X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid5.c;h=d29215d966dadc23f4c1a6844a725dc89d6a8304;hb=9a1607071c293e48b08bd703733480b1d55c7b93;hp=0a5cf217121411f8654d405c2ec7bf9ca43c010b;hpb=f9dd2134374c8de6b911e2b8652c6c9622eaa658;p=safe%2Fjmp%2Flinux-2.6

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0a5cf21..d29215d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -156,13 +156,16 @@ static inline int raid6_next_disk(int disk, int raid_disks)
 static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
 			     int *count, int syndrome_disks)
 {
-	int slot;
+	int slot = *count;
 
+	if (sh->ddf_layout)
+		(*count)++;
 	if (idx == sh->pd_idx)
 		return syndrome_disks;
 	if (idx == sh->qd_idx)
 		return syndrome_disks + 1;
-	slot = (*count)++;
+	if (!sh->ddf_layout)
+		(*count)++;
 	return slot;
 }
 
@@ -502,13 +505,17 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 	int i;
 	int page_offset;
 	struct async_submit_ctl submit;
+	enum async_tx_flags flags = 0;
 
 	if (bio->bi_sector >= sector)
 		page_offset = (signed)(bio->bi_sector - sector) * 512;
 	else
 		page_offset = (signed)(sector - bio->bi_sector) * -512;
 
-	init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
+	if (frombio)
+		flags |= ASYNC_TX_FENCE;
+	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
+
 	bio_for_each_segment(bvl, bio, i) {
 		int len = bio_iovec_idx(bio, i)->bv_len;
 		int clen;
@@ -685,7 +692,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 
 	atomic_inc(&sh->count);
 
-	init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL,
+	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
 			  ops_complete_compute, sh, to_addr_conv(sh, percpu));
 	if (unlikely(count == 1))
 		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
@@ -713,7 +720,7 @@ static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh)
 	int i;
 
 	for (i = 0; i < disks; i++)
-		srcs[i] = (void *)raid6_empty_zero_page;
+		srcs[i] = NULL;
 
 	count = 0;
 	i = d0_idx;
@@ -723,9 +730,8 @@ static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh)
 		srcs[slot] = sh->dev[i].page;
 		i = raid6_next_disk(i, disks);
 	} while (i != d0_idx);
-	BUG_ON(count != syndrome_disks);
 
-	return count;
+	return syndrome_disks;
 }
 
 static struct dma_async_tx_descriptor *
@@ -763,7 +769,8 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 		count = set_syndrome_sources(blocks, sh);
 		blocks[count] = NULL; /* regenerating p is not necessary */
 		BUG_ON(blocks[count+1] != dest); /* q should already be set */
-		init_async_submit(&submit, 0, NULL, ops_complete_compute, sh,
+		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+				  ops_complete_compute, sh,
 				  to_addr_conv(sh, percpu));
 		tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
 	} else {
@@ -775,8 +782,8 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 			blocks[count++] = sh->dev[i].page;
 		}
 
-		init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL,
-				  ops_complete_compute, sh,
+		init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
+				  NULL, ops_complete_compute, sh,
 				  to_addr_conv(sh, percpu));
 		tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit);
 	}
@@ -805,11 +812,11 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt2->flags));
 
-	/* we need to open-code set_syndrome_sources to handle to the
+	/* we need to open-code set_syndrome_sources to handle the
 	 * slot number conversion for 'faila' and 'failb'
 	 */
 	for (i = 0; i < disks ; i++)
-		blocks[i] = (void *)raid6_empty_zero_page;
+		blocks[i] = NULL;
 	count = 0;
 	i = d0_idx;
 	do {
@@ -823,7 +830,6 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			failb = slot;
 		i = raid6_next_disk(i, disks);
 	} while (i != d0_idx);
-	BUG_ON(count != syndrome_disks);
 
 	BUG_ON(faila == failb);
 	if (failb < faila)
@@ -837,9 +843,10 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 		/* Q disk is one of the missing disks */
 		if (faila == syndrome_disks) {
 			/* Missing P+Q, just recompute */
-			init_async_submit(&submit, 0, NULL, ops_complete_compute,
-					  sh, to_addr_conv(sh, percpu));
-			return async_gen_syndrome(blocks, 0, count+2,
+			init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+					  ops_complete_compute, sh,
+					  to_addr_conv(sh, percpu));
+			return async_gen_syndrome(blocks, 0, syndrome_disks+2,
 						  STRIPE_SIZE, &submit);
 		} else {
 			struct page *dest;
@@ -859,29 +866,35 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 				blocks[count++] = sh->dev[i].page;
 			}
 			dest = sh->dev[data_target].page;
-			init_async_submit(&submit, ASYNC_TX_XOR_ZERO_DST, NULL,
-					  NULL, NULL, to_addr_conv(sh, percpu));
+			init_async_submit(&submit,
+					  ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
+					  NULL, NULL, NULL,
+					  to_addr_conv(sh, percpu));
 			tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE,
 				       &submit);
 
 			count = set_syndrome_sources(blocks, sh);
-			init_async_submit(&submit, 0, tx, ops_complete_compute,
-					  sh, to_addr_conv(sh, percpu));
+			init_async_submit(&submit, ASYNC_TX_FENCE, tx,
+					  ops_complete_compute, sh,
+					  to_addr_conv(sh, percpu));
 			return async_gen_syndrome(blocks, 0, count+2,
 						  STRIPE_SIZE, &submit);
 		}
-	}
-
-	init_async_submit(&submit, 0, NULL, ops_complete_compute, sh,
-			  to_addr_conv(sh, percpu));
-	if (failb == syndrome_disks) {
-		/* We're missing D+P. */
-		return async_raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE,
-					       faila, blocks, &submit);
 	} else {
-		/* We're missing D+D. */
-		return async_raid6_2data_recov(syndrome_disks+2, STRIPE_SIZE,
-					       faila, failb, blocks, &submit);
+		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
+				  ops_complete_compute, sh,
+				  to_addr_conv(sh, percpu));
+		if (failb == syndrome_disks) {
+			/* We're missing D+P. */
+			return async_raid6_datap_recov(syndrome_disks+2,
+						       STRIPE_SIZE, faila,
+						       blocks, &submit);
+		} else {
+			/* We're missing D+D. */
+			return async_raid6_2data_recov(syndrome_disks+2,
+						       STRIPE_SIZE, faila, failb,
+						       blocks, &submit);
+		}
 	}
 }
 
@@ -916,7 +929,7 @@ ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu,
 			xor_srcs[count++] = dev->page;
 	}
 
-	init_async_submit(&submit, ASYNC_TX_XOR_DROP_DST, tx,
+	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  ops_complete_prexor, sh, to_addr_conv(sh, percpu));
 	tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
 
@@ -1127,7 +1140,7 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
 			   &sh->ops.zero_sum_result, percpu->spare_page, &submit);
 }
 
-static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 {
 	int overlap_clear = 0, i, disks = sh->disks;
 	struct dma_async_tx_descriptor *tx = NULL;
@@ -1192,22 +1205,55 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	put_cpu();
 }
 
+#ifdef CONFIG_MULTICORE_RAID456
+static void async_run_ops(void *param, async_cookie_t cookie)
+{
+	struct stripe_head *sh = param;
+	unsigned long ops_request = sh->ops.request;
+
+	clear_bit_unlock(STRIPE_OPS_REQ_PENDING, &sh->state);
+	wake_up(&sh->ops.wait_for_ops);
+
+	__raid_run_ops(sh, ops_request);
+	release_stripe(sh);
+}
+
+static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+{
+	/* since handle_stripe can be called outside of raid5d context
+	 * we need to ensure sh->ops.request is de-staged before another
+	 * request arrives
+	 */
+	wait_event(sh->ops.wait_for_ops,
+		   !test_and_set_bit_lock(STRIPE_OPS_REQ_PENDING, &sh->state));
+	sh->ops.request = ops_request;
+
+	atomic_inc(&sh->count);
+	async_schedule(async_run_ops, sh);
+}
+#else
+#define raid_run_ops __raid_run_ops
+#endif
+
 static int grow_one_stripe(raid5_conf_t *conf)
 {
 	struct stripe_head *sh;
+	int disks = max(conf->raid_disks, conf->previous_raid_disks);
 	sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
 	if (!sh)
 		return 0;
-	memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
+	memset(sh, 0, sizeof(*sh) + (disks-1)*sizeof(struct r5dev));
 	sh->raid_conf = conf;
 	spin_lock_init(&sh->lock);
+	#ifdef CONFIG_MULTICORE_RAID456
+	init_waitqueue_head(&sh->ops.wait_for_ops);
+	#endif
 
-	if (grow_buffers(sh, conf->raid_disks)) {
-		shrink_buffers(sh, conf->raid_disks);
+	if (grow_buffers(sh, disks)) {
+		shrink_buffers(sh, disks);
 		kmem_cache_free(conf->slab_cache, sh);
 		return 0;
 	}
-	sh->disks = conf->raid_disks;
 	/* we just created an active stripe so... */
 	atomic_set(&sh->count, 1);
 	atomic_inc(&conf->active_stripes);
@@ -1219,7 +1265,7 @@ static int grow_one_stripe(raid5_conf_t *conf)
 static int grow_stripes(raid5_conf_t *conf, int num)
 {
 	struct kmem_cache *sc;
-	int devs = conf->raid_disks;
+	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
 	sprintf(conf->cache_name[0],
 		"raid%d-%s", conf->level, mdname(conf->mddev));
@@ -1317,6 +1363,9 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 
 		nsh->raid_conf = conf;
 		spin_lock_init(&nsh->lock);
+		#ifdef CONFIG_MULTICORE_RAID456
+		init_waitqueue_head(&nsh->ops.wait_for_ops);
+		#endif
 
 		list_add(&nsh->lru, &newstripes);
 	}
@@ -1608,8 +1657,8 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
 	sector_t new_sector;
 	int algorithm = previous ? conf->prev_algo
 				 : conf->algorithm;
-	int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
-					 : (conf->chunk_size >> 9);
+	int sectors_per_chunk = previous ? conf->prev_chunk_sectors
+					 : conf->chunk_sectors;
 	int raid_disks = previous ? conf->previous_raid_disks
 				  : conf->raid_disks;
 	int data_disks = raid_disks - conf->max_degraded;
@@ -1814,8 +1863,8 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 	int raid_disks = sh->disks;
 	int data_disks = raid_disks - conf->max_degraded;
 	sector_t new_sector = sh->sector, check;
-	int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
-					 : (conf->chunk_size >> 9);
+	int sectors_per_chunk = previous ? conf->prev_chunk_sectors
+					 : conf->chunk_sectors;
 	int algorithm = previous ? conf->prev_algo
 				 : conf->algorithm;
 	sector_t stripe;
@@ -1887,10 +1936,15 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 		case ALGORITHM_PARITY_N:
 			break;
 		case ALGORITHM_ROTATING_N_CONTINUE:
+			/* Like left_symmetric, but P is before Q */
 			if (sh->pd_idx == 0)
 				i--;	/* P D D D Q */
-			else if (i > sh->pd_idx)
-				i -= 2; /* D D Q P D */
+			else {
+				/* D D Q P D */
+				if (i < sh->pd_idx)
+					i += raid_disks;
+				i -= (sh->pd_idx + 1);
+			}
 			break;
 		case ALGORITHM_LEFT_ASYMMETRIC_6:
 		case ALGORITHM_RIGHT_ASYMMETRIC_6:
@@ -2089,8 +2143,7 @@ static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
 			    struct stripe_head *sh)
 {
 	int sectors_per_chunk =
-		previous ? (conf->prev_chunk >> 9)
-			 : (conf->chunk_size >> 9);
+		previous ? conf->prev_chunk_sectors : conf->chunk_sectors;
 	int dd_idx;
 	int chunk_offset = sector_div(stripe, sectors_per_chunk);
 	int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
@@ -2885,7 +2938,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
  *
  */
 
-static bool handle_stripe5(struct stripe_head *sh)
+static void handle_stripe5(struct stripe_head *sh)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int disks = sh->disks, i;
@@ -2913,7 +2966,8 @@ static bool handle_stripe5(struct stripe_head *sh)
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
-		struct r5dev *dev = &sh->dev[i];
+
+		dev = &sh->dev[i];
 		clear_bit(R5_Insync, &dev->flags);
 
 		pr_debug("check %d: state 0x%lx toread %p read %p write %p "
@@ -3155,11 +3209,9 @@ static bool handle_stripe5(struct stripe_head *sh)
 	ops_run_io(sh, &s);
 
 	return_io(return_bi);
-
-	return blocked_rdev == NULL;
 }
 
-static bool handle_stripe6(struct stripe_head *sh)
+static void handle_stripe6(struct stripe_head *sh)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int disks = sh->disks;
@@ -3206,8 +3258,10 @@ static bool handle_stripe6(struct stripe_head *sh)
 		/* now count some things */
 		if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
 		if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
-		if (test_bit(R5_Wantcompute, &dev->flags))
-			BUG_ON(++s.compute > 2);
+		if (test_bit(R5_Wantcompute, &dev->flags)) {
+			s.compute++;
+			BUG_ON(s.compute > 2);
+		}
 
 		if (test_bit(R5_Wantfill, &dev->flags)) {
 			s.to_fill++;
@@ -3441,17 +3495,14 @@ static bool handle_stripe6(struct stripe_head *sh)
 	ops_run_io(sh, &s);
 
 	return_io(return_bi);
-
-	return blocked_rdev == NULL;
 }
 
-/* returns true if the stripe was handled */
-static bool handle_stripe(struct stripe_head *sh)
+static void handle_stripe(struct stripe_head *sh)
 {
 	if (sh->raid_conf->level == 6)
-		return handle_stripe6(sh);
+		handle_stripe6(sh);
 	else
-		return handle_stripe5(sh);
+		handle_stripe5(sh);
 }
 
 static void raid5_activate_delayed(raid5_conf_t *conf)
@@ -3487,11 +3538,12 @@ static void activate_bit_delay(raid5_conf_t *conf)
 
 static void unplug_slaves(mddev_t *mddev)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	int i;
+	int devs = max(conf->raid_disks, conf->previous_raid_disks);
 
 	rcu_read_lock();
-	for (i = 0; i < conf->raid_disks; i++) {
+	for (i = 0; i < devs; i++) {
 		mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
 			struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
@@ -3511,7 +3563,7 @@ static void unplug_slaves(mddev_t *mddev)
 static void raid5_unplug_device(struct request_queue *q)
 {
 	mddev_t *mddev = q->queuedata;
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	unsigned long flags;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
@@ -3530,11 +3582,14 @@ static void raid5_unplug_device(struct request_queue *q)
 static int raid5_congested(void *data, int bits)
 {
 	mddev_t *mddev = data;
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 
 	/* No difference between reads and writes.  Just check
 	 * how busy the stripe_cache is
 	 */
+
+	if (mddev_congested(mddev, bits))
+		return 1;
 	if (conf->inactive_blocked)
 		return 1;
 	if (conf->quiesce)
@@ -3555,14 +3610,14 @@ static int raid5_mergeable_bvec(struct request_queue *q,
 	mddev_t *mddev = q->queuedata;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
-	unsigned int chunk_sectors = mddev->chunk_size >> 9;
+	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bvm->bi_size >> 9;
 
 	if ((bvm->bi_rw & 1) == WRITE)
 		return biovec->bv_len; /* always allow writes to be mergeable */
 
-	if (mddev->new_chunk < mddev->chunk_size)
-		chunk_sectors = mddev->new_chunk >> 9;
+	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
+		chunk_sectors = mddev->new_chunk_sectors;
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0;
 	if (max <= biovec->bv_len && bio_sectors == 0)
@@ -3575,11 +3630,11 @@ static int raid5_mergeable_bvec(struct request_queue *q,
 static int in_chunk_boundary(mddev_t *mddev, struct bio *bio)
 {
 	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
-	unsigned int chunk_sectors = mddev->chunk_size >> 9;
+	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bio->bi_size >> 9;
 
-	if (mddev->new_chunk < mddev->chunk_size)
-		chunk_sectors = mddev->new_chunk >> 9;
+	if (mddev->new_chunk_sectors < mddev->chunk_sectors)
+		chunk_sectors = mddev->new_chunk_sectors;
 	return  chunk_sectors >=
 		((sector & (chunk_sectors - 1)) + bio_sectors);
 }
@@ -3643,7 +3698,7 @@ static void raid5_align_endio(struct bio *bi, int error)
 	bio_put(bi);
 
 	mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
-	conf = mddev_to_conf(mddev);
+	conf = mddev->private;
 	rdev = (void*)raid_bi->bi_next;
 	raid_bi->bi_next = NULL;
 
@@ -3666,10 +3721,10 @@ static int bio_fits_rdev(struct bio *bi)
 {
 	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
 
-	if ((bi->bi_size>>9) > q->max_sectors)
+	if ((bi->bi_size>>9) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > q->max_phys_segments)
+	if (bi->bi_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
 	if (q->merge_bvec_fn)
@@ -3685,7 +3740,7 @@ static int bio_fits_rdev(struct bio *bi)
 static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
 {
 	mddev_t *mddev = q->queuedata;
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	unsigned int dd_idx;
 	struct bio* align_bi;
 	mdk_rdev_t *rdev;
@@ -3802,7 +3857,7 @@ static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf)
 static int make_request(struct request_queue *q, struct bio * bi)
 {
 	mddev_t *mddev = q->queuedata;
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	int dd_idx;
 	sector_t new_sector;
 	sector_t logical_sector, last_sector;
@@ -3810,7 +3865,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	const int rw = bio_data_dir(bi);
 	int cpu, remaining;
 
-	if (unlikely(bio_barrier(bi))) {
+	if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
 		bio_endio(bi, -EOPNOTSUPP);
 		return 0;
 	}
@@ -3899,16 +3954,25 @@ static int make_request(struct request_queue *q, struct bio * bi)
 				spin_unlock_irq(&conf->device_lock);
 				if (must_retry) {
 					release_stripe(sh);
+					schedule();
 					goto retry;
 				}
 			}
-			/* FIXME what if we get a false positive because these
-			 * are being updated.
-			 */
-			if (logical_sector >= mddev->suspend_lo &&
+
+			if (bio_data_dir(bi) == WRITE &&
+			    logical_sector >= mddev->suspend_lo &&
 			    logical_sector < mddev->suspend_hi) {
 				release_stripe(sh);
-				schedule();
+				/* As the suspend_* range is controlled by
+				 * userspace, we want an interruptible
+				 * wait.
+				 */
+				flush_signals(current);
+				prepare_to_wait(&conf->wait_for_overlap,
+						&w, TASK_INTERRUPTIBLE);
+				if (logical_sector >= mddev->suspend_lo &&
+				    logical_sector < mddev->suspend_hi)
+					schedule();
 				goto retry;
 			}
 
@@ -3980,11 +4044,13 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 		    conf->reshape_progress < raid5_size(mddev, 0, 0)) {
 			sector_nr = raid5_size(mddev, 0, 0)
 				- conf->reshape_progress;
-		} else if (mddev->delta_disks > 0 &&
+		} else if (mddev->delta_disks >= 0 &&
 			   conf->reshape_progress > 0)
 			sector_nr = conf->reshape_progress;
 		sector_div(sector_nr, new_data_disks);
 		if (sector_nr) {
+			mddev->curr_resync_completed = sector_nr;
+			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 			*skipped = 1;
 			return sector_nr;
 		}
@@ -3994,10 +4060,10 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 	 * If old and new chunk sizes differ, we need to process the
 	 * largest of these
 	 */
-	if (mddev->new_chunk > mddev->chunk_size)
-		reshape_sectors = mddev->new_chunk / 512;
+	if (mddev->new_chunk_sectors > mddev->chunk_sectors)
+		reshape_sectors = mddev->new_chunk_sectors;
 	else
-		reshape_sectors = mddev->chunk_size / 512;
+		reshape_sectors = mddev->chunk_sectors;
 
 	/* we update the metadata when there is more than 3Meg
 	 * in the block range (that is rather arbitrary, should
@@ -4075,7 +4141,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 	INIT_LIST_HEAD(&stripes);
 	for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
 		int j;
-		int skipped = 0;
+		int skipped_disk = 0;
 		sh = get_active_stripe(conf, stripe_addr+i, 0, 0, 1);
 		set_bit(STRIPE_EXPANDING, &sh->state);
 		atomic_inc(&conf->reshape_stripes);
@@ -4091,14 +4157,14 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 				continue;
 			s = compute_blocknr(sh, j, 0);
 			if (s < raid5_size(mddev, 0, 0)) {
-				skipped = 1;
+				skipped_disk = 1;
 				continue;
 			}
 			memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE);
 			set_bit(R5_Expanded, &sh->dev[j].flags);
 			set_bit(R5_UPTODATE, &sh->dev[j].flags);
 		}
-		if (!skipped) {
+		if (!skipped_disk) {
 			set_bit(STRIPE_EXPAND_READY, &sh->state);
 			set_bit(STRIPE_HANDLE, &sh->state);
 		}
@@ -4120,7 +4186,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 				     1, &dd_idx, NULL);
 	last_sector =
 		raid5_compute_sector(conf, ((stripe_addr+reshape_sectors)
-					    *(new_data_disks) - 1),
+					    * new_data_disks - 1),
 				     1, &dd_idx, NULL);
 	if (last_sector >= mddev->dev_sectors)
 		last_sector = mddev->dev_sectors - 1;
@@ -4149,7 +4215,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 		wait_event(conf->wait_for_overlap,
 			   atomic_read(&conf->reshape_stripes) == 0);
 		mddev->reshape_position = conf->reshape_progress;
-		mddev->curr_resync_completed = mddev->curr_resync;
+		mddev->curr_resync_completed = mddev->curr_resync + reshape_sectors;
 		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
@@ -4194,6 +4260,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 		return 0;
 	}
 
+	/* Allow raid5_quiesce to complete */
+	wait_event(conf->wait_for_overlap, conf->quiesce != 2);
+
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 		return reshape_request(mddev, sector_nr, skipped);
 
@@ -4248,9 +4317,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 	clear_bit(STRIPE_INSYNC, &sh->state);
 	spin_unlock(&sh->lock);
 
-	/* wait for any blocked device to be handled */
-	while (unlikely(!handle_stripe(sh)))
-		;
+	handle_stripe(sh);
 	release_stripe(sh);
 
 	return STRIPE_SECTORS;
@@ -4320,37 +4387,6 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 	return handled;
 }
 
-#ifdef CONFIG_MULTICORE_RAID456
-static void __process_stripe(void *param, async_cookie_t cookie)
-{
-	struct stripe_head *sh = param;
-
-	handle_stripe(sh);
-	release_stripe(sh);
-}
-
-static void process_stripe(struct stripe_head *sh, struct list_head *domain)
-{
-	async_schedule_domain(__process_stripe, sh, domain);
-}
-
-static void synchronize_stripe_processing(struct list_head *domain)
-{
-	async_synchronize_full_domain(domain);
-}
-#else
-static void process_stripe(struct stripe_head *sh, struct list_head *domain)
-{
-	handle_stripe(sh);
-	release_stripe(sh);
-	cond_resched();
-}
-
-static void synchronize_stripe_processing(struct list_head *domain)
-{
-}
-#endif
-
 
 /*
  * This is our raid5 kernel thread.
@@ -4362,9 +4398,8 @@ static void synchronize_stripe_processing(struct list_head *domain)
 static void raid5d(mddev_t *mddev)
 {
 	struct stripe_head *sh;
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	int handled;
-	LIST_HEAD(raid_domain);
 
 	pr_debug("+++ raid5d active\n");
 
@@ -4401,7 +4436,9 @@ static void raid5d(mddev_t *mddev)
 		spin_unlock_irq(&conf->device_lock);
 		
 		handled++;
-		process_stripe(sh, &raid_domain);
+		handle_stripe(sh);
+		release_stripe(sh);
+		cond_resched();
 
 		spin_lock_irq(&conf->device_lock);
 	}
@@ -4409,7 +4446,6 @@ static void raid5d(mddev_t *mddev)
 
 	spin_unlock_irq(&conf->device_lock);
 
-	synchronize_stripe_processing(&raid_domain);
 	async_tx_issue_pending_all();
 	unplug_slaves(mddev);
 
@@ -4419,7 +4455,7 @@ static void raid5d(mddev_t *mddev)
 static ssize_t
 raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	if (conf)
 		return sprintf(page, "%d\n", conf->max_nr_stripes);
 	else
@@ -4429,7 +4465,7 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
 static ssize_t
 raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	unsigned long new;
 	int err;
 
@@ -4467,7 +4503,7 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR,
 static ssize_t
 raid5_show_preread_threshold(mddev_t *mddev, char *page)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	if (conf)
 		return sprintf(page, "%d\n", conf->bypass_threshold);
 	else
@@ -4477,7 +4513,7 @@ raid5_show_preread_threshold(mddev_t *mddev, char *page)
 static ssize_t
 raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	unsigned long new;
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
@@ -4501,7 +4537,7 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
 static ssize_t
 stripe_cache_active_show(mddev_t *mddev, char *page)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	if (conf)
 		return sprintf(page, "%d\n", atomic_read(&conf->active_stripes));
 	else
@@ -4525,20 +4561,16 @@ static struct attribute_group raid5_attrs_group = {
 static sector_t
 raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 
 	if (!sectors)
 		sectors = mddev->dev_sectors;
-	if (!raid_disks) {
+	if (!raid_disks)
 		/* size is defined by the smallest of previous and new size */
-		if (conf->raid_disks < conf->previous_raid_disks)
-			raid_disks = conf->raid_disks;
-		else
-			raid_disks = conf->previous_raid_disks;
-	}
+		raid_disks = min(conf->raid_disks, conf->previous_raid_disks);
 
-	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
-	sectors &= ~((sector_t)mddev->new_chunk/512 - 1);
+	sectors &= ~((sector_t)mddev->chunk_sectors - 1);
+	sectors &= ~((sector_t)mddev->new_chunk_sectors - 1);
 	return sectors * (raid_disks - conf->max_degraded);
 }
 
@@ -4636,7 +4668,7 @@ static int raid5_alloc_percpu(raid5_conf_t *conf)
 			}
 			per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
 		}
-		scribble = kmalloc(scribble_len(conf->raid_disks), GFP_KERNEL);
+		scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
 		if (!scribble) {
 			err = -ENOMEM;
 			break;
@@ -4657,7 +4689,7 @@ static int raid5_alloc_percpu(raid5_conf_t *conf)
 static raid5_conf_t *setup_conf(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
-	int raid_disk, memory;
+	int raid_disk, memory, max_disks;
 	mdk_rdev_t *rdev;
 	struct disk_info *disk;
 
@@ -4682,24 +4714,39 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (!mddev->new_chunk || mddev->new_chunk % PAGE_SIZE) {
+	if (!mddev->new_chunk_sectors ||
+	    (mddev->new_chunk_sectors << 9) % PAGE_SIZE ||
+	    !is_power_of_2(mddev->new_chunk_sectors)) {
 		printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
-			mddev->new_chunk, mdname(mddev));
+		       mddev->new_chunk_sectors << 9, mdname(mddev));
 		return ERR_PTR(-EINVAL);
 	}
 
 	conf = kzalloc(sizeof(raid5_conf_t), GFP_KERNEL);
 	if (conf == NULL)
 		goto abort;
+	spin_lock_init(&conf->device_lock);
+	init_waitqueue_head(&conf->wait_for_stripe);
+	init_waitqueue_head(&conf->wait_for_overlap);
+	INIT_LIST_HEAD(&conf->handle_list);
+	INIT_LIST_HEAD(&conf->hold_list);
+	INIT_LIST_HEAD(&conf->delayed_list);
+	INIT_LIST_HEAD(&conf->bitmap_list);
+	INIT_LIST_HEAD(&conf->inactive_list);
+	atomic_set(&conf->active_stripes, 0);
+	atomic_set(&conf->preread_active_stripes, 0);
+	atomic_set(&conf->active_aligned_reads, 0);
+	conf->bypass_threshold = BYPASS_THRESHOLD;
 
 	conf->raid_disks = mddev->raid_disks;
-	conf->scribble_len = scribble_len(conf->raid_disks);
 	if (mddev->reshape_position == MaxSector)
 		conf->previous_raid_disks = mddev->raid_disks;
 	else
 		conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks;
+	max_disks = max(conf->raid_disks, conf->previous_raid_disks);
+	conf->scribble_len = scribble_len(max_disks);
 
-	conf->disks = kzalloc(conf->raid_disks * sizeof(struct disk_info),
+	conf->disks = kzalloc(max_disks * sizeof(struct disk_info),
 			      GFP_KERNEL);
 	if (!conf->disks)
 		goto abort;
@@ -4713,24 +4760,11 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	if (raid5_alloc_percpu(conf) != 0)
 		goto abort;
 
-	spin_lock_init(&conf->device_lock);
-	init_waitqueue_head(&conf->wait_for_stripe);
-	init_waitqueue_head(&conf->wait_for_overlap);
-	INIT_LIST_HEAD(&conf->handle_list);
-	INIT_LIST_HEAD(&conf->hold_list);
-	INIT_LIST_HEAD(&conf->delayed_list);
-	INIT_LIST_HEAD(&conf->bitmap_list);
-	INIT_LIST_HEAD(&conf->inactive_list);
-	atomic_set(&conf->active_stripes, 0);
-	atomic_set(&conf->preread_active_stripes, 0);
-	atomic_set(&conf->active_aligned_reads, 0);
-	conf->bypass_threshold = BYPASS_THRESHOLD;
-
 	pr_debug("raid5: run(%s) called.\n", mdname(mddev));
 
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
 		raid_disk = rdev->raid_disk;
-		if (raid_disk >= conf->raid_disks
+		if (raid_disk >= max_disks
 		    || raid_disk < 0)
 			continue;
 		disk = conf->disks + raid_disk;
@@ -4747,7 +4781,8 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 			conf->fullsync = 1;
 	}
 
-	conf->chunk_size = mddev->new_chunk;
+	conf->chunk_sectors = mddev->new_chunk_sectors;
+	conf->level = mddev->new_level;
 	if (conf->level == 6)
 		conf->max_degraded = 2;
 	else
@@ -4756,12 +4791,12 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 	conf->max_nr_stripes = NR_STRIPES;
 	conf->reshape_progress = mddev->reshape_position;
 	if (conf->reshape_progress != MaxSector) {
-		conf->prev_chunk = mddev->chunk_size;
+		conf->prev_chunk_sectors = mddev->chunk_sectors;
 		conf->prev_algo = mddev->layout;
 	}
 
 	memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
-		 conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
+		 max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
 	if (grow_stripes(conf, conf->max_nr_stripes)) {
 		printk(KERN_ERR
 			"raid5: couldn't allocate %dkB for buffers\n", memory);
@@ -4770,7 +4805,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 		printk(KERN_INFO "raid5: allocated %dkB for %s\n",
 			memory, mdname(mddev));
 
-	conf->thread = md_register_thread(raid5d, mddev, "%s_raid5");
+	conf->thread = md_register_thread(raid5d, mddev, NULL);
 	if (!conf->thread) {
 		printk(KERN_ERR
 		       "raid5: couldn't allocate thread for %s\n",
@@ -4788,12 +4823,45 @@ static raid5_conf_t *setup_conf(mddev_t *mddev)
 		return ERR_PTR(-ENOMEM);
 }
 
+
+static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
+{
+	switch (algo) {
+	case ALGORITHM_PARITY_0:
+		if (raid_disk < max_degraded)
+			return 1;
+		break;
+	case ALGORITHM_PARITY_N:
+		if (raid_disk >= raid_disks - max_degraded)
+			return 1;
+		break;
+	case ALGORITHM_PARITY_0_6:
+		if (raid_disk == 0 || 
+		    raid_disk == raid_disks - 1)
+			return 1;
+		break;
+	case ALGORITHM_LEFT_ASYMMETRIC_6:
+	case ALGORITHM_RIGHT_ASYMMETRIC_6:
+	case ALGORITHM_LEFT_SYMMETRIC_6:
+	case ALGORITHM_RIGHT_SYMMETRIC_6:
+		if (raid_disk == raid_disks - 1)
+			return 1;
+	}
+	return 0;
+}
+
 static int run(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
-	int working_disks = 0;
+	int working_disks = 0, chunk_size;
+	int dirty_parity_disks = 0;
 	mdk_rdev_t *rdev;
+	sector_t reshape_offset = 0;
 
+	if (mddev->recovery_cp != MaxSector)
+		printk(KERN_NOTICE "raid5: %s is not clean"
+		       " -- starting background reconstruction\n",
+		       mdname(mddev));
 	if (mddev->reshape_position != MaxSector) {
 		/* Check that we can continue the reshape.
 		 * Currently only disks can change, it must
@@ -4816,19 +4884,39 @@ static int run(mddev_t *mddev)
 		 * geometry.
 		 */
 		here_new = mddev->reshape_position;
-		if (sector_div(here_new, (mddev->new_chunk>>9)*
+		if (sector_div(here_new, mddev->new_chunk_sectors *
 			       (mddev->raid_disks - max_degraded))) {
 			printk(KERN_ERR "raid5: reshape_position not "
 			       "on a stripe boundary\n");
 			return -EINVAL;
 		}
+		reshape_offset = here_new * mddev->new_chunk_sectors;
 		/* here_new is the stripe we will write to */
 		here_old = mddev->reshape_position;
-		sector_div(here_old, (mddev->chunk_size>>9)*
+		sector_div(here_old, mddev->chunk_sectors *
 			   (old_disks-max_degraded));
 		/* here_old is the first stripe that we might need to read
 		 * from */
-		if (here_new >= here_old) {
+		if (mddev->delta_disks == 0) {
+			/* We cannot be sure it is safe to start an in-place
+			 * reshape.  It is only safe if user-space if monitoring
+			 * and taking constant backups.
+			 * mdadm always starts a situation like this in
+			 * readonly mode so it can take control before
+			 * allowing any writes.  So just check for that.
+			 */
+			if ((here_new * mddev->new_chunk_sectors != 
+			     here_old * mddev->chunk_sectors) ||
+			    mddev->ro == 0) {
+				printk(KERN_ERR "raid5: in-place reshape must be started"
+				       " in read-only mode - aborting\n");
+				return -EINVAL;
+			}
+		} else if (mddev->delta_disks < 0
+		    ? (here_new * mddev->new_chunk_sectors <=
+		       here_old * mddev->chunk_sectors)
+		    : (here_new * mddev->new_chunk_sectors >=
+		       here_old * mddev->chunk_sectors)) {
 			/* Reading from the same stripe as writing to - bad */
 			printk(KERN_ERR "raid5: reshape_position too early for "
 			       "auto-recovery - aborting.\n");
@@ -4839,7 +4927,7 @@ static int run(mddev_t *mddev)
 	} else {
 		BUG_ON(mddev->level != mddev->new_level);
 		BUG_ON(mddev->layout != mddev->new_layout);
-		BUG_ON(mddev->chunk_size != mddev->new_chunk);
+		BUG_ON(mddev->chunk_sectors != mddev->new_chunk_sectors);
 		BUG_ON(mddev->delta_disks != 0);
 	}
 
@@ -4858,12 +4946,54 @@ static int run(mddev_t *mddev)
 	/*
 	 * 0 for a fully functional array, 1 or 2 for a degraded array.
 	 */
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		if (rdev->raid_disk >= 0 &&
-		    test_bit(In_sync, &rdev->flags))
+	list_for_each_entry(rdev, &mddev->disks, same_set) {
+		if (rdev->raid_disk < 0)
+			continue;
+		if (test_bit(In_sync, &rdev->flags))
 			working_disks++;
+		/* This disc is not fully in-sync.  However if it
+		 * just stored parity (beyond the recovery_offset),
+		 * when we don't need to be concerned about the
+		 * array being dirty.
+		 * When reshape goes 'backwards', we never have
+		 * partially completed devices, so we only need
+		 * to worry about reshape going forwards.
+		 */
+		/* Hack because v0.91 doesn't store recovery_offset properly. */
+		if (mddev->major_version == 0 &&
+		    mddev->minor_version > 90)
+			rdev->recovery_offset = reshape_offset;
+			
+		printk("%d: w=%d pa=%d pr=%d m=%d a=%d r=%d op1=%d op2=%d\n",
+		       rdev->raid_disk, working_disks, conf->prev_algo,
+		       conf->previous_raid_disks, conf->max_degraded,
+		       conf->algorithm, conf->raid_disks, 
+		       only_parity(rdev->raid_disk,
+				   conf->prev_algo,
+				   conf->previous_raid_disks,
+				   conf->max_degraded),
+		       only_parity(rdev->raid_disk,
+				   conf->algorithm,
+				   conf->raid_disks,
+				   conf->max_degraded));
+		if (rdev->recovery_offset < reshape_offset) {
+			/* We need to check old and new layout */
+			if (!only_parity(rdev->raid_disk,
+					 conf->algorithm,
+					 conf->raid_disks,
+					 conf->max_degraded))
+				continue;
+		}
+		if (!only_parity(rdev->raid_disk,
+				 conf->prev_algo,
+				 conf->previous_raid_disks,
+				 conf->max_degraded))
+			continue;
+		dirty_parity_disks++;
+	}
 
-	mddev->degraded = conf->raid_disks - working_disks;
+	mddev->degraded = (max(conf->raid_disks, conf->previous_raid_disks)
+			   - working_disks);
 
 	if (mddev->degraded > conf->max_degraded) {
 		printk(KERN_ERR "raid5: not enough operational devices for %s"
@@ -4873,10 +5003,10 @@ static int run(mddev_t *mddev)
 	}
 
 	/* device size must be a multiple of chunk size */
-	mddev->dev_sectors &= ~(mddev->chunk_size / 512 - 1);
+	mddev->dev_sectors &= ~(mddev->chunk_sectors - 1);
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
-	if (mddev->degraded > 0 &&
+	if (mddev->degraded > dirty_parity_disks &&
 	    mddev->recovery_cp != MaxSector) {
 		if (mddev->ok_start_degraded)
 			printk(KERN_WARNING
@@ -4913,7 +5043,7 @@ static int run(mddev_t *mddev)
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 		set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 		mddev->sync_thread = md_register_thread(md_do_sync, mddev,
-							"%s_reshape");
+							"reshape");
 	}
 
 	/* read-ahead size must cover two whole stripes, which is
@@ -4922,7 +5052,7 @@ static int run(mddev_t *mddev)
 	{
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
-			(mddev->chunk_size / PAGE_SIZE);
+			((mddev->chunk_sectors << 9) / PAGE_SIZE);
 		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
 	}
@@ -4942,6 +5072,14 @@ static int run(mddev_t *mddev)
 	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
 	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+	chunk_size = mddev->chunk_sectors << 9;
+	blk_queue_io_min(mddev->queue, chunk_size);
+	blk_queue_io_opt(mddev->queue, chunk_size *
+			 (conf->raid_disks - conf->max_degraded));
+
+	list_for_each_entry(rdev, &mddev->disks, same_set)
+		disk_stack_limits(mddev->gendisk, rdev->bdev,
+				  rdev->data_offset << 9);
 
 	return 0;
 abort:
@@ -5012,7 +5150,8 @@ static void status(struct seq_file *seq, mddev_t *mddev)
 	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
 	int i;
 
-	seq_printf (seq, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
+	seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
+		mddev->chunk_sectors / 2, mddev->layout);
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
 	for (i = 0; i < conf->raid_disks; i++)
 		seq_printf (seq, "%s",
@@ -5160,7 +5299,7 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 	 * any io in the removed space completes, but it hardly seems
 	 * worth it.
 	 */
-	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
+	sectors &= ~((sector_t)mddev->chunk_sectors - 1);
 	md_set_array_sectors(mddev, raid5_size(mddev, sectors,
 					       mddev->raid_disks));
 	if (mddev->array_sectors >
@@ -5168,6 +5307,7 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 		return -EINVAL;
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
+	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->dev_sectors;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -5177,14 +5317,37 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 	return 0;
 }
 
-static int raid5_check_reshape(mddev_t *mddev)
+static int check_stripe_cache(mddev_t *mddev)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	/* Can only proceed if there are plenty of stripe_heads.
+	 * We need a minimum of one full stripe,, and for sensible progress
+	 * it is best to have about 4 times that.
+	 * If we require 4 times, then the default 256 4K stripe_heads will
+	 * allow for chunk sizes up to 256K, which is probably OK.
+	 * If the chunk size is greater, user-space should request more
+	 * stripe_heads first.
+	 */
+	raid5_conf_t *conf = mddev->private;
+	if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4
+	    > conf->max_nr_stripes ||
+	    ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
+	    > conf->max_nr_stripes) {
+		printk(KERN_WARNING "raid5: reshape: not enough stripes.  Needed %lu\n",
+		       ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9)
+			/ STRIPE_SIZE)*4);
+		return 0;
+	}
+	return 1;
+}
+
+static int check_reshape(mddev_t *mddev)
+{
+	raid5_conf_t *conf = mddev->private;
 
 	if (mddev->delta_disks == 0 &&
 	    mddev->new_layout == mddev->layout &&
-	    mddev->new_chunk == mddev->chunk_size)
-		return -EINVAL; /* nothing to do */
+	    mddev->new_chunk_sectors == mddev->chunk_sectors)
+		return 0; /* nothing to do */
 	if (mddev->bitmap)
 		/* Cannot grow a bitmap yet */
 		return -EBUSY;
@@ -5203,28 +5366,15 @@ static int raid5_check_reshape(mddev_t *mddev)
 			return -EINVAL;
 	}
 
-	/* Can only proceed if there are plenty of stripe_heads.
-	 * We need a minimum of one full stripe,, and for sensible progress
-	 * it is best to have about 4 times that.
-	 * If we require 4 times, then the default 256 4K stripe_heads will
-	 * allow for chunk sizes up to 256K, which is probably OK.
-	 * If the chunk size is greater, user-space should request more
-	 * stripe_heads first.
-	 */
-	if ((mddev->chunk_size / STRIPE_SIZE) * 4 > conf->max_nr_stripes ||
-	    (mddev->new_chunk / STRIPE_SIZE) * 4 > conf->max_nr_stripes) {
-		printk(KERN_WARNING "raid5: reshape: not enough stripes.  Needed %lu\n",
-		       (max(mddev->chunk_size, mddev->new_chunk)
-			/ STRIPE_SIZE)*4);
+	if (!check_stripe_cache(mddev))
 		return -ENOSPC;
-	}
 
 	return resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
 }
 
 static int raid5_start_reshape(mddev_t *mddev)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 	mdk_rdev_t *rdev;
 	int spares = 0;
 	int added_devices = 0;
@@ -5233,6 +5383,9 @@ static int raid5_start_reshape(mddev_t *mddev)
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
 		return -EBUSY;
 
+	if (!check_stripe_cache(mddev))
+		return -ENOSPC;
+
 	list_for_each_entry(rdev, &mddev->disks, same_set)
 		if (rdev->raid_disk < 0 &&
 		    !test_bit(Faulty, &rdev->flags))
@@ -5259,8 +5412,8 @@ static int raid5_start_reshape(mddev_t *mddev)
 	spin_lock_irq(&conf->device_lock);
 	conf->previous_raid_disks = conf->raid_disks;
 	conf->raid_disks += mddev->delta_disks;
-	conf->prev_chunk = conf->chunk_size;
-	conf->chunk_size = mddev->new_chunk;
+	conf->prev_chunk_sectors = conf->chunk_sectors;
+	conf->chunk_sectors = mddev->new_chunk_sectors;
 	conf->prev_algo = conf->algorithm;
 	conf->algorithm = mddev->new_layout;
 	if (mddev->delta_disks < 0)
@@ -5279,9 +5432,11 @@ static int raid5_start_reshape(mddev_t *mddev)
 		    !test_bit(Faulty, &rdev->flags)) {
 			if (raid5_add_disk(mddev, rdev) == 0) {
 				char nm[20];
-				set_bit(In_sync, &rdev->flags);
+				if (rdev->raid_disk >= conf->previous_raid_disks)
+					set_bit(In_sync, &rdev->flags);
+				else
+					rdev->recovery_offset = 0;
 				added_devices++;
-				rdev->recovery_offset = 0;
 				sprintf(nm, "rd%d", rdev->raid_disk);
 				if (sysfs_create_link(&mddev->kobj,
 						      &rdev->kobj, nm))
@@ -5300,7 +5455,7 @@ static int raid5_start_reshape(mddev_t *mddev)
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 	mddev->raid_disks = conf->raid_disks;
-	mddev->reshape_position = 0;
+	mddev->reshape_position = conf->reshape_progress;
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -5308,7 +5463,7 @@ static int raid5_start_reshape(mddev_t *mddev)
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 	mddev->sync_thread = md_register_thread(md_do_sync, mddev,
-						"%s_reshape");
+						"reshape");
 	if (!mddev->sync_thread) {
 		mddev->recovery = 0;
 		spin_lock_irq(&conf->device_lock);
@@ -5342,7 +5497,7 @@ static void end_reshape(raid5_conf_t *conf)
 		 */
 		{
 			int data_disks = conf->raid_disks - conf->max_degraded;
-			int stripe = data_disks * (conf->chunk_size
+			int stripe = data_disks * ((conf->chunk_sectors << 9)
 						   / PAGE_SIZE);
 			if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 				conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
@@ -5355,8 +5510,7 @@ static void end_reshape(raid5_conf_t *conf)
  */
 static void raid5_finish_reshape(mddev_t *mddev)
 {
-	struct block_device *bdev;
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 
@@ -5364,15 +5518,7 @@ static void raid5_finish_reshape(mddev_t *mddev)
 			md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 			set_capacity(mddev->gendisk, mddev->array_sectors);
 			mddev->changed = 1;
-
-			bdev = bdget_disk(mddev->gendisk, 0);
-			if (bdev) {
-				mutex_lock(&bdev->bd_inode->i_mutex);
-				i_size_write(bdev->bd_inode,
-					     (loff_t)mddev->array_sectors << 9);
-				mutex_unlock(&bdev->bd_inode->i_mutex);
-				bdput(bdev);
-			}
+			revalidate_disk(mddev->gendisk);
 		} else {
 			int d;
 			mddev->degraded = conf->raid_disks;
@@ -5383,11 +5529,18 @@ static void raid5_finish_reshape(mddev_t *mddev)
 					mddev->degraded--;
 			for (d = conf->raid_disks ;
 			     d < conf->raid_disks - mddev->delta_disks;
-			     d++)
-				raid5_remove_disk(mddev, d);
+			     d++) {
+				mdk_rdev_t *rdev = conf->disks[d].rdev;
+				if (rdev && raid5_remove_disk(mddev, d) == 0) {
+					char nm[20];
+					sprintf(nm, "rd%d", rdev->raid_disk);
+					sysfs_remove_link(&mddev->kobj, nm);
+					rdev->raid_disk = -1;
+				}
+			}
 		}
 		mddev->layout = conf->algorithm;
-		mddev->chunk_size = conf->chunk_size;
+		mddev->chunk_sectors = conf->chunk_sectors;
 		mddev->reshape_position = MaxSector;
 		mddev->delta_disks = 0;
 	}
@@ -5395,7 +5548,7 @@ static void raid5_finish_reshape(mddev_t *mddev)
 
 static void raid5_quiesce(mddev_t *mddev, int state)
 {
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
 
 	switch(state) {
 	case 2: /* resume for a suspend */
@@ -5404,12 +5557,18 @@ static void raid5_quiesce(mddev_t *mddev, int state)
 
 	case 1: /* stop all writes */
 		spin_lock_irq(&conf->device_lock);
-		conf->quiesce = 1;
+		/* '2' tells resync/reshape to pause so that all
+		 * active stripes can drain
+		 */
+		conf->quiesce = 2;
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    atomic_read(&conf->active_stripes) == 0 &&
 				    atomic_read(&conf->active_aligned_reads) == 0,
 				    conf->device_lock, /* nothing */);
+		conf->quiesce = 1;
 		spin_unlock_irq(&conf->device_lock);
+		/* allow reshape to continue */
+		wake_up(&conf->wait_for_overlap);
 		break;
 
 	case 0: /* re-enable writes */
@@ -5445,7 +5604,7 @@ static void *raid5_takeover_raid1(mddev_t *mddev)
 
 	mddev->new_level = 5;
 	mddev->new_layout = ALGORITHM_LEFT_SYMMETRIC;
-	mddev->new_chunk = chunksect << 9;
+	mddev->new_chunk_sectors = chunksect;
 
 	return setup_conf(mddev);
 }
@@ -5484,24 +5643,24 @@ static void *raid5_takeover_raid6(mddev_t *mddev)
 }
 
 
-static int raid5_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+static int raid5_check_reshape(mddev_t *mddev)
 {
 	/* For a 2-drive array, the layout and chunk size can be changed
 	 * immediately as not restriping is needed.
 	 * For larger arrays we record the new value - after validation
 	 * to be used by a reshape pass.
 	 */
-	raid5_conf_t *conf = mddev_to_conf(mddev);
+	raid5_conf_t *conf = mddev->private;
+	int new_chunk = mddev->new_chunk_sectors;
 
-	if (new_layout >= 0 && !algorithm_valid_raid5(new_layout))
+	if (mddev->new_layout >= 0 && !algorithm_valid_raid5(mddev->new_layout))
 		return -EINVAL;
 	if (new_chunk > 0) {
-		if (new_chunk & (new_chunk-1))
-			/* not a power of 2 */
+		if (!is_power_of_2(new_chunk))
 			return -EINVAL;
-		if (new_chunk < PAGE_SIZE)
+		if (new_chunk < (PAGE_SIZE>>9))
 			return -EINVAL;
-		if (mddev->array_sectors & ((new_chunk>>9)-1))
+		if (mddev->array_sectors & (new_chunk-1))
 			/* not factor of array size */
 			return -EINVAL;
 	}
@@ -5509,49 +5668,39 @@ static int raid5_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
 	/* They look valid */
 
 	if (mddev->raid_disks == 2) {
-
-		if (new_layout >= 0) {
-			conf->algorithm = new_layout;
-			mddev->layout = mddev->new_layout = new_layout;
+		/* can make the change immediately */
+		if (mddev->new_layout >= 0) {
+			conf->algorithm = mddev->new_layout;
+			mddev->layout = mddev->new_layout;
 		}
 		if (new_chunk > 0) {
-			conf->chunk_size = new_chunk;
-			mddev->chunk_size = mddev->new_chunk = new_chunk;
+			conf->chunk_sectors = new_chunk ;
+			mddev->chunk_sectors = new_chunk;
 		}
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
-	} else {
-		if (new_layout >= 0)
-			mddev->new_layout = new_layout;
-		if (new_chunk > 0)
-			mddev->new_chunk = new_chunk;
 	}
-	return 0;
+	return check_reshape(mddev);
 }
 
-static int raid6_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+static int raid6_check_reshape(mddev_t *mddev)
 {
-	if (new_layout >= 0 && !algorithm_valid_raid6(new_layout))
+	int new_chunk = mddev->new_chunk_sectors;
+
+	if (mddev->new_layout >= 0 && !algorithm_valid_raid6(mddev->new_layout))
 		return -EINVAL;
 	if (new_chunk > 0) {
-		if (new_chunk & (new_chunk-1))
-			/* not a power of 2 */
+		if (!is_power_of_2(new_chunk))
 			return -EINVAL;
-		if (new_chunk < PAGE_SIZE)
+		if (new_chunk < (PAGE_SIZE >> 9))
 			return -EINVAL;
-		if (mddev->array_sectors & ((new_chunk>>9)-1))
+		if (mddev->array_sectors & (new_chunk-1))
 			/* not factor of array size */
 			return -EINVAL;
 	}
 
 	/* They look valid */
-
-	if (new_layout >= 0)
-		mddev->new_layout = new_layout;
-	if (new_chunk > 0)
-		mddev->new_chunk = new_chunk;
-
-	return 0;
+	return check_reshape(mddev);
 }
 
 static void *raid5_takeover(mddev_t *mddev)
@@ -5561,8 +5710,6 @@ static void *raid5_takeover(mddev_t *mddev)
 	 *  raid1 - if there are two drives.  We need to know the chunk size
 	 *  raid4 - trivial - just use a raid4 layout.
 	 *  raid6 - Providing it is a *_6 layout
-	 *
-	 * For now, just do raid1
 	 */
 
 	if (mddev->level == 1)
@@ -5644,12 +5791,11 @@ static struct mdk_personality raid6_personality =
 	.sync_request	= sync_request,
 	.resize		= raid5_resize,
 	.size		= raid5_size,
-	.check_reshape	= raid5_check_reshape,
+	.check_reshape	= raid6_check_reshape,
 	.start_reshape  = raid5_start_reshape,
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
-	.reconfig	= raid6_reconfig,
 };
 static struct mdk_personality raid5_personality =
 {
@@ -5672,7 +5818,6 @@ static struct mdk_personality raid5_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
-	.reconfig	= raid5_reconfig,
 };
 
 static struct mdk_personality raid4_personality =