X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid1.c;h=7b4f5f7155d8726705c1f42757f68dd1de869624;hb=97a39896816489fe9a67c223e782e8dda06f25c9;hp=b3cfae41f7690d0cc8e09ba25896ebffc3b4e5ef;hpb=5fd6c1dce06ec24ef3de20fe0c7ecf2ba9fe5ef9;p=safe%2Fjmp%2Flinux-2.6

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index b3cfae4..7b4f5f7 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
@@ -32,6 +32,7 @@
  */
 
 #include "dm-bio-list.h"
+#include <linux/delay.h>
 #include <linux/raid/raid1.h>
 #include <linux/raid/bitmap.h>
 
@@ -238,7 +239,7 @@ 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);
@@ -255,37 +256,38 @@ 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:
 	 */
 	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
-		 * 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.
+	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"
 		 */
-		if (uptodate)
-			set_bit(R1BIO_Uptodate, &r1_bio->state);
+		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 {
+	else {
 		/*
 		 * oops, read error:
 		 */
@@ -297,10 +299,9 @@ 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);
@@ -308,8 +309,6 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 	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)
@@ -362,7 +361,7 @@ 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);
 				}
 			}
 		}
@@ -396,8 +395,6 @@ static int raid1_end_write_request(struct bio *bio, unsigned int bytes_done, int
 
 	if (to_put)
 		bio_put(to_put);
-
-	return 0;
 }
 
 
@@ -548,13 +545,12 @@ 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();
@@ -563,7 +559,7 @@ 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;
 
@@ -571,36 +567,63 @@ 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_write_congested)) || 1)
+				ret |= bdi_congested(&q->backing_dev_info, bits);
+			else
+				ret &= bdi_congested(&q->backing_dev_info, bits);
 		}
 	}
 	rcu_read_unlock();
 	return ret;
 }
 
+
+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.
@@ -682,15 +705,23 @@ 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
+	 * 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->barrier+conf->nr_pending == conf->nr_queued+2,
+			    conf->nr_pending == conf->nr_queued+1,
 			    conf->resync_lock,
-			    raid1_unplug(conf->mddev->queue));
+			    ({ flush_pending_writes(conf);
+			       raid1_unplug(conf->mddev->queue); }));
 	spin_unlock_irq(&conf->resync_lock);
 }
 static void unfreeze_array(conf_t *conf)
@@ -735,7 +766,7 @@ do_sync_io:
 	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);
@@ -743,13 +774,14 @@ 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;
+	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
@@ -765,14 +797,19 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
 		if (rw == WRITE)
 			md_write_end(mddev);
-		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
 
 	wait_barrier(conf);
 
-	disk_stat_inc(mddev->gendisk, ios[rw]);
-	disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bio));
+	bitmap = mddev->bitmap;
+
+	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
@@ -809,7 +846,7 @@ 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);
@@ -831,10 +868,17 @@ 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)) {
 				rdev_dec_pending(rdev, mddev);
@@ -847,6 +891,20 @@ 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) {
@@ -880,7 +938,7 @@ 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) {
@@ -915,6 +973,11 @@ 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);
@@ -929,11 +992,14 @@ 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, "]");
 }
 
@@ -950,49 +1016,57 @@ 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)
@@ -1008,20 +1082,21 @@ 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);
 		}
 	}
 
@@ -1033,11 +1108,16 @@ 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;
 
-	for (mirror=0; mirror < mddev->raid_disks; mirror++)
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
+
+	for (mirror = first; mirror <= last; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
@@ -1052,7 +1132,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			/* As all devices are equivalent, we don't need a full recovery
 			 * if this was recently any drive of the array
 			 */
@@ -1063,7 +1143,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid1_remove_disk(mddev_t *mddev, int number)
@@ -1081,6 +1161,14 @@ 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)) {
@@ -1096,14 +1184,11 @@ 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)
 {
 	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
 	int i;
 
-	if (bio->bi_size)
-		return 1;
-
 	for (i=r1_bio->mddev->raid_disks; i--; )
 		if (r1_bio->bios[i] == bio)
 			break;
@@ -1119,10 +1204,9 @@ static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
 
 	if (atomic_dec_and_test(&r1_bio->remaining))
 		reschedule_retry(r1_bio);
-	return 0;
 }
 
-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);
@@ -1131,9 +1215,6 @@ 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;
@@ -1145,7 +1226,7 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 		long sectors_to_go = r1_bio->sectors;
 		/* make sure these bits doesn't get cleared. */
 		do {
-			bitmap_end_sync(mddev->bitmap, r1_bio->sector,
+			bitmap_end_sync(mddev->bitmap, s,
 					&sync_blocks, 1);
 			s += sync_blocks;
 			sectors_to_go -= sync_blocks;
@@ -1159,7 +1240,6 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 		md_done_sync(mddev, r1_bio->sectors, uptodate);
 		put_buf(r1_bio);
 	}
-	return 0;
 }
 
 static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
@@ -1199,37 +1279,58 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 			}
 		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)) {
+			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];
-				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 (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)) {
+				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_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;
+					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);
+					}
+
 				}
 			}
 	}
@@ -1237,7 +1338,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 		/* 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
+		 * 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
@@ -1257,6 +1358,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 				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,
@@ -1359,6 +1464,95 @@ 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;
@@ -1373,29 +1567,14 @@ 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--;
@@ -1415,6 +1594,7 @@ static void raid1d(mddev_t *mddev)
 			 * 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++)
@@ -1435,7 +1615,7 @@ 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);
@@ -1451,77 +1631,14 @@ static void raid1d(mddev_t *mddev)
 			 * 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;
+			if (mddev->ro == 0) {
+				freeze_array(conf);
+				fix_read_error(conf, r1_bio->read_disk,
+					       r1_bio->sector,
+					       r1_bio->sectors);
+				unfreeze_array(conf);
 			}
 
-			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"
@@ -1530,6 +1647,7 @@ static void raid1d(mddev_t *mddev)
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
 			} else {
+				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;
@@ -1545,14 +1663,13 @@ 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);
 }
@@ -1622,6 +1739,13 @@ 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
 	 */
@@ -1639,6 +1763,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	if (!go_faster && conf->nr_waiting)
 		msleep_interruptible(1000);
 
+	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
 	raise_barrier(conf);
 
 	conf->next_resync = sector_nr;
@@ -1666,11 +1791,10 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, 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;
@@ -1721,6 +1845,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		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 {
@@ -1777,19 +1903,17 @@ 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 == end_sync_read) {
-				md_sync_acct(conf->mirrors[i].rdev->bdev, nr_sectors);
+				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(conf->mirrors[r1_bio->read_disk].rdev->bdev,
-			     nr_sectors);
+		md_sync_acct(bio->bi_bdev, nr_sectors);
 		generic_make_request(bio);
 
 	}
-
 	return nr_sectors;
 }
 
@@ -1799,7 +1923,6 @@ static int run(mddev_t *mddev)
 	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",
@@ -1841,7 +1964,10 @@ 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)
@@ -1861,15 +1987,10 @@ 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_barrier);
@@ -1877,11 +1998,6 @@ static int run(mddev_t *mddev)
 	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++) {
@@ -1892,8 +2008,17 @@ static int run(mddev_t *mddev)
 		    !test_bit(In_sync, &disk->rdev->flags)) {
 			disk->head_position = 0;
 			mddev->degraded++;
+			if (disk->rdev)
+				conf->fullsync = 1;
 		}
 	}
+	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
@@ -1921,10 +2046,11 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_size = mddev->size;
+	mddev->array_sectors = mddev->size * 2;
 
 	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;
 
@@ -1982,14 +2108,15 @@ 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);
+	mddev->array_sectors = sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
-	if (mddev->array_size > mddev->size && mddev->recovery_cp == MaxSector) {
+	if (mddev->array_sectors / 2 > mddev->size &&
+	    mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->size << 1;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
-	mddev->size = mddev->array_size;
+	mddev->size = mddev->array_sectors / 2;
 	mddev->resync_max_sectors = sectors;
 	return 0;
 }
@@ -2012,8 +2139,8 @@ static int raid1_reshape(mddev_t *mddev)
 	mirror_info_t *newmirrors;
 	conf_t *conf = mddev_to_conf(mddev);
 	int cnt, raid_disks;
-
-	int d, d2;
+	unsigned long flags;
+	int d, d2, err;
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_size != mddev->new_chunk ||
@@ -2025,6 +2152,10 @@ static int raid1_reshape(mddev_t *mddev)
 		return -EINVAL;
 	}
 
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
+
 	raid_disks = mddev->raid_disks + mddev->delta_disks;
 
 	if (raid_disks < conf->raid_disks) {
@@ -2061,17 +2192,33 @@ static int raid1_reshape(mddev_t *mddev)
 	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;