X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid1.c;h=4070eff6f0f8aca1d1c931a1505431c3d6cc1a2b;hb=43bc926fffd92024b46cafaf7350d669ba9ca884;hp=1db5de52d37665e2ec1aa28c2f8678a5565fbb84;hpb=cee37fe97739d85991964371c1f3a745c00dd236;p=linux-2.6.git

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1db5de52d..4070eff6f 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -12,6 +12,15 @@
  * Fixes to reconstruction by Jakob Østergaard" <jakob@ostenfeld.dk>
  * Various fixes by Neil Brown <neilb@cse.unsw.edu.au>
  *
+ * Changes by Peter T. Breuer <ptb@it.uc3m.es> 31/1/2003 to support
+ * bitmapped intelligence in resync:
+ *
+ *      - bitmap marked during normal i/o
+ *      - bitmap used to skip nondirty blocks during sync
+ *
+ * Additions to bitmap code, (C) 2003-2004 Paul Clements, SteelEye Technology:
+ * - persistent bitmap code
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2, or (at your option)
@@ -22,29 +31,37 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include "dm-bio-list.h"
 #include <linux/raid/raid1.h>
+#include <linux/raid/bitmap.h>
+
+#define DEBUG 0
+#if DEBUG
+#define PRINTK(x...) printk(x)
+#else
+#define PRINTK(x...)
+#endif
 
 /*
  * Number of guaranteed r1bios in case of extreme VM load:
  */
 #define	NR_RAID1_BIOS 256
 
-static mdk_personality_t raid1_personality;
 
 static void unplug_slaves(mddev_t *mddev);
 
+static void allow_barrier(conf_t *conf);
+static void lower_barrier(conf_t *conf);
 
-static void * r1bio_pool_alloc(unsigned int __nocast gfp_flags, void *data)
+static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct pool_info *pi = data;
 	r1bio_t *r1_bio;
 	int size = offsetof(r1bio_t, bios[pi->raid_disks]);
 
 	/* allocate a r1bio with room for raid_disks entries in the bios array */
-	r1_bio = kmalloc(size, gfp_flags);
-	if (r1_bio)
-		memset(r1_bio, 0, size);
-	else
+	r1_bio = kzalloc(size, gfp_flags);
+	if (!r1_bio)
 		unplug_slaves(pi->mddev);
 
 	return r1_bio;
@@ -61,7 +78,7 @@ static void r1bio_pool_free(void *r1_bio, void *data)
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
 #define RESYNC_WINDOW (2048*1024)
 
-static void * r1buf_pool_alloc(unsigned int __nocast gfp_flags, void *data)
+static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
 	struct pool_info *pi = data;
 	struct page *page;
@@ -86,15 +103,30 @@ static void * r1buf_pool_alloc(unsigned int __nocast gfp_flags, void *data)
 	}
 	/*
 	 * Allocate RESYNC_PAGES data pages and attach them to
-	 * the first bio;
+	 * the first bio.
+	 * If this is a user-requested check/repair, allocate
+	 * RESYNC_PAGES for each bio.
 	 */
-	bio = r1_bio->bios[0];
-	for (i = 0; i < RESYNC_PAGES; i++) {
-		page = alloc_page(gfp_flags);
-		if (unlikely(!page))
-			goto out_free_pages;
-
-		bio->bi_io_vec[i].bv_page = page;
+	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
+		j = pi->raid_disks;
+	else
+		j = 1;
+	while(j--) {
+		bio = r1_bio->bios[j];
+		for (i = 0; i < RESYNC_PAGES; i++) {
+			page = alloc_page(gfp_flags);
+			if (unlikely(!page))
+				goto out_free_pages;
+
+			bio->bi_io_vec[i].bv_page = page;
+		}
+	}
+	/* If not user-requests, copy the page pointers to all bios */
+	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
+		for (i=0; i<RESYNC_PAGES ; i++)
+			for (j=1; j<pi->raid_disks; j++)
+				r1_bio->bios[j]->bi_io_vec[i].bv_page =
+					r1_bio->bios[0]->bi_io_vec[i].bv_page;
 	}
 
 	r1_bio->master_bio = NULL;
@@ -102,8 +134,10 @@ static void * r1buf_pool_alloc(unsigned int __nocast gfp_flags, void *data)
 	return r1_bio;
 
 out_free_pages:
-	for ( ; i > 0 ; i--)
-		__free_page(bio->bi_io_vec[i-1].bv_page);
+	for (i=0; i < RESYNC_PAGES ; i++)
+		for (j=0 ; j < pi->raid_disks; j++)
+			safe_put_page(r1_bio->bios[j]->bi_io_vec[i].bv_page);
+	j = -1;
 out_free_bio:
 	while ( ++j < pi->raid_disks )
 		bio_put(r1_bio->bios[j]);
@@ -114,14 +148,16 @@ out_free_bio:
 static void r1buf_pool_free(void *__r1_bio, void *data)
 {
 	struct pool_info *pi = data;
-	int i;
+	int i,j;
 	r1bio_t *r1bio = __r1_bio;
-	struct bio *bio = r1bio->bios[0];
 
-	for (i = 0; i < RESYNC_PAGES; i++) {
-		__free_page(bio->bi_io_vec[i].bv_page);
-		bio->bi_io_vec[i].bv_page = NULL;
-	}
+	for (i = 0; i < RESYNC_PAGES; i++)
+		for (j = pi->raid_disks; j-- ;) {
+			if (j == 0 ||
+			    r1bio->bios[j]->bi_io_vec[i].bv_page !=
+			    r1bio->bios[0]->bi_io_vec[i].bv_page)
+				safe_put_page(r1bio->bios[j]->bi_io_vec[i].bv_page);
+		}
 	for (i=0 ; i < pi->raid_disks; i++)
 		bio_put(r1bio->bios[i]);
 
@@ -134,52 +170,40 @@ static void put_all_bios(conf_t *conf, r1bio_t *r1_bio)
 
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct bio **bio = r1_bio->bios + i;
-		if (*bio)
+		if (*bio && *bio != IO_BLOCKED)
 			bio_put(*bio);
 		*bio = NULL;
 	}
 }
 
-static inline void free_r1bio(r1bio_t *r1_bio)
+static void free_r1bio(r1bio_t *r1_bio)
 {
-	unsigned long flags;
-
 	conf_t *conf = mddev_to_conf(r1_bio->mddev);
 
 	/*
 	 * Wake up any possible resync thread that waits for the device
 	 * to go idle.
 	 */
-	spin_lock_irqsave(&conf->resync_lock, flags);
-	if (!--conf->nr_pending) {
-		wake_up(&conf->wait_idle);
-		wake_up(&conf->wait_resume);
-	}
-	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	allow_barrier(conf);
 
 	put_all_bios(conf, r1_bio);
 	mempool_free(r1_bio, conf->r1bio_pool);
 }
 
-static inline void put_buf(r1bio_t *r1_bio)
+static void put_buf(r1bio_t *r1_bio)
 {
 	conf_t *conf = mddev_to_conf(r1_bio->mddev);
-	unsigned long flags;
+	int i;
+
+	for (i=0; i<conf->raid_disks; i++) {
+		struct bio *bio = r1_bio->bios[i];
+		if (bio->bi_end_io)
+			rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
+	}
 
 	mempool_free(r1_bio, conf->r1buf_pool);
 
-	spin_lock_irqsave(&conf->resync_lock, flags);
-	if (!conf->barrier)
-		BUG();
-	--conf->barrier;
-	wake_up(&conf->wait_resume);
-	wake_up(&conf->wait_idle);
-
-	if (!--conf->nr_pending) {
-		wake_up(&conf->wait_idle);
-		wake_up(&conf->wait_resume);
-	}
-	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	lower_barrier(conf);
 }
 
 static void reschedule_retry(r1bio_t *r1_bio)
@@ -190,8 +214,10 @@ static void reschedule_retry(r1bio_t *r1_bio)
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 	list_add(&r1_bio->retry_list, &conf->retry_list);
+	conf->nr_queued ++;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
+	wake_up(&conf->wait_barrier);
 	md_wakeup_thread(mddev->thread);
 }
 
@@ -204,8 +230,17 @@ 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);
 }
 
@@ -234,9 +269,9 @@ static int raid1_end_read_request(struct bio *bio, unsigned int bytes_done, int
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate)
-		md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
-	else
+	update_head_pos(mirror, r1_bio);
+
+	if (uptodate || conf->working_disks <= 1) {
 		/*
 		 * Set R1BIO_Uptodate in our master bio, so that
 		 * we will return a good error code for to the higher
@@ -246,16 +281,11 @@ static int raid1_end_read_request(struct bio *bio, unsigned int bytes_done, int
 		 * user-side. So if something waits for IO, then it will
 		 * wait for the 'master' bio.
 		 */
-		set_bit(R1BIO_Uptodate, &r1_bio->state);
+		if (uptodate)
+			set_bit(R1BIO_Uptodate, &r1_bio->state);
 
-	update_head_pos(mirror, r1_bio);
-
-	/*
-	 * we have only one bio on the read side
-	 */
-	if (uptodate)
 		raid_end_bio_io(r1_bio);
-	else {
+	} else {
 		/*
 		 * oops, read error:
 		 */
@@ -274,8 +304,9 @@ 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 = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	conf_t *conf = mddev_to_conf(r1_bio->mddev);
+	struct bio *to_put = NULL;
 
 	if (bio->bi_size)
 		return 1;
@@ -284,36 +315,88 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 		if (r1_bio->bios[mirror] == bio)
 			break;
 
-	/*
-	 * this branch is our 'one mirror IO has finished' event handler:
-	 */
-	if (!uptodate)
-		md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
-	else
+	if (error == -EOPNOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
+		set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
+		set_bit(R1BIO_BarrierRetry, &r1_bio->state);
+		r1_bio->mddev->barriers_work = 0;
+		/* Don't rdev_dec_pending in this branch - keep it for the retry */
+	} else {
 		/*
-		 * Set R1BIO_Uptodate in our master bio, so that
-		 * we will return a good error code for to the higher
-		 * levels even if IO on some other mirrored buffer fails.
-		 *
-		 * The 'master' represents the composite IO operation to
-		 * user-side. So if something waits for IO, then it will
-		 * wait for the 'master' bio.
+		 * this branch is our 'one mirror IO has finished' event handler:
 		 */
-		set_bit(R1BIO_Uptodate, &r1_bio->state);
-
-	update_head_pos(mirror, r1_bio);
-
+		r1_bio->bios[mirror] = NULL;
+		to_put = bio;
+		if (!uptodate) {
+			md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
+			/* an I/O failed, we can't clear the bitmap */
+			set_bit(R1BIO_Degraded, &r1_bio->state);
+		} else
+			/*
+			 * Set R1BIO_Uptodate in our master bio, so that
+			 * we will return a good error code for to the higher
+			 * levels even if IO on some other mirrored buffer fails.
+			 *
+			 * The 'master' represents the composite IO operation to
+			 * user-side. So if something waits for IO, then it will
+			 * wait for the 'master' bio.
+			 */
+			set_bit(R1BIO_Uptodate, &r1_bio->state);
+
+		update_head_pos(mirror, r1_bio);
+
+		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);
+				}
+			}
+		}
+		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+	}
 	/*
 	 *
 	 * Let's see if all mirrored write operations have finished
 	 * already.
 	 */
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
+		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
+			reschedule_retry(r1_bio);
+			goto out;
+		}
+		/* it really is the end of this request */
+		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+			/* free extra copy of the data pages */
+			int i = bio->bi_vcnt;
+			while (i--)
+				safe_put_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),
+				behind);
 		md_write_end(r1_bio->mddev);
 		raid_end_bio_io(r1_bio);
 	}
+ out:
+	if (to_put)
+		bio_put(to_put);
 
-	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
 	return 0;
 }
 
@@ -336,13 +419,14 @@ 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.
 	 */
@@ -352,11 +436,18 @@ 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 = rcu_dereference(conf->mirrors[new_disk].rdev);
+		     r1_bio->bios[new_disk] == IO_BLOCKED ||
+		     !rdev || !test_bit(In_sync, &rdev->flags)
+			     || test_bit(WriteMostly, &rdev->flags);
+		     rdev = rcu_dereference(conf->mirrors[++new_disk].rdev)) {
+
+			if (rdev && test_bit(In_sync, &rdev->flags) &&
+				r1_bio->bios[new_disk] != IO_BLOCKED)
+				wonly_disk = new_disk;
+
+			if (new_disk == conf->raid_disks - 1) {
+				new_disk = wonly_disk;
 				break;
 			}
 		}
@@ -365,16 +456,28 @@ 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 = rcu_dereference(conf->mirrors[new_disk].rdev);
+	     r1_bio->bios[new_disk] == IO_BLOCKED ||
+	     !rdev || !test_bit(In_sync, &rdev->flags) ||
+		     test_bit(WriteMostly, &rdev->flags);
+	     rdev = rcu_dereference(conf->mirrors[new_disk].rdev)) {
+
+		if (rdev && test_bit(In_sync, &rdev->flags) &&
+		    r1_bio->bios[new_disk] != IO_BLOCKED)
+			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 */
 
@@ -395,37 +498,41 @@ 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 = rcu_dereference(conf->mirrors[disk].rdev);
+
+		if (!rdev || r1_bio->bios[disk] == IO_BLOCKED ||
+		    !test_bit(In_sync, &rdev->flags) ||
+		    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 = rcu_dereference(conf->mirrors[new_disk].rdev);
+		if (!rdev)
+			goto retry;
+		atomic_inc(&rdev->nr_pending);
+		if (!test_bit(In_sync, &rdev->flags)) {
 			/* cannot risk returning a device that failed
 			 * before we inc'ed nr_pending
 			 */
-			atomic_dec(&new_rdev->nr_pending);
+			rdev_dec_pending(rdev, conf->mddev);
 			goto retry;
 		}
+		conf->next_seq_sect = this_sector + sectors;
+		conf->last_used = new_disk;
 	}
 	rcu_read_unlock();
 
@@ -439,8 +546,8 @@ static void unplug_slaves(mddev_t *mddev)
 
 	rcu_read_lock();
 	for (i=0; i<mddev->raid_disks; i++) {
-		mdk_rdev_t *rdev = conf->mirrors[i].rdev;
-		if (rdev && !rdev->faulty && atomic_read(&rdev->nr_pending)) {
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
 			request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
 
 			atomic_inc(&rdev->nr_pending);
@@ -458,7 +565,10 @@ static void unplug_slaves(mddev_t *mddev)
 
 static void raid1_unplug(request_queue_t *q)
 {
-	unplug_slaves(q->queuedata);
+	mddev_t *mddev = q->queuedata;
+
+	unplug_slaves(mddev);
+	md_wakeup_thread(mddev->thread);
 }
 
 static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk,
@@ -470,8 +580,8 @@ static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk,
 
 	rcu_read_lock();
 	for (i=0; i<mddev->raid_disks && ret == 0; i++) {
-		mdk_rdev_t *rdev = conf->mirrors[i].rdev;
-		if (rdev && !rdev->faulty) {
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct block_device *bdev = rdev->bdev;
 			request_queue_t *r_queue = bdev_get_queue(bdev);
 
@@ -491,30 +601,140 @@ static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk,
 	return ret;
 }
 
-/*
- * Throttle resync depth, so that we can both get proper overlapping of
- * requests, but are still able to handle normal requests quickly.
+/* Barriers....
+ * Sometimes we need to suspend IO while we do something else,
+ * either some resync/recovery, or reconfigure the array.
+ * To do this we raise a 'barrier'.
+ * The 'barrier' is a counter that can be raised multiple times
+ * to count how many activities are happening which preclude
+ * normal IO.
+ * We can only raise the barrier if there is no pending IO.
+ * i.e. if nr_pending == 0.
+ * We choose only to raise the barrier if no-one is waiting for the
+ * barrier to go down.  This means that as soon as an IO request
+ * is ready, no other operations which require a barrier will start
+ * until the IO request has had a chance.
+ *
+ * So: regular IO calls 'wait_barrier'.  When that returns there
+ *    is no backgroup IO happening,  It must arrange to call
+ *    allow_barrier when it has finished its IO.
+ * backgroup IO calls must call raise_barrier.  Once that returns
+ *    there is no normal IO happeing.  It must arrange to call
+ *    lower_barrier when the particular background IO completes.
  */
 #define RESYNC_DEPTH 32
 
-static void device_barrier(conf_t *conf, sector_t sect)
+static void raise_barrier(conf_t *conf)
 {
 	spin_lock_irq(&conf->resync_lock);
-	wait_event_lock_irq(conf->wait_idle, !waitqueue_active(&conf->wait_resume),
-			    conf->resync_lock, unplug_slaves(conf->mddev));
-	
-	if (!conf->barrier++) {
-		wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
-				    conf->resync_lock, unplug_slaves(conf->mddev));
-		if (conf->nr_pending)
-			BUG();
+
+	/* Wait until no block IO is waiting */
+	wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting,
+			    conf->resync_lock,
+			    raid1_unplug(conf->mddev->queue));
+
+	/* block any new IO from starting */
+	conf->barrier++;
+
+	/* No wait for all pending IO to complete */
+	wait_event_lock_irq(conf->wait_barrier,
+			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
+			    conf->resync_lock,
+			    raid1_unplug(conf->mddev->queue));
+
+	spin_unlock_irq(&conf->resync_lock);
+}
+
+static void lower_barrier(conf_t *conf)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&conf->resync_lock, flags);
+	conf->barrier--;
+	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	wake_up(&conf->wait_barrier);
+}
+
+static void wait_barrier(conf_t *conf)
+{
+	spin_lock_irq(&conf->resync_lock);
+	if (conf->barrier) {
+		conf->nr_waiting++;
+		wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
+				    conf->resync_lock,
+				    raid1_unplug(conf->mddev->queue));
+		conf->nr_waiting--;
 	}
-	wait_event_lock_irq(conf->wait_resume, conf->barrier < RESYNC_DEPTH,
-			    conf->resync_lock, unplug_slaves(conf->mddev));
-	conf->next_resync = sect;
+	conf->nr_pending++;
 	spin_unlock_irq(&conf->resync_lock);
 }
 
+static void allow_barrier(conf_t *conf)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&conf->resync_lock, flags);
+	conf->nr_pending--;
+	spin_unlock_irqrestore(&conf->resync_lock, flags);
+	wake_up(&conf->wait_barrier);
+}
+
+static void freeze_array(conf_t *conf)
+{
+	/* stop syncio and normal IO and wait for everything to
+	 * go quite.
+	 * We increment barrier and nr_waiting, and then
+	 * wait until barrier+nr_pending match nr_queued+2
+	 */
+	spin_lock_irq(&conf->resync_lock);
+	conf->barrier++;
+	conf->nr_waiting++;
+	wait_event_lock_irq(conf->wait_barrier,
+			    conf->barrier+conf->nr_pending == conf->nr_queued+2,
+			    conf->resync_lock,
+			    raid1_unplug(conf->mddev->queue));
+	spin_unlock_irq(&conf->resync_lock);
+}
+static void unfreeze_array(conf_t *conf)
+{
+	/* reverse the effect of the freeze */
+	spin_lock_irq(&conf->resync_lock);
+	conf->barrier--;
+	conf->nr_waiting--;
+	wake_up(&conf->wait_barrier);
+	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 = kzalloc(bio->bi_vcnt * sizeof(struct page *),
+					GFP_NOIO);
+	if (unlikely(!pages))
+		goto do_sync_io;
+
+	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++)
+			put_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;
@@ -522,27 +742,38 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	mirror_info_t *mirror;
 	r1bio_t *r1_bio;
 	struct bio *read_bio;
-	int i, disks;
+	int i, targets = 0, disks;
 	mdk_rdev_t *rdev;
+	struct bitmap *bitmap = mddev->bitmap;
+	unsigned long flags;
+	struct bio_list bl;
+	struct page **behind_pages = NULL;
+	const int rw = bio_data_dir(bio);
+	int do_barriers;
 
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
 	 * Continue immediately if no resync is active currently.
+	 * We test barriers_work *after* md_write_start as md_write_start
+	 * may cause the first superblock write, and that will check out
+	 * if barriers work.
 	 */
-	spin_lock_irq(&conf->resync_lock);
-	wait_event_lock_irq(conf->wait_resume, !conf->barrier, conf->resync_lock, );
-	conf->nr_pending++;
-	spin_unlock_irq(&conf->resync_lock);
 
-	if (bio_data_dir(bio)==WRITE) {
-		disk_stat_inc(mddev->gendisk, writes);
-		disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bio));
-	} else {
-		disk_stat_inc(mddev->gendisk, reads);
-		disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bio));
+	md_write_start(mddev, bio); /* wait on superblock update early */
+
+	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+		if (rw == WRITE)
+			md_write_end(mddev);
+		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		return 0;
 	}
 
+	wait_barrier(conf);
+
+	disk_stat_inc(mddev->gendisk, ios[rw]);
+	disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
+
 	/*
 	 * make_request() can abort the operation when READA is being
 	 * used and no empty request is available.
@@ -552,13 +783,11 @@ static int make_request(request_queue_t *q, struct bio * bio)
 
 	r1_bio->master_bio = bio;
 	r1_bio->sectors = bio->bi_size >> 9;
-
+	r1_bio->state = 0;
 	r1_bio->mddev = mddev;
 	r1_bio->sector = bio->bi_sector;
 
-	r1_bio->state = 0;
-
-	if (bio_data_dir(bio) == READ) {
+	if (rw == READ) {
 		/*
 		 * read balancing logic:
 		 */
@@ -595,23 +824,51 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	 * bios[x] to bio
 	 */
 	disks = conf->raid_disks;
+#if 0
+	{ static int first=1;
+	if (first) printk("First Write sector %llu disks %d\n",
+			  (unsigned long long)r1_bio->sector, disks);
+	first = 0;
+	}
+#endif
 	rcu_read_lock();
 	for (i = 0;  i < disks; i++) {
-		if ((rdev=conf->mirrors[i].rdev) != NULL &&
-		    !rdev->faulty) {
+		if ((rdev=rcu_dereference(conf->mirrors[i].rdev)) != NULL &&
+		    !test_bit(Faulty, &rdev->flags)) {
 			atomic_inc(&rdev->nr_pending);
-			if (rdev->faulty) {
-				atomic_dec(&rdev->nr_pending);
+			if (test_bit(Faulty, &rdev->flags)) {
+				rdev_dec_pending(rdev, mddev);
 				r1_bio->bios[i] = NULL;
 			} else
 				r1_bio->bios[i] = bio;
+			targets++;
 		} else
 			r1_bio->bios[i] = NULL;
 	}
 	rcu_read_unlock();
 
-	atomic_set(&r1_bio->remaining, 1);
-	md_write_start(mddev);
+	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);
+
+	do_barriers = bio_barrier(bio);
+	if (do_barriers)
+		set_bit(R1BIO_Barrier, &r1_bio->state);
+
+	bio_list_init(&bl);
 	for (i = 0; i < disks; i++) {
 		struct bio *mbio;
 		if (!r1_bio->bios[i])
@@ -623,17 +880,45 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		mbio->bi_sector	= r1_bio->sector + conf->mirrors[i].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_rw = WRITE;
+		mbio->bi_rw = WRITE | do_barriers;
 		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);
-		generic_make_request(mbio);
-	}
 
-	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		md_write_end(mddev);
-		raid_end_bio_io(r1_bio);
+		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,
+				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);
+
+	blk_plug_device(mddev->queue);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
+
+#if 0
+	while ((bio = bio_list_pop(&bl)) != NULL)
+		generic_make_request(bio);
+#endif
 
 	return 0;
 }
@@ -648,7 +933,7 @@ static void status(struct seq_file *seq, mddev_t *mddev)
 	for (i = 0; i < conf->raid_disks; i++)
 		seq_printf(seq, "%s",
 			      conf->mirrors[i].rdev &&
-			      conf->mirrors[i].rdev->in_sync ? "U" : "_");
+			      test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
 	seq_printf(seq, "]");
 }
 
@@ -664,14 +949,14 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	 * next level up know.
 	 * else mark the drive as failed
 	 */
-	if (rdev->in_sync
+	if (test_bit(In_sync, &rdev->flags)
 	    && conf->working_disks == 1)
 		/*
 		 * Don't fail the drive, act as though we were just a
 		 * normal single drive
 		 */
 		return;
-	if (rdev->in_sync) {
+	if (test_bit(In_sync, &rdev->flags)) {
 		mddev->degraded++;
 		conf->working_disks--;
 		/*
@@ -679,8 +964,8 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		 */
 		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
 	}
-	rdev->in_sync = 0;
-	rdev->faulty = 1;
+	clear_bit(In_sync, &rdev->flags);
+	set_bit(Faulty, &rdev->flags);
 	mddev->sb_dirty = 1;
 	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device. \n"
 		"	Operation continuing on %d devices\n",
@@ -705,20 +990,15 @@ static void print_conf(conf_t *conf)
 		tmp = conf->mirrors + i;
 		if (tmp->rdev)
 			printk(" disk %d, wo:%d, o:%d, dev:%s\n",
-				i, !tmp->rdev->in_sync, !tmp->rdev->faulty,
+				i, !test_bit(In_sync, &tmp->rdev->flags), !test_bit(Faulty, &tmp->rdev->flags),
 				bdevname(tmp->rdev->bdev,b));
 	}
 }
 
 static void close_sync(conf_t *conf)
 {
-	spin_lock_irq(&conf->resync_lock);
-	wait_event_lock_irq(conf->wait_resume, !conf->barrier,
-			    conf->resync_lock, 	unplug_slaves(conf->mddev));
-	spin_unlock_irq(&conf->resync_lock);
-
-	if (conf->barrier) BUG();
-	if (waitqueue_active(&conf->wait_idle)) BUG();
+	wait_barrier(conf);
+	allow_barrier(conf);
 
 	mempool_destroy(conf->r1buf_pool);
 	conf->r1buf_pool = NULL;
@@ -737,11 +1017,11 @@ static int raid1_spare_active(mddev_t *mddev)
 	for (i = 0; i < conf->raid_disks; i++) {
 		tmp = conf->mirrors + i;
 		if (tmp->rdev 
-		    && !tmp->rdev->faulty
-		    && !tmp->rdev->in_sync) {
+		    && !test_bit(Faulty, &tmp->rdev->flags)
+		    && !test_bit(In_sync, &tmp->rdev->flags)) {
 			conf->working_disks++;
 			mddev->degraded--;
-			tmp->rdev->in_sync = 1;
+			set_bit(In_sync, &tmp->rdev->flags);
 		}
 	}
 
@@ -754,7 +1034,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
 	int found = 0;
-	int mirror;
+	int mirror = 0;
 	mirror_info_t *p;
 
 	for (mirror=0; mirror < mddev->raid_disks; mirror++)
@@ -773,7 +1053,12 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
 			found = 1;
-			p->rdev = rdev;
+			/* As all devices are equivalent, we don't need a full recovery
+			 * if this was recently any drive of the array
+			 */
+			if (rdev->saved_raid_disk < 0)
+				conf->fullsync = 1;
+			rcu_assign_pointer(p->rdev, rdev);
 			break;
 		}
 
@@ -791,7 +1076,7 @@ static int raid1_remove_disk(mddev_t *mddev, int number)
 	print_conf(conf);
 	rdev = p->rdev;
 	if (rdev) {
-		if (rdev->in_sync ||
+		if (test_bit(In_sync, &rdev->flags) ||
 		    atomic_read(&rdev->nr_pending)) {
 			err = -EBUSY;
 			goto abort;
@@ -813,28 +1098,27 @@ abort:
 
 static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
-	conf_t *conf = mddev_to_conf(r1_bio->mddev);
+	int i;
 
 	if (bio->bi_size)
 		return 1;
 
-	if (r1_bio->bios[r1_bio->read_disk] != bio)
-		BUG();
-	update_head_pos(r1_bio->read_disk, r1_bio);
+	for (i=r1_bio->mddev->raid_disks; i--; )
+		if (r1_bio->bios[i] == bio)
+			break;
+	BUG_ON(i < 0);
+	update_head_pos(i, r1_bio);
 	/*
 	 * we have read a block, now it needs to be re-written,
 	 * or re-read if the read failed.
 	 * We don't do much here, just schedule handling by raid1d
 	 */
-	if (!uptodate)
-		md_error(r1_bio->mddev,
-			 conf->mirrors[r1_bio->read_disk].rdev);
-	else
+	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
-	rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
-	reschedule_retry(r1_bio);
+
+	if (atomic_dec_and_test(&r1_bio->remaining))
+		reschedule_retry(r1_bio);
 	return 0;
 }
 
@@ -855,15 +1139,26 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 			mirror = i;
 			break;
 		}
-	if (!uptodate)
+	if (!uptodate) {
+		int sync_blocks = 0;
+		sector_t s = r1_bio->sector;
+		long sectors_to_go = r1_bio->sectors;
+		/* make sure these bits doesn't get cleared. */
+		do {
+			bitmap_end_sync(mddev->bitmap, r1_bio->sector,
+					&sync_blocks, 1);
+			s += sync_blocks;
+			sectors_to_go -= sync_blocks;
+		} while (sectors_to_go > 0);
 		md_error(mddev, conf->mirrors[mirror].rdev);
+	}
+
 	update_head_pos(mirror, r1_bio);
 
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
 		md_done_sync(mddev, r1_bio->sectors, uptodate);
 		put_buf(r1_bio);
 	}
-	rdev_dec_pending(conf->mirrors[mirror].rdev, mddev);
 	return 0;
 }
 
@@ -876,37 +1171,181 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 
 	bio = r1_bio->bios[r1_bio->read_disk];
 
-	/*
-	 * schedule writes
-	 */
+
+	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+		/* We have read all readable devices.  If we haven't
+		 * got the block, then there is no hope left.
+		 * If we have, then we want to do a comparison
+		 * and skip the write if everything is the same.
+		 * If any blocks failed to read, then we need to
+		 * attempt an over-write
+		 */
+		int primary;
+		if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+			for (i=0; i<mddev->raid_disks; i++)
+				if (r1_bio->bios[i]->bi_end_io == end_sync_read)
+					md_error(mddev, conf->mirrors[i].rdev);
+
+			md_done_sync(mddev, r1_bio->sectors, 1);
+			put_buf(r1_bio);
+			return;
+		}
+		for (primary=0; primary<mddev->raid_disks; primary++)
+			if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
+			    test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
+				r1_bio->bios[primary]->bi_end_io = NULL;
+				rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
+				break;
+			}
+		r1_bio->read_disk = primary;
+		for (i=0; i<mddev->raid_disks; i++)
+			if (r1_bio->bios[i]->bi_end_io == end_sync_read &&
+			    test_bit(BIO_UPTODATE, &r1_bio->bios[i]->bi_flags)) {
+				int j;
+				int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
+				struct bio *pbio = r1_bio->bios[primary];
+				struct bio *sbio = r1_bio->bios[i];
+				for (j = vcnt; j-- ; )
+					if (memcmp(page_address(pbio->bi_io_vec[j].bv_page),
+						   page_address(sbio->bi_io_vec[j].bv_page),
+						   PAGE_SIZE))
+						break;
+				if (j >= 0)
+					mddev->resync_mismatches += r1_bio->sectors;
+				if (j < 0 || test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
+					sbio->bi_end_io = NULL;
+					rdev_dec_pending(conf->mirrors[i].rdev, mddev);
+				} else {
+					/* fixup the bio for reuse */
+					sbio->bi_vcnt = vcnt;
+					sbio->bi_size = r1_bio->sectors << 9;
+					sbio->bi_idx = 0;
+					sbio->bi_phys_segments = 0;
+					sbio->bi_hw_segments = 0;
+					sbio->bi_hw_front_size = 0;
+					sbio->bi_hw_back_size = 0;
+					sbio->bi_flags &= ~(BIO_POOL_MASK - 1);
+					sbio->bi_flags |= 1 << BIO_UPTODATE;
+					sbio->bi_next = NULL;
+					sbio->bi_sector = r1_bio->sector +
+						conf->mirrors[i].rdev->data_offset;
+					sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+				}
+			}
+	}
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
-		/*
-		 * There is no point trying a read-for-reconstruct as
-		 * reconstruct is about to be aborted
+		/* ouch - failed to read all of that.
+		 * Try some synchronous reads of other devices to get
+		 * good data, much like with normal read errors.  Only
+		 * read into the pages we already have so they we don't
+		 * need to re-issue the read request.
+		 * We don't need to freeze the array, because being in an
+		 * active sync request, there is no normal IO, and
+		 * no overlapping syncs.
 		 */
-		char b[BDEVNAME_SIZE];
-		printk(KERN_ALERT "raid1: %s: unrecoverable I/O read error"
-			" for block %llu\n",
-			bdevname(bio->bi_bdev,b), 
-			(unsigned long long)r1_bio->sector);
-		md_done_sync(mddev, r1_bio->sectors, 0);
-		put_buf(r1_bio);
-		return;
+		sector_t sect = r1_bio->sector;
+		int sectors = r1_bio->sectors;
+		int idx = 0;
+
+		while(sectors) {
+			int s = sectors;
+			int d = r1_bio->read_disk;
+			int success = 0;
+			mdk_rdev_t *rdev;
+
+			if (s > (PAGE_SIZE>>9))
+				s = PAGE_SIZE >> 9;
+			do {
+				if (r1_bio->bios[d]->bi_end_io == end_sync_read) {
+					rdev = conf->mirrors[d].rdev;
+					if (sync_page_io(rdev->bdev,
+							 sect + rdev->data_offset,
+							 s<<9,
+							 bio->bi_io_vec[idx].bv_page,
+							 READ)) {
+						success = 1;
+						break;
+					}
+				}
+				d++;
+				if (d == conf->raid_disks)
+					d = 0;
+			} while (!success && d != r1_bio->read_disk);
+
+			if (success) {
+				int start = d;
+				/* write it back and re-read */
+				set_bit(R1BIO_Uptodate, &r1_bio->state);
+				while (d != r1_bio->read_disk) {
+					if (d == 0)
+						d = conf->raid_disks;
+					d--;
+					if (r1_bio->bios[d]->bi_end_io != end_sync_read)
+						continue;
+					rdev = conf->mirrors[d].rdev;
+					atomic_add(s, &rdev->corrected_errors);
+					if (sync_page_io(rdev->bdev,
+							 sect + rdev->data_offset,
+							 s<<9,
+							 bio->bi_io_vec[idx].bv_page,
+							 WRITE) == 0)
+						md_error(mddev, rdev);
+				}
+				d = start;
+				while (d != r1_bio->read_disk) {
+					if (d == 0)
+						d = conf->raid_disks;
+					d--;
+					if (r1_bio->bios[d]->bi_end_io != end_sync_read)
+						continue;
+					rdev = conf->mirrors[d].rdev;
+					if (sync_page_io(rdev->bdev,
+							 sect + rdev->data_offset,
+							 s<<9,
+							 bio->bi_io_vec[idx].bv_page,
+							 READ) == 0)
+						md_error(mddev, rdev);
+				}
+			} else {
+				char b[BDEVNAME_SIZE];
+				/* Cannot read from anywhere, array is toast */
+				md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
+				printk(KERN_ALERT "raid1: %s: unrecoverable I/O read error"
+				       " for block %llu\n",
+				       bdevname(bio->bi_bdev,b),
+				       (unsigned long long)r1_bio->sector);
+				md_done_sync(mddev, r1_bio->sectors, 0);
+				put_buf(r1_bio);
+				return;
+			}
+			sectors -= s;
+			sect += s;
+			idx ++;
+		}
 	}
 
+	/*
+	 * schedule writes
+	 */
 	atomic_set(&r1_bio->remaining, 1);
 	for (i = 0; i < disks ; i++) {
 		wbio = r1_bio->bios[i];
-		if (wbio->bi_end_io != end_sync_write)
+		if (wbio->bi_end_io == NULL ||
+		    (wbio->bi_end_io == end_sync_read &&
+		     (i == r1_bio->read_disk ||
+		      !test_bit(MD_RECOVERY_SYNC, &mddev->recovery))))
 			continue;
 
-		atomic_inc(&conf->mirrors[i].rdev->nr_pending);
+		wbio->bi_rw = WRITE;
+		wbio->bi_end_io = end_sync_write;
 		atomic_inc(&r1_bio->remaining);
 		md_sync_acct(conf->mirrors[i].rdev->bdev, wbio->bi_size >> 9);
+
 		generic_make_request(wbio);
 	}
 
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
+		/* if we're here, all write(s) have completed, so clean up */
 		md_done_sync(mddev, r1_bio->sectors, 1);
 		put_buf(r1_bio);
 	}
@@ -931,15 +1370,35 @@ static void raid1d(mddev_t *mddev)
 	mdk_rdev_t *rdev;
 
 	md_check_recovery(mddev);
-	md_handle_safemode(mddev);
 	
 	for (;;) {
 		char b[BDEVNAME_SIZE];
 		spin_lock_irqsave(&conf->device_lock, flags);
+
+		if (conf->pending_bio_list.head) {
+			bio = bio_list_get(&conf->pending_bio_list);
+			blk_remove_plug(mddev->queue);
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			/* flush any pending bitmap writes to disk before proceeding w/ I/O */
+			if (bitmap_unplug(mddev->bitmap) != 0)
+				printk("%s: bitmap file write failed!\n", mdname(mddev));
+
+			while (bio) { /* submit pending writes */
+				struct bio *next = bio->bi_next;
+				bio->bi_next = NULL;
+				generic_make_request(bio);
+				bio = next;
+			}
+			unplug = 1;
+
+			continue;
+		}
+
 		if (list_empty(head))
 			break;
 		r1_bio = list_entry(head->prev, r1bio_t, retry_list);
 		list_del(head->prev);
+		conf->nr_queued--;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 
 		mddev = r1_bio->mddev;
@@ -947,8 +1406,122 @@ static void raid1d(mddev_t *mddev)
 		if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
 			sync_request_write(mddev, r1_bio);
 			unplug = 1;
+		} else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
+			/* some requests in the r1bio were BIO_RW_BARRIER
+			 * requests which failed with -EOPNOTSUPP.  Hohumm..
+			 * Better resubmit without the barrier.
+			 * We know which devices to resubmit for, because
+			 * all others have had their bios[] entry cleared.
+			 * We already have a nr_pending reference on these rdevs.
+			 */
+			int i;
+			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
+			clear_bit(R1BIO_Barrier, &r1_bio->state);
+			for (i=0; i < conf->raid_disks; i++)
+				if (r1_bio->bios[i])
+					atomic_inc(&r1_bio->remaining);
+			for (i=0; i < conf->raid_disks; i++)
+				if (r1_bio->bios[i]) {
+					struct bio_vec *bvec;
+					int j;
+
+					bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
+					/* copy pages from the failed bio, as
+					 * this might be a write-behind device */
+					__bio_for_each_segment(bvec, bio, j, 0)
+						bvec->bv_page = bio_iovec_idx(r1_bio->bios[i], j)->bv_page;
+					bio_put(r1_bio->bios[i]);
+					bio->bi_sector = r1_bio->sector +
+						conf->mirrors[i].rdev->data_offset;
+					bio->bi_bdev = conf->mirrors[i].rdev->bdev;
+					bio->bi_end_io = raid1_end_write_request;
+					bio->bi_rw = WRITE;
+					bio->bi_private = r1_bio;
+					r1_bio->bios[i] = bio;
+					generic_make_request(bio);
+				}
 		} else {
 			int disk;
+
+			/* we got a read error. Maybe the drive is bad.  Maybe just
+			 * the block and we can fix it.
+			 * We freeze all other IO, and try reading the block from
+			 * other devices.  When we find one, we re-write
+			 * and check it that fixes the read error.
+			 * This is all done synchronously while the array is
+			 * frozen
+			 */
+			sector_t sect = r1_bio->sector;
+			int sectors = r1_bio->sectors;
+			freeze_array(conf);
+			if (mddev->ro == 0) while(sectors) {
+				int s = sectors;
+				int d = r1_bio->read_disk;
+				int success = 0;
+
+				if (s > (PAGE_SIZE>>9))
+					s = PAGE_SIZE >> 9;
+
+				do {
+					rdev = conf->mirrors[d].rdev;
+					if (rdev &&
+					    test_bit(In_sync, &rdev->flags) &&
+					    sync_page_io(rdev->bdev,
+							 sect + rdev->data_offset,
+							 s<<9,
+							 conf->tmppage, READ))
+						success = 1;
+					else {
+						d++;
+						if (d == conf->raid_disks)
+							d = 0;
+					}
+				} while (!success && d != r1_bio->read_disk);
+
+				if (success) {
+					/* write it back and re-read */
+					int start = d;
+					while (d != r1_bio->read_disk) {
+						if (d==0)
+							d = conf->raid_disks;
+						d--;
+						rdev = conf->mirrors[d].rdev;
+						atomic_add(s, &rdev->corrected_errors);
+						if (rdev &&
+						    test_bit(In_sync, &rdev->flags)) {
+							if (sync_page_io(rdev->bdev,
+									 sect + rdev->data_offset,
+									 s<<9, conf->tmppage, WRITE) == 0)
+								/* Well, this device is dead */
+								md_error(mddev, rdev);
+						}
+					}
+					d = start;
+					while (d != r1_bio->read_disk) {
+						if (d==0)
+							d = conf->raid_disks;
+						d--;
+						rdev = conf->mirrors[d].rdev;
+						if (rdev &&
+						    test_bit(In_sync, &rdev->flags)) {
+							if (sync_page_io(rdev->bdev,
+									 sect + rdev->data_offset,
+									 s<<9, conf->tmppage, READ) == 0)
+								/* Well, this device is dead */
+								md_error(mddev, rdev);
+						}
+					}
+				} else {
+					/* Cannot read from anywhere -- bye bye array */
+					md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
+					break;
+				}
+				sectors -= s;
+				sect += s;
+			}
+
+			unfreeze_array(conf);
+
 			bio = r1_bio->bios[r1_bio->read_disk];
 			if ((disk=read_balance(conf, r1_bio)) == -1) {
 				printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
@@ -957,7 +1530,8 @@ static void raid1d(mddev_t *mddev)
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
 			} else {
-				r1_bio->bios[r1_bio->read_disk] = NULL;
+				r1_bio->bios[r1_bio->read_disk] =
+					mddev->ro ? IO_BLOCKED : NULL;
 				r1_bio->read_disk = disk;
 				bio_put(bio);
 				bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
@@ -989,8 +1563,7 @@ static int init_resync(conf_t *conf)
 	int buffs;
 
 	buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
-	if (conf->r1buf_pool)
-		BUG();
+	BUG_ON(conf->r1buf_pool);
 	conf->r1buf_pool = mempool_create(buffs, r1buf_pool_alloc, r1buf_pool_free,
 					  conf->poolinfo);
 	if (!conf->r1buf_pool)
@@ -1009,69 +1582,85 @@ static int init_resync(conf_t *conf)
  * that can be installed to exclude normal IO requests.
  */
 
-static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
+static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
 {
 	conf_t *conf = mddev_to_conf(mddev);
-	mirror_info_t *mirror;
 	r1bio_t *r1_bio;
 	struct bio *bio;
 	sector_t max_sector, nr_sectors;
-	int disk;
+	int disk = -1;
 	int i;
-	int write_targets = 0;
+	int wonly = -1;
+	int write_targets = 0, read_targets = 0;
+	int sync_blocks;
+	int still_degraded = 0;
 
 	if (!conf->r1buf_pool)
+	{
+/*
+		printk("sync start - bitmap %p\n", mddev->bitmap);
+*/
 		if (init_resync(conf))
-			return -ENOMEM;
+			return 0;
+	}
 
 	max_sector = mddev->size << 1;
 	if (sector_nr >= max_sector) {
+		/* If we aborted, we need to abort the
+		 * sync on the 'current' bitmap chunk (there will
+		 * only be one in raid1 resync.
+		 * We can find the current addess in mddev->curr_resync
+		 */
+		if (mddev->curr_resync < max_sector) /* aborted */
+			bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
+						&sync_blocks, 1);
+		else /* completed sync */
+			conf->fullsync = 0;
+
+		bitmap_close_sync(mddev->bitmap);
 		close_sync(conf);
 		return 0;
 	}
 
-	/*
-	 * If there is non-resync activity waiting for us then
-	 * put in a delay to throttle resync.
+	/* before building a request, check if we can skip these blocks..
+	 * This call the bitmap_start_sync doesn't actually record anything
 	 */
-	if (!go_faster && waitqueue_active(&conf->wait_resume))
-		msleep_interruptible(1000);
-	device_barrier(conf, sector_nr + RESYNC_SECTORS);
-
+	if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+	    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+		/* We can skip this block, and probably several more */
+		*skipped = 1;
+		return sync_blocks;
+	}
 	/*
-	 * If reconstructing, and >1 working disc,
-	 * could dedicate one to rebuild and others to
-	 * service read requests ..
+	 * If there is non-resync activity waiting for a turn,
+	 * and resync is going fast enough,
+	 * then let it though before starting on this new sync request.
 	 */
-	disk = conf->last_used;
-	/* make sure disk is operational */
-
-	while (conf->mirrors[disk].rdev == NULL ||
-	       !conf->mirrors[disk].rdev->in_sync) {
-		if (disk <= 0)
-			disk = conf->raid_disks;
-		disk--;
-		if (disk == conf->last_used)
-			break;
-	}
-	conf->last_used = disk;
-	atomic_inc(&conf->mirrors[disk].rdev->nr_pending);
+	if (!go_faster && conf->nr_waiting)
+		msleep_interruptible(1000);
 
+	raise_barrier(conf);
 
-	mirror = conf->mirrors + disk;
+	conf->next_resync = sector_nr;
 
 	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
-
-	spin_lock_irq(&conf->resync_lock);
-	conf->nr_pending++;
-	spin_unlock_irq(&conf->resync_lock);
+	rcu_read_lock();
+	/*
+	 * If we get a correctably read error during resync or recovery,
+	 * we might want to read from a different device.  So we
+	 * flag all drives that could conceivably be read from for READ,
+	 * and any others (which will be non-In_sync devices) for WRITE.
+	 * If a read fails, we try reading from something else for which READ
+	 * is OK.
+	 */
 
 	r1_bio->mddev = mddev;
 	r1_bio->sector = sector_nr;
+	r1_bio->state = 0;
 	set_bit(R1BIO_IsSync, &r1_bio->state);
-	r1_bio->read_disk = disk;
 
 	for (i=0; i < conf->raid_disks; i++) {
+		mdk_rdev_t *rdev;
 		bio = r1_bio->bios[i];
 
 		/* take from bio_init */
@@ -1086,34 +1675,54 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
 		bio->bi_end_io = NULL;
 		bio->bi_private = NULL;
 
-		if (i == disk) {
-			bio->bi_rw = READ;
-			bio->bi_end_io = end_sync_read;
-		} else if (conf->mirrors[i].rdev &&
-			   !conf->mirrors[i].rdev->faulty &&
-			   (!conf->mirrors[i].rdev->in_sync ||
-			    sector_nr + RESYNC_SECTORS > mddev->recovery_cp)) {
+		rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev == NULL ||
+			   test_bit(Faulty, &rdev->flags)) {
+			still_degraded = 1;
+			continue;
+		} else if (!test_bit(In_sync, &rdev->flags)) {
 			bio->bi_rw = WRITE;
 			bio->bi_end_io = end_sync_write;
 			write_targets ++;
-		} else
-			continue;
-		bio->bi_sector = sector_nr + conf->mirrors[i].rdev->data_offset;
-		bio->bi_bdev = conf->mirrors[i].rdev->bdev;
+		} else {
+			/* may need to read from here */
+			bio->bi_rw = READ;
+			bio->bi_end_io = end_sync_read;
+			if (test_bit(WriteMostly, &rdev->flags)) {
+				if (wonly < 0)
+					wonly = i;
+			} else {
+				if (disk < 0)
+					disk = i;
+			}
+			read_targets++;
+		}
+		atomic_inc(&rdev->nr_pending);
+		bio->bi_sector = sector_nr + rdev->data_offset;
+		bio->bi_bdev = rdev->bdev;
 		bio->bi_private = r1_bio;
 	}
-	if (write_targets == 0) {
+	rcu_read_unlock();
+	if (disk < 0)
+		disk = wonly;
+	r1_bio->read_disk = disk;
+
+	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && read_targets > 0)
+		/* extra read targets are also write targets */
+		write_targets += read_targets-1;
+
+	if (write_targets == 0 || read_targets == 0) {
 		/* There is nowhere to write, so all non-sync
 		 * drives must be failed - so we are finished
 		 */
-		int rv = max_sector - sector_nr;
-		md_done_sync(mddev, rv, 1);
+		sector_t rv = max_sector - sector_nr;
+		*skipped = 1;
 		put_buf(r1_bio);
-		rdev_dec_pending(conf->mirrors[disk].rdev, mddev);
 		return rv;
 	}
 
 	nr_sectors = 0;
+	sync_blocks = 0;
 	do {
 		struct page *page;
 		int len = PAGE_SIZE;
@@ -1121,17 +1730,29 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
 			len = (max_sector - sector_nr) << 9;
 		if (len == 0)
 			break;
+		if (sync_blocks == 0) {
+			if (!bitmap_start_sync(mddev->bitmap, sector_nr,
+					       &sync_blocks, still_degraded) &&
+			    !conf->fullsync &&
+			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+				break;
+			BUG_ON(sync_blocks < (PAGE_SIZE>>9));
+			if (len > (sync_blocks<<9))
+				len = sync_blocks<<9;
+		}
+
 		for (i=0 ; i < conf->raid_disks; i++) {
 			bio = r1_bio->bios[i];
 			if (bio->bi_end_io) {
-				page = r1_bio->bios[0]->bi_io_vec[bio->bi_vcnt].bv_page;
+				page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
 				if (bio_add_page(bio, page, len, 0) == 0) {
 					/* stop here */
-					r1_bio->bios[0]->bi_io_vec[bio->bi_vcnt].bv_page = page;
+					bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
 					while (i > 0) {
 						i--;
 						bio = r1_bio->bios[i];
-						if (bio->bi_end_io==NULL) continue;
+						if (bio->bi_end_io==NULL)
+							continue;
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
 						bio->bi_size -= len;
@@ -1143,14 +1764,31 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
 		}
 		nr_sectors += len>>9;
 		sector_nr += len>>9;
+		sync_blocks -= (len>>9);
 	} while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
  bio_full:
-	bio = r1_bio->bios[disk];
 	r1_bio->sectors = nr_sectors;
 
-	md_sync_acct(mirror->rdev->bdev, nr_sectors);
+	/* For a user-requested sync, we read all readable devices and do a
+	 * compare
+	 */
+	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+		atomic_set(&r1_bio->remaining, read_targets);
+		for (i=0; i<conf->raid_disks; i++) {
+			bio = r1_bio->bios[i];
+			if (bio->bi_end_io == end_sync_read) {
+				md_sync_acct(conf->mirrors[i].rdev->bdev, nr_sectors);
+				generic_make_request(bio);
+			}
+		}
+	} else {
+		atomic_set(&r1_bio->remaining, 1);
+		bio = r1_bio->bios[r1_bio->read_disk];
+		md_sync_acct(conf->mirrors[r1_bio->read_disk].rdev->bdev,
+			     nr_sectors);
+		generic_make_request(bio);
 
-	generic_make_request(bio);
+	}
 
 	return nr_sectors;
 }
@@ -1168,23 +1806,29 @@ static int run(mddev_t *mddev)
 		       mdname(mddev), mddev->level);
 		goto out;
 	}
+	if (mddev->reshape_position != MaxSector) {
+		printk("raid1: %s: reshape_position set but not supported\n",
+		       mdname(mddev));
+		goto out;
+	}
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),
 	 * should be freed in stop()]
 	 */
-	conf = kmalloc(sizeof(conf_t), GFP_KERNEL);
+	conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
 	mddev->private = conf;
 	if (!conf)
 		goto out_no_mem;
 
-	memset(conf, 0, sizeof(*conf));
-	conf->mirrors = kmalloc(sizeof(struct mirror_info)*mddev->raid_disks, 
+	conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
 				 GFP_KERNEL);
 	if (!conf->mirrors)
 		goto out_no_mem;
 
-	memset(conf->mirrors, 0, sizeof(struct mirror_info)*mddev->raid_disks);
+	conf->tmppage = alloc_page(GFP_KERNEL);
+	if (!conf->tmppage)
+		goto out_no_mem;
 
 	conf->poolinfo = kmalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
 	if (!conf->poolinfo)
@@ -1217,7 +1861,7 @@ static int run(mddev_t *mddev)
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
-		if (!rdev->faulty && rdev->in_sync)
+		if (!test_bit(Faulty, &rdev->flags) && test_bit(In_sync, &rdev->flags))
 			conf->working_disks++;
 	}
 	conf->raid_disks = mddev->raid_disks;
@@ -1228,8 +1872,10 @@ static int run(mddev_t *mddev)
 		mddev->recovery_cp = MaxSector;
 
 	spin_lock_init(&conf->resync_lock);
-	init_waitqueue_head(&conf->wait_idle);
-	init_waitqueue_head(&conf->wait_resume);
+	init_waitqueue_head(&conf->wait_barrier);
+
+	bio_list_init(&conf->pending_bio_list);
+	bio_list_init(&conf->flushing_bio_list);
 
 	if (!conf->working_disks) {
 		printk(KERN_ERR "raid1: no operational mirrors for %s\n",
@@ -1254,21 +1900,19 @@ static int run(mddev_t *mddev)
 	 */
 	for (j = 0; j < conf->raid_disks &&
 		     (!conf->mirrors[j].rdev ||
-		      !conf->mirrors[j].rdev->in_sync) ; j++)
+		      !test_bit(In_sync, &conf->mirrors[j].rdev->flags)) ; j++)
 		/* nothing */;
 	conf->last_used = j;
 
 
-
-	{
-		mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
-		if (!mddev->thread) {
-			printk(KERN_ERR 
-				"raid1: couldn't allocate thread for %s\n", 
-				mdname(mddev));
-			goto out_free_conf;
-		}
+	mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
+	if (!mddev->thread) {
+		printk(KERN_ERR
+		       "raid1: couldn't allocate thread for %s\n",
+		       mdname(mddev));
+		goto out_free_conf;
 	}
+
 	printk(KERN_INFO 
 		"raid1: raid set %s active with %d out of %d mirrors\n",
 		mdname(mddev), mddev->raid_disks - mddev->degraded, 
@@ -1291,10 +1935,9 @@ out_free_conf:
 	if (conf) {
 		if (conf->r1bio_pool)
 			mempool_destroy(conf->r1bio_pool);
-		if (conf->mirrors)
-			kfree(conf->mirrors);
-		if (conf->poolinfo)
-			kfree(conf->poolinfo);
+		kfree(conf->mirrors);
+		safe_put_page(conf->tmppage);
+		kfree(conf->poolinfo);
 		kfree(conf);
 		mddev->private = NULL;
 	}
@@ -1305,16 +1948,25 @@ 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;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	if (conf->r1bio_pool)
 		mempool_destroy(conf->r1bio_pool);
-	if (conf->mirrors)
-		kfree(conf->mirrors);
-	if (conf->poolinfo)
-		kfree(conf->poolinfo);
+	kfree(conf->mirrors);
+	kfree(conf->poolinfo);
 	kfree(conf);
 	mddev->private = NULL;
 	return 0;
@@ -1337,10 +1989,11 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 	mddev->size = mddev->array_size;
+	mddev->resync_max_sectors = sectors;
 	return 0;
 }
 
-static int raid1_reshape(mddev_t *mddev, int raid_disks)
+static int raid1_reshape(mddev_t *mddev)
 {
 	/* We need to:
 	 * 1/ resize the r1bio_pool
@@ -1349,17 +2002,38 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
 	 * We allocate a new r1bio_pool if we can.
 	 * Then raise a device barrier and wait until all IO stops.
 	 * Then resize conf->mirrors and swap in the new r1bio pool.
+	 *
+	 * At the same time, we "pack" the devices so that all the missing
+	 * devices have the higher raid_disk numbers.
 	 */
 	mempool_t *newpool, *oldpool;
 	struct pool_info *newpoolinfo;
 	mirror_info_t *newmirrors;
 	conf_t *conf = mddev_to_conf(mddev);
+	int cnt, raid_disks;
+
+	int d, d2;
+
+	/* Cannot change chunk_size, layout, or level */
+	if (mddev->chunk_size != mddev->new_chunk ||
+	    mddev->layout != mddev->new_layout ||
+	    mddev->level != mddev->new_level) {
+		mddev->new_chunk = mddev->chunk_size;
+		mddev->new_layout = mddev->layout;
+		mddev->new_level = mddev->level;
+		return -EINVAL;
+	}
 
-	int d;
+	raid_disks = mddev->raid_disks + mddev->delta_disks;
 
-	for (d= raid_disks; d < conf->raid_disks; d++)
-		if (conf->mirrors[d].rdev)
+	if (raid_disks < conf->raid_disks) {
+		cnt=0;
+		for (d= 0; d < conf->raid_disks; d++)
+			if (conf->mirrors[d].rdev)
+				cnt++;
+		if (cnt > raid_disks)
 			return -EBUSY;
+	}
 
 	newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL);
 	if (!newpoolinfo)
@@ -1373,25 +2047,24 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
 		kfree(newpoolinfo);
 		return -ENOMEM;
 	}
-	newmirrors = kmalloc(sizeof(struct mirror_info) * raid_disks, GFP_KERNEL);
+	newmirrors = kzalloc(sizeof(struct mirror_info) * raid_disks, GFP_KERNEL);
 	if (!newmirrors) {
 		kfree(newpoolinfo);
 		mempool_destroy(newpool);
 		return -ENOMEM;
 	}
-	memset(newmirrors, 0, sizeof(struct mirror_info)*raid_disks);
 
-	spin_lock_irq(&conf->resync_lock);
-	conf->barrier++;
-	wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
-			    conf->resync_lock, unplug_slaves(mddev));
-	spin_unlock_irq(&conf->resync_lock);
+	raise_barrier(conf);
 
 	/* ok, everything is stopped */
 	oldpool = conf->r1bio_pool;
 	conf->r1bio_pool = newpool;
-	for (d=0; d < raid_disks && d < conf->raid_disks; d++)
-		newmirrors[d] = conf->mirrors[d];
+
+	for (d=d2=0; d < conf->raid_disks; d++)
+		if (conf->mirrors[d].rdev) {
+			conf->mirrors[d].rdev->raid_disk = d2;
+			newmirrors[d2++].rdev = conf->mirrors[d].rdev;
+		}
 	kfree(conf->mirrors);
 	conf->mirrors = newmirrors;
 	kfree(conf->poolinfo);
@@ -1399,13 +2072,10 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
 
 	mddev->degraded += (raid_disks - conf->raid_disks);
 	conf->raid_disks = mddev->raid_disks = raid_disks;
+	mddev->delta_disks = 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);
-
+	conf->last_used = 0; /* just make sure it is in-range */
+	lower_barrier(conf);
 
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
@@ -1414,10 +2084,25 @@ 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:
+		raise_barrier(conf);
+		break;
+	case 0:
+		lower_barrier(conf);
+		break;
+	}
+}
+
 
-static mdk_personality_t raid1_personality =
+static struct mdk_personality raid1_personality =
 {
 	.name		= "raid1",
+	.level		= 1,
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
@@ -1429,20 +2114,23 @@ static mdk_personality_t raid1_personality =
 	.spare_active	= raid1_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid1_resize,
-	.reshape	= raid1_reshape,
+	.check_reshape	= raid1_reshape,
+	.quiesce	= raid1_quiesce,
 };
 
 static int __init raid_init(void)
 {
-	return register_md_personality(RAID1, &raid1_personality);
+	return register_md_personality(&raid1_personality);
 }
 
 static void raid_exit(void)
 {
-	unregister_md_personality(RAID1);
+	unregister_md_personality(&raid1_personality);
 }
 
 module_init(raid_init);
 module_exit(raid_exit);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("md-personality-3"); /* RAID1 */
+MODULE_ALIAS("md-raid1");
+MODULE_ALIAS("md-level-1");