1 files changed, 225 insertions, 203 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 77b562d18a9..cb882aae9e2 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -97,7 +97,7 @@ static int max_queued_requests = 1024;
 
 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);
@@ -392,11 +392,9 @@ static void raid10_end_read_request(struct bio *bio, int error)
 		 * 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);
@@ -490,7 +488,17 @@ static void raid10_end_write_request(struct bio *bio, int error)
 		sector_t first_bad;
 		int bad_sectors;
 
-		set_bit(R10BIO_Uptodate, &r10_bio->state);
+		/*
+		 * Do not set R10BIO_Uptodate if the current device is
+		 * rebuilding or Faulty. This is because we cannot use
+		 * such device for properly reading the data back (we could
+		 * potentially use it, if the current write would have felt
+		 * before rdev->recovery_offset, but for simplicity we don't
+		 * check this here.
+		 */
+		if (test_bit(In_sync, &rdev->flags) &&
+		    !test_bit(Faulty, &rdev->flags))
+			set_bit(R10BIO_Uptodate, &r10_bio->state);
 
 		/* Maybe we can clear some bad blocks. */
 		if (is_badblock(rdev,
@@ -1055,17 +1063,17 @@ static void allow_barrier(struct r10conf *conf)
 	wake_up(&conf->wait_barrier);
 }
 
-static void freeze_array(struct r10conf *conf)
+static void freeze_array(struct r10conf *conf, int extra)
 {
 	/* stop syncio and normal IO and wait for everything to
 	 * go quiet.
 	 * We increment barrier and nr_waiting, and then
-	 * wait until nr_pending match nr_queued+1
+	 * wait until nr_pending match nr_queued+extra
 	 * This is called in the context of one normal IO request
 	 * that has failed. Thus any sync request that might be pending
 	 * will be blocked by nr_pending, and we need to wait for
 	 * pending IO requests to complete or be queued for re-try.
-	 * Thus the number queued (nr_queued) plus this request (1)
+	 * Thus the number queued (nr_queued) plus this request (extra)
 	 * must match the number of pending IOs (nr_pending) before
 	 * we continue.
 	 */
@@ -1073,7 +1081,7 @@ static void freeze_array(struct r10conf *conf)
 	conf->barrier++;
 	conf->nr_waiting++;
 	wait_event_lock_irq_cmd(conf->wait_barrier,
-				conf->nr_pending == conf->nr_queued+1,
+				conf->nr_pending == conf->nr_queued+extra,
 				conf->resync_lock,
 				flush_pending_writes(conf));
 
@@ -1133,20 +1141,23 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
 		bio->bi_next = NULL;
-		generic_make_request(bio);
+		if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+		    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+			/* Just ignore it */
+			bio_endio(bio, 0);
+		else
+			generic_make_request(bio);
 		bio = next;
 	}
 	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);
@@ -1161,62 +1172,6 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	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->bi_size >> 9)
-		     > 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->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
-		    bio->bi_idx != 0)
-			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->bi_size >> 10);
-
-		bio_io_error(bio);
-		return;
-	}
-
-	md_write_start(mddev, bio);
-
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
@@ -1224,26 +1179,27 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	 */
 	wait_barrier(conf);
 
-	sectors = bio->bi_size >> 9;
+	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);
@@ -1261,7 +1217,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	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
@@ -1290,13 +1246,13 @@ read_again:
 		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;
@@ -1307,15 +1263,15 @@ read_again:
 			/* Could not read all from this device, so we will
 			 * need another r10_bio.
 			 */
-			sectors_handled = (r10_bio->sectors + max_sectors
-					   - bio->bi_sector);
+			sectors_handled = (r10_bio->sector + max_sectors
+					   - bio->bi_iter.bi_sector);
 			r10_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
 			if (bio->bi_phys_segments == 0)
 				bio->bi_phys_segments = 2;
 			else
 				bio->bi_phys_segments++;
-			spin_unlock(&conf->device_lock);
+			spin_unlock_irq(&conf->device_lock);
 			/* Cannot call generic_make_request directly
 			 * as that will be queued in __generic_make_request
 			 * and subsequent mempool_alloc might block
@@ -1326,11 +1282,11 @@ read_again:
 			r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
 			r10_bio->master_bio = bio;
-			r10_bio->sectors = ((bio->bi_size >> 9)
-					    - sectors_handled);
+			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);
@@ -1488,7 +1444,8 @@ retry_write:
 			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);
@@ -1499,11 +1456,11 @@ retry_write:
 		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;
@@ -1542,11 +1499,11 @@ retry_write:
 				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;
@@ -1569,7 +1526,7 @@ retry_write:
 	 * after checking if we need to go around again.
 	 */
 
-	if (sectors_handled < (bio->bi_size >> 9)) {
+	if (sectors_handled < bio_sectors(bio)) {
 		one_write_done(r10_bio);
 		/* We need another r10_bio.  It has already been counted
 		 * in bio->bi_phys_segments.
@@ -1577,14 +1534,54 @@ retry_write:
 		r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
 
 		r10_bio->master_bio = bio;
-		r10_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+		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;
+	}
+
+	md_write_start(mddev, bio);
+
+
+	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;
+		}
+
+		__make_request(mddev, split);
+	} while (split != bio);
 
 	/* In case raid10d snuck in to freeze_array */
 	wake_up(&conf->wait_barrier);
@@ -1619,37 +1616,58 @@ static void status(struct seq_file *seq, struct mddev *mddev)
  * 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
@@ -1657,18 +1675,18 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 	 * 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.
 		 */
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		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);
-		/*
+			/*
 		 * if recovery is running, make sure it aborts.
 		 */
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
@@ -1676,6 +1694,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &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",
@@ -1749,6 +1768,7 @@ static int raid10_spare_active(struct mddev *mddev)
 			}
 			sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
 		} else if (tmp->rdev
+			   && tmp->rdev->recovery_offset == MaxSector
 			   && !test_bit(Faulty, &tmp->rdev->flags)
 			   && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
 			count++;
@@ -1778,7 +1798,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * 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 (rdev->raid_disk >= 0)
@@ -1806,15 +1826,17 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			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;
@@ -1834,8 +1856,8 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		 * we wait for all outstanding requests to complete.
 		 */
 		synchronize_sched();
-		raise_barrier(conf, 0);
-		lower_barrier(conf);
+		freeze_array(conf, 0);
+		unfreeze_array(conf);
 		clear_bit(Unmerged, &rdev->flags);
 	}
 	md_integrity_add_rdev(rdev, mddev);
@@ -2062,11 +2084,17 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 			 * both 'first' and 'i', so we just compare them.
 			 * All vec entries are PAGE_SIZE;
 			 */
-			for (j = 0; j < vcnt; j++)
+			int sectors = r10_bio->sectors;
+			for (j = 0; j < vcnt; j++) {
+				int len = PAGE_SIZE;
+				if (sectors < (len / 512))
+					len = sectors * 512;
 				if (memcmp(page_address(fbio->bi_io_vec[j].bv_page),
 					   page_address(tbio->bi_io_vec[j].bv_page),
-					   fbio->bi_io_vec[j].bv_len))
+					   len))
 					break;
+				sectors -= len/512;
+			}
 			if (j == vcnt)
 				continue;
 			atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
@@ -2079,16 +2107,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		 * First we need to fixup bv_offset, bv_len and
 		 * bi_vecs, as the read request might have corrupted these
 		 */
+		bio_reset(tbio);
+
 		tbio->bi_vcnt = vcnt;
-		tbio->bi_size = r10_bio->sectors << 9;
-		tbio->bi_idx = 0;
-		tbio->bi_phys_segments = 0;
-		tbio->bi_flags &= ~(BIO_POOL_MASK - 1);
-		tbio->bi_flags |= 1 << BIO_UPTODATE;
-		tbio->bi_next = NULL;
+		tbio->bi_iter.bi_size = r10_bio->sectors << 9;
 		tbio->bi_rw = WRITE;
 		tbio->bi_private = r10_bio;
-		tbio->bi_sector = r10_bio->devs[i].addr;
+		tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
 
 		for (j=0; j < vcnt ; j++) {
 			tbio->bi_io_vec[j].bv_offset = 0;
@@ -2103,9 +2128,9 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		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, tbio->bi_size >> 9);
+		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);
 	}
@@ -2128,7 +2153,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		d = r10_bio->devs[i].devnum;
 		atomic_inc(&r10_bio->remaining);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     tbio->bi_size >> 9);
+			     bio_sectors(tbio));
 		generic_make_request(tbio);
 	}
 
@@ -2252,15 +2277,21 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	d = r10_bio->devs[1].devnum;
 	wbio = r10_bio->devs[1].bio;
 	wbio2 = r10_bio->devs[1].repl_bio;
+	/* Need to test wbio2->bi_end_io before we call
+	 * generic_make_request as if the former is NULL,
+	 * the latter is free to free wbio2.
+	 */
+	if (wbio2 && !wbio2->bi_end_io)
+		wbio2 = NULL;
 	if (wbio->bi_end_io) {
 		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
-		md_sync_acct(conf->mirrors[d].rdev->bdev, wbio->bi_size >> 9);
+		md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
 		generic_make_request(wbio);
 	}
-	if (wbio2 && wbio2->bi_end_io) {
+	if (wbio2) {
 		atomic_inc(&conf->mirrors[d].replacement->nr_pending);
 		md_sync_acct(conf->mirrors[d].replacement->bdev,
-			     wbio2->bi_size >> 9);
+			     bio_sectors(wbio2));
 		generic_make_request(wbio2);
 	}
 }
@@ -2531,25 +2562,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	}
 }
 
-static void bi_complete(struct bio *bio, int error)
-{
-	complete((struct completion *)bio->bi_private);
-}
-
-static int submit_bio_wait(int rw, struct bio *bio)
-{
-	struct completion event;
-	rw |= REQ_SYNC;
-
-	init_completion(&event);
-	bio->bi_private = &event;
-	bio->bi_end_io = bi_complete;
-	submit_bio(rw, bio);
-	wait_for_completion(&event);
-
-	return test_bit(BIO_UPTODATE, &bio->bi_flags);
-}
-
 static int narrow_write_error(struct r10bio *r10_bio, int i)
 {
 	struct bio *bio = r10_bio->master_bio;
@@ -2588,8 +2600,8 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 			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;
@@ -2631,7 +2643,7 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 	r10_bio->devs[slot].bio = NULL;
 
 	if (mddev->ro == 0) {
-		freeze_array(conf);
+		freeze_array(conf, 1);
 		fix_read_error(conf, mddev, r10_bio);
 		unfreeze_array(conf);
 	} else
@@ -2661,12 +2673,10 @@ read_more:
 		(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;
@@ -2677,7 +2687,7 @@ read_more:
 		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)
@@ -2690,13 +2700,12 @@ read_more:
 		r10_bio = mempool_alloc(conf->r10bio_pool,
 					GFP_NOIO);
 		r10_bio->master_bio = mbio;
-		r10_bio->sectors = (mbio->bi_size >> 9)
-			- sectors_handled;
+		r10_bio->sectors = bio_sectors(mbio) - sectors_handled;
 		r10_bio->state = 0;
 		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;
@@ -2913,6 +2922,21 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (init_resync(conf))
 			return 0;
 
+	/*
+	 * Allow skipping a full rebuild for incremental assembly
+	 * of a clean array, like RAID1 does.
+	 */
+	if (mddev->bitmap == NULL &&
+	    mddev->recovery_cp == MaxSector &&
+	    mddev->reshape_position == MaxSector &&
+	    !test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	    conf->fullsync == 0) {
+		*skipped = 1;
+		return mddev->dev_sectors - sector_nr;
+	}
+
  skipped:
 	max_sector = mddev->dev_sectors;
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
@@ -3112,13 +3136,15 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 					}
 				}
 				bio = r10_bio->devs[0].bio;
+				bio_reset(bio);
 				bio->bi_next = biolist;
 				biolist = bio;
 				bio->bi_private = r10_bio;
 				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) */
@@ -3136,12 +3162,13 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				rdev = mirror->rdev;
 				if (!test_bit(In_sync, &rdev->flags)) {
 					bio = r10_bio->devs[1].bio;
+					bio_reset(bio);
 					bio->bi_next = biolist;
 					biolist = bio;
 					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);
@@ -3164,12 +3191,14 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				if (rdev == NULL || bio == NULL ||
 				    test_bit(Faulty, &rdev->flags))
 					break;
+				bio_reset(bio);
 				bio->bi_next = biolist;
 				biolist = bio;
 				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;
@@ -3177,10 +3206,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
-				put_buf(r10_bio);
-				if (rb2)
-					atomic_dec(&rb2->remaining);
-				r10_bio = rb2;
 				if (any_working) {
 					/* problem is that there are bad blocks
 					 * on other device(s)
@@ -3212,6 +3237,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 					mirror->recovery_disabled
 						= mddev->recovery_disabled;
 				}
+				put_buf(r10_bio);
+				if (rb2)
+					atomic_dec(&rb2->remaining);
+				r10_bio = rb2;
 				break;
 			}
 		}
@@ -3262,7 +3291,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				r10_bio->devs[i].repl_bio->bi_end_io = NULL;
 
 			bio = r10_bio->devs[i].bio;
-			bio->bi_end_io = NULL;
+			bio_reset(bio);
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 			if (conf->mirrors[d].rdev == NULL ||
 			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
@@ -3287,7 +3316,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			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++;
@@ -3299,6 +3328,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 			/* 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);
 
 			sector = r10_bio->devs[i].addr;
@@ -3308,7 +3338,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			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++;
@@ -3332,17 +3362,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 		}
 	}
 
-	for (bio = biolist; bio ; bio=bio->bi_next) {
-
-		bio->bi_flags &= ~(BIO_POOL_MASK - 1);
-		if (bio->bi_end_io)
-			bio->bi_flags |= 1 << BIO_UPTODATE;
-		bio->bi_vcnt = 0;
-		bio->bi_idx = 0;
-		bio->bi_phys_segments = 0;
-		bio->bi_size = 0;
-	}
-
 	nr_sectors = 0;
 	if (sector_nr + max_sync < max_sector)
 		max_sector = sector_nr + max_sync;
@@ -3366,7 +3385,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			     bio2 = bio2->bi_next) {
 				/* remove last page from this bio */
 				bio2->bi_vcnt--;
-				bio2->bi_size -= len;
+				bio2->bi_iter.bi_size -= len;
 				bio2->bi_flags &= ~(1<< BIO_SEG_VALID);
 			}
 			goto bio_full;
@@ -3387,6 +3406,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 
 		if (bio->bi_end_io == end_sync_read) {
 			md_sync_acct(bio->bi_bdev, nr_sectors);
+			set_bit(BIO_UPTODATE, &bio->bi_flags);
 			generic_make_request(bio);
 		}
 	}
@@ -3533,7 +3553,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 
 	/* FIXME calc properly */
 	conf->mirrors = kzalloc(sizeof(struct raid10_info)*(mddev->raid_disks +
-							    max(0,mddev->delta_disks)),
+							    max(0,-mddev->delta_disks)),
 				GFP_KERNEL);
 	if (!conf->mirrors)
 		goto out;
@@ -3620,8 +3640,7 @@ static int run(struct mddev *mddev)
 	if (mddev->queue) {
 		blk_queue_max_discard_sectors(mddev->queue,
 					      mddev->chunk_sectors);
-		blk_queue_max_write_same_sectors(mddev->queue,
-						 mddev->chunk_sectors);
+		blk_queue_max_write_same_sectors(mddev->queue, 0);
 		blk_queue_io_min(mddev->queue, chunk_size);
 		if (conf->geo.raid_disks % conf->geo.near_copies)
 			blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
@@ -3693,7 +3712,7 @@ static int run(struct mddev *mddev)
 		    conf->geo.far_offset == 0)
 			goto out_free_conf;
 		if (conf->prev.far_copies != 1 &&
-		    conf->geo.far_offset == 0)
+		    conf->prev.far_offset == 0)
 			goto out_free_conf;
 	}
 
@@ -3716,7 +3735,8 @@ static int run(struct mddev *mddev)
 		    !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;
@@ -3810,6 +3830,7 @@ static int stop(struct mddev *mddev)
 
 	if (conf->r10bio_pool)
 		mempool_destroy(conf->r10bio_pool);
+	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf);
 	mddev->private = NULL;
@@ -4352,7 +4373,11 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 		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);
 	}
@@ -4381,7 +4406,7 @@ read_more:
 	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;
@@ -4389,8 +4414,7 @@ read_more:
 	read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
 	read_bio->bi_flags |= 1 << BIO_UPTODATE;
 	read_bio->bi_vcnt = 0;
-	read_bio->bi_idx = 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;
 
@@ -4413,17 +4437,15 @@ read_more:
 		}
 		if (!rdev2 || test_bit(Faulty, &rdev2->flags))
 			continue;
+
+		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;
-		b->bi_flags &= ~(BIO_POOL_MASK - 1);
-		b->bi_flags |= 1 << BIO_UPTODATE;
 		b->bi_next = blist;
-		b->bi_vcnt = 0;
-		b->bi_idx = 0;
-		b->bi_size = 0;
 		blist = b;
 	}
 
@@ -4446,7 +4468,7 @@ read_more:
 			     bio2 = bio2->bi_next) {
 				/* Remove last page from this bio */
 				bio2->bi_vcnt--;
-				bio2->bi_size -= len;
+				bio2->bi_iter.bi_size -= len;
 				bio2->bi_flags &= ~(1<<BIO_SEG_VALID);
 			}
 			goto bio_full;