--- zzzz-none-000/linux-3.10.107/drivers/md/raid10.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/drivers/md/raid10.c	2021-02-04 17:41:59.000000000 +0000
@@ -39,6 +39,7 @@
  *    far_copies (stored in second byte of layout)
  *    far_offset (stored in bit 16 of layout )
  *    use_far_sets (stored in bit 17 of layout )
+ *    use_far_sets_bugfixed (stored in bit 18 of layout )
  *
  * The data to be stored is divided into chunks using chunksize.  Each device
  * is divided into far_copies sections.   In each section, chunks are laid out
@@ -97,11 +98,11 @@
 
 static void allow_barrier(struct r10conf *conf);
 static void lower_barrier(struct r10conf *conf);
-static int enough(struct r10conf *conf, int ignore);
+static int _enough(struct r10conf *conf, int previous, int ignore);
 static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 				int *skipped);
 static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
-static void end_reshape_write(struct bio *bio, int error);
+static void end_reshape_write(struct bio *bio);
 static void end_reshape(struct r10conf *conf);
 
 static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
@@ -307,9 +308,9 @@
 	} else
 		done = 1;
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		bio->bi_error = -EIO;
 	if (done) {
-		bio_endio(bio, 0);
+		bio_endio(bio);
 		/*
 		 * Wake up any possible resync thread that waits for the device
 		 * to go idle.
@@ -358,15 +359,14 @@
 	return r10_bio->devs[slot].devnum;
 }
 
-static void raid10_end_read_request(struct bio *bio, int error)
+static void raid10_end_read_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	int uptodate = !bio->bi_error;
 	struct r10bio *r10_bio = bio->bi_private;
 	int slot, dev;
 	struct md_rdev *rdev;
 	struct r10conf *conf = r10_bio->mddev->private;
 
-
 	slot = r10_bio->read_slot;
 	dev = r10_bio->devs[slot].devnum;
 	rdev = r10_bio->devs[slot].rdev;
@@ -392,11 +392,9 @@
 		 * than fail the last device.  Here we redefine
 		 * "uptodate" to mean "Don't want to retry"
 		 */
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		if (!enough(conf, rdev->raid_disk))
+		if (!_enough(conf, test_bit(R10BIO_Previous, &r10_bio->state),
+			     rdev->raid_disk))
 			uptodate = 1;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 	if (uptodate) {
 		raid_end_bio_io(r10_bio);
@@ -441,9 +439,8 @@
 	}
 }
 
-static void raid10_end_write_request(struct bio *bio, int error)
+static void raid10_end_write_request(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	int dev;
 	int dec_rdev = 1;
@@ -463,7 +460,7 @@
 	/*
 	 * this branch is our 'one mirror IO has finished' event handler:
 	 */
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			/* Never record new bad blocks to replacement,
 			 * just fail it.
@@ -675,94 +672,6 @@
 	return (vchunk << geo->chunk_shift) + offset;
 }
 
-/**
- *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- *	@q: request queue
- *	@bvm: properties of new bio
- *	@biovec: the request that could be merged to it.
- *
- *	Return amount of bytes we can accept at this offset
- *	This requires checking for end-of-chunk if near_copies != raid_disks,
- *	and for subordinate merge_bvec_fns if merge_check_needed.
- */
-static int raid10_mergeable_bvec(struct request_queue *q,
-				 struct bvec_merge_data *bvm,
-				 struct bio_vec *biovec)
-{
-	struct mddev *mddev = q->queuedata;
-	struct r10conf *conf = mddev->private;
-	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
-	int max;
-	unsigned int chunk_sectors;
-	unsigned int bio_sectors = bvm->bi_size >> 9;
-	struct geom *geo = &conf->geo;
-
-	chunk_sectors = (conf->geo.chunk_mask & conf->prev.chunk_mask) + 1;
-	if (conf->reshape_progress != MaxSector &&
-	    ((sector >= conf->reshape_progress) !=
-	     conf->mddev->reshape_backwards))
-		geo = &conf->prev;
-
-	if (geo->near_copies < geo->raid_disks) {
-		max = (chunk_sectors - ((sector & (chunk_sectors - 1))
-					+ bio_sectors)) << 9;
-		if (max < 0)
-			/* bio_add cannot handle a negative return */
-			max = 0;
-		if (max <= biovec->bv_len && bio_sectors == 0)
-			return biovec->bv_len;
-	} else
-		max = biovec->bv_len;
-
-	if (mddev->merge_check_needed) {
-		struct {
-			struct r10bio r10_bio;
-			struct r10dev devs[conf->copies];
-		} on_stack;
-		struct r10bio *r10_bio = &on_stack.r10_bio;
-		int s;
-		if (conf->reshape_progress != MaxSector) {
-			/* Cannot give any guidance during reshape */
-			if (max <= biovec->bv_len && bio_sectors == 0)
-				return biovec->bv_len;
-			return 0;
-		}
-		r10_bio->sector = sector;
-		raid10_find_phys(conf, r10_bio);
-		rcu_read_lock();
-		for (s = 0; s < conf->copies; s++) {
-			int disk = r10_bio->devs[s].devnum;
-			struct md_rdev *rdev = rcu_dereference(
-				conf->mirrors[disk].rdev);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-			rdev = rcu_dereference(conf->mirrors[disk].replacement);
-			if (rdev && !test_bit(Faulty, &rdev->flags)) {
-				struct request_queue *q =
-					bdev_get_queue(rdev->bdev);
-				if (q->merge_bvec_fn) {
-					bvm->bi_sector = r10_bio->devs[s].addr
-						+ rdev->data_offset;
-					bvm->bi_bdev = rdev->bdev;
-					max = min(max, q->merge_bvec_fn(
-							  q, bvm, biovec));
-				}
-			}
-		}
-		rcu_read_unlock();
-	}
-	return max;
-}
-
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -825,12 +734,10 @@
 		disk = r10_bio->devs[slot].devnum;
 		rdev = rcu_dereference(conf->mirrors[disk].replacement);
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags) ||
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
 			rdev = rcu_dereference(conf->mirrors[disk].rdev);
 		if (rdev == NULL ||
-		    test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags))
+		    test_bit(Faulty, &rdev->flags))
 			continue;
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
@@ -913,12 +820,12 @@
 	return rdev;
 }
 
-int md_raid10_congested(struct mddev *mddev, int bits)
+static int raid10_congested(struct mddev *mddev, int bits)
 {
 	struct r10conf *conf = mddev->private;
 	int i, ret = 0;
 
-	if ((bits & (1 << BDI_async_congested)) &&
+	if ((bits & (1 << WB_async_congested)) &&
 	    conf->pending_count >= max_queued_requests)
 		return 1;
 
@@ -937,15 +844,6 @@
 	rcu_read_unlock();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(md_raid10_congested);
-
-static int raid10_congested(void *data, int bits)
-{
-	struct mddev *mddev = data;
-
-	return mddev_congested(mddev, bits) ||
-		md_raid10_congested(mddev, bits);
-}
 
 static void flush_pending_writes(struct r10conf *conf)
 {
@@ -970,7 +868,7 @@
 			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 				/* Just ignore it */
-				bio_endio(bio, 0);
+				bio_endio(bio);
 			else
 				generic_make_request(bio);
 			bio = next;
@@ -1048,7 +946,8 @@
 				    !conf->barrier ||
 				    (conf->nr_pending &&
 				     current->bio_list &&
-				     !bio_list_empty(current->bio_list)),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1]))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
@@ -1146,7 +1045,7 @@
 		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
 		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
 			/* Just ignore it */
-			bio_endio(bio, 0);
+			bio_endio(bio);
 		else
 			generic_make_request(bio);
 		bio = next;
@@ -1154,14 +1053,12 @@
 	kfree(plug);
 }
 
-static void make_request(struct mddev *mddev, struct bio * bio)
+static void __make_request(struct mddev *mddev, struct bio *bio)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
 	struct bio *read_bio;
 	int i;
-	sector_t chunk_mask = (conf->geo.chunk_mask & conf->prev.chunk_mask);
-	int chunk_sects = chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
@@ -1176,59 +1073,6 @@
 	int max_sectors;
 	int sectors;
 
-	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
-		md_flush_request(mddev, bio);
-		return;
-	}
-
-	/* If this request crosses a chunk boundary, we need to
-	 * split it.  This will only happen for 1 PAGE (or less) requests.
-	 */
-	if (unlikely((bio->bi_sector & chunk_mask) + bio_sectors(bio)
-		     > chunk_sects
-		     && (conf->geo.near_copies < conf->geo.raid_disks
-			 || conf->prev.near_copies < conf->prev.raid_disks))) {
-		struct bio_pair *bp;
-		/* Sanity check -- queue functions should prevent this happening */
-		if (bio_segments(bio) > 1)
-			goto bad_map;
-		/* This is a one page bio that upper layers
-		 * refuse to split for us, so we need to split it.
-		 */
-		bp = bio_split(bio,
-			       chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
-
-		/* Each of these 'make_request' calls will call 'wait_barrier'.
-		 * If the first succeeds but the second blocks due to the resync
-		 * thread raising the barrier, we will deadlock because the
-		 * IO to the underlying device will be queued in generic_make_request
-		 * and will never complete, so will never reduce nr_pending.
-		 * So increment nr_waiting here so no new raise_barriers will
-		 * succeed, and so the second wait_barrier cannot block.
-		 */
-		spin_lock_irq(&conf->resync_lock);
-		conf->nr_waiting++;
-		spin_unlock_irq(&conf->resync_lock);
-
-		make_request(mddev, &bp->bio1);
-		make_request(mddev, &bp->bio2);
-
-		spin_lock_irq(&conf->resync_lock);
-		conf->nr_waiting--;
-		wake_up(&conf->wait_barrier);
-		spin_unlock_irq(&conf->resync_lock);
-
-		bio_pair_release(bp);
-		return;
-	bad_map:
-		printk("md/raid10:%s: make_request bug: can't convert block across chunks"
-		       " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2,
-		       (unsigned long long)bio->bi_sector, bio_sectors(bio) / 2);
-
-		bio_io_error(bio);
-		return;
-	}
-
 	md_write_start(mddev, bio);
 
 	/*
@@ -1240,24 +1084,25 @@
 
 	sectors = bio_sectors(bio);
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
-	    bio->bi_sector < conf->reshape_progress &&
-	    bio->bi_sector + sectors > conf->reshape_progress) {
+	    bio->bi_iter.bi_sector < conf->reshape_progress &&
+	    bio->bi_iter.bi_sector + sectors > conf->reshape_progress) {
 		/* IO spans the reshape position.  Need to wait for
 		 * reshape to pass
 		 */
 		allow_barrier(conf);
 		wait_event(conf->wait_barrier,
-			   conf->reshape_progress <= bio->bi_sector ||
-			   conf->reshape_progress >= bio->bi_sector + sectors);
+			   conf->reshape_progress <= bio->bi_iter.bi_sector ||
+			   conf->reshape_progress >= bio->bi_iter.bi_sector +
+			   sectors);
 		wait_barrier(conf);
 	}
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio_data_dir(bio) == WRITE &&
 	    (mddev->reshape_backwards
-	     ? (bio->bi_sector < conf->reshape_safe &&
-		bio->bi_sector + sectors > conf->reshape_progress)
-	     : (bio->bi_sector + sectors > conf->reshape_safe &&
-		bio->bi_sector < conf->reshape_progress))) {
+	     ? (bio->bi_iter.bi_sector < conf->reshape_safe &&
+		bio->bi_iter.bi_sector + sectors > conf->reshape_progress)
+	     : (bio->bi_iter.bi_sector + sectors > conf->reshape_safe &&
+		bio->bi_iter.bi_sector < conf->reshape_progress))) {
 		/* Need to update reshape_position in metadata */
 		mddev->reshape_position = conf->reshape_progress;
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -1275,7 +1120,7 @@
 	r10_bio->sectors = sectors;
 
 	r10_bio->mddev = mddev;
-	r10_bio->sector = bio->bi_sector;
+	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
 
 	/* We might need to issue multiple reads to different
@@ -1286,7 +1131,7 @@
 	 * non-zero, then it is the number of not-completed requests.
 	 */
 	bio->bi_phys_segments = 0;
-	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
+	bio_clear_flag(bio, BIO_SEG_VALID);
 
 	if (rw == READ) {
 		/*
@@ -1304,13 +1149,13 @@
 		slot = r10_bio->read_slot;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(read_bio, r10_bio->sector - bio->bi_sector,
-			    max_sectors);
+		bio_trim(read_bio, r10_bio->sector - bio->bi_iter.bi_sector,
+			 max_sectors);
 
 		r10_bio->devs[slot].bio = read_bio;
 		r10_bio->devs[slot].rdev = rdev;
 
-		read_bio->bi_sector = r10_bio->devs[slot].addr +
+		read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
 			choose_data_offset(r10_bio, rdev);
 		read_bio->bi_bdev = rdev->bdev;
 		read_bio->bi_end_io = raid10_end_read_request;
@@ -1322,7 +1167,7 @@
 			 * need another r10_bio.
 			 */
 			sectors_handled = (r10_bio->sector + max_sectors
-					   - bio->bi_sector);
+					   - bio->bi_iter.bi_sector);
 			r10_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
 			if (bio->bi_phys_segments == 0)
@@ -1343,7 +1188,8 @@
 			r10_bio->sectors = bio_sectors(bio) - sectors_handled;
 			r10_bio->state = 0;
 			r10_bio->mddev = mddev;
-			r10_bio->sector = bio->bi_sector + sectors_handled;
+			r10_bio->sector = bio->bi_iter.bi_sector +
+				sectors_handled;
 			goto read_again;
 		} else
 			generic_make_request(read_bio);
@@ -1394,11 +1240,9 @@
 			blocked_rdev = rrdev;
 			break;
 		}
-		if (rdev && (test_bit(Faulty, &rdev->flags)
-			     || test_bit(Unmerged, &rdev->flags)))
+		if (rdev && (test_bit(Faulty, &rdev->flags)))
 			rdev = NULL;
-		if (rrdev && (test_bit(Faulty, &rrdev->flags)
-			      || test_bit(Unmerged, &rrdev->flags)))
+		if (rrdev && (test_bit(Faulty, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
@@ -1501,7 +1345,8 @@
 			bio->bi_phys_segments++;
 		spin_unlock_irq(&conf->device_lock);
 	}
-	sectors_handled = r10_bio->sector + max_sectors - bio->bi_sector;
+	sectors_handled = r10_bio->sector + max_sectors -
+		bio->bi_iter.bi_sector;
 
 	atomic_set(&r10_bio->remaining, 1);
 	bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);
@@ -1512,11 +1357,11 @@
 		if (r10_bio->devs[i].bio) {
 			struct md_rdev *rdev = conf->mirrors[d].rdev;
 			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-				    max_sectors);
+			bio_trim(mbio, r10_bio->sector - bio->bi_iter.bi_sector,
+				 max_sectors);
 			r10_bio->devs[i].bio = mbio;
 
-			mbio->bi_sector	= (r10_bio->devs[i].addr+
+			mbio->bi_iter.bi_sector	= (r10_bio->devs[i].addr+
 					   choose_data_offset(r10_bio,
 							      rdev));
 			mbio->bi_bdev = rdev->bdev;
@@ -1555,11 +1400,11 @@
 				rdev = conf->mirrors[d].rdev;
 			}
 			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-				    max_sectors);
+			bio_trim(mbio, r10_bio->sector - bio->bi_iter.bi_sector,
+				 max_sectors);
 			r10_bio->devs[i].repl_bio = mbio;
 
-			mbio->bi_sector	= (r10_bio->devs[i].addr +
+			mbio->bi_iter.bi_sector	= (r10_bio->devs[i].addr +
 					   choose_data_offset(
 						   r10_bio, rdev));
 			mbio->bi_bdev = rdev->bdev;
@@ -1593,11 +1438,66 @@
 		r10_bio->sectors = bio_sectors(bio) - sectors_handled;
 
 		r10_bio->mddev = mddev;
-		r10_bio->sector = bio->bi_sector + sectors_handled;
+		r10_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
 		r10_bio->state = 0;
 		goto retry_write;
 	}
 	one_write_done(r10_bio);
+}
+
+static void make_request(struct mddev *mddev, struct bio *bio)
+{
+	struct r10conf *conf = mddev->private;
+	sector_t chunk_mask = (conf->geo.chunk_mask & conf->prev.chunk_mask);
+	int chunk_sects = chunk_mask + 1;
+
+	struct bio *split;
+
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
+		return;
+	}
+
+	do {
+
+		/*
+		 * If this request crosses a chunk boundary, we need to split
+		 * it.
+		 */
+		if (unlikely((bio->bi_iter.bi_sector & chunk_mask) +
+			     bio_sectors(bio) > chunk_sects
+			     && (conf->geo.near_copies < conf->geo.raid_disks
+				 || conf->prev.near_copies <
+				 conf->prev.raid_disks))) {
+			split = bio_split(bio, chunk_sects -
+					  (bio->bi_iter.bi_sector &
+					   (chunk_sects - 1)),
+					  GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
+
+		/*
+		 * If a bio is splitted, the first part of bio will pass
+		 * barrier but the bio is queued in current->bio_list (see
+		 * generic_make_request). If there is a raise_barrier() called
+		 * here, the second part of bio can't pass barrier. But since
+		 * the first part bio isn't dispatched to underlaying disks
+		 * yet, the barrier is never released, hence raise_barrier will
+		 * alays wait. We have a deadlock.
+		 * Note, this only happens in read path. For write path, the
+		 * first part of bio is dispatched in a schedule() call
+		 * (because of blk plug) or offloaded to raid10d.
+		 * Quitting from the function immediately can change the bio
+		 * order queued in bio_list and avoid the deadlock.
+		 */
+		__make_request(mddev, split);
+		if (split != bio && bio_data_dir(bio) == READ) {
+			generic_make_request(bio);
+			break;
+		}
+	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
 	wake_up(&conf->wait_barrier);
@@ -1617,6 +1517,8 @@
 			seq_printf(seq, " %d offset-copies", conf->geo.far_copies);
 		else
 			seq_printf(seq, " %d far-copies", conf->geo.far_copies);
+		if (conf->geo.far_set_size != conf->geo.raid_disks)
+			seq_printf(seq, " %d devices per set", conf->geo.far_set_size);
 	}
 	seq_printf(seq, " [%d/%d] [", conf->geo.raid_disks,
 					conf->geo.raid_disks - mddev->degraded);
@@ -1632,37 +1534,58 @@
  * Don't consider the device numbered 'ignore'
  * as we might be about to remove it.
  */
-static int _enough(struct r10conf *conf, struct geom *geo, int ignore)
+static int _enough(struct r10conf *conf, int previous, int ignore)
 {
 	int first = 0;
+	int has_enough = 0;
+	int disks, ncopies;
+	if (previous) {
+		disks = conf->prev.raid_disks;
+		ncopies = conf->prev.near_copies;
+	} else {
+		disks = conf->geo.raid_disks;
+		ncopies = conf->geo.near_copies;
+	}
 
+	rcu_read_lock();
 	do {
 		int n = conf->copies;
 		int cnt = 0;
 		int this = first;
 		while (n--) {
-			if (conf->mirrors[this].rdev &&
-			    this != ignore)
+			struct md_rdev *rdev;
+			if (this != ignore &&
+			    (rdev = rcu_dereference(conf->mirrors[this].rdev)) &&
+			    test_bit(In_sync, &rdev->flags))
 				cnt++;
-			this = (this+1) % geo->raid_disks;
+			this = (this+1) % disks;
 		}
 		if (cnt == 0)
-			return 0;
-		first = (first + geo->near_copies) % geo->raid_disks;
+			goto out;
+		first = (first + ncopies) % disks;
 	} while (first != 0);
-	return 1;
+	has_enough = 1;
+out:
+	rcu_read_unlock();
+	return has_enough;
 }
 
 static int enough(struct r10conf *conf, int ignore)
 {
-	return _enough(conf, &conf->geo, ignore) &&
-		_enough(conf, &conf->prev, ignore);
+	/* when calling 'enough', both 'prev' and 'geo' must
+	 * be stable.
+	 * This is ensured if ->reconfig_mutex or ->device_lock
+	 * is held.
+	 */
+	return _enough(conf, 0, ignore) &&
+		_enough(conf, 1, ignore);
 }
 
 static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r10conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1670,18 +1593,17 @@
 	 * next level up know.
 	 * else mark the drive as failed
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_bit(In_sync, &rdev->flags)
-	    && !enough(conf, rdev->raid_disk))
+	    && !enough(conf, rdev->raid_disk)) {
 		/*
 		 * Don't fail the drive, just return an IO error.
 		 */
-		return;
-	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		mddev->degraded++;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
+		return;
 	}
+	if (test_and_clear_bit(In_sync, &rdev->flags))
+		mddev->degraded++;
 	/*
 	 * If recovery is running, make sure it aborts.
 	 */
@@ -1689,6 +1611,8 @@
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_CHANGE_PENDING, &mddev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	printk(KERN_ALERT
 	       "md/raid10:%s: Disk failure on %s, disabling device.\n"
 	       "md/raid10:%s: Operation continuing on %d devices.\n",
@@ -1777,7 +1701,6 @@
 	return count;
 }
 
-
 static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r10conf *conf = mddev->private;
@@ -1785,24 +1708,21 @@
 	int mirror;
 	int first = 0;
 	int last = conf->geo.raid_disks - 1;
-	struct request_queue *q = bdev_get_queue(rdev->bdev);
 
 	if (mddev->recovery_cp < MaxSector)
 		/* only hot-add to in-sync arrays, as recovery is
 		 * very different from resync
 		 */
 		return -EBUSY;
-	if (rdev->saved_raid_disk < 0 && !_enough(conf, &conf->prev, -1))
+	if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1))
 		return -EINVAL;
 
+	if (md_integrity_add_rdev(rdev, mddev))
+		return -ENXIO;
+
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
-	if (q->merge_bvec_fn) {
-		set_bit(Unmerged, &rdev->flags);
-		mddev->merge_check_needed = 1;
-	}
-
 	if (rdev->saved_raid_disk >= first &&
 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
 		mirror = rdev->saved_raid_disk;
@@ -1820,15 +1740,17 @@
 			set_bit(Replacement, &rdev->flags);
 			rdev->raid_disk = mirror;
 			err = 0;
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
+			if (mddev->gendisk)
+				disk_stack_limits(mddev->gendisk, rdev->bdev,
+						  rdev->data_offset << 9);
 			conf->fullsync = 1;
 			rcu_assign_pointer(p->replacement, rdev);
 			break;
 		}
 
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
+		if (mddev->gendisk)
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
 
 		p->head_position = 0;
 		p->recovery_disabled = mddev->recovery_disabled - 1;
@@ -1839,20 +1761,6 @@
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
-	if (err == 0 && test_bit(Unmerged, &rdev->flags)) {
-		/* Some requests might not have seen this new
-		 * merge_bvec_fn.  We must wait for them to complete
-		 * before merging the device fully.
-		 * First we make sure any code which has tested
-		 * our function has submitted the request, then
-		 * we wait for all outstanding requests to complete.
-		 */
-		synchronize_sched();
-		freeze_array(conf, 0);
-		unfreeze_array(conf);
-		clear_bit(Unmerged, &rdev->flags);
-	}
-	md_integrity_add_rdev(rdev, mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
 
@@ -1922,8 +1830,7 @@
 	return err;
 }
 
-
-static void end_sync_read(struct bio *bio, int error)
+static void end_sync_read(struct bio *bio)
 {
 	struct r10bio *r10_bio = bio->bi_private;
 	struct r10conf *conf = r10_bio->mddev->private;
@@ -1935,7 +1842,7 @@
 	} else
 		d = find_bio_disk(conf, r10_bio, bio, NULL, NULL);
 
-	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+	if (!bio->bi_error)
 		set_bit(R10BIO_Uptodate, &r10_bio->state);
 	else
 		/* The write handler will notice the lack of
@@ -1984,9 +1891,8 @@
 	}
 }
 
-static void end_sync_write(struct bio *bio, int error)
+static void end_sync_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -2003,7 +1909,7 @@
 	else
 		rdev = conf->mirrors[d].rdev;
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		if (repl)
 			md_error(mddev, rdev);
 		else {
@@ -2051,7 +1957,7 @@
 
 	/* find the first device with a block */
 	for (i=0; i<conf->copies; i++)
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags))
+		if (!r10_bio->devs[i].bio->bi_error)
 			break;
 
 	if (i == conf->copies)
@@ -2059,6 +1965,8 @@
 
 	first = i;
 	fbio = r10_bio->devs[i].bio;
+	fbio->bi_iter.bi_size = r10_bio->sectors << 9;
+	fbio->bi_iter.bi_idx = 0;
 
 	vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9);
 	/* now find blocks with errors */
@@ -2071,7 +1979,7 @@
 			continue;
 		if (i == first)
 			continue;
-		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags)) {
+		if (!r10_bio->devs[i].bio->bi_error) {
 			/* We know that the bi_io_vec layout is the same for
 			 * both 'first' and 'i', so we just compare them.
 			 * All vec entries are PAGE_SIZE;
@@ -2102,27 +2010,20 @@
 		bio_reset(tbio);
 
 		tbio->bi_vcnt = vcnt;
-		tbio->bi_size = r10_bio->sectors << 9;
+		tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
 		tbio->bi_rw = WRITE;
 		tbio->bi_private = r10_bio;
-		tbio->bi_sector = r10_bio->devs[i].addr;
-
-		for (j=0; j < vcnt ; j++) {
-			tbio->bi_io_vec[j].bv_offset = 0;
-			tbio->bi_io_vec[j].bv_len = PAGE_SIZE;
-
-			memcpy(page_address(tbio->bi_io_vec[j].bv_page),
-			       page_address(fbio->bi_io_vec[j].bv_page),
-			       PAGE_SIZE);
-		}
+		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
 		tbio->bi_end_io = end_sync_write;
 
+		bio_copy_data(tbio, fbio);
+
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
 		atomic_inc(&r10_bio->remaining);
 		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio));
 
-		tbio->bi_sector += conf->mirrors[d].rdev->data_offset;
+		tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset;
 		tbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		generic_make_request(tbio);
 	}
@@ -2131,17 +2032,14 @@
 	 * that are active
 	 */
 	for (i = 0; i < conf->copies; i++) {
-		int j, d;
+		int d;
 
 		tbio = r10_bio->devs[i].repl_bio;
 		if (!tbio || !tbio->bi_end_io)
 			continue;
 		if (r10_bio->devs[i].bio->bi_end_io != end_sync_write
 		    && r10_bio->devs[i].bio != fbio)
-			for (j = 0; j < vcnt; j++)
-				memcpy(page_address(tbio->bi_io_vec[j].bv_page),
-				       page_address(fbio->bi_io_vec[j].bv_page),
-				       PAGE_SIZE);
+			bio_copy_data(tbio, fbio);
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
@@ -2288,7 +2186,6 @@
 	}
 }
 
-
 /*
  * Used by fix_read_error() to decay the per rdev read_errors.
  * We halve the read error count for every hour that has elapsed
@@ -2412,7 +2309,6 @@
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (rdev &&
-			    !test_bit(Unmerged, &rdev->flags) &&
 			    test_bit(In_sync, &rdev->flags) &&
 			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
 					&first_bad, &bad_sectors) == 0) {
@@ -2466,7 +2362,6 @@
 			d = r10_bio->devs[sl].devnum;
 			rdev = rcu_dereference(conf->mirrors[d].rdev);
 			if (!rdev ||
-			    test_bit(Unmerged, &rdev->flags) ||
 			    !test_bit(In_sync, &rdev->flags))
 				continue;
 
@@ -2580,7 +2475,8 @@
 	if (rdev->badblocks.shift < 0)
 		return 0;
 
-	block_sectors = 1 << rdev->badblocks.shift;
+	block_sectors = roundup(1 << rdev->badblocks.shift,
+				bdev_logical_block_size(rdev->bdev) >> 9);
 	sector = r10_bio->sector;
 	sectors = ((r10_bio->sector + block_sectors)
 		   & ~(sector_t)(block_sectors - 1))
@@ -2592,8 +2488,8 @@
 			sectors = sect_to_write;
 		/* Write at 'sector' for 'sectors' */
 		wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(wbio, sector - bio->bi_sector, sectors);
-		wbio->bi_sector = (r10_bio->devs[i].addr+
+		bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
+		wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
 				   choose_data_offset(r10_bio, rdev) +
 				   (sector - r10_bio->sector));
 		wbio->bi_bdev = rdev->bdev;
@@ -2665,12 +2561,10 @@
 		(unsigned long long)r10_bio->sector);
 	bio = bio_clone_mddev(r10_bio->master_bio,
 			      GFP_NOIO, mddev);
-	md_trim_bio(bio,
-		    r10_bio->sector - bio->bi_sector,
-		    max_sectors);
+	bio_trim(bio, r10_bio->sector - bio->bi_iter.bi_sector, max_sectors);
 	r10_bio->devs[slot].bio = bio;
 	r10_bio->devs[slot].rdev = rdev;
-	bio->bi_sector = r10_bio->devs[slot].addr
+	bio->bi_iter.bi_sector = r10_bio->devs[slot].addr
 		+ choose_data_offset(r10_bio, rdev);
 	bio->bi_bdev = rdev->bdev;
 	bio->bi_rw = READ | do_sync;
@@ -2681,7 +2575,7 @@
 		struct bio *mbio = r10_bio->master_bio;
 		int sectors_handled =
 			r10_bio->sector + max_sectors
-			- mbio->bi_sector;
+			- mbio->bi_iter.bi_sector;
 		r10_bio->sectors = max_sectors;
 		spin_lock_irq(&conf->device_lock);
 		if (mbio->bi_phys_segments == 0)
@@ -2699,7 +2593,7 @@
 		set_bit(R10BIO_ReadError,
 			&r10_bio->state);
 		r10_bio->mddev = mddev;
-		r10_bio->sector = mbio->bi_sector
+		r10_bio->sector = mbio->bi_iter.bi_sector
 			+ sectors_handled;
 
 		goto read_more;
@@ -2725,8 +2619,7 @@
 			rdev = conf->mirrors[dev].rdev;
 			if (r10_bio->devs[m].bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].bio->bi_flags)) {
+			if (!r10_bio->devs[m].bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
@@ -2741,8 +2634,8 @@
 			rdev = conf->mirrors[dev].replacement;
 			if (r10_bio->devs[m].repl_bio == NULL)
 				continue;
-			if (test_bit(BIO_UPTODATE,
-				     &r10_bio->devs[m].repl_bio->bi_flags)) {
+
+			if (!r10_bio->devs[m].repl_bio->bi_error) {
 				rdev_clear_badblocks(
 					rdev,
 					r10_bio->devs[m].addr,
@@ -2757,6 +2650,7 @@
 		}
 		put_buf(r10_bio);
 	} else {
+		bool fail = false;
 		for (m = 0; m < conf->copies; m++) {
 			int dev = r10_bio->devs[m].devnum;
 			struct bio *bio = r10_bio->devs[m].bio;
@@ -2767,8 +2661,8 @@
 					r10_bio->devs[m].addr,
 					r10_bio->sectors, 0);
 				rdev_dec_pending(rdev, conf->mddev);
-			} else if (bio != NULL &&
-				   !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+			} else if (bio != NULL && bio->bi_error) {
+				fail = true;
 				if (!narrow_write_error(r10_bio, m)) {
 					md_error(conf->mddev, rdev);
 					set_bit(R10BIO_Degraded,
@@ -2786,10 +2680,18 @@
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 		}
-		if (test_bit(R10BIO_WriteError,
-			     &r10_bio->state))
-			close_write(r10_bio);
-		raid_end_bio_io(r10_bio);
+		if (fail) {
+			spin_lock_irq(&conf->device_lock);
+			list_add(&r10_bio->retry_list, &conf->bio_end_io_list);
+			conf->nr_queued++;
+			spin_unlock_irq(&conf->device_lock);
+			md_wakeup_thread(conf->mddev->thread);
+		} else {
+			if (test_bit(R10BIO_WriteError,
+				     &r10_bio->state))
+				close_write(r10_bio);
+			raid_end_bio_io(r10_bio);
+		}
 	}
 }
 
@@ -2804,6 +2706,31 @@
 
 	md_check_recovery(mddev);
 
+	if (!list_empty_careful(&conf->bio_end_io_list) &&
+	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		LIST_HEAD(tmp);
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+			while (!list_empty(&conf->bio_end_io_list)) {
+				list_move(conf->bio_end_io_list.prev, &tmp);
+				conf->nr_queued--;
+			}
+		}
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+		while (!list_empty(&tmp)) {
+			r10_bio = list_first_entry(&tmp, struct r10bio,
+						   retry_list);
+			list_del(&r10_bio->retry_list);
+			if (mddev->degraded)
+				set_bit(R10BIO_Degraded, &r10_bio->state);
+
+			if (test_bit(R10BIO_WriteError,
+				     &r10_bio->state))
+				close_write(r10_bio);
+			raid_end_bio_io(r10_bio);
+		}
+	}
+
 	blk_start_plug(&plug);
 	for (;;) {
 
@@ -2847,7 +2774,6 @@
 	blk_finish_plug(&plug);
 }
 
-
 static int init_resync(struct r10conf *conf)
 {
 	int buffs;
@@ -2899,7 +2825,7 @@
  */
 
 static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
-			     int *skipped, int go_faster)
+			     int *skipped)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
@@ -3004,12 +2930,6 @@
 	if (conf->geo.near_copies < conf->geo.raid_disks &&
 	    max_sector > (sector_nr | chunk_mask))
 		max_sector = (sector_nr | chunk_mask) + 1;
-	/*
-	 * If there is non-resync activity waiting for us then
-	 * put in a delay to throttle resync.
-	 */
-	if (!go_faster && conf->nr_waiting)
-		msleep_interruptible(1000);
 
 	/* Again, very different code for resync and recovery.
 	 * Both must result in an r10bio with a list of bios that
@@ -3077,6 +2997,7 @@
 			}
 
 			r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+			r10_bio->state = 0;
 			raise_barrier(conf, rb2 != NULL);
 			atomic_set(&r10_bio->remaining, 0);
 
@@ -3138,7 +3059,8 @@
 				bio->bi_end_io = end_sync_read;
 				bio->bi_rw = READ;
 				from_addr = r10_bio->devs[j].addr;
-				bio->bi_sector = from_addr + rdev->data_offset;
+				bio->bi_iter.bi_sector = from_addr +
+					rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
 				atomic_inc(&rdev->nr_pending);
 				/* and we write to 'i' (if not in_sync) */
@@ -3162,7 +3084,7 @@
 					bio->bi_private = r10_bio;
 					bio->bi_end_io = end_sync_write;
 					bio->bi_rw = WRITE;
-					bio->bi_sector = to_addr
+					bio->bi_iter.bi_sector = to_addr
 						+ rdev->data_offset;
 					bio->bi_bdev = rdev->bdev;
 					atomic_inc(&r10_bio->remaining);
@@ -3191,7 +3113,8 @@
 				bio->bi_private = r10_bio;
 				bio->bi_end_io = end_sync_write;
 				bio->bi_rw = WRITE;
-				bio->bi_sector = to_addr + rdev->data_offset;
+				bio->bi_iter.bi_sector = to_addr +
+					rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
 				atomic_inc(&r10_bio->remaining);
 				break;
@@ -3250,7 +3173,7 @@
 		/* resync. Schedule a read for every block at this virt offset */
 		int count = 0;
 
-		bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+		bitmap_cond_end_sync(mddev->bitmap, sector_nr, 0);
 
 		if (!bitmap_start_sync(mddev->bitmap, sector_nr,
 				       &sync_blocks, mddev->degraded) &&
@@ -3263,6 +3186,7 @@
 		if (sync_blocks < max_sync)
 			max_sync = sync_blocks;
 		r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+		r10_bio->state = 0;
 
 		r10_bio->mddev = mddev;
 		atomic_set(&r10_bio->remaining, 0);
@@ -3285,7 +3209,7 @@
 
 			bio = r10_bio->devs[i].bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
 				continue;
@@ -3309,7 +3233,7 @@
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_read;
 			bio->bi_rw = READ;
-			bio->bi_sector = sector +
+			bio->bi_iter.bi_sector = sector +
 				conf->mirrors[d].rdev->data_offset;
 			bio->bi_bdev = conf->mirrors[d].rdev->bdev;
 			count++;
@@ -3322,7 +3246,7 @@
 			/* Need to set up for writing to the replacement */
 			bio = r10_bio->devs[i].repl_bio;
 			bio_reset(bio);
-			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = -EIO;
 
 			sector = r10_bio->devs[i].addr;
 			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
@@ -3331,7 +3255,7 @@
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_write;
 			bio->bi_rw = WRITE;
-			bio->bi_sector = sector +
+			bio->bi_iter.bi_sector = sector +
 				conf->mirrors[d].replacement->data_offset;
 			bio->bi_bdev = conf->mirrors[d].replacement->bdev;
 			count++;
@@ -3378,8 +3302,8 @@
 			     bio2 = bio2->bi_next) {
 				/* remove last page from this bio */
 				bio2->bi_vcnt--;
-				bio2->bi_size -= len;
-				bio2->bi_flags &= ~(1<< BIO_SEG_VALID);
+				bio2->bi_iter.bi_size -= len;
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
@@ -3399,7 +3323,7 @@
 
 		if (bio->bi_end_io == end_sync_read) {
 			md_sync_acct(bio->bi_bdev, nr_sectors);
-			set_bit(BIO_UPTODATE, &bio->bi_flags);
+			bio->bi_error = 0;
 			generic_make_request(bio);
 		}
 	}
@@ -3499,7 +3423,7 @@
 		disks = mddev->raid_disks + mddev->delta_disks;
 		break;
 	}
-	if (layout >> 18)
+	if (layout >> 19)
 		return -1;
 	if (chunk < (PAGE_SIZE >> 9) ||
 	    !is_power_of_2(chunk))
@@ -3511,7 +3435,22 @@
 	geo->near_copies = nc;
 	geo->far_copies = fc;
 	geo->far_offset = fo;
-	geo->far_set_size = (layout & (1<<17)) ? disks / fc : disks;
+	switch (layout >> 17) {
+	case 0:	/* original layout.  simple but not always optimal */
+		geo->far_set_size = disks;
+		break;
+	case 1: /* "improved" layout which was buggy.  Hopefully no-one is
+		 * actually using this, but leave code here just in case.*/
+		geo->far_set_size = disks/fc;
+		WARN(geo->far_set_size < fc,
+		     "This RAID10 layout does not provide data safety - please backup and create new array\n");
+		break;
+	case 2: /* "improved" layout fixed to match documentation */
+		geo->far_set_size = fc * nc;
+		break;
+	default: /* Not a valid layout */
+		return -1;
+	}
 	geo->chunk_mask = chunk - 1;
 	geo->chunk_shift = ffz(~chunk);
 	return nc*fc;
@@ -3581,6 +3520,7 @@
 	conf->reshape_safe = conf->reshape_progress;
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
+	INIT_LIST_HEAD(&conf->bio_end_io_list);
 
 	spin_lock_init(&conf->resync_lock);
 	init_waitqueue_head(&conf->wait_barrier);
@@ -3597,8 +3537,7 @@
 		printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
 		       mdname(mddev));
 	if (conf) {
-		if (conf->r10bio_pool)
-			mempool_destroy(conf->r10bio_pool);
+		mempool_destroy(conf->r10bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
 		kfree(conf);
@@ -3665,8 +3604,6 @@
 			disk->rdev = rdev;
 		}
 		q = bdev_get_queue(rdev->bdev);
-		if (q->merge_bvec_fn)
-			mddev->merge_check_needed = 1;
 		diff = (rdev->new_data_offset - rdev->data_offset);
 		if (!mddev->reshape_backwards)
 			diff = -diff;
@@ -3729,7 +3666,8 @@
 		    !test_bit(In_sync, &disk->rdev->flags)) {
 			disk->head_position = 0;
 			mddev->degraded++;
-			if (disk->rdev)
+			if (disk->rdev &&
+			    disk->rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
 		}
 		disk->recovery_disabled = mddev->recovery_disabled - 1;
@@ -3754,8 +3692,6 @@
 	if (mddev->queue) {
 		int stripe = conf->geo.raid_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		mddev->queue->backing_dev_info.congested_fn = raid10_congested;
-		mddev->queue->backing_dev_info.congested_data = mddev;
 
 		/* Calculate max read-ahead size.
 		 * We need to readahead at least twice a whole stripe....
@@ -3764,10 +3700,8 @@
 		stripe /= conf->geo.near_copies;
 		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
-		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
 	}
 
-
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
 
@@ -3798,8 +3732,7 @@
 
 out_free_conf:
 	md_unregister_thread(&mddev->thread);
-	if (conf->r10bio_pool)
-		mempool_destroy(conf->r10bio_pool);
+	mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf);
@@ -3808,25 +3741,16 @@
 	return -EIO;
 }
 
-static int stop(struct mddev *mddev)
+static void raid10_free(struct mddev *mddev, void *priv)
 {
-	struct r10conf *conf = mddev->private;
+	struct r10conf *conf = priv;
 
-	raise_barrier(conf, 0);
-	lower_barrier(conf);
-
-	md_unregister_thread(&mddev->thread);
-	if (mddev->queue)
-		/* the unplug fn references 'conf'*/
-		blk_sync_queue(mddev->queue);
-
-	if (conf->r10bio_pool)
-		mempool_destroy(conf->r10bio_pool);
+	mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
+	kfree(conf->mirrors_old);
+	kfree(conf->mirrors_new);
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 static void raid10_quiesce(struct mddev *mddev, int state)
@@ -3890,7 +3814,7 @@
 	return 0;
 }
 
-static void *raid10_takeover_raid0(struct mddev *mddev)
+static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs)
 {
 	struct md_rdev *rdev;
 	struct r10conf *conf;
@@ -3900,6 +3824,7 @@
 		       mdname(mddev));
 		return ERR_PTR(-EINVAL);
 	}
+	sector_div(size, devs);
 
 	/* Set new parameters */
 	mddev->new_level = 10;
@@ -3910,12 +3835,15 @@
 	mddev->raid_disks *= 2;
 	/* make sure it will be not marked as dirty */
 	mddev->recovery_cp = MaxSector;
+	mddev->dev_sectors = size;
 
 	conf = setup_conf(mddev);
 	if (!IS_ERR(conf)) {
 		rdev_for_each(rdev, mddev)
-			if (rdev->raid_disk >= 0)
+			if (rdev->raid_disk >= 0) {
 				rdev->new_raid_disk = rdev->raid_disk * 2;
+				rdev->sectors = size;
+			}
 		conf->barrier = 1;
 	}
 
@@ -3938,7 +3866,9 @@
 			       mdname(mddev));
 			return ERR_PTR(-EINVAL);
 		}
-		return raid10_takeover_raid0(mddev);
+		return raid10_takeover_raid0(mddev,
+			raid0_conf->strip_zone->zone_end,
+			raid0_conf->strip_zone->nb_dev);
 	}
 	return ERR_PTR(-EINVAL);
 }
@@ -4111,7 +4041,7 @@
 		memcpy(conf->mirrors_new, conf->mirrors,
 		       sizeof(struct raid10_info)*conf->prev.raid_disks);
 		smp_mb();
-		kfree(conf->mirrors_old); /* FIXME and elsewhere */
+		kfree(conf->mirrors_old);
 		conf->mirrors_old = conf->mirrors;
 		conf->mirrors = conf->mirrors_new;
 		conf->mirrors_new = NULL;
@@ -4174,6 +4104,7 @@
 
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 
@@ -4241,7 +4172,7 @@
 	 * at a time, possibly less if that exceeds RESYNC_PAGES,
 	 * or we hit a bad block or something.
 	 * This might mean we pause for normal IO in the middle of
-	 * a chunk, but that is not a problem was mddev->reshape_position
+	 * a chunk, but that is not a problem as mddev->reshape_position
 	 * can record any location.
 	 *
 	 * If we will want to write to a location that isn't
@@ -4265,7 +4196,7 @@
 	 *
 	 * In all this the minimum difference in data offsets
 	 * (conf->offset_diff - always positive) allows a bit of slack,
-	 * so next can be after 'safe', but not by more than offset_disk
+	 * so next can be after 'safe', but not by more than offset_diff
 	 *
 	 * We need to prepare all the bios here before we start any IO
 	 * to ensure the size we choose is acceptable to all devices.
@@ -4367,7 +4298,11 @@
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
 		wait_event(mddev->sb_wait, mddev->flags == 0 ||
-			   kthread_should_stop());
+			   test_bit(MD_RECOVERY_INTR, &mddev->recovery));
+		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+			allow_barrier(conf);
+			return sectors_done;
+		}
 		conf->reshape_safe = mddev->reshape_position;
 		allow_barrier(conf);
 	}
@@ -4375,6 +4310,7 @@
 read_more:
 	/* Now schedule reads for blocks from sector_nr to last */
 	r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+	r10_bio->state = 0;
 	raise_barrier(conf, sectors_done != 0);
 	atomic_set(&r10_bio->remaining, 0);
 	r10_bio->mddev = mddev;
@@ -4389,6 +4325,7 @@
 		 * on all the target devices.
 		 */
 		// FIXME
+		mempool_free(r10_bio, conf->r10buf_pool);
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 		return sectors_done;
 	}
@@ -4396,15 +4333,15 @@
 	read_bio = bio_alloc_mddev(GFP_KERNEL, RESYNC_PAGES, mddev);
 
 	read_bio->bi_bdev = rdev->bdev;
-	read_bio->bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
+	read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
 			       + rdev->data_offset);
 	read_bio->bi_private = r10_bio;
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
-	read_bio->bi_flags |= 1 << BIO_UPTODATE;
+	read_bio->bi_error = 0;
 	read_bio->bi_vcnt = 0;
-	read_bio->bi_size = 0;
+	read_bio->bi_iter.bi_size = 0;
 	r10_bio->master_bio = read_bio;
 	r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum;
 
@@ -4430,7 +4367,8 @@
 
 		bio_reset(b);
 		b->bi_bdev = rdev2->bdev;
-		b->bi_sector = r10_bio->devs[s/2].addr + rdev2->new_data_offset;
+		b->bi_iter.bi_sector = r10_bio->devs[s/2].addr +
+			rdev2->new_data_offset;
 		b->bi_private = r10_bio;
 		b->bi_end_io = end_reshape_write;
 		b->bi_rw = WRITE;
@@ -4457,8 +4395,8 @@
 			     bio2 = bio2->bi_next) {
 				/* Remove last page from this bio */
 				bio2->bi_vcnt--;
-				bio2->bi_size -= len;
-				bio2->bi_flags &= ~(1<<BIO_SEG_VALID);
+				bio2->bi_iter.bi_size -= len;
+				bio_clear_flag(bio2, BIO_SEG_VALID);
 			}
 			goto bio_full;
 		}
@@ -4561,7 +4499,6 @@
 	conf->fullsync = 0;
 }
 
-
 static int handle_reshape_read_error(struct mddev *mddev,
 				     struct r10bio *r10_bio)
 {
@@ -4624,9 +4561,8 @@
 	return 0;
 }
 
-static void end_reshape_write(struct bio *bio, int error)
+static void end_reshape_write(struct bio *bio)
 {
-	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct r10bio *r10_bio = bio->bi_private;
 	struct mddev *mddev = r10_bio->mddev;
 	struct r10conf *conf = mddev->private;
@@ -4643,7 +4579,7 @@
 		rdev = conf->mirrors[d].rdev;
 	}
 
-	if (!uptodate) {
+	if (bio->bi_error) {
 		/* FIXME should record badblock */
 		md_error(mddev, rdev);
 	}
@@ -4705,7 +4641,7 @@
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= raid10_free,
 	.status		= status,
 	.error_handler	= error,
 	.hot_add_disk	= raid10_add_disk,
@@ -4719,6 +4655,7 @@
 	.check_reshape	= raid10_check_reshape,
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
+	.congested	= raid10_congested,
 };
 
 static int __init raid_init(void)