Merge remote-tracking branch 'md/for-next'

4 files changed, 251 insertions, 616 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4332fc2f25d4..91e31e260b4a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7088,6 +7088,7 @@ static int remove_and_add_spares(mddev_t *mddev)
 		list_for_each_entry(rdev, &mddev->disks, same_set) {
 			if (rdev->raid_disk >= 0 &&
 			    !test_bit(In_sync, &rdev->flags) &&
+			    !test_bit(Faulty, &rdev->flags) &&
 			    !test_bit(Blocked, &rdev->flags))
 				spares++;
 			if (rdev->raid_disk < 0
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6e846688962f..3715e220e5e0 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -123,7 +123,14 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
 	for (j = 0 ; j < nalloc; j++) {
 		bio = r10_bio->devs[j].bio;
 		for (i = 0; i < RESYNC_PAGES; i++) {
-			page = alloc_page(gfp_flags);
+			if (j == 1 && !test_bit(MD_RECOVERY_SYNC,
+						&conf->mddev->recovery)) {
+				/* we can share bv_page's during recovery */
+				struct bio *rbio = r10_bio->devs[0].bio;
+				page = rbio->bi_io_vec[i].bv_page;
+				get_page(page);
+			} else
+				page = alloc_page(gfp_flags);
 			if (unlikely(!page))
 				goto out_free_pages;
 
@@ -244,6 +251,23 @@ static inline void update_head_pos(int slot, r10bio_t *r10_bio)
 		r10_bio->devs[slot].addr + (r10_bio->sectors);
 }
 
+/*
+ * Find the disk number which triggered given bio
+ */
+static int find_bio_disk(conf_t *conf, r10bio_t *r10_bio, struct bio *bio)
+{
+	int slot;
+
+	for (slot = 0; slot < conf->copies; slot++)
+		if (r10_bio->devs[slot].bio == bio)
+			break;
+
+	BUG_ON(slot == conf->copies);
+	update_head_pos(slot, r10_bio);
+
+	return r10_bio->devs[slot].devnum;
+}
+
 static void raid10_end_read_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -289,13 +313,10 @@ static void raid10_end_write_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	r10bio_t *r10_bio = bio->bi_private;
-	int slot, dev;
+	int dev;
 	conf_t *conf = r10_bio->mddev->private;
 
-	for (slot = 0; slot < conf->copies; slot++)
-		if (r10_bio->devs[slot].bio == bio)
-			break;
-	dev = r10_bio->devs[slot].devnum;
+	dev = find_bio_disk(conf, r10_bio, bio);
 
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
@@ -316,8 +337,6 @@ static void raid10_end_write_request(struct bio *bio, int error)
 		 */
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
 
-	update_head_pos(slot, r10_bio);
-
 	/*
 	 *
 	 * Let's see if all mirrored write operations have finished
@@ -1093,8 +1112,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
-	if (rdev->saved_raid_disk >= 0 &&
-	    rdev->saved_raid_disk >= first &&
+	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
 	else
@@ -1174,14 +1192,9 @@ static void end_sync_read(struct bio *bio, int error)
 {
 	r10bio_t *r10_bio = bio->bi_private;
 	conf_t *conf = r10_bio->mddev->private;
-	int i,d;
+	int d;
 
-	for (i=0; i<conf->copies; i++)
-		if (r10_bio->devs[i].bio == bio)
-			break;
-	BUG_ON(i == conf->copies);
-	update_head_pos(i, r10_bio);
-	d = r10_bio->devs[i].devnum;
+	d = find_bio_disk(conf, r10_bio, bio);
 
 	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
@@ -1212,18 +1225,13 @@ static void end_sync_write(struct bio *bio, int error)
 	r10bio_t *r10_bio = bio->bi_private;
 	mddev_t *mddev = r10_bio->mddev;
 	conf_t *conf = mddev->private;
-	int i,d;
+	int d;
 
-	for (i = 0; i < conf->copies; i++)
-		if (r10_bio->devs[i].bio == bio)
-			break;
-	d = r10_bio->devs[i].devnum;
+	d = find_bio_disk(conf, r10_bio, bio);
 
 	if (!uptodate)
 		md_error(mddev, conf->mirrors[d].rdev);
 
-	update_head_pos(i, r10_bio);
-
 	rdev_dec_pending(conf->mirrors[d].rdev, mddev);
 	while (atomic_dec_and_test(&r10_bio->remaining)) {
 		if (r10_bio->master_bio == NULL) {
@@ -1359,20 +1367,14 @@ done:
 static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio)
 {
 	conf_t *conf = mddev->private;
-	int i, d;
-	struct bio *bio, *wbio;
+	int d;
+	struct bio *wbio;
 
-
-	/* move the pages across to the second bio
+	/*
+	 * share the pages with the first bio
 	 * and submit the write request
 	 */
-	bio = r10_bio->devs[0].bio;
 	wbio = r10_bio->devs[1].bio;
-	for (i=0; i < wbio->bi_vcnt; i++) {
-		struct page *p = bio->bi_io_vec[i].bv_page;
-		bio->bi_io_vec[i].bv_page = wbio->bi_io_vec[i].bv_page;
-		wbio->bi_io_vec[i].bv_page = p;
-	}
 	d = r10_bio->devs[1].devnum;
 
 	atomic_inc(&conf->mirrors[d].rdev->nr_pending);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b72edf35ec54..82c07fb38961 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1020,12 +1020,12 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 		if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
 			struct bio *wbi;
 
-			spin_lock(&sh->lock);
+			spin_lock_irq(&sh->raid_conf->device_lock);
 			chosen = dev->towrite;
 			dev->towrite = NULL;
 			BUG_ON(dev->written);
 			wbi = dev->written = chosen;
-			spin_unlock(&sh->lock);
+			spin_unlock_irq(&sh->raid_conf->device_lock);
 
 			while (wbi && wbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
@@ -1315,12 +1315,11 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 static int grow_one_stripe(raid5_conf_t *conf)
 {
 	struct stripe_head *sh;
-	sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
+	sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL);
 	if (!sh)
 		return 0;
-	memset(sh, 0, sizeof(*sh) + (conf->pool_size-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
@@ -1435,14 +1434,11 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 		return -ENOMEM;
 
 	for (i = conf->max_nr_stripes; i; i--) {
-		nsh = kmem_cache_alloc(sc, GFP_KERNEL);
+		nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
 		if (!nsh)
 			break;
 
-		memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev));
-
 		nsh->raid_conf = conf;
-		spin_lock_init(&nsh->lock);
 		#ifdef CONFIG_MULTICORE_RAID456
 		init_waitqueue_head(&nsh->ops.wait_for_ops);
 		#endif
@@ -1760,7 +1756,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
 	/*
 	 * Select the parity disk based on the user selected algorithm.
 	 */
-	pd_idx = qd_idx = ~0;
+	pd_idx = qd_idx = -1;
 	switch(conf->level) {
 	case 4:
 		pd_idx = data_disks;
@@ -2148,7 +2144,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		(unsigned long long)sh->sector);
 
 
-	spin_lock(&sh->lock);
 	spin_lock_irq(&conf->device_lock);
 	if (forwrite) {
 		bip = &sh->dev[dd_idx].towrite;
@@ -2169,19 +2164,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		bi->bi_next = *bip;
 	*bip = bi;
 	bi->bi_phys_segments++;
-	spin_unlock_irq(&conf->device_lock);
-	spin_unlock(&sh->lock);
-
-	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
-		(unsigned long long)bi->bi_sector,
-		(unsigned long long)sh->sector, dd_idx);
-
-	if (conf->mddev->bitmap && firstwrite) {
-		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
-				  STRIPE_SECTORS, 0);
-		sh->bm_seq = conf->seq_flush+1;
-		set_bit(STRIPE_BIT_DELAY, &sh->state);
-	}
 
 	if (forwrite) {
 		/* check if page is covered */
@@ -2196,12 +2178,23 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
 			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
 	}
+	spin_unlock_irq(&conf->device_lock);
+
+	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
+		(unsigned long long)bi->bi_sector,
+		(unsigned long long)sh->sector, dd_idx);
+
+	if (conf->mddev->bitmap && firstwrite) {
+		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
+				  STRIPE_SECTORS, 0);
+		sh->bm_seq = conf->seq_flush+1;
+		set_bit(STRIPE_BIT_DELAY, &sh->state);
+	}
 	return 1;
 
  overlap:
 	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
 	spin_unlock_irq(&conf->device_lock);
-	spin_unlock(&sh->lock);
 	return 0;
 }
 
@@ -2315,17 +2308,18 @@ handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
 			md_wakeup_thread(conf->mddev->thread);
 }
 
-/* fetch_block5 - checks the given member device to see if its data needs
+/* fetch_block - 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
+ * 0 to tell the loop in handle_stripe_fill to continue
  */
-static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s,
-			int disk_idx, int disks)
+static int fetch_block(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];
+	struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
+				  &sh->dev[s->failed_num[1]] };
 
 	/* is the data in this block needed, and can we get it? */
 	if (!test_bit(R5_LOCKED, &dev->flags) &&
@@ -2333,91 +2327,19 @@ static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s,
 	    (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)) {
-			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;
-			sh->ops.target2 = -1;
-			s->req_compute = 1;
-			/* Careful: from this point on 'uptodate' is in the eye
-			 * of raid_run_ops which services 'compute' operations
-			 * before writes. R5_Wantcompute flags a block that will
-			 * be R5_UPTODATE by the time it is needed for a
-			 * subsequent operation.
-			 */
-			s->uptodate++;
-			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);
-			s->locked++;
-			pr_debug("Reading block %d (sync=%d)\n", disk_idx,
-				s->syncing);
-		}
-	}
-
-	return 0;
-}
-
-/**
- * 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;
-
-	/* 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_COMPUTE_RUN, &sh->state) && !sh->check_state &&
-	    !sh->reconstruct_state)
-		for (i = disks; i--; )
-			if (fetch_block5(sh, s, i, disks))
-				break;
-	set_bit(STRIPE_HANDLE, &sh->state);
-}
-
-/* fetch_block6 - 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_fill6 to continue
- */
-static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
-			 struct r6_state *r6s, int disk_idx, int disks)
-{
-	struct r5dev *dev = &sh->dev[disk_idx];
-	struct r5dev *fdev[2] = { &sh->dev[r6s->failed_num[0]],
-				  &sh->dev[r6s->failed_num[1]] };
-
-	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 >= 1 &&
-	      (fdev[0]->toread || s->to_write)) ||
-	     (s->failed >= 2 &&
-	      (fdev[1]->toread || s->to_write)))) {
+	     (s->failed >= 1 && fdev[0]->toread) ||
+	     (s->failed >= 2 && fdev[1]->toread) ||
+	     (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
+	      !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
+	     (sh->raid_conf->level == 6 && s->failed && s->to_write))) {
 		/* we would like to get this block, possibly by computing it,
 		 * otherwise read it if the backing disk is insync
 		 */
 		BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
 		BUG_ON(test_bit(R5_Wantread, &dev->flags));
 		if ((s->uptodate == disks - 1) &&
-		    (s->failed && (disk_idx == r6s->failed_num[0] ||
-				   disk_idx == r6s->failed_num[1]))) {
+		    (s->failed && (disk_idx == s->failed_num[0] ||
+				   disk_idx == s->failed_num[1]))) {
 			/* have disk failed, and we're requested to fetch it;
 			 * do compute it
 			 */
@@ -2429,6 +2351,12 @@ static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
 			sh->ops.target = disk_idx;
 			sh->ops.target2 = -1; /* no 2nd target */
 			s->req_compute = 1;
+			/* Careful: from this point on 'uptodate' is in the eye
+			 * of raid_run_ops which services 'compute' operations
+			 * before writes. R5_Wantcompute flags a block that will
+			 * be R5_UPTODATE by the time it is needed for a
+			 * subsequent operation.
+			 */
 			s->uptodate++;
 			return 1;
 		} else if (s->uptodate == disks-2 && s->failed >= 2) {
@@ -2469,11 +2397,11 @@ static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
 }
 
 /**
- * handle_stripe_fill6 - read or compute data to satisfy pending requests.
+ * handle_stripe_fill - read or compute data to satisfy pending requests.
  */
-static void handle_stripe_fill6(struct stripe_head *sh,
-			struct stripe_head_state *s, struct r6_state *r6s,
-			int disks)
+static void handle_stripe_fill(struct stripe_head *sh,
+			       struct stripe_head_state *s,
+			       int disks)
 {
 	int i;
 
@@ -2484,7 +2412,7 @@ static void handle_stripe_fill6(struct stripe_head *sh,
 	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
 	    !sh->reconstruct_state)
 		for (i = disks; i--; )
-			if (fetch_block6(sh, s, r6s, i, disks))
+			if (fetch_block(sh, s, i, disks))
 				break;
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
@@ -2540,11 +2468,19 @@ static void handle_stripe_clean_event(raid5_conf_t *conf,
 			md_wakeup_thread(conf->mddev->thread);
 }
 
-static void handle_stripe_dirtying5(raid5_conf_t *conf,
-		struct stripe_head *sh,	struct stripe_head_state *s, int disks)
+static void handle_stripe_dirtying(raid5_conf_t *conf,
+				   struct stripe_head *sh,
+				   struct stripe_head_state *s,
+				   int disks)
 {
 	int rmw = 0, rcw = 0, i;
-	for (i = disks; i--; ) {
+	if (conf->max_degraded == 2) {
+		/* RAID6 requires 'rcw' in current implementation
+		 * Calculate the real rcw later - for now fake it
+		 * look like rcw is cheaper
+		 */
+		rcw = 1; rmw = 2;
+	} else for (i = disks; i--; ) {
 		/* would I have to read this buffer for read_modify_write */
 		struct r5dev *dev = &sh->dev[i];
 		if ((dev->towrite || i == sh->pd_idx) &&
@@ -2591,16 +2527,19 @@ static void handle_stripe_dirtying5(raid5_conf_t *conf,
 				}
 			}
 		}
-	if (rcw <= rmw && rcw > 0)
+	if (rcw <= rmw && rcw > 0) {
 		/* want reconstruct write, but need to get some data */
+		rcw = 0;
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 			if (!test_bit(R5_OVERWRITE, &dev->flags) &&
-			    i != sh->pd_idx &&
+			    i != sh->pd_idx && i != sh->qd_idx &&
 			    !test_bit(R5_LOCKED, &dev->flags) &&
 			    !(test_bit(R5_UPTODATE, &dev->flags) ||
-			    test_bit(R5_Wantcompute, &dev->flags)) &&
-			    test_bit(R5_Insync, &dev->flags)) {
+			      test_bit(R5_Wantcompute, &dev->flags))) {
+				rcw++;
+				if (!test_bit(R5_Insync, &dev->flags))
+					continue; /* it's a failed drive */
 				if (
 				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 					pr_debug("Read_old block "
@@ -2614,6 +2553,7 @@ static void handle_stripe_dirtying5(raid5_conf_t *conf,
 				}
 			}
 		}
+	}
 	/* now if nothing is locked, and if we have enough data,
 	 * we can start a write request
 	 */
@@ -2630,53 +2570,6 @@ static void handle_stripe_dirtying5(raid5_conf_t *conf,
 		schedule_reconstruction(sh, s, rcw == 0, 0);
 }
 
-static void handle_stripe_dirtying6(raid5_conf_t *conf,
-		struct stripe_head *sh,	struct stripe_head_state *s,
-		struct r6_state *r6s, int disks)
-{
-	int rcw = 0, pd_idx = sh->pd_idx, i;
-	int qd_idx = sh->qd_idx;
-
-	set_bit(STRIPE_HANDLE, &sh->state);
-	for (i = disks; i--; ) {
-		struct r5dev *dev = &sh->dev[i];
-		/* check if we haven't enough data */
-		if (!test_bit(R5_OVERWRITE, &dev->flags) &&
-		    i != pd_idx && i != qd_idx &&
-		    !test_bit(R5_LOCKED, &dev->flags) &&
-		    !(test_bit(R5_UPTODATE, &dev->flags) ||
-		      test_bit(R5_Wantcompute, &dev->flags))) {
-			rcw++;
-			if (!test_bit(R5_Insync, &dev->flags))
-				continue; /* it's a failed drive */
-
-			if (
-			  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-				pr_debug("Read_old stripe %llu "
-					"block %d for Reconstruct\n",
-				     (unsigned long long)sh->sector, i);
-				set_bit(R5_LOCKED, &dev->flags);
-				set_bit(R5_Wantread, &dev->flags);
-				s->locked++;
-			} else {
-				pr_debug("Request delayed stripe %llu "
-					"block %d for Reconstruct\n",
-				     (unsigned long long)sh->sector, i);
-				set_bit(STRIPE_DELAYED, &sh->state);
-				set_bit(STRIPE_HANDLE, &sh->state);
-			}
-		}
-	}
-	/* now if nothing is locked, and if we have enough data, we can start a
-	 * write request
-	 */
-	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
-	    s->locked == 0 && rcw == 0 &&
-	    !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
-		schedule_reconstruction(sh, s, 1, 0);
-	}
-}
-
 static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 				struct stripe_head_state *s, int disks)
 {
@@ -2695,7 +2588,7 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 			s->uptodate--;
 			break;
 		}
-		dev = &sh->dev[s->failed_num];
+		dev = &sh->dev[s->failed_num[0]];
 		/* fall through */
 	case check_state_compute_result:
 		sh->check_state = check_state_idle;
@@ -2767,7 +2660,7 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
 
 static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 				  struct stripe_head_state *s,
-				  struct r6_state *r6s, int disks)
+				  int disks)
 {
 	int pd_idx = sh->pd_idx;
 	int qd_idx = sh->qd_idx;
@@ -2786,14 +2679,14 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 	switch (sh->check_state) {
 	case check_state_idle:
 		/* start a new check operation if there are < 2 failures */
-		if (s->failed == r6s->q_failed) {
+		if (s->failed == s->q_failed) {
 			/* The only possible failed device holds Q, so it
 			 * makes sense to check P (If anything else were failed,
 			 * we would have used P to recreate it).
 			 */
 			sh->check_state = check_state_run;
 		}
-		if (!r6s->q_failed && s->failed < 2) {
+		if (!s->q_failed && s->failed < 2) {
 			/* Q is not failed, and we didn't use it to generate
 			 * anything, so it makes sense to check it
 			 */
@@ -2835,13 +2728,13 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 		 */
 		BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
 		if (s->failed == 2) {
-			dev = &sh->dev[r6s->failed_num[1]];
+			dev = &sh->dev[s->failed_num[1]];
 			s->locked++;
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantwrite, &dev->flags);
 		}
 		if (s->failed >= 1) {
-			dev = &sh->dev[r6s->failed_num[0]];
+			dev = &sh->dev[s->failed_num[0]];
 			s->locked++;
 			set_bit(R5_LOCKED, &dev->flags);
 			set_bit(R5_Wantwrite, &dev->flags);
@@ -2929,7 +2822,7 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 }
 
 static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
-				struct r6_state *r6s)
+				    struct stripe_head_state *r6s)
 {
 	int i;
 
@@ -2971,7 +2864,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 			set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
 			for (j = 0; j < conf->raid_disks; j++)
 				if (j != sh2->pd_idx &&
-				    (!r6s || j != sh2->qd_idx) &&
+				    (r6s || j != sh2->qd_idx) &&
 				    !test_bit(R5_Expanded, &sh2->dev[j].flags))
 					break;
 			if (j == conf->raid_disks) {
@@ -3006,43 +2899,24 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
  *
  */
 
-static void handle_stripe5(struct stripe_head *sh)
+static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 {
 	raid5_conf_t *conf = sh->raid_conf;
-	int disks = sh->disks, i;
-	struct bio *return_bi = NULL;
-	struct stripe_head_state s;
+	int disks = sh->disks;
 	struct r5dev *dev;
-	mdk_rdev_t *blocked_rdev = NULL;
-	int prexor;
-	int dec_preread_active = 0;
-
-	memset(&s, 0, sizeof(s));
-	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);
-	clear_bit(STRIPE_DELAYED, &sh->state);
-
-	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);
+	int i;
 
 	/* Now to look around and see what can be done */
 	rcu_read_lock();
+	spin_lock_irq(&conf->device_lock);
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
 
 		dev = &sh->dev[i];
 
-		pr_debug("check %d: state 0x%lx toread %p read %p write %p "
-			"written %p\n",	i, dev->flags, dev->toread, dev->read,
-			dev->towrite, dev->written);
-
-		/* maybe we can request a biofill operation
+		pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
+			i, dev->flags, dev->toread, dev->towrite, dev->written);
+		/* maybe we can reply to a read
 		 *
 		 * new wantfill requests are only permitted while
 		 * ops_complete_biofill is guaranteed to be inactive
@@ -3052,25 +2926,30 @@ static void handle_stripe5(struct stripe_head *sh)
 			set_bit(R5_Wantfill, &dev->flags);
 
 		/* 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)) s.compute++;
+		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)) {
+			s->compute++;
+			BUG_ON(s->compute > 2);
+		}
 
 		if (test_bit(R5_Wantfill, &dev->flags))
-			s.to_fill++;
+			s->to_fill++;
 		else if (dev->toread)
-			s.to_read++;
+			s->to_read++;
 		if (dev->towrite) {
-			s.to_write++;
+			s->to_write++;
 			if (!test_bit(R5_OVERWRITE, &dev->flags))
-				s.non_overwrite++;
+				s->non_overwrite++;
 		}
 		if (dev->written)
-			s.written++;
+			s->written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (blocked_rdev == NULL &&
+		if (s->blocked_rdev == NULL &&
 		    rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			blocked_rdev = rdev;
+			s->blocked_rdev = rdev;
 			atomic_inc(&rdev->nr_pending);
 		}
 		clear_bit(R5_Insync, &dev->flags);
@@ -3079,7 +2958,7 @@ static void handle_stripe5(struct stripe_head *sh)
 		else if (test_bit(In_sync, &rdev->flags))
 			set_bit(R5_Insync, &dev->flags);
 		else {
-			/* could be in-sync depending on recovery/reshape status */
+			/* in sync if before recovery_offset */
 			if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
 				set_bit(R5_Insync, &dev->flags);
 		}
@@ -3091,313 +2970,62 @@ static void handle_stripe5(struct stripe_head *sh)
 		if (test_bit(R5_ReadError, &dev->flags))
 			clear_bit(R5_Insync, &dev->flags);
 		if (!test_bit(R5_Insync, &dev->flags)) {
-			s.failed++;
-			s.failed_num = i;
+			if (s->failed < 2)
+				s->failed_num[s->failed] = i;
+			s->failed++;
 		}
 	}
+	spin_unlock_irq(&conf->device_lock);
 	rcu_read_unlock();
-
-	if (unlikely(blocked_rdev)) {
-		if (s.syncing || s.expanding || s.expanded ||
-		    s.to_write || s.written) {
-			set_bit(STRIPE_HANDLE, &sh->state);
-			goto unlock;
-		}
-		/* There is nothing for the blocked_rdev to block */
-		rdev_dec_pending(blocked_rdev, conf->mddev);
-		blocked_rdev = NULL;
-	}
-
-	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",
-		s.locked, s.uptodate, s.to_read, s.to_write,
-		s.failed, s.failed_num);
-	/* check if the array has lost two devices and, if so, some requests might
-	 * need to be failed
-	 */
-	if (s.failed > 1 && s.to_read+s.to_write+s.written)
-		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);
-		s.syncing = 0;
-	}
-
-	/* might be able to return some write requests if the parity block
-	 * is safe, or on a failed drive
-	 */
-	dev = &sh->dev[sh->pd_idx];
-	if ( s.written &&
-	     ((test_bit(R5_Insync, &dev->flags) &&
-	       !test_bit(R5_LOCKED, &dev->flags) &&
-	       test_bit(R5_UPTODATE, &dev->flags)) ||
-	       (s.failed == 1 && s.failed_num == sh->pd_idx)))
-		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)
-		handle_stripe_fill5(sh, &s, disks);
-
-	/* Now we check to see if any write operations have recently
-	 * completed
-	 */
-	prexor = 0;
-	if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
-		prexor = 1;
-	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
-		 */
-		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
-		for (i = disks; i--; ) {
-			dev = &sh->dev[i];
-			if (test_bit(R5_LOCKED, &dev->flags) &&
-				(i == sh->pd_idx || dev->written)) {
-				pr_debug("Writing block %d\n", i);
-				set_bit(R5_Wantwrite, &dev->flags);
-				if (prexor)
-					continue;
-				if (!test_bit(R5_Insync, &dev->flags) ||
-				    (i == sh->pd_idx && s.failed == 0))
-					set_bit(STRIPE_INSYNC, &sh->state);
-			}
-		}
-		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
-			dec_preread_active = 1;
-	}
-
-	/* Now to consider new write requests and what else, if anything
-	 * should be read.  We do not handle new writes when:
-	 * 1/ A 'write' operation (copy+xor) is already in flight.
-	 * 2/ A 'check' operation is in flight, as it may clobber the parity
-	 *    block.
-	 */
-	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 (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)) {
-		md_done_sync(conf->mddev, STRIPE_SECTORS,1);
-		clear_bit(STRIPE_SYNCING, &sh->state);
-	}
-
-	/* If the failed drive is just a ReadError, then we might need to progress
-	 * the repair/check process
-	 */
-	if (s.failed == 1 && !conf->mddev->ro &&
-	    test_bit(R5_ReadError, &sh->dev[s.failed_num].flags)
-	    && !test_bit(R5_LOCKED, &sh->dev[s.failed_num].flags)
-	    && test_bit(R5_UPTODATE, &sh->dev[s.failed_num].flags)
-		) {
-		dev = &sh->dev[s.failed_num];
-		if (!test_bit(R5_ReWrite, &dev->flags)) {
-			set_bit(R5_Wantwrite, &dev->flags);
-			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);
-			set_bit(R5_LOCKED, &dev->flags);
-			s.locked++;
-		}
-	}
-
-	/* Finish reconstruct operations initiated by the expansion process */
-	if (sh->reconstruct_state == reconstruct_state_result) {
-		struct stripe_head *sh2
-			= get_active_stripe(conf, sh->sector, 1, 1, 1);
-		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
-			/* sh cannot be written until sh2 has been read.
-			 * so arrange for sh to be delayed a little
-			 */
-			set_bit(STRIPE_DELAYED, &sh->state);
-			set_bit(STRIPE_HANDLE, &sh->state);
-			if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
-					      &sh2->state))
-				atomic_inc(&conf->preread_active_stripes);
-			release_stripe(sh2);
-			goto unlock;
-		}
-		if (sh2)
-			release_stripe(sh2);
-
-		sh->reconstruct_state = reconstruct_state_idle;
-		clear_bit(STRIPE_EXPANDING, &sh->state);
-		for (i = conf->raid_disks; i--; ) {
-			set_bit(R5_Wantwrite, &sh->dev[i].flags);
-			set_bit(R5_LOCKED, &sh->dev[i].flags);
-			s.locked++;
-		}
-	}
-
-	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
-	    !sh->reconstruct_state) {
-		/* Need to write out all blocks after computing parity */
-		sh->disks = conf->raid_disks;
-		stripe_set_idx(sh->sector, conf, 0, sh);
-		schedule_reconstruction(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);
-		md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
-	}
-
-	if (s.expanding && s.locked == 0 &&
-	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
-		handle_stripe_expansion(conf, sh, NULL);
-
- unlock:
-	spin_unlock(&sh->lock);
-
-	/* wait for this device to become unblocked */
-	if (unlikely(blocked_rdev))
-		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
-
-	if (s.ops_request)
-		raid_run_ops(sh, s.ops_request);
-
-	ops_run_io(sh, &s);
-
-	if (dec_preread_active) {
-		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a flush, it won't continue until the writes
-		 * have actually been submitted.
-		 */
-		atomic_dec(&conf->preread_active_stripes);
-		if (atomic_read(&conf->preread_active_stripes) <
-		    IO_THRESHOLD)
-			md_wakeup_thread(conf->mddev->thread);
-	}
-	return_io(return_bi);
 }
 
-static void handle_stripe6(struct stripe_head *sh)
+static void handle_stripe(struct stripe_head *sh)
 {
+	struct stripe_head_state s;
 	raid5_conf_t *conf = sh->raid_conf;
+	int i;
+	int prexor;
 	int disks = sh->disks;
-	struct bio *return_bi = NULL;
-	int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx;
-	struct stripe_head_state s;
-	struct r6_state r6s;
-	struct r5dev *dev, *pdev, *qdev;
-	mdk_rdev_t *blocked_rdev = NULL;
-	int dec_preread_active = 0;
+	struct r5dev *pdev, *qdev;
+
+	clear_bit(STRIPE_HANDLE, &sh->state);
+	if (test_and_set_bit(STRIPE_ACTIVE, &sh->state)) {
+		/* already being handled, ensure it gets handled
+		 * again when current action finishes */
+		set_bit(STRIPE_HANDLE, &sh->state);
+		return;
+	}
+
+	if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+		set_bit(STRIPE_SYNCING, &sh->state);
+		clear_bit(STRIPE_INSYNC, &sh->state);
+	}
+	clear_bit(STRIPE_DELAYED, &sh->state);
 
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
 		"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
 	       (unsigned long long)sh->sector, sh->state,
-	       atomic_read(&sh->count), pd_idx, qd_idx,
+	       atomic_read(&sh->count), sh->pd_idx, sh->qd_idx,
 	       sh->check_state, sh->reconstruct_state);
 	memset(&s, 0, sizeof(s));
 
-	spin_lock(&sh->lock);
-	clear_bit(STRIPE_HANDLE, &sh->state);
-	clear_bit(STRIPE_DELAYED, &sh->state);
-
 	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 */
+	s.failed_num[0] = -1;
+	s.failed_num[1] = -1;
 
-	rcu_read_lock();
-	for (i=disks; i--; ) {
-		mdk_rdev_t *rdev;
-		dev = &sh->dev[i];
-
-		pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
-			i, dev->flags, dev->toread, dev->towrite, dev->written);
-		/* maybe we can reply to a read
-		 *
-		 * new wantfill requests are only permitted while
-		 * ops_complete_biofill is guaranteed to be inactive
-		 */
-		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
-		    !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
-			set_bit(R5_Wantfill, &dev->flags);
-
-		/* 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)) {
-			s.compute++;
-			BUG_ON(s.compute > 2);
-		}
-
-		if (test_bit(R5_Wantfill, &dev->flags)) {
-			s.to_fill++;
-		} else if (dev->toread)
-			s.to_read++;
-		if (dev->towrite) {
-			s.to_write++;
-			if (!test_bit(R5_OVERWRITE, &dev->flags))
-				s.non_overwrite++;
-		}
-		if (dev->written)
-			s.written++;
-		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (blocked_rdev == NULL &&
-		    rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			blocked_rdev = rdev;
-			atomic_inc(&rdev->nr_pending);
-		}
-		clear_bit(R5_Insync, &dev->flags);
-		if (!rdev)
-			/* Not in-sync */;
-		else if (test_bit(In_sync, &rdev->flags))
-			set_bit(R5_Insync, &dev->flags);
-		else {
-			/* in sync if before recovery_offset */
-			if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
-				set_bit(R5_Insync, &dev->flags);
-		}
-		if (!test_bit(R5_Insync, &dev->flags)) {
-			/* The ReadError flag will just be confusing now */
-			clear_bit(R5_ReadError, &dev->flags);
-			clear_bit(R5_ReWrite, &dev->flags);
-		}
-		if (test_bit(R5_ReadError, &dev->flags))
-			clear_bit(R5_Insync, &dev->flags);
-		if (!test_bit(R5_Insync, &dev->flags)) {
-			if (s.failed < 2)
-				r6s.failed_num[s.failed] = i;
-			s.failed++;
-		}
-	}
-	rcu_read_unlock();
+	analyse_stripe(sh, &s);
 
-	if (unlikely(blocked_rdev)) {
+	if (unlikely(s.blocked_rdev)) {
 		if (s.syncing || s.expanding || s.expanded ||
 		    s.to_write || s.written) {
 			set_bit(STRIPE_HANDLE, &sh->state);
-			goto unlock;
+			goto finish;
 		}
 		/* There is nothing for the blocked_rdev to block */
-		rdev_dec_pending(blocked_rdev, conf->mddev);
-		blocked_rdev = NULL;
+		rdev_dec_pending(s.blocked_rdev, conf->mddev);
+		s.blocked_rdev = NULL;
 	}
 
 	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
@@ -3408,13 +3036,13 @@ static void handle_stripe6(struct stripe_head *sh)
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
-	       r6s.failed_num[0], r6s.failed_num[1]);
+	       s.failed_num[0], s.failed_num[1]);
 	/* check if the array has lost >2 devices and, if so, some requests
 	 * might need to be failed
 	 */
-	if (s.failed > 2 && s.to_read+s.to_write+s.written)
-		handle_failed_stripe(conf, sh, &s, disks, &return_bi);
-	if (s.failed > 2 && s.syncing) {
+	if (s.failed > conf->max_degraded && s.to_read+s.to_write+s.written)
+		handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+	if (s.failed > conf->max_degraded && s.syncing) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,0);
 		clear_bit(STRIPE_SYNCING, &sh->state);
 		s.syncing = 0;
@@ -3424,67 +3052,74 @@ static void handle_stripe6(struct stripe_head *sh)
 	 * might be able to return some write requests if the parity blocks
 	 * are safe, or on a failed drive
 	 */
-	pdev = &sh->dev[pd_idx];
-	r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx)
-		|| (s.failed >= 2 && r6s.failed_num[1] == pd_idx);
-	qdev = &sh->dev[qd_idx];
-	r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == qd_idx)
-		|| (s.failed >= 2 && r6s.failed_num[1] == qd_idx);
+	pdev = &sh->dev[sh->pd_idx];
+	s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
+		|| (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
+	qdev = &sh->dev[sh->qd_idx];
+	s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
+		|| (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
+		|| conf->level < 6;
 
 	if ( s.written &&
-	     ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
+	     ( s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
 			     && !test_bit(R5_LOCKED, &pdev->flags)
 			     && test_bit(R5_UPTODATE, &pdev->flags)))) &&
-	     ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
+	     ( s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
 			     && !test_bit(R5_LOCKED, &qdev->flags)
 			     && test_bit(R5_UPTODATE, &qdev->flags)))))
-		handle_stripe_clean_event(conf, sh, disks, &return_bi);
+		handle_stripe_clean_event(conf, sh, disks, &s.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.to_write && s.failed) ||
+	if (s.to_read || s.non_overwrite || (conf->level == 6 && s.to_write && s.failed) ||
 	    (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
-		handle_stripe_fill6(sh, &s, &r6s, disks);
+		handle_stripe_fill(sh, &s, disks);
 
 	/* Now we check to see if any write operations have recently
 	 * completed
 	 */
-	if (sh->reconstruct_state == reconstruct_state_drain_result) {
-
+	prexor = 0;
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
+		prexor = 1;
+	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 blocks are ready to
+
+		/* All the 'written' buffers and the parity block are ready to
 		 * be written back to disk
 		 */
 		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
-		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags));
+		BUG_ON(sh->qd_idx >= 0 &&
+		       !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags));
 		for (i = disks; i--; ) {
-			dev = &sh->dev[i];
+			struct r5dev *dev = &sh->dev[i];
 			if (test_bit(R5_LOCKED, &dev->flags) &&
-			    (i == sh->pd_idx || i == qd_idx ||
-			     dev->written)) {
+				(i == sh->pd_idx || i == sh->qd_idx ||
+				 dev->written)) {
 				pr_debug("Writing block %d\n", i);
-				BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
 				set_bit(R5_Wantwrite, &dev->flags);
+				if (prexor)
+					continue;
 				if (!test_bit(R5_Insync, &dev->flags) ||
-				    ((i == sh->pd_idx || i == qd_idx) &&
-				      s.failed == 0))
+				    ((i == sh->pd_idx || i == sh->qd_idx)  &&
+				     s.failed == 0))
 					set_bit(STRIPE_INSYNC, &sh->state);
 			}
 		}
 		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
-			dec_preread_active = 1;
+			s.dec_preread_active = 1;
 	}
 
 	/* Now to consider new write requests and what else, if anything
 	 * should be read.  We do not handle new writes when:
-	 * 1/ A 'write' operation (copy+gen_syndrome) is already in flight.
+	 * 1/ A 'write' operation (copy+xor) is already in flight.
 	 * 2/ A 'check' operation is in flight, as it may clobber the parity
 	 *    block.
 	 */
 	if (s.to_write && !sh->reconstruct_state && !sh->check_state)
-		handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
+		handle_stripe_dirtying(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
@@ -3494,8 +3129,12 @@ static void handle_stripe6(struct stripe_head *sh)
 	if (sh->check_state ||
 	    (s.syncing && s.locked == 0 &&
 	     !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
-	     !test_bit(STRIPE_INSYNC, &sh->state)))
-		handle_parity_checks6(conf, sh, &s, &r6s, disks);
+	     !test_bit(STRIPE_INSYNC, &sh->state))) {
+		if (conf->level == 6)
+			handle_parity_checks6(conf, sh, &s, disks);
+		else
+			handle_parity_checks5(conf, sh, &s, disks);
+	}
 
 	if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
 		md_done_sync(conf->mddev, STRIPE_SECTORS,1);
@@ -3505,9 +3144,9 @@ static void handle_stripe6(struct stripe_head *sh)
 	/* If the failed drives are just a ReadError, then we might need
 	 * to progress the repair/check process
 	 */
-	if (s.failed <= 2 && !conf->mddev->ro)
+	if (s.failed <= conf->max_degraded && !conf->mddev->ro)
 		for (i = 0; i < s.failed; i++) {
-			dev = &sh->dev[r6s.failed_num[i]];
+			struct r5dev *dev = &sh->dev[s.failed_num[i]];
 			if (test_bit(R5_ReadError, &dev->flags)
 			    && !test_bit(R5_LOCKED, &dev->flags)
 			    && test_bit(R5_UPTODATE, &dev->flags)
@@ -3526,19 +3165,9 @@ static void handle_stripe6(struct stripe_head *sh)
 			}
 		}
 
+
 	/* 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);
-		for (i = conf->raid_disks; i--; ) {
-			set_bit(R5_Wantwrite, &sh->dev[i].flags);
-			set_bit(R5_LOCKED, &sh->dev[i].flags);
-			s.locked++;
-		}
-	}
-
-	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
-	    !sh->reconstruct_state) {
 		struct stripe_head *sh2
 			= get_active_stripe(conf, sh->sector, 1, 1, 1);
 		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
@@ -3551,12 +3180,23 @@ static void handle_stripe6(struct stripe_head *sh)
 					      &sh2->state))
 				atomic_inc(&conf->preread_active_stripes);
 			release_stripe(sh2);
-			goto unlock;
+			goto finish;
 		}
 		if (sh2)
 			release_stripe(sh2);
 
-		/* Need to write out all blocks after computing P&Q */
+		sh->reconstruct_state = reconstruct_state_idle;
+		clear_bit(STRIPE_EXPANDING, &sh->state);
+		for (i = conf->raid_disks; i--; ) {
+			set_bit(R5_Wantwrite, &sh->dev[i].flags);
+			set_bit(R5_LOCKED, &sh->dev[i].flags);
+			s.locked++;
+		}
+	}
+
+	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
+	    !sh->reconstruct_state) {
+		/* Need to write out all blocks after computing parity */
 		sh->disks = conf->raid_disks;
 		stripe_set_idx(sh->sector, conf, 0, sh);
 		schedule_reconstruction(sh, &s, 1, 1);
@@ -3569,14 +3209,12 @@ static void handle_stripe6(struct stripe_head *sh)
 
 	if (s.expanding && s.locked == 0 &&
 	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
-		handle_stripe_expansion(conf, sh, &r6s);
-
- unlock:
-	spin_unlock(&sh->lock);
+		handle_stripe_expansion(conf, sh, NULL);
 
+finish:
 	/* wait for this device to become unblocked */
-	if (unlikely(blocked_rdev))
-		md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+	if (unlikely(s.blocked_rdev))
+		md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
 
 	if (s.ops_request)
 		raid_run_ops(sh, s.ops_request);
@@ -3584,7 +3222,7 @@ static void handle_stripe6(struct stripe_head *sh)
 	ops_run_io(sh, &s);
 
 
-	if (dec_preread_active) {
+	if (s.dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
 		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
@@ -3595,15 +3233,9 @@ static void handle_stripe6(struct stripe_head *sh)
 			md_wakeup_thread(conf->mddev->thread);
 	}
 
-	return_io(return_bi);
-}
+	return_io(s.return_bi);
 
-static void handle_stripe(struct stripe_head *sh)
-{
-	if (sh->raid_conf->level == 6)
-		handle_stripe6(sh);
-	else
-		handle_stripe5(sh);
+	clear_bit(STRIPE_ACTIVE, &sh->state);
 }
 
 static void raid5_activate_delayed(raid5_conf_t *conf)
@@ -4016,7 +3648,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 				}
 			}
 
-			if (bio_data_dir(bi) == WRITE &&
+			if (rw == WRITE &&
 			    logical_sector >= mddev->suspend_lo &&
 			    logical_sector < mddev->suspend_hi) {
 				release_stripe(sh);
@@ -4034,7 +3666,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 			}
 
 			if (test_bit(STRIPE_EXPANDING, &sh->state) ||
-			    !add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
+			    !add_stripe_bio(sh, bi, dd_idx, rw)) {
 				/* Stripe is busy expanding or
 				 * add failed due to overlap.  Flush everything
 				 * and wait a while
@@ -4375,10 +4007,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 
 	bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
 
-	spin_lock(&sh->lock);
-	set_bit(STRIPE_SYNCING, &sh->state);
-	clear_bit(STRIPE_INSYNC, &sh->state);
-	spin_unlock(&sh->lock);
+	set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
 
 	handle_stripe(sh);
 	release_stripe(sh);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 3ca77a2613ba..9ceb574e9dca 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -209,7 +209,6 @@ struct stripe_head {
 	short			ddf_layout;/* use DDF ordering to calculate Q */
 	unsigned long		state;		/* state flags */
 	atomic_t		count;	      /* nr of active thread/requests */
-	spinlock_t		lock;
 	int			bm_seq;	/* sequence number for bitmap flushes */
 	int			disks;		/* disks in stripe */
 	enum check_states	check_state;
@@ -246,13 +245,13 @@ struct stripe_head_state {
 	int syncing, expanding, expanded;
 	int locked, uptodate, to_read, to_write, failed, written;
 	int to_fill, compute, req_compute, non_overwrite;
-	int failed_num;
+	int failed_num[2];
 	unsigned long ops_request;
-};
+	int p_failed, q_failed;
 
-/* r6_state - extra state data only relevant to r6 */
-struct r6_state {
-	int p_failed, q_failed, failed_num[2];
+	struct bio *return_bi;
+	mdk_rdev_t *blocked_rdev;
+	int dec_preread_active;
 };
 
 /* Flags */
@@ -289,21 +288,25 @@ struct r6_state {
 /*
  * Stripe state
  */
-#define STRIPE_HANDLE		2
-#define	STRIPE_SYNCING		3
-#define	STRIPE_INSYNC		4
-#define	STRIPE_PREREAD_ACTIVE	5
-#define	STRIPE_DELAYED		6
-#define	STRIPE_DEGRADED		7
-#define	STRIPE_BIT_DELAY	8
-#define	STRIPE_EXPANDING	9
-#define	STRIPE_EXPAND_SOURCE	10
-#define	STRIPE_EXPAND_READY	11
-#define	STRIPE_IO_STARTED	12 /* do not count towards 'bypass_count' */
-#define	STRIPE_FULL_WRITE	13 /* all blocks are set to be overwritten */
-#define	STRIPE_BIOFILL_RUN	14
-#define	STRIPE_COMPUTE_RUN	15
-#define	STRIPE_OPS_REQ_PENDING	16
+enum {
+	STRIPE_ACTIVE,
+	STRIPE_HANDLE,
+	STRIPE_SYNC_REQUESTED,
+	STRIPE_SYNCING,
+	STRIPE_INSYNC,
+	STRIPE_PREREAD_ACTIVE,
+	STRIPE_DELAYED,
+	STRIPE_DEGRADED,
+	STRIPE_BIT_DELAY,
+	STRIPE_EXPANDING,
+	STRIPE_EXPAND_SOURCE,
+	STRIPE_EXPAND_READY,
+	STRIPE_IO_STARTED,	/* do not count towards 'bypass_count' */
+	STRIPE_FULL_WRITE,	/* all blocks are set to be overwritten */
+	STRIPE_BIOFILL_RUN,
+	STRIPE_COMPUTE_RUN,
+	STRIPE_OPS_REQ_PENDING,
+};
 
 /*
  * Operation request flags