Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (52 commits)
  md: Protect access to mddev->disks list using RCU
  md: only count actual openers as access which prevent a 'stop'
  md: linear: Make array_size sector-based and rename it to array_sectors.
  md: Make mddev->array_size sector-based.
  md: Make super_type->rdev_size_change() take sector-based sizes.
  md: Fix check for overlapping devices.
  md: Tidy up rdev_size_store a bit:
  md: Remove some unused macros.
  md: Turn rdev->sb_offset into a sector-based quantity.
  md: Make calc_dev_sboffset() return a sector count.
  md: Replace calc_dev_size() by calc_num_sectors().
  md: Make update_size() take the number of sectors.
  md: Better control of when do_md_stop is allowed to stop the array.
  md: get_disk_info(): Don't convert between signed and unsigned and back.
  md: Simplify restart_array().
  md: alloc_disk_sb(): Return proper error value.
  md: Simplify sb_equal().
  md: Simplify uuid_equal().
  md: sb_equal(): Fix misleading printk.
  md: Fix a typo in the comment to cmd_match().
  ...

1 files changed, 255 insertions, 490 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9ce7154845c6..55e7c56045a0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -115,15 +115,20 @@ static void return_io(struct bio *return_bi)
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
 		bi->bi_size = 0;
-		bi->bi_end_io(bi,
-			      test_bit(BIO_UPTODATE, &bi->bi_flags)
-			        ? 0 : -EIO);
+		bio_endio(bi, 0);
 		bi = return_bi;
 	}
 }
 
 static void print_raid5_conf (raid5_conf_t *conf);
 
+static int stripe_operations_active(struct stripe_head *sh)
+{
+	return sh->check_state || sh->reconstruct_state ||
+	       test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
+	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
+}
+
 static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 {
 	if (atomic_dec_and_test(&sh->count)) {
@@ -143,7 +148,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 			}
 			md_wakeup_thread(conf->mddev->thread);
 		} else {
-			BUG_ON(sh->ops.pending);
+			BUG_ON(stripe_operations_active(sh));
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 				atomic_dec(&conf->preread_active_stripes);
 				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
@@ -245,7 +250,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int
 
 	BUG_ON(atomic_read(&sh->count) != 0);
 	BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
-	BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete);
+	BUG_ON(stripe_operations_active(sh));
 
 	CHECK_DEVLOCK();
 	pr_debug("init_stripe called, stripe %llu\n",
@@ -346,62 +351,18 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector
 	return sh;
 }
 
-/* test_and_ack_op() ensures that we only dequeue an operation once */
-#define test_and_ack_op(op, pend) \
-do {							\
-	if (test_bit(op, &sh->ops.pending) &&		\
-		!test_bit(op, &sh->ops.complete)) {	\
-		if (test_and_set_bit(op, &sh->ops.ack)) \
-			clear_bit(op, &pend);		\
-		else					\
-			ack++;				\
-	} else						\
-		clear_bit(op, &pend);			\
-} while (0)
-
-/* find new work to run, do not resubmit work that is already
- * in flight
- */
-static unsigned long get_stripe_work(struct stripe_head *sh)
-{
-	unsigned long pending;
-	int ack = 0;
-
-	pending = sh->ops.pending;
-
-	test_and_ack_op(STRIPE_OP_BIOFILL, pending);
-	test_and_ack_op(STRIPE_OP_COMPUTE_BLK, pending);
-	test_and_ack_op(STRIPE_OP_PREXOR, pending);
-	test_and_ack_op(STRIPE_OP_BIODRAIN, pending);
-	test_and_ack_op(STRIPE_OP_POSTXOR, pending);
-	test_and_ack_op(STRIPE_OP_CHECK, pending);
-	if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending))
-		ack++;
-
-	sh->ops.count -= ack;
-	if (unlikely(sh->ops.count < 0)) {
-		printk(KERN_ERR "pending: %#lx ops.pending: %#lx ops.ack: %#lx "
-			"ops.complete: %#lx\n", pending, sh->ops.pending,
-			sh->ops.ack, sh->ops.complete);
-		BUG();
-	}
-
-	return pending;
-}
-
 static void
 raid5_end_read_request(struct bio *bi, int error);
 static void
 raid5_end_write_request(struct bio *bi, int error);
 
-static void ops_run_io(struct stripe_head *sh)
+static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int i, disks = sh->disks;
 
 	might_sleep();
 
-	set_bit(STRIPE_IO_STARTED, &sh->state);
 	for (i = disks; i--; ) {
 		int rw;
 		struct bio *bi;
@@ -430,11 +391,11 @@ static void ops_run_io(struct stripe_head *sh)
 		rcu_read_unlock();
 
 		if (rdev) {
-			if (test_bit(STRIPE_SYNCING, &sh->state) ||
-				test_bit(STRIPE_EXPAND_SOURCE, &sh->state) ||
-				test_bit(STRIPE_EXPAND_READY, &sh->state))
+			if (s->syncing || s->expanding || s->expanded)
 				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
 
+			set_bit(STRIPE_IO_STARTED, &sh->state);
+
 			bi->bi_bdev = rdev->bdev;
 			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
 				__func__, (unsigned long long)sh->sector,
@@ -528,38 +489,34 @@ static void ops_complete_biofill(void *stripe_head_ref)
 		(unsigned long long)sh->sector);
 
 	/* clear completed biofills */
+	spin_lock_irq(&conf->device_lock);
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
 		/* acknowledge completion of a biofill operation */
 		/* and check if we need to reply to a read request,
 		 * new R5_Wantfill requests are held off until
-		 * !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending)
+		 * !STRIPE_BIOFILL_RUN
 		 */
 		if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
 			struct bio *rbi, *rbi2;
 
-			/* The access to dev->read is outside of the
-			 * spin_lock_irq(&conf->device_lock), but is protected
-			 * by the STRIPE_OP_BIOFILL pending bit
-			 */
 			BUG_ON(!dev->read);
 			rbi = dev->read;
 			dev->read = NULL;
 			while (rbi && rbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
-				spin_lock_irq(&conf->device_lock);
 				if (--rbi->bi_phys_segments == 0) {
 					rbi->bi_next = return_bi;
 					return_bi = rbi;
 				}
-				spin_unlock_irq(&conf->device_lock);
 				rbi = rbi2;
 			}
 		}
 	}
-	set_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
+	spin_unlock_irq(&conf->device_lock);
+	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
 	return_io(return_bi);
 
@@ -610,13 +567,14 @@ static void ops_complete_compute5(void *stripe_head_ref)
 	set_bit(R5_UPTODATE, &tgt->flags);
 	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
 	clear_bit(R5_Wantcompute, &tgt->flags);
-	set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
+	clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
+	if (sh->check_state == check_state_compute_run)
+		sh->check_state = check_state_compute_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
 
-static struct dma_async_tx_descriptor *
-ops_run_compute5(struct stripe_head *sh, unsigned long pending)
+static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
@@ -646,10 +604,6 @@ ops_run_compute5(struct stripe_head *sh, unsigned long pending)
 			ASYNC_TX_XOR_ZERO_DST, NULL,
 			ops_complete_compute5, sh);
 
-	/* ack now if postxor is not set to be run */
-	if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending))
-		async_tx_ack(tx);
-
 	return tx;
 }
 
@@ -659,8 +613,6 @@ static void ops_complete_prexor(void *stripe_head_ref)
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
-
-	set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
 }
 
 static struct dma_async_tx_descriptor *
@@ -680,7 +632,7 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		/* Only process blocks that are known to be uptodate */
-		if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags))
+		if (test_bit(R5_Wantdrain, &dev->flags))
 			xor_srcs[count++] = dev->page;
 	}
 
@@ -692,16 +644,10 @@ ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 }
 
 static struct dma_async_tx_descriptor *
-ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		 unsigned long pending)
+ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 {
 	int disks = sh->disks;
-	int pd_idx = sh->pd_idx, i;
-
-	/* check if prexor is active which means only process blocks
-	 * that are part of a read-modify-write (Wantprexor)
-	 */
-	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
+	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
@@ -709,20 +655,8 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		struct bio *chosen;
-		int towrite;
-
-		towrite = 0;
-		if (prexor) { /* rmw */
-			if (dev->towrite &&
-			    test_bit(R5_Wantprexor, &dev->flags))
-				towrite = 1;
-		} else { /* rcw */
-			if (i != pd_idx && dev->towrite &&
-				test_bit(R5_LOCKED, &dev->flags))
-				towrite = 1;
-		}
 
-		if (towrite) {
+		if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
 			struct bio *wbi;
 
 			spin_lock(&sh->lock);
@@ -747,18 +681,6 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 static void ops_complete_postxor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-
-	pr_debug("%s: stripe %llu\n", __func__,
-		(unsigned long long)sh->sector);
-
-	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
-}
-
-static void ops_complete_write(void *stripe_head_ref)
-{
-	struct stripe_head *sh = stripe_head_ref;
 	int disks = sh->disks, i, pd_idx = sh->pd_idx;
 
 	pr_debug("%s: stripe %llu\n", __func__,
@@ -770,16 +692,21 @@ static void ops_complete_write(void *stripe_head_ref)
 			set_bit(R5_UPTODATE, &dev->flags);
 	}
 
-	set_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
-	set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
+	if (sh->reconstruct_state == reconstruct_state_drain_run)
+		sh->reconstruct_state = reconstruct_state_drain_result;
+	else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run)
+		sh->reconstruct_state = reconstruct_state_prexor_drain_result;
+	else {
+		BUG_ON(sh->reconstruct_state != reconstruct_state_run);
+		sh->reconstruct_state = reconstruct_state_result;
+	}
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
 
 static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		unsigned long pending)
+ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
@@ -787,9 +714,8 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest;
-	int prexor = test_bit(STRIPE_OP_PREXOR, &pending);
+	int prexor = 0;
 	unsigned long flags;
-	dma_async_tx_callback callback;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
@@ -797,7 +723,8 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 	/* check if prexor is active which means only process blocks
 	 * that are part of a read-modify-write (written)
 	 */
-	if (prexor) {
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
+		prexor = 1;
 		xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
@@ -813,10 +740,6 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 		}
 	}
 
-	/* check whether this postxor is part of a write */
-	callback = test_bit(STRIPE_OP_BIODRAIN, &pending) ?
-		ops_complete_write : ops_complete_postxor;
-
 	/* 1/ if we prexor'd then the dest is reused as a source
 	 * 2/ if we did not prexor then we are redoing the parity
 	 * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
@@ -830,25 +753,20 @@ ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
 	if (unlikely(count == 1)) {
 		flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
 		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
-			flags, tx, callback, sh);
+			flags, tx, ops_complete_postxor, sh);
 	} else
 		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-			flags, tx, callback, sh);
+			flags, tx, ops_complete_postxor, sh);
 }
 
 static void ops_complete_check(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-	int pd_idx = sh->pd_idx;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
-		sh->ops.zero_sum_result == 0)
-		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-
-	set_bit(STRIPE_OP_CHECK, &sh->ops.complete);
+	sh->check_state = check_state_check_result;
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
@@ -875,46 +793,42 @@ static void ops_run_check(struct stripe_head *sh)
 	tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
 		&sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
 
-	if (tx)
-		set_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-	else
-		clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-
 	atomic_inc(&sh->count);
 	tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
 		ops_complete_check, sh);
 }
 
-static void raid5_run_ops(struct stripe_head *sh, unsigned long pending)
+static void raid5_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;
 
-	if (test_bit(STRIPE_OP_BIOFILL, &pending)) {
+	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending))
-		tx = ops_run_compute5(sh, pending);
+	if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
+		tx = ops_run_compute5(sh);
+		/* terminate the chain if postxor is not set to be run */
+		if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
+			async_tx_ack(tx);
+	}
 
-	if (test_bit(STRIPE_OP_PREXOR, &pending))
+	if (test_bit(STRIPE_OP_PREXOR, &ops_request))
 		tx = ops_run_prexor(sh, tx);
 
-	if (test_bit(STRIPE_OP_BIODRAIN, &pending)) {
-		tx = ops_run_biodrain(sh, tx, pending);
+	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
+		tx = ops_run_biodrain(sh, tx);
 		overlap_clear++;
 	}
 
-	if (test_bit(STRIPE_OP_POSTXOR, &pending))
-		ops_run_postxor(sh, tx, pending);
+	if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
+		ops_run_postxor(sh, tx);
 
-	if (test_bit(STRIPE_OP_CHECK, &pending))
+	if (test_bit(STRIPE_OP_CHECK, &ops_request))
 		ops_run_check(sh);
 
-	if (test_bit(STRIPE_OP_IO, &pending))
-		ops_run_io(sh);
-
 	if (overlap_clear)
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
@@ -997,14 +911,16 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
-	int err = 0;
+	int err;
 	struct kmem_cache *sc;
 	int i;
 
 	if (newsize <= conf->pool_size)
 		return 0; /* never bother to shrink */
 
-	md_allow_write(conf->mddev);
+	err = md_allow_write(conf->mddev);
+	if (err)
+		return err;
 
 	/* Step 1 */
 	sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
@@ -1703,11 +1619,11 @@ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
 	}
 }
 
-static int
-handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
+static void
+schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
+			 int rcw, int expand)
 {
 	int i, pd_idx = sh->pd_idx, disks = sh->disks;
-	int locked = 0;
 
 	if (rcw) {
 		/* if we are not expanding this is a proper write request, and
@@ -1715,53 +1631,48 @@ handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
 		 * stripe cache
 		 */
 		if (!expand) {
-			set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-			sh->ops.count++;
-		}
+			sh->reconstruct_state = reconstruct_state_drain_run;
+			set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		} else
+			sh->reconstruct_state = reconstruct_state_run;
 
-		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-		sh->ops.count++;
+		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 
 			if (dev->towrite) {
 				set_bit(R5_LOCKED, &dev->flags);
+				set_bit(R5_Wantdrain, &dev->flags);
 				if (!expand)
 					clear_bit(R5_UPTODATE, &dev->flags);
-				locked++;
+				s->locked++;
 			}
 		}
-		if (locked + 1 == disks)
+		if (s->locked + 1 == disks)
 			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
 				atomic_inc(&sh->raid_conf->pending_full_writes);
 	} else {
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
-		set_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-		set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-		set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-
-		sh->ops.count += 3;
+		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
+		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (i == pd_idx)
 				continue;
 
-			/* For a read-modify write there may be blocks that are
-			 * locked for reading while others are ready to be
-			 * written so we distinguish these blocks by the
-			 * R5_Wantprexor bit
-			 */
 			if (dev->towrite &&
 			    (test_bit(R5_UPTODATE, &dev->flags) ||
-			    test_bit(R5_Wantcompute, &dev->flags))) {
-				set_bit(R5_Wantprexor, &dev->flags);
+			     test_bit(R5_Wantcompute, &dev->flags))) {
+				set_bit(R5_Wantdrain, &dev->flags);
 				set_bit(R5_LOCKED, &dev->flags);
 				clear_bit(R5_UPTODATE, &dev->flags);
-				locked++;
+				s->locked++;
 			}
 		}
 	}
@@ -1771,13 +1682,11 @@ handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
 	 */
 	set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
 	clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-	locked++;
+	s->locked++;
 
-	pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
+	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
 		__func__, (unsigned long long)sh->sector,
-		locked, sh->ops.pending);
-
-	return locked;
+		s->locked, s->ops_request);
 }
 
 /*
@@ -1876,7 +1785,7 @@ static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
 }
 
 static void
-handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
+handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks,
 				struct bio **return_bi)
 {
@@ -1967,48 +1876,38 @@ handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
 			md_wakeup_thread(conf->mddev->thread);
 }
 
-/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
- * to process
+/* fetch_block5 - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill5 to continue
  */
-static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
-			struct stripe_head_state *s, int disk_idx, int disks)
+static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s,
+			int disk_idx, int disks)
 {
 	struct r5dev *dev = &sh->dev[disk_idx];
 	struct r5dev *failed_dev = &sh->dev[s->failed_num];
 
-	/* don't schedule compute operations or reads on the parity block while
-	 * a check is in flight
-	 */
-	if ((disk_idx == sh->pd_idx) &&
-	     test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
-		return ~0;
-
 	/* is the data in this block needed, and can we get it? */
 	if (!test_bit(R5_LOCKED, &dev->flags) &&
-	    !test_bit(R5_UPTODATE, &dev->flags) && (dev->toread ||
-	    (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
-	     s->syncing || s->expanding || (s->failed &&
-	     (failed_dev->toread || (failed_dev->towrite &&
-	     !test_bit(R5_OVERWRITE, &failed_dev->flags)
-	     ))))) {
-		/* 1/ We would like to get this block, possibly by computing it,
-		 * but we might not be able to.
-		 *
-		 * 2/ Since parity check operations potentially make the parity
-		 * block !uptodate it will need to be refreshed before any
-		 * compute operations on data disks are scheduled.
-		 *
-		 * 3/ We hold off parity block re-reads until check operations
-		 * have quiesced.
+	    !test_bit(R5_UPTODATE, &dev->flags) &&
+	    (dev->toread ||
+	     (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
+	     s->syncing || s->expanding ||
+	     (s->failed &&
+	      (failed_dev->toread ||
+	       (failed_dev->towrite &&
+		!test_bit(R5_OVERWRITE, &failed_dev->flags)))))) {
+		/* We would like to get this block, possibly by computing it,
+		 * otherwise read it if the backing disk is insync
 		 */
 		if ((s->uptodate == disks - 1) &&
-		    (s->failed && disk_idx == s->failed_num) &&
-		    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
-			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
+		    (s->failed && disk_idx == s->failed_num)) {
+			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
 			set_bit(R5_Wantcompute, &dev->flags);
 			sh->ops.target = disk_idx;
 			s->req_compute = 1;
-			sh->ops.count++;
 			/* Careful: from this point on 'uptodate' is in the eye
 			 * of raid5_run_ops which services 'compute' operations
 			 * before writes. R5_Wantcompute flags a block that will
@@ -2016,53 +1915,40 @@ static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
 			 * subsequent operation.
 			 */
 			s->uptodate++;
-			return 0; /* uptodate + compute == disks */
+			return 1; /* uptodate + compute == disks */
 		} else if (test_bit(R5_Insync, &dev->flags)) {
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantread, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			s->locked++;
 			pr_debug("Reading block %d (sync=%d)\n", disk_idx,
 				s->syncing);
 		}
 	}
 
-	return ~0;
+	return 0;
 }
 
-static void handle_issuing_new_read_requests5(struct stripe_head *sh,
+/**
+ * handle_stripe_fill5 - read or compute data to satisfy pending requests.
+ */
+static void handle_stripe_fill5(struct stripe_head *sh,
 			struct stripe_head_state *s, int disks)
 {
 	int i;
 
-	/* Clear completed compute operations.  Parity recovery
-	 * (STRIPE_OP_MOD_REPAIR_PD) implies a write-back which is handled
-	 * later on in this routine
-	 */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-		!test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
-
 	/* look for blocks to read/compute, skip this if a compute
 	 * is already in flight, or if the stripe contents are in the
 	 * midst of changing due to a write
 	 */
-	if (!test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
-		!test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+	    !sh->reconstruct_state)
 		for (i = disks; i--; )
-			if (__handle_issuing_new_read_requests5(
-				sh, s, i, disks) == 0)
+			if (fetch_block5(sh, s, i, disks))
 				break;
-	}
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
-static void handle_issuing_new_read_requests6(struct stripe_head *sh,
+static void handle_stripe_fill6(struct stripe_head *sh,
 			struct stripe_head_state *s, struct r6_state *r6s,
 			int disks)
 {
@@ -2121,12 +2007,12 @@ static void handle_issuing_new_read_requests6(struct stripe_head *sh,
 }
 
 
-/* handle_completed_write_requests
+/* handle_stripe_clean_event
  * any written block on an uptodate or failed drive can be returned.
  * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
  * never LOCKED, so we don't need to test 'failed' directly.
  */
-static void handle_completed_write_requests(raid5_conf_t *conf,
+static void handle_stripe_clean_event(raid5_conf_t *conf,
 	struct stripe_head *sh, int disks, struct bio **return_bi)
 {
 	int i;
@@ -2171,7 +2057,7 @@ static void handle_completed_write_requests(raid5_conf_t *conf,
 			md_wakeup_thread(conf->mddev->thread);
 }
 
-static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
+static void handle_stripe_dirtying5(raid5_conf_t *conf,
 		struct stripe_head *sh,	struct stripe_head_state *s, int disks)
 {
 	int rmw = 0, rcw = 0, i;
@@ -2215,9 +2101,6 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
 						"%d for r-m-w\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
-					if (!test_and_set_bit(
-						STRIPE_OP_IO, &sh->ops.pending))
-						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);
@@ -2241,9 +2124,6 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
 						"%d for Reconstruct\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
-					if (!test_and_set_bit(
-						STRIPE_OP_IO, &sh->ops.pending))
-						sh->ops.count++;
 					s->locked++;
 				} else {
 					set_bit(STRIPE_DELAYED, &sh->state);
@@ -2261,14 +2141,13 @@ static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
 	 * simultaneously.  If this is not the case then new writes need to be
 	 * held off until the compute completes.
 	 */
-	if ((s->req_compute ||
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) &&
-		(s->locked == 0 && (rcw == 0 || rmw == 0) &&
-		!test_bit(STRIPE_BIT_DELAY, &sh->state)))
-		s->locked += handle_write_operations5(sh, rcw == 0, 0);
+	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+	    (s->locked == 0 && (rcw == 0 || rmw == 0) &&
+	    !test_bit(STRIPE_BIT_DELAY, &sh->state)))
+		schedule_reconstruction5(sh, s, rcw == 0, 0);
 }
 
-static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
+static void handle_stripe_dirtying6(raid5_conf_t *conf,
 		struct stripe_head *sh,	struct stripe_head_state *s,
 		struct r6_state *r6s, int disks)
 {
@@ -2371,92 +2250,86 @@ static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
 static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks)
 {
-	int canceled_check = 0;
+	struct r5dev *dev = NULL;
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 
-	/* complete a check operation */
-	if (test_and_clear_bit(STRIPE_OP_CHECK, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_CHECK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_CHECK, &sh->ops.pending);
+	switch (sh->check_state) {
+	case check_state_idle:
+		/* start a new check operation if there are no failures */
 		if (s->failed == 0) {
-			if (sh->ops.zero_sum_result == 0)
-				/* parity is correct (on disc,
-				 * not in buffer any more)
-				 */
-				set_bit(STRIPE_INSYNC, &sh->state);
-			else {
-				conf->mddev->resync_mismatches +=
-					STRIPE_SECTORS;
-				if (test_bit(
-				     MD_RECOVERY_CHECK, &conf->mddev->recovery))
-					/* don't try to repair!! */
-					set_bit(STRIPE_INSYNC, &sh->state);
-				else {
-					set_bit(STRIPE_OP_COMPUTE_BLK,
-						&sh->ops.pending);
-					set_bit(STRIPE_OP_MOD_REPAIR_PD,
-						&sh->ops.pending);
-					set_bit(R5_Wantcompute,
-						&sh->dev[sh->pd_idx].flags);
-					sh->ops.target = sh->pd_idx;
-					sh->ops.count++;
-					s->uptodate++;
-				}
-			}
-		} else
-			canceled_check = 1; /* STRIPE_INSYNC is not set */
-	}
-
-	/* start a new check operation if there are no failures, the stripe is
-	 * not insync, and a repair is not in flight
-	 */
-	if (s->failed == 0 &&
-	    !test_bit(STRIPE_INSYNC, &sh->state) &&
-	    !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-		if (!test_and_set_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
 			BUG_ON(s->uptodate != disks);
+			sh->check_state = check_state_run;
+			set_bit(STRIPE_OP_CHECK, &s->ops_request);
 			clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
-			sh->ops.count++;
 			s->uptodate--;
+			break;
 		}
-	}
-
-	/* check if we can clear a parity disk reconstruct */
-	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
-	    test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
-
-		clear_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
-		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
-	}
-
+		dev = &sh->dev[s->failed_num];
+		/* fall through */
+	case check_state_compute_result:
+		sh->check_state = check_state_idle;
+		if (!dev)
+			dev = &sh->dev[sh->pd_idx];
+
+		/* check that a write has not made the stripe insync */
+		if (test_bit(STRIPE_INSYNC, &sh->state))
+			break;
 
-	/* Wait for check parity and compute block operations to complete
-	 * before write-back.  If a failure occurred while the check operation
-	 * was in flight we need to cycle this stripe through handle_stripe
-	 * since the parity block may not be uptodate
-	 */
-	if (!canceled_check && !test_bit(STRIPE_INSYNC, &sh->state) &&
-	    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending) &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) {
-		struct r5dev *dev;
 		/* either failed parity check, or recovery is happening */
-		if (s->failed == 0)
-			s->failed_num = sh->pd_idx;
-		dev = &sh->dev[s->failed_num];
 		BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
 		BUG_ON(s->uptodate != disks);
 
 		set_bit(R5_LOCKED, &dev->flags);
+		s->locked++;
 		set_bit(R5_Wantwrite, &dev->flags);
-		if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-			sh->ops.count++;
 
 		clear_bit(STRIPE_DEGRADED, &sh->state);
-		s->locked++;
 		set_bit(STRIPE_INSYNC, &sh->state);
+		break;
+	case check_state_run:
+		break; /* we will be called again upon completion */
+	case check_state_check_result:
+		sh->check_state = check_state_idle;
+
+		/* if a failure occurred during the check operation, leave
+		 * STRIPE_INSYNC not set and let the stripe be handled again
+		 */
+		if (s->failed)
+			break;
+
+		/* handle a successful check operation, if parity is correct
+		 * we are done.  Otherwise update the mismatch count and repair
+		 * parity if !MD_RECOVERY_CHECK
+		 */
+		if (sh->ops.zero_sum_result == 0)
+			/* parity is correct (on disc,
+			 * not in buffer any more)
+			 */
+			set_bit(STRIPE_INSYNC, &sh->state);
+		else {
+			conf->mddev->resync_mismatches += STRIPE_SECTORS;
+			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+				/* don't try to repair!! */
+				set_bit(STRIPE_INSYNC, &sh->state);
+			else {
+				sh->check_state = check_state_compute_run;
+				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+				set_bit(R5_Wantcompute,
+					&sh->dev[sh->pd_idx].flags);
+				sh->ops.target = sh->pd_idx;
+				s->uptodate++;
+			}
+		}
+		break;
+	case check_state_compute_run:
+		break;
+	default:
+		printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+		       __func__, sh->check_state,
+		       (unsigned long long) sh->sector);
+		BUG();
 	}
 }
 
@@ -2641,15 +2514,14 @@ static void handle_stripe5(struct stripe_head *sh)
 	struct bio *return_bi = NULL;
 	struct stripe_head_state s;
 	struct r5dev *dev;
-	unsigned long pending = 0;
 	mdk_rdev_t *blocked_rdev = NULL;
 	int prexor;
 
 	memset(&s, 0, sizeof(s));
-	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
-		"ops=%lx:%lx:%lx\n", (unsigned long long)sh->sector, sh->state,
-		atomic_read(&sh->count), sh->pd_idx,
-		sh->ops.pending, sh->ops.ack, sh->ops.complete);
+	pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
+		 "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state,
+		 atomic_read(&sh->count), sh->pd_idx, sh->check_state,
+		 sh->reconstruct_state);
 
 	spin_lock(&sh->lock);
 	clear_bit(STRIPE_HANDLE, &sh->state);
@@ -2658,15 +2530,8 @@ static void handle_stripe5(struct stripe_head *sh)
 	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
 	s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
-	/* Now to look around and see what can be done */
-
-	/* clean-up completed biofill operations */
-	if (test_bit(STRIPE_OP_BIOFILL, &sh->ops.complete)) {
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIOFILL, &sh->ops.complete);
-	}
 
+	/* Now to look around and see what can be done */
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
@@ -2680,10 +2545,10 @@ static void handle_stripe5(struct stripe_head *sh)
 		/* maybe we can request a biofill operation
 		 *
 		 * new wantfill requests are only permitted while
-		 * STRIPE_OP_BIOFILL is clear
+		 * ops_complete_biofill is guaranteed to be inactive
 		 */
 		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
-			!test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+		    !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
 			set_bit(R5_Wantfill, &dev->flags);
 
 		/* now count some things */
@@ -2727,8 +2592,10 @@ static void handle_stripe5(struct stripe_head *sh)
 		goto unlock;
 	}
 
-	if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
-		sh->ops.count++;
+	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+		set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+		set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+	}
 
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 		" to_write=%d failed=%d failed_num=%d\n",
@@ -2738,8 +2605,7 @@ static void handle_stripe5(struct stripe_head *sh)
 	 * need to be failed
 	 */
 	if (s.failed > 1 && s.to_read+s.to_write+s.written)
-		handle_requests_to_failed_array(conf, sh, &s, disks,
-						&return_bi);
+		handle_failed_stripe(conf, sh, &s, disks, &return_bi);
 	if (s.failed > 1 && s.syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
 		clear_bit(STRIPE_SYNCING, &sh->state);
@@ -2755,48 +2621,25 @@ static void handle_stripe5(struct stripe_head *sh)
 	       !test_bit(R5_LOCKED, &dev->flags) &&
 	       test_bit(R5_UPTODATE, &dev->flags)) ||
 	       (s.failed == 1 && s.failed_num == sh->pd_idx)))
-		handle_completed_write_requests(conf, sh, disks, &return_bi);
+		handle_stripe_clean_event(conf, sh, disks, &return_bi);
 
 	/* Now we might consider reading some blocks, either to check/generate
 	 * parity, or to satisfy requests
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite ||
-	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding ||
-	    test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
-		handle_issuing_new_read_requests5(sh, &s, disks);
+	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
+		handle_stripe_fill5(sh, &s, disks);
 
 	/* Now we check to see if any write operations have recently
 	 * completed
 	 */
-
-	/* leave prexor set until postxor is done, allows us to distinguish
-	 * a rmw from a rcw during biodrain
-	 */
 	prexor = 0;
-	if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
 		prexor = 1;
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-
-		for (i = disks; i--; )
-			clear_bit(R5_Wantprexor, &sh->dev[i].flags);
-	}
-
-	/* if only POSTXOR is set then this is an 'expand' postxor */
-	if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) &&
-		test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack);
-		clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+	if (sh->reconstruct_state == reconstruct_state_drain_result ||
+	    sh->reconstruct_state == reconstruct_state_prexor_drain_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
 
 		/* All the 'written' buffers and the parity block are ready to
 		 * be written back to disk
@@ -2808,9 +2651,6 @@ static void handle_stripe5(struct stripe_head *sh)
 				(i == sh->pd_idx || dev->written)) {
 				pr_debug("Writing block %d\n", i);
 				set_bit(R5_Wantwrite, &dev->flags);
-				if (!test_and_set_bit(
-				    STRIPE_OP_IO, &sh->ops.pending))
-					sh->ops.count++;
 				if (prexor)
 					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
@@ -2832,20 +2672,18 @@ static void handle_stripe5(struct stripe_head *sh)
 	 * 2/ A 'check' operation is in flight, as it may clobber the parity
 	 *    block.
 	 */
-	if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) &&
-			  !test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
-		handle_issuing_new_write_requests5(conf, sh, &s, disks);
+	if (s.to_write && !sh->reconstruct_state && !sh->check_state)
+		handle_stripe_dirtying5(conf, sh, &s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe
 	 * Any reads will already have been scheduled, so we just see if enough
 	 * data is available.  The parity check is held off while parity
 	 * dependent operations are in flight.
 	 */
-	if ((s.syncing && s.locked == 0 &&
-	     !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
-	     !test_bit(STRIPE_INSYNC, &sh->state)) ||
-	      test_bit(STRIPE_OP_CHECK, &sh->ops.pending) ||
-	      test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending))
+	if (sh->check_state ||
+	    (s.syncing && s.locked == 0 &&
+	     !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
+	     !test_bit(STRIPE_INSYNC, &sh->state)))
 		handle_parity_checks5(conf, sh, &s, disks);
 
 	if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
@@ -2864,52 +2702,35 @@ static void handle_stripe5(struct stripe_head *sh)
 		dev = &sh->dev[s.failed_num];
 		if (!test_bit(R5_ReWrite, &dev->flags)) {
 			set_bit(R5_Wantwrite, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			set_bit(R5_ReWrite, &dev->flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		} else {
 			/* let's read it back */
 			set_bit(R5_Wantread, &dev->flags);
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
 		}
 	}
 
-	/* Finish postxor operations initiated by the expansion
-	 * process
-	 */
-	if (test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete) &&
-		!test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending)) {
-
+	/* Finish reconstruct operations initiated by the expansion process */
+	if (sh->reconstruct_state == reconstruct_state_result) {
+		sh->reconstruct_state = reconstruct_state_idle;
 		clear_bit(STRIPE_EXPANDING, &sh->state);
-
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
-		clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
-
-		for (i = conf->raid_disks; i--; ) {
+		for (i = conf->raid_disks; i--; )
 			set_bit(R5_Wantwrite, &sh->dev[i].flags);
 			set_bit(R5_LOCKED, &dev->flags);
 			s.locked++;
-			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
-				sh->ops.count++;
-		}
 	}
 
 	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+	    !sh->reconstruct_state) {
 		/* Need to write out all blocks after computing parity */
 		sh->disks = conf->raid_disks;
 		sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
 			conf->raid_disks);
-		s.locked += handle_write_operations5(sh, 1, 1);
-	} else if (s.expanded &&
-		   s.locked == 0 &&
-		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+		schedule_reconstruction5(sh, &s, 1, 1);
+	} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
 		atomic_dec(&conf->reshape_stripes);
 		wake_up(&conf->wait_for_overlap);
@@ -2917,12 +2738,9 @@ static void handle_stripe5(struct stripe_head *sh)
 	}
 
 	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
 		handle_stripe_expansion(conf, sh, NULL);
 
-	if (sh->ops.count)
-		pending = get_stripe_work(sh);
-
  unlock:
 	spin_unlock(&sh->lock);
 
@@ -2930,11 +2748,12 @@ static void handle_stripe5(struct stripe_head *sh)
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
-	if (pending)
-		raid5_run_ops(sh, pending);
+	if (s.ops_request)
+		raid5_run_ops(sh, s.ops_request);
 
-	return_io(return_bi);
+	ops_run_io(sh, &s);
 
+	return_io(return_bi);
 }
 
 static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
@@ -3042,8 +2861,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	 * might need to be failed
 	 */
 	if (s.failed > 2 && s.to_read+s.to_write+s.written)
-		handle_requests_to_failed_array(conf, sh, &s, disks,
-						&return_bi);
+		handle_failed_stripe(conf, sh, &s, disks, &return_bi);
 	if (s.failed > 2 && s.syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
 		clear_bit(STRIPE_SYNCING, &sh->state);
@@ -3068,7 +2886,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	     ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
 			     && !test_bit(R5_LOCKED, &qdev->flags)
 			     && test_bit(R5_UPTODATE, &qdev->flags)))))
-		handle_completed_write_requests(conf, sh, disks, &return_bi);
+		handle_stripe_clean_event(conf, sh, disks, &return_bi);
 
 	/* Now we might consider reading some blocks, either to check/generate
 	 * parity, or to satisfy requests
@@ -3076,11 +2894,11 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	 */
 	if (s.to_read || s.non_overwrite || (s.to_write && s.failed) ||
 	    (s.syncing && (s.uptodate < disks)) || s.expanding)
-		handle_issuing_new_read_requests6(sh, &s, &r6s, disks);
+		handle_stripe_fill6(sh, &s, &r6s, disks);
 
 	/* now to consider writing and what else, if anything should be read */
 	if (s.to_write)
-		handle_issuing_new_write_requests6(conf, sh, &s, &r6s, disks);
+		handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
 
 	/* maybe we need to check and possibly fix the parity for this stripe
 	 * Any reads will already have been scheduled, so we just see if enough
@@ -3136,7 +2954,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	}
 
 	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
 		handle_stripe_expansion(conf, sh, &r6s);
 
  unlock:
@@ -3146,68 +2964,9 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	if (unlikely(blocked_rdev))
 		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
 
-	return_io(return_bi);
-
-	for (i=disks; i-- ;) {
-		int rw;
-		struct bio *bi;
-		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
-			rw = READ;
-		else
-			continue;
-
-		set_bit(STRIPE_IO_STARTED, &sh->state);
-
-		bi = &sh->dev[i].req;
-
-		bi->bi_rw = rw;
-		if (rw == WRITE)
-			bi->bi_end_io = raid5_end_write_request;
-		else
-			bi->bi_end_io = raid5_end_read_request;
-
-		rcu_read_lock();
-		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (rdev && test_bit(Faulty, &rdev->flags))
-			rdev = NULL;
-		if (rdev)
-			atomic_inc(&rdev->nr_pending);
-		rcu_read_unlock();
+	ops_run_io(sh, &s);
 
-		if (rdev) {
-			if (s.syncing || s.expanding || s.expanded)
-				md_sync_acct(rdev->bdev, STRIPE_SECTORS);
-
-			bi->bi_bdev = rdev->bdev;
-			pr_debug("for %llu schedule op %ld on disc %d\n",
-				(unsigned long long)sh->sector, bi->bi_rw, i);
-			atomic_inc(&sh->count);
-			bi->bi_sector = sh->sector + rdev->data_offset;
-			bi->bi_flags = 1 << BIO_UPTODATE;
-			bi->bi_vcnt = 1;
-			bi->bi_max_vecs = 1;
-			bi->bi_idx = 0;
-			bi->bi_io_vec = &sh->dev[i].vec;
-			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
-			bi->bi_io_vec[0].bv_offset = 0;
-			bi->bi_size = STRIPE_SIZE;
-			bi->bi_next = NULL;
-			if (rw == WRITE &&
-			    test_bit(R5_ReWrite, &sh->dev[i].flags))
-				atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
-			generic_make_request(bi);
-		} else {
-			if (rw == WRITE)
-				set_bit(STRIPE_DEGRADED, &sh->state);
-			pr_debug("skip op %ld on disc %d for sector %llu\n",
-				bi->bi_rw, i, (unsigned long long)sh->sector);
-			clear_bit(R5_LOCKED, &sh->dev[i].flags);
-			set_bit(STRIPE_HANDLE, &sh->state);
-		}
-	}
+	return_io(return_bi);
 }
 
 static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
@@ -3697,9 +3456,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 		if ( rw == WRITE )
 			md_write_end(mddev);
 
-		bi->bi_end_io(bi,
-			      test_bit(BIO_UPTODATE, &bi->bi_flags)
-			        ? 0 : -EIO);
+		bio_endio(bi, 0);
 	}
 	return 0;
 }
@@ -3785,7 +3542,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 			    j == raid6_next_disk(sh->pd_idx, sh->disks))
 				continue;
 			s = compute_blocknr(sh, j);
-			if (s < (mddev->array_size<<1)) {
+			if (s < mddev->array_sectors) {
 				skipped = 1;
 				continue;
 			}
@@ -4002,12 +3759,8 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 	spin_lock_irq(&conf->device_lock);
 	remaining = --raid_bio->bi_phys_segments;
 	spin_unlock_irq(&conf->device_lock);
-	if (remaining == 0) {
-
-		raid_bio->bi_end_io(raid_bio,
-			      test_bit(BIO_UPTODATE, &raid_bio->bi_flags)
-			        ? 0 : -EIO);
-	}
+	if (remaining == 0)
+		bio_endio(raid_bio, 0);
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_stripe);
 	return handled;
@@ -4094,6 +3847,8 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
 	unsigned long new;
+	int err;
+
 	if (len >= PAGE_SIZE)
 		return -EINVAL;
 	if (!conf)
@@ -4109,7 +3864,9 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
 		else
 			break;
 	}
-	md_allow_write(mddev);
+	err = md_allow_write(mddev);
+	if (err)
+		return err;
 	while (new > conf->max_nr_stripes) {
 		if (grow_one_stripe(conf))
 			conf->max_nr_stripes++;
@@ -4434,7 +4191,7 @@ static int run(mddev_t *mddev)
 	mddev->queue->backing_dev_info.congested_data = mddev;
 	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
 
-	mddev->array_size =  mddev->size * (conf->previous_raid_disks -
+	mddev->array_sectors = 2 * mddev->size * (conf->previous_raid_disks -
 					    conf->max_degraded);
 
 	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
@@ -4609,35 +4366,41 @@ abort:
 static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 {
 	raid5_conf_t *conf = mddev->private;
-	int found = 0;
+	int err = -EEXIST;
 	int disk;
 	struct disk_info *p;
+	int first = 0;
+	int last = conf->raid_disks - 1;
 
 	if (mddev->degraded > conf->max_degraded)
 		/* no point adding a device */
-		return 0;
+		return -EINVAL;
+
+	if (rdev->raid_disk >= 0)
+		first = last = rdev->raid_disk;
 
 	/*
 	 * find the disk ... but prefer rdev->saved_raid_disk
 	 * if possible.
 	 */
 	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
 	    conf->disks[rdev->saved_raid_disk].rdev == NULL)
 		disk = rdev->saved_raid_disk;
 	else
-		disk = 0;
-	for ( ; disk < conf->raid_disks; disk++)
+		disk = first;
+	for ( ; disk <= last ; disk++)
 		if ((p=conf->disks + disk)->rdev == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = disk;
-			found = 1;
+			err = 0;
 			if (rdev->saved_raid_disk != disk)
 				conf->fullsync = 1;
 			rcu_assign_pointer(p->rdev, rdev);
 			break;
 		}
 	print_raid5_conf(conf);
-	return found;
+	return err;
 }
 
 static int raid5_resize(mddev_t *mddev, sector_t sectors)
@@ -4652,8 +4415,9 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 	raid5_conf_t *conf = mddev_to_conf(mddev);
 
 	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
-	mddev->array_size = (sectors * (mddev->raid_disks-conf->max_degraded))>>1;
-	set_capacity(mddev->gendisk, mddev->array_size << 1);
+	mddev->array_sectors = sectors * (mddev->raid_disks
+					  - conf->max_degraded);
+	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
 	if (sectors/2  > mddev->size && mddev->recovery_cp == MaxSector) {
 		mddev->recovery_cp = mddev->size << 1;
@@ -4738,7 +4502,7 @@ static int raid5_start_reshape(mddev_t *mddev)
 	rdev_for_each(rdev, rtmp, mddev)
 		if (rdev->raid_disk < 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
-			if (raid5_add_disk(mddev, rdev)) {
+			if (raid5_add_disk(mddev, rdev) == 0) {
 				char nm[20];
 				set_bit(In_sync, &rdev->flags);
 				added_devices++;
@@ -4786,15 +4550,16 @@ static void end_reshape(raid5_conf_t *conf)
 	struct block_device *bdev;
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
-		conf->mddev->array_size = conf->mddev->size *
+		conf->mddev->array_sectors = 2 * conf->mddev->size *
 			(conf->raid_disks - conf->max_degraded);
-		set_capacity(conf->mddev->gendisk, conf->mddev->array_size << 1);
+		set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors);
 		conf->mddev->changed = 1;
 
 		bdev = bdget_disk(conf->mddev->gendisk, 0);
 		if (bdev) {
 			mutex_lock(&bdev->bd_inode->i_mutex);
-			i_size_write(bdev->bd_inode, (loff_t)conf->mddev->array_size << 10);
+			i_size_write(bdev->bd_inode,
+				     (loff_t)conf->mddev->array_sectors << 9);
 			mutex_unlock(&bdev->bd_inode->i_mutex);
 			bdput(bdev);
 		}