X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid10.c;h=499620afb44b259184d3a04ba73fb5a1e7d2c724;hb=f94b61c2c9fdcc90773c49df9ccf9ede3ad0d7db;hp=f0141910bb8d8a0166df17903c977c404057514c;hpb=802ba064c49f655d20fed563f2a4924c8256ea10;p=safe%2Fjmp%2Flinux-2.6

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index f014191..499620a 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -18,9 +18,12 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include "dm-bio-list.h"
-#include <linux/raid/raid10.h>
-#include <linux/raid/bitmap.h>
+#include <linux/delay.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid10.h"
+#include "bitmap.h"
 
 /*
  * RAID10 provides a combination of RAID0 and RAID1 functionality.
@@ -76,11 +79,13 @@ static void r10bio_pool_free(void *r10_bio, void *data)
 	kfree(r10_bio);
 }
 
+/* Maximum size of each resync request */
 #define RESYNC_BLOCK_SIZE (64*1024)
-//#define RESYNC_BLOCK_SIZE PAGE_SIZE
-#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
-#define RESYNC_WINDOW (2048*1024)
+/* amount of memory to reserve for resync requests */
+#define RESYNC_WINDOW (1024*1024)
+/* maximum number of concurrent requests, memory permitting */
+#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
 
 /*
  * When performing a resync, we need to read and compare, so
@@ -215,6 +220,9 @@ static void reschedule_retry(r10bio_t *r10_bio)
 	conf->nr_queued ++;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
+	/* wake up frozen array... */
+	wake_up(&conf->wait_barrier);
+
 	md_wakeup_thread(mddev->thread);
 }
 
@@ -227,7 +235,7 @@ static void raid_end_bio_io(r10bio_t *r10_bio)
 {
 	struct bio *bio = r10_bio->master_bio;
 
-	bio_endio(bio, bio->bi_size,
+	bio_endio(bio,
 		test_bit(R10BIO_Uptodate, &r10_bio->state) ? 0 : -EIO);
 	free_r10bio(r10_bio);
 }
@@ -243,15 +251,13 @@ static inline void update_head_pos(int slot, r10bio_t *r10_bio)
 		r10_bio->devs[slot].addr + (r10_bio->sectors);
 }
 
-static int raid10_end_read_request(struct bio *bio, unsigned int bytes_done, int error)
+static void raid10_end_read_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
 	int slot, dev;
 	conf_t *conf = mddev_to_conf(r10_bio->mddev);
 
-	if (bio->bi_size)
-		return 1;
 
 	slot = r10_bio->read_slot;
 	dev = r10_bio->devs[slot].devnum;
@@ -284,19 +290,15 @@ static int raid10_end_read_request(struct bio *bio, unsigned int bytes_done, int
 	}
 
 	rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
-	return 0;
 }
 
-static int raid10_end_write_request(struct bio *bio, unsigned int bytes_done, int error)
+static void raid10_end_write_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
 	int slot, dev;
 	conf_t *conf = mddev_to_conf(r10_bio->mddev);
 
-	if (bio->bi_size)
-		return 1;
-
 	for (slot = 0; slot < conf->copies; slot++)
 		if (r10_bio->devs[slot].bio == bio)
 			break;
@@ -339,7 +341,6 @@ static int raid10_end_write_request(struct bio *bio, unsigned int bytes_done, in
 	}
 
 	rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
-	return 0;
 }
 
 
@@ -429,7 +430,7 @@ static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
 		if (dev < 0)
 			dev += conf->raid_disks;
 	} else {
-		while (sector > conf->stride) {
+		while (sector >= conf->stride) {
 			sector -= conf->stride;
 			if (dev < conf->near_copies)
 				dev += conf->raid_disks - conf->near_copies;
@@ -446,26 +447,27 @@ static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
 /**
  *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
  *      If near_copies == raid_disk, there are no striping issues,
  *      but in that case, the function isn't called at all.
  */
-static int raid10_mergeable_bvec(request_queue_t *q, struct bio *bio,
-				struct bio_vec *bio_vec)
+static int raid10_mergeable_bvec(struct request_queue *q,
+				 struct bvec_merge_data *bvm,
+				 struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
-	if (max <= bio_vec->bv_len && bio_sectors == 0)
-		return bio_vec->bv_len;
+	if (max <= biovec->bv_len && bio_sectors == 0)
+		return biovec->bv_len;
 	else
 		return max;
 }
@@ -544,7 +546,8 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
 	current_distance = abs(r10_bio->devs[slot].addr -
 			       conf->mirrors[disk].head_position);
 
-	/* Find the disk whose head is closest */
+	/* Find the disk whose head is closest,
+	 * or - for far > 1 - find the closest to partition beginning */
 
 	for (nslot = slot; nslot < conf->copies; nslot++) {
 		int ndisk = r10_bio->devs[nslot].devnum;
@@ -564,8 +567,13 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio)
 			slot = nslot;
 			break;
 		}
-		new_distance = abs(r10_bio->devs[nslot].addr -
-				   conf->mirrors[ndisk].head_position);
+
+		/* for far > 1 always use the lowest address */
+		if (conf->far_copies > 1)
+			new_distance = r10_bio->devs[nslot].addr;
+		else
+			new_distance = abs(r10_bio->devs[nslot].addr -
+					   conf->mirrors[ndisk].head_position);
 		if (new_distance < current_distance) {
 			current_distance = new_distance;
 			disk = ndisk;
@@ -595,13 +603,12 @@ 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();
@@ -610,7 +617,7 @@ static void unplug_slaves(mddev_t *mddev)
 	rcu_read_unlock();
 }
 
-static void raid10_unplug(request_queue_t *q)
+static void raid10_unplug(struct request_queue *q)
 {
 	mddev_t *mddev = q->queuedata;
 
@@ -618,36 +625,6 @@ static void raid10_unplug(request_queue_t *q)
 	md_wakeup_thread(mddev->thread);
 }
 
-static int raid10_issue_flush(request_queue_t *q, struct gendisk *disk,
-			     sector_t *error_sector)
-{
-	mddev_t *mddev = q->queuedata;
-	conf_t *conf = mddev_to_conf(mddev);
-	int i, ret = 0;
-
-	rcu_read_lock();
-	for (i=0; i<mddev->raid_disks && ret == 0; 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);
-
-			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();
-			}
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 static int raid10_congested(void *data, int bits)
 {
 	mddev_t *mddev = data;
@@ -658,7 +635,7 @@ static int raid10_congested(void *data, int bits)
 	for (i = 0; i < mddev->raid_disks && ret == 0; i++) {
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			request_queue_t *q = bdev_get_queue(rdev->bdev);
+			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 			ret |= bdi_congested(&q->backing_dev_info, bits);
 		}
@@ -667,7 +644,36 @@ static int raid10_congested(void *data, int bits)
 	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.
@@ -689,7 +695,6 @@ static int raid10_congested(void *data, int bits)
  *    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 raise_barrier(conf_t *conf, int force)
 {
@@ -750,15 +755,23 @@ static void freeze_array(conf_t *conf)
 	/* stop syncio and normal IO and wait for everything to
 	 * go quiet.
 	 * 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,
-			    raid10_unplug(conf->mddev->queue));
+			    ({ flush_pending_writes(conf);
+			       raid10_unplug(conf->mddev->queue); }));
 	spin_unlock_irq(&conf->resync_lock);
 }
 
@@ -772,21 +785,24 @@ static void unfreeze_array(conf_t *conf)
 	spin_unlock_irq(&conf->resync_lock);
 }
 
-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);
 	mirror_info_t *mirror;
 	r10bio_t *r10_bio;
 	struct bio *read_bio;
+	int cpu;
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
+	const int do_sync = bio_sync(bio);
 	struct bio_list bl;
 	unsigned long flags;
+	mdk_rdev_t *blocked_rdev;
 
 	if (unlikely(bio_barrier(bio))) {
-		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
+		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
 
@@ -804,7 +820,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		/* This is a one page bio that upper layers
 		 * refuse to split for us, so we need to split it.
 		 */
-		bp = bio_split(bio, bio_split_pool,
+		bp = bio_split(bio,
 			       chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
 		if (make_request(q, &bp->bio1))
 			generic_make_request(&bp->bio1);
@@ -818,7 +834,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		       " or bigger than %dk %llu %d\n", chunk_sects/2,
 		       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
 
-		bio_io_error(bio, bio->bi_size);
+		bio_io_error(bio);
 		return 0;
 	}
 
@@ -831,8 +847,11 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	 */
 	wait_barrier(conf);
 
-	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();
 
 	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
@@ -863,7 +882,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 			mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid10_end_read_request;
-		read_bio->bi_rw = READ;
+		read_bio->bi_rw = READ | do_sync;
 		read_bio->bi_private = r10_bio;
 
 		generic_make_request(read_bio);
@@ -873,17 +892,23 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	/*
 	 * WRITE:
 	 */
-	/* first select target devices under spinlock and
+	/* first select target devices under rcu_lock and
 	 * inc refcount on their rdev.  Record them by setting
 	 * bios[x] to bio
 	 */
 	raid10_find_phys(conf, r10_bio);
+ retry_write:
+	blocked_rdev = NULL;
 	rcu_read_lock();
 	for (i = 0;  i < conf->copies; i++) {
 		int d = r10_bio->devs[i].devnum;
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[d].rdev);
-		if (rdev &&
-		    !test_bit(Faulty, &rdev->flags)) {
+		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);
 			r10_bio->devs[i].bio = bio;
 		} else {
@@ -893,6 +918,22 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	}
 	rcu_read_unlock();
 
+	if (unlikely(blocked_rdev)) {
+		/* Have to wait for this device to get unblocked, then retry */
+		int j;
+		int d;
+
+		for (j = 0; j < i; j++)
+			if (r10_bio->devs[j].bio) {
+				d = r10_bio->devs[j].devnum;
+				rdev_dec_pending(conf->mirrors[d].rdev, mddev);
+			}
+		allow_barrier(conf);
+		md_wait_for_blocked_rdev(blocked_rdev, mddev);
+		wait_barrier(conf);
+		goto retry_write;
+	}
+
 	atomic_set(&r10_bio->remaining, 0);
 
 	bio_list_init(&bl);
@@ -909,19 +950,32 @@ static int make_request(request_queue_t *q, struct bio * bio)
 			conf->mirrors[d].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE;
+		mbio->bi_rw = WRITE | do_sync;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
 		bio_list_add(&bl, mbio);
 	}
 
+	if (unlikely(!atomic_read(&r10_bio->remaining))) {
+		/* the array is dead */
+		md_write_end(mddev);
+		raid_end_bio_io(r10_bio);
+		return 0;
+	}
+
 	bitmap_startwrite(mddev->bitmap, bio->bi_sector, r10_bio->sectors, 0);
 	spin_lock_irqsave(&conf->device_lock, flags);
 	bio_list_merge(&conf->pending_bio_list, &bl);
 	blk_plug_device(mddev->queue);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
+	/* In case raid10d snuck in to freeze_array */
+	wake_up(&conf->wait_barrier);
+
+	if (do_sync)
+		md_wakeup_thread(mddev->thread);
+
 	return 0;
 }
 
@@ -978,12 +1032,12 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		/*
 		 * if recovery is running, make sure it aborts.
 		 */
-		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	}
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "raid10: Disk failure on %s, disabling device. \n"
-		"	Operation continuing on %d devices\n",
+	printk(KERN_ALERT "raid10: Disk failure on %s, disabling device.\n"
+		"raid10: Operation continuing on %d devices.\n",
 		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
 }
 
@@ -1071,24 +1125,30 @@ static int raid10_spare_active(mddev_t *mddev)
 static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int mirror;
 	mirror_info_t *p;
+	int first = 0;
+	int last = mddev->raid_disks - 1;
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
-		return 0;
+		return -EBUSY;
 	if (!enough(conf))
-		return 0;
+		return -EINVAL;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
 	else
-		mirror = 0;
-	for ( ; mirror < mddev->raid_disks; mirror++)
+		mirror = first;
+	for ( ; mirror <= last ; mirror++)
 		if ( !(p=conf->mirrors+mirror)->rdev) {
 
 			blk_queue_stack_limits(mddev->queue,
@@ -1103,7 +1163,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != mirror)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
@@ -1111,7 +1171,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		}
 
 	print_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid10_remove_disk(mddev_t *mddev, int number)
@@ -1129,6 +1189,14 @@ static int raid10_remove_disk(mddev_t *mddev, int number)
 			err = -EBUSY;
 			goto abort;
 		}
+		/* Only remove faulty devices in recovery
+		 * is not possible.
+		 */
+		if (!test_bit(Faulty, &rdev->flags) &&
+		    enough(conf)) {
+			err = -EBUSY;
+			goto abort;
+		}
 		p->rdev = NULL;
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
@@ -1144,15 +1212,12 @@ 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)
 {
 	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
 	conf_t *conf = mddev_to_conf(r10_bio->mddev);
 	int i,d;
 
-	if (bio->bi_size)
-		return 1;
-
 	for (i=0; i<conf->copies; i++)
 		if (r10_bio->devs[i].bio == bio)
 			break;
@@ -1173,6 +1238,7 @@ static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
 	/* for reconstruct, we always reschedule after a read.
 	 * for resync, only after all reads
 	 */
+	rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
 	if (test_bit(R10BIO_IsRecover, &r10_bio->state) ||
 	    atomic_dec_and_test(&r10_bio->remaining)) {
 		/* we have read all the blocks,
@@ -1180,11 +1246,9 @@ static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
 		 */
 		reschedule_retry(r10_bio);
 	}
-	rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
-	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);
 	r10bio_t * r10_bio = (r10bio_t *)(bio->bi_private);
@@ -1192,9 +1256,6 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 	conf_t *conf = mddev_to_conf(mddev);
 	int i,d;
 
-	if (bio->bi_size)
-		return 1;
-
 	for (i = 0; i < conf->copies; i++)
 		if (r10_bio->devs[i].bio == bio)
 			break;
@@ -1202,13 +1263,16 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 
 	if (!uptodate)
 		md_error(mddev, conf->mirrors[d].rdev);
+
 	update_head_pos(i, r10_bio);
 
+	rdev_dec_pending(conf->mirrors[d].rdev, mddev);
 	while (atomic_dec_and_test(&r10_bio->remaining)) {
 		if (r10_bio->master_bio == NULL) {
 			/* the primary of several recovery bios */
-			md_done_sync(mddev, r10_bio->sectors, 1);
+			sector_t s = r10_bio->sectors;
 			put_buf(r10_bio);
+			md_done_sync(mddev, s, 1);
 			break;
 		} else {
 			r10bio_t *r10_bio2 = (r10bio_t *)r10_bio->master_bio;
@@ -1216,8 +1280,6 @@ static int end_sync_write(struct bio *bio, unsigned int bytes_done, int error)
 			r10_bio = r10_bio2;
 		}
 	}
-	rdev_dec_pending(conf->mirrors[d].rdev, mddev);
-	return 0;
 }
 
 /*
@@ -1291,9 +1353,6 @@ static void sync_request_write(mddev_t *mddev, r10bio_t *r10_bio)
 		tbio->bi_size = r10_bio->sectors << 9;
 		tbio->bi_idx = 0;
 		tbio->bi_phys_segments = 0;
-		tbio->bi_hw_segments = 0;
-		tbio->bi_hw_front_size = 0;
-		tbio->bi_hw_back_size = 0;
 		tbio->bi_flags &= ~(BIO_POOL_MASK - 1);
 		tbio->bi_flags |= 1 << BIO_UPTODATE;
 		tbio->bi_next = NULL;
@@ -1363,7 +1422,7 @@ static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio)
 	if (test_bit(R10BIO_Uptodate, &r10_bio->state))
 		generic_make_request(wbio);
 	else
-		bio_endio(wbio, wbio->bi_size, -EIO);
+		bio_endio(wbio, -EIO);
 }
 
 
@@ -1499,29 +1558,14 @@ static void raid10d(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));
 
-			while (bio) { /* submit pending writes */
-				struct bio *next = bio->bi_next;
-				bio->bi_next = NULL;
-				generic_make_request(bio);
-				bio = next;
-			}
-			unplug = 1;
+		unplug += flush_pending_writes(conf);
 
-			continue;
-		}
-
-		if (list_empty(head))
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (list_empty(head)) {
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 			break;
+		}
 		r10_bio = list_entry(head->prev, r10bio_t, retry_list);
 		list_del(head->prev);
 		conf->nr_queued--;
@@ -1554,7 +1598,6 @@ static void raid10d(mddev_t *mddev)
 			bio = r10_bio->devs[r10_bio->read_slot].bio;
 			r10_bio->devs[r10_bio->read_slot].bio =
 				mddev->ro ? IO_BLOCKED : NULL;
-			bio_put(bio);
 			mirror = read_balance(conf, r10_bio);
 			if (mirror == -1) {
 				printk(KERN_ALERT "raid10: %s: unrecoverable I/O"
@@ -1562,7 +1605,10 @@ static void raid10d(mddev_t *mddev)
 				       bdevname(bio->bi_bdev,b),
 				       (unsigned long long)r10_bio->sector);
 				raid_end_bio_io(r10_bio);
+				bio_put(bio);
 			} else {
+				const int do_sync = bio_sync(r10_bio->master_bio);
+				bio_put(bio);
 				rdev = conf->mirrors[mirror].rdev;
 				if (printk_ratelimit())
 					printk(KERN_ERR "raid10: %s: redirecting sector %llu to"
@@ -1574,7 +1620,7 @@ static void raid10d(mddev_t *mddev)
 				bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
 					+ rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
-				bio->bi_rw = READ;
+				bio->bi_rw = READ | do_sync;
 				bio->bi_private = r10_bio;
 				bio->bi_end_io = raid10_end_read_request;
 				unplug = 1;
@@ -1582,7 +1628,6 @@ static void raid10d(mddev_t *mddev)
 			}
 		}
 	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
 	if (unplug)
 		unplug_slaves(mddev);
 }
@@ -1652,7 +1697,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			return 0;
 
  skipped:
-	max_sector = mddev->size << 1;
+	max_sector = mddev->dev_sectors;
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
 		max_sector = mddev->resync_max_sectors;
 	if (sector_nr >= max_sector) {
@@ -1691,6 +1736,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		return (max_sector - sector_nr) + sectors_skipped;
 	}
 
+	if (max_sector > mddev->resync_max)
+		max_sector = mddev->resync_max; /* Don't do IO beyond here */
+
 	/* make sure whole request will fit in a chunk - if chunks
 	 * are meaningful
 	 */
@@ -1761,17 +1809,17 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 				r10_bio->sector = sect;
 
 				raid10_find_phys(conf, r10_bio);
-				/* Need to check if this section will still be
+
+				/* Need to check if the array will still be
 				 * degraded
 				 */
-				for (j=0; j<conf->copies;j++) {
-					int d = r10_bio->devs[j].devnum;
-					if (conf->mirrors[d].rdev == NULL ||
-					    test_bit(Faulty, &conf->mirrors[d].rdev->flags)) {
+				for (j=0; j<conf->raid_disks; j++)
+					if (conf->mirrors[j].rdev == NULL ||
+					    test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
 						still_degraded = 1;
 						break;
 					}
-				}
+
 				must_sync = bitmap_start_sync(mddev->bitmap, sect,
 							      &sync_blocks, still_degraded);
 
@@ -1796,6 +1844,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 						for (k=0; k<conf->copies; k++)
 							if (r10_bio->devs[k].devnum == i)
 								break;
+						BUG_ON(k == conf->copies);
 						bio = r10_bio->devs[1].bio;
 						bio->bi_next = biolist;
 						biolist = bio;
@@ -1815,8 +1864,11 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 				if (j == conf->copies) {
 					/* Cannot recover, so abort the recovery */
 					put_buf(r10_bio);
+					if (rb2)
+						atomic_dec(&rb2->remaining);
 					r10_bio = rb2;
-					if (!test_and_set_bit(MD_RECOVERY_ERR, &mddev->recovery))
+					if (!test_and_set_bit(MD_RECOVERY_INTR,
+							      &mddev->recovery))
 						printk(KERN_INFO "raid10: %s: insufficient working devices for recovery.\n",
 						       mdname(mddev));
 					break;
@@ -1835,6 +1887,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		/* resync. Schedule a read for every block at this virt offset */
 		int count = 0;
 
+		bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
 		if (!bitmap_start_sync(mddev->bitmap, sector_nr,
 				       &sync_blocks, mddev->degraded) &&
 		    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
@@ -1861,6 +1915,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			int d = r10_bio->devs[i].devnum;
 			bio = r10_bio->devs[i].bio;
 			bio->bi_end_io = NULL;
+			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
 				continue;
@@ -1897,7 +1952,6 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 		bio->bi_vcnt = 0;
 		bio->bi_idx = 0;
 		bio->bi_phys_segments = 0;
-		bio->bi_hw_segments = 0;
 		bio->bi_size = 0;
 	}
 
@@ -1959,13 +2013,32 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	/* There is nowhere to write, so all non-sync
 	 * drives must be failed, so try the next chunk...
 	 */
-	{
-	sector_t sec = max_sector - sector_nr;
-	sectors_skipped += sec;
+	if (sector_nr + max_sync < max_sector)
+		max_sector = sector_nr + max_sync;
+
+	sectors_skipped += (max_sector - sector_nr);
 	chunks_skipped ++;
 	sector_nr = max_sector;
 	goto skipped;
-	}
+}
+
+static sector_t
+raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	sector_t size;
+	conf_t *conf = mddev_to_conf(mddev);
+
+	if (!raid_disks)
+		raid_disks = mddev->raid_disks;
+	if (!sectors)
+		sectors = mddev->dev_sectors;
+
+	size = sectors >> conf->chunk_shift;
+	sector_div(size, conf->far_copies);
+	size = size * raid_disks;
+	sector_div(size, conf->near_copies);
+
+	return size << conf->chunk_shift;
 }
 
 static int run(mddev_t *mddev)
@@ -1974,12 +2047,12 @@ static int run(mddev_t *mddev)
 	int i, disk_idx;
 	mirror_info_t *disk;
 	mdk_rdev_t *rdev;
-	struct list_head *tmp;
 	int nc, fc, fo;
 	sector_t stride, size;
 
-	if (mddev->chunk_size == 0) {
-		printk(KERN_ERR "md/raid10: non-zero chunk size required.\n");
+	if (mddev->chunk_size < PAGE_SIZE) {
+		printk(KERN_ERR "md/raid10: chunk size must be "
+		       "at least PAGE_SIZE(%ld).\n", PAGE_SIZE);
 		return -EINVAL;
 	}
 
@@ -2016,19 +2089,35 @@ static int run(mddev_t *mddev)
 	if (!conf->tmppage)
 		goto out_free_conf;
 
+	conf->mddev = mddev;
+	conf->raid_disks = mddev->raid_disks;
 	conf->near_copies = nc;
 	conf->far_copies = fc;
 	conf->copies = nc*fc;
 	conf->far_offset = fo;
 	conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
 	conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
+	size = mddev->dev_sectors >> conf->chunk_shift;
+	sector_div(size, fc);
+	size = size * conf->raid_disks;
+	sector_div(size, nc);
+	/* 'size' is now the number of chunks in the array */
+	/* calculate "used chunks per device" in 'stride' */
+	stride = size * conf->copies;
+
+	/* We need to round up when dividing by raid_disks to
+	 * get the stride size.
+	 */
+	stride += conf->raid_disks - 1;
+	sector_div(stride, conf->raid_disks);
+	mddev->dev_sectors = stride << conf->chunk_shift;
+
 	if (fo)
-		conf->stride = 1 << conf->chunk_shift;
-	else {
-		stride = mddev->size >> (conf->chunk_shift-1);
+		stride = 1;
+	else
 		sector_div(stride, fc);
-		conf->stride = stride << conf->chunk_shift;
-	}
+	conf->stride = stride << conf->chunk_shift;
+
 	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
 						r10bio_pool_free, conf);
 	if (!conf->r10bio_pool) {
@@ -2037,7 +2126,10 @@ static int run(mddev_t *mddev)
 		goto out_free_conf;
 	}
 
-	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)
@@ -2058,9 +2150,6 @@ static int run(mddev_t *mddev)
 
 		disk->head_position = 0;
 	}
-	conf->raid_disks = mddev->raid_disks;
-	conf->mddev = mddev;
-	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
 
 	spin_lock_init(&conf->resync_lock);
@@ -2082,6 +2171,8 @@ static int run(mddev_t *mddev)
 		    !test_bit(In_sync, &disk->rdev->flags)) {
 			disk->head_position = 0;
 			mddev->degraded++;
+			if (disk->rdev)
+				conf->fullsync = 1;
 		}
 	}
 
@@ -2101,19 +2192,10 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	if (conf->far_offset) {
-		size = mddev->size >> (conf->chunk_shift-1);
-		size *= conf->raid_disks;
-		size <<= conf->chunk_shift;
-		sector_div(size, conf->far_copies);
-	} else
-		size = conf->stride * conf->raid_disks;
-	sector_div(size, conf->near_copies);
-	mddev->array_size = size/2;
-	mddev->resync_max_sectors = size;
+	md_set_array_sectors(mddev, raid10_size(mddev, 0, 0));
+	mddev->resync_max_sectors = raid10_size(mddev, 0, 0);
 
 	mddev->queue->unplug_fn = raid10_unplug;
-	mddev->queue->issue_flush_fn = raid10_issue_flush;
 	mddev->queue->backing_dev_info.congested_fn = raid10_congested;
 	mddev->queue->backing_dev_info.congested_data = mddev;
 
@@ -2147,6 +2229,9 @@ static int stop(mddev_t *mddev)
 {
 	conf_t *conf = mddev_to_conf(mddev);
 
+	raise_barrier(conf, 0);
+	lower_barrier(conf);
+
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
@@ -2194,6 +2279,7 @@ static struct mdk_personality raid10_personality =
 	.spare_active	= raid10_spare_active,
 	.sync_request	= sync_request,
 	.quiesce	= raid10_quiesce,
+	.size		= raid10_size,
 };
 
 static int __init raid_init(void)