,6 +1703,35 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
 	return 0;
 }
 
+static void raid1_quiesce(mddev_t *mddev, int state)
+{
+	conf_t *conf = mddev_to_conf(mddev);
+
+	switch(state) {
+	case 1:
+		spin_lock_irq(&conf->resync_lock);
+		conf->barrier++;
+		wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
+				    conf->resync_lock, raid1_unplug(mddev->queue));
+		spin_unlock_irq(&conf->resync_lock);
+		break;
+	case 0:
+		spin_lock_irq(&conf->resync_lock);
+		conf->barrier--;
+		spin_unlock_irq(&conf->resync_lock);
+		wake_up(&conf->wait_resume);
+		wake_up(&conf->wait_idle);
+		break;
+	}
+	if (mddev->thread) {
+		if (mddev->bitmap)
+			mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
+		else
+			mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+		md_wakeup_thread(mddev->thread);
+	}
+}
+
 
 static mdk_personality_t raid1_personality =
 {
@@ -1577,6 +1748,7 @@ static mdk_personality_t raid1_personality =
 	.sync_request	= sync_request,
 	.resize		= raid1_resize,
 	.reshape	= raid1_reshape,
+	.quiesce	= raid1_quiesce,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 62ebb1bc72be..5bd1e9ec899d 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -538,7 +538,8 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
 	}
 
 
-	current_distance = abs(this_sector - conf->mirrors[disk].head_position);
+	current_distance = abs(r10_bio->devs[slot].addr -
+			       conf->mirrors[disk].head_position);
 
 	/* Find the disk whose head is closest */
 
@@ -668,6 +669,11 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 
+	if (unlikely(bio_barrier(bio))) {
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	/* If this request crosses a chunk boundary, we need to
 	 * split it.  This will only happen for 1 PAGE (or less) requests.
 	 */
@@ -900,6 +906,27 @@ static void close_sync(conf_t *conf)
 	conf->r10buf_pool = NULL;
 }
 
+/* check if there are enough drives for
+ * every block to appear on atleast one
+ */
+static int enough(conf_t *conf)
+{
+	int first = 0;
+
+	do {
+		int n = conf->copies;
+		int cnt = 0;
+		while (n--) {
+			if (conf->mirrors[first].rdev)
+				cnt++;
+			first = (first+1) % conf->raid_disks;
+		}
+		if (cnt == 0)
+			return 0;
+	} while (first != 0);
+	return 1;
+}
+
 static int raid10_spare_active(mddev_t *mddev)
 {
 	int i;
@@ -938,6 +965,8 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		 * very different from resync
 		 */
 		return 0;
+	if (!enough(conf))
+		return 0;
 
 	for (mirror=0; mirror < mddev->raid_disks; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
@@ -1445,7 +1474,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 					}
 				}
 				if (j == conf->copies) {
-					BUG();
+					/* Cannot recover, so abort the recovery */
+					put_buf(r10_bio);
+					r10_bio = rb2;
+					if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery))
+						printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
+						       mdname(mddev));
+					break;
 				}
 			}
 		if (biolist == NULL) {
@@ -1678,9 +1713,10 @@ static int run(mddev_t *mddev)
 	init_waitqueue_head(&conf->wait_idle);
 	init_waitqueue_head(&conf->wait_resume);
 
-	if (!conf->working_disks) {
-		printk(KERN_ERR "raid10: no operational mirrors for %s\n",
-			mdname(mddev));
+	/* need to check that every block has at least one working mirror */
+	if (!enough(conf)) {
+		printk(KERN_ERR "raid10: not enough operational mirrors for %s\n",
+		       mdname(mddev));
 		goto out_free_conf;
 	}
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 43f231a467d5..4683ca24c046 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -24,6 +24,8 @@
 #include <linux/bitops.h>
 #include <asm/atomic.h>
 
+#include <linux/raid/bitmap.h>
+
 /*
  * Stripe cache
  */
@@ -79,8 +81,13 @@ static inline void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 		if (test_bit(STRIPE_HANDLE, &sh->state)) {
 			if (test_bit(STRIPE_DELAYED, &sh->state))
 				list_add_tail(&sh->lru, &conf->delayed_list);
-			else
+			else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+				 conf->seq_write == sh->bm_seq)
+				list_add_tail(&sh->lru, &conf->bitmap_list);
+			else {
+				clear_bit(STRIPE_BIT_DELAY, &sh->state);
 				list_add_tail(&sh->lru, &conf->handle_list);
+			}
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
@@ -244,6 +251,9 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector
 	spin_lock_irq(&conf->device_lock);
 
 	do {
+		wait_event_lock_irq(conf->wait_for_stripe,
+				    conf->quiesce == 0,
+				    conf->device_lock, /* nothing */);
 		sh = __find_stripe(conf, sector);
 		if (!sh) {
 			if (!conf->inactive_blocked)
@@ -803,6 +813,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 {
 	struct bio **bip;
 	raid5_conf_t *conf = sh->raid_conf;
+	int firstwrite=0;
 
 	PRINTK("adding bh b#%llu to stripe s#%llu\n",
 		(unsigned long long)bi->bi_sector,
@@ -811,9 +822,11 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 
 	spin_lock(&sh->lock);
 	spin_lock_irq(&conf->device_lock);
-	if (forwrite)
+	if (forwrite) {
 		bip = &sh->dev[dd_idx].towrite;
-	else
+		if (*bip == NULL && sh->dev[dd_idx].written == NULL)
+			firstwrite = 1;
+	} else
 		bip = &sh->dev[dd_idx].toread;
 	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
 		if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
@@ -836,6 +849,13 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		(unsigned long long)bi->bi_sector,
 		(unsigned long long)sh->sector, dd_idx);
 
+	if (conf->mddev->bitmap && firstwrite) {
+		sh->bm_seq = conf->seq_write;
+		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
+				  STRIPE_SECTORS, 0);
+		set_bit(STRIPE_BIT_DELAY, &sh->state);
+	}
+
 	if (forwrite) {
 		/* check if page is covered */
 		sector_t sector = sh->dev[dd_idx].sector;
@@ -958,12 +978,13 @@ static void handle_stripe(struct stripe_head *sh)
 	 * need to be failed
 	 */
 	if (failed > 1 && to_read+to_write+written) {
-		spin_lock_irq(&conf->device_lock);
 		for (i=disks; i--; ) {
+			int bitmap_end = 0;
+			spin_lock_irq(&conf->device_lock);
 			/* fail all writes first */
 			bi = sh->dev[i].towrite;
 			sh->dev[i].towrite = NULL;
-			if (bi) to_write--;
+			if (bi) { to_write--; bitmap_end = 1; }
 
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up(&conf->wait_for_overlap);
@@ -981,6 +1002,7 @@ static void handle_stripe(struct stripe_head *sh)
 			/* and fail all 'written' */
 			bi = sh->dev[i].written;
 			sh->dev[i].written = NULL;
+			if (bi) bitmap_end = 1;
 			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 				clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -1009,8 +1031,11 @@ static void handle_stripe(struct stripe_head *sh)
 					bi = nextbi;
 				}
 			}
+			spin_unlock_irq(&conf->device_lock);
+			if (bitmap_end)
+				bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+						STRIPE_SECTORS, 0, 0);
 		}
-		spin_unlock_irq(&conf->device_lock);
 	}
 	if (failed > 1 && syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
@@ -1038,6 +1063,7 @@ static void handle_stripe(struct stripe_head *sh)
 			 test_bit(R5_UPTODATE, &dev->flags) ) {
 			/* We can return any write requests */
 			    struct bio *wbi, *wbi2;
+			    int bitmap_end = 0;
 			    PRINTK("Return write for disc %d\n", i);
 			    spin_lock_irq(&conf->device_lock);
 			    wbi = dev->written;
@@ -1051,7 +1077,13 @@ static void handle_stripe(struct stripe_head *sh)
 				    }
 				    wbi = wbi2;
 			    }
+			    if (dev->towrite == NULL)
+				    bitmap_end = 1;
 			    spin_unlock_irq(&conf->device_lock);
+			    if (bitmap_end)
+				    bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+						    STRIPE_SECTORS,
+						    !test_bit(STRIPE_DEGRADED, &sh->state), 0);
 		    }
 		}
 	}
@@ -1175,7 +1207,8 @@ static void handle_stripe(struct stripe_head *sh)
 				}
 			}
 		/* now if nothing is locked, and if we have enough data, we can start a write request */
-		if (locked == 0 && (rcw == 0 ||rmw == 0)) {
+		if (locked == 0 && (rcw == 0 ||rmw == 0) &&
+		    !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
 			PRINTK("Computing parity...\n");
 			compute_parity(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE);
 			/* now every locked buffer is ready to be written */
@@ -1231,6 +1264,7 @@ static void handle_stripe(struct stripe_head *sh)
 			dev = &sh->dev[failed_num];
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantwrite, &dev->flags);
+			clear_bit(STRIPE_DEGRADED, &sh->state);
 			locked++;
 			set_bit(STRIPE_INSYNC, &sh->state);
 			set_bit(R5_Syncio, &dev->flags);
@@ -1298,6 +1332,8 @@ static void handle_stripe(struct stripe_head *sh)
 			bi->bi_next = NULL;
 			generic_make_request(bi);
 		} else {
+			if (rw == 1)
+				set_bit(STRIPE_DEGRADED, &sh->state);
 			PRINTK("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);
@@ -1322,6 +1358,20 @@ static inline void raid5_activate_delayed(raid5_conf_t *conf)
 	}
 }
 
+static inline void activate_bit_delay(raid5_conf_t *conf)
+{
+	/* device_lock is held */
+	struct list_head head;
+	list_add(&head, &conf->bitmap_list);
+	list_del_init(&conf->bitmap_list);
+	while (!list_empty(&head)) {
+		struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
+		list_del_init(&sh->lru);
+		atomic_inc(&sh->count);
+		__release_stripe(conf, sh);
+	}
+}
+
 static void unplug_slaves(mddev_t *mddev)
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
@@ -1354,8 +1404,10 @@ static void raid5_unplug_device(request_queue_t *q)
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 
-	if (blk_remove_plug(q))
+	if (blk_remove_plug(q)) {
+		conf->seq_flush++;
 		raid5_activate_delayed(conf);
+	}
 	md_wakeup_thread(mddev->thread);
 
 	spin_unlock_irqrestore(&conf->device_lock, flags);
@@ -1411,6 +1463,11 @@ static int make_request (request_queue_t *q, struct bio * bi)
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 
+	if (unlikely(bio_barrier(bi))) {
+		bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	md_write_start(mddev, bi);
 
 	if (bio_data_dir(bi)==WRITE) {
@@ -1488,10 +1545,20 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	sector_t first_sector;
 	int raid_disks = conf->raid_disks;
 	int data_disks = raid_disks-1;
+	sector_t max_sector = mddev->size << 1;
+	int sync_blocks;
 
-	if (sector_nr >= mddev->size <<1) {
+	if (sector_nr >= max_sector) {
 		/* just being told to finish up .. nothing much to do */
 		unplug_slaves(mddev);
+
+		if (mddev->curr_resync < max_sector) /* aborted */
+			bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
+					&sync_blocks, 1);
+		else /* compelted sync */
+			conf->fullsync = 0;
+		bitmap_close_sync(mddev->bitmap);
+
 		return 0;
 	}
 	/* if there is 1 or more failed drives and we are trying
@@ -1503,6 +1570,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		*skipped = 1;
 		return rv;
 	}
+	if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	    !conf->fullsync && sync_blocks >= STRIPE_SECTORS) {
+		/* we can skip this block, and probably more */
+		sync_blocks /= STRIPE_SECTORS;
+		*skipped = 1;
+		return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
+	}
 
 	x = sector_nr;
 	chunk_offset = sector_div(x, sectors_per_chunk);
@@ -1520,6 +1594,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule_timeout(1);
 	}
+	bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 0);
 	spin_lock(&sh->lock);	
 	set_bit(STRIPE_SYNCING, &sh->state);
 	clear_bit(STRIPE_INSYNC, &sh->state);
@@ -1553,6 +1628,13 @@ static void raid5d (mddev_t *mddev)
 	while (1) {
 		struct list_head *first;
 
+		if (conf->seq_flush - conf->seq_write > 0) {
+			int seq = conf->seq_flush;
+			bitmap_unplug(mddev->bitmap);
+			conf->seq_write = seq;
+			activate_bit_delay(conf);
+		}
+
 		if (list_empty(&conf->handle_list) &&
 		    atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
 		    !blk_queue_plugged(mddev->queue) &&
@@ -1586,7 +1668,7 @@ static void raid5d (mddev_t *mddev)
 	PRINTK("--- raid5d inactive\n");
 }
 
-static int run (mddev_t *mddev)
+static int run(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
 	int raid_disk, memory;
@@ -1616,6 +1698,7 @@ static int run (mddev_t *mddev)
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
 	INIT_LIST_HEAD(&conf->delayed_list);
+	INIT_LIST_HEAD(&conf->bitmap_list);
 	INIT_LIST_HEAD(&conf->inactive_list);
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
@@ -1727,6 +1810,9 @@ memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
 
 	/* Ok, everything is just fine now */
 
+	if (mddev->bitmap)
+		mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
+
 	mddev->queue->unplug_fn = raid5_unplug_device;
 	mddev->queue->issue_flush_fn = raid5_issue_flush;
 
@@ -1907,6 +1993,8 @@ static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			rdev->in_sync = 0;
 			rdev->raid_disk = disk;
 			found = 1;
+			if (rdev->saved_raid_disk != disk)
+				conf->fullsync = 1;
 			p->rdev = rdev;
 			break;
 		}
@@ -1936,6 +2024,35 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 	return 0;
 }
 
+static void raid5_quiesce(mddev_t *mddev, int state)
+{
+	raid5_conf_t *conf = mddev_to_conf(mddev);
+
+	switch(state) {
+	case 1: /* stop all writes */
+		spin_lock_irq(&conf->device_lock);
+		conf->quiesce = 1;
+		wait_event_lock_irq(conf->wait_for_stripe,
+				    atomic_read(&conf->active_stripes) == 0,
+				    conf->device_lock, /* nothing */);
+		spin_unlock_irq(&conf->device_lock);
+		break;
+
+	case 0: /* re-enable writes */
+		spin_lock_irq(&conf->device_lock);
+		conf->quiesce = 0;
+		wake_up(&conf->wait_for_stripe);
+		spin_unlock_irq(&conf->device_lock);
+		break;
+	}
+	if (mddev->thread) {
+		if (mddev->bitmap)
+			mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
+		else
+			mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+		md_wakeup_thread(mddev->thread);
+	}
+}
 static mdk_personality_t raid5_personality=
 {
 	.name		= "raid5",
@@ -1950,6 +2067,7 @@ static mdk_personality_t raid5_personality=
 	.spare_active	= raid5_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid5_resize,
+	.quiesce	= raid5_quiesce,
 };
 
 static int __init raid5_init (void)
diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c
index 495dee1d1e83..267eb1430c83 100644
--- a/drivers/md/raid6main.c
+++ b/drivers/md/raid6main.c
@@ -29,6 +29,8 @@
 #include <asm/atomic.h>
 #include "raid6.h"
 
+#include <linux/raid/bitmap.h>
+
 /*
  * Stripe cache
  */
@@ -98,8 +100,13 @@ static inline void __release_stripe(raid6_conf_t *conf, struct stripe_head *sh)
 		if (test_bit(STRIPE_HANDLE, &sh->state)) {
 			if (test_bit(STRIPE_DELAYED, &sh->state))
 				list_add_tail(&sh->lru, &conf->delayed_list);
-			else
+			else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+				 conf->seq_write == sh->bm_seq)
+				list_add_tail(&sh->lru, &conf->bitmap_list);
+			else {
+				clear_bit(STRIPE_BIT_DELAY, &sh->state);
 				list_add_tail(&sh->lru, &conf->handle_list);
+			}
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
@@ -262,6 +269,9 @@ static struct stripe_head *get_active_stripe(raid6_conf_t *conf, sector_t sector
 	spin_lock_irq(&conf->device_lock);
 
 	do {
+		wait_event_lock_irq(conf->wait_for_stripe,
+				    conf->quiesce == 0,
+				    conf->device_lock, /* nothing */);
 		sh = __find_stripe(conf, sector);
 		if (!sh) {
 			if (!conf->inactive_blocked)
@@ -906,6 +916,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 {
 	struct bio **bip;
 	raid6_conf_t *conf = sh->raid_conf;
+	int firstwrite=0;
 
 	PRINTK("adding bh b#%llu to stripe s#%llu\n",
 		(unsigned long long)bi->bi_sector,
@@ -914,9 +925,11 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 
 	spin_lock(&sh->lock);
 	spin_lock_irq(&conf->device_lock);
-	if (forwrite)
+	if (forwrite) {
 		bip = &sh->dev[dd_idx].towrite;
-	else
+		if (*bip == NULL && sh->dev[dd_idx].written == NULL)
+			firstwrite = 1;
+	} else
 		bip = &sh->dev[dd_idx].toread;
 	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
 		if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
@@ -939,6 +952,13 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		(unsigned long long)bi->bi_sector,
 		(unsigned long long)sh->sector, dd_idx);
 
+	if (conf->mddev->bitmap && firstwrite) {
+		sh->bm_seq = conf->seq_write;
+		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
+				  STRIPE_SECTORS, 0);
+		set_bit(STRIPE_BIT_DELAY, &sh->state);
+	}
+
 	if (forwrite) {
 		/* check if page is covered */
 		sector_t sector = sh->dev[dd_idx].sector;
@@ -1066,12 +1086,13 @@ static void handle_stripe(struct stripe_head *sh)
 	 * need to be failed
 	 */
 	if (failed > 2 && to_read+to_write+written) {
-		spin_lock_irq(&conf->device_lock);
 		for (i=disks; i--; ) {
+			int bitmap_end = 0;
+			spin_lock_irq(&conf->device_lock);
 			/* fail all writes first */
 			bi = sh->dev[i].towrite;
 			sh->dev[i].towrite = NULL;
-			if (bi) to_write--;
+			if (bi) { to_write--; bitmap_end = 1; }
 
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up(&conf->wait_for_overlap);
@@ -1089,6 +1110,7 @@ static void handle_stripe(struct stripe_head *sh)
 			/* and fail all 'written' */
 			bi = sh->dev[i].written;
 			sh->dev[i].written = NULL;
+			if (bi) bitmap_end = 1;
 			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 				clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -1117,8 +1139,11 @@ static void handle_stripe(struct stripe_head *sh)
 					bi = nextbi;
 				}
 			}
+			spin_unlock_irq(&conf->device_lock);
+			if (bitmap_end)
+				bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+						STRIPE_SECTORS, 0, 0);
 		}
-		spin_unlock_irq(&conf->device_lock);
 	}
 	if (failed > 2 && syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
@@ -1155,6 +1180,7 @@ static void handle_stripe(struct stripe_head *sh)
 				if (!test_bit(R5_LOCKED, &dev->flags) &&
 				    test_bit(R5_UPTODATE, &dev->flags) ) {
 					/* We can return any write requests */
+					int bitmap_end = 0;
 					struct bio *wbi, *wbi2;
 					PRINTK("Return write for stripe %llu disc %d\n",
 					       (unsigned long long)sh->sector, i);
@@ -1170,7 +1196,13 @@ static void handle_stripe(struct stripe_head *sh)
 						}
 						wbi = wbi2;
 					}
+					if (dev->towrite == NULL)
+						bitmap_end = 1;
 					spin_unlock_irq(&conf->device_lock);
+					if (bitmap_end)
+						bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+								STRIPE_SECTORS,
+								!test_bit(STRIPE_DEGRADED, &sh->state), 0);
 				}
 			}
 	}
@@ -1285,7 +1317,8 @@ static void handle_stripe(struct stripe_head *sh)
 				}
 			}
 		/* now if nothing is locked, and if we have enough data, we can start a write request */
-		if (locked == 0 && rcw == 0) {
+		if (locked == 0 && rcw == 0 &&
+		    !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
 			if ( must_compute > 0 ) {
 				/* We have failed blocks and need to compute them */
 				switch ( failed ) {
@@ -1388,6 +1421,7 @@ static void handle_stripe(struct stripe_head *sh)
 			bdev = &sh->dev[failed_num[1]];
 			locked += !test_bit(R5_LOCKED, &bdev->flags);
 			set_bit(R5_LOCKED, &bdev->flags);
+			clear_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(R5_Wantwrite, &bdev->flags);
 
 			set_bit(STRIPE_INSYNC, &sh->state);
@@ -1457,6 +1491,8 @@ static void handle_stripe(struct stripe_head *sh)
 			bi->bi_next = NULL;
 			generic_make_request(bi);
 		} else {
+			if (rw == 1)
+				set_bit(STRIPE_DEGRADED, &sh->state);
 			PRINTK("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);
@@ -1481,6 +1517,20 @@ static inline void raid6_activate_delayed(raid6_conf_t *conf)
 	}
 }
 
+static inline void activate_bit_delay(raid6_conf_t *conf)
+{
+	/* device_lock is held */
+	struct list_head head;
+	list_add(&head, &conf->bitmap_list);
+	list_del_init(&conf->bitmap_list);
+	while (!list_empty(&head)) {
+		struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
+		list_del_init(&sh->lru);
+		atomic_inc(&sh->count);
+		__release_stripe(conf, sh);
+	}
+}
+
 static void unplug_slaves(mddev_t *mddev)
 {
 	raid6_conf_t *conf = mddev_to_conf(mddev);
@@ -1513,8 +1563,10 @@ static void raid6_unplug_device(request_queue_t *q)
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 
-	if (blk_remove_plug(q))
+	if (blk_remove_plug(q)) {
+		conf->seq_flush++;
 		raid6_activate_delayed(conf);
+	}
 	md_wakeup_thread(mddev->thread);
 
 	spin_unlock_irqrestore(&conf->device_lock, flags);
@@ -1570,6 +1622,11 @@ static int make_request (request_queue_t *q, struct bio * bi)
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 
+	if (unlikely(bio_barrier(bi))) {
+		bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
+		return 0;
+	}
+
 	md_write_start(mddev, bi);
 
 	if (bio_data_dir(bi)==WRITE) {
@@ -1647,10 +1704,20 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	sector_t first_sector;
 	int raid_disks = conf->raid_disks;
 	int data_disks = raid_disks - 2;
+	sector_t max_sector = mddev->size << 1;
+	int sync_blocks;
 
-	if (sector_nr >= mddev->size <<1) {
+	if (sector_nr >= max_sector) {
 		/* just being told to finish up .. nothing much to do */
 		unplug_slaves(mddev);
+
+		if (mddev->curr_resync < max_sector) /* aborted */
+			bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
+					&sync_blocks, 1);
+		else /* compelted sync */
+			conf->fullsync = 0;
+		bitmap_close_sync(mddev->bitmap);
+
 		return 0;
 	}
 	/* if there are 2 or more failed drives and we are trying
@@ -1662,6 +1729,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		*skipped = 1;
 		return rv;
 	}
+	if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	    !conf->fullsync && sync_blocks >= STRIPE_SECTORS) {
+		/* we can skip this block, and probably more */
+		sync_blocks /= STRIPE_SECTORS;
+		*skipped = 1;
+		return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
+	}
 
 	x = sector_nr;
 	chunk_offset = sector_div(x, sectors_per_chunk);
@@ -1679,6 +1753,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule_timeout(1);
 	}
+	bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 0);
 	spin_lock(&sh->lock);
 	set_bit(STRIPE_SYNCING, &sh->state);
 	clear_bit(STRIPE_INSYNC, &sh->state);
@@ -1712,6 +1787,13 @@ static void raid6d (mddev_t *mddev)
 	while (1) {
 		struct list_head *first;
 
+		if (conf->seq_flush - conf->seq_write > 0) {
+			int seq = conf->seq_flush;
+			bitmap_unplug(mddev->bitmap);
+			conf->seq_write = seq;
+			activate_bit_delay(conf);
+		}
+
 		if (list_empty(&conf->handle_list) &&
 		    atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
 		    !blk_queue_plugged(mddev->queue) &&
@@ -1745,7 +1827,7 @@ static void raid6d (mddev_t *mddev)
 	PRINTK("--- raid6d inactive\n");
 }
 
-static int run (mddev_t *mddev)
+static int run(mddev_t *mddev)
 {
 	raid6_conf_t *conf;
 	int raid_disk, memory;
@@ -1775,6 +1857,7 @@ static int run (mddev_t *mddev)
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
 	INIT_LIST_HEAD(&conf->delayed_list);
+	INIT_LIST_HEAD(&conf->bitmap_list);
 	INIT_LIST_HEAD(&conf->inactive_list);
 	atomic_set(&conf->active_stripes, 0);
 	atomic_set(&conf->preread_active_stripes, 0);
@@ -1894,6 +1977,9 @@ static int run (mddev_t *mddev)
 	/* Ok, everything is just fine now */
 	mddev->array_size =  mddev->size * (mddev->raid_disks - 2);
 
+	if (mddev->bitmap)
+		mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
+
 	mddev->queue->unplug_fn = raid6_unplug_device;
 	mddev->queue->issue_flush_fn = raid6_issue_flush;
 	return 0;
@@ -2071,6 +2157,8 @@ static int raid6_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			rdev->in_sync = 0;
 			rdev->raid_disk = disk;
 			found = 1;
+			if (rdev->saved_raid_disk != disk)
+				conf->fullsync = 1;
 			p->rdev = rdev;
 			break;
 		}
@@ -2100,6 +2188,35 @@ static int raid6_resize(mddev_t *mddev, sector_t sectors)
 	return 0;
 }
 
+static void raid6_quiesce(mddev_t *mddev, int state)
+{
+	raid6_conf_t *conf = mddev_to_conf(mddev);
+
+	switch(state) {
+	case 1: /* stop all writes */
+		spin_lock_irq(&conf->device_lock);
+		conf->quiesce = 1;
+		wait_event_lock_irq(conf->wait_for_stripe,
+				    atomic_read(&conf->active_stripes) == 0,
+				    conf->device_lock, /* nothing */);
+		spin_unlock_irq(&conf->device_lock);
+		break;
+
+	case 0: /* re-enable writes */
+		spin_lock_irq(&conf->device_lock);
+		conf->quiesce = 0;
+		wake_up(&conf->wait_for_stripe);
+		spin_unlock_irq(&conf->device_lock);
+		break;
+	}
+	if (mddev->thread) {
+		if (mddev->bitmap)
+			mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
+		else
+			mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
+		md_wakeup_thread(mddev->thread);
+	}
+}
 static mdk_personality_t raid6_personality=
 {
 	.name		= "raid6",
@@ -2114,6 +2231,7 @@ static mdk_personality_t raid6_personality=
 	.spare_active	= raid6_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid6_resize,
+	.quiesce	= raid6_quiesce,
 };
 
 static int __init raid6_init (void)