Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block

Pull core block IO changes from Jens Axboe:
 "The major piece in here is the immutable bio_ve series from Kent, the
  rest is fairly minor.  It was supposed to go in last round, but
  various issues pushed it to this release instead.  The pull request
  contains:

   - Various smaller blk-mq fixes from different folks.  Nothing major
     here, just minor fixes and cleanups.

   - Fix for a memory leak in the error path in the block ioctl code
     from Christian Engelmayer.

   - Header export fix from CaiZhiyong.

   - Finally the immutable biovec changes from Kent Overstreet.  This
     enables some nice future work on making arbitrarily sized bios
     possible, and splitting more efficient.  Related fixes to immutable
     bio_vecs:

        - dm-cache immutable fixup from Mike Snitzer.
        - btrfs immutable fixup from Muthu Kumar.

  - bio-integrity fix from Nic Bellinger, which is also going to stable"

* 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits)
  xtensa: fixup simdisk driver to work with immutable bio_vecs
  block/blk-mq-cpu.c: use hotcpu_notifier()
  blk-mq: for_each_* macro correctness
  block: Fix memory leak in rw_copy_check_uvector() handling
  bio-integrity: Fix bio_integrity_verify segment start bug
  block: remove unrelated header files and export symbol
  blk-mq: uses page->list incorrectly
  blk-mq: use __smp_call_function_single directly
  btrfs: fix missing increment of bi_remaining
  Revert "block: Warn and free bio if bi_end_io is not set"
  block: Warn and free bio if bi_end_io is not set
  blk-mq: fix initializing request's start time
  block: blk-mq: don't export blk_mq_free_queue()
  block: blk-mq: make blk_sync_queue support mq
  block: blk-mq: support draining mq queue
  dm cache: increment bi_remaining when bi_end_io is restored
  block: fixup for generic bio chaining
  block: Really silence spurious compiler warnings
  block: Silence spurious compiler warnings
  block: Kill bio_pair_split()
  ...

drivers/md/bcache/bcache.h

@@ -280,7 +280,6 @@ struct bcache_device {
 	unsigned long		sectors_dirty_last;
 	long			sectors_dirty_derivative;
 
-	mempool_t		*unaligned_bvec;
 	struct bio_set		*bio_split;
 
 	unsigned		data_csum:1;
@@ -902,7 +901,6 @@ void bch_bbio_endio(struct cache_set *, struct bio *, int, const char *);
 void bch_bbio_free(struct bio *, struct cache_set *);
 struct bio *bch_bbio_alloc(struct cache_set *);
 
-struct bio *bch_bio_split(struct bio *, int, gfp_t, struct bio_set *);
 void bch_generic_make_request(struct bio *, struct bio_split_pool *);
 void __bch_submit_bbio(struct bio *, struct cache_set *);
 void bch_submit_bbio(struct bio *, struct cache_set *, struct bkey *, unsigned);

drivers/md/bcache/btree.c

@@ -299,7 +299,7 @@ void bch_btree_node_read(struct btree *b)
 
 	bio = bch_bbio_alloc(b->c);
 	bio->bi_rw	= REQ_META|READ_SYNC;
-	bio->bi_size	= KEY_SIZE(&b->key) << 9;
+	bio->bi_iter.bi_size = KEY_SIZE(&b->key) << 9;
 	bio->bi_end_io	= btree_node_read_endio;
 	bio->bi_private	= &cl;
 
@@ -362,7 +362,7 @@ static void btree_node_write_done(struct closure *cl)
 	struct bio_vec *bv;
 	int n;
 
-	__bio_for_each_segment(bv, b->bio, n, 0)
+	bio_for_each_segment_all(bv, b->bio, n)
 		__free_page(bv->bv_page);
 
 	__btree_node_write_done(cl);
@@ -395,7 +395,7 @@ static void do_btree_node_write(struct btree *b)
 	b->bio->bi_end_io	= btree_node_write_endio;
 	b->bio->bi_private	= cl;
 	b->bio->bi_rw		= REQ_META|WRITE_SYNC|REQ_FUA;
-	b->bio->bi_size		= set_blocks(i, b->c) * block_bytes(b->c);
+	b->bio->bi_iter.bi_size	= set_blocks(i, b->c) * block_bytes(b->c);
 	bch_bio_map(b->bio, i);
 
 	/*
@@ -421,7 +421,7 @@ static void do_btree_node_write(struct btree *b)
 		struct bio_vec *bv;
 		void *base = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
 
-		bio_for_each_segment(bv, b->bio, j)
+		bio_for_each_segment_all(bv, b->bio, j)
 			memcpy(page_address(bv->bv_page),
 			       base + j * PAGE_SIZE, PAGE_SIZE);
 

drivers/md/bcache/debug.c

@@ -173,7 +173,8 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 {
 	char name[BDEVNAME_SIZE];
 	struct bio *check;
-	struct bio_vec *bv;
+	struct bio_vec bv, *bv2;
+	struct bvec_iter iter;
 	int i;
 
 	check = bio_clone(bio, GFP_NOIO);
@@ -185,23 +186,23 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 
 	submit_bio_wait(READ_SYNC, check);
 
-	bio_for_each_segment(bv, bio, i) {
-		void *p1 = kmap_atomic(bv->bv_page);
-		void *p2 = page_address(check->bi_io_vec[i].bv_page);
+	bio_for_each_segment(bv, bio, iter) {
+		void *p1 = kmap_atomic(bv.bv_page);
+		void *p2 = page_address(check->bi_io_vec[iter.bi_idx].bv_page);
 
-		cache_set_err_on(memcmp(p1 + bv->bv_offset,
-					p2 + bv->bv_offset,
-					bv->bv_len),
+		cache_set_err_on(memcmp(p1 + bv.bv_offset,
+					p2 + bv.bv_offset,
+					bv.bv_len),
 				 dc->disk.c,
 				 "verify failed at dev %s sector %llu",
 				 bdevname(dc->bdev, name),
-				 (uint64_t) bio->bi_sector);
+				 (uint64_t) bio->bi_iter.bi_sector);
 
 		kunmap_atomic(p1);
 	}
 
-	bio_for_each_segment_all(bv, check, i)
-		__free_page(bv->bv_page);
+	bio_for_each_segment_all(bv2, check, i)
+		__free_page(bv2->bv_page);
 out_put:
 	bio_put(check);
 }

drivers/md/bcache/io.c

@@ -11,178 +11,40 @@
 
 #include <linux/blkdev.h>
 
-static void bch_bi_idx_hack_endio(struct bio *bio, int error)
-{
-	struct bio *p = bio->bi_private;
-
-	bio_endio(p, error);
-	bio_put(bio);
-}
-
-static void bch_generic_make_request_hack(struct bio *bio)
-{
-	if (bio->bi_idx) {
-		struct bio *clone = bio_alloc(GFP_NOIO, bio_segments(bio));
-
-		memcpy(clone->bi_io_vec,
-		       bio_iovec(bio),
-		       bio_segments(bio) * sizeof(struct bio_vec));
-
-		clone->bi_sector	= bio->bi_sector;
-		clone->bi_bdev		= bio->bi_bdev;
-		clone->bi_rw		= bio->bi_rw;
-		clone->bi_vcnt		= bio_segments(bio);
-		clone->bi_size		= bio->bi_size;
-
-		clone->bi_private	= bio;
-		clone->bi_end_io	= bch_bi_idx_hack_endio;
-
-		bio = clone;
-	}
-
-	/*
-	 * Hack, since drivers that clone bios clone up to bi_max_vecs, but our
-	 * bios might have had more than that (before we split them per device
-	 * limitations).
-	 *
-	 * To be taken out once immutable bvec stuff is in.
-	 */
-	bio->bi_max_vecs = bio->bi_vcnt;
-
-	generic_make_request(bio);
-}
-
-/**
- * bch_bio_split - split a bio
- * @bio:	bio to split
- * @sectors:	number of sectors to split from the front of @bio
- * @gfp:	gfp mask
- * @bs:		bio set to allocate from
- *
- * Allocates and returns a new bio which represents @sectors from the start of
- * @bio, and updates @bio to represent the remaining sectors.
- *
- * If bio_sectors(@bio) was less than or equal to @sectors, returns @bio
- * unchanged.
- *
- * The newly allocated bio will point to @bio's bi_io_vec, if the split was on a
- * bvec boundry; it is the caller's responsibility to ensure that @bio is not
- * freed before the split.
- */
-struct bio *bch_bio_split(struct bio *bio, int sectors,
-			  gfp_t gfp, struct bio_set *bs)
-{
-	unsigned idx = bio->bi_idx, vcnt = 0, nbytes = sectors << 9;
-	struct bio_vec *bv;
-	struct bio *ret = NULL;
-
-	BUG_ON(sectors <= 0);
-
-	if (sectors >= bio_sectors(bio))
-		return bio;
-
-	if (bio->bi_rw & REQ_DISCARD) {
-		ret = bio_alloc_bioset(gfp, 1, bs);
-		if (!ret)
-			return NULL;
-		idx = 0;
-		goto out;
-	}
-
-	bio_for_each_segment(bv, bio, idx) {
-		vcnt = idx - bio->bi_idx;
-
-		if (!nbytes) {
-			ret = bio_alloc_bioset(gfp, vcnt, bs);
-			if (!ret)
-				return NULL;
-
-			memcpy(ret->bi_io_vec, bio_iovec(bio),
-			       sizeof(struct bio_vec) * vcnt);
-
-			break;
-		} else if (nbytes < bv->bv_len) {
-			ret = bio_alloc_bioset(gfp, ++vcnt, bs);
-			if (!ret)
-				return NULL;
-
-			memcpy(ret->bi_io_vec, bio_iovec(bio),
-			       sizeof(struct bio_vec) * vcnt);
-
-			ret->bi_io_vec[vcnt - 1].bv_len = nbytes;
-			bv->bv_offset	+= nbytes;
-			bv->bv_len	-= nbytes;
-			break;
-		}
-
-		nbytes -= bv->bv_len;
-	}
-out:
-	ret->bi_bdev	= bio->bi_bdev;
-	ret->bi_sector	= bio->bi_sector;
-	ret->bi_size	= sectors << 9;
-	ret->bi_rw	= bio->bi_rw;
-	ret->bi_vcnt	= vcnt;
-	ret->bi_max_vecs = vcnt;
-
-	bio->bi_sector	+= sectors;
-	bio->bi_size	-= sectors << 9;
-	bio->bi_idx	 = idx;
-
-	if (bio_integrity(bio)) {
-		if (bio_integrity_clone(ret, bio, gfp)) {
-			bio_put(ret);
-			return NULL;
-		}
-
-		bio_integrity_trim(ret, 0, bio_sectors(ret));
-		bio_integrity_trim(bio, bio_sectors(ret), bio_sectors(bio));
-	}
-
-	return ret;
-}
-
 static unsigned bch_bio_max_sectors(struct bio *bio)
 {
-	unsigned ret = bio_sectors(bio);
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned max_segments = min_t(unsigned, BIO_MAX_PAGES,
-				      queue_max_segments(q));
+	struct bio_vec bv;
+	struct bvec_iter iter;
+	unsigned ret = 0, seg = 0;
 
 	if (bio->bi_rw & REQ_DISCARD)
-		return min(ret, q->limits.max_discard_sectors);
+		return min(bio_sectors(bio), q->limits.max_discard_sectors);
 
-	if (bio_segments(bio) > max_segments ||
-	    q->merge_bvec_fn) {
-		struct bio_vec *bv;
-		int i, seg = 0;
+	bio_for_each_segment(bv, bio, iter) {
+		struct bvec_merge_data bvm = {
+			.bi_bdev	= bio->bi_bdev,
+			.bi_sector	= bio->bi_iter.bi_sector,
+			.bi_size	= ret << 9,
+			.bi_rw		= bio->bi_rw,
+		};
 
-		ret = 0;
+		if (seg == min_t(unsigned, BIO_MAX_PAGES,
+				 queue_max_segments(q)))
+			break;
 
-		bio_for_each_segment(bv, bio, i) {
-			struct bvec_merge_data bvm = {
-				.bi_bdev	= bio->bi_bdev,
-				.bi_sector	= bio->bi_sector,
-				.bi_size	= ret << 9,
-				.bi_rw		= bio->bi_rw,
-			};
+		if (q->merge_bvec_fn &&
+		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
+			break;
 
-			if (seg == max_segments)
-				break;
-
-			if (q->merge_bvec_fn &&
-			    q->merge_bvec_fn(q, &bvm, bv) < (int) bv->bv_len)
-				break;
-
-			seg++;
-			ret += bv->bv_len >> 9;
-		}
+		seg++;
+		ret += bv.bv_len >> 9;
 	}
 
 	ret = min(ret, queue_max_sectors(q));
 
 	WARN_ON(!ret);
-	ret = max_t(int, ret, bio_iovec(bio)->bv_len >> 9);
+	ret = max_t(int, ret, bio_iovec(bio).bv_len >> 9);
 
 	return ret;
 }
@@ -193,7 +55,7 @@ static void bch_bio_submit_split_done(struct closure *cl)
 
 	s->bio->bi_end_io = s->bi_end_io;
 	s->bio->bi_private = s->bi_private;
-	bio_endio(s->bio, 0);
+	bio_endio_nodec(s->bio, 0);
 
 	closure_debug_destroy(&s->cl);
 	mempool_free(s, s->p->bio_split_hook);
@@ -232,19 +94,19 @@ void bch_generic_make_request(struct bio *bio, struct bio_split_pool *p)
 	bio_get(bio);
 
 	do {
-		n = bch_bio_split(bio, bch_bio_max_sectors(bio),
-				  GFP_NOIO, s->p->bio_split);
+		n = bio_next_split(bio, bch_bio_max_sectors(bio),
+				   GFP_NOIO, s->p->bio_split);
 
 		n->bi_end_io	= bch_bio_submit_split_endio;
 		n->bi_private	= &s->cl;
 
 		closure_get(&s->cl);
-		bch_generic_make_request_hack(n);
+		generic_make_request(n);
 	} while (n != bio);
 
 	continue_at(&s->cl, bch_bio_submit_split_done, NULL);
 submit:
-	bch_generic_make_request_hack(bio);
+	generic_make_request(bio);
 }
 
 /* Bios with headers */
@@ -272,8 +134,8 @@ void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
 
-	bio->bi_sector	= PTR_OFFSET(&b->key, 0);
-	bio->bi_bdev	= PTR_CACHE(c, &b->key, 0)->bdev;
+	bio->bi_iter.bi_sector	= PTR_OFFSET(&b->key, 0);
+	bio->bi_bdev		= PTR_CACHE(c, &b->key, 0)->bdev;
 
 	b->submit_time_us = local_clock_us();
 	closure_bio_submit(bio, bio->bi_private, PTR_CACHE(c, &b->key, 0));

drivers/md/bcache/journal.c

@@ -51,10 +51,10 @@ reread:		left = ca->sb.bucket_size - offset;
 		len = min_t(unsigned, left, PAGE_SECTORS * 8);
 
 		bio_reset(bio);
-		bio->bi_sector	= bucket + offset;
+		bio->bi_iter.bi_sector	= bucket + offset;
 		bio->bi_bdev	= ca->bdev;
 		bio->bi_rw	= READ;
-		bio->bi_size	= len << 9;
+		bio->bi_iter.bi_size	= len << 9;
 
 		bio->bi_end_io	= journal_read_endio;
 		bio->bi_private = &cl;
@@ -437,13 +437,13 @@ static void do_journal_discard(struct cache *ca)
 		atomic_set(&ja->discard_in_flight, DISCARD_IN_FLIGHT);
 
 		bio_init(bio);
-		bio->bi_sector		= bucket_to_sector(ca->set,
+		bio->bi_iter.bi_sector	= bucket_to_sector(ca->set,
 						ca->sb.d[ja->discard_idx]);
 		bio->bi_bdev		= ca->bdev;
 		bio->bi_rw		= REQ_WRITE|REQ_DISCARD;
 		bio->bi_max_vecs	= 1;
 		bio->bi_io_vec		= bio->bi_inline_vecs;
-		bio->bi_size		= bucket_bytes(ca);
+		bio->bi_iter.bi_size	= bucket_bytes(ca);
 		bio->bi_end_io		= journal_discard_endio;
 
 		closure_get(&ca->set->cl);
@@ -608,10 +608,10 @@ static void journal_write_unlocked(struct closure *cl)
 		atomic_long_add(sectors, &ca->meta_sectors_written);
 
 		bio_reset(bio);
-		bio->bi_sector	= PTR_OFFSET(k, i);
+		bio->bi_iter.bi_sector	= PTR_OFFSET(k, i);
 		bio->bi_bdev	= ca->bdev;
 		bio->bi_rw	= REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH|REQ_FUA;
-		bio->bi_size	= sectors << 9;
+		bio->bi_iter.bi_size = sectors << 9;
 
 		bio->bi_end_io	= journal_write_endio;
 		bio->bi_private = w;

drivers/md/bcache/movinggc.c

@@ -86,7 +86,7 @@ static void moving_init(struct moving_io *io)
 	bio_get(bio);
 	bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
 
-	bio->bi_size		= KEY_SIZE(&io->w->key) << 9;
+	bio->bi_iter.bi_size	= KEY_SIZE(&io->w->key) << 9;
 	bio->bi_max_vecs	= DIV_ROUND_UP(KEY_SIZE(&io->w->key),
 					       PAGE_SECTORS);
 	bio->bi_private		= &io->cl;
@@ -102,7 +102,7 @@ static void write_moving(struct closure *cl)
 	if (!op->error) {
 		moving_init(io);
 
-		io->bio.bio.bi_sector = KEY_START(&io->w->key);
+		io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key);
 		op->write_prio		= 1;
 		op->bio			= &io->bio.bio;
 

drivers/md/bcache/request.c

@@ -197,14 +197,14 @@ static bool verify(struct cached_dev *dc, struct bio *bio)
 
 static void bio_csum(struct bio *bio, struct bkey *k)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
+	struct bvec_iter iter;
 	uint64_t csum = 0;
-	int i;
 
-	bio_for_each_segment(bv, bio, i) {
-		void *d = kmap(bv->bv_page) + bv->bv_offset;
-		csum = bch_crc64_update(csum, d, bv->bv_len);
-		kunmap(bv->bv_page);
+	bio_for_each_segment(bv, bio, iter) {
+		void *d = kmap(bv.bv_page) + bv.bv_offset;
+		csum = bch_crc64_update(csum, d, bv.bv_len);
+		kunmap(bv.bv_page);
 	}
 
 	k->ptr[KEY_PTRS(k)] = csum & (~0ULL >> 1);
@@ -260,7 +260,7 @@ static void bch_data_invalidate(struct closure *cl)
 	struct bio *bio = op->bio;
 
 	pr_debug("invalidating %i sectors from %llu",
-		 bio_sectors(bio), (uint64_t) bio->bi_sector);
+		 bio_sectors(bio), (uint64_t) bio->bi_iter.bi_sector);
 
 	while (bio_sectors(bio)) {
 		unsigned sectors = min(bio_sectors(bio),
@@ -269,11 +269,11 @@ static void bch_data_invalidate(struct closure *cl)
 		if (bch_keylist_realloc(&op->insert_keys, 0, op->c))
 			goto out;
 
-		bio->bi_sector	+= sectors;
-		bio->bi_size	-= sectors << 9;
+		bio->bi_iter.bi_sector	+= sectors;
+		bio->bi_iter.bi_size	-= sectors << 9;
 
 		bch_keylist_add(&op->insert_keys,
-				&KEY(op->inode, bio->bi_sector, sectors));
+				&KEY(op->inode, bio->bi_iter.bi_sector, sectors));
 	}
 
 	op->insert_data_done = true;
@@ -363,14 +363,14 @@ static void bch_data_insert_start(struct closure *cl)
 		k = op->insert_keys.top;
 		bkey_init(k);
 		SET_KEY_INODE(k, op->inode);
-		SET_KEY_OFFSET(k, bio->bi_sector);
+		SET_KEY_OFFSET(k, bio->bi_iter.bi_sector);
 
 		if (!bch_alloc_sectors(op->c, k, bio_sectors(bio),
 				       op->write_point, op->write_prio,
 				       op->writeback))
 			goto err;
 
-		n = bch_bio_split(bio, KEY_SIZE(k), GFP_NOIO, split);
+		n = bio_next_split(bio, KEY_SIZE(k), GFP_NOIO, split);
 
 		n->bi_end_io	= bch_data_insert_endio;
 		n->bi_private	= cl;
@@ -521,7 +521,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	     (bio->bi_rw & REQ_WRITE)))
 		goto skip;
 
-	if (bio->bi_sector & (c->sb.block_size - 1) ||
+	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
 	    bio_sectors(bio) & (c->sb.block_size - 1)) {
 		pr_debug("skipping unaligned io");
 		goto skip;
@@ -545,8 +545,8 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 
 	spin_lock(&dc->io_lock);
 
-	hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash)
-		if (i->last == bio->bi_sector &&
+	hlist_for_each_entry(i, iohash(dc, bio->bi_iter.bi_sector), hash)
+		if (i->last == bio->bi_iter.bi_sector &&
 		    time_before(jiffies, i->jiffies))
 			goto found;
 
@@ -555,8 +555,8 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 	add_sequential(task);
 	i->sequential = 0;
 found:
-	if (i->sequential + bio->bi_size > i->sequential)
-		i->sequential	+= bio->bi_size;
+	if (i->sequential + bio->bi_iter.bi_size > i->sequential)
+		i->sequential	+= bio->bi_iter.bi_size;
 
 	i->last			 = bio_end_sector(bio);
 	i->jiffies		 = jiffies + msecs_to_jiffies(5000);
@@ -605,7 +605,6 @@ struct search {
 	unsigned		insert_bio_sectors;
 
 	unsigned		recoverable:1;
-	unsigned		unaligned_bvec:1;
 	unsigned		write:1;
 	unsigned		read_dirty_data:1;
 
@@ -649,15 +648,15 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	struct bkey *bio_key;
 	unsigned ptr;
 
-	if (bkey_cmp(k, &KEY(s->iop.inode, bio->bi_sector, 0)) <= 0)
+	if (bkey_cmp(k, &KEY(s->iop.inode, bio->bi_iter.bi_sector, 0)) <= 0)
 		return MAP_CONTINUE;
 
 	if (KEY_INODE(k) != s->iop.inode ||
-	    KEY_START(k) > bio->bi_sector) {
+	    KEY_START(k) > bio->bi_iter.bi_sector) {
 		unsigned bio_sectors = bio_sectors(bio);
 		unsigned sectors = KEY_INODE(k) == s->iop.inode
 			? min_t(uint64_t, INT_MAX,
-				KEY_START(k) - bio->bi_sector)
+				KEY_START(k) - bio->bi_iter.bi_sector)
 			: INT_MAX;
 
 		int ret = s->d->cache_miss(b, s, bio, sectors);
@@ -679,14 +678,14 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	if (KEY_DIRTY(k))
 		s->read_dirty_data = true;
 
-	n = bch_bio_split(bio, min_t(uint64_t, INT_MAX,
-				     KEY_OFFSET(k) - bio->bi_sector),
-			  GFP_NOIO, s->d->bio_split);
+	n = bio_next_split(bio, min_t(uint64_t, INT_MAX,
+				      KEY_OFFSET(k) - bio->bi_iter.bi_sector),
+			   GFP_NOIO, s->d->bio_split);
 
 	bio_key = &container_of(n, struct bbio, bio)->key;
 	bch_bkey_copy_single_ptr(bio_key, k, ptr);
 
-	bch_cut_front(&KEY(s->iop.inode, n->bi_sector, 0), bio_key);
+	bch_cut_front(&KEY(s->iop.inode, n->bi_iter.bi_sector, 0), bio_key);
 	bch_cut_back(&KEY(s->iop.inode, bio_end_sector(n), 0), bio_key);
 
 	n->bi_end_io	= bch_cache_read_endio;
@@ -713,7 +712,7 @@ static void cache_lookup(struct closure *cl)
 	struct bio *bio = &s->bio.bio;
 
 	int ret = bch_btree_map_keys(&s->op, s->iop.c,
-				     &KEY(s->iop.inode, bio->bi_sector, 0),
+				     &KEY(s->iop.inode, bio->bi_iter.bi_sector, 0),
 				     cache_lookup_fn, MAP_END_KEY);
 	if (ret == -EAGAIN)
 		continue_at(cl, cache_lookup, bcache_wq);
@@ -758,10 +757,12 @@ static void bio_complete(struct search *s)
 static void do_bio_hook(struct search *s)
 {
 	struct bio *bio = &s->bio.bio;
-	memcpy(bio, s->orig_bio, sizeof(struct bio));
 
+	bio_init(bio);
+	__bio_clone_fast(bio, s->orig_bio);
 	bio->bi_end_io		= request_endio;
 	bio->bi_private		= &s->cl;
+
 	atomic_set(&bio->bi_cnt, 3);
 }
 
@@ -773,9 +774,6 @@ static void search_free(struct closure *cl)
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
-	if (s->unaligned_bvec)
-		mempool_free(s->bio.bio.bi_io_vec, s->d->unaligned_bvec);
-
 	closure_debug_destroy(cl);
 	mempool_free(s, s->d->c->search);
 }
@@ -783,7 +781,6 @@ static void search_free(struct closure *cl)
 static struct search *search_alloc(struct bio *bio, struct bcache_device *d)
 {
 	struct search *s;
-	struct bio_vec *bv;
 
 	s = mempool_alloc(d->c->search, GFP_NOIO);
 	memset(s, 0, offsetof(struct search, iop.insert_keys));
@@ -802,15 +799,6 @@ static struct search *search_alloc(struct bio *bio, struct bcache_device *d)
 	s->start_time		= jiffies;
 	do_bio_hook(s);
 
-	if (bio->bi_size != bio_segments(bio) * PAGE_SIZE) {
-		bv = mempool_alloc(d->unaligned_bvec, GFP_NOIO);
-		memcpy(bv, bio_iovec(bio),
-		       sizeof(struct bio_vec) * bio_segments(bio));
-
-		s->bio.bio.bi_io_vec	= bv;
-		s->unaligned_bvec	= 1;
-	}
-
 	return s;
 }
 
@@ -849,26 +837,13 @@ static void cached_dev_read_error(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 	struct bio *bio = &s->bio.bio;
-	struct bio_vec *bv;
-	int i;
 
 	if (s->recoverable) {
 		/* Retry from the backing device: */
 		trace_bcache_read_retry(s->orig_bio);
 
 		s->iop.error = 0;
-		bv = s->bio.bio.bi_io_vec;
 		do_bio_hook(s);
-		s->bio.bio.bi_io_vec = bv;
-
-		if (!s->unaligned_bvec)
-			bio_for_each_segment(bv, s->orig_bio, i)
-				bv->bv_offset = 0, bv->bv_len = PAGE_SIZE;
-		else
-			memcpy(s->bio.bio.bi_io_vec,
-			       bio_iovec(s->orig_bio),
-			       sizeof(struct bio_vec) *
-			       bio_segments(s->orig_bio));
 
 		/* XXX: invalidate cache */
 
@@ -893,9 +868,9 @@ static void cached_dev_read_done(struct closure *cl)
 
 	if (s->iop.bio) {
 		bio_reset(s->iop.bio);
-		s->iop.bio->bi_sector = s->cache_miss->bi_sector;
+		s->iop.bio->bi_iter.bi_sector = s->cache_miss->bi_iter.bi_sector;
 		s->iop.bio->bi_bdev = s->cache_miss->bi_bdev;
-		s->iop.bio->bi_size = s->insert_bio_sectors << 9;
+		s->iop.bio->bi_iter.bi_size = s->insert_bio_sectors << 9;
 		bch_bio_map(s->iop.bio, NULL);
 
 		bio_copy_data(s->cache_miss, s->iop.bio);
@@ -904,8 +879,7 @@ static void cached_dev_read_done(struct closure *cl)
 		s->cache_miss = NULL;
 	}
 
-	if (verify(dc, &s->bio.bio) && s->recoverable &&
-	    !s->unaligned_bvec && !s->read_dirty_data)
+	if (verify(dc, &s->bio.bio) && s->recoverable && !s->read_dirty_data)
 		bch_data_verify(dc, s->orig_bio);
 
 	bio_complete(s);
@@ -945,7 +919,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	struct bio *miss, *cache_bio;
 
 	if (s->cache_miss || s->iop.bypass) {
-		miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+		miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
 		ret = miss == bio ? MAP_DONE : MAP_CONTINUE;
 		goto out_submit;
 	}
@@ -959,7 +933,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada);
 
 	s->iop.replace_key = KEY(s->iop.inode,
-				 bio->bi_sector + s->insert_bio_sectors,
+				 bio->bi_iter.bi_sector + s->insert_bio_sectors,
 				 s->insert_bio_sectors);
 
 	ret = bch_btree_insert_check_key(b, &s->op, &s->iop.replace_key);
@@ -968,7 +942,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 
 	s->iop.replace = true;
 
-	miss = bch_bio_split(bio, sectors, GFP_NOIO, s->d->bio_split);
+	miss = bio_next_split(bio, sectors, GFP_NOIO, s->d->bio_split);
 
 	/* btree_search_recurse()'s btree iterator is no good anymore */
 	ret = miss == bio ? MAP_DONE : -EINTR;
@@ -979,9 +953,9 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	if (!cache_bio)
 		goto out_submit;
 
-	cache_bio->bi_sector	= miss->bi_sector;
-	cache_bio->bi_bdev	= miss->bi_bdev;
-	cache_bio->bi_size	= s->insert_bio_sectors << 9;
+	cache_bio->bi_iter.bi_sector	= miss->bi_iter.bi_sector;
+	cache_bio->bi_bdev		= miss->bi_bdev;
+	cache_bio->bi_iter.bi_size	= s->insert_bio_sectors << 9;
 
 	cache_bio->bi_end_io	= request_endio;
 	cache_bio->bi_private	= &s->cl;
@@ -1031,7 +1005,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 {
 	struct closure *cl = &s->cl;
 	struct bio *bio = &s->bio.bio;
-	struct bkey start = KEY(dc->disk.id, bio->bi_sector, 0);
+	struct bkey start = KEY(dc->disk.id, bio->bi_iter.bi_sector, 0);
 	struct bkey end = KEY(dc->disk.id, bio_end_sector(bio), 0);
 
 	bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &start, &end);
@@ -1087,8 +1061,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			closure_bio_submit(flush, cl, s->d);
 		}
 	} else {
-		s->iop.bio = bio_clone_bioset(bio, GFP_NOIO,
-					      dc->disk.bio_split);
+		s->iop.bio = bio_clone_fast(bio, GFP_NOIO, dc->disk.bio_split);
 
 		closure_bio_submit(bio, cl, s->d);
 	}
@@ -1126,13 +1099,13 @@ static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
 	part_stat_unlock();
 
 	bio->bi_bdev = dc->bdev;
-	bio->bi_sector += dc->sb.data_offset;
+	bio->bi_iter.bi_sector += dc->sb.data_offset;
 
 	if (cached_dev_get(dc)) {
 		s = search_alloc(bio, d);
 		trace_bcache_request_start(s->d, bio);
 
-		if (!bio->bi_size) {
+		if (!bio->bi_iter.bi_size) {
 			/*
 			 * can't call bch_journal_meta from under
 			 * generic_make_request
@@ -1204,24 +1177,24 @@ void bch_cached_dev_request_init(struct cached_dev *dc)
 static int flash_dev_cache_miss(struct btree *b, struct search *s,
 				struct bio *bio, unsigned sectors)
 {
-	struct bio_vec *bv;
-	int i;
+	struct bio_vec bv;
+	struct bvec_iter iter;
 
 	/* Zero fill bio */
 
-	bio_for_each_segment(bv, bio, i) {
-		unsigned j = min(bv->bv_len >> 9, sectors);
+	bio_for_each_segment(bv, bio, iter) {
+		unsigned j = min(bv.bv_len >> 9, sectors);
 
-		void *p = kmap(bv->bv_page);
-		memset(p + bv->bv_offset, 0, j << 9);
-		kunmap(bv->bv_page);
+		void *p = kmap(bv.bv_page);
+		memset(p + bv.bv_offset, 0, j << 9);
+		kunmap(bv.bv_page);
 
 		sectors	-= j;
 	}
 
-	bio_advance(bio, min(sectors << 9, bio->bi_size));
+	bio_advance(bio, min(sectors << 9, bio->bi_iter.bi_size));
 
-	if (!bio->bi_size)
+	if (!bio->bi_iter.bi_size)
 		return MAP_DONE;
 
 	return MAP_CONTINUE;
@@ -1255,7 +1228,7 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
 
 	trace_bcache_request_start(s->d, bio);
 
-	if (!bio->bi_size) {
+	if (!bio->bi_iter.bi_size) {
 		/*
 		 * can't call bch_journal_meta from under
 		 * generic_make_request
@@ -1265,7 +1238,7 @@ static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
 				      bcache_wq);
 	} else if (rw) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
-					&KEY(d->id, bio->bi_sector, 0),
+					&KEY(d->id, bio->bi_iter.bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
 
 		s->iop.bypass		= (bio->bi_rw & REQ_DISCARD) != 0;

drivers/md/bcache/super.c

@@ -233,9 +233,9 @@ static void __write_super(struct cache_sb *sb, struct bio *bio)
 	struct cache_sb *out = page_address(bio->bi_io_vec[0].bv_page);
 	unsigned i;
 
-	bio->bi_sector	= SB_SECTOR;
-	bio->bi_rw	= REQ_SYNC|REQ_META;
-	bio->bi_size	= SB_SIZE;
+	bio->bi_iter.bi_sector	= SB_SECTOR;
+	bio->bi_rw		= REQ_SYNC|REQ_META;
+	bio->bi_iter.bi_size	= SB_SIZE;
 	bch_bio_map(bio, NULL);
 
 	out->offset		= cpu_to_le64(sb->offset);
@@ -347,7 +347,7 @@ static void uuid_io(struct cache_set *c, unsigned long rw,
 		struct bio *bio = bch_bbio_alloc(c);
 
 		bio->bi_rw	= REQ_SYNC|REQ_META|rw;
-		bio->bi_size	= KEY_SIZE(k) << 9;
+		bio->bi_iter.bi_size = KEY_SIZE(k) << 9;
 
 		bio->bi_end_io	= uuid_endio;
 		bio->bi_private = cl;
@@ -503,10 +503,10 @@ static void prio_io(struct cache *ca, uint64_t bucket, unsigned long rw)
 
 	closure_init_stack(cl);
 
-	bio->bi_sector	= bucket * ca->sb.bucket_size;
-	bio->bi_bdev	= ca->bdev;
-	bio->bi_rw	= REQ_SYNC|REQ_META|rw;
-	bio->bi_size	= bucket_bytes(ca);
+	bio->bi_iter.bi_sector	= bucket * ca->sb.bucket_size;
+	bio->bi_bdev		= ca->bdev;
+	bio->bi_rw		= REQ_SYNC|REQ_META|rw;
+	bio->bi_iter.bi_size	= bucket_bytes(ca);
 
 	bio->bi_end_io	= prio_endio;
 	bio->bi_private = ca;
@@ -739,8 +739,6 @@ static void bcache_device_free(struct bcache_device *d)
 	}
 
 	bio_split_pool_free(&d->bio_split_hook);
-	if (d->unaligned_bvec)
-		mempool_destroy(d->unaligned_bvec);
 	if (d->bio_split)
 		bioset_free(d->bio_split);
 	if (is_vmalloc_addr(d->full_dirty_stripes))
@@ -793,8 +791,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		return minor;
 
 	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
-	    !(d->unaligned_bvec = mempool_create_kmalloc_pool(1,
-				sizeof(struct bio_vec) * BIO_MAX_PAGES)) ||
 	    bio_split_pool_init(&d->bio_split_hook) ||
 	    !(d->disk = alloc_disk(1))) {
 		ida_simple_remove(&bcache_minor, minor);

drivers/md/bcache/util.c

@@ -224,10 +224,10 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 
 void bch_bio_map(struct bio *bio, void *base)
 {
-	size_t size = bio->bi_size;
+	size_t size = bio->bi_iter.bi_size;
 	struct bio_vec *bv = bio->bi_io_vec;
 
-	BUG_ON(!bio->bi_size);
+	BUG_ON(!bio->bi_iter.bi_size);
 	BUG_ON(bio->bi_vcnt);
 
 	bv->bv_offset = base ? ((unsigned long) base) % PAGE_SIZE : 0;

drivers/md/bcache/writeback.c

@@ -111,7 +111,7 @@ static void dirty_init(struct keybuf_key *w)
 	if (!io->dc->writeback_percent)
 		bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
 
-	bio->bi_size		= KEY_SIZE(&w->key) << 9;
+	bio->bi_iter.bi_size	= KEY_SIZE(&w->key) << 9;
 	bio->bi_max_vecs	= DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS);
 	bio->bi_private		= w;
 	bio->bi_io_vec		= bio->bi_inline_vecs;
@@ -184,7 +184,7 @@ static void write_dirty(struct closure *cl)
 
 	dirty_init(w);
 	io->bio.bi_rw		= WRITE;
-	io->bio.bi_sector	= KEY_START(&w->key);
+	io->bio.bi_iter.bi_sector = KEY_START(&w->key);
 	io->bio.bi_bdev		= io->dc->bdev;
 	io->bio.bi_end_io	= dirty_endio;
 
@@ -253,7 +253,7 @@ static void read_dirty(struct cached_dev *dc)
 		io->dc		= dc;
 
 		dirty_init(w);
-		io->bio.bi_sector	= PTR_OFFSET(&w->key, 0);
+		io->bio.bi_iter.bi_sector = PTR_OFFSET(&w->key, 0);
 		io->bio.bi_bdev		= PTR_CACHE(dc->disk.c,
 						    &w->key, 0)->bdev;
 		io->bio.bi_rw		= READ;

drivers/md/bcache/writeback.h

@@ -50,7 +50,7 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
 		return false;
 
 	if (dc->partial_stripes_expensive &&
-	    bcache_dev_stripe_dirty(dc, bio->bi_sector,
+	    bcache_dev_stripe_dirty(dc, bio->bi_iter.bi_sector,
 				    bio_sectors(bio)))
 		return true;
 

drivers/md/dm-bio-record.h

@@ -17,55 +17,24 @@
  * original bio state.
  */
 
-struct dm_bio_vec_details {
-#if PAGE_SIZE < 65536
-	__u16 bv_len;
-	__u16 bv_offset;
-#else
-	unsigned bv_len;
-	unsigned bv_offset;
-#endif
-};
-
 struct dm_bio_details {
-	sector_t bi_sector;
 	struct block_device *bi_bdev;
-	unsigned int bi_size;
-	unsigned short bi_idx;
 	unsigned long bi_flags;
-	struct dm_bio_vec_details bi_io_vec[BIO_MAX_PAGES];
+	struct bvec_iter bi_iter;
 };
 
 static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
 {
-	unsigned i;
-
-	bd->bi_sector = bio->bi_sector;
 	bd->bi_bdev = bio->bi_bdev;
-	bd->bi_size = bio->bi_size;
-	bd->bi_idx = bio->bi_idx;
 	bd->bi_flags = bio->bi_flags;
-
-	for (i = 0; i < bio->bi_vcnt; i++) {
-		bd->bi_io_vec[i].bv_len = bio->bi_io_vec[i].bv_len;
-		bd->bi_io_vec[i].bv_offset = bio->bi_io_vec[i].bv_offset;
-	}
+	bd->bi_iter = bio->bi_iter;
 }
 
 static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
 {
-	unsigned i;
-
-	bio->bi_sector = bd->bi_sector;
 	bio->bi_bdev = bd->bi_bdev;
-	bio->bi_size = bd->bi_size;
-	bio->bi_idx = bd->bi_idx;
 	bio->bi_flags = bd->bi_flags;
-
-	for (i = 0; i < bio->bi_vcnt; i++) {
-		bio->bi_io_vec[i].bv_len = bd->bi_io_vec[i].bv_len;
-		bio->bi_io_vec[i].bv_offset = bd->bi_io_vec[i].bv_offset;
-	}
+	bio->bi_iter = bd->bi_iter;
 }
 
 #endif

drivers/md/dm-bufio.c

@@ -540,7 +540,7 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 	bio_init(&b->bio);
 	b->bio.bi_io_vec = b->bio_vec;
 	b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
-	b->bio.bi_sector = block << b->c->sectors_per_block_bits;
+	b->bio.bi_iter.bi_sector = block << b->c->sectors_per_block_bits;
 	b->bio.bi_bdev = b->c->bdev;
 	b->bio.bi_end_io = end_io;
 

drivers/md/dm-cache-policy-mq.c

@@ -72,7 +72,7 @@ static enum io_pattern iot_pattern(struct io_tracker *t)
 
 static void iot_update_stats(struct io_tracker *t, struct bio *bio)
 {
-	if (bio->bi_sector == from_oblock(t->last_end_oblock) + 1)
+	if (bio->bi_iter.bi_sector == from_oblock(t->last_end_oblock) + 1)
 		t->nr_seq_samples++;
 	else {
 		/*
@@ -87,7 +87,7 @@ static void iot_update_stats(struct io_tracker *t, struct bio *bio)
 		t->nr_rand_samples++;
 	}
 
-	t->last_end_oblock = to_oblock(bio->bi_sector + bio_sectors(bio) - 1);
+	t->last_end_oblock = to_oblock(bio_end_sector(bio) - 1);
 }
 
 static void iot_check_for_pattern_switch(struct io_tracker *t)

drivers/md/dm-cache-target.c

@@ -85,6 +85,12 @@ static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
 {
 	bio->bi_end_io = h->bi_end_io;
 	bio->bi_private = h->bi_private;
+
+	/*
+	 * Must bump bi_remaining to allow bio to complete with
+	 * restored bi_end_io.
+	 */
+	atomic_inc(&bio->bi_remaining);
 }
 
 /*----------------------------------------------------------------*/
@@ -664,15 +670,17 @@ static void remap_to_origin(struct cache *cache, struct bio *bio)
 static void remap_to_cache(struct cache *cache, struct bio *bio,
 			   dm_cblock_t cblock)
 {
-	sector_t bi_sector = bio->bi_sector;
+	sector_t bi_sector = bio->bi_iter.bi_sector;
 
 	bio->bi_bdev = cache->cache_dev->bdev;
 	if (!block_size_is_power_of_two(cache))
-		bio->bi_sector = (from_cblock(cblock) * cache->sectors_per_block) +
-				sector_div(bi_sector, cache->sectors_per_block);
+		bio->bi_iter.bi_sector =
+			(from_cblock(cblock) * cache->sectors_per_block) +
+			sector_div(bi_sector, cache->sectors_per_block);
 	else
-		bio->bi_sector = (from_cblock(cblock) << cache->sectors_per_block_shift) |
-				(bi_sector & (cache->sectors_per_block - 1));
+		bio->bi_iter.bi_sector =
+			(from_cblock(cblock) << cache->sectors_per_block_shift) |
+			(bi_sector & (cache->sectors_per_block - 1));
 }
 
 static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
@@ -712,7 +720,7 @@ static void remap_to_cache_dirty(struct cache *cache, struct bio *bio,
 
 static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
 {
-	sector_t block_nr = bio->bi_sector;
+	sector_t block_nr = bio->bi_iter.bi_sector;
 
 	if (!block_size_is_power_of_two(cache))
 		(void) sector_div(block_nr, cache->sectors_per_block);
@@ -1027,7 +1035,7 @@ static void issue_overwrite(struct dm_cache_migration *mg, struct bio *bio)
 static bool bio_writes_complete_block(struct cache *cache, struct bio *bio)
 {
 	return (bio_data_dir(bio) == WRITE) &&
-		(bio->bi_size == (cache->sectors_per_block << SECTOR_SHIFT));
+		(bio->bi_iter.bi_size == (cache->sectors_per_block << SECTOR_SHIFT));
 }
 
 static void avoid_copy(struct dm_cache_migration *mg)
@@ -1252,7 +1260,7 @@ static void process_flush_bio(struct cache *cache, struct bio *bio)
 	size_t pb_data_size = get_per_bio_data_size(cache);
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 
-	BUG_ON(bio->bi_size);
+	BUG_ON(bio->bi_iter.bi_size);
 	if (!pb->req_nr)
 		remap_to_origin(cache, bio);
 	else
@@ -1275,9 +1283,9 @@ static void process_flush_bio(struct cache *cache, struct bio *bio)
  */
 static void process_discard_bio(struct cache *cache, struct bio *bio)
 {
-	dm_block_t start_block = dm_sector_div_up(bio->bi_sector,
+	dm_block_t start_block = dm_sector_div_up(bio->bi_iter.bi_sector,
 						  cache->discard_block_size);
-	dm_block_t end_block = bio->bi_sector + bio_sectors(bio);
+	dm_block_t end_block = bio_end_sector(bio);
 	dm_block_t b;
 
 	end_block = block_div(end_block, cache->discard_block_size);

drivers/md/dm-crypt.c

@@ -39,10 +39,8 @@ struct convert_context {
 	struct completion restart;
 	struct bio *bio_in;
 	struct bio *bio_out;
-	unsigned int offset_in;
-	unsigned int offset_out;
-	unsigned int idx_in;
-	unsigned int idx_out;
+	struct bvec_iter iter_in;
+	struct bvec_iter iter_out;
 	sector_t cc_sector;
 	atomic_t cc_pending;
 };
@@ -826,10 +824,10 @@ static void crypt_convert_init(struct crypt_config *cc,
 {
 	ctx->bio_in = bio_in;
 	ctx->bio_out = bio_out;
-	ctx->offset_in = 0;
-	ctx->offset_out = 0;
-	ctx->idx_in = bio_in ? bio_in->bi_idx : 0;
-	ctx->idx_out = bio_out ? bio_out->bi_idx : 0;
+	if (bio_in)
+		ctx->iter_in = bio_in->bi_iter;
+	if (bio_out)
+		ctx->iter_out = bio_out->bi_iter;
 	ctx->cc_sector = sector + cc->iv_offset;
 	init_completion(&ctx->restart);
 }
@@ -857,8 +855,8 @@ static int crypt_convert_block(struct crypt_config *cc,
 			       struct convert_context *ctx,
 			       struct ablkcipher_request *req)
 {
-	struct bio_vec *bv_in = bio_iovec_idx(ctx->bio_in, ctx->idx_in);
-	struct bio_vec *bv_out = bio_iovec_idx(ctx->bio_out, ctx->idx_out);
+	struct bio_vec bv_in = bio_iter_iovec(ctx->bio_in, ctx->iter_in);
+	struct bio_vec bv_out = bio_iter_iovec(ctx->bio_out, ctx->iter_out);
 	struct dm_crypt_request *dmreq;
 	u8 *iv;
 	int r;
@@ -869,24 +867,15 @@ static int crypt_convert_block(struct crypt_config *cc,
 	dmreq->iv_sector = ctx->cc_sector;
 	dmreq->ctx = ctx;
 	sg_init_table(&dmreq->sg_in, 1);
-	sg_set_page(&dmreq->sg_in, bv_in->bv_page, 1 << SECTOR_SHIFT,
-		    bv_in->bv_offset + ctx->offset_in);
+	sg_set_page(&dmreq->sg_in, bv_in.bv_page, 1 << SECTOR_SHIFT,
+		    bv_in.bv_offset);
 
 	sg_init_table(&dmreq->sg_out, 1);
-	sg_set_page(&dmreq->sg_out, bv_out->bv_page, 1 << SECTOR_SHIFT,
-		    bv_out->bv_offset + ctx->offset_out);
+	sg_set_page(&dmreq->sg_out, bv_out.bv_page, 1 << SECTOR_SHIFT,
+		    bv_out.bv_offset);
 
-	ctx->offset_in += 1 << SECTOR_SHIFT;
-	if (ctx->offset_in >= bv_in->bv_len) {
-		ctx->offset_in = 0;
-		ctx->idx_in++;
-	}
-
-	ctx->offset_out += 1 << SECTOR_SHIFT;
-	if (ctx->offset_out >= bv_out->bv_len) {
-		ctx->offset_out = 0;
-		ctx->idx_out++;
-	}
+	bio_advance_iter(ctx->bio_in, &ctx->iter_in, 1 << SECTOR_SHIFT);
+	bio_advance_iter(ctx->bio_out, &ctx->iter_out, 1 << SECTOR_SHIFT);
 
 	if (cc->iv_gen_ops) {
 		r = cc->iv_gen_ops->generator(cc, iv, dmreq);
@@ -937,8 +926,7 @@ static int crypt_convert(struct crypt_config *cc,
 
 	atomic_set(&ctx->cc_pending, 1);
 
-	while(ctx->idx_in < ctx->bio_in->bi_vcnt &&
-	      ctx->idx_out < ctx->bio_out->bi_vcnt) {
+	while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
 
 		crypt_alloc_req(cc, ctx);
 
@@ -1021,7 +1009,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size,
 		size -= len;
 	}
 
-	if (!clone->bi_size) {
+	if (!clone->bi_iter.bi_size) {
 		bio_put(clone);
 		return NULL;
 	}
@@ -1161,7 +1149,7 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	crypt_inc_pending(io);
 
 	clone_init(io, clone);
-	clone->bi_sector = cc->start + io->sector;
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 
 	generic_make_request(clone);
 	return 0;
@@ -1207,9 +1195,9 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 	}
 
 	/* crypt_convert should have filled the clone bio */
-	BUG_ON(io->ctx.idx_out < clone->bi_vcnt);
+	BUG_ON(io->ctx.iter_out.bi_size);
 
-	clone->bi_sector = cc->start + io->sector;
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 
 	if (async)
 		kcryptd_queue_io(io);
@@ -1224,7 +1212,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	struct dm_crypt_io *new_io;
 	int crypt_finished;
 	unsigned out_of_pages = 0;
-	unsigned remaining = io->base_bio->bi_size;
+	unsigned remaining = io->base_bio->bi_iter.bi_size;
 	sector_t sector = io->sector;
 	int r;
 
@@ -1246,9 +1234,9 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		}
 
 		io->ctx.bio_out = clone;
-		io->ctx.idx_out = 0;
+		io->ctx.iter_out = clone->bi_iter;
 
-		remaining -= clone->bi_size;
+		remaining -= clone->bi_iter.bi_size;
 		sector += bio_sectors(clone);
 
 		crypt_inc_pending(io);
@@ -1290,8 +1278,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 			crypt_inc_pending(new_io);
 			crypt_convert_init(cc, &new_io->ctx, NULL,
 					   io->base_bio, sector);
-			new_io->ctx.idx_in = io->ctx.idx_in;
-			new_io->ctx.offset_in = io->ctx.offset_in;
+			new_io->ctx.iter_in = io->ctx.iter_in;
 
 			/*
 			 * Fragments after the first use the base_io
@@ -1869,11 +1856,12 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) {
 		bio->bi_bdev = cc->dev->bdev;
 		if (bio_sectors(bio))
-			bio->bi_sector = cc->start + dm_target_offset(ti, bio->bi_sector);
+			bio->bi_iter.bi_sector = cc->start +
+				dm_target_offset(ti, bio->bi_iter.bi_sector);
 		return DM_MAPIO_REMAPPED;
 	}
 
-	io = crypt_io_alloc(cc, bio, dm_target_offset(ti, bio->bi_sector));
+	io = crypt_io_alloc(cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
 
 	if (bio_data_dir(io->base_bio) == READ) {
 		if (kcryptd_io_read(io, GFP_NOWAIT))

drivers/md/dm-delay.c

@@ -277,14 +277,15 @@ static int delay_map(struct dm_target *ti, struct bio *bio)
 	if ((bio_data_dir(bio) == WRITE) && (dc->dev_write)) {
 		bio->bi_bdev = dc->dev_write->bdev;
 		if (bio_sectors(bio))
-			bio->bi_sector = dc->start_write +
-					 dm_target_offset(ti, bio->bi_sector);
+			bio->bi_iter.bi_sector = dc->start_write +
+				dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 		return delay_bio(dc, dc->write_delay, bio);
 	}
 
 	bio->bi_bdev = dc->dev_read->bdev;
-	bio->bi_sector = dc->start_read + dm_target_offset(ti, bio->bi_sector);
+	bio->bi_iter.bi_sector = dc->start_read +
+		dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 	return delay_bio(dc, dc->read_delay, bio);
 }

drivers/md/dm-flakey.c

@@ -248,7 +248,8 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 
 	bio->bi_bdev = fc->dev->bdev;
 	if (bio_sectors(bio))
-		bio->bi_sector = flakey_map_sector(ti, bio->bi_sector);
+		bio->bi_iter.bi_sector =
+			flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
 
 static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
@@ -265,8 +266,8 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
 		DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
 			"(rw=%c bi_rw=%lu bi_sector=%llu cur_bytes=%u)\n",
 			bio, fc->corrupt_bio_value, fc->corrupt_bio_byte,
-			(bio_data_dir(bio) == WRITE) ? 'w' : 'r',
-			bio->bi_rw, (unsigned long long)bio->bi_sector, bio_bytes);
+			(bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_rw,
+			(unsigned long long)bio->bi_iter.bi_sector, bio_bytes);
 	}
 }
 

drivers/md/dm-io.c

@@ -201,26 +201,29 @@ static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned offse
 /*
  * Functions for getting the pages from a bvec.
  */
-static void bvec_get_page(struct dpages *dp,
+static void bio_get_page(struct dpages *dp,
 		  struct page **p, unsigned long *len, unsigned *offset)
 {
-	struct bio_vec *bvec = (struct bio_vec *) dp->context_ptr;
-	*p = bvec->bv_page;
-	*len = bvec->bv_len;
-	*offset = bvec->bv_offset;
+	struct bio *bio = dp->context_ptr;
+	struct bio_vec bvec = bio_iovec(bio);
+	*p = bvec.bv_page;
+	*len = bvec.bv_len;
+	*offset = bvec.bv_offset;
 }
 
-static void bvec_next_page(struct dpages *dp)
+static void bio_next_page(struct dpages *dp)
 {
-	struct bio_vec *bvec = (struct bio_vec *) dp->context_ptr;
-	dp->context_ptr = bvec + 1;
+	struct bio *bio = dp->context_ptr;
+	struct bio_vec bvec = bio_iovec(bio);
+
+	bio_advance(bio, bvec.bv_len);
 }
 
-static void bvec_dp_init(struct dpages *dp, struct bio_vec *bvec)
+static void bio_dp_init(struct dpages *dp, struct bio *bio)
 {
-	dp->get_page = bvec_get_page;
-	dp->next_page = bvec_next_page;
-	dp->context_ptr = bvec;
+	dp->get_page = bio_get_page;
+	dp->next_page = bio_next_page;
+	dp->context_ptr = bio;
 }
 
 /*
@@ -304,14 +307,14 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 					  dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
 
 		bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
-		bio->bi_sector = where->sector + (where->count - remaining);
+		bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
 		bio->bi_bdev = where->bdev;
 		bio->bi_end_io = endio;
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (rw & REQ_DISCARD) {
 			num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
-			bio->bi_size = num_sectors << SECTOR_SHIFT;
+			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 			remaining -= num_sectors;
 		} else if (rw & REQ_WRITE_SAME) {
 			/*
@@ -320,7 +323,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 			dp->get_page(dp, &page, &len, &offset);
 			bio_add_page(bio, page, logical_block_size, offset);
 			num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining);
-			bio->bi_size = num_sectors << SECTOR_SHIFT;
+			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 
 			offset = 0;
 			remaining -= num_sectors;
@@ -457,8 +460,8 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp,
 		list_dp_init(dp, io_req->mem.ptr.pl, io_req->mem.offset);
 		break;
 
-	case DM_IO_BVEC:
-		bvec_dp_init(dp, io_req->mem.ptr.bvec);
+	case DM_IO_BIO:
+		bio_dp_init(dp, io_req->mem.ptr.bio);
 		break;
 
 	case DM_IO_VMA:

drivers/md/dm-linear.c

@@ -85,7 +85,8 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio)
 
 	bio->bi_bdev = lc->dev->bdev;
 	if (bio_sectors(bio))
-		bio->bi_sector = linear_map_sector(ti, bio->bi_sector);
+		bio->bi_iter.bi_sector =
+			linear_map_sector(ti, bio->bi_iter.bi_sector);
 }
 
 static int linear_map(struct dm_target *ti, struct bio *bio)

drivers/md/dm-raid1.c

@@ -432,7 +432,7 @@ static int mirror_available(struct mirror_set *ms, struct bio *bio)
 	region_t region = dm_rh_bio_to_region(ms->rh, bio);
 
 	if (log->type->in_sync(log, region, 0))
-		return choose_mirror(ms,  bio->bi_sector) ? 1 : 0;
+		return choose_mirror(ms,  bio->bi_iter.bi_sector) ? 1 : 0;
 
 	return 0;
 }
@@ -442,15 +442,15 @@ static int mirror_available(struct mirror_set *ms, struct bio *bio)
  */
 static sector_t map_sector(struct mirror *m, struct bio *bio)
 {
-	if (unlikely(!bio->bi_size))
+	if (unlikely(!bio->bi_iter.bi_size))
 		return 0;
-	return m->offset + dm_target_offset(m->ms->ti, bio->bi_sector);
+	return m->offset + dm_target_offset(m->ms->ti, bio->bi_iter.bi_sector);
 }
 
 static void map_bio(struct mirror *m, struct bio *bio)
 {
 	bio->bi_bdev = m->dev->bdev;
-	bio->bi_sector = map_sector(m, bio);
+	bio->bi_iter.bi_sector = map_sector(m, bio);
 }
 
 static void map_region(struct dm_io_region *io, struct mirror *m,
@@ -526,8 +526,8 @@ static void read_async_bio(struct mirror *m, struct bio *bio)
 	struct dm_io_region io;
 	struct dm_io_request io_req = {
 		.bi_rw = READ,
-		.mem.type = DM_IO_BVEC,
-		.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
+		.mem.type = DM_IO_BIO,
+		.mem.ptr.bio = bio,
 		.notify.fn = read_callback,
 		.notify.context = bio,
 		.client = m->ms->io_client,
@@ -559,7 +559,7 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
 		 * We can only read balance if the region is in sync.
 		 */
 		if (likely(region_in_sync(ms, region, 1)))
-			m = choose_mirror(ms, bio->bi_sector);
+			m = choose_mirror(ms, bio->bi_iter.bi_sector);
 		else if (m && atomic_read(&m->error_count))
 			m = NULL;
 
@@ -629,8 +629,8 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	struct mirror *m;
 	struct dm_io_request io_req = {
 		.bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
-		.mem.type = DM_IO_BVEC,
-		.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
+		.mem.type = DM_IO_BIO,
+		.mem.ptr.bio = bio,
 		.notify.fn = write_callback,
 		.notify.context = bio,
 		.client = ms->io_client,
@@ -1181,7 +1181,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
 	 * The region is in-sync and we can perform reads directly.
 	 * Store enough information so we can retry if it fails.
 	 */
-	m = choose_mirror(ms, bio->bi_sector);
+	m = choose_mirror(ms, bio->bi_iter.bi_sector);
 	if (unlikely(!m))
 		return -EIO;
 

drivers/md/dm-region-hash.c

@@ -126,7 +126,8 @@ EXPORT_SYMBOL_GPL(dm_rh_region_to_sector);
 
 region_t dm_rh_bio_to_region(struct dm_region_hash *rh, struct bio *bio)
 {
-	return dm_rh_sector_to_region(rh, bio->bi_sector - rh->target_begin);
+	return dm_rh_sector_to_region(rh, bio->bi_iter.bi_sector -
+				      rh->target_begin);
 }
 EXPORT_SYMBOL_GPL(dm_rh_bio_to_region);
 

drivers/md/dm-snap.c

@@ -1438,6 +1438,7 @@ out:
 	if (full_bio) {
 		full_bio->bi_end_io = pe->full_bio_end_io;
 		full_bio->bi_private = pe->full_bio_private;
+		atomic_inc(&full_bio->bi_remaining);
 	}
 	free_pending_exception(pe);
 
@@ -1619,11 +1620,10 @@ static void remap_exception(struct dm_snapshot *s, struct dm_exception *e,
 			    struct bio *bio, chunk_t chunk)
 {
 	bio->bi_bdev = s->cow->bdev;
-	bio->bi_sector = chunk_to_sector(s->store,
-					 dm_chunk_number(e->new_chunk) +
-					 (chunk - e->old_chunk)) +
-					 (bio->bi_sector &
-					  s->store->chunk_mask);
+	bio->bi_iter.bi_sector =
+		chunk_to_sector(s->store, dm_chunk_number(e->new_chunk) +
+				(chunk - e->old_chunk)) +
+		(bio->bi_iter.bi_sector & s->store->chunk_mask);
 }
 
 static int snapshot_map(struct dm_target *ti, struct bio *bio)
@@ -1641,7 +1641,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 	}
 
-	chunk = sector_to_chunk(s->store, bio->bi_sector);
+	chunk = sector_to_chunk(s->store, bio->bi_iter.bi_sector);
 
 	/* Full snapshots are not usable */
 	/* To get here the table must be live so s->active is always set. */
@@ -1702,7 +1702,8 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 		r = DM_MAPIO_SUBMITTED;
 
 		if (!pe->started &&
-		    bio->bi_size == (s->store->chunk_size << SECTOR_SHIFT)) {
+		    bio->bi_iter.bi_size ==
+		    (s->store->chunk_size << SECTOR_SHIFT)) {
 			pe->started = 1;
 			up_write(&s->lock);
 			start_full_bio(pe, bio);
@@ -1758,7 +1759,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 	}
 
-	chunk = sector_to_chunk(s->store, bio->bi_sector);
+	chunk = sector_to_chunk(s->store, bio->bi_iter.bi_sector);
 
 	down_write(&s->lock);
 
@@ -2095,7 +2096,7 @@ static int do_origin(struct dm_dev *origin, struct bio *bio)
 	down_read(&_origins_lock);
 	o = __lookup_origin(origin->bdev);
 	if (o)
-		r = __origin_write(&o->snapshots, bio->bi_sector, bio);
+		r = __origin_write(&o->snapshots, bio->bi_iter.bi_sector, bio);
 	up_read(&_origins_lock);
 
 	return r;

drivers/md/dm-stripe.c

@@ -259,13 +259,15 @@ static int stripe_map_range(struct stripe_c *sc, struct bio *bio,
 {
 	sector_t begin, end;
 
-	stripe_map_range_sector(sc, bio->bi_sector, target_stripe, &begin);
+	stripe_map_range_sector(sc, bio->bi_iter.bi_sector,
+				target_stripe, &begin);
 	stripe_map_range_sector(sc, bio_end_sector(bio),
 				target_stripe, &end);
 	if (begin < end) {
 		bio->bi_bdev = sc->stripe[target_stripe].dev->bdev;
-		bio->bi_sector = begin + sc->stripe[target_stripe].physical_start;
-		bio->bi_size = to_bytes(end - begin);
+		bio->bi_iter.bi_sector = begin +
+			sc->stripe[target_stripe].physical_start;
+		bio->bi_iter.bi_size = to_bytes(end - begin);
 		return DM_MAPIO_REMAPPED;
 	} else {
 		/* The range doesn't map to the target stripe */
@@ -293,9 +295,10 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 		return stripe_map_range(sc, bio, target_bio_nr);
 	}
 
-	stripe_map_sector(sc, bio->bi_sector, &stripe, &bio->bi_sector);
+	stripe_map_sector(sc, bio->bi_iter.bi_sector,
+			  &stripe, &bio->bi_iter.bi_sector);
 
-	bio->bi_sector += sc->stripe[stripe].physical_start;
+	bio->bi_iter.bi_sector += sc->stripe[stripe].physical_start;
 	bio->bi_bdev = sc->stripe[stripe].dev->bdev;
 
 	return DM_MAPIO_REMAPPED;

drivers/md/dm-switch.c

@@ -311,11 +311,11 @@ error:
 static int switch_map(struct dm_target *ti, struct bio *bio)
 {
 	struct switch_ctx *sctx = ti->private;
-	sector_t offset = dm_target_offset(ti, bio->bi_sector);
+	sector_t offset = dm_target_offset(ti, bio->bi_iter.bi_sector);
 	unsigned path_nr = switch_get_path_nr(sctx, offset);
 
 	bio->bi_bdev = sctx->path_list[path_nr].dmdev->bdev;
-	bio->bi_sector = sctx->path_list[path_nr].start + offset;
+	bio->bi_iter.bi_sector = sctx->path_list[path_nr].start + offset;
 
 	return DM_MAPIO_REMAPPED;
 }

drivers/md/dm-thin.c

@@ -414,7 +414,7 @@ static bool block_size_is_power_of_two(struct pool *pool)
 static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
-	sector_t block_nr = bio->bi_sector;
+	sector_t block_nr = bio->bi_iter.bi_sector;
 
 	if (block_size_is_power_of_two(pool))
 		block_nr >>= pool->sectors_per_block_shift;
@@ -427,14 +427,15 @@ static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio)
 static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block)
 {
 	struct pool *pool = tc->pool;
-	sector_t bi_sector = bio->bi_sector;
+	sector_t bi_sector = bio->bi_iter.bi_sector;
 
 	bio->bi_bdev = tc->pool_dev->bdev;
 	if (block_size_is_power_of_two(pool))
-		bio->bi_sector = (block << pool->sectors_per_block_shift) |
-				(bi_sector & (pool->sectors_per_block - 1));
+		bio->bi_iter.bi_sector =
+			(block << pool->sectors_per_block_shift) |
+			(bi_sector & (pool->sectors_per_block - 1));
 	else
-		bio->bi_sector = (block * pool->sectors_per_block) +
+		bio->bi_iter.bi_sector = (block * pool->sectors_per_block) +
 				 sector_div(bi_sector, pool->sectors_per_block);
 }
 
@@ -612,8 +613,10 @@ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *c
 
 static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 {
-	if (m->bio)
+	if (m->bio) {
 		m->bio->bi_end_io = m->saved_bi_end_io;
+		atomic_inc(&m->bio->bi_remaining);
+	}
 	cell_error(m->tc->pool, m->cell);
 	list_del(&m->list);
 	mempool_free(m, m->tc->pool->mapping_pool);
@@ -627,8 +630,10 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	int r;
 
 	bio = m->bio;
-	if (bio)
+	if (bio) {
 		bio->bi_end_io = m->saved_bi_end_io;
+		atomic_inc(&bio->bi_remaining);
+	}
 
 	if (m->err) {
 		cell_error(pool, m->cell);
@@ -731,7 +736,8 @@ static void process_prepared(struct pool *pool, struct list_head *head,
  */
 static int io_overlaps_block(struct pool *pool, struct bio *bio)
 {
-	return bio->bi_size == (pool->sectors_per_block << SECTOR_SHIFT);
+	return bio->bi_iter.bi_size ==
+		(pool->sectors_per_block << SECTOR_SHIFT);
 }
 
 static int io_overwrites_block(struct pool *pool, struct bio *bio)
@@ -1136,7 +1142,7 @@ static void process_shared_bio(struct thin_c *tc, struct bio *bio,
 	if (bio_detain(pool, &key, bio, &cell))
 		return;
 
-	if (bio_data_dir(bio) == WRITE && bio->bi_size)
+	if (bio_data_dir(bio) == WRITE && bio->bi_iter.bi_size)
 		break_sharing(tc, bio, block, &key, lookup_result, cell);
 	else {
 		struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
@@ -1159,7 +1165,7 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block
 	/*
 	 * Remap empty bios (flushes) immediately, without provisioning.
 	 */
-	if (!bio->bi_size) {
+	if (!bio->bi_iter.bi_size) {
 		inc_all_io_entry(pool, bio);
 		cell_defer_no_holder(tc, cell);
 
@@ -1258,7 +1264,7 @@ static void process_bio_read_only(struct thin_c *tc, struct bio *bio)
 	r = dm_thin_find_block(tc->td, block, 1, &lookup_result);
 	switch (r) {
 	case 0:
-		if (lookup_result.shared && (rw == WRITE) && bio->bi_size)
+		if (lookup_result.shared && (rw == WRITE) && bio->bi_iter.bi_size)
 			handle_unserviceable_bio(tc->pool, bio);
 		else {
 			inc_all_io_entry(tc->pool, bio);
@@ -2939,7 +2945,7 @@ out_unlock:
 
 static int thin_map(struct dm_target *ti, struct bio *bio)
 {
-	bio->bi_sector = dm_target_offset(ti, bio->bi_sector);
+	bio->bi_iter.bi_sector = dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 	return thin_bio_map(ti, bio);
 }

drivers/md/dm-verity.c

@@ -73,15 +73,10 @@ struct dm_verity_io {
 	sector_t block;
 	unsigned n_blocks;
 
-	/* saved bio vector */
-	struct bio_vec *io_vec;
-	unsigned io_vec_size;
+	struct bvec_iter iter;
 
 	struct work_struct work;
 
-	/* A space for short vectors; longer vectors are allocated separately. */
-	struct bio_vec io_vec_inline[DM_VERITY_IO_VEC_INLINE];
-
 	/*
 	 * Three variably-size fields follow this struct:
 	 *
@@ -284,9 +279,10 @@ release_ret_r:
 static int verity_verify_io(struct dm_verity_io *io)
 {
 	struct dm_verity *v = io->v;
+	struct bio *bio = dm_bio_from_per_bio_data(io,
+						   v->ti->per_bio_data_size);
 	unsigned b;
 	int i;
-	unsigned vector = 0, offset = 0;
 
 	for (b = 0; b < io->n_blocks; b++) {
 		struct shash_desc *desc;
@@ -336,31 +332,22 @@ test_block_hash:
 		}
 
 		todo = 1 << v->data_dev_block_bits;
-		do {
-			struct bio_vec *bv;
+		while (io->iter.bi_size) {
 			u8 *page;
-			unsigned len;
+			struct bio_vec bv = bio_iter_iovec(bio, io->iter);
 
-			BUG_ON(vector >= io->io_vec_size);
-			bv = &io->io_vec[vector];
-			page = kmap_atomic(bv->bv_page);
-			len = bv->bv_len - offset;
-			if (likely(len >= todo))
-				len = todo;
-			r = crypto_shash_update(desc,
-					page + bv->bv_offset + offset, len);
+			page = kmap_atomic(bv.bv_page);
+			r = crypto_shash_update(desc, page + bv.bv_offset,
+						bv.bv_len);
 			kunmap_atomic(page);
+
 			if (r < 0) {
 				DMERR("crypto_shash_update failed: %d", r);
 				return r;
 			}
-			offset += len;
-			if (likely(offset == bv->bv_len)) {
-				offset = 0;
-				vector++;
-			}
-			todo -= len;
-		} while (todo);
+
+			bio_advance_iter(bio, &io->iter, bv.bv_len);
+		}
 
 		if (!v->version) {
 			r = crypto_shash_update(desc, v->salt, v->salt_size);
@@ -383,8 +370,6 @@ test_block_hash:
 			return -EIO;
 		}
 	}
-	BUG_ON(vector != io->io_vec_size);
-	BUG_ON(offset);
 
 	return 0;
 }
@@ -400,10 +385,7 @@ static void verity_finish_io(struct dm_verity_io *io, int error)
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_private = io->orig_bi_private;
 
-	if (io->io_vec != io->io_vec_inline)
-		mempool_free(io->io_vec, v->vec_mempool);
-
-	bio_endio(bio, error);
+	bio_endio_nodec(bio, error);
 }
 
 static void verity_work(struct work_struct *w)
@@ -493,9 +475,9 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 	struct dm_verity_io *io;
 
 	bio->bi_bdev = v->data_dev->bdev;
-	bio->bi_sector = verity_map_sector(v, bio->bi_sector);
+	bio->bi_iter.bi_sector = verity_map_sector(v, bio->bi_iter.bi_sector);
 
-	if (((unsigned)bio->bi_sector | bio_sectors(bio)) &
+	if (((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) &
 	    ((1 << (v->data_dev_block_bits - SECTOR_SHIFT)) - 1)) {
 		DMERR_LIMIT("unaligned io");
 		return -EIO;
@@ -514,18 +496,12 @@ static int verity_map(struct dm_target *ti, struct bio *bio)
 	io->v = v;
 	io->orig_bi_end_io = bio->bi_end_io;
 	io->orig_bi_private = bio->bi_private;
-	io->block = bio->bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT);
-	io->n_blocks = bio->bi_size >> v->data_dev_block_bits;
+	io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT);
+	io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits;
 
 	bio->bi_end_io = verity_end_io;
 	bio->bi_private = io;
-	io->io_vec_size = bio_segments(bio);
-	if (io->io_vec_size < DM_VERITY_IO_VEC_INLINE)
-		io->io_vec = io->io_vec_inline;
-	else
-		io->io_vec = mempool_alloc(v->vec_mempool, GFP_NOIO);
-	memcpy(io->io_vec, bio_iovec(bio),
-	       io->io_vec_size * sizeof(struct bio_vec));
+	io->iter = bio->bi_iter;
 
 	verity_submit_prefetch(v, io);
 

drivers/md/dm.c

@@ -575,7 +575,7 @@ static void start_io_acct(struct dm_io *io)
 		atomic_inc_return(&md->pending[rw]));
 
 	if (unlikely(dm_stats_used(&md->stats)))
-		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector,
+		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
 				    bio_sectors(bio), false, 0, &io->stats_aux);
 }
 
@@ -593,7 +593,7 @@ static void end_io_acct(struct dm_io *io)
 	part_stat_unlock();
 
 	if (unlikely(dm_stats_used(&md->stats)))
-		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector,
+		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_iter.bi_sector,
 				    bio_sectors(bio), true, duration, &io->stats_aux);
 
 	/*
@@ -742,7 +742,7 @@ static void dec_pending(struct dm_io *io, int error)
 		if (io_error == DM_ENDIO_REQUEUE)
 			return;
 
-		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_size) {
+		if ((bio->bi_rw & REQ_FLUSH) && bio->bi_iter.bi_size) {
 			/*
 			 * Preflush done for flush with data, reissue
 			 * without REQ_FLUSH.
@@ -797,7 +797,7 @@ static void end_clone_bio(struct bio *clone, int error)
 	struct dm_rq_clone_bio_info *info = clone->bi_private;
 	struct dm_rq_target_io *tio = info->tio;
 	struct bio *bio = info->orig;
-	unsigned int nr_bytes = info->orig->bi_size;
+	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
 
 	bio_put(clone);
 
@@ -1128,7 +1128,7 @@ static void __map_bio(struct dm_target_io *tio)
 	 * this io.
 	 */
 	atomic_inc(&tio->io->io_count);
-	sector = clone->bi_sector;
+	sector = clone->bi_iter.bi_sector;
 	r = ti->type->map(ti, clone);
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
@@ -1155,76 +1155,32 @@ struct clone_info {
 	struct dm_io *io;
 	sector_t sector;
 	sector_t sector_count;
-	unsigned short idx;
 };
 
 static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len)
 {
-	bio->bi_sector = sector;
-	bio->bi_size = to_bytes(len);
-}
-
-static void bio_setup_bv(struct bio *bio, unsigned short idx, unsigned short bv_count)
-{
-	bio->bi_idx = idx;
-	bio->bi_vcnt = idx + bv_count;
-	bio->bi_flags &= ~(1 << BIO_SEG_VALID);
-}
-
-static void clone_bio_integrity(struct bio *bio, struct bio *clone,
-				unsigned short idx, unsigned len, unsigned offset,
-				unsigned trim)
-{
-	if (!bio_integrity(bio))
-		return;
-
-	bio_integrity_clone(clone, bio, GFP_NOIO);
-
-	if (trim)
-		bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len);
-}
-
-/*
- * Creates a little bio that just does part of a bvec.
- */
-static void clone_split_bio(struct dm_target_io *tio, struct bio *bio,
-			    sector_t sector, unsigned short idx,
-			    unsigned offset, unsigned len)
-{
-	struct bio *clone = &tio->clone;
-	struct bio_vec *bv = bio->bi_io_vec + idx;
-
-	*clone->bi_io_vec = *bv;
-
-	bio_setup_sector(clone, sector, len);
-
-	clone->bi_bdev = bio->bi_bdev;
-	clone->bi_rw = bio->bi_rw;
-	clone->bi_vcnt = 1;
-	clone->bi_io_vec->bv_offset = offset;
-	clone->bi_io_vec->bv_len = clone->bi_size;
-	clone->bi_flags |= 1 << BIO_CLONED;
-
-	clone_bio_integrity(bio, clone, idx, len, offset, 1);
+	bio->bi_iter.bi_sector = sector;
+	bio->bi_iter.bi_size = to_bytes(len);
 }
 
 /*
  * Creates a bio that consists of range of complete bvecs.
  */
 static void clone_bio(struct dm_target_io *tio, struct bio *bio,
-		      sector_t sector, unsigned short idx,
-		      unsigned short bv_count, unsigned len)
+		      sector_t sector, unsigned len)
 {
 	struct bio *clone = &tio->clone;
-	unsigned trim = 0;
 
-	__bio_clone(clone, bio);
-	bio_setup_sector(clone, sector, len);
-	bio_setup_bv(clone, idx, bv_count);
+	__bio_clone_fast(clone, bio);
 
-	if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
-		trim = 1;
-	clone_bio_integrity(bio, clone, idx, len, 0, trim);
+	if (bio_integrity(bio))
+		bio_integrity_clone(clone, bio, GFP_NOIO);
+
+	bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
+	clone->bi_iter.bi_size = to_bytes(len);
+
+	if (bio_integrity(bio))
+		bio_integrity_trim(clone, 0, len);
 }
 
 static struct dm_target_io *alloc_tio(struct clone_info *ci,
@@ -1257,7 +1213,7 @@ static void __clone_and_map_simple_bio(struct clone_info *ci,
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
 	 * and discard, so no need for concern about wasted bvec allocations.
 	 */
-	 __bio_clone(clone, ci->bio);
+	 __bio_clone_fast(clone, ci->bio);
 	if (len)
 		bio_setup_sector(clone, ci->sector, len);
 
@@ -1286,10 +1242,7 @@ static int __send_empty_flush(struct clone_info *ci)
 }
 
 static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
-				     sector_t sector, int nr_iovecs,
-				     unsigned short idx, unsigned short bv_count,
-				     unsigned offset, unsigned len,
-				     unsigned split_bvec)
+				     sector_t sector, unsigned len)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target_io *tio;
@@ -1303,11 +1256,8 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
 		num_target_bios = ti->num_write_bios(ti, bio);
 
 	for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
-		tio = alloc_tio(ci, ti, nr_iovecs, target_bio_nr);
-		if (split_bvec)
-			clone_split_bio(tio, bio, sector, idx, offset, len);
-		else
-			clone_bio(tio, bio, sector, idx, bv_count, len);
+		tio = alloc_tio(ci, ti, 0, target_bio_nr);
+		clone_bio(tio, bio, sector, len);
 		__map_bio(tio);
 	}
 }
@@ -1378,60 +1328,6 @@ static int __send_write_same(struct clone_info *ci)
 	return __send_changing_extent_only(ci, get_num_write_same_bios, NULL);
 }
 
-/*
- * Find maximum number of sectors / bvecs we can process with a single bio.
- */
-static sector_t __len_within_target(struct clone_info *ci, sector_t max, int *idx)
-{
-	struct bio *bio = ci->bio;
-	sector_t bv_len, total_len = 0;
-
-	for (*idx = ci->idx; max && (*idx < bio->bi_vcnt); (*idx)++) {
-		bv_len = to_sector(bio->bi_io_vec[*idx].bv_len);
-
-		if (bv_len > max)
-			break;
-
-		max -= bv_len;
-		total_len += bv_len;
-	}
-
-	return total_len;
-}
-
-static int __split_bvec_across_targets(struct clone_info *ci,
-				       struct dm_target *ti, sector_t max)
-{
-	struct bio *bio = ci->bio;
-	struct bio_vec *bv = bio->bi_io_vec + ci->idx;
-	sector_t remaining = to_sector(bv->bv_len);
-	unsigned offset = 0;
-	sector_t len;
-
-	do {
-		if (offset) {
-			ti = dm_table_find_target(ci->map, ci->sector);
-			if (!dm_target_is_valid(ti))
-				return -EIO;
-
-			max = max_io_len(ci->sector, ti);
-		}
-
-		len = min(remaining, max);
-
-		__clone_and_map_data_bio(ci, ti, ci->sector, 1, ci->idx, 0,
-					 bv->bv_offset + offset, len, 1);
-
-		ci->sector += len;
-		ci->sector_count -= len;
-		offset += to_bytes(len);
-	} while (remaining -= len);
-
-	ci->idx++;
-
-	return 0;
-}
-
 /*
  * Select the correct strategy for processing a non-flush bio.
  */
@@ -1439,8 +1335,7 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target *ti;
-	sector_t len, max;
-	int idx;
+	unsigned len;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD))
 		return __send_discard(ci);
@@ -1451,41 +1346,14 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	if (!dm_target_is_valid(ti))
 		return -EIO;
 
-	max = max_io_len(ci->sector, ti);
+	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
-	/*
-	 * Optimise for the simple case where we can do all of
-	 * the remaining io with a single clone.
-	 */
-	if (ci->sector_count <= max) {
-		__clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
-					 ci->idx, bio->bi_vcnt - ci->idx, 0,
-					 ci->sector_count, 0);
-		ci->sector_count = 0;
-		return 0;
-	}
+	__clone_and_map_data_bio(ci, ti, ci->sector, len);
 
-	/*
-	 * There are some bvecs that don't span targets.
-	 * Do as many of these as possible.
-	 */
-	if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
-		len = __len_within_target(ci, max, &idx);
+	ci->sector += len;
+	ci->sector_count -= len;
 
-		__clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
-					 ci->idx, idx - ci->idx, 0, len, 0);
-
-		ci->sector += len;
-		ci->sector_count -= len;
-		ci->idx = idx;
-
-		return 0;
-	}
-
-	/*
-	 * Handle a bvec that must be split between two or more targets.
-	 */
-	return __split_bvec_across_targets(ci, ti, max);
+	return 0;
 }
 
 /*
@@ -1510,8 +1378,7 @@ static void __split_and_process_bio(struct mapped_device *md,
 	ci.io->bio = bio;
 	ci.io->md = md;
 	spin_lock_init(&ci.io->endio_lock);
-	ci.sector = bio->bi_sector;
-	ci.idx = bio->bi_idx;
+	ci.sector = bio->bi_iter.bi_sector;
 
 	start_io_acct(ci.io);
 

drivers/md/faulty.c

@@ -74,8 +74,8 @@ static void faulty_fail(struct bio *bio, int error)
 {
 	struct bio *b = bio->bi_private;
 
-	b->bi_size = bio->bi_size;
-	b->bi_sector = bio->bi_sector;
+	b->bi_iter.bi_size = bio->bi_iter.bi_size;
+	b->bi_iter.bi_sector = bio->bi_iter.bi_sector;
 
 	bio_put(bio);
 
@@ -185,26 +185,31 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 			return;
 		}
 
-		if (check_sector(conf, bio->bi_sector, bio_end_sector(bio), WRITE))
+		if (check_sector(conf, bio->bi_iter.bi_sector,
+				 bio_end_sector(bio), WRITE))
 			failit = 1;
 		if (check_mode(conf, WritePersistent)) {
-			add_sector(conf, bio->bi_sector, WritePersistent);
+			add_sector(conf, bio->bi_iter.bi_sector,
+				   WritePersistent);
 			failit = 1;
 		}
 		if (check_mode(conf, WriteTransient))
 			failit = 1;
 	} else {
 		/* read request */
-		if (check_sector(conf, bio->bi_sector, bio_end_sector(bio), READ))
+		if (check_sector(conf, bio->bi_iter.bi_sector,
+				 bio_end_sector(bio), READ))
 			failit = 1;
 		if (check_mode(conf, ReadTransient))
 			failit = 1;
 		if (check_mode(conf, ReadPersistent)) {
-			add_sector(conf, bio->bi_sector, ReadPersistent);
+			add_sector(conf, bio->bi_iter.bi_sector,
+				   ReadPersistent);
 			failit = 1;
 		}
 		if (check_mode(conf, ReadFixable)) {
-			add_sector(conf, bio->bi_sector, ReadFixable);
+			add_sector(conf, bio->bi_iter.bi_sector,
+				   ReadFixable);
 			failit = 1;
 		}
 	}

drivers/md/linear.c

@@ -288,65 +288,65 @@ static int linear_stop (struct mddev *mddev)
 
 static void linear_make_request(struct mddev *mddev, struct bio *bio)
 {
+	char b[BDEVNAME_SIZE];
 	struct dev_info *tmp_dev;
-	sector_t start_sector;
+	struct bio *split;
+	sector_t start_sector, end_sector, data_offset;
 
 	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
 
-	rcu_read_lock();
-	tmp_dev = which_dev(mddev, bio->bi_sector);
-	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+	do {
+		rcu_read_lock();
 
-
-	if (unlikely(bio->bi_sector >= (tmp_dev->end_sector)
-		     || (bio->bi_sector < start_sector))) {
-		char b[BDEVNAME_SIZE];
-
-		printk(KERN_ERR
-		       "md/linear:%s: make_request: Sector %llu out of bounds on "
-		       "dev %s: %llu sectors, offset %llu\n",
-		       mdname(mddev),
-		       (unsigned long long)bio->bi_sector,
-		       bdevname(tmp_dev->rdev->bdev, b),
-		       (unsigned long long)tmp_dev->rdev->sectors,
-		       (unsigned long long)start_sector);
-		rcu_read_unlock();
-		bio_io_error(bio);
-		return;
-	}
-	if (unlikely(bio_end_sector(bio) > tmp_dev->end_sector)) {
-		/* This bio crosses a device boundary, so we have to
-		 * split it.
-		 */
-		struct bio_pair *bp;
-		sector_t end_sector = tmp_dev->end_sector;
+		tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);
+		start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
+		end_sector = tmp_dev->end_sector;
+		data_offset = tmp_dev->rdev->data_offset;
+		bio->bi_bdev = tmp_dev->rdev->bdev;
 
 		rcu_read_unlock();
 
-		bp = bio_split(bio, end_sector - bio->bi_sector);
+		if (unlikely(bio->bi_iter.bi_sector >= end_sector ||
+			     bio->bi_iter.bi_sector < start_sector))
+			goto out_of_bounds;
 
-		linear_make_request(mddev, &bp->bio1);
-		linear_make_request(mddev, &bp->bio2);
-		bio_pair_release(bp);
-		return;
-	}
-		    
-	bio->bi_bdev = tmp_dev->rdev->bdev;
-	bio->bi_sector = bio->bi_sector - start_sector
-		+ tmp_dev->rdev->data_offset;
-	rcu_read_unlock();
+		if (unlikely(bio_end_sector(bio) > end_sector)) {
+			/* This bio crosses a device boundary, so we have to
+			 * split it.
+			 */
+			split = bio_split(bio, end_sector -
+					  bio->bi_iter.bi_sector,
+					  GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
 
-	if (unlikely((bio->bi_rw & REQ_DISCARD) &&
-		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
-		/* Just ignore it */
-		bio_endio(bio, 0);
-		return;
-	}
+		split->bi_iter.bi_sector = split->bi_iter.bi_sector -
+			start_sector + data_offset;
 
-	generic_make_request(bio);
+		if (unlikely((split->bi_rw & REQ_DISCARD) &&
+			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
+			/* Just ignore it */
+			bio_endio(split, 0);
+		} else
+			generic_make_request(split);
+	} while (split != bio);
+	return;
+
+out_of_bounds:
+	printk(KERN_ERR
+	       "md/linear:%s: make_request: Sector %llu out of bounds on "
+	       "dev %s: %llu sectors, offset %llu\n",
+	       mdname(mddev),
+	       (unsigned long long)bio->bi_iter.bi_sector,
+	       bdevname(tmp_dev->rdev->bdev, b),
+	       (unsigned long long)tmp_dev->rdev->sectors,
+	       (unsigned long long)start_sector);
+	bio_io_error(bio);
 }
 
 static void linear_status (struct seq_file *seq, struct mddev *mddev)

drivers/md/md.c

@@ -393,7 +393,7 @@ static void md_submit_flush_data(struct work_struct *ws)
 	struct mddev *mddev = container_of(ws, struct mddev, flush_work);
 	struct bio *bio = mddev->flush_bio;
 
-	if (bio->bi_size == 0)
+	if (bio->bi_iter.bi_size == 0)
 		/* an empty barrier - all done */
 		bio_endio(bio, 0);
 	else {
@@ -754,7 +754,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);
 
 	bio->bi_bdev = rdev->meta_bdev ? rdev->meta_bdev : rdev->bdev;
-	bio->bi_sector = sector;
+	bio->bi_iter.bi_sector = sector;
 	bio_add_page(bio, page, size, 0);
 	bio->bi_private = rdev;
 	bio->bi_end_io = super_written;
@@ -782,18 +782,16 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev);
 	int ret;
 
-	rw |= REQ_SYNC;
-
 	bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
 		rdev->meta_bdev : rdev->bdev;
 	if (metadata_op)
-		bio->bi_sector = sector + rdev->sb_start;
+		bio->bi_iter.bi_sector = sector + rdev->sb_start;
 	else if (rdev->mddev->reshape_position != MaxSector &&
 		 (rdev->mddev->reshape_backwards ==
 		  (sector >= rdev->mddev->reshape_position)))
-		bio->bi_sector = sector + rdev->new_data_offset;
+		bio->bi_iter.bi_sector = sector + rdev->new_data_offset;
 	else
-		bio->bi_sector = sector + rdev->data_offset;
+		bio->bi_iter.bi_sector = sector + rdev->data_offset;
 	bio_add_page(bio, page, size, 0);
 	submit_bio_wait(rw, bio);
 

drivers/md/multipath.c

@@ -100,7 +100,7 @@ static void multipath_end_request(struct bio *bio, int error)
 		md_error (mp_bh->mddev, rdev);
 		printk(KERN_ERR "multipath: %s: rescheduling sector %llu\n", 
 		       bdevname(rdev->bdev,b), 
-		       (unsigned long long)bio->bi_sector);
+		       (unsigned long long)bio->bi_iter.bi_sector);
 		multipath_reschedule_retry(mp_bh);
 	} else
 		multipath_end_bh_io(mp_bh, error);
@@ -132,7 +132,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
 	multipath = conf->multipaths + mp_bh->path;
 
 	mp_bh->bio = *bio;
-	mp_bh->bio.bi_sector += multipath->rdev->data_offset;
+	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
 	mp_bh->bio.bi_bdev = multipath->rdev->bdev;
 	mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT;
 	mp_bh->bio.bi_end_io = multipath_end_request;
@@ -355,21 +355,22 @@ static void multipathd(struct md_thread *thread)
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 
 		bio = &mp_bh->bio;
-		bio->bi_sector = mp_bh->master_bio->bi_sector;
+		bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
 		
 		if ((mp_bh->path = multipath_map (conf))<0) {
 			printk(KERN_ALERT "multipath: %s: unrecoverable IO read"
 				" error for block %llu\n",
 				bdevname(bio->bi_bdev,b),
-				(unsigned long long)bio->bi_sector);
+				(unsigned long long)bio->bi_iter.bi_sector);
 			multipath_end_bh_io(mp_bh, -EIO);
 		} else {
 			printk(KERN_ERR "multipath: %s: redirecting sector %llu"
 				" to another IO path\n",
 				bdevname(bio->bi_bdev,b),
-				(unsigned long long)bio->bi_sector);
+				(unsigned long long)bio->bi_iter.bi_sector);
 			*bio = *(mp_bh->master_bio);
-			bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset;
+			bio->bi_iter.bi_sector +=
+				conf->multipaths[mp_bh->path].rdev->data_offset;
 			bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev;
 			bio->bi_rw |= REQ_FAILFAST_TRANSPORT;
 			bio->bi_end_io = multipath_end_request;

drivers/md/raid0.c

@@ -501,10 +501,11 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev,
 			unsigned int chunk_sects, struct bio *bio)
 {
 	if (likely(is_power_of_2(chunk_sects))) {
-		return chunk_sects >= ((bio->bi_sector & (chunk_sects-1))
+		return chunk_sects >=
+			((bio->bi_iter.bi_sector & (chunk_sects-1))
 					+ bio_sectors(bio));
 	} else{
-		sector_t sector = bio->bi_sector;
+		sector_t sector = bio->bi_iter.bi_sector;
 		return chunk_sects >= (sector_div(sector, chunk_sects)
 						+ bio_sectors(bio));
 	}
@@ -512,64 +513,44 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev,
 
 static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 {
-	unsigned int chunk_sects;
-	sector_t sector_offset;
 	struct strip_zone *zone;
 	struct md_rdev *tmp_dev;
+	struct bio *split;
 
 	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
 		md_flush_request(mddev, bio);
 		return;
 	}
 
-	chunk_sects = mddev->chunk_sectors;
-	if (unlikely(!is_io_in_chunk_boundary(mddev, chunk_sects, bio))) {
-		sector_t sector = bio->bi_sector;
-		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.
-		 */
-		if (likely(is_power_of_2(chunk_sects)))
-			bp = bio_split(bio, chunk_sects - (sector &
-							   (chunk_sects-1)));
-		else
-			bp = bio_split(bio, chunk_sects -
-				       sector_div(sector, chunk_sects));
-		raid0_make_request(mddev, &bp->bio1);
-		raid0_make_request(mddev, &bp->bio2);
-		bio_pair_release(bp);
-		return;
-	}
+	do {
+		sector_t sector = bio->bi_iter.bi_sector;
+		unsigned chunk_sects = mddev->chunk_sectors;
 
-	sector_offset = bio->bi_sector;
-	zone = find_zone(mddev->private, &sector_offset);
-	tmp_dev = map_sector(mddev, zone, bio->bi_sector,
-			     &sector_offset);
-	bio->bi_bdev = tmp_dev->bdev;
-	bio->bi_sector = sector_offset + zone->dev_start +
-		tmp_dev->data_offset;
+		unsigned sectors = chunk_sects -
+			(likely(is_power_of_2(chunk_sects))
+			 ? (sector & (chunk_sects-1))
+			 : sector_div(sector, chunk_sects));
 
-	if (unlikely((bio->bi_rw & REQ_DISCARD) &&
-		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
-		/* Just ignore it */
-		bio_endio(bio, 0);
-		return;
-	}
+		if (sectors < bio_sectors(bio)) {
+			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
 
-	generic_make_request(bio);
-	return;
+		zone = find_zone(mddev->private, &sector);
+		tmp_dev = map_sector(mddev, zone, sector, &sector);
+		split->bi_bdev = tmp_dev->bdev;
+		split->bi_iter.bi_sector = sector + zone->dev_start +
+			tmp_dev->data_offset;
 
-bad_map:
-	printk("md/raid0:%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;
+		if (unlikely((split->bi_rw & REQ_DISCARD) &&
+			 !blk_queue_discard(bdev_get_queue(split->bi_bdev)))) {
+			/* Just ignore it */
+			bio_endio(split, 0);
+		} else
+			generic_make_request(split);
+	} while (split != bio);
 }
 
 static void raid0_status(struct seq_file *seq, struct mddev *mddev)

drivers/md/raid1.c

@@ -229,7 +229,7 @@ static void call_bio_endio(struct r1bio *r1_bio)
 	int done;
 	struct r1conf *conf = r1_bio->mddev->private;
 	sector_t start_next_window = r1_bio->start_next_window;
-	sector_t bi_sector = bio->bi_sector;
+	sector_t bi_sector = bio->bi_iter.bi_sector;
 
 	if (bio->bi_phys_segments) {
 		unsigned long flags;
@@ -265,9 +265,8 @@ static void raid_end_bio_io(struct r1bio *r1_bio)
 	if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
 		pr_debug("raid1: sync end %s on sectors %llu-%llu\n",
 			 (bio_data_dir(bio) == WRITE) ? "write" : "read",
-			 (unsigned long long) bio->bi_sector,
-			 (unsigned long long) bio->bi_sector +
-			 bio_sectors(bio) - 1);
+			 (unsigned long long) bio->bi_iter.bi_sector,
+			 (unsigned long long) bio_end_sector(bio) - 1);
 
 		call_bio_endio(r1_bio);
 	}
@@ -466,9 +465,8 @@ static void raid1_end_write_request(struct bio *bio, int error)
 				struct bio *mbio = r1_bio->master_bio;
 				pr_debug("raid1: behind end write sectors"
 					 " %llu-%llu\n",
-					 (unsigned long long) mbio->bi_sector,
-					 (unsigned long long) mbio->bi_sector +
-					 bio_sectors(mbio) - 1);
+					 (unsigned long long) mbio->bi_iter.bi_sector,
+					 (unsigned long long) bio_end_sector(mbio) - 1);
 				call_bio_endio(r1_bio);
 			}
 		}
@@ -875,7 +873,7 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio)
 		else if ((conf->next_resync - RESYNC_WINDOW_SECTORS
 				>= bio_end_sector(bio)) ||
 			 (conf->next_resync + NEXT_NORMALIO_DISTANCE
-				<= bio->bi_sector))
+				<= bio->bi_iter.bi_sector))
 			wait = false;
 		else
 			wait = true;
@@ -913,14 +911,14 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 
 	if (bio && bio_data_dir(bio) == WRITE) {
 		if (conf->next_resync + NEXT_NORMALIO_DISTANCE
-		    <= bio->bi_sector) {
+		    <= bio->bi_iter.bi_sector) {
 			if (conf->start_next_window == MaxSector)
 				conf->start_next_window =
 					conf->next_resync +
 					NEXT_NORMALIO_DISTANCE;
 
 			if ((conf->start_next_window + NEXT_NORMALIO_DISTANCE)
-			    <= bio->bi_sector)
+			    <= bio->bi_iter.bi_sector)
 				conf->next_window_requests++;
 			else
 				conf->current_window_requests++;
@@ -1027,7 +1025,8 @@ do_sync_io:
 		if (bvecs[i].bv_page)
 			put_page(bvecs[i].bv_page);
 	kfree(bvecs);
-	pr_debug("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
+	pr_debug("%dB behind alloc failed, doing sync I/O\n",
+		 bio->bi_iter.bi_size);
 }
 
 struct raid1_plug_cb {
@@ -1107,7 +1106,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 
 	if (bio_data_dir(bio) == WRITE &&
 	    bio_end_sector(bio) > mddev->suspend_lo &&
-	    bio->bi_sector < mddev->suspend_hi) {
+	    bio->bi_iter.bi_sector < mddev->suspend_hi) {
 		/* As the suspend_* range is controlled by
 		 * userspace, we want an interruptible
 		 * wait.
@@ -1118,7 +1117,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 			prepare_to_wait(&conf->wait_barrier,
 					&w, TASK_INTERRUPTIBLE);
 			if (bio_end_sector(bio) <= mddev->suspend_lo ||
-			    bio->bi_sector >= mddev->suspend_hi)
+			    bio->bi_iter.bi_sector >= mddev->suspend_hi)
 				break;
 			schedule();
 		}
@@ -1140,7 +1139,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	r1_bio->sectors = bio_sectors(bio);
 	r1_bio->state = 0;
 	r1_bio->mddev = mddev;
-	r1_bio->sector = bio->bi_sector;
+	r1_bio->sector = bio->bi_iter.bi_sector;
 
 	/* We might need to issue multiple reads to different
 	 * devices if there are bad blocks around, so we keep
@@ -1180,12 +1179,13 @@ read_again:
 		r1_bio->read_disk = rdisk;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(read_bio, r1_bio->sector - bio->bi_sector,
+		bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
 			 max_sectors);
 
 		r1_bio->bios[rdisk] = read_bio;
 
-		read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
+		read_bio->bi_iter.bi_sector = r1_bio->sector +
+			mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid1_end_read_request;
 		read_bio->bi_rw = READ | do_sync;
@@ -1197,7 +1197,7 @@ read_again:
 			 */
 
 			sectors_handled = (r1_bio->sector + max_sectors
-					   - bio->bi_sector);
+					   - bio->bi_iter.bi_sector);
 			r1_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
 			if (bio->bi_phys_segments == 0)
@@ -1218,7 +1218,8 @@ read_again:
 			r1_bio->sectors = bio_sectors(bio) - sectors_handled;
 			r1_bio->state = 0;
 			r1_bio->mddev = mddev;
-			r1_bio->sector = bio->bi_sector + sectors_handled;
+			r1_bio->sector = bio->bi_iter.bi_sector +
+				sectors_handled;
 			goto read_again;
 		} else
 			generic_make_request(read_bio);
@@ -1321,7 +1322,7 @@ read_again:
 			if (r1_bio->bios[j])
 				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
 		r1_bio->state = 0;
-		allow_barrier(conf, start_next_window, bio->bi_sector);
+		allow_barrier(conf, start_next_window, bio->bi_iter.bi_sector);
 		md_wait_for_blocked_rdev(blocked_rdev, mddev);
 		start_next_window = wait_barrier(conf, bio);
 		/*
@@ -1348,7 +1349,7 @@ read_again:
 			bio->bi_phys_segments++;
 		spin_unlock_irq(&conf->device_lock);
 	}
-	sectors_handled = r1_bio->sector + max_sectors - bio->bi_sector;
+	sectors_handled = r1_bio->sector + max_sectors - bio->bi_iter.bi_sector;
 
 	atomic_set(&r1_bio->remaining, 1);
 	atomic_set(&r1_bio->behind_remaining, 0);
@@ -1360,7 +1361,7 @@ read_again:
 			continue;
 
 		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(mbio, r1_bio->sector - bio->bi_sector, max_sectors);
+		bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector, max_sectors);
 
 		if (first_clone) {
 			/* do behind I/O ?
@@ -1394,7 +1395,7 @@ read_again:
 
 		r1_bio->bios[i] = mbio;
 
-		mbio->bi_sector	= (r1_bio->sector +
+		mbio->bi_iter.bi_sector	= (r1_bio->sector +
 				   conf->mirrors[i].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
@@ -1434,7 +1435,7 @@ read_again:
 		r1_bio->sectors = bio_sectors(bio) - sectors_handled;
 		r1_bio->state = 0;
 		r1_bio->mddev = mddev;
-		r1_bio->sector = bio->bi_sector + sectors_handled;
+		r1_bio->sector = bio->bi_iter.bi_sector + sectors_handled;
 		goto retry_write;
 	}
 
@@ -1958,14 +1959,14 @@ static int process_checks(struct r1bio *r1_bio)
 		/* fixup the bio for reuse */
 		bio_reset(b);
 		b->bi_vcnt = vcnt;
-		b->bi_size = r1_bio->sectors << 9;
-		b->bi_sector = r1_bio->sector +
+		b->bi_iter.bi_size = r1_bio->sectors << 9;
+		b->bi_iter.bi_sector = r1_bio->sector +
 			conf->mirrors[i].rdev->data_offset;
 		b->bi_bdev = conf->mirrors[i].rdev->bdev;
 		b->bi_end_io = end_sync_read;
 		b->bi_private = r1_bio;
 
-		size = b->bi_size;
+		size = b->bi_iter.bi_size;
 		for (j = 0; j < vcnt ; j++) {
 			struct bio_vec *bi;
 			bi = &b->bi_io_vec[j];
@@ -2220,11 +2221,11 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 		}
 
 		wbio->bi_rw = WRITE;
-		wbio->bi_sector = r1_bio->sector;
-		wbio->bi_size = r1_bio->sectors << 9;
+		wbio->bi_iter.bi_sector = r1_bio->sector;
+		wbio->bi_iter.bi_size = r1_bio->sectors << 9;
 
 		bio_trim(wbio, sector - r1_bio->sector, sectors);
-		wbio->bi_sector += rdev->data_offset;
+		wbio->bi_iter.bi_sector += rdev->data_offset;
 		wbio->bi_bdev = rdev->bdev;
 		if (submit_bio_wait(WRITE, wbio) == 0)
 			/* failure! */
@@ -2338,7 +2339,8 @@ read_more:
 		}
 		r1_bio->read_disk = disk;
 		bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
-		bio_trim(bio, r1_bio->sector - bio->bi_sector, max_sectors);
+		bio_trim(bio, r1_bio->sector - bio->bi_iter.bi_sector,
+			 max_sectors);
 		r1_bio->bios[r1_bio->read_disk] = bio;
 		rdev = conf->mirrors[disk].rdev;
 		printk_ratelimited(KERN_ERR
@@ -2347,7 +2349,7 @@ read_more:
 				   mdname(mddev),
 				   (unsigned long long)r1_bio->sector,
 				   bdevname(rdev->bdev, b));
-		bio->bi_sector = r1_bio->sector + rdev->data_offset;
+		bio->bi_iter.bi_sector = r1_bio->sector + rdev->data_offset;
 		bio->bi_bdev = rdev->bdev;
 		bio->bi_end_io = raid1_end_read_request;
 		bio->bi_rw = READ | do_sync;
@@ -2356,7 +2358,7 @@ read_more:
 			/* Drat - have to split this up more */
 			struct bio *mbio = r1_bio->master_bio;
 			int sectors_handled = (r1_bio->sector + max_sectors
-					       - mbio->bi_sector);
+					       - mbio->bi_iter.bi_sector);
 			r1_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
 			if (mbio->bi_phys_segments == 0)
@@ -2374,7 +2376,8 @@ read_more:
 			r1_bio->state = 0;
 			set_bit(R1BIO_ReadError, &r1_bio->state);
 			r1_bio->mddev = mddev;
-			r1_bio->sector = mbio->bi_sector + sectors_handled;
+			r1_bio->sector = mbio->bi_iter.bi_sector +
+				sectors_handled;
 
 			goto read_more;
 		} else
@@ -2598,7 +2601,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 		}
 		if (bio->bi_end_io) {
 			atomic_inc(&rdev->nr_pending);
-			bio->bi_sector = sector_nr + rdev->data_offset;
+			bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
 			bio->bi_bdev = rdev->bdev;
 			bio->bi_private = r1_bio;
 		}
@@ -2698,7 +2701,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 							continue;
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
-						bio->bi_size -= len;
+						bio->bi_iter.bi_size -= len;
 						bio->bi_flags &= ~(1<< BIO_SEG_VALID);
 					}
 					goto bio_full;

drivers/md/raid10.c

@@ -1152,14 +1152,12 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	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);
@@ -1174,88 +1172,27 @@ 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_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);
-
-	/*
-	 * Register the new request and wait if the reconstruction
-	 * thread has put up a bar for new requests.
-	 * Continue immediately if no resync is active currently.
-	 */
-	wait_barrier(conf);
-
 	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);
@@ -1273,7 +1210,7 @@ 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
@@ -1302,13 +1239,13 @@ read_again:
 		slot = r10_bio->read_slot;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		bio_trim(read_bio, r10_bio->sector - bio->bi_sector,
+		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;
@@ -1320,7 +1257,7 @@ read_again:
 			 * 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)
@@ -1341,7 +1278,8 @@ read_again:
 			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);
@@ -1499,7 +1437,8 @@ 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);
@@ -1510,11 +1449,11 @@ retry_write:
 		if (r10_bio->devs[i].bio) {
 			struct md_rdev *rdev = conf->mirrors[d].rdev;
 			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-			bio_trim(mbio, r10_bio->sector - bio->bi_sector,
+			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;
@@ -1553,11 +1492,11 @@ retry_write:
 				rdev = conf->mirrors[d].rdev;
 			}
 			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-			bio_trim(mbio, r10_bio->sector - bio->bi_sector,
+			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;
@@ -1591,11 +1530,57 @@ retry_write:
 		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);
+
+	/*
+	 * Register the new request and wait if the reconstruction
+	 * thread has put up a bar for new requests.
+	 * Continue immediately if no resync is active currently.
+	 */
+	wait_barrier(conf);
+
+	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);
@@ -2124,10 +2109,10 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		bio_reset(tbio);
 
 		tbio->bi_vcnt = vcnt;
-		tbio->bi_size = r10_bio->sectors << 9;
+		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;
@@ -2144,7 +2129,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		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);
 	}
@@ -2614,8 +2599,8 @@ 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);
-		bio_trim(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;
@@ -2687,10 +2672,10 @@ read_more:
 		(unsigned long long)r10_bio->sector);
 	bio = bio_clone_mddev(r10_bio->master_bio,
 			      GFP_NOIO, mddev);
-	bio_trim(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;
@@ -2701,7 +2686,7 @@ 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)
@@ -2719,7 +2704,7 @@ read_more:
 		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;
@@ -3157,7 +3142,8 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				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) */
@@ -3181,7 +3167,7 @@ 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 = to_addr
+					bio->bi_iter.bi_sector = to_addr
 						+ rdev->data_offset;
 					bio->bi_bdev = rdev->bdev;
 					atomic_inc(&r10_bio->remaining);
@@ -3210,7 +3196,8 @@ 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 = 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;
@@ -3328,7 +3315,7 @@ 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++;
@@ -3350,7 +3337,7 @@ 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++;
@@ -3397,7 +3384,7 @@ 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;
@@ -4418,7 +4405,7 @@ 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;
@@ -4426,7 +4413,7 @@ 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_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;
 
@@ -4452,7 +4439,8 @@ read_more:
 
 		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;
@@ -4479,7 +4467,7 @@ 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;

drivers/md/raid5.c

@@ -133,7 +133,7 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
 static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 {
 	int sectors = bio_sectors(bio);
-	if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
+	if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
 		return bio->bi_next;
 	else
 		return NULL;
@@ -225,7 +225,7 @@ static void return_io(struct bio *return_bi)
 
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
-		bi->bi_size = 0;
+		bi->bi_iter.bi_size = 0;
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
 		bio_endio(bi, 0);
@@ -852,10 +852,10 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 				bi->bi_rw, i);
 			atomic_inc(&sh->count);
 			if (use_new_offset(conf, sh))
-				bi->bi_sector = (sh->sector
+				bi->bi_iter.bi_sector = (sh->sector
 						 + rdev->new_data_offset);
 			else
-				bi->bi_sector = (sh->sector
+				bi->bi_iter.bi_sector = (sh->sector
 						 + rdev->data_offset);
 			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 				bi->bi_rw |= REQ_NOMERGE;
@@ -863,7 +863,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			bi->bi_vcnt = 1;
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
-			bi->bi_size = STRIPE_SIZE;
+			bi->bi_iter.bi_size = STRIPE_SIZE;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -899,15 +899,15 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 				rbi->bi_rw, i);
 			atomic_inc(&sh->count);
 			if (use_new_offset(conf, sh))
-				rbi->bi_sector = (sh->sector
+				rbi->bi_iter.bi_sector = (sh->sector
 						  + rrdev->new_data_offset);
 			else
-				rbi->bi_sector = (sh->sector
+				rbi->bi_iter.bi_sector = (sh->sector
 						  + rrdev->data_offset);
 			rbi->bi_vcnt = 1;
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
-			rbi->bi_size = STRIPE_SIZE;
+			rbi->bi_iter.bi_size = STRIPE_SIZE;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -935,24 +935,24 @@ static struct dma_async_tx_descriptor *
 async_copy_data(int frombio, struct bio *bio, struct page *page,
 	sector_t sector, struct dma_async_tx_descriptor *tx)
 {
-	struct bio_vec *bvl;
+	struct bio_vec bvl;
+	struct bvec_iter iter;
 	struct page *bio_page;
-	int i;
 	int page_offset;
 	struct async_submit_ctl submit;
 	enum async_tx_flags flags = 0;
 
-	if (bio->bi_sector >= sector)
-		page_offset = (signed)(bio->bi_sector - sector) * 512;
+	if (bio->bi_iter.bi_sector >= sector)
+		page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512;
 	else
-		page_offset = (signed)(sector - bio->bi_sector) * -512;
+		page_offset = (signed)(sector - bio->bi_iter.bi_sector) * -512;
 
 	if (frombio)
 		flags |= ASYNC_TX_FENCE;
 	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
 
-	bio_for_each_segment(bvl, bio, i) {
-		int len = bvl->bv_len;
+	bio_for_each_segment(bvl, bio, iter) {
+		int len = bvl.bv_len;
 		int clen;
 		int b_offset = 0;
 
@@ -968,8 +968,8 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 			clen = len;
 
 		if (clen > 0) {
-			b_offset += bvl->bv_offset;
-			bio_page = bvl->bv_page;
+			b_offset += bvl.bv_offset;
+			bio_page = bvl.bv_page;
 			if (frombio)
 				tx = async_memcpy(page, bio_page, page_offset,
 						  b_offset, clen, &submit);
@@ -1012,7 +1012,7 @@ static void ops_complete_biofill(void *stripe_head_ref)
 			BUG_ON(!dev->read);
 			rbi = dev->read;
 			dev->read = NULL;
-			while (rbi && rbi->bi_sector <
+			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
 				if (!raid5_dec_bi_active_stripes(rbi)) {
@@ -1048,7 +1048,7 @@ static void ops_run_biofill(struct stripe_head *sh)
 			dev->read = rbi = dev->toread;
 			dev->toread = NULL;
 			spin_unlock_irq(&sh->stripe_lock);
-			while (rbi && rbi->bi_sector <
+			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				tx = async_copy_data(0, rbi, dev->page,
 					dev->sector, tx);
@@ -1390,7 +1390,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 			wbi = dev->written = chosen;
 			spin_unlock_irq(&sh->stripe_lock);
 
-			while (wbi && wbi->bi_sector <
+			while (wbi && wbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				if (wbi->bi_rw & REQ_FUA)
 					set_bit(R5_WantFUA, &dev->flags);
@@ -2615,7 +2615,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 	int firstwrite=0;
 
 	pr_debug("adding bi b#%llu to stripe s#%llu\n",
-		(unsigned long long)bi->bi_sector,
+		(unsigned long long)bi->bi_iter.bi_sector,
 		(unsigned long long)sh->sector);
 
 	/*
@@ -2633,12 +2633,12 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 			firstwrite = 1;
 	} else
 		bip = &sh->dev[dd_idx].toread;
-	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
-		if (bio_end_sector(*bip) > bi->bi_sector)
+	while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) {
+		if (bio_end_sector(*bip) > bi->bi_iter.bi_sector)
 			goto overlap;
 		bip = & (*bip)->bi_next;
 	}
-	if (*bip && (*bip)->bi_sector < bio_end_sector(bi))
+	if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi))
 		goto overlap;
 
 	BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
@@ -2652,7 +2652,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		sector_t sector = sh->dev[dd_idx].sector;
 		for (bi=sh->dev[dd_idx].towrite;
 		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
-			     bi && bi->bi_sector <= sector;
+			     bi && bi->bi_iter.bi_sector <= sector;
 		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
 			if (bio_end_sector(bi) >= sector)
 				sector = bio_end_sector(bi);
@@ -2662,7 +2662,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 	}
 
 	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
-		(unsigned long long)(*bip)->bi_sector,
+		(unsigned long long)(*bip)->bi_iter.bi_sector,
 		(unsigned long long)sh->sector, dd_idx);
 	spin_unlock_irq(&sh->stripe_lock);
 
@@ -2737,7 +2737,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 			wake_up(&conf->wait_for_overlap);
 
-		while (bi && bi->bi_sector <
+		while (bi && bi->bi_iter.bi_sector <
 			sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -2756,7 +2756,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		bi = sh->dev[i].written;
 		sh->dev[i].written = NULL;
 		if (bi) bitmap_end = 1;
-		while (bi && bi->bi_sector <
+		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -2780,7 +2780,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			spin_unlock_irq(&sh->stripe_lock);
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up(&conf->wait_for_overlap);
-			while (bi && bi->bi_sector <
+			while (bi && bi->bi_iter.bi_sector <
 			       sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *nextbi =
 					r5_next_bio(bi, sh->dev[i].sector);
@@ -3004,7 +3004,7 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 					clear_bit(R5_UPTODATE, &dev->flags);
 				wbi = dev->written;
 				dev->written = NULL;
-				while (wbi && wbi->bi_sector <
+				while (wbi && wbi->bi_iter.bi_sector <
 					dev->sector + STRIPE_SECTORS) {
 					wbi2 = r5_next_bio(wbi, dev->sector);
 					if (!raid5_dec_bi_active_stripes(wbi)) {
@@ -4096,7 +4096,7 @@ static int raid5_mergeable_bvec(struct request_queue *q,
 
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev);
 	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bio_sectors(bio);
 
@@ -4233,9 +4233,9 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 	/*
 	 *	compute position
 	 */
-	align_bi->bi_sector =  raid5_compute_sector(conf, raid_bio->bi_sector,
-						    0,
-						    &dd_idx, NULL);
+	align_bi->bi_iter.bi_sector =
+		raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector,
+				     0, &dd_idx, NULL);
 
 	end_sector = bio_end_sector(align_bi);
 	rcu_read_lock();
@@ -4260,7 +4260,8 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 		if (!bio_fits_rdev(align_bi) ||
-		    is_badblock(rdev, align_bi->bi_sector, bio_sectors(align_bi),
+		    is_badblock(rdev, align_bi->bi_iter.bi_sector,
+				bio_sectors(align_bi),
 				&first_bad, &bad_sectors)) {
 			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
@@ -4269,7 +4270,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		}
 
 		/* No reshape active, so we can trust rdev->data_offset */
-		align_bi->bi_sector += rdev->data_offset;
+		align_bi->bi_iter.bi_sector += rdev->data_offset;
 
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
@@ -4281,7 +4282,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		if (mddev->gendisk)
 			trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
 					      align_bi, disk_devt(mddev->gendisk),
-					      raid_bio->bi_sector);
+					      raid_bio->bi_iter.bi_sector);
 		generic_make_request(align_bi);
 		return 1;
 	} else {
@@ -4464,8 +4465,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		/* Skip discard while reshape is happening */
 		return;
 
-	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	last_sector = bi->bi_sector + (bi->bi_size>>9);
+	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+	last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
 
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
@@ -4569,7 +4570,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 		return;
 	}
 
-	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
@@ -5053,7 +5054,8 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	int remaining;
 	int handled = 0;
 
-	logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+	logical_sector = raid_bio->bi_iter.bi_sector &
+		~((sector_t)STRIPE_SECTORS-1);
 	sector = raid5_compute_sector(conf, logical_sector,
 				      0, &dd_idx, NULL);
 	last_sector = bio_end_sector(raid_bio);