X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid1.c;h=36df9109cde18bb33aec2992afbfb00b1309b587;hb=395df11f5fa7fe852be28ccec8aaa15634386ad1;hp=2da9d3ba902dd1337ff2d724e46838f9d604f148;hpb=e5de485f00d6e6c15f487869faaf999c708f69b1;p=safe%2Fjmp%2Flinux-2.6

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 2da9d3b..36df910 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -9,7 +9,7 @@
  *
  * Better read-balancing code written by Mika Kuoppala <miku@iki.fi>, 2000
  *
- * Fixes to reconstruction by Jakob Østergaard" <jakob@ostenfeld.dk>
+ * 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
@@ -31,9 +31,12 @@
  * 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>
+#include <linux/delay.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid1.h"
+#include "bitmap.h"
 
 #define DEBUG 0
 #if DEBUG
@@ -47,10 +50,11 @@
  */
 #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(gfp_t gfp_flags, void *data)
 {
@@ -59,10 +63,8 @@ static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
 	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;
@@ -104,15 +106,31 @@ static void * r1buf_pool_alloc(gfp_t 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;
+			bio->bi_vcnt = i+1;
+		}
+	}
+	/* 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;
@@ -120,8 +138,10 @@ static void * r1buf_pool_alloc(gfp_t 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 (j=0 ; j < pi->raid_disks; j++)
+		for (i=0; i < r1_bio->bios[j]->bi_vcnt ; i++)
+			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]);
@@ -132,14 +152,16 @@ 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]);
 
@@ -152,52 +174,40 @@ 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)
@@ -208,8 +218,10 @@ 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);
 }
 
@@ -230,7 +242,7 @@ static void raid_end_bio_io(r1bio_t *r1_bio)
 			(unsigned long long) bio->bi_sector +
 				(bio->bi_size >> 9) - 1);
 
-		bio_endio(bio, bio->bi_size,
+		bio_endio(bio,
 			test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
 	}
 	free_r1bio(r1_bio);
@@ -247,39 +259,35 @@ static inline void update_head_pos(int disk, r1bio_t *r1_bio)
 		r1_bio->sector + (r1_bio->sectors);
 }
 
-static int raid1_end_read_request(struct bio *bio, unsigned int bytes_done, int error)
+static void raid1_end_read_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
 	int mirror;
 	conf_t *conf = mddev_to_conf(r1_bio->mddev);
 
-	if (bio->bi_size)
-		return 1;
-	
 	mirror = r1_bio->read_disk;
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate)
-		md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
-	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);
 
-	/*
-	 * we have only one bio on the read side
-	 */
+	if (uptodate)
+		set_bit(R1BIO_Uptodate, &r1_bio->state);
+	else {
+		/* If all other devices have failed, we want to return
+		 * the error upwards rather than fail the last device.
+		 * Here we redefine "uptodate" to mean "Don't want to retry"
+		 */
+		unsigned long flags;
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (r1_bio->mddev->degraded == conf->raid_disks ||
+		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
+		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+			uptodate = 1;
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+	}
+
 	if (uptodate)
 		raid_end_bio_io(r1_bio);
 	else {
@@ -294,33 +302,32 @@ static int raid1_end_read_request(struct bio *bio, unsigned int bytes_done, int
 	}
 
 	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
-	return 0;
 }
 
-static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int error)
+static void raid1_end_write_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
 	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;
 
 	for (mirror = 0; mirror < conf->raid_disks; mirror++)
 		if (r1_bio->bios[mirror] == bio)
 			break;
 
-	if (error == -ENOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
+	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 {
 		/*
 		 * this branch is our 'one mirror IO has finished' event handler:
 		 */
 		r1_bio->bios[mirror] = NULL;
-		bio_put(bio);
+		to_put = bio;
 		if (!uptodate) {
 			md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
 			/* an I/O failed, we can't clear the bitmap */
@@ -357,10 +364,11 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 					       (unsigned long long) mbio->bi_sector,
 					       (unsigned long long) mbio->bi_sector +
 					       (mbio->bi_size >> 9) - 1);
-					bio_endio(mbio, mbio->bi_size, 0);
+					bio_endio(mbio, 0);
 				}
 			}
 		}
+		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
 	}
 	/*
 	 *
@@ -368,31 +376,28 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 	 * already.
 	 */
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
+		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state))
 			reschedule_retry(r1_bio);
-			/* Don't dec_pending yet, we want to hold
-			 * the reference over the retry
-			 */
-			return 0;
-		}
-		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
-			/* free extra copy of the data pages */
-/* FIXME bio has been freed!!! */
-			int i = bio->bi_vcnt;
-			while (i--)
-				__free_page(bio->bi_io_vec[i].bv_page);
+		else {
+			/* 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);
 		}
-		/* 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);
 	}
 
-	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
-	return 0;
+	if (to_put)
+		bio_put(to_put);
 }
 
 
@@ -432,11 +437,13 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 		new_disk = 0;
 
 		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))
+			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) {
@@ -450,11 +457,13 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 
 	/* make sure the disk is operational */
 	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))
+		if (rdev && test_bit(In_sync, &rdev->flags) &&
+		    r1_bio->bios[new_disk] != IO_BLOCKED)
 			wonly_disk = new_disk;
 
 		if (new_disk <= 0)
@@ -491,7 +500,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 
 		rdev = rcu_dereference(conf->mirrors[disk].rdev);
 
-		if (!rdev ||
+		if (!rdev || r1_bio->bios[disk] == IO_BLOCKED ||
 		    !test_bit(In_sync, &rdev->flags) ||
 		    test_bit(WriteMostly, &rdev->flags))
 			continue;
@@ -519,7 +528,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 			/* cannot risk returning a device that failed
 			 * before we inc'ed nr_pending
 			 */
-			atomic_dec(&rdev->nr_pending);
+			rdev_dec_pending(rdev, conf->mddev);
 			goto retry;
 		}
 		conf->next_seq_sect = this_sector + sectors;
@@ -539,13 +548,12 @@ static void unplug_slaves(mddev_t *mddev)
 	for (i=0; i<mddev->raid_disks; i++) {
 		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);
+			struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
 
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
 
-			if (r_queue->unplug_fn)
-				r_queue->unplug_fn(r_queue);
+			blk_unplug(r_queue);
 
 			rdev_dec_pending(rdev, mddev);
 			rcu_read_lock();
@@ -554,7 +562,7 @@ static void unplug_slaves(mddev_t *mddev)
 	rcu_read_unlock();
 }
 
-static void raid1_unplug(request_queue_t *q)
+static void raid1_unplug(struct request_queue *q)
 {
 	mddev_t *mddev = q->queuedata;
 
@@ -562,72 +570,184 @@ static void raid1_unplug(request_queue_t *q)
 	md_wakeup_thread(mddev->thread);
 }
 
-static int raid1_issue_flush(request_queue_t *q, struct gendisk *disk,
-			     sector_t *error_sector)
+static int raid1_congested(void *data, int bits)
 {
-	mddev_t *mddev = q->queuedata;
+	mddev_t *mddev = data;
 	conf_t *conf = mddev_to_conf(mddev);
 	int i, ret = 0;
 
 	rcu_read_lock();
-	for (i=0; i<mddev->raid_disks && ret == 0; i++) {
+	for (i = 0; i < mddev->raid_disks; i++) {
 		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);
+			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
-			if (!r_queue->issue_flush_fn)
-				ret = -EOPNOTSUPP;
-			else {
-				atomic_inc(&rdev->nr_pending);
-				rcu_read_unlock();
-				ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk,
-							      error_sector);
-				rdev_dec_pending(rdev, mddev);
-				rcu_read_lock();
-			}
+			/* Note the '|| 1' - when read_balance prefers
+			 * non-congested targets, it can be removed
+			 */
+			if ((bits & (1<<BDI_async_congested)) || 1)
+				ret |= bdi_congested(&q->backing_dev_info, bits);
+			else
+				ret &= bdi_congested(&q->backing_dev_info, bits);
 		}
 	}
 	rcu_read_unlock();
 	return ret;
 }
 
-/*
- * Throttle resync depth, so that we can both get proper overlapping of
- * requests, but are still able to handle normal requests quickly.
+
+static int flush_pending_writes(conf_t *conf)
+{
+	/* Any writes that have been queued but are awaiting
+	 * bitmap updates get flushed here.
+	 * We return 1 if any requests were actually submitted.
+	 */
+	int rv = 0;
+
+	spin_lock_irq(&conf->device_lock);
+
+	if (conf->pending_bio_list.head) {
+		struct bio *bio;
+		bio = bio_list_get(&conf->pending_bio_list);
+		blk_remove_plug(conf->mddev->queue);
+		spin_unlock_irq(&conf->device_lock);
+		/* flush any pending bitmap writes to
+		 * disk before proceeding w/ I/O */
+		bitmap_unplug(conf->mddev->bitmap);
+
+		while (bio) { /* submit pending writes */
+			struct bio *next = bio->bi_next;
+			bio->bi_next = NULL;
+			generic_make_request(bio);
+			bio = next;
+		}
+		rv = 1;
+	} else
+		spin_unlock_irq(&conf->device_lock);
+	return rv;
+}
+
+/* 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, raid1_unplug(conf->mddev->queue));
-	
-	if (!conf->barrier++) {
-		wait_event_lock_irq(conf->wait_idle, !conf->nr_pending,
-				    conf->resync_lock, raid1_unplug(conf->mddev->queue));
-		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, raid1_unplug(conf->mddev->queue));
-	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 nr_pending match nr_queued+1
+	 * This is called in the context of one normal IO request
+	 * that has failed. Thus any sync request that might be pending
+	 * will be blocked by nr_pending, and we need to wait for
+	 * pending IO requests to complete or be queued for re-try.
+	 * Thus the number queued (nr_queued) plus this request (1)
+	 * must match the number of pending IOs (nr_pending) before
+	 * we continue.
+	 */
+	spin_lock_irq(&conf->resync_lock);
+	conf->barrier++;
+	conf->nr_waiting++;
+	wait_event_lock_irq(conf->wait_barrier,
+			    conf->nr_pending == conf->nr_queued+1,
+			    conf->resync_lock,
+			    ({ flush_pending_writes(conf);
+			       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 = kmalloc(bio->bi_vcnt * sizeof(struct page *),
+	struct page **pages = kzalloc(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]))
@@ -643,13 +763,13 @@ static struct page **alloc_behind_pages(struct bio *bio)
 do_sync_io:
 	if (pages)
 		for (i = 0; i < bio->bi_vcnt && pages[i]; i++)
-			__free_page(pages[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)
+static int make_request(struct request_queue *q, struct bio * bio)
 {
 	mddev_t *mddev = q->queuedata;
 	conf_t *conf = mddev_to_conf(mddev);
@@ -657,33 +777,42 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	r1bio_t *r1_bio;
 	struct bio *read_bio;
 	int i, targets = 0, disks;
-	mdk_rdev_t *rdev;
-	struct bitmap *bitmap = mddev->bitmap;
+	struct bitmap *bitmap;
 	unsigned long flags;
 	struct bio_list bl;
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
-	int do_barriers;
-
-	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
-		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
-		return 0;
-	}
+	const int do_sync = bio_sync(bio);
+	int cpu, do_barriers;
+	mdk_rdev_t *blocked_rdev;
 
 	/*
 	 * 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.
 	 */
+
 	md_write_start(mddev, bio); /* wait on superblock update early */
 
-	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 (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+		if (rw == WRITE)
+			md_write_end(mddev);
+		bio_endio(bio, -EOPNOTSUPP);
+		return 0;
+	}
+
+	wait_barrier(conf);
+
+	bitmap = mddev->bitmap;
 
-	disk_stat_inc(mddev->gendisk, ios[rw]);
-	disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
+	cpu = part_stat_lock();
+	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
+		      bio_sectors(bio));
+	part_stat_unlock();
 
 	/*
 	 * make_request() can abort the operation when READA is being
@@ -720,7 +849,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid1_end_read_request;
-		read_bio->bi_rw = READ;
+		read_bio->bi_rw = READ | do_sync;
 		read_bio->bi_private = r1_bio;
 
 		generic_make_request(read_bio);
@@ -742,13 +871,20 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	first = 0;
 	}
 #endif
+ retry_write:
+	blocked_rdev = NULL;
 	rcu_read_lock();
 	for (i = 0;  i < disks; i++) {
-		if ((rdev=rcu_dereference(conf->mirrors[i].rdev)) != NULL &&
-		    !test_bit(Faulty, &rdev->flags)) {
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+			atomic_inc(&rdev->nr_pending);
+			blocked_rdev = rdev;
+			break;
+		}
+		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			atomic_inc(&rdev->nr_pending);
 			if (test_bit(Faulty, &rdev->flags)) {
-				atomic_dec(&rdev->nr_pending);
+				rdev_dec_pending(rdev, mddev);
 				r1_bio->bios[i] = NULL;
 			} else
 				r1_bio->bios[i] = bio;
@@ -758,6 +894,20 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	}
 	rcu_read_unlock();
 
+	if (unlikely(blocked_rdev)) {
+		/* Wait for this device to become unblocked */
+		int j;
+
+		for (j = 0; j < i; j++)
+			if (r1_bio->bios[j])
+				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
+
+		allow_barrier(conf);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_write;
+	}
+
 	BUG_ON(targets == 0); /* we never fail the last device */
 
 	if (targets < conf->raid_disks) {
@@ -775,7 +925,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	atomic_set(&r1_bio->remaining, 0);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
-	do_barriers = bio->bi_rw & BIO_RW_BARRIER;
+	do_barriers = bio_barrier(bio);
 	if (do_barriers)
 		set_bit(R1BIO_Barrier, &r1_bio->state);
 
@@ -791,7 +941,7 @@ 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 | do_barriers;
+		mbio->bi_rw = WRITE | do_barriers | do_sync;
 		mbio->bi_private = r1_bio;
 
 		if (behind_pages) {
@@ -826,6 +976,11 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	blk_plug_device(mddev->queue);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
+	/* In case raid1d snuck into freeze_array */
+	wake_up(&conf->wait_barrier);
+
+	if (do_sync)
+		md_wakeup_thread(mddev->thread);
 #if 0
 	while ((bio = bio_list_pop(&bl)) != NULL)
 		generic_make_request(bio);
@@ -840,11 +995,14 @@ static void status(struct seq_file *seq, mddev_t *mddev)
 	int i;
 
 	seq_printf(seq, " [%d/%d] [", conf->raid_disks,
-						conf->working_disks);
-	for (i = 0; i < conf->raid_disks; i++)
+		   conf->raid_disks - mddev->degraded);
+	rcu_read_lock();
+	for (i = 0; i < conf->raid_disks; i++) {
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		seq_printf(seq, "%s",
-			      conf->mirrors[i].rdev &&
-			      test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
+			   rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
+	}
+	rcu_read_unlock();
 	seq_printf(seq, "]");
 }
 
@@ -861,60 +1019,63 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	 * else mark the drive as failed
 	 */
 	if (test_bit(In_sync, &rdev->flags)
-	    && conf->working_disks == 1)
+	    && (conf->raid_disks - mddev->degraded) == 1) {
 		/*
 		 * Don't fail the drive, act as though we were just a
-		 * normal single drive
+		 * normal single drive.
+		 * However don't try a recovery from this drive as
+		 * it is very likely to fail.
 		 */
+		mddev->recovery_disabled = 1;
 		return;
-	if (test_bit(In_sync, &rdev->flags)) {
+	}
+	if (test_and_clear_bit(In_sync, &rdev->flags)) {
+		unsigned long flags;
+		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
-		conf->working_disks--;
+		set_bit(Faulty, &rdev->flags);
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		/*
 		 * if recovery is running, make sure it aborts.
 		 */
-		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
-	}
-	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",
-		bdevname(rdev->bdev,b), conf->working_disks);
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+	} else
+		set_bit(Faulty, &rdev->flags);
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device.\n"
+		"raid1: Operation continuing on %d devices.\n",
+		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(conf_t *conf)
 {
 	int i;
-	mirror_info_t *tmp;
 
 	printk("RAID1 conf printout:\n");
 	if (!conf) {
 		printk("(!conf)\n");
 		return;
 	}
-	printk(" --- wd:%d rd:%d\n", conf->working_disks,
+	printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 		conf->raid_disks);
 
+	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
 		char b[BDEVNAME_SIZE];
-		tmp = conf->mirrors + i;
-		if (tmp->rdev)
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev)
 			printk(" disk %d, wo:%d, o:%d, dev:%s\n",
-				i, !test_bit(In_sync, &tmp->rdev->flags), !test_bit(Faulty, &tmp->rdev->flags),
-				bdevname(tmp->rdev->bdev,b));
+			       i, !test_bit(In_sync, &rdev->flags),
+			       !test_bit(Faulty, &rdev->flags),
+			       bdevname(rdev->bdev,b));
 	}
+	rcu_read_unlock();
 }
 
 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, 	raid1_unplug(conf->mddev->queue));
-	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;
@@ -924,20 +1085,21 @@ static int raid1_spare_active(mddev_t *mddev)
 {
 	int i;
 	conf_t *conf = mddev->private;
-	mirror_info_t *tmp;
 
 	/*
 	 * Find all failed disks within the RAID1 configuration 
-	 * and mark them readable
+	 * and mark them readable.
+	 * Called under mddev lock, so rcu protection not needed.
 	 */
 	for (i = 0; i < conf->raid_disks; i++) {
-		tmp = conf->mirrors + i;
-		if (tmp->rdev 
-		    && !test_bit(Faulty, &tmp->rdev->flags)
-		    && !test_bit(In_sync, &tmp->rdev->flags)) {
-			conf->working_disks++;
+		mdk_rdev_t *rdev = conf->mirrors[i].rdev;
+		if (rdev
+		    && !test_bit(Faulty, &rdev->flags)
+		    && !test_and_set_bit(In_sync, &rdev->flags)) {
+			unsigned long flags;
+			spin_lock_irqsave(&conf->device_lock, flags);
 			mddev->degraded--;
-			set_bit(In_sync, &tmp->rdev->flags);
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 		}
 	}
 
@@ -949,14 +1111,16 @@ static int raid1_spare_active(mddev_t *mddev)
 static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror = 0;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
-	if (rdev->saved_raid_disk >= 0 &&
-	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
-		mirror = rdev->saved_raid_disk;
-	for (mirror=0; mirror < mddev->raid_disks; mirror++)
+	for (mirror = first; mirror <= last; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
@@ -971,15 +1135,18 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
-			if (rdev->saved_raid_disk != mirror)
+			err = 0;
+			/* 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;
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid1_remove_disk(mddev_t *mddev, int number)
@@ -997,6 +1164,14 @@ static int raid1_remove_disk(mddev_t *mddev, int number)
 			err = -EBUSY;
 			goto abort;
 		}
+		/* Only remove non-faulty devices is recovery
+		 * is not possible.
+		 */
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    mddev->degraded < conf->raid_disks) {
+			err = -EBUSY;
+			goto abort;
+		}
 		p->rdev = NULL;
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
@@ -1012,34 +1187,29 @@ abort:
 }
 
 
-static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
+static void end_sync_read(struct bio *bio, 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);
-
-	if (bio->bi_size)
-		return 1;
+	int i;
 
-	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);
-	return 0;
+
+	if (atomic_dec_and_test(&r1_bio->remaining))
+		reschedule_retry(r1_bio);
 }
 
-static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
+static void end_sync_write(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
@@ -1048,25 +1218,32 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 	int i;
 	int mirror=0;
 
-	if (bio->bi_size)
-		return 1;
-
 	for (i = 0; i < conf->raid_disks; i++)
 		if (r1_bio->bios[i] == bio) {
 			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, s,
+					&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);
+		sector_t s = r1_bio->sectors;
 		put_buf(r1_bio);
+		md_done_sync(mddev, s, uptodate);
 	}
-	rdev_dec_pending(conf->mirrors[mirror].rdev, mddev);
-	return 0;
 }
 
 static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
@@ -1078,34 +1255,198 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 
 	bio = r1_bio->bios[r1_bio->read_disk];
 
-/*
-	if (r1_bio->sector == 0) printk("First sync write startss\n");
-*/
-	/*
-	 * 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) {
+				int j;
+				int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
+				struct bio *pbio = r1_bio->bios[primary];
+				struct bio *sbio = r1_bio->bios[i];
+
+				if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+					for (j = vcnt; j-- ; ) {
+						struct page *p, *s;
+						p = pbio->bi_io_vec[j].bv_page;
+						s = sbio->bi_io_vec[j].bv_page;
+						if (memcmp(page_address(p),
+							   page_address(s),
+							   PAGE_SIZE))
+							break;
+					}
+				} else
+					j = 0;
+				if (j >= 0)
+					mddev->resync_mismatches += r1_bio->sectors;
+				if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
+					      && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+					sbio->bi_end_io = NULL;
+					rdev_dec_pending(conf->mirrors[i].rdev, mddev);
+				} else {
+					/* fixup the bio for reuse */
+					int size;
+					sbio->bi_vcnt = vcnt;
+					sbio->bi_size = r1_bio->sectors << 9;
+					sbio->bi_idx = 0;
+					sbio->bi_phys_segments = 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;
+					size = sbio->bi_size;
+					for (j = 0; j < vcnt ; j++) {
+						struct bio_vec *bi;
+						bi = &sbio->bi_io_vec[j];
+						bi->bv_offset = 0;
+						if (size > PAGE_SIZE)
+							bi->bv_len = PAGE_SIZE;
+						else
+							bi->bv_len = size;
+						size -= PAGE_SIZE;
+						memcpy(page_address(bi->bv_page),
+						       page_address(pbio->bi_io_vec[j].bv_page),
+						       PAGE_SIZE);
+					}
+
+				}
+			}
+	}
 	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 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) {
+					/* No rcu protection needed here devices
+					 * can only be removed when no resync is
+					 * active, and resync is currently active
+					 */
+					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);
 
@@ -1127,6 +1468,95 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
  *	3.	Performs writes following reads for array syncronising.
  */
 
+static void fix_read_error(conf_t *conf, int read_disk,
+			   sector_t sect, int sectors)
+{
+	mddev_t *mddev = conf->mddev;
+	while(sectors) {
+		int s = sectors;
+		int d = read_disk;
+		int success = 0;
+		int start;
+		mdk_rdev_t *rdev;
+
+		if (s > (PAGE_SIZE>>9))
+			s = PAGE_SIZE >> 9;
+
+		do {
+			/* Note: no rcu protection needed here
+			 * as this is synchronous in the raid1d thread
+			 * which is the thread that might remove
+			 * a device.  If raid1d ever becomes multi-threaded....
+			 */
+			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 != read_disk);
+
+		if (!success) {
+			/* Cannot read from anywhere -- bye bye array */
+			md_error(mddev, conf->mirrors[read_disk].rdev);
+			break;
+		}
+		/* write it back and re-read */
+		start = d;
+		while (d != 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, WRITE)
+				    == 0)
+					/* Well, this device is dead */
+					md_error(mddev, rdev);
+			}
+		}
+		d = start;
+		while (d != read_disk) {
+			char b[BDEVNAME_SIZE];
+			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 {
+					atomic_add(s, &rdev->corrected_errors);
+					printk(KERN_INFO
+					       "raid1:%s: read error corrected "
+					       "(%d sectors at %llu on %s)\n",
+					       mdname(mddev), s,
+					       (unsigned long long)(sect +
+					           rdev->data_offset),
+					       bdevname(rdev->bdev, b));
+				}
+			}
+		}
+		sectors -= s;
+		sect += s;
+	}
+}
+
 static void raid1d(mddev_t *mddev)
 {
 	r1bio_t *r1_bio;
@@ -1141,31 +1571,17 @@ static void raid1d(mddev_t *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));
+		unplug += flush_pending_writes(conf);
 
-			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))
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (list_empty(head)) {
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 			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;
@@ -1175,15 +1591,20 @@ static void raid1d(mddev_t *mddev)
 			unplug = 1;
 		} else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
 			/* some requests in the r1bio were BIO_RW_BARRIER
-			 * requests which failed with -ENOTSUPP.  Hohumm..
+			 * 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;
+			const int do_sync = bio_sync(r1_bio->master_bio);
 			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;
@@ -1198,22 +1619,42 @@ static void raid1d(mddev_t *mddev)
 						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_rw = WRITE | do_sync;
 					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
+			 */
+			if (mddev->ro == 0) {
+				freeze_array(conf);
+				fix_read_error(conf, r1_bio->read_disk,
+					       r1_bio->sector,
+					       r1_bio->sectors);
+				unfreeze_array(conf);
+			}
+
 			bio = r1_bio->bios[r1_bio->read_disk];
-			if ((disk=read_balance(conf, r1_bio)) == -1) {
+			if ((disk=read_balance(conf, r1_bio)) == -1 ||
+			    disk == r1_bio->read_disk) {
 				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);
 				raid_end_bio_io(r1_bio);
 			} else {
-				r1_bio->bios[r1_bio->read_disk] = NULL;
+				const int do_sync = bio_sync(r1_bio->master_bio);
+				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);
@@ -1227,14 +1668,13 @@ static void raid1d(mddev_t *mddev)
 				bio->bi_sector = r1_bio->sector + rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
 				bio->bi_end_io = raid1_end_read_request;
-				bio->bi_rw = READ;
+				bio->bi_rw = READ | do_sync;
 				bio->bi_private = r1_bio;
 				unplug = 1;
 				generic_make_request(bio);
 			}
 		}
 	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
 	if (unplug)
 		unplug_slaves(mddev);
 }
@@ -1245,8 +1685,7 @@ 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)
@@ -1268,14 +1707,13 @@ static int init_resync(conf_t *conf)
 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 wonly;
-	int write_targets = 0;
+	int wonly = -1;
+	int write_targets = 0, read_targets = 0;
 	int sync_blocks;
 	int still_degraded = 0;
 
@@ -1288,7 +1726,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			return 0;
 	}
 
-	max_sector = mddev->size << 1;
+	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
 		/* If we aborted, we need to abort the
 		 * sync on the 'current' bitmap chunk (there will
@@ -1306,6 +1744,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		return 0;
 	}
 
+	if (mddev->bitmap == NULL &&
+	    mddev->recovery_cp == MaxSector &&
+	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+	    conf->fullsync == 0) {
+		*skipped = 1;
+		return max_sector - sector_nr;
+	}
 	/* before building a request, check if we can skip these blocks..
 	 * This call the bitmap_start_sync doesn't actually record anything
 	 */
@@ -1316,101 +1761,97 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		return sync_blocks;
 	}
 	/*
-	 * If there is non-resync activity waiting for us then
-	 * put in a delay to throttle resync.
+	 * 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.
 	 */
-	if (!go_faster && waitqueue_active(&conf->wait_resume))
+	if (!go_faster && conf->nr_waiting)
 		msleep_interruptible(1000);
-	device_barrier(conf, sector_nr + RESYNC_SECTORS);
-
-	/*
-	 * If reconstructing, and >1 working disc,
-	 * could dedicate one to rebuild and others to
-	 * service read requests ..
-	 */
-	disk = conf->last_used;
-	/* make sure disk is operational */
-	wonly = disk;
-	while (conf->mirrors[disk].rdev == NULL ||
-	       !test_bit(In_sync, &conf->mirrors[disk].rdev->flags) ||
-	       test_bit(WriteMostly, &conf->mirrors[disk].rdev->flags)
-		) {
-		if (conf->mirrors[disk].rdev  &&
-		    test_bit(In_sync, &conf->mirrors[disk].rdev->flags))
-			wonly = disk;
-		if (disk <= 0)
-			disk = conf->raid_disks;
-		disk--;
-		if (disk == conf->last_used) {
-			disk = wonly;
-			break;
-		}
-	}
-	conf->last_used = disk;
-	atomic_inc(&conf->mirrors[disk].rdev->nr_pending);
 
+	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+	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 */
 		bio->bi_next = NULL;
 		bio->bi_flags |= 1 << BIO_UPTODATE;
-		bio->bi_rw = 0;
+		bio->bi_rw = READ;
 		bio->bi_vcnt = 0;
 		bio->bi_idx = 0;
 		bio->bi_phys_segments = 0;
-		bio->bi_hw_segments = 0;
 		bio->bi_size = 0;
 		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 == NULL ||
-			   test_bit(Faulty, &conf->mirrors[i].rdev->flags)) {
+		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, &conf->mirrors[i].rdev->flags) ||
-			   sector_nr + RESYNC_SECTORS > mddev->recovery_cp   ||
-			   test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+		} else if (!test_bit(In_sync, &rdev->flags)) {
 			bio->bi_rw = WRITE;
 			bio->bi_end_io = end_sync_write;
 			write_targets ++;
-		} else
-			/* no need to read or write here */
-			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;
 	}
+	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) {
+	if (write_targets == 0 || read_targets == 0) {
 		/* There is nowhere to write, so all non-sync
 		 * drives must be failed - so we are finished
 		 */
 		sector_t rv = max_sector - sector_nr;
 		*skipped = 1;
 		put_buf(r1_bio);
-		rdev_dec_pending(conf->mirrors[disk].rdev, mddev);
 		return rv;
 	}
 
+	if (max_sector > mddev->resync_max)
+		max_sector = mddev->resync_max; /* Don't do IO beyond here */
 	nr_sectors = 0;
 	sync_blocks = 0;
 	do {
@@ -1426,8 +1867,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			    !conf->fullsync &&
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
-			if (sync_blocks < (PAGE_SIZE>>9))
-				BUG();
+			BUG_ON(sync_blocks < (PAGE_SIZE>>9));
 			if (len > (sync_blocks<<9))
 				len = sync_blocks<<9;
 		}
@@ -1435,10 +1875,10 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		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];
@@ -1458,46 +1898,73 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		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);
-
-	generic_make_request(bio);
+	/* 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(bio->bi_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(bio->bi_bdev, nr_sectors);
+		generic_make_request(bio);
 
+	}
 	return nr_sectors;
 }
 
+static sector_t raid1_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	if (sectors)
+		return sectors;
+
+	return mddev->dev_sectors;
+}
+
 static int run(mddev_t *mddev)
 {
 	conf_t *conf;
 	int i, j, disk_idx;
 	mirror_info_t *disk;
 	mdk_rdev_t *rdev;
-	struct list_head *tmp;
 
 	if (mddev->level != 1) {
 		printk("raid1: %s: raid level not set to mirroring (%d)\n",
 		       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)
@@ -1510,7 +1977,10 @@ static int run(mddev_t *mddev)
 	if (!conf->r1bio_pool)
 		goto out_no_mem;
 
-	ITERATE_RDEV(mddev, rdev, tmp) {
+	spin_lock_init(&conf->device_lock);
+	mddev->queue->queue_lock = &conf->device_lock;
+
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		disk_idx = rdev->raid_disk;
 		if (disk_idx >= mddev->raid_disks
 		    || disk_idx < 0)
@@ -1530,39 +2000,38 @@ static int run(mddev_t *mddev)
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
-		if (!test_bit(Faulty, &rdev->flags) && test_bit(In_sync, &rdev->flags))
-			conf->working_disks++;
 	}
 	conf->raid_disks = mddev->raid_disks;
 	conf->mddev = mddev;
-	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
-	if (conf->working_disks == 1)
-		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",
-			mdname(mddev));
-		goto out_free_conf;
-	}
 
 	mddev->degraded = 0;
 	for (i = 0; i < conf->raid_disks; i++) {
 
 		disk = conf->mirrors + i;
 
-		if (!disk->rdev) {
+		if (!disk->rdev ||
+		    !test_bit(In_sync, &disk->rdev->flags)) {
 			disk->head_position = 0;
 			mddev->degraded++;
+			if (disk->rdev)
+				conf->fullsync = 1;
 		}
 	}
+	if (mddev->degraded == conf->raid_disks) {
+		printk(KERN_ERR "raid1: no operational mirrors for %s\n",
+			mdname(mddev));
+		goto out_free_conf;
+	}
+	if (conf->raid_disks - mddev->degraded == 1)
+		mddev->recovery_cp = MaxSector;
 
 	/*
 	 * find the first working one and use it as a starting point
@@ -1582,7 +2051,6 @@ static int run(mddev_t *mddev)
 		       mdname(mddev));
 		goto out_free_conf;
 	}
-	if (mddev->bitmap) mddev->thread->timeout = mddev->bitmap->daemon_sleep * HZ;
 
 	printk(KERN_INFO 
 		"raid1: raid set %s active with %d out of %d mirrors\n",
@@ -1591,10 +2059,11 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	mddev->queue->unplug_fn = raid1_unplug;
-	mddev->queue->issue_flush_fn = raid1_issue_flush;
+	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
+	mddev->queue->backing_dev_info.congested_data = mddev;
 
 	return 0;
 
@@ -1607,6 +2076,7 @@ out_free_conf:
 		if (conf->r1bio_pool)
 			mempool_destroy(conf->r1bio_pool);
 		kfree(conf->mirrors);
+		safe_put_page(conf->tmppage);
 		kfree(conf->poolinfo);
 		kfree(conf);
 		mddev->private = NULL;
@@ -1630,6 +2100,9 @@ static int stop(mddev_t *mddev)
 		/* need to kick something here to make sure I/O goes? */
 	}
 
+	raise_barrier(conf);
+	lower_barrier(conf);
+
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
@@ -1651,19 +2124,22 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
 	 * any io in the removed space completes, but it hardly seems
 	 * worth it.
 	 */
-	mddev->array_size = sectors>>1;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	md_set_array_sectors(mddev, raid1_size(mddev, sectors, 0));
+	if (mddev->array_sectors > raid1_size(mddev, sectors, 0))
+		return -EINVAL;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
-	if (mddev->array_size > mddev->size && mddev->recovery_cp == MaxSector) {
-		mddev->recovery_cp = mddev->size << 1;
+	if (sectors > mddev->dev_sectors &&
+	    mddev->recovery_cp == MaxSector) {
+		mddev->recovery_cp = mddev->dev_sectors;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
-	mddev->size = mddev->array_size;
+	mddev->dev_sectors = sectors;
 	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
@@ -1680,9 +2156,25 @@ static int raid1_reshape(mddev_t *mddev, int raid_disks)
 	struct pool_info *newpoolinfo;
 	mirror_info_t *newmirrors;
 	conf_t *conf = mddev_to_conf(mddev);
-	int cnt;
+	int cnt, raid_disks;
+	unsigned long flags;
+	int d, d2, err;
+
+	/* 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;
+	}
+
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
 
-	int d, d2;
+	raid_disks = mddev->raid_disks + mddev->delta_disks;
 
 	if (raid_disks < conf->raid_disks) {
 		cnt=0;
@@ -1705,44 +2197,51 @@ 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, raid1_unplug(mddev->queue));
-	spin_unlock_irq(&conf->resync_lock);
+	raise_barrier(conf);
 
 	/* ok, everything is stopped */
 	oldpool = conf->r1bio_pool;
 	conf->r1bio_pool = newpool;
 
-	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;
+	for (d = d2 = 0; d < conf->raid_disks; d++) {
+		mdk_rdev_t *rdev = conf->mirrors[d].rdev;
+		if (rdev && rdev->raid_disk != d2) {
+			char nm[20];
+			sprintf(nm, "rd%d", rdev->raid_disk);
+			sysfs_remove_link(&mddev->kobj, nm);
+			rdev->raid_disk = d2;
+			sprintf(nm, "rd%d", rdev->raid_disk);
+			sysfs_remove_link(&mddev->kobj, nm);
+			if (sysfs_create_link(&mddev->kobj,
+					      &rdev->kobj, nm))
+				printk(KERN_WARNING
+				       "md/raid1: cannot register "
+				       "%s for %s\n",
+				       nm, mdname(mddev));
 		}
+		if (rdev)
+			newmirrors[d2++].rdev = rdev;
+	}
 	kfree(conf->mirrors);
 	conf->mirrors = newmirrors;
 	kfree(conf->poolinfo);
 	conf->poolinfo = newpoolinfo;
 
+	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded += (raid_disks - conf->raid_disks);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	conf->raid_disks = mddev->raid_disks = raid_disks;
+	mddev->delta_disks = 0;
 
 	conf->last_used = 0; /* just make sure it is in-range */
-	spin_lock_irq(&conf->resync_lock);
-	conf->barrier--;
-	spin_unlock_irq(&conf->resync_lock);
-	wake_up(&conf->wait_resume);
-	wake_up(&conf->wait_idle);
-
+	lower_barrier(conf);
 
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
@@ -1757,33 +2256,19 @@ static void raid1_quiesce(mddev_t *mddev, int state)
 
 	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);
+		raise_barrier(conf);
 		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);
+		lower_barrier(conf);
 		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 =
+static struct mdk_personality raid1_personality =
 {
 	.name		= "raid1",
+	.level		= 1,
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
@@ -1795,21 +2280,24 @@ static mdk_personality_t raid1_personality =
 	.spare_active	= raid1_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid1_resize,
-	.reshape	= raid1_reshape,
+	.size		= raid1_size,
+	.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");