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()
  ...

Documentation/block/biodoc.txt

@@ -447,14 +447,13 @@ struct bio_vec {
  * main unit of I/O for the block layer and lower layers (ie drivers)
  */
 struct bio {
-       sector_t            bi_sector;
        struct bio          *bi_next;    /* request queue link */
        struct block_device *bi_bdev;	/* target device */
        unsigned long       bi_flags;    /* status, command, etc */
        unsigned long       bi_rw;       /* low bits: r/w, high: priority */
 
        unsigned int	bi_vcnt;     /* how may bio_vec's */
-       unsigned int	bi_idx;		/* current index into bio_vec array */
+       struct bvec_iter	bi_iter;	/* current index into bio_vec array */
 
        unsigned int	bi_size;     /* total size in bytes */
        unsigned short 	bi_phys_segments; /* segments after physaddr coalesce*/
@@ -480,7 +479,7 @@ With this multipage bio design:
 - Code that traverses the req list can find all the segments of a bio
   by using rq_for_each_segment.  This handles the fact that a request
   has multiple bios, each of which can have multiple segments.
-- Drivers which can't process a large bio in one shot can use the bi_idx
+- Drivers which can't process a large bio in one shot can use the bi_iter
   field to keep track of the next bio_vec entry to process.
   (e.g a 1MB bio_vec needs to be handled in max 128kB chunks for IDE)
   [TBD: Should preferably also have a bi_voffset and bi_vlen to avoid modifying
@@ -589,7 +588,7 @@ driver should not modify these values. The block layer sets up the
 nr_sectors and current_nr_sectors fields (based on the corresponding
 hard_xxx values and the number of bytes transferred) and updates it on
 every transfer that invokes end_that_request_first. It does the same for the
-buffer, bio, bio->bi_idx fields too.
+buffer, bio, bio->bi_iter fields too.
 
 The buffer field is just a virtual address mapping of the current segment
 of the i/o buffer in cases where the buffer resides in low-memory. For high

Documentation/block/biovecs.txt

@@ -0,0 +1,111 @@
+
+Immutable biovecs and biovec iterators:
+=======================================
+
+Kent Overstreet <kmo@daterainc.com>
+
+As of 3.13, biovecs should never be modified after a bio has been submitted.
+Instead, we have a new struct bvec_iter which represents a range of a biovec -
+the iterator will be modified as the bio is completed, not the biovec.
+
+More specifically, old code that needed to partially complete a bio would
+update bi_sector and bi_size, and advance bi_idx to the next biovec. If it
+ended up partway through a biovec, it would increment bv_offset and decrement
+bv_len by the number of bytes completed in that biovec.
+
+In the new scheme of things, everything that must be mutated in order to
+partially complete a bio is segregated into struct bvec_iter: bi_sector,
+bi_size and bi_idx have been moved there; and instead of modifying bv_offset
+and bv_len, struct bvec_iter has bi_bvec_done, which represents the number of
+bytes completed in the current bvec.
+
+There are a bunch of new helper macros for hiding the gory details - in
+particular, presenting the illusion of partially completed biovecs so that
+normal code doesn't have to deal with bi_bvec_done.
+
+ * Driver code should no longer refer to biovecs directly; we now have
+   bio_iovec() and bio_iovec_iter() macros that return literal struct biovecs,
+   constructed from the raw biovecs but taking into account bi_bvec_done and
+   bi_size.
+
+   bio_for_each_segment() has been updated to take a bvec_iter argument
+   instead of an integer (that corresponded to bi_idx); for a lot of code the
+   conversion just required changing the types of the arguments to
+   bio_for_each_segment().
+
+ * Advancing a bvec_iter is done with bio_advance_iter(); bio_advance() is a
+   wrapper around bio_advance_iter() that operates on bio->bi_iter, and also
+   advances the bio integrity's iter if present.
+
+   There is a lower level advance function - bvec_iter_advance() - which takes
+   a pointer to a biovec, not a bio; this is used by the bio integrity code.
+
+What's all this get us?
+=======================
+
+Having a real iterator, and making biovecs immutable, has a number of
+advantages:
+
+ * Before, iterating over bios was very awkward when you weren't processing
+   exactly one bvec at a time - for example, bio_copy_data() in fs/bio.c,
+   which copies the contents of one bio into another. Because the biovecs
+   wouldn't necessarily be the same size, the old code was tricky convoluted -
+   it had to walk two different bios at the same time, keeping both bi_idx and
+   and offset into the current biovec for each.
+
+   The new code is much more straightforward - have a look. This sort of
+   pattern comes up in a lot of places; a lot of drivers were essentially open
+   coding bvec iterators before, and having common implementation considerably
+   simplifies a lot of code.
+
+ * Before, any code that might need to use the biovec after the bio had been
+   completed (perhaps to copy the data somewhere else, or perhaps to resubmit
+   it somewhere else if there was an error) had to save the entire bvec array
+   - again, this was being done in a fair number of places.
+
+ * Biovecs can be shared between multiple bios - a bvec iter can represent an
+   arbitrary range of an existing biovec, both starting and ending midway
+   through biovecs. This is what enables efficient splitting of arbitrary
+   bios. Note that this means we _only_ use bi_size to determine when we've
+   reached the end of a bio, not bi_vcnt - and the bio_iovec() macro takes
+   bi_size into account when constructing biovecs.
+
+ * Splitting bios is now much simpler. The old bio_split() didn't even work on
+   bios with more than a single bvec! Now, we can efficiently split arbitrary
+   size bios - because the new bio can share the old bio's biovec.
+
+   Care must be taken to ensure the biovec isn't freed while the split bio is
+   still using it, in case the original bio completes first, though. Using
+   bio_chain() when splitting bios helps with this.
+
+ * Submitting partially completed bios is now perfectly fine - this comes up
+   occasionally in stacking block drivers and various code (e.g. md and
+   bcache) had some ugly workarounds for this.
+
+   It used to be the case that submitting a partially completed bio would work
+   fine to _most_ devices, but since accessing the raw bvec array was the
+   norm, not all drivers would respect bi_idx and those would break. Now,
+   since all drivers _must_ go through the bvec iterator - and have been
+   audited to make sure they are - submitting partially completed bios is
+   perfectly fine.
+
+Other implications:
+===================
+
+ * Almost all usage of bi_idx is now incorrect and has been removed; instead,
+   where previously you would have used bi_idx you'd now use a bvec_iter,
+   probably passing it to one of the helper macros.
+
+   I.e. instead of using bio_iovec_idx() (or bio->bi_iovec[bio->bi_idx]), you
+   now use bio_iter_iovec(), which takes a bvec_iter and returns a
+   literal struct bio_vec - constructed on the fly from the raw biovec but
+   taking into account bi_bvec_done (and bi_size).
+
+ * bi_vcnt can't be trusted or relied upon by driver code - i.e. anything that
+   doesn't actually own the bio. The reason is twofold: firstly, it's not
+   actually needed for iterating over the bio anymore - we only use bi_size.
+   Secondly, when cloning a bio and reusing (a portion of) the original bio's
+   biovec, in order to calculate bi_vcnt for the new bio we'd have to iterate
+   over all the biovecs in the new bio - which is silly as it's not needed.
+
+   So, don't use bi_vcnt anymore.

arch/m68k/emu/nfblock.c

@@ -62,17 +62,18 @@ struct nfhd_device {
 static void nfhd_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct nfhd_device *dev = queue->queuedata;
-	struct bio_vec *bvec;
-	int i, dir, len, shift;
-	sector_t sec = bio->bi_sector;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	int dir, len, shift;
+	sector_t sec = bio->bi_iter.bi_sector;
 
 	dir = bio_data_dir(bio);
 	shift = dev->bshift;
-	bio_for_each_segment(bvec, bio, i) {
-		len = bvec->bv_len;
+	bio_for_each_segment(bvec, bio, iter) {
+		len = bvec.bv_len;
 		len >>= 9;
 		nfhd_read_write(dev->id, 0, dir, sec >> shift, len >> shift,
-				bvec_to_phys(bvec));
+				bvec_to_phys(&bvec));
 		sec += len;
 	}
 	bio_endio(bio, 0);

arch/powerpc/sysdev/axonram.c

@@ -109,27 +109,28 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
 	struct axon_ram_bank *bank = bio->bi_bdev->bd_disk->private_data;
 	unsigned long phys_mem, phys_end;
 	void *user_mem;
-	struct bio_vec *vec;
+	struct bio_vec vec;
 	unsigned int transfered;
-	unsigned short idx;
+	struct bvec_iter iter;
 
-	phys_mem = bank->io_addr + (bio->bi_sector << AXON_RAM_SECTOR_SHIFT);
+	phys_mem = bank->io_addr + (bio->bi_iter.bi_sector <<
+				    AXON_RAM_SECTOR_SHIFT);
 	phys_end = bank->io_addr + bank->size;
 	transfered = 0;
-	bio_for_each_segment(vec, bio, idx) {
-		if (unlikely(phys_mem + vec->bv_len > phys_end)) {
+	bio_for_each_segment(vec, bio, iter) {
+		if (unlikely(phys_mem + vec.bv_len > phys_end)) {
 			bio_io_error(bio);
 			return;
 		}
 
-		user_mem = page_address(vec->bv_page) + vec->bv_offset;
+		user_mem = page_address(vec.bv_page) + vec.bv_offset;
 		if (bio_data_dir(bio) == READ)
-			memcpy(user_mem, (void *) phys_mem, vec->bv_len);
+			memcpy(user_mem, (void *) phys_mem, vec.bv_len);
 		else
-			memcpy((void *) phys_mem, user_mem, vec->bv_len);
+			memcpy((void *) phys_mem, user_mem, vec.bv_len);
 
-		phys_mem += vec->bv_len;
-		transfered += vec->bv_len;
+		phys_mem += vec.bv_len;
+		transfered += vec.bv_len;
 	}
 	bio_endio(bio, 0);
 }

arch/xtensa/platforms/iss/simdisk.c

@@ -103,18 +103,18 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 
 static int simdisk_xfer_bio(struct simdisk *dev, struct bio *bio)
 {
-	int i;
-	struct bio_vec *bvec;
-	sector_t sector = bio->bi_sector;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	sector_t sector = bio->bi_iter.bi_sector;
 
-	bio_for_each_segment(bvec, bio, i) {
-		char *buffer = __bio_kmap_atomic(bio, i);
-		unsigned len = bvec->bv_len >> SECTOR_SHIFT;
+	bio_for_each_segment(bvec, bio, iter) {
+		char *buffer = __bio_kmap_atomic(bio, iter);
+		unsigned len = bvec.bv_len >> SECTOR_SHIFT;
 
 		simdisk_transfer(dev, sector, len, buffer,
 				bio_data_dir(bio) == WRITE);
 		sector += len;
-		__bio_kunmap_atomic(bio);
+		__bio_kunmap_atomic(buffer);
 	}
 	return 0;
 }

block/blk-core.c

@@ -38,6 +38,7 @@
 
 #include "blk.h"
 #include "blk-cgroup.h"
+#include "blk-mq.h"
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
@@ -130,7 +131,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
 		bio_endio(bio, error);
 }
 
@@ -245,7 +246,16 @@ EXPORT_SYMBOL(blk_stop_queue);
 void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->timeout);
-	cancel_delayed_work_sync(&q->delay_work);
+
+	if (q->mq_ops) {
+		struct blk_mq_hw_ctx *hctx;
+		int i;
+
+		queue_for_each_hw_ctx(q, hctx, i)
+			cancel_delayed_work_sync(&hctx->delayed_work);
+	} else {
+		cancel_delayed_work_sync(&q->delay_work);
+	}
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -497,8 +507,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
-	spin_lock_irq(lock);
-	__blk_drain_queue(q, true);
+	if (q->mq_ops) {
+		blk_mq_drain_queue(q);
+		spin_lock_irq(lock);
+	} else {
+		spin_lock_irq(lock);
+		__blk_drain_queue(q, true);
+	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
@@ -1326,7 +1341,7 @@ void blk_add_request_payload(struct request *rq, struct page *page,
 	bio->bi_io_vec->bv_offset = 0;
 	bio->bi_io_vec->bv_len = len;
 
-	bio->bi_size = len;
+	bio->bi_iter.bi_size = len;
 	bio->bi_vcnt = 1;
 	bio->bi_phys_segments = 1;
 
@@ -1351,7 +1366,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
-	req->__data_len += bio->bi_size;
+	req->__data_len += bio->bi_iter.bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	blk_account_io_start(req, false);
@@ -1380,8 +1395,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 	 * not touch req->buffer either...
 	 */
 	req->buffer = bio_data(bio);
-	req->__sector = bio->bi_sector;
-	req->__data_len += bio->bi_size;
+	req->__sector = bio->bi_iter.bi_sector;
+	req->__data_len += bio->bi_iter.bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	blk_account_io_start(req, false);
@@ -1459,7 +1474,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
 	req->errors = 0;
-	req->__sector = bio->bi_sector;
+	req->__sector = bio->bi_iter.bi_sector;
 	req->ioprio = bio_prio(bio);
 	blk_rq_bio_prep(req->q, req, bio);
 }
@@ -1583,12 +1598,12 @@ static inline void blk_partition_remap(struct bio *bio)
 	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
 		struct hd_struct *p = bdev->bd_part;
 
-		bio->bi_sector += p->start_sect;
+		bio->bi_iter.bi_sector += p->start_sect;
 		bio->bi_bdev = bdev->bd_contains;
 
 		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
 				      bdev->bd_dev,
-				      bio->bi_sector - p->start_sect);
+				      bio->bi_iter.bi_sector - p->start_sect);
 	}
 }
 
@@ -1654,7 +1669,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
 	/* Test device or partition size, when known. */
 	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
 	if (maxsector) {
-		sector_t sector = bio->bi_sector;
+		sector_t sector = bio->bi_iter.bi_sector;
 
 		if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
 			/*
@@ -1690,7 +1705,7 @@ generic_make_request_checks(struct bio *bio)
 		       "generic_make_request: Trying to access "
 			"nonexistent block-device %s (%Lu)\n",
 			bdevname(bio->bi_bdev, b),
-			(long long) bio->bi_sector);
+			(long long) bio->bi_iter.bi_sector);
 		goto end_io;
 	}
 
@@ -1704,9 +1719,9 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	part = bio->bi_bdev->bd_part;
-	if (should_fail_request(part, bio->bi_size) ||
+	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
-				bio->bi_size))
+				bio->bi_iter.bi_size))
 		goto end_io;
 
 	/*
@@ -1865,7 +1880,7 @@ void submit_bio(int rw, struct bio *bio)
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {
-			task_io_account_read(bio->bi_size);
+			task_io_account_read(bio->bi_iter.bi_size);
 			count_vm_events(PGPGIN, count);
 		}
 
@@ -1874,7 +1889,7 @@ void submit_bio(int rw, struct bio *bio)
 			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
 				(rw & WRITE) ? "WRITE" : "READ",
-				(unsigned long long)bio->bi_sector,
+				(unsigned long long)bio->bi_iter.bi_sector,
 				bdevname(bio->bi_bdev, b),
 				count);
 		}
@@ -2007,7 +2022,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
 		if ((bio->bi_rw & ff) != ff)
 			break;
-		bytes += bio->bi_size;
+		bytes += bio->bi_iter.bi_size;
 	}
 
 	/* this could lead to infinite loop */
@@ -2378,9 +2393,9 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	total_bytes = 0;
 	while (req->bio) {
 		struct bio *bio = req->bio;
-		unsigned bio_bytes = min(bio->bi_size, nr_bytes);
+		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_size)
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
 
 		req_bio_endio(req, bio, bio_bytes, error);
@@ -2728,7 +2743,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
 		rq->buffer = bio_data(bio);
 	}
-	rq->__data_len = bio->bi_size;
+	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
 
 	if (bio->bi_bdev)
@@ -2746,10 +2761,10 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 void rq_flush_dcache_pages(struct request *rq)
 {
 	struct req_iterator iter;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 
 	rq_for_each_segment(bvec, rq, iter)
-		flush_dcache_page(bvec->bv_page);
+		flush_dcache_page(bvec.bv_page);
 }
 EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
 #endif

block/blk-exec.c

@@ -60,6 +60,10 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 
+	/*
+	 * don't check dying flag for MQ because the request won't
+	 * be resued after dying flag is set
+	 */
 	if (q->mq_ops) {
 		blk_mq_insert_request(q, rq, true);
 		return;

block/blk-flush.c

@@ -548,7 +548,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 	 * copied from blk_rq_pos(rq).
 	 */
 	if (error_sector)
-		*error_sector = bio->bi_sector;
+		*error_sector = bio->bi_iter.bi_sector;
 
 	bio_put(bio);
 	return ret;

block/blk-integrity.c

@@ -43,30 +43,32 @@ static const char *bi_unsupported_name = "unsupported";
  */
 int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio)
 {
-	struct bio_vec *iv, *ivprv = NULL;
+	struct bio_vec iv, ivprv = { NULL };
 	unsigned int segments = 0;
 	unsigned int seg_size = 0;
-	unsigned int i = 0;
+	struct bvec_iter iter;
+	int prev = 0;
 
-	bio_for_each_integrity_vec(iv, bio, i) {
+	bio_for_each_integrity_vec(iv, bio, iter) {
 
-		if (ivprv) {
-			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+		if (prev) {
+			if (!BIOVEC_PHYS_MERGEABLE(&ivprv, &iv))
 				goto new_segment;
 
-			if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv))
+			if (!BIOVEC_SEG_BOUNDARY(q, &ivprv, &iv))
 				goto new_segment;
 
-			if (seg_size + iv->bv_len > queue_max_segment_size(q))
+			if (seg_size + iv.bv_len > queue_max_segment_size(q))
 				goto new_segment;
 
-			seg_size += iv->bv_len;
+			seg_size += iv.bv_len;
 		} else {
 new_segment:
 			segments++;
-			seg_size = iv->bv_len;
+			seg_size = iv.bv_len;
 		}
 
+		prev = 1;
 		ivprv = iv;
 	}
 
@@ -87,24 +89,25 @@ EXPORT_SYMBOL(blk_rq_count_integrity_sg);
 int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio,
 			    struct scatterlist *sglist)
 {
-	struct bio_vec *iv, *ivprv = NULL;
+	struct bio_vec iv, ivprv = { NULL };
 	struct scatterlist *sg = NULL;
 	unsigned int segments = 0;
-	unsigned int i = 0;
+	struct bvec_iter iter;
+	int prev = 0;
 
-	bio_for_each_integrity_vec(iv, bio, i) {
+	bio_for_each_integrity_vec(iv, bio, iter) {
 
-		if (ivprv) {
-			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+		if (prev) {
+			if (!BIOVEC_PHYS_MERGEABLE(&ivprv, &iv))
 				goto new_segment;
 
-			if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv))
+			if (!BIOVEC_SEG_BOUNDARY(q, &ivprv, &iv))
 				goto new_segment;
 
-			if (sg->length + iv->bv_len > queue_max_segment_size(q))
+			if (sg->length + iv.bv_len > queue_max_segment_size(q))
 				goto new_segment;
 
-			sg->length += iv->bv_len;
+			sg->length += iv.bv_len;
 		} else {
 new_segment:
 			if (!sg)
@@ -114,10 +117,11 @@ new_segment:
 				sg = sg_next(sg);
 			}
 
-			sg_set_page(sg, iv->bv_page, iv->bv_len, iv->bv_offset);
+			sg_set_page(sg, iv.bv_page, iv.bv_len, iv.bv_offset);
 			segments++;
 		}
 
+		prev = 1;
 		ivprv = iv;
 	}
 

block/blk-lib.c

@@ -108,12 +108,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
-		bio->bi_sector = sector;
+		bio->bi_iter.bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
 		bio->bi_private = &bb;
 
-		bio->bi_size = req_sects << 9;
+		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
 		sector = end_sect;
 
@@ -174,7 +174,7 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 			break;
 		}
 
-		bio->bi_sector = sector;
+		bio->bi_iter.bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
 		bio->bi_private = &bb;
@@ -184,11 +184,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
 
 		if (nr_sects > max_write_same_sectors) {
-			bio->bi_size = max_write_same_sectors << 9;
+			bio->bi_iter.bi_size = max_write_same_sectors << 9;
 			nr_sects -= max_write_same_sectors;
 			sector += max_write_same_sectors;
 		} else {
-			bio->bi_size = nr_sects << 9;
+			bio->bi_iter.bi_size = nr_sects << 9;
 			nr_sects = 0;
 		}
 
@@ -240,7 +240,7 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			break;
 		}
 
-		bio->bi_sector = sector;
+		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev   = bdev;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_private = &bb;

block/blk-map.c

@@ -20,7 +20,7 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
 
-		rq->__data_len += bio->bi_size;
+		rq->__data_len += bio->bi_iter.bi_size;
 	}
 	return 0;
 }
@@ -76,7 +76,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
 
 	ret = blk_rq_append_bio(q, rq, bio);
 	if (!ret)
-		return bio->bi_size;
+		return bio->bi_iter.bi_size;
 
 	/* if it was boucned we must call the end io function */
 	bio_endio(bio, 0);
@@ -220,7 +220,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (bio->bi_size != len) {
+	if (bio->bi_iter.bi_size != len) {
 		/*
 		 * Grab an extra reference to this bio, as bio_unmap_user()
 		 * expects to be able to drop it twice as it happens on the

block/blk-merge.c

@@ -12,10 +12,11 @@
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
-	struct bio_vec *bv, *bvprv = NULL;
-	int cluster, i, high, highprv = 1;
+	struct bio_vec bv, bvprv = { NULL };
+	int cluster, high, highprv = 1;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
+	struct bvec_iter iter;
 
 	if (!bio)
 		return 0;
@@ -25,25 +26,23 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
-		bio_for_each_segment(bv, bio, i) {
+		bio_for_each_segment(bv, bio, iter) {
 			/*
 			 * the trick here is making sure that a high page is
 			 * never considered part of another segment, since that
 			 * might change with the bounce page.
 			 */
-			high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q);
-			if (high || highprv)
-				goto new_segment;
-			if (cluster) {
-				if (seg_size + bv->bv_len
+			high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q);
+			if (!high && !highprv && cluster) {
+				if (seg_size + bv.bv_len
 				    > queue_max_segment_size(q))
 					goto new_segment;
-				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
+				if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
 					goto new_segment;
-				if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
+				if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
 					goto new_segment;
 
-				seg_size += bv->bv_len;
+				seg_size += bv.bv_len;
 				bvprv = bv;
 				continue;
 			}
@@ -54,7 +53,7 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
-			seg_size = bv->bv_len;
+			seg_size = bv.bv_len;
 			highprv = high;
 		}
 		bbio = bio;
@@ -87,6 +86,9 @@ EXPORT_SYMBOL(blk_recount_segments);
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
+	struct bio_vec end_bv = { NULL }, nxt_bv;
+	struct bvec_iter iter;
+
 	if (!blk_queue_cluster(q))
 		return 0;
 
@@ -97,34 +99,40 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	if (!bio_has_data(bio))
 		return 1;
 
-	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
+	bio_for_each_segment(end_bv, bio, iter)
+		if (end_bv.bv_len == iter.bi_size)
+			break;
+
+	nxt_bv = bio_iovec(nxt);
+
+	if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv))
 		return 0;
 
 	/*
 	 * bio and nxt are contiguous in memory; check if the queue allows
 	 * these two to be merged into one
 	 */
-	if (BIO_SEG_BOUNDARY(q, bio, nxt))
+	if (BIOVEC_SEG_BOUNDARY(q, &end_bv, &nxt_bv))
 		return 1;
 
 	return 0;
 }
 
-static void
+static inline void
 __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
-		     struct scatterlist *sglist, struct bio_vec **bvprv,
+		     struct scatterlist *sglist, struct bio_vec *bvprv,
 		     struct scatterlist **sg, int *nsegs, int *cluster)
 {
 
 	int nbytes = bvec->bv_len;
 
-	if (*bvprv && *cluster) {
+	if (*sg && *cluster) {
 		if ((*sg)->length + nbytes > queue_max_segment_size(q))
 			goto new_segment;
 
-		if (!BIOVEC_PHYS_MERGEABLE(*bvprv, bvec))
+		if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
 			goto new_segment;
-		if (!BIOVEC_SEG_BOUNDARY(q, *bvprv, bvec))
+		if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
 			goto new_segment;
 
 		(*sg)->length += nbytes;
@@ -150,7 +158,7 @@ new_segment:
 		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
 		(*nsegs)++;
 	}
-	*bvprv = bvec;
+	*bvprv = *bvec;
 }
 
 /*
@@ -160,7 +168,7 @@ new_segment:
 int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		  struct scatterlist *sglist)
 {
-	struct bio_vec *bvec, *bvprv;
+	struct bio_vec bvec, bvprv = { NULL };
 	struct req_iterator iter;
 	struct scatterlist *sg;
 	int nsegs, cluster;
@@ -171,10 +179,9 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	/*
 	 * for each bio in rq
 	 */
-	bvprv = NULL;
 	sg = NULL;
 	rq_for_each_segment(bvec, rq, iter) {
-		__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+		__blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
 				     &nsegs, &cluster);
 	} /* segments in rq */
 
@@ -223,18 +230,17 @@ EXPORT_SYMBOL(blk_rq_map_sg);
 int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
 		   struct scatterlist *sglist)
 {
-	struct bio_vec *bvec, *bvprv;
+	struct bio_vec bvec, bvprv = { NULL };
 	struct scatterlist *sg;
 	int nsegs, cluster;
-	unsigned long i;
+	struct bvec_iter iter;
 
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	bvprv = NULL;
 	sg = NULL;
-	bio_for_each_segment(bvec, bio, i) {
-		__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+	bio_for_each_segment(bvec, bio, iter) {
+		__blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg,
 				     &nsegs, &cluster);
 	} /* segments in bio */
 
@@ -543,9 +549,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 
 int blk_try_merge(struct request *rq, struct bio *bio)
 {
-	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_sector)
+	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
 		return ELEVATOR_BACK_MERGE;
-	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_sector)
+	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
 		return ELEVATOR_FRONT_MERGE;
 	return ELEVATOR_NO_MERGE;
 }

block/blk-mq-cpu.c

@@ -28,36 +28,6 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static void blk_mq_cpu_notify(void *data, unsigned long action,
-			      unsigned int cpu)
-{
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		/*
-		 * If the CPU goes away, ensure that we run any pending
-		 * completions.
-		 */
-		struct llist_node *node;
-		struct request *rq;
-
-		local_irq_disable();
-
-		node = llist_del_all(&per_cpu(ipi_lists, cpu));
-		while (node) {
-			struct llist_node *next = node->next;
-
-			rq = llist_entry(node, struct request, ll_list);
-			__blk_mq_end_io(rq, rq->errors);
-			node = next;
-		}
-
-		local_irq_enable();
-	}
-}
-
-static struct notifier_block __cpuinitdata blk_mq_main_cpu_notifier = {
-	.notifier_call	= blk_mq_main_cpu_notify,
-};
-
 void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
 	BUG_ON(!notifier->notify);
@@ -82,12 +52,7 @@ void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
 	notifier->data = data;
 }
 
-static struct blk_mq_cpu_notifier __cpuinitdata cpu_notifier = {
-	.notify = blk_mq_cpu_notify,
-};
-
 void __init blk_mq_cpu_init(void)
 {
-	register_hotcpu_notifier(&blk_mq_main_cpu_notifier);
-	blk_mq_register_cpu_notifier(&cpu_notifier);
+	hotcpu_notifier(blk_mq_main_cpu_notify, 0);
 }

block/blk-mq.c

@@ -27,8 +27,6 @@ static LIST_HEAD(all_q_list);
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx);
 
-DEFINE_PER_CPU(struct llist_head, ipi_lists);
-
 static struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
@@ -106,10 +104,13 @@ static int blk_mq_queue_enter(struct request_queue *q)
 
 	spin_lock_irq(q->queue_lock);
 	ret = wait_event_interruptible_lock_irq(q->mq_freeze_wq,
-		!blk_queue_bypass(q), *q->queue_lock);
+		!blk_queue_bypass(q) || blk_queue_dying(q),
+		*q->queue_lock);
 	/* inc usage with lock hold to avoid freeze_queue runs here */
-	if (!ret)
+	if (!ret && !blk_queue_dying(q))
 		__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
+	else if (blk_queue_dying(q))
+		ret = -ENODEV;
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -120,6 +121,22 @@ static void blk_mq_queue_exit(struct request_queue *q)
 	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
 }
 
+static void __blk_mq_drain_queue(struct request_queue *q)
+{
+	while (true) {
+		s64 count;
+
+		spin_lock_irq(q->queue_lock);
+		count = percpu_counter_sum(&q->mq_usage_counter);
+		spin_unlock_irq(q->queue_lock);
+
+		if (count == 0)
+			break;
+		blk_mq_run_queues(q, false);
+		msleep(10);
+	}
+}
+
 /*
  * Guarantee no request is in use, so we can change any data structure of
  * the queue afterward.
@@ -133,21 +150,13 @@ static void blk_mq_freeze_queue(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_BYPASS, q);
 	spin_unlock_irq(q->queue_lock);
 
-	if (!drain)
-		return;
-
-	while (true) {
-		s64 count;
-
-		spin_lock_irq(q->queue_lock);
-		count = percpu_counter_sum(&q->mq_usage_counter);
-		spin_unlock_irq(q->queue_lock);
+	if (drain)
+		__blk_mq_drain_queue(q);
+}
 
-		if (count == 0)
-			break;
-		blk_mq_run_queues(q, false);
-		msleep(10);
-	}
+void blk_mq_drain_queue(struct request_queue *q)
+{
+	__blk_mq_drain_queue(q);
 }
 
 static void blk_mq_unfreeze_queue(struct request_queue *q)
@@ -179,6 +188,8 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 
 	rq->mq_ctx = ctx;
 	rq->cmd_flags = rw_flags;
+	rq->start_time = jiffies;
+	set_start_time_ns(rq);
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
 }
 
@@ -305,7 +316,7 @@ void blk_mq_complete_request(struct request *rq, int error)
 		struct bio *next = bio->bi_next;
 
 		bio->bi_next = NULL;
-		bytes += bio->bi_size;
+		bytes += bio->bi_iter.bi_size;
 		blk_mq_bio_endio(rq, bio, error);
 		bio = next;
 	}
@@ -326,55 +337,12 @@ void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_complete_request(rq, error);
 }
 
-#if defined(CONFIG_SMP)
-
-/*
- * Called with interrupts disabled.
- */
-static void ipi_end_io(void *data)
-{
-	struct llist_head *list = &per_cpu(ipi_lists, smp_processor_id());
-	struct llist_node *entry, *next;
-	struct request *rq;
-
-	entry = llist_del_all(list);
-
-	while (entry) {
-		next = entry->next;
-		rq = llist_entry(entry, struct request, ll_list);
-		__blk_mq_end_io(rq, rq->errors);
-		entry = next;
-	}
-}
-
-static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
-			  struct request *rq, const int error)
+static void blk_mq_end_io_remote(void *data)
 {
-	struct call_single_data *data = &rq->csd;
-
-	rq->errors = error;
-	rq->ll_list.next = NULL;
+	struct request *rq = data;
 
-	/*
-	 * If the list is non-empty, an existing IPI must already
-	 * be "in flight". If that is the case, we need not schedule
-	 * a new one.
-	 */
-	if (llist_add(&rq->ll_list, &per_cpu(ipi_lists, ctx->cpu))) {
-		data->func = ipi_end_io;
-		data->flags = 0;
-		__smp_call_function_single(ctx->cpu, data, 0);
-	}
-
-	return true;
-}
-#else /* CONFIG_SMP */
-static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu,
-			  struct request *rq, const int error)
-{
-	return false;
+	__blk_mq_end_io(rq, rq->errors);
 }
-#endif
 
 /*
  * End IO on this request on a multiqueue enabled driver. We'll either do
@@ -390,11 +358,15 @@ void blk_mq_end_io(struct request *rq, int error)
 		return __blk_mq_end_io(rq, error);
 
 	cpu = get_cpu();
-
-	if (cpu == ctx->cpu || !cpu_online(ctx->cpu) ||
-	    !ipi_remote_cpu(ctx, cpu, rq, error))
+	if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
+		rq->errors = error;
+		rq->csd.func = blk_mq_end_io_remote;
+		rq->csd.info = rq;
+		rq->csd.flags = 0;
+		__smp_call_function_single(ctx->cpu, &rq->csd, 0);
+	} else {
 		__blk_mq_end_io(rq, error);
-
+	}
 	put_cpu();
 }
 EXPORT_SYMBOL(blk_mq_end_io);
@@ -1091,8 +1063,8 @@ static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx)
 	struct page *page;
 
 	while (!list_empty(&hctx->page_list)) {
-		page = list_first_entry(&hctx->page_list, struct page, list);
-		list_del_init(&page->list);
+		page = list_first_entry(&hctx->page_list, struct page, lru);
+		list_del_init(&page->lru);
 		__free_pages(page, page->private);
 	}
 
@@ -1156,7 +1128,7 @@ static int blk_mq_init_rq_map(struct blk_mq_hw_ctx *hctx,
 			break;
 
 		page->private = this_order;
-		list_add_tail(&page->list, &hctx->page_list);
+		list_add_tail(&page->lru, &hctx->page_list);
 
 		p = page_address(page);
 		entries_per_page = order_to_size(this_order) / rq_size;
@@ -1429,7 +1401,6 @@ void blk_mq_free_queue(struct request_queue *q)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		cancel_delayed_work_sync(&hctx->delayed_work);
 		kfree(hctx->ctx_map);
 		kfree(hctx->ctxs);
 		blk_mq_free_rq_map(hctx);
@@ -1451,7 +1422,6 @@ void blk_mq_free_queue(struct request_queue *q)
 	list_del_init(&q->all_q_node);
 	mutex_unlock(&all_q_mutex);
 }
-EXPORT_SYMBOL(blk_mq_free_queue);
 
 /* Basically redo blk_mq_init_queue with queue frozen */
 static void blk_mq_queue_reinit(struct request_queue *q)
@@ -1495,11 +1465,6 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 
 static int __init blk_mq_init(void)
 {
-	unsigned int i;
-
-	for_each_possible_cpu(i)
-		init_llist_head(&per_cpu(ipi_lists, i));
-
 	blk_mq_cpu_init();
 
 	/* Must be called after percpu_counter_hotcpu_callback() */

block/blk-mq.h

@@ -27,6 +27,8 @@ void blk_mq_complete_request(struct request *rq, int error);
 void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_init_flush(struct request_queue *q);
+void blk_mq_drain_queue(struct request_queue *q);
+void blk_mq_free_queue(struct request_queue *q);
 
 /*
  * CPU hotplug helpers
@@ -38,7 +40,6 @@ void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
 void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
 void blk_mq_cpu_init(void);
-DECLARE_PER_CPU(struct llist_head, ipi_lists);
 
 /*
  * CPU -> queue mappings

block/blk-sysfs.c

@@ -11,6 +11,7 @@
 
 #include "blk.h"
 #include "blk-cgroup.h"
+#include "blk-mq.h"
 
 struct queue_sysfs_entry {
 	struct attribute attr;

block/blk-throttle.c

@@ -877,14 +877,14 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
-	if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) {
+	if (tg->bytes_disp[rw] + bio->bi_iter.bi_size <= bytes_allowed) {
 		if (wait)
 			*wait = 0;
 		return 1;
 	}
 
 	/* Calc approx time to dispatch */
-	extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed;
+	extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
 	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
 
 	if (!jiffy_wait)
@@ -987,7 +987,7 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	bool rw = bio_data_dir(bio);
 
 	/* Charge the bio to the group */
-	tg->bytes_disp[rw] += bio->bi_size;
+	tg->bytes_disp[rw] += bio->bi_iter.bi_size;
 	tg->io_disp[rw]++;
 
 	/*
@@ -1003,8 +1003,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	 */
 	if (!(bio->bi_rw & REQ_THROTTLED)) {
 		bio->bi_rw |= REQ_THROTTLED;
-		throtl_update_dispatch_stats(tg_to_blkg(tg), bio->bi_size,
-					     bio->bi_rw);
+		throtl_update_dispatch_stats(tg_to_blkg(tg),
+					     bio->bi_iter.bi_size, bio->bi_rw);
 	}
 }
 
@@ -1503,7 +1503,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 	if (tg) {
 		if (!tg->has_rules[rw]) {
 			throtl_update_dispatch_stats(tg_to_blkg(tg),
-						     bio->bi_size, bio->bi_rw);
+					bio->bi_iter.bi_size, bio->bi_rw);
 			goto out_unlock_rcu;
 		}
 	}
@@ -1559,7 +1559,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 	/* out-of-limit, queue to @tg */
 	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
 		   rw == READ ? 'R' : 'W',
-		   tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
+		   tg->bytes_disp[rw], bio->bi_iter.bi_size, tg->bps[rw],
 		   tg->io_disp[rw], tg->iops[rw],
 		   sq->nr_queued[READ], sq->nr_queued[WRITE]);
 

block/cmdline-parser.c

@@ -4,8 +4,7 @@
  * Written by Cai Zhiyong <caizhiyong@huawei.com>
  *
  */
-#include <linux/buffer_head.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/cmdline-parser.h>
 
 static int parse_subpart(struct cmdline_subpart **subpart, char *partdef)
@@ -159,6 +158,7 @@ void cmdline_parts_free(struct cmdline_parts **parts)
 		*parts = next_parts;
 	}
 }
+EXPORT_SYMBOL(cmdline_parts_free);
 
 int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline)
 {
@@ -206,6 +206,7 @@ fail:
 	cmdline_parts_free(parts);
 	goto done;
 }
+EXPORT_SYMBOL(cmdline_parts_parse);
 
 struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts,
 					 const char *bdev)
@@ -214,17 +215,17 @@ struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts,
 		parts = parts->next_parts;
 	return parts;
 }
+EXPORT_SYMBOL(cmdline_parts_find);
 
 /*
  *  add_part()
  *    0 success.
  *    1 can not add so many partitions.
  */
-void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
-		       int slot,
-		       int (*add_part)(int, struct cmdline_subpart *, void *),
-		       void *param)
-
+int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
+		      int slot,
+		      int (*add_part)(int, struct cmdline_subpart *, void *),
+		      void *param)
 {
 	sector_t from = 0;
 	struct cmdline_subpart *subpart;
@@ -247,4 +248,7 @@ void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
 		if (add_part(slot, subpart, param))
 			break;
 	}
+
+	return slot;
 }
+EXPORT_SYMBOL(cmdline_parts_set);

block/elevator.c

@@ -440,7 +440,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	/*
 	 * See if our hash lookup can find a potential backmerge.
 	 */
-	__rq = elv_rqhash_find(q, bio->bi_sector);
+	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
 	if (__rq && elv_rq_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_BACK_MERGE;

block/scsi_ioctl.c

@@ -323,12 +323,14 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 
 	if (hdr->iovec_count) {
 		size_t iov_data_len;
-		struct iovec *iov;
+		struct iovec *iov = NULL;
 
 		ret = rw_copy_check_uvector(-1, hdr->dxferp, hdr->iovec_count,
 					    0, NULL, &iov);
-		if (ret < 0)
+		if (ret < 0) {
+			kfree(iov);
 			goto out;
+		}
 
 		iov_data_len = ret;
 		ret = 0;

drivers/block/aoe/aoe.h

@@ -100,11 +100,8 @@ enum {
 
 struct buf {
 	ulong nframesout;
-	ulong resid;
-	ulong bv_resid;
-	sector_t sector;
 	struct bio *bio;
-	struct bio_vec *bv;
+	struct bvec_iter iter;
 	struct request *rq;
 };
 
@@ -120,13 +117,10 @@ struct frame {
 	ulong waited;
 	ulong waited_total;
 	struct aoetgt *t;		/* parent target I belong to */
-	sector_t lba;
 	struct sk_buff *skb;		/* command skb freed on module exit */
 	struct sk_buff *r_skb;		/* response skb for async processing */
 	struct buf *buf;
-	struct bio_vec *bv;
-	ulong bcnt;
-	ulong bv_off;
+	struct bvec_iter iter;
 	char flags;
 };
 

drivers/block/aoe/aoecmd.c

@@ -196,8 +196,7 @@ aoe_freetframe(struct frame *f)
 
 	t = f->t;
 	f->buf = NULL;
-	f->lba = 0;
-	f->bv = NULL;
+	memset(&f->iter, 0, sizeof(f->iter));
 	f->r_skb = NULL;
 	f->flags = 0;
 	list_add(&f->head, &t->ffree);
@@ -295,21 +294,14 @@ newframe(struct aoedev *d)
 }
 
 static void
-skb_fillup(struct sk_buff *skb, struct bio_vec *bv, ulong off, ulong cnt)
+skb_fillup(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter)
 {
 	int frag = 0;
-	ulong fcnt;
-loop:
-	fcnt = bv->bv_len - (off - bv->bv_offset);
-	if (fcnt > cnt)
-		fcnt = cnt;
-	skb_fill_page_desc(skb, frag++, bv->bv_page, off, fcnt);
-	cnt -= fcnt;
-	if (cnt <= 0)
-		return;
-	bv++;
-	off = bv->bv_offset;
-	goto loop;
+	struct bio_vec bv;
+
+	__bio_for_each_segment(bv, bio, iter, iter)
+		skb_fill_page_desc(skb, frag++, bv.bv_page,
+				   bv.bv_offset, bv.bv_len);
 }
 
 static void
@@ -346,12 +338,10 @@ ata_rw_frameinit(struct frame *f)
 	t->nout++;
 	f->waited = 0;
 	f->waited_total = 0;
-	if (f->buf)
-		f->lba = f->buf->sector;
 
 	/* set up ata header */
-	ah->scnt = f->bcnt >> 9;
-	put_lba(ah, f->lba);
+	ah->scnt = f->iter.bi_size >> 9;
+	put_lba(ah, f->iter.bi_sector);
 	if (t->d->flags & DEVFL_EXT) {
 		ah->aflags |= AOEAFL_EXT;
 	} else {
@@ -360,11 +350,11 @@ ata_rw_frameinit(struct frame *f)
 		ah->lba3 |= 0xe0;	/* LBA bit + obsolete 0xa0 */
 	}
 	if (f->buf && bio_data_dir(f->buf->bio) == WRITE) {
-		skb_fillup(skb, f->bv, f->bv_off, f->bcnt);
+		skb_fillup(skb, f->buf->bio, f->iter);
 		ah->aflags |= AOEAFL_WRITE;
-		skb->len += f->bcnt;
-		skb->data_len = f->bcnt;
-		skb->truesize += f->bcnt;
+		skb->len += f->iter.bi_size;
+		skb->data_len = f->iter.bi_size;
+		skb->truesize += f->iter.bi_size;
 		t->wpkts++;
 	} else {
 		t->rpkts++;
@@ -382,7 +372,6 @@ aoecmd_ata_rw(struct aoedev *d)
 	struct buf *buf;
 	struct sk_buff *skb;
 	struct sk_buff_head queue;
-	ulong bcnt, fbcnt;
 
 	buf = nextbuf(d);
 	if (buf == NULL)
@@ -390,39 +379,22 @@ aoecmd_ata_rw(struct aoedev *d)
 	f = newframe(d);
 	if (f == NULL)
 		return 0;
-	bcnt = d->maxbcnt;
-	if (bcnt == 0)
-		bcnt = DEFAULTBCNT;
-	if (bcnt > buf->resid)
-		bcnt = buf->resid;
-	fbcnt = bcnt;
-	f->bv = buf->bv;
-	f->bv_off = f->bv->bv_offset + (f->bv->bv_len - buf->bv_resid);
-	do {
-		if (fbcnt < buf->bv_resid) {
-			buf->bv_resid -= fbcnt;
-			buf->resid -= fbcnt;
-			break;
-		}
-		fbcnt -= buf->bv_resid;
-		buf->resid -= buf->bv_resid;
-		if (buf->resid == 0) {
-			d->ip.buf = NULL;
-			break;
-		}
-		buf->bv++;
-		buf->bv_resid = buf->bv->bv_len;
-		WARN_ON(buf->bv_resid == 0);
-	} while (fbcnt);
 
 	/* initialize the headers & frame */
 	f->buf = buf;
-	f->bcnt = bcnt;
-	ata_rw_frameinit(f);
+	f->iter = buf->iter;
+	f->iter.bi_size = min_t(unsigned long,
+				d->maxbcnt ?: DEFAULTBCNT,
+				f->iter.bi_size);
+	bio_advance_iter(buf->bio, &buf->iter, f->iter.bi_size);
+
+	if (!buf->iter.bi_size)
+		d->ip.buf = NULL;
 
 	/* mark all tracking fields and load out */
 	buf->nframesout += 1;
-	buf->sector += bcnt >> 9;
+
+	ata_rw_frameinit(f);
 
 	skb = skb_clone(f->skb, GFP_ATOMIC);
 	if (skb) {
@@ -613,10 +585,7 @@ reassign_frame(struct frame *f)
 	skb = nf->skb;
 	nf->skb = f->skb;
 	nf->buf = f->buf;
-	nf->bcnt = f->bcnt;
-	nf->lba = f->lba;
-	nf->bv = f->bv;
-	nf->bv_off = f->bv_off;
+	nf->iter = f->iter;
 	nf->waited = 0;
 	nf->waited_total = f->waited_total;
 	nf->sent = f->sent;
@@ -648,19 +617,19 @@ probe(struct aoetgt *t)
 	}
 	f->flags |= FFL_PROBE;
 	ifrotate(t);
-	f->bcnt = t->d->maxbcnt ? t->d->maxbcnt : DEFAULTBCNT;
+	f->iter.bi_size = t->d->maxbcnt ? t->d->maxbcnt : DEFAULTBCNT;
 	ata_rw_frameinit(f);
 	skb = f->skb;
-	for (frag = 0, n = f->bcnt; n > 0; ++frag, n -= m) {
+	for (frag = 0, n = f->iter.bi_size; n > 0; ++frag, n -= m) {
 		if (n < PAGE_SIZE)
 			m = n;
 		else
 			m = PAGE_SIZE;
 		skb_fill_page_desc(skb, frag, empty_page, 0, m);
 	}
-	skb->len += f->bcnt;
-	skb->data_len = f->bcnt;
-	skb->truesize += f->bcnt;
+	skb->len += f->iter.bi_size;
+	skb->data_len = f->iter.bi_size;
+	skb->truesize += f->iter.bi_size;
 
 	skb = skb_clone(f->skb, GFP_ATOMIC);
 	if (skb) {
@@ -897,15 +866,15 @@ rqbiocnt(struct request *r)
 static void
 bio_pageinc(struct bio *bio)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	struct page *page;
-	int i;
+	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, i) {
+	bio_for_each_segment(bv, bio, iter) {
 		/* Non-zero page count for non-head members of
 		 * compound pages is no longer allowed by the kernel.
 		 */
-		page = compound_trans_head(bv->bv_page);
+		page = compound_trans_head(bv.bv_page);
 		atomic_inc(&page->_count);
 	}
 }
@@ -913,12 +882,12 @@ bio_pageinc(struct bio *bio)
 static void
 bio_pagedec(struct bio *bio)
 {
-	struct bio_vec *bv;
 	struct page *page;
-	int i;
+	struct bio_vec bv;
+	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, i) {
-		page = compound_trans_head(bv->bv_page);
+	bio_for_each_segment(bv, bio, iter) {
+		page = compound_trans_head(bv.bv_page);
 		atomic_dec(&page->_count);
 	}
 }
@@ -929,12 +898,8 @@ bufinit(struct buf *buf, struct request *rq, struct bio *bio)
 	memset(buf, 0, sizeof(*buf));
 	buf->rq = rq;
 	buf->bio = bio;
-	buf->resid = bio->bi_size;
-	buf->sector = bio->bi_sector;
+	buf->iter = bio->bi_iter;
 	bio_pageinc(bio);
-	buf->bv = bio_iovec(bio);
-	buf->bv_resid = buf->bv->bv_len;
-	WARN_ON(buf->bv_resid == 0);
 }
 
 static struct buf *
@@ -1119,24 +1084,18 @@ gettgt(struct aoedev *d, char *addr)
 }
 
 static void
-bvcpy(struct bio_vec *bv, ulong off, struct sk_buff *skb, long cnt)
+bvcpy(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter, long cnt)
 {
-	ulong fcnt;
-	char *p;
 	int soff = 0;
-loop:
-	fcnt = bv->bv_len - (off - bv->bv_offset);
-	if (fcnt > cnt)
-		fcnt = cnt;
-	p = page_address(bv->bv_page) + off;
-	skb_copy_bits(skb, soff, p, fcnt);
-	soff += fcnt;
-	cnt -= fcnt;
-	if (cnt <= 0)
-		return;
-	bv++;
-	off = bv->bv_offset;
-	goto loop;
+	struct bio_vec bv;
+
+	iter.bi_size = cnt;
+
+	__bio_for_each_segment(bv, bio, iter, iter) {
+		char *p = page_address(bv.bv_page) + bv.bv_offset;
+		skb_copy_bits(skb, soff, p, bv.bv_len);
+		soff += bv.bv_len;
+	}
 }
 
 void
@@ -1152,7 +1111,7 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
 	do {
 		bio = rq->bio;
 		bok = !fastfail && test_bit(BIO_UPTODATE, &bio->bi_flags);
-	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_size));
+	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size));
 
 	/* cf. http://lkml.org/lkml/2006/10/31/28 */
 	if (!fastfail)
@@ -1229,7 +1188,15 @@ noskb:		if (buf)
 			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
 			break;
 		}
-		bvcpy(f->bv, f->bv_off, skb, n);
+		if (n > f->iter.bi_size) {
+			pr_err_ratelimited("%s e%ld.%d.  bytes=%ld need=%u\n",
+				"aoe: too-large data size in read from",
+				(long) d->aoemajor, d->aoeminor,
+				n, f->iter.bi_size);
+			clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
+			break;
+		}
+		bvcpy(skb, f->buf->bio, f->iter, n);
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
@@ -1272,7 +1239,7 @@ out:
 
 	aoe_freetframe(f);
 
-	if (buf && --buf->nframesout == 0 && buf->resid == 0)
+	if (buf && --buf->nframesout == 0 && buf->iter.bi_size == 0)
 		aoe_end_buf(d, buf);
 
 	spin_unlock_irq(&d->lock);
@@ -1727,7 +1694,7 @@ aoe_failbuf(struct aoedev *d, struct buf *buf)
 {
 	if (buf == NULL)
 		return;
-	buf->resid = 0;
+	buf->iter.bi_size = 0;
 	clear_bit(BIO_UPTODATE, &buf->bio->bi_flags);
 	if (buf->nframesout == 0)
 		aoe_end_buf(d, buf);

drivers/block/brd.c

@@ -328,18 +328,18 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 	struct block_device *bdev = bio->bi_bdev;
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int rw;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	sector_t sector;
-	int i;
+	struct bvec_iter iter;
 	int err = -EIO;
 
-	sector = bio->bi_sector;
+	sector = bio->bi_iter.bi_sector;
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
 		goto out;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		err = 0;
-		discard_from_brd(brd, sector, bio->bi_size);
+		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
 		goto out;
 	}
 
@@ -347,10 +347,10 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 	if (rw == READA)
 		rw = READ;
 
-	bio_for_each_segment(bvec, bio, i) {
-		unsigned int len = bvec->bv_len;
-		err = brd_do_bvec(brd, bvec->bv_page, len,
-					bvec->bv_offset, rw, sector);
+	bio_for_each_segment(bvec, bio, iter) {
+		unsigned int len = bvec.bv_len;
+		err = brd_do_bvec(brd, bvec.bv_page, len,
+					bvec.bv_offset, rw, sector);
 		if (err)
 			break;
 		sector += len >> SECTOR_SHIFT;

drivers/block/drbd/drbd_actlog.c

@@ -159,7 +159,7 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 
 	bio = bio_alloc_drbd(GFP_NOIO);
 	bio->bi_bdev = bdev->md_bdev;
-	bio->bi_sector = sector;
+	bio->bi_iter.bi_sector = sector;
 	err = -EIO;
 	if (bio_add_page(bio, page, size, 0) != size)
 		goto out;

drivers/block/drbd/drbd_bitmap.c

@@ -1028,7 +1028,7 @@ static void bm_page_io_async(struct bm_aio_ctx *ctx, int page_nr, int rw) __must
 	} else
 		page = b->bm_pages[page_nr];
 	bio->bi_bdev = mdev->ldev->md_bdev;
-	bio->bi_sector = on_disk_sector;
+	bio->bi_iter.bi_sector = on_disk_sector;
 	/* bio_add_page of a single page to an empty bio will always succeed,
 	 * according to api.  Do we want to assert that? */
 	bio_add_page(bio, page, len, 0);

drivers/block/drbd/drbd_main.c

@@ -1537,15 +1537,17 @@ static int _drbd_send_page(struct drbd_conf *mdev, struct page *page,
 
 static int _drbd_send_bio(struct drbd_conf *mdev, struct bio *bio)
 {
-	struct bio_vec *bvec;
-	int i;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+
 	/* hint all but last page with MSG_MORE */
-	bio_for_each_segment(bvec, bio, i) {
+	bio_for_each_segment(bvec, bio, iter) {
 		int err;
 
-		err = _drbd_no_send_page(mdev, bvec->bv_page,
-					 bvec->bv_offset, bvec->bv_len,
-					 i == bio->bi_vcnt - 1 ? 0 : MSG_MORE);
+		err = _drbd_no_send_page(mdev, bvec.bv_page,
+					 bvec.bv_offset, bvec.bv_len,
+					 bio_iter_last(bvec, iter)
+					 ? 0 : MSG_MORE);
 		if (err)
 			return err;
 	}
@@ -1554,15 +1556,16 @@ static int _drbd_send_bio(struct drbd_conf *mdev, struct bio *bio)
 
 static int _drbd_send_zc_bio(struct drbd_conf *mdev, struct bio *bio)
 {
-	struct bio_vec *bvec;
-	int i;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+
 	/* hint all but last page with MSG_MORE */
-	bio_for_each_segment(bvec, bio, i) {
+	bio_for_each_segment(bvec, bio, iter) {
 		int err;
 
-		err = _drbd_send_page(mdev, bvec->bv_page,
-				      bvec->bv_offset, bvec->bv_len,
-				      i == bio->bi_vcnt - 1 ? 0 : MSG_MORE);
+		err = _drbd_send_page(mdev, bvec.bv_page,
+				      bvec.bv_offset, bvec.bv_len,
+				      bio_iter_last(bvec, iter) ? 0 : MSG_MORE);
 		if (err)
 			return err;
 	}

drivers/block/drbd/drbd_receiver.c

@@ -1333,7 +1333,7 @@ next_bio:
 		goto fail;
 	}
 	/* > peer_req->i.sector, unless this is the first bio */
-	bio->bi_sector = sector;
+	bio->bi_iter.bi_sector = sector;
 	bio->bi_bdev = mdev->ldev->backing_bdev;
 	bio->bi_rw = rw;
 	bio->bi_private = peer_req;
@@ -1353,7 +1353,7 @@ next_bio:
 				dev_err(DEV,
 					"bio_add_page failed for len=%u, "
 					"bi_vcnt=0 (bi_sector=%llu)\n",
-					len, (unsigned long long)bio->bi_sector);
+					len, (uint64_t)bio->bi_iter.bi_sector);
 				err = -ENOSPC;
 				goto fail;
 			}
@@ -1595,9 +1595,10 @@ static int drbd_drain_block(struct drbd_conf *mdev, int data_size)
 static int recv_dless_read(struct drbd_conf *mdev, struct drbd_request *req,
 			   sector_t sector, int data_size)
 {
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct bio *bio;
-	int dgs, err, i, expect;
+	int dgs, err, expect;
 	void *dig_in = mdev->tconn->int_dig_in;
 	void *dig_vv = mdev->tconn->int_dig_vv;
 
@@ -1615,13 +1616,13 @@ static int recv_dless_read(struct drbd_conf *mdev, struct drbd_request *req,
 	mdev->recv_cnt += data_size>>9;
 
 	bio = req->master_bio;
-	D_ASSERT(sector == bio->bi_sector);
+	D_ASSERT(sector == bio->bi_iter.bi_sector);
 
-	bio_for_each_segment(bvec, bio, i) {
-		void *mapped = kmap(bvec->bv_page) + bvec->bv_offset;
-		expect = min_t(int, data_size, bvec->bv_len);
+	bio_for_each_segment(bvec, bio, iter) {
+		void *mapped = kmap(bvec.bv_page) + bvec.bv_offset;
+		expect = min_t(int, data_size, bvec.bv_len);
 		err = drbd_recv_all_warn(mdev->tconn, mapped, expect);
-		kunmap(bvec->bv_page);
+		kunmap(bvec.bv_page);
 		if (err)
 			return err;
 		data_size -= expect;

drivers/block/drbd/drbd_req.c

@@ -77,8 +77,8 @@ static struct drbd_request *drbd_req_new(struct drbd_conf *mdev,
 	req->epoch       = 0;
 
 	drbd_clear_interval(&req->i);
-	req->i.sector     = bio_src->bi_sector;
-	req->i.size      = bio_src->bi_size;
+	req->i.sector     = bio_src->bi_iter.bi_sector;
+	req->i.size      = bio_src->bi_iter.bi_size;
 	req->i.local = true;
 	req->i.waiting = false;
 
@@ -1280,7 +1280,7 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	/*
 	 * what we "blindly" assume:
 	 */
-	D_ASSERT(IS_ALIGNED(bio->bi_size, 512));
+	D_ASSERT(IS_ALIGNED(bio->bi_iter.bi_size, 512));
 
 	inc_ap_bio(mdev);
 	__drbd_make_request(mdev, bio, start_time);

drivers/block/drbd/drbd_req.h

@@ -269,7 +269,7 @@ static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bi
 
 /* Short lived temporary struct on the stack.
  * We could squirrel the error to be returned into
- * bio->bi_size, or similar. But that would be too ugly. */
+ * bio->bi_iter.bi_size, or similar. But that would be too ugly. */
 struct bio_and_error {
 	struct bio *bio;
 	int error;

drivers/block/drbd/drbd_worker.c

@@ -313,8 +313,8 @@ void drbd_csum_bio(struct drbd_conf *mdev, struct crypto_hash *tfm, struct bio *
 {
 	struct hash_desc desc;
 	struct scatterlist sg;
-	struct bio_vec *bvec;
-	int i;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 
 	desc.tfm = tfm;
 	desc.flags = 0;
@@ -322,8 +322,8 @@ void drbd_csum_bio(struct drbd_conf *mdev, struct crypto_hash *tfm, struct bio *
 	sg_init_table(&sg, 1);
 	crypto_hash_init(&desc);
 
-	bio_for_each_segment(bvec, bio, i) {
-		sg_set_page(&sg, bvec->bv_page, bvec->bv_len, bvec->bv_offset);
+	bio_for_each_segment(bvec, bio, iter) {
+		sg_set_page(&sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
 		crypto_hash_update(&desc, &sg, sg.length);
 	}
 	crypto_hash_final(&desc, digest);

drivers/block/floppy.c

@@ -2351,7 +2351,7 @@ static void rw_interrupt(void)
 /* Compute maximal contiguous buffer size. */
 static int buffer_chain_size(void)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	int size;
 	struct req_iterator iter;
 	char *base;
@@ -2360,10 +2360,10 @@ static int buffer_chain_size(void)
 	size = 0;
 
 	rq_for_each_segment(bv, current_req, iter) {
-		if (page_address(bv->bv_page) + bv->bv_offset != base + size)
+		if (page_address(bv.bv_page) + bv.bv_offset != base + size)
 			break;
 
-		size += bv->bv_len;
+		size += bv.bv_len;
 	}
 
 	return size >> 9;
@@ -2389,7 +2389,7 @@ static int transfer_size(int ssize, int max_sector, int max_size)
 static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 {
 	int remaining;		/* number of transferred 512-byte sectors */
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *buffer;
 	char *dma_buffer;
 	int size;
@@ -2427,10 +2427,10 @@ static void copy_buffer(int ssize, int max_sector, int max_sector_2)
 		if (!remaining)
 			break;
 
-		size = bv->bv_len;
+		size = bv.bv_len;
 		SUPBOUND(size, remaining);
 
-		buffer = page_address(bv->bv_page) + bv->bv_offset;
+		buffer = page_address(bv.bv_page) + bv.bv_offset;
 		if (dma_buffer + size >
 		    floppy_track_buffer + (max_buffer_sectors << 10) ||
 		    dma_buffer < floppy_track_buffer) {
@@ -3775,9 +3775,9 @@ static int __floppy_read_block_0(struct block_device *bdev)
 	bio_vec.bv_len = size;
 	bio_vec.bv_offset = 0;
 	bio.bi_vcnt = 1;
-	bio.bi_size = size;
+	bio.bi_iter.bi_size = size;
 	bio.bi_bdev = bdev;
-	bio.bi_sector = 0;
+	bio.bi_iter.bi_sector = 0;
 	bio.bi_flags = (1 << BIO_QUIET);
 	init_completion(&complete);
 	bio.bi_private = &complete;

drivers/block/loop.c

@@ -288,9 +288,10 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 {
 	int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
 			struct page *page);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct page *page = NULL;
-	int i, ret = 0;
+	int ret = 0;
 
 	if (lo->transfer != transfer_none) {
 		page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
@@ -302,11 +303,11 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 		do_lo_send = do_lo_send_direct_write;
 	}
 
-	bio_for_each_segment(bvec, bio, i) {
-		ret = do_lo_send(lo, bvec, pos, page);
+	bio_for_each_segment(bvec, bio, iter) {
+		ret = do_lo_send(lo, &bvec, pos, page);
 		if (ret < 0)
 			break;
-		pos += bvec->bv_len;
+		pos += bvec.bv_len;
 	}
 	if (page) {
 		kunmap(page);
@@ -392,20 +393,20 @@ do_lo_receive(struct loop_device *lo,
 static int
 lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
 {
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	ssize_t s;
-	int i;
 
-	bio_for_each_segment(bvec, bio, i) {
-		s = do_lo_receive(lo, bvec, bsize, pos);
+	bio_for_each_segment(bvec, bio, iter) {
+		s = do_lo_receive(lo, &bvec, bsize, pos);
 		if (s < 0)
 			return s;
 
-		if (s != bvec->bv_len) {
+		if (s != bvec.bv_len) {
 			zero_fill_bio(bio);
 			break;
 		}
-		pos += bvec->bv_len;
+		pos += bvec.bv_len;
 	}
 	return 0;
 }
@@ -415,7 +416,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	loff_t pos;
 	int ret;
 
-	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
+	pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
 		struct file *file = lo->lo_backing_file;
@@ -444,7 +445,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 				goto out;
 			}
 			ret = file->f_op->fallocate(file, mode, pos,
-						    bio->bi_size);
+						    bio->bi_iter.bi_size);
 			if (unlikely(ret && ret != -EINVAL &&
 				     ret != -EOPNOTSUPP))
 				ret = -EIO;

drivers/block/mtip32xx/mtip32xx.c

@@ -3962,8 +3962,9 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct driver_data *dd = queue->queuedata;
 	struct scatterlist *sg;
-	struct bio_vec *bvec;
-	int i, nents = 0;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	int nents = 0;
 	int tag = 0, unaligned = 0;
 
 	if (unlikely(dd->dd_flag & MTIP_DDF_STOP_IO)) {
@@ -3993,7 +3994,7 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 	}
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
-		bio_endio(bio, mtip_send_trim(dd, bio->bi_sector,
+		bio_endio(bio, mtip_send_trim(dd, bio->bi_iter.bi_sector,
 						bio_sectors(bio)));
 		return;
 	}
@@ -4006,7 +4007,8 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 
 	if (bio_data_dir(bio) == WRITE && bio_sectors(bio) <= 64 &&
 							dd->unal_qdepth) {
-		if (bio->bi_sector % 8 != 0) /* Unaligned on 4k boundaries */
+		if (bio->bi_iter.bi_sector % 8 != 0)
+			/* Unaligned on 4k boundaries */
 			unaligned = 1;
 		else if (bio_sectors(bio) % 8 != 0) /* Aligned but not 4k/8k */
 			unaligned = 1;
@@ -4025,17 +4027,17 @@ static void mtip_make_request(struct request_queue *queue, struct bio *bio)
 		}
 
 		/* Create the scatter list for this bio. */
-		bio_for_each_segment(bvec, bio, i) {
+		bio_for_each_segment(bvec, bio, iter) {
 			sg_set_page(&sg[nents],
-					bvec->bv_page,
-					bvec->bv_len,
-					bvec->bv_offset);
+					bvec.bv_page,
+					bvec.bv_len,
+					bvec.bv_offset);
 			nents++;
 		}
 
 		/* Issue the read/write. */
 		mtip_hw_submit_io(dd,
-				bio->bi_sector,
+				bio->bi_iter.bi_sector,
 				bio_sectors(bio),
 				nents,
 				tag,

drivers/block/nbd.c

@@ -271,18 +271,18 @@ static int nbd_send_req(struct nbd_device *nbd, struct request *req)
 
 	if (nbd_cmd(req) == NBD_CMD_WRITE) {
 		struct req_iterator iter;
-		struct bio_vec *bvec;
+		struct bio_vec bvec;
 		/*
 		 * we are really probing at internals to determine
 		 * whether to set MSG_MORE or not...
 		 */
 		rq_for_each_segment(bvec, req, iter) {
 			flags = 0;
-			if (!rq_iter_last(req, iter))
+			if (!rq_iter_last(bvec, iter))
 				flags = MSG_MORE;
 			dprintk(DBG_TX, "%s: request %p: sending %d bytes data\n",
-					nbd->disk->disk_name, req, bvec->bv_len);
-			result = sock_send_bvec(nbd, bvec, flags);
+					nbd->disk->disk_name, req, bvec.bv_len);
+			result = sock_send_bvec(nbd, &bvec, flags);
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
@@ -378,10 +378,10 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 			nbd->disk->disk_name, req);
 	if (nbd_cmd(req) == NBD_CMD_READ) {
 		struct req_iterator iter;
-		struct bio_vec *bvec;
+		struct bio_vec bvec;
 
 		rq_for_each_segment(bvec, req, iter) {
-			result = sock_recv_bvec(nbd, bvec);
+			result = sock_recv_bvec(nbd, &bvec);
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
 					result);
@@ -389,7 +389,7 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 				return req;
 			}
 			dprintk(DBG_RX, "%s: request %p: got %d bytes data\n",
-				nbd->disk->disk_name, req, bvec->bv_len);
+				nbd->disk->disk_name, req, bvec.bv_len);
 		}
 	}
 	return req;

drivers/block/nvme-core.c

@@ -441,104 +441,19 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
 	return total_len;
 }
 
-struct nvme_bio_pair {
-	struct bio b1, b2, *parent;
-	struct bio_vec *bv1, *bv2;
-	int err;
-	atomic_t cnt;
-};
-
-static void nvme_bio_pair_endio(struct bio *bio, int err)
-{
-	struct nvme_bio_pair *bp = bio->bi_private;
-
-	if (err)
-		bp->err = err;
-
-	if (atomic_dec_and_test(&bp->cnt)) {
-		bio_endio(bp->parent, bp->err);
-		kfree(bp->bv1);
-		kfree(bp->bv2);
-		kfree(bp);
-	}
-}
-
-static struct nvme_bio_pair *nvme_bio_split(struct bio *bio, int idx,
-							int len, int offset)
-{
-	struct nvme_bio_pair *bp;
-
-	BUG_ON(len > bio->bi_size);
-	BUG_ON(idx > bio->bi_vcnt);
-
-	bp = kmalloc(sizeof(*bp), GFP_ATOMIC);
-	if (!bp)
-		return NULL;
-	bp->err = 0;
-
-	bp->b1 = *bio;
-	bp->b2 = *bio;
-
-	bp->b1.bi_size = len;
-	bp->b2.bi_size -= len;
-	bp->b1.bi_vcnt = idx;
-	bp->b2.bi_idx = idx;
-	bp->b2.bi_sector += len >> 9;
-
-	if (offset) {
-		bp->bv1 = kmalloc(bio->bi_max_vecs * sizeof(struct bio_vec),
-								GFP_ATOMIC);
-		if (!bp->bv1)
-			goto split_fail_1;
-
-		bp->bv2 = kmalloc(bio->bi_max_vecs * sizeof(struct bio_vec),
-								GFP_ATOMIC);
-		if (!bp->bv2)
-			goto split_fail_2;
-
-		memcpy(bp->bv1, bio->bi_io_vec,
-			bio->bi_max_vecs * sizeof(struct bio_vec));
-		memcpy(bp->bv2, bio->bi_io_vec,
-			bio->bi_max_vecs * sizeof(struct bio_vec));
-
-		bp->b1.bi_io_vec = bp->bv1;
-		bp->b2.bi_io_vec = bp->bv2;
-		bp->b2.bi_io_vec[idx].bv_offset += offset;
-		bp->b2.bi_io_vec[idx].bv_len -= offset;
-		bp->b1.bi_io_vec[idx].bv_len = offset;
-		bp->b1.bi_vcnt++;
-	} else
-		bp->bv1 = bp->bv2 = NULL;
-
-	bp->b1.bi_private = bp;
-	bp->b2.bi_private = bp;
-
-	bp->b1.bi_end_io = nvme_bio_pair_endio;
-	bp->b2.bi_end_io = nvme_bio_pair_endio;
-
-	bp->parent = bio;
-	atomic_set(&bp->cnt, 2);
-
-	return bp;
-
- split_fail_2:
-	kfree(bp->bv1);
- split_fail_1:
-	kfree(bp);
-	return NULL;
-}
-
 static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
-						int idx, int len, int offset)
+				 int len)
 {
-	struct nvme_bio_pair *bp = nvme_bio_split(bio, idx, len, offset);
-	if (!bp)
+	struct bio *split = bio_split(bio, len >> 9, GFP_ATOMIC, NULL);
+	if (!split)
 		return -ENOMEM;
 
+	bio_chain(split, bio);
+
 	if (bio_list_empty(&nvmeq->sq_cong))
 		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
-	bio_list_add(&nvmeq->sq_cong, &bp->b1);
-	bio_list_add(&nvmeq->sq_cong, &bp->b2);
+	bio_list_add(&nvmeq->sq_cong, split);
+	bio_list_add(&nvmeq->sq_cong, bio);
 
 	return 0;
 }
@@ -550,41 +465,44 @@ static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
 static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 		struct bio *bio, enum dma_data_direction dma_dir, int psegs)
 {
-	struct bio_vec *bvec, *bvprv = NULL;
+	struct bio_vec bvec, bvprv;
+	struct bvec_iter iter;
 	struct scatterlist *sg = NULL;
-	int i, length = 0, nsegs = 0, split_len = bio->bi_size;
+	int length = 0, nsegs = 0, split_len = bio->bi_iter.bi_size;
+	int first = 1;
 
 	if (nvmeq->dev->stripe_size)
 		split_len = nvmeq->dev->stripe_size -
-			((bio->bi_sector << 9) & (nvmeq->dev->stripe_size - 1));
+			((bio->bi_iter.bi_sector << 9) &
+			 (nvmeq->dev->stripe_size - 1));
 
 	sg_init_table(iod->sg, psegs);
-	bio_for_each_segment(bvec, bio, i) {
-		if (bvprv && BIOVEC_PHYS_MERGEABLE(bvprv, bvec)) {
-			sg->length += bvec->bv_len;
+	bio_for_each_segment(bvec, bio, iter) {
+		if (!first && BIOVEC_PHYS_MERGEABLE(&bvprv, &bvec)) {
+			sg->length += bvec.bv_len;
 		} else {
-			if (bvprv && BIOVEC_NOT_VIRT_MERGEABLE(bvprv, bvec))
-				return nvme_split_and_submit(bio, nvmeq, i,
-								length, 0);
+			if (!first && BIOVEC_NOT_VIRT_MERGEABLE(&bvprv, &bvec))
+				return nvme_split_and_submit(bio, nvmeq,
+							     length);
 
 			sg = sg ? sg + 1 : iod->sg;
-			sg_set_page(sg, bvec->bv_page, bvec->bv_len,
-							bvec->bv_offset);
+			sg_set_page(sg, bvec.bv_page,
+				    bvec.bv_len, bvec.bv_offset);
 			nsegs++;
 		}
 
-		if (split_len - length < bvec->bv_len)
-			return nvme_split_and_submit(bio, nvmeq, i, split_len,
-							split_len - length);
-		length += bvec->bv_len;
+		if (split_len - length < bvec.bv_len)
+			return nvme_split_and_submit(bio, nvmeq, split_len);
+		length += bvec.bv_len;
 		bvprv = bvec;
+		first = 0;
 	}
 	iod->nents = nsegs;
 	sg_mark_end(sg);
 	if (dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir) == 0)
 		return -ENOMEM;
 
-	BUG_ON(length != bio->bi_size);
+	BUG_ON(length != bio->bi_iter.bi_size);
 	return length;
 }
 
@@ -608,8 +526,8 @@ static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	iod->npages = 0;
 
 	range->cattr = cpu_to_le32(0);
-	range->nlb = cpu_to_le32(bio->bi_size >> ns->lba_shift);
-	range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_sector));
+	range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
+	range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
 
 	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
@@ -674,7 +592,7 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	}
 
 	result = -ENOMEM;
-	iod = nvme_alloc_iod(psegs, bio->bi_size, GFP_ATOMIC);
+	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
 	if (!iod)
 		goto nomem;
 	iod->private = bio;
@@ -723,7 +641,7 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
 	length = nvme_setup_prps(nvmeq->dev, &cmnd->common, iod, length,
 								GFP_ATOMIC);
-	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_sector));
+	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
 	cmnd->rw.length = cpu_to_le16((length >> ns->lba_shift) - 1);
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);

drivers/block/pktcdvd.c

@@ -651,7 +651,7 @@ static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s
 
 	for (;;) {
 		tmp = rb_entry(n, struct pkt_rb_node, rb_node);
-		if (s <= tmp->bio->bi_sector)
+		if (s <= tmp->bio->bi_iter.bi_sector)
 			next = n->rb_left;
 		else
 			next = n->rb_right;
@@ -660,12 +660,12 @@ static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s
 		n = next;
 	}
 
-	if (s > tmp->bio->bi_sector) {
+	if (s > tmp->bio->bi_iter.bi_sector) {
 		tmp = pkt_rbtree_next(tmp);
 		if (!tmp)
 			return NULL;
 	}
-	BUG_ON(s > tmp->bio->bi_sector);
+	BUG_ON(s > tmp->bio->bi_iter.bi_sector);
 	return tmp;
 }
 
@@ -676,13 +676,13 @@ static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *nod
 {
 	struct rb_node **p = &pd->bio_queue.rb_node;
 	struct rb_node *parent = NULL;
-	sector_t s = node->bio->bi_sector;
+	sector_t s = node->bio->bi_iter.bi_sector;
 	struct pkt_rb_node *tmp;
 
 	while (*p) {
 		parent = *p;
 		tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
-		if (s < tmp->bio->bi_sector)
+		if (s < tmp->bio->bi_iter.bi_sector)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -857,7 +857,8 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
 			spin_lock(&pd->iosched.lock);
 			bio = bio_list_peek(&pd->iosched.write_queue);
 			spin_unlock(&pd->iosched.lock);
-			if (bio && (bio->bi_sector == pd->iosched.last_write))
+			if (bio && (bio->bi_iter.bi_sector ==
+				    pd->iosched.last_write))
 				need_write_seek = 0;
 			if (need_write_seek && reads_queued) {
 				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
@@ -888,7 +889,8 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
 			continue;
 
 		if (bio_data_dir(bio) == READ)
-			pd->iosched.successive_reads += bio->bi_size >> 10;
+			pd->iosched.successive_reads +=
+				bio->bi_iter.bi_size >> 10;
 		else {
 			pd->iosched.successive_reads = 0;
 			pd->iosched.last_write = bio_end_sector(bio);
@@ -978,7 +980,7 @@ static void pkt_end_io_read(struct bio *bio, int err)
 
 	pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
 		bio, (unsigned long long)pkt->sector,
-		(unsigned long long)bio->bi_sector, err);
+		(unsigned long long)bio->bi_iter.bi_sector, err);
 
 	if (err)
 		atomic_inc(&pkt->io_errors);
@@ -1026,8 +1028,9 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 	memset(written, 0, sizeof(written));
 	spin_lock(&pkt->lock);
 	bio_list_for_each(bio, &pkt->orig_bios) {
-		int first_frame = (bio->bi_sector - pkt->sector) / (CD_FRAMESIZE >> 9);
-		int num_frames = bio->bi_size / CD_FRAMESIZE;
+		int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
+			(CD_FRAMESIZE >> 9);
+		int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
 		pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
 		BUG_ON(first_frame < 0);
 		BUG_ON(first_frame + num_frames > pkt->frames);
@@ -1053,7 +1056,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
 
 		bio = pkt->r_bios[f];
 		bio_reset(bio);
-		bio->bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
+		bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
 		bio->bi_bdev = pd->bdev;
 		bio->bi_end_io = pkt_end_io_read;
 		bio->bi_private = pkt;
@@ -1150,8 +1153,8 @@ static int pkt_start_recovery(struct packet_data *pkt)
 	bio_reset(pkt->bio);
 	pkt->bio->bi_bdev = pd->bdev;
 	pkt->bio->bi_rw = REQ_WRITE;
-	pkt->bio->bi_sector = new_sector;
-	pkt->bio->bi_size = pkt->frames * CD_FRAMESIZE;
+	pkt->bio->bi_iter.bi_sector = new_sector;
+	pkt->bio->bi_iter.bi_size = pkt->frames * CD_FRAMESIZE;
 	pkt->bio->bi_vcnt = pkt->frames;
 
 	pkt->bio->bi_end_io = pkt_end_io_packet_write;
@@ -1213,7 +1216,7 @@ static int pkt_handle_queue(struct pktcdvd_device *pd)
 	node = first_node;
 	while (node) {
 		bio = node->bio;
-		zone = get_zone(bio->bi_sector, pd);
+		zone = get_zone(bio->bi_iter.bi_sector, pd);
 		list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
 			if (p->sector == zone) {
 				bio = NULL;
@@ -1252,14 +1255,14 @@ try_next_bio:
 	pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
 	while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
 		bio = node->bio;
-		pkt_dbg(2, pd, "found zone=%llx\n",
-			(unsigned long long)get_zone(bio->bi_sector, pd));
-		if (get_zone(bio->bi_sector, pd) != zone)
+		pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long)
+			get_zone(bio->bi_iter.bi_sector, pd));
+		if (get_zone(bio->bi_iter.bi_sector, pd) != zone)
 			break;
 		pkt_rbtree_erase(pd, node);
 		spin_lock(&pkt->lock);
 		bio_list_add(&pkt->orig_bios, bio);
-		pkt->write_size += bio->bi_size / CD_FRAMESIZE;
+		pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
 		spin_unlock(&pkt->lock);
 	}
 	/* check write congestion marks, and if bio_queue_size is
@@ -1293,7 +1296,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	struct bio_vec *bvec = pkt->w_bio->bi_io_vec;
 
 	bio_reset(pkt->w_bio);
-	pkt->w_bio->bi_sector = pkt->sector;
+	pkt->w_bio->bi_iter.bi_sector = pkt->sector;
 	pkt->w_bio->bi_bdev = pd->bdev;
 	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
 	pkt->w_bio->bi_private = pkt;
@@ -2335,75 +2338,29 @@ static void pkt_end_io_read_cloned(struct bio *bio, int err)
 	pkt_bio_finished(pd);
 }
 
-static void pkt_make_request(struct request_queue *q, struct bio *bio)
+static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 {
-	struct pktcdvd_device *pd;
-	char b[BDEVNAME_SIZE];
+	struct bio *cloned_bio = bio_clone(bio, GFP_NOIO);
+	struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
+
+	psd->pd = pd;
+	psd->bio = bio;
+	cloned_bio->bi_bdev = pd->bdev;
+	cloned_bio->bi_private = psd;
+	cloned_bio->bi_end_io = pkt_end_io_read_cloned;
+	pd->stats.secs_r += bio_sectors(bio);
+	pkt_queue_bio(pd, cloned_bio);
+}
+
+static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+{
+	struct pktcdvd_device *pd = q->queuedata;
 	sector_t zone;
 	struct packet_data *pkt;
 	int was_empty, blocked_bio;
 	struct pkt_rb_node *node;
 
-	pd = q->queuedata;
-	if (!pd) {
-		pr_err("%s incorrect request queue\n",
-		       bdevname(bio->bi_bdev, b));
-		goto end_io;
-	}
-
-	/*
-	 * Clone READ bios so we can have our own bi_end_io callback.
-	 */
-	if (bio_data_dir(bio) == READ) {
-		struct bio *cloned_bio = bio_clone(bio, GFP_NOIO);
-		struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
-
-		psd->pd = pd;
-		psd->bio = bio;
-		cloned_bio->bi_bdev = pd->bdev;
-		cloned_bio->bi_private = psd;
-		cloned_bio->bi_end_io = pkt_end_io_read_cloned;
-		pd->stats.secs_r += bio_sectors(bio);
-		pkt_queue_bio(pd, cloned_bio);
-		return;
-	}
-
-	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
-		pkt_notice(pd, "WRITE for ro device (%llu)\n",
-			   (unsigned long long)bio->bi_sector);
-		goto end_io;
-	}
-
-	if (!bio->bi_size || (bio->bi_size % CD_FRAMESIZE)) {
-		pkt_err(pd, "wrong bio size\n");
-		goto end_io;
-	}
-
-	blk_queue_bounce(q, &bio);
-
-	zone = get_zone(bio->bi_sector, pd);
-	pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
-		(unsigned long long)bio->bi_sector,
-		(unsigned long long)bio_end_sector(bio));
-
-	/* Check if we have to split the bio */
-	{
-		struct bio_pair *bp;
-		sector_t last_zone;
-		int first_sectors;
-
-		last_zone = get_zone(bio_end_sector(bio) - 1, pd);
-		if (last_zone != zone) {
-			BUG_ON(last_zone != zone + pd->settings.size);
-			first_sectors = last_zone - bio->bi_sector;
-			bp = bio_split(bio, first_sectors);
-			BUG_ON(!bp);
-			pkt_make_request(q, &bp->bio1);
-			pkt_make_request(q, &bp->bio2);
-			bio_pair_release(bp);
-			return;
-		}
-	}
+	zone = get_zone(bio->bi_iter.bi_sector, pd);
 
 	/*
 	 * If we find a matching packet in state WAITING or READ_WAIT, we can
@@ -2417,7 +2374,8 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 			if ((pkt->state == PACKET_WAITING_STATE) ||
 			    (pkt->state == PACKET_READ_WAIT_STATE)) {
 				bio_list_add(&pkt->orig_bios, bio);
-				pkt->write_size += bio->bi_size / CD_FRAMESIZE;
+				pkt->write_size +=
+					bio->bi_iter.bi_size / CD_FRAMESIZE;
 				if ((pkt->write_size >= pkt->frames) &&
 				    (pkt->state == PACKET_WAITING_STATE)) {
 					atomic_inc(&pkt->run_sm);
@@ -2476,6 +2434,64 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 		 */
 		wake_up(&pd->wqueue);
 	}
+}
+
+static void pkt_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct pktcdvd_device *pd;
+	char b[BDEVNAME_SIZE];
+	struct bio *split;
+
+	pd = q->queuedata;
+	if (!pd) {
+		pr_err("%s incorrect request queue\n",
+		       bdevname(bio->bi_bdev, b));
+		goto end_io;
+	}
+
+	pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
+		(unsigned long long)bio->bi_iter.bi_sector,
+		(unsigned long long)bio_end_sector(bio));
+
+	/*
+	 * Clone READ bios so we can have our own bi_end_io callback.
+	 */
+	if (bio_data_dir(bio) == READ) {
+		pkt_make_request_read(pd, bio);
+		return;
+	}
+
+	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
+		pkt_notice(pd, "WRITE for ro device (%llu)\n",
+			   (unsigned long long)bio->bi_iter.bi_sector);
+		goto end_io;
+	}
+
+	if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
+		pkt_err(pd, "wrong bio size\n");
+		goto end_io;
+	}
+
+	blk_queue_bounce(q, &bio);
+
+	do {
+		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
+		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
+
+		if (last_zone != zone) {
+			BUG_ON(last_zone != zone + pd->settings.size);
+
+			split = bio_split(bio, last_zone -
+					  bio->bi_iter.bi_sector,
+					  GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
+
+		pkt_make_request_write(q, split);
+	} while (split != bio);
+
 	return;
 end_io:
 	bio_io_error(bio);

drivers/block/ps3disk.c

@@ -94,26 +94,25 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
 {
 	unsigned int offset = 0;
 	struct req_iterator iter;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
 	unsigned int i = 0;
 	size_t size;
 	void *buf;
 
 	rq_for_each_segment(bvec, req, iter) {
 		unsigned long flags;
-		dev_dbg(&dev->sbd.core,
-			"%s:%u: bio %u: %u segs %u sectors from %lu\n",
-			__func__, __LINE__, i, bio_segments(iter.bio),
-			bio_sectors(iter.bio), iter.bio->bi_sector);
+		dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %lu\n",
+			__func__, __LINE__, i, bio_sectors(iter.bio),
+			iter.bio->bi_iter.bi_sector);
 
-		size = bvec->bv_len;
-		buf = bvec_kmap_irq(bvec, &flags);
+		size = bvec.bv_len;
+		buf = bvec_kmap_irq(&bvec, &flags);
 		if (gather)
 			memcpy(dev->bounce_buf+offset, buf, size);
 		else
 			memcpy(buf, dev->bounce_buf+offset, size);
 		offset += size;
-		flush_kernel_dcache_page(bvec->bv_page);
+		flush_kernel_dcache_page(bvec.bv_page);
 		bvec_kunmap_irq(buf, &flags);
 		i++;
 	}
@@ -130,7 +129,7 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
 
 #ifdef DEBUG
 	unsigned int n = 0;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	struct req_iterator iter;
 
 	rq_for_each_segment(bv, req, iter)

drivers/block/ps3vram.c

@@ -553,16 +553,16 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
 	int write = bio_data_dir(bio) == WRITE;
 	const char *op = write ? "write" : "read";
-	loff_t offset = bio->bi_sector << 9;
+	loff_t offset = bio->bi_iter.bi_sector << 9;
 	int error = 0;
-	struct bio_vec *bvec;
-	unsigned int i;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct bio *next;
 
-	bio_for_each_segment(bvec, bio, i) {
+	bio_for_each_segment(bvec, bio, iter) {
 		/* PS3 is ppc64, so we don't handle highmem */
-		char *ptr = page_address(bvec->bv_page) + bvec->bv_offset;
-		size_t len = bvec->bv_len, retlen;
+		char *ptr = page_address(bvec.bv_page) + bvec.bv_offset;
+		size_t len = bvec.bv_len, retlen;
 
 		dev_dbg(&dev->core, "    %s %zu bytes at offset %llu\n", op,
 			len, offset);

drivers/block/rbd.c

@@ -1156,23 +1156,23 @@ static void bio_chain_put(struct bio *chain)
  */
 static void zero_bio_chain(struct bio *chain, int start_ofs)
 {
-	struct bio_vec *bv;
+	struct bio_vec bv;
+	struct bvec_iter iter;
 	unsigned long flags;
 	void *buf;
-	int i;
 	int pos = 0;
 
 	while (chain) {
-		bio_for_each_segment(bv, chain, i) {
-			if (pos + bv->bv_len > start_ofs) {
+		bio_for_each_segment(bv, chain, iter) {
+			if (pos + bv.bv_len > start_ofs) {
 				int remainder = max(start_ofs - pos, 0);
-				buf = bvec_kmap_irq(bv, &flags);
+				buf = bvec_kmap_irq(&bv, &flags);
 				memset(buf + remainder, 0,
-				       bv->bv_len - remainder);
-				flush_dcache_page(bv->bv_page);
+				       bv.bv_len - remainder);
+				flush_dcache_page(bv.bv_page);
 				bvec_kunmap_irq(buf, &flags);
 			}
-			pos += bv->bv_len;
+			pos += bv.bv_len;
 		}
 
 		chain = chain->bi_next;
@@ -1220,74 +1220,14 @@ static struct bio *bio_clone_range(struct bio *bio_src,
 					unsigned int len,
 					gfp_t gfpmask)
 {
-	struct bio_vec *bv;
-	unsigned int resid;
-	unsigned short idx;
-	unsigned int voff;
-	unsigned short end_idx;
-	unsigned short vcnt;
 	struct bio *bio;
 
-	/* Handle the easy case for the caller */
-
-	if (!offset && len == bio_src->bi_size)
-		return bio_clone(bio_src, gfpmask);
-
-	if (WARN_ON_ONCE(!len))
-		return NULL;
-	if (WARN_ON_ONCE(len > bio_src->bi_size))
-		return NULL;
-	if (WARN_ON_ONCE(offset > bio_src->bi_size - len))
-		return NULL;
-
-	/* Find first affected segment... */
-
-	resid = offset;
-	bio_for_each_segment(bv, bio_src, idx) {
-		if (resid < bv->bv_len)
-			break;
-		resid -= bv->bv_len;
-	}
-	voff = resid;
-
-	/* ...and the last affected segment */
-
-	resid += len;
-	__bio_for_each_segment(bv, bio_src, end_idx, idx) {
-		if (resid <= bv->bv_len)
-			break;
-		resid -= bv->bv_len;
-	}
-	vcnt = end_idx - idx + 1;
-
-	/* Build the clone */
-
-	bio = bio_alloc(gfpmask, (unsigned int) vcnt);
+	bio = bio_clone(bio_src, gfpmask);
 	if (!bio)
 		return NULL;	/* ENOMEM */
 
-	bio->bi_bdev = bio_src->bi_bdev;
-	bio->bi_sector = bio_src->bi_sector + (offset >> SECTOR_SHIFT);
-	bio->bi_rw = bio_src->bi_rw;
-	bio->bi_flags |= 1 << BIO_CLONED;
-
-	/*
-	 * Copy over our part of the bio_vec, then update the first
-	 * and last (or only) entries.
-	 */
-	memcpy(&bio->bi_io_vec[0], &bio_src->bi_io_vec[idx],
-			vcnt * sizeof (struct bio_vec));
-	bio->bi_io_vec[0].bv_offset += voff;
-	if (vcnt > 1) {
-		bio->bi_io_vec[0].bv_len -= voff;
-		bio->bi_io_vec[vcnt - 1].bv_len = resid;
-	} else {
-		bio->bi_io_vec[0].bv_len = len;
-	}
-
-	bio->bi_vcnt = vcnt;
-	bio->bi_size = len;
-	bio->bi_idx = 0;
+	bio_advance(bio, offset);
+	bio->bi_iter.bi_size = len;
 
 	return bio;
 }
@@ -1318,7 +1258,7 @@ static struct bio *bio_chain_clone_range(struct bio **bio_src,
 
 	/* Build up a chain of clone bios up to the limit */
 
-	if (!bi || off >= bi->bi_size || !len)
+	if (!bi || off >= bi->bi_iter.bi_size || !len)
 		return NULL;		/* Nothing to clone */
 
 	end = &chain;
@@ -1330,7 +1270,7 @@ static struct bio *bio_chain_clone_range(struct bio **bio_src,
 			rbd_warn(NULL, "bio_chain exhausted with %u left", len);
 			goto out_err;	/* EINVAL; ran out of bio's */
 		}
-		bi_size = min_t(unsigned int, bi->bi_size - off, len);
+		bi_size = min_t(unsigned int, bi->bi_iter.bi_size - off, len);
 		bio = bio_clone_range(bi, off, bi_size, gfpmask);
 		if (!bio)
 			goto out_err;	/* ENOMEM */
@@ -1339,7 +1279,7 @@ static struct bio *bio_chain_clone_range(struct bio **bio_src,
 		end = &bio->bi_next;
 
 		off += bi_size;
-		if (off == bi->bi_size) {
+		if (off == bi->bi_iter.bi_size) {
 			bi = bi->bi_next;
 			off = 0;
 		}
@@ -2227,7 +2167,8 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 
 	if (type == OBJ_REQUEST_BIO) {
 		bio_list = data_desc;
-		rbd_assert(img_offset == bio_list->bi_sector << SECTOR_SHIFT);
+		rbd_assert(img_offset ==
+			   bio_list->bi_iter.bi_sector << SECTOR_SHIFT);
 	} else {
 		rbd_assert(type == OBJ_REQUEST_PAGES);
 		pages = data_desc;

drivers/block/rsxx/dev.c

@@ -174,7 +174,7 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 	if (!card)
 		goto req_err;
 
-	if (bio->bi_sector + (bio->bi_size >> 9) > get_capacity(card->gendisk))
+	if (bio_end_sector(bio) > get_capacity(card->gendisk))
 		goto req_err;
 
 	if (unlikely(card->halt)) {
@@ -187,7 +187,7 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 		goto req_err;
 	}
 
-	if (bio->bi_size == 0) {
+	if (bio->bi_iter.bi_size == 0) {
 		dev_err(CARD_TO_DEV(card), "size zero BIO!\n");
 		goto req_err;
 	}
@@ -208,7 +208,7 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 
 	dev_dbg(CARD_TO_DEV(card), "BIO[%c]: meta: %p addr8: x%llx size: %d\n",
 		 bio_data_dir(bio) ? 'W' : 'R', bio_meta,
-		 (u64)bio->bi_sector << 9, bio->bi_size);
+		 (u64)bio->bi_iter.bi_sector << 9, bio->bi_iter.bi_size);
 
 	st = rsxx_dma_queue_bio(card, bio, &bio_meta->pending_dmas,
 				    bio_dma_done_cb, bio_meta);

drivers/block/rsxx/dma.c

@@ -684,7 +684,8 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 			   void *cb_data)
 {
 	struct list_head dma_list[RSXX_MAX_TARGETS];
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	unsigned long long addr8;
 	unsigned int laddr;
 	unsigned int bv_len;
@@ -696,7 +697,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 	int st;
 	int i;
 
-	addr8 = bio->bi_sector << 9; /* sectors are 512 bytes */
+	addr8 = bio->bi_iter.bi_sector << 9; /* sectors are 512 bytes */
 	atomic_set(n_dmas, 0);
 
 	for (i = 0; i < card->n_targets; i++) {
@@ -705,7 +706,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 	}
 
 	if (bio->bi_rw & REQ_DISCARD) {
-		bv_len = bio->bi_size;
+		bv_len = bio->bi_iter.bi_size;
 
 		while (bv_len > 0) {
 			tgt   = rsxx_get_dma_tgt(card, addr8);
@@ -722,9 +723,9 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 			bv_len -= RSXX_HW_BLK_SIZE;
 		}
 	} else {
-		bio_for_each_segment(bvec, bio, i) {
-			bv_len = bvec->bv_len;
-			bv_off = bvec->bv_offset;
+		bio_for_each_segment(bvec, bio, iter) {
+			bv_len = bvec.bv_len;
+			bv_off = bvec.bv_offset;
 
 			while (bv_len > 0) {
 				tgt   = rsxx_get_dma_tgt(card, addr8);
@@ -736,7 +737,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 				st = rsxx_queue_dma(card, &dma_list[tgt],
 							bio_data_dir(bio),
 							dma_off, dma_len,
-							laddr, bvec->bv_page,
+							laddr, bvec.bv_page,
 							bv_off, cb, cb_data);
 				if (st)
 					goto bvec_err;

drivers/block/umem.c

@@ -108,8 +108,7 @@ struct cardinfo {
 				    * have been written
 				    */
 	struct bio	*bio, *currentbio, **biotail;
-	int		current_idx;
-	sector_t	current_sector;
+	struct bvec_iter current_iter;
 
 	struct request_queue *queue;
 
@@ -118,7 +117,7 @@ struct cardinfo {
 		struct mm_dma_desc	*desc;
 		int	 		cnt, headcnt;
 		struct bio		*bio, **biotail;
-		int			idx;
+		struct bvec_iter	iter;
 	} mm_pages[2];
 #define DESC_PER_PAGE ((PAGE_SIZE*2)/sizeof(struct mm_dma_desc))
 
@@ -344,16 +343,13 @@ static int add_bio(struct cardinfo *card)
 	dma_addr_t dma_handle;
 	int offset;
 	struct bio *bio;
-	struct bio_vec *vec;
-	int idx;
+	struct bio_vec vec;
 	int rw;
-	int len;
 
 	bio = card->currentbio;
 	if (!bio && card->bio) {
 		card->currentbio = card->bio;
-		card->current_idx = card->bio->bi_idx;
-		card->current_sector = card->bio->bi_sector;
+		card->current_iter = card->bio->bi_iter;
 		card->bio = card->bio->bi_next;
 		if (card->bio == NULL)
 			card->biotail = &card->bio;
@@ -362,18 +358,17 @@ static int add_bio(struct cardinfo *card)
 	}
 	if (!bio)
 		return 0;
-	idx = card->current_idx;
 
 	rw = bio_rw(bio);
 	if (card->mm_pages[card->Ready].cnt >= DESC_PER_PAGE)
 		return 0;
 
-	vec = bio_iovec_idx(bio, idx);
-	len = vec->bv_len;
+	vec = bio_iter_iovec(bio, card->current_iter);
+
 	dma_handle = pci_map_page(card->dev,
-				  vec->bv_page,
-				  vec->bv_offset,
-				  len,
+				  vec.bv_page,
+				  vec.bv_offset,
+				  vec.bv_len,
 				  (rw == READ) ?
 				  PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE);
 
@@ -381,7 +376,7 @@ static int add_bio(struct cardinfo *card)
 	desc = &p->desc[p->cnt];
 	p->cnt++;
 	if (p->bio == NULL)
-		p->idx = idx;
+		p->iter = card->current_iter;
 	if ((p->biotail) != &bio->bi_next) {
 		*(p->biotail) = bio;
 		p->biotail = &(bio->bi_next);
@@ -391,8 +386,8 @@ static int add_bio(struct cardinfo *card)
 	desc->data_dma_handle = dma_handle;
 
 	desc->pci_addr = cpu_to_le64((u64)desc->data_dma_handle);
-	desc->local_addr = cpu_to_le64(card->current_sector << 9);
-	desc->transfer_size = cpu_to_le32(len);
+	desc->local_addr = cpu_to_le64(card->current_iter.bi_sector << 9);
+	desc->transfer_size = cpu_to_le32(vec.bv_len);
 	offset = (((char *)&desc->sem_control_bits) - ((char *)p->desc));
 	desc->sem_addr = cpu_to_le64((u64)(p->page_dma+offset));
 	desc->zero1 = desc->zero2 = 0;
@@ -407,10 +402,9 @@ static int add_bio(struct cardinfo *card)
 		desc->control_bits |= cpu_to_le32(DMASCR_TRANSFER_READ);
 	desc->sem_control_bits = desc->control_bits;
 
-	card->current_sector += (len >> 9);
-	idx++;
-	card->current_idx = idx;
-	if (idx >= bio->bi_vcnt)
+
+	bio_advance_iter(bio, &card->current_iter, vec.bv_len);
+	if (!card->current_iter.bi_size)
 		card->currentbio = NULL;
 
 	return 1;
@@ -439,23 +433,25 @@ static void process_page(unsigned long data)
 		struct mm_dma_desc *desc = &page->desc[page->headcnt];
 		int control = le32_to_cpu(desc->sem_control_bits);
 		int last = 0;
-		int idx;
+		struct bio_vec vec;
 
 		if (!(control & DMASCR_DMA_COMPLETE)) {
 			control = dma_status;
 			last = 1;
 		}
+
 		page->headcnt++;
-		idx = page->idx;
-		page->idx++;
-		if (page->idx >= bio->bi_vcnt) {
+		vec = bio_iter_iovec(bio, page->iter);
+		bio_advance_iter(bio, &page->iter, vec.bv_len);
+
+		if (!page->iter.bi_size) {
 			page->bio = bio->bi_next;
 			if (page->bio)
-				page->idx = page->bio->bi_idx;
+				page->iter = page->bio->bi_iter;
 		}
 
 		pci_unmap_page(card->dev, desc->data_dma_handle,
-			       bio_iovec_idx(bio, idx)->bv_len,
+			       vec.bv_len,
 				 (control & DMASCR_TRANSFER_READ) ?
 				PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
 		if (control & DMASCR_HARD_ERROR) {
@@ -532,7 +528,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct cardinfo *card = q->queuedata;
 	pr_debug("mm_make_request %llu %u\n",
-		 (unsigned long long)bio->bi_sector, bio->bi_size);
+		 (unsigned long long)bio->bi_iter.bi_sector,
+		 bio->bi_iter.bi_size);
 
 	spin_lock_irq(&card->lock);
 	*card->biotail = bio;

drivers/block/xen-blkback/blkback.c

@@ -1257,7 +1257,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 			bio->bi_bdev    = preq.bdev;
 			bio->bi_private = pending_req;
 			bio->bi_end_io  = end_block_io_op;
-			bio->bi_sector  = preq.sector_number;
+			bio->bi_iter.bi_sector  = preq.sector_number;
 		}
 
 		preq.sector_number += seg[i].nsec;

drivers/block/xen-blkfront.c

@@ -1547,7 +1547,7 @@ static int blkif_recover(struct blkfront_info *info)
 			for (i = 0; i < pending; i++) {
 				offset = (i * segs * PAGE_SIZE) >> 9;
 				size = min((unsigned int)(segs * PAGE_SIZE) >> 9,
-					   (unsigned int)(bio->bi_size >> 9) - offset);
+					   (unsigned int)bio_sectors(bio) - offset);
 				cloned_bio = bio_clone(bio, GFP_NOIO);
 				BUG_ON(cloned_bio == NULL);
 				bio_trim(cloned_bio, offset, size);

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);
-
-	if (bio_segments(bio) > max_segments ||
-	    q->merge_bvec_fn) {
-		struct bio_vec *bv;
-		int i, seg = 0;
-
-		ret = 0;
-
-		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 (seg == max_segments)
-				break;
+		return min(bio_sectors(bio), q->limits.max_discard_sectors);
+
+	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,
+		};
+
+		if (seg == min_t(unsigned, BIO_MAX_PAGES,
+				 queue_max_segments(q)))
+			break;
 
-			if (q->merge_bvec_fn &&
-			    q->merge_bvec_fn(q, &bvm, bv) < (int) bv->bv_len)
-				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;
-
-			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);
+			struct bio_vec bv = bio_iter_iovec(bio, io->iter);
+
+			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 (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 (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_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);
-
-	/*
-	 * 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;
-	}
-
-	/*
-	 * 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);
-
-		__clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
-					 ci->idx, idx - ci->idx, 0, len, 0);
+	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
-		ci->sector += len;
-		ci->sector_count -= len;
-		ci->idx = idx;
+	__clone_and_map_data_bio(ci, ti, ci->sector, len);
 
-		return 0;
-	}
+	ci->sector += len;
+	ci->sector_count -= len;
 
-	/*
-	 * 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;
-
-
-	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;
+	do {
+		rcu_read_lock();
 
-		rcu_read_unlock();
-
-		bp = bio_split(bio, end_sector - bio->bi_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;
 
-		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();
+		rcu_read_unlock();
 
-	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 (unlikely(bio->bi_iter.bi_sector >= end_sector ||
+			     bio->bi_iter.bi_sector < start_sector))
+			goto out_of_bounds;
+
+		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;
+		}
 
-	generic_make_request(bio);
+		split->bi_iter.bi_sector = split->bi_iter.bi_sector -
+			start_sector + data_offset;
+
+		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;
-
-	if (unlikely((bio->bi_rw & REQ_DISCARD) &&
-		     !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) {
-		/* Just ignore it */
-		bio_endio(bio, 0);
-		return;
-	}
+		unsigned sectors = chunk_sects -
+			(likely(is_power_of_2(chunk_sects))
+			 ? (sector & (chunk_sects-1))
+			 : sector_div(sector, chunk_sects));
 
-	generic_make_request(bio);
-	return;
-
-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);
+		if (sectors < bio_sectors(bio)) {
+			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
 
-	bio_io_error(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;
+
+		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);

drivers/message/fusion/mptsas.c

@@ -2235,10 +2235,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	}
 
 	/* do we need to support multiple segments? */
-	if (bio_segments(req->bio) > 1 || bio_segments(rsp->bio) > 1) {
-		printk(MYIOC_s_ERR_FMT "%s: multiple segments req %u %u, rsp %u %u\n",
-		    ioc->name, __func__, bio_segments(req->bio), blk_rq_bytes(req),
-		    bio_segments(rsp->bio), blk_rq_bytes(rsp));
+	if (bio_multiple_segments(req->bio) ||
+	    bio_multiple_segments(rsp->bio)) {
+		printk(MYIOC_s_ERR_FMT "%s: multiple segments req %u, rsp %u\n",
+		    ioc->name, __func__, blk_rq_bytes(req), blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 

drivers/s390/block/dasd_diag.c

@@ -504,7 +504,7 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	struct dasd_diag_req *dreq;
 	struct dasd_diag_bio *dbio;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst;
 	unsigned int count, datasize;
 	sector_t recid, first_rec, last_rec;
@@ -525,10 +525,10 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	/* Check struct bio and count the number of blocks for the request. */
 	count = 0;
 	rq_for_each_segment(bv, req, iter) {
-		if (bv->bv_len & (blksize - 1))
+		if (bv.bv_len & (blksize - 1))
 			/* Fba can only do full blocks. */
 			return ERR_PTR(-EINVAL);
-		count += bv->bv_len >> (block->s2b_shift + 9);
+		count += bv.bv_len >> (block->s2b_shift + 9);
 	}
 	/* Paranoia. */
 	if (count != last_rec - first_rec + 1)
@@ -545,8 +545,8 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	dbio = dreq->bio;
 	recid = first_rec;
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
-		for (off = 0; off < bv->bv_len; off += blksize) {
+		dst = page_address(bv.bv_page) + bv.bv_offset;
+		for (off = 0; off < bv.bv_len; off += blksize) {
 			memset(dbio, 0, sizeof (struct dasd_diag_bio));
 			dbio->type = rw_cmd;
 			dbio->block_number = recid + 1;

drivers/s390/block/dasd_eckd.c

@@ -2551,7 +2551,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
 	struct dasd_ccw_req *cqr;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst;
 	unsigned int off;
 	int count, cidaw, cplength, datasize;
@@ -2573,13 +2573,13 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
 	count = 0;
 	cidaw = 0;
 	rq_for_each_segment(bv, req, iter) {
-		if (bv->bv_len & (blksize - 1))
+		if (bv.bv_len & (blksize - 1))
 			/* Eckd can only do full blocks. */
 			return ERR_PTR(-EINVAL);
-		count += bv->bv_len >> (block->s2b_shift + 9);
+		count += bv.bv_len >> (block->s2b_shift + 9);
 #if defined(CONFIG_64BIT)
-		if (idal_is_needed (page_address(bv->bv_page), bv->bv_len))
-			cidaw += bv->bv_len >> (block->s2b_shift + 9);
+		if (idal_is_needed (page_address(bv.bv_page), bv.bv_len))
+			cidaw += bv.bv_len >> (block->s2b_shift + 9);
 #endif
 	}
 	/* Paranoia. */
@@ -2650,16 +2650,16 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
 			      last_rec - recid + 1, cmd, basedev, blksize);
 	}
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
+		dst = page_address(bv.bv_page) + bv.bv_offset;
 		if (dasd_page_cache) {
 			char *copy = kmem_cache_alloc(dasd_page_cache,
 						      GFP_DMA | __GFP_NOWARN);
 			if (copy && rq_data_dir(req) == WRITE)
-				memcpy(copy + bv->bv_offset, dst, bv->bv_len);
+				memcpy(copy + bv.bv_offset, dst, bv.bv_len);
 			if (copy)
-				dst = copy + bv->bv_offset;
+				dst = copy + bv.bv_offset;
 		}
-		for (off = 0; off < bv->bv_len; off += blksize) {
+		for (off = 0; off < bv.bv_len; off += blksize) {
 			sector_t trkid = recid;
 			unsigned int recoffs = sector_div(trkid, blk_per_trk);
 			rcmd = cmd;
@@ -2735,7 +2735,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track(
 	struct dasd_ccw_req *cqr;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst, *idaw_dst;
 	unsigned int cidaw, cplength, datasize;
 	unsigned int tlf;
@@ -2813,8 +2813,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_track(
 	idaw_dst = NULL;
 	idaw_len = 0;
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
-		seg_len = bv->bv_len;
+		dst = page_address(bv.bv_page) + bv.bv_offset;
+		seg_len = bv.bv_len;
 		while (seg_len) {
 			if (new_track) {
 				trkid = recid;
@@ -3039,7 +3039,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
 {
 	struct dasd_ccw_req *cqr;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst;
 	unsigned int trkcount, ctidaw;
 	unsigned char cmd;
@@ -3125,8 +3125,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
 		new_track = 1;
 		recid = first_rec;
 		rq_for_each_segment(bv, req, iter) {
-			dst = page_address(bv->bv_page) + bv->bv_offset;
-			seg_len = bv->bv_len;
+			dst = page_address(bv.bv_page) + bv.bv_offset;
+			seg_len = bv.bv_len;
 			while (seg_len) {
 				if (new_track) {
 					trkid = recid;
@@ -3158,9 +3158,9 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
 		}
 	} else {
 		rq_for_each_segment(bv, req, iter) {
-			dst = page_address(bv->bv_page) + bv->bv_offset;
+			dst = page_address(bv.bv_page) + bv.bv_offset;
 			last_tidaw = itcw_add_tidaw(itcw, 0x00,
-						    dst, bv->bv_len);
+						    dst, bv.bv_len);
 			if (IS_ERR(last_tidaw)) {
 				ret = -EINVAL;
 				goto out_error;
@@ -3278,7 +3278,7 @@ static struct dasd_ccw_req *dasd_raw_build_cp(struct dasd_device *startdev,
 	struct dasd_ccw_req *cqr;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst;
 	unsigned char cmd;
 	unsigned int trkcount;
@@ -3378,8 +3378,8 @@ static struct dasd_ccw_req *dasd_raw_build_cp(struct dasd_device *startdev,
 			idaws = idal_create_words(idaws, rawpadpage, PAGE_SIZE);
 	}
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
-		seg_len = bv->bv_len;
+		dst = page_address(bv.bv_page) + bv.bv_offset;
+		seg_len = bv.bv_len;
 		if (cmd == DASD_ECKD_CCW_READ_TRACK)
 			memset(dst, 0, seg_len);
 		if (!len_to_track_end) {
@@ -3424,7 +3424,7 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	struct dasd_eckd_private *private;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst, *cda;
 	unsigned int blksize, blk_per_trk, off;
 	sector_t recid;
@@ -3442,8 +3442,8 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	if (private->uses_cdl == 0 || recid > 2*blk_per_trk)
 		ccw++;
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
-		for (off = 0; off < bv->bv_len; off += blksize) {
+		dst = page_address(bv.bv_page) + bv.bv_offset;
+		for (off = 0; off < bv.bv_len; off += blksize) {
 			/* Skip locate record. */
 			if (private->uses_cdl && recid <= 2*blk_per_trk)
 				ccw++;
@@ -3454,7 +3454,7 @@ dasd_eckd_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 					cda = (char *)((addr_t) ccw->cda);
 				if (dst != cda) {
 					if (rq_data_dir(req) == READ)
-						memcpy(dst, cda, bv->bv_len);
+						memcpy(dst, cda, bv.bv_len);
 					kmem_cache_free(dasd_page_cache,
 					    (void *)((addr_t)cda & PAGE_MASK));
 				}

drivers/s390/block/dasd_fba.c

@@ -260,7 +260,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 	struct dasd_ccw_req *cqr;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst;
 	int count, cidaw, cplength, datasize;
 	sector_t recid, first_rec, last_rec;
@@ -283,13 +283,13 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 	count = 0;
 	cidaw = 0;
 	rq_for_each_segment(bv, req, iter) {
-		if (bv->bv_len & (blksize - 1))
+		if (bv.bv_len & (blksize - 1))
 			/* Fba can only do full blocks. */
 			return ERR_PTR(-EINVAL);
-		count += bv->bv_len >> (block->s2b_shift + 9);
+		count += bv.bv_len >> (block->s2b_shift + 9);
 #if defined(CONFIG_64BIT)
-		if (idal_is_needed (page_address(bv->bv_page), bv->bv_len))
-			cidaw += bv->bv_len / blksize;
+		if (idal_is_needed (page_address(bv.bv_page), bv.bv_len))
+			cidaw += bv.bv_len / blksize;
 #endif
 	}
 	/* Paranoia. */
@@ -326,16 +326,16 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 	}
 	recid = first_rec;
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
+		dst = page_address(bv.bv_page) + bv.bv_offset;
 		if (dasd_page_cache) {
 			char *copy = kmem_cache_alloc(dasd_page_cache,
 						      GFP_DMA | __GFP_NOWARN);
 			if (copy && rq_data_dir(req) == WRITE)
-				memcpy(copy + bv->bv_offset, dst, bv->bv_len);
+				memcpy(copy + bv.bv_offset, dst, bv.bv_len);
 			if (copy)
-				dst = copy + bv->bv_offset;
+				dst = copy + bv.bv_offset;
 		}
-		for (off = 0; off < bv->bv_len; off += blksize) {
+		for (off = 0; off < bv.bv_len; off += blksize) {
 			/* Locate record for stupid devices. */
 			if (private->rdc_data.mode.bits.data_chain == 0) {
 				ccw[-1].flags |= CCW_FLAG_CC;
@@ -384,7 +384,7 @@ dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	struct dasd_fba_private *private;
 	struct ccw1 *ccw;
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	char *dst, *cda;
 	unsigned int blksize, off;
 	int status;
@@ -399,8 +399,8 @@ dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	if (private->rdc_data.mode.bits.data_chain != 0)
 		ccw++;
 	rq_for_each_segment(bv, req, iter) {
-		dst = page_address(bv->bv_page) + bv->bv_offset;
-		for (off = 0; off < bv->bv_len; off += blksize) {
+		dst = page_address(bv.bv_page) + bv.bv_offset;
+		for (off = 0; off < bv.bv_len; off += blksize) {
 			/* Skip locate record. */
 			if (private->rdc_data.mode.bits.data_chain == 0)
 				ccw++;
@@ -411,7 +411,7 @@ dasd_fba_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 					cda = (char *)((addr_t) ccw->cda);
 				if (dst != cda) {
 					if (rq_data_dir(req) == READ)
-						memcpy(dst, cda, bv->bv_len);
+						memcpy(dst, cda, bv.bv_len);
 					kmem_cache_free(dasd_page_cache,
 					    (void *)((addr_t)cda & PAGE_MASK));
 				}

drivers/s390/block/dcssblk.c

@@ -808,18 +808,19 @@ static void
 dcssblk_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct dcssblk_dev_info *dev_info;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	unsigned long index;
 	unsigned long page_addr;
 	unsigned long source_addr;
 	unsigned long bytes_done;
-	int i;
 
 	bytes_done = 0;
 	dev_info = bio->bi_bdev->bd_disk->private_data;
 	if (dev_info == NULL)
 		goto fail;
-	if ((bio->bi_sector & 7) != 0 || (bio->bi_size & 4095) != 0)
+	if ((bio->bi_iter.bi_sector & 7) != 0 ||
+	    (bio->bi_iter.bi_size & 4095) != 0)
 		/* Request is not page-aligned. */
 		goto fail;
 	if (bio_end_sector(bio) > get_capacity(bio->bi_bdev->bd_disk)) {
@@ -842,22 +843,22 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 		}
 	}
 
-	index = (bio->bi_sector >> 3);
-	bio_for_each_segment(bvec, bio, i) {
+	index = (bio->bi_iter.bi_sector >> 3);
+	bio_for_each_segment(bvec, bio, iter) {
 		page_addr = (unsigned long)
-			page_address(bvec->bv_page) + bvec->bv_offset;
+			page_address(bvec.bv_page) + bvec.bv_offset;
 		source_addr = dev_info->start + (index<<12) + bytes_done;
-		if (unlikely((page_addr & 4095) != 0) || (bvec->bv_len & 4095) != 0)
+		if (unlikely((page_addr & 4095) != 0) || (bvec.bv_len & 4095) != 0)
 			// More paranoia.
 			goto fail;
 		if (bio_data_dir(bio) == READ) {
 			memcpy((void*)page_addr, (void*)source_addr,
-				bvec->bv_len);
+				bvec.bv_len);
 		} else {
 			memcpy((void*)source_addr, (void*)page_addr,
-				bvec->bv_len);
+				bvec.bv_len);
 		}
-		bytes_done += bvec->bv_len;
+		bytes_done += bvec.bv_len;
 	}
 	bio_endio(bio, 0);
 	return;

drivers/s390/block/scm_blk.c

@@ -130,7 +130,7 @@ static void scm_request_prepare(struct scm_request *scmrq)
 	struct aidaw *aidaw = scmrq->aidaw;
 	struct msb *msb = &scmrq->aob->msb[0];
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 
 	msb->bs = MSB_BS_4K;
 	scmrq->aob->request.msb_count = 1;
@@ -142,9 +142,9 @@ static void scm_request_prepare(struct scm_request *scmrq)
 	msb->data_addr = (u64) aidaw;
 
 	rq_for_each_segment(bv, scmrq->request, iter) {
-		WARN_ON(bv->bv_offset);
-		msb->blk_count += bv->bv_len >> 12;
-		aidaw->data_addr = (u64) page_address(bv->bv_page);
+		WARN_ON(bv.bv_offset);
+		msb->blk_count += bv.bv_len >> 12;
+		aidaw->data_addr = (u64) page_address(bv.bv_page);
 		aidaw++;
 	}
 }

drivers/s390/block/scm_blk_cluster.c

@@ -122,7 +122,7 @@ static void scm_prepare_cluster_request(struct scm_request *scmrq)
 	struct aidaw *aidaw = scmrq->aidaw;
 	struct msb *msb = &scmrq->aob->msb[0];
 	struct req_iterator iter;
-	struct bio_vec *bv;
+	struct bio_vec bv;
 	int i = 0;
 	u64 addr;
 
@@ -163,7 +163,7 @@ static void scm_prepare_cluster_request(struct scm_request *scmrq)
 			i++;
 		}
 		rq_for_each_segment(bv, req, iter) {
-			aidaw->data_addr = (u64) page_address(bv->bv_page);
+			aidaw->data_addr = (u64) page_address(bv.bv_page);
 			aidaw++;
 			i++;
 		}

drivers/s390/block/xpram.c

@@ -184,25 +184,26 @@ static unsigned long xpram_highest_page_index(void)
 static void xpram_make_request(struct request_queue *q, struct bio *bio)
 {
 	xpram_device_t *xdev = bio->bi_bdev->bd_disk->private_data;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	unsigned int index;
 	unsigned long page_addr;
 	unsigned long bytes;
-	int i;
 
-	if ((bio->bi_sector & 7) != 0 || (bio->bi_size & 4095) != 0)
+	if ((bio->bi_iter.bi_sector & 7) != 0 ||
+	    (bio->bi_iter.bi_size & 4095) != 0)
 		/* Request is not page-aligned. */
 		goto fail;
-	if ((bio->bi_size >> 12) > xdev->size)
+	if ((bio->bi_iter.bi_size >> 12) > xdev->size)
 		/* Request size is no page-aligned. */
 		goto fail;
-	if ((bio->bi_sector >> 3) > 0xffffffffU - xdev->offset)
+	if ((bio->bi_iter.bi_sector >> 3) > 0xffffffffU - xdev->offset)
 		goto fail;
-	index = (bio->bi_sector >> 3) + xdev->offset;
-	bio_for_each_segment(bvec, bio, i) {
+	index = (bio->bi_iter.bi_sector >> 3) + xdev->offset;
+	bio_for_each_segment(bvec, bio, iter) {
 		page_addr = (unsigned long)
-			kmap(bvec->bv_page) + bvec->bv_offset;
-		bytes = bvec->bv_len;
+			kmap(bvec.bv_page) + bvec.bv_offset;
+		bytes = bvec.bv_len;
 		if ((page_addr & 4095) != 0 || (bytes & 4095) != 0)
 			/* More paranoia. */
 			goto fail;

drivers/scsi/libsas/sas_expander.c

@@ -2163,10 +2163,10 @@ int sas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	}
 
 	/* do we need to support multiple segments? */
-	if (bio_segments(req->bio) > 1 || bio_segments(rsp->bio) > 1) {
-		printk("%s: multiple segments req %u %u, rsp %u %u\n",
-		       __func__, bio_segments(req->bio), blk_rq_bytes(req),
-		       bio_segments(rsp->bio), blk_rq_bytes(rsp));
+	if (bio_multiple_segments(req->bio) ||
+	    bio_multiple_segments(rsp->bio)) {
+		printk("%s: multiple segments req %u, rsp %u\n",
+		       __func__, blk_rq_bytes(req), blk_rq_bytes(rsp));
 		return -EINVAL;
 	}
 

drivers/scsi/mpt2sas/mpt2sas_transport.c

@@ -1901,7 +1901,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	struct MPT2SAS_ADAPTER *ioc = shost_priv(shost);
 	Mpi2SmpPassthroughRequest_t *mpi_request;
 	Mpi2SmpPassthroughReply_t *mpi_reply;
-	int rc, i;
+	int rc;
 	u16 smid;
 	u32 ioc_state;
 	unsigned long timeleft;
@@ -1916,7 +1916,8 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	void *pci_addr_out = NULL;
 	u16 wait_state_count;
 	struct request *rsp = req->next_rq;
-	struct bio_vec *bvec = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 
 	if (!rsp) {
 		printk(MPT2SAS_ERR_FMT "%s: the smp response space is "
@@ -1942,7 +1943,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	ioc->transport_cmds.status = MPT2_CMD_PENDING;
 
 	/* Check if the request is split across multiple segments */
-	if (bio_segments(req->bio) > 1) {
+	if (bio_multiple_segments(req->bio)) {
 		u32 offset = 0;
 
 		/* Allocate memory and copy the request */
@@ -1955,11 +1956,11 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 			goto out;
 		}
 
-		bio_for_each_segment(bvec, req->bio, i) {
+		bio_for_each_segment(bvec, req->bio, iter) {
 			memcpy(pci_addr_out + offset,
-			    page_address(bvec->bv_page) + bvec->bv_offset,
-			    bvec->bv_len);
-			offset += bvec->bv_len;
+			    page_address(bvec.bv_page) + bvec.bv_offset,
+			    bvec.bv_len);
+			offset += bvec.bv_len;
 		}
 	} else {
 		dma_addr_out = pci_map_single(ioc->pdev, bio_data(req->bio),
@@ -1974,7 +1975,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
 	/* Check if the response needs to be populated across
 	 * multiple segments */
-	if (bio_segments(rsp->bio) > 1) {
+	if (bio_multiple_segments(rsp->bio)) {
 		pci_addr_in = pci_alloc_consistent(ioc->pdev, blk_rq_bytes(rsp),
 		    &pci_dma_in);
 		if (!pci_addr_in) {
@@ -2041,7 +2042,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	sgl_flags = (MPI2_SGE_FLAGS_SIMPLE_ELEMENT |
 	    MPI2_SGE_FLAGS_END_OF_BUFFER | MPI2_SGE_FLAGS_HOST_TO_IOC);
 	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	if (bio_segments(req->bio) > 1) {
+	if (bio_multiple_segments(req->bio)) {
 		ioc->base_add_sg_single(psge, sgl_flags |
 		    (blk_rq_bytes(req) - 4), pci_dma_out);
 	} else {
@@ -2057,7 +2058,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	    MPI2_SGE_FLAGS_LAST_ELEMENT | MPI2_SGE_FLAGS_END_OF_BUFFER |
 	    MPI2_SGE_FLAGS_END_OF_LIST);
 	sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
-	if (bio_segments(rsp->bio) > 1) {
+	if (bio_multiple_segments(rsp->bio)) {
 		ioc->base_add_sg_single(psge, sgl_flags |
 		    (blk_rq_bytes(rsp) + 4), pci_dma_in);
 	} else {
@@ -2102,23 +2103,23 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		    le16_to_cpu(mpi_reply->ResponseDataLength);
 		/* check if the resp needs to be copied from the allocated
 		 * pci mem */
-		if (bio_segments(rsp->bio) > 1) {
+		if (bio_multiple_segments(rsp->bio)) {
 			u32 offset = 0;
 			u32 bytes_to_copy =
 			    le16_to_cpu(mpi_reply->ResponseDataLength);
-			bio_for_each_segment(bvec, rsp->bio, i) {
-				if (bytes_to_copy <= bvec->bv_len) {
-					memcpy(page_address(bvec->bv_page) +
-					    bvec->bv_offset, pci_addr_in +
+			bio_for_each_segment(bvec, rsp->bio, iter) {
+				if (bytes_to_copy <= bvec.bv_len) {
+					memcpy(page_address(bvec.bv_page) +
+					    bvec.bv_offset, pci_addr_in +
 					    offset, bytes_to_copy);
 					break;
 				} else {
-					memcpy(page_address(bvec->bv_page) +
-					    bvec->bv_offset, pci_addr_in +
-					    offset, bvec->bv_len);
-					bytes_to_copy -= bvec->bv_len;
+					memcpy(page_address(bvec.bv_page) +
+					    bvec.bv_offset, pci_addr_in +
+					    offset, bvec.bv_len);
+					bytes_to_copy -= bvec.bv_len;
 				}
-				offset += bvec->bv_len;
+				offset += bvec.bv_len;
 			}
 		}
 	} else {

drivers/scsi/mpt3sas/mpt3sas_transport.c

@@ -1884,7 +1884,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
 	Mpi2SmpPassthroughRequest_t *mpi_request;
 	Mpi2SmpPassthroughReply_t *mpi_reply;
-	int rc, i;
+	int rc;
 	u16 smid;
 	u32 ioc_state;
 	unsigned long timeleft;
@@ -1898,7 +1898,8 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	void *pci_addr_out = NULL;
 	u16 wait_state_count;
 	struct request *rsp = req->next_rq;
-	struct bio_vec *bvec = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 
 	if (!rsp) {
 		pr_err(MPT3SAS_FMT "%s: the smp response space is missing\n",
@@ -1925,7 +1926,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	ioc->transport_cmds.status = MPT3_CMD_PENDING;
 
 	/* Check if the request is split across multiple segments */
-	if (req->bio->bi_vcnt > 1) {
+	if (bio_multiple_segments(req->bio)) {
 		u32 offset = 0;
 
 		/* Allocate memory and copy the request */
@@ -1938,11 +1939,11 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 			goto out;
 		}
 
-		bio_for_each_segment(bvec, req->bio, i) {
+		bio_for_each_segment(bvec, req->bio, iter) {
 			memcpy(pci_addr_out + offset,
-			    page_address(bvec->bv_page) + bvec->bv_offset,
-			    bvec->bv_len);
-			offset += bvec->bv_len;
+			    page_address(bvec.bv_page) + bvec.bv_offset,
+			    bvec.bv_len);
+			offset += bvec.bv_len;
 		}
 	} else {
 		dma_addr_out = pci_map_single(ioc->pdev, bio_data(req->bio),
@@ -1957,7 +1958,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
 	/* Check if the response needs to be populated across
 	 * multiple segments */
-	if (rsp->bio->bi_vcnt > 1) {
+	if (bio_multiple_segments(rsp->bio)) {
 		pci_addr_in = pci_alloc_consistent(ioc->pdev, blk_rq_bytes(rsp),
 		    &pci_dma_in);
 		if (!pci_addr_in) {
@@ -2018,7 +2019,7 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 	mpi_request->RequestDataLength = cpu_to_le16(blk_rq_bytes(req) - 4);
 	psge = &mpi_request->SGL;
 
-	if (req->bio->bi_vcnt > 1)
+	if (bio_multiple_segments(req->bio))
 		ioc->build_sg(ioc, psge, pci_dma_out, (blk_rq_bytes(req) - 4),
 		    pci_dma_in, (blk_rq_bytes(rsp) + 4));
 	else
@@ -2063,23 +2064,23 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 
 		/* check if the resp needs to be copied from the allocated
 		 * pci mem */
-		if (rsp->bio->bi_vcnt > 1) {
+		if (bio_multiple_segments(rsp->bio)) {
 			u32 offset = 0;
 			u32 bytes_to_copy =
 			    le16_to_cpu(mpi_reply->ResponseDataLength);
-			bio_for_each_segment(bvec, rsp->bio, i) {
-				if (bytes_to_copy <= bvec->bv_len) {
-					memcpy(page_address(bvec->bv_page) +
-					    bvec->bv_offset, pci_addr_in +
+			bio_for_each_segment(bvec, rsp->bio, iter) {
+				if (bytes_to_copy <= bvec.bv_len) {
+					memcpy(page_address(bvec.bv_page) +
+					    bvec.bv_offset, pci_addr_in +
 					    offset, bytes_to_copy);
 					break;
 				} else {
-					memcpy(page_address(bvec->bv_page) +
-					    bvec->bv_offset, pci_addr_in +
-					    offset, bvec->bv_len);
-					bytes_to_copy -= bvec->bv_len;
+					memcpy(page_address(bvec.bv_page) +
+					    bvec.bv_offset, pci_addr_in +
+					    offset, bvec.bv_len);
+					bytes_to_copy -= bvec.bv_len;
 				}
-				offset += bvec->bv_len;
+				offset += bvec.bv_len;
 			}
 		}
 	} else {

drivers/scsi/osd/osd_initiator.c

@@ -731,7 +731,7 @@ static int _osd_req_list_objects(struct osd_request *or,
 
 	bio->bi_rw &= ~REQ_WRITE;
 	or->in.bio = bio;
-	or->in.total_bytes = bio->bi_size;
+	or->in.total_bytes = bio->bi_iter.bi_size;
 	return 0;
 }
 

drivers/scsi/sd.c

@@ -801,7 +801,7 @@ static int sd_setup_write_same_cmnd(struct scsi_device *sdp, struct request *rq)
 	if (sdkp->device->no_write_same)
 		return BLKPREP_KILL;
 
-	BUG_ON(bio_offset(bio) || bio_iovec(bio)->bv_len != sdp->sector_size);
+	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
 
 	sector >>= ilog2(sdp->sector_size) - 9;
 	nr_sectors >>= ilog2(sdp->sector_size) - 9;

drivers/scsi/sd_dif.c

@@ -365,7 +365,6 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 	struct bio *bio;
 	struct scsi_disk *sdkp;
 	struct sd_dif_tuple *sdt;
-	unsigned int i, j;
 	u32 phys, virt;
 
 	sdkp = rq->bio->bi_bdev->bd_disk->private_data;
@@ -376,19 +375,21 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
 	phys = hw_sector & 0xffffffff;
 
 	__rq_for_each_bio(bio, rq) {
-		struct bio_vec *iv;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+		unsigned int j;
 
 		/* Already remapped? */
 		if (bio_flagged(bio, BIO_MAPPED_INTEGRITY))
 			break;
 
-		virt = bio->bi_integrity->bip_sector & 0xffffffff;
+		virt = bio->bi_integrity->bip_iter.bi_sector & 0xffffffff;
 
-		bip_for_each_vec(iv, bio->bi_integrity, i) {
-			sdt = kmap_atomic(iv->bv_page)
-				+ iv->bv_offset;
+		bip_for_each_vec(iv, bio->bi_integrity, iter) {
+			sdt = kmap_atomic(iv.bv_page)
+				+ iv.bv_offset;
 
-			for (j = 0 ; j < iv->bv_len ; j += tuple_sz, sdt++) {
+			for (j = 0; j < iv.bv_len; j += tuple_sz, sdt++) {
 
 				if (be32_to_cpu(sdt->ref_tag) == virt)
 					sdt->ref_tag = cpu_to_be32(phys);
@@ -414,7 +415,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 	struct scsi_disk *sdkp;
 	struct bio *bio;
 	struct sd_dif_tuple *sdt;
-	unsigned int i, j, sectors, sector_sz;
+	unsigned int j, sectors, sector_sz;
 	u32 phys, virt;
 
 	sdkp = scsi_disk(scmd->request->rq_disk);
@@ -430,15 +431,16 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 		phys >>= 3;
 
 	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_vec *iv;
+		struct bio_vec iv;
+		struct bvec_iter iter;
 
-		virt = bio->bi_integrity->bip_sector & 0xffffffff;
+		virt = bio->bi_integrity->bip_iter.bi_sector & 0xffffffff;
 
-		bip_for_each_vec(iv, bio->bi_integrity, i) {
-			sdt = kmap_atomic(iv->bv_page)
-				+ iv->bv_offset;
+		bip_for_each_vec(iv, bio->bi_integrity, iter) {
+			sdt = kmap_atomic(iv.bv_page)
+				+ iv.bv_offset;
 
-			for (j = 0 ; j < iv->bv_len ; j += tuple_sz, sdt++) {
+			for (j = 0; j < iv.bv_len; j += tuple_sz, sdt++) {
 
 				if (sectors == 0) {
 					kunmap_atomic(sdt);

drivers/staging/lustre/lustre/llite/lloop.c

@@ -194,10 +194,10 @@ static int do_bio_lustrebacked(struct lloop_device *lo, struct bio *head)
 	struct cl_object     *obj = ll_i2info(inode)->lli_clob;
 	pgoff_t	       offset;
 	int		   ret;
-	int		   i;
 	int		   rw;
 	obd_count	     page_count = 0;
-	struct bio_vec       *bvec;
+	struct bio_vec       bvec;
+	struct bvec_iter   iter;
 	struct bio	   *bio;
 	ssize_t	       bytes;
 
@@ -220,15 +220,15 @@ static int do_bio_lustrebacked(struct lloop_device *lo, struct bio *head)
 	for (bio = head; bio != NULL; bio = bio->bi_next) {
 		LASSERT(rw == bio->bi_rw);
 
-		offset = (pgoff_t)(bio->bi_sector << 9) + lo->lo_offset;
-		bio_for_each_segment(bvec, bio, i) {
-			BUG_ON(bvec->bv_offset != 0);
-			BUG_ON(bvec->bv_len != PAGE_CACHE_SIZE);
+		offset = (pgoff_t)(bio->bi_iter.bi_sector << 9) + lo->lo_offset;
+		bio_for_each_segment(bvec, bio, iter) {
+			BUG_ON(bvec.bv_offset != 0);
+			BUG_ON(bvec.bv_len != PAGE_CACHE_SIZE);
 
-			pages[page_count] = bvec->bv_page;
+			pages[page_count] = bvec.bv_page;
 			offsets[page_count] = offset;
 			page_count++;
-			offset += bvec->bv_len;
+			offset += bvec.bv_len;
 		}
 		LASSERT(page_count <= LLOOP_MAX_SEGMENTS);
 	}
@@ -313,7 +313,8 @@ static unsigned int loop_get_bio(struct lloop_device *lo, struct bio **req)
 	bio = &lo->lo_bio;
 	while (*bio && (*bio)->bi_rw == rw) {
 		CDEBUG(D_INFO, "bio sector %llu size %u count %u vcnt%u \n",
-		       (unsigned long long)(*bio)->bi_sector, (*bio)->bi_size,
+		       (unsigned long long)(*bio)->bi_iter.bi_sector,
+		       (*bio)->bi_iter.bi_size,
 		       page_count, (*bio)->bi_vcnt);
 		if (page_count + (*bio)->bi_vcnt > LLOOP_MAX_SEGMENTS)
 			break;
@@ -347,7 +348,8 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 		goto err;
 
 	CDEBUG(D_INFO, "submit bio sector %llu size %u\n",
-	       (unsigned long long)old_bio->bi_sector, old_bio->bi_size);
+	       (unsigned long long)old_bio->bi_iter.bi_sector,
+	       old_bio->bi_iter.bi_size);
 
 	spin_lock_irq(&lo->lo_lock);
 	inactive = (lo->lo_state != LLOOP_BOUND);
@@ -367,7 +369,7 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 	loop_add_bio(lo, old_bio);
 	return;
 err:
-	cfs_bio_io_error(old_bio, old_bio->bi_size);
+	cfs_bio_io_error(old_bio, old_bio->bi_iter.bi_size);
 }
 
 
@@ -378,7 +380,7 @@ static inline void loop_handle_bio(struct lloop_device *lo, struct bio *bio)
 	while (bio) {
 		struct bio *tmp = bio->bi_next;
 		bio->bi_next = NULL;
-		cfs_bio_endio(bio, bio->bi_size, ret);
+		cfs_bio_endio(bio, bio->bi_iter.bi_size, ret);
 		bio = tmp;
 	}
 }

drivers/staging/zram/zram_drv.c

@@ -171,13 +171,14 @@ static inline int valid_io_request(struct zram *zram, struct bio *bio)
 	u64 start, end, bound;
 
 	/* unaligned request */
-	if (unlikely(bio->bi_sector & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+	if (unlikely(bio->bi_iter.bi_sector &
+		     (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
 		return 0;
-	if (unlikely(bio->bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+	if (unlikely(bio->bi_iter.bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
 		return 0;
 
-	start = bio->bi_sector;
-	end = start + (bio->bi_size >> SECTOR_SHIFT);
+	start = bio->bi_iter.bi_sector;
+	end = start + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
 	bound = zram->disksize >> SECTOR_SHIFT;
 	/* out of range range */
 	if (unlikely(start >= bound || end > bound || start > end))
@@ -680,9 +681,10 @@ out:
 
 static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
 {
-	int i, offset;
+	int offset;
 	u32 index;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 
 	switch (rw) {
 	case READ:
@@ -693,36 +695,37 @@ static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
 		break;
 	}
 
-	index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
-	offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
+	index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
+	offset = (bio->bi_iter.bi_sector &
+		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
-	bio_for_each_segment(bvec, bio, i) {
+	bio_for_each_segment(bvec, bio, iter) {
 		int max_transfer_size = PAGE_SIZE - offset;
 
-		if (bvec->bv_len > max_transfer_size) {
+		if (bvec.bv_len > max_transfer_size) {
 			/*
 			 * zram_bvec_rw() can only make operation on a single
 			 * zram page. Split the bio vector.
 			 */
 			struct bio_vec bv;
 
-			bv.bv_page = bvec->bv_page;
+			bv.bv_page = bvec.bv_page;
 			bv.bv_len = max_transfer_size;
-			bv.bv_offset = bvec->bv_offset;
+			bv.bv_offset = bvec.bv_offset;
 
 			if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0)
 				goto out;
 
-			bv.bv_len = bvec->bv_len - max_transfer_size;
+			bv.bv_len = bvec.bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
 			if (zram_bvec_rw(zram, &bv, index+1, 0, bio, rw) < 0)
 				goto out;
 		} else
-			if (zram_bvec_rw(zram, bvec, index, offset, bio, rw)
+			if (zram_bvec_rw(zram, &bvec, index, offset, bio, rw)
 			    < 0)
 				goto out;
 
-		update_position(&index, &offset, bvec);
+		update_position(&index, &offset, &bvec);
 	}
 
 	set_bit(BIO_UPTODATE, &bio->bi_flags);

drivers/target/target_core_iblock.c

@@ -319,7 +319,7 @@ iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num)
 	bio->bi_bdev = ib_dev->ibd_bd;
 	bio->bi_private = cmd;
 	bio->bi_end_io = &iblock_bio_done;
-	bio->bi_sector = lba;
+	bio->bi_iter.bi_sector = lba;
 
 	return bio;
 }

fs/bio-integrity.c

@@ -134,8 +134,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 		return 0;
 	}
 
-	iv = bip_vec_idx(bip, bip->bip_vcnt);
-	BUG_ON(iv == NULL);
+	iv = bip->bip_vec + bip->bip_vcnt;
 
 	iv->bv_page = page;
 	iv->bv_len = len;
@@ -203,6 +202,12 @@ static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
 	return sectors;
 }
 
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
+}
+
 /**
  * bio_integrity_tag_size - Retrieve integrity tag space
  * @bio:	bio to inspect
@@ -215,9 +220,9 @@ unsigned int bio_integrity_tag_size(struct bio *bio)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
-	BUG_ON(bio->bi_size == 0);
+	BUG_ON(bio->bi_iter.bi_size == 0);
 
-	return bi->tag_size * (bio->bi_size / bi->sector_size);
+	return bi->tag_size * (bio->bi_iter.bi_size / bi->sector_size);
 }
 EXPORT_SYMBOL(bio_integrity_tag_size);
 
@@ -235,9 +240,9 @@ int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set)
 	nr_sectors = bio_integrity_hw_sectors(bi,
 					DIV_ROUND_UP(len, bi->tag_size));
 
-	if (nr_sectors * bi->tuple_size > bip->bip_size) {
-		printk(KERN_ERR "%s: tag too big for bio: %u > %u\n",
-		       __func__, nr_sectors * bi->tuple_size, bip->bip_size);
+	if (nr_sectors * bi->tuple_size > bip->bip_iter.bi_size) {
+		printk(KERN_ERR "%s: tag too big for bio: %u > %u\n", __func__,
+		       nr_sectors * bi->tuple_size, bip->bip_iter.bi_size);
 		return -1;
 	}
 
@@ -299,29 +304,30 @@ static void bio_integrity_generate(struct bio *bio)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	struct blk_integrity_exchg bix;
-	struct bio_vec *bv;
-	sector_t sector = bio->bi_sector;
-	unsigned int i, sectors, total;
+	struct bio_vec bv;
+	struct bvec_iter iter;
+	sector_t sector = bio->bi_iter.bi_sector;
+	unsigned int sectors, total;
 	void *prot_buf = bio->bi_integrity->bip_buf;
 
 	total = 0;
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
 
-	bio_for_each_segment(bv, bio, i) {
-		void *kaddr = kmap_atomic(bv->bv_page);
-		bix.data_buf = kaddr + bv->bv_offset;
-		bix.data_size = bv->bv_len;
+	bio_for_each_segment(bv, bio, iter) {
+		void *kaddr = kmap_atomic(bv.bv_page);
+		bix.data_buf = kaddr + bv.bv_offset;
+		bix.data_size = bv.bv_len;
 		bix.prot_buf = prot_buf;
 		bix.sector = sector;
 
 		bi->generate_fn(&bix);
 
-		sectors = bv->bv_len / bi->sector_size;
+		sectors = bv.bv_len / bi->sector_size;
 		sector += sectors;
 		prot_buf += sectors * bi->tuple_size;
 		total += sectors * bi->tuple_size;
-		BUG_ON(total > bio->bi_integrity->bip_size);
+		BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
 
 		kunmap_atomic(kaddr);
 	}
@@ -386,8 +392,8 @@ int bio_integrity_prep(struct bio *bio)
 
 	bip->bip_owns_buf = 1;
 	bip->bip_buf = buf;
-	bip->bip_size = len;
-	bip->bip_sector = bio->bi_sector;
+	bip->bip_iter.bi_size = len;
+	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
 
 	/* Map it */
 	offset = offset_in_page(buf);
@@ -442,16 +448,18 @@ static int bio_integrity_verify(struct bio *bio)
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	struct blk_integrity_exchg bix;
 	struct bio_vec *bv;
-	sector_t sector = bio->bi_integrity->bip_sector;
-	unsigned int i, sectors, total, ret;
+	sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
+	unsigned int sectors, total, ret;
 	void *prot_buf = bio->bi_integrity->bip_buf;
+	int i;
 
 	ret = total = 0;
 	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	bix.sector_size = bi->sector_size;
 
-	bio_for_each_segment(bv, bio, i) {
+	bio_for_each_segment_all(bv, bio, i) {
 		void *kaddr = kmap_atomic(bv->bv_page);
+
 		bix.data_buf = kaddr + bv->bv_offset;
 		bix.data_size = bv->bv_len;
 		bix.prot_buf = prot_buf;
@@ -468,7 +476,7 @@ static int bio_integrity_verify(struct bio *bio)
 		sector += sectors;
 		prot_buf += sectors * bi->tuple_size;
 		total += sectors * bi->tuple_size;
-		BUG_ON(total > bio->bi_integrity->bip_size);
+		BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
 
 		kunmap_atomic(kaddr);
 	}
@@ -495,7 +503,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
-	bio_endio(bio, error);
+	bio_endio_nodec(bio, error);
 }
 
 /**
@@ -532,56 +540,6 @@ void bio_integrity_endio(struct bio *bio, int error)
 }
 EXPORT_SYMBOL(bio_integrity_endio);
 
-/**
- * bio_integrity_mark_head - Advance bip_vec skip bytes
- * @bip:	Integrity vector to advance
- * @skip:	Number of bytes to advance it
- */
-void bio_integrity_mark_head(struct bio_integrity_payload *bip,
-			     unsigned int skip)
-{
-	struct bio_vec *iv;
-	unsigned int i;
-
-	bip_for_each_vec(iv, bip, i) {
-		if (skip == 0) {
-			bip->bip_idx = i;
-			return;
-		} else if (skip >= iv->bv_len) {
-			skip -= iv->bv_len;
-		} else { /* skip < iv->bv_len) */
-			iv->bv_offset += skip;
-			iv->bv_len -= skip;
-			bip->bip_idx = i;
-			return;
-		}
-	}
-}
-
-/**
- * bio_integrity_mark_tail - Truncate bip_vec to be len bytes long
- * @bip:	Integrity vector to truncate
- * @len:	New length of integrity vector
- */
-void bio_integrity_mark_tail(struct bio_integrity_payload *bip,
-			     unsigned int len)
-{
-	struct bio_vec *iv;
-	unsigned int i;
-
-	bip_for_each_vec(iv, bip, i) {
-		if (len == 0) {
-			bip->bip_vcnt = i;
-			return;
-		} else if (len >= iv->bv_len) {
-			len -= iv->bv_len;
-		} else { /* len < iv->bv_len) */
-			iv->bv_len = len;
-			len = 0;
-		}
-	}
-}
-
 /**
  * bio_integrity_advance - Advance integrity vector
  * @bio:	bio whose integrity vector to update
@@ -595,13 +553,9 @@ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 {
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	unsigned int nr_sectors;
+	unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
 
-	BUG_ON(bip == NULL);
-	BUG_ON(bi == NULL);
-
-	nr_sectors = bio_integrity_hw_sectors(bi, bytes_done >> 9);
-	bio_integrity_mark_head(bip, nr_sectors * bi->tuple_size);
+	bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes);
 }
 EXPORT_SYMBOL(bio_integrity_advance);
 
@@ -621,63 +575,12 @@ void bio_integrity_trim(struct bio *bio, unsigned int offset,
 {
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	unsigned int nr_sectors;
-
-	BUG_ON(bip == NULL);
-	BUG_ON(bi == NULL);
-	BUG_ON(!bio_flagged(bio, BIO_CLONED));
 
-	nr_sectors = bio_integrity_hw_sectors(bi, sectors);
-	bip->bip_sector = bip->bip_sector + offset;
-	bio_integrity_mark_head(bip, offset * bi->tuple_size);
-	bio_integrity_mark_tail(bip, sectors * bi->tuple_size);
+	bio_integrity_advance(bio, offset << 9);
+	bip->bip_iter.bi_size = bio_integrity_bytes(bi, sectors);
 }
 EXPORT_SYMBOL(bio_integrity_trim);
 
-/**
- * bio_integrity_split - Split integrity metadata
- * @bio:	Protected bio
- * @bp:		Resulting bio_pair
- * @sectors:	Offset
- *
- * Description: Splits an integrity page into a bio_pair.
- */
-void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors)
-{
-	struct blk_integrity *bi;
-	struct bio_integrity_payload *bip = bio->bi_integrity;
-	unsigned int nr_sectors;
-
-	if (bio_integrity(bio) == 0)
-		return;
-
-	bi = bdev_get_integrity(bio->bi_bdev);
-	BUG_ON(bi == NULL);
-	BUG_ON(bip->bip_vcnt != 1);
-
-	nr_sectors = bio_integrity_hw_sectors(bi, sectors);
-
-	bp->bio1.bi_integrity = &bp->bip1;
-	bp->bio2.bi_integrity = &bp->bip2;
-
-	bp->iv1 = bip->bip_vec[bip->bip_idx];
-	bp->iv2 = bip->bip_vec[bip->bip_idx];
-
-	bp->bip1.bip_vec = &bp->iv1;
-	bp->bip2.bip_vec = &bp->iv2;
-
-	bp->iv1.bv_len = sectors * bi->tuple_size;
-	bp->iv2.bv_offset += sectors * bi->tuple_size;
-	bp->iv2.bv_len -= sectors * bi->tuple_size;
-
-	bp->bip1.bip_sector = bio->bi_integrity->bip_sector;
-	bp->bip2.bip_sector = bio->bi_integrity->bip_sector + nr_sectors;
-
-	bp->bip1.bip_vcnt = bp->bip2.bip_vcnt = 1;
-	bp->bip1.bip_idx = bp->bip2.bip_idx = 0;
-}
-EXPORT_SYMBOL(bio_integrity_split);
-
 /**
  * bio_integrity_clone - Callback for cloning bios with integrity metadata
  * @bio:	New bio
@@ -702,9 +605,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 	memcpy(bip->bip_vec, bip_src->bip_vec,
 	       bip_src->bip_vcnt * sizeof(struct bio_vec));
 
-	bip->bip_sector = bip_src->bip_sector;
 	bip->bip_vcnt = bip_src->bip_vcnt;
-	bip->bip_idx = bip_src->bip_idx;
+	bip->bip_iter = bip_src->bip_iter;
 
 	return 0;
 }

fs/bio.c

@@ -38,8 +38,6 @@
  */
 #define BIO_INLINE_VECS		4
 
-static mempool_t *bio_split_pool __read_mostly;
-
 /*
  * if you change this list, also change bvec_alloc or things will
  * break badly! cannot be bigger than what you can fit into an
@@ -273,6 +271,7 @@ void bio_init(struct bio *bio)
 {
 	memset(bio, 0, sizeof(*bio));
 	bio->bi_flags = 1 << BIO_UPTODATE;
+	atomic_set(&bio->bi_remaining, 1);
 	atomic_set(&bio->bi_cnt, 1);
 }
 EXPORT_SYMBOL(bio_init);
@@ -295,9 +294,35 @@ void bio_reset(struct bio *bio)
 
 	memset(bio, 0, BIO_RESET_BYTES);
 	bio->bi_flags = flags|(1 << BIO_UPTODATE);
+	atomic_set(&bio->bi_remaining, 1);
 }
 EXPORT_SYMBOL(bio_reset);
 
+static void bio_chain_endio(struct bio *bio, int error)
+{
+	bio_endio(bio->bi_private, error);
+	bio_put(bio);
+}
+
+/**
+ * bio_chain - chain bio completions
+ *
+ * The caller won't have a bi_end_io called when @bio completes - instead,
+ * @parent's bi_end_io won't be called until both @parent and @bio have
+ * completed; the chained bio will also be freed when it completes.
+ *
+ * The caller must not set bi_private or bi_end_io in @bio.
+ */
+void bio_chain(struct bio *bio, struct bio *parent)
+{
+	BUG_ON(bio->bi_private || bio->bi_end_io);
+
+	bio->bi_private = parent;
+	bio->bi_end_io	= bio_chain_endio;
+	atomic_inc(&parent->bi_remaining);
+}
+EXPORT_SYMBOL(bio_chain);
+
 static void bio_alloc_rescue(struct work_struct *work)
 {
 	struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
@@ -473,13 +498,13 @@ EXPORT_SYMBOL(bio_alloc_bioset);
 void zero_fill_bio(struct bio *bio)
 {
 	unsigned long flags;
-	struct bio_vec *bv;
-	int i;
+	struct bio_vec bv;
+	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, i) {
-		char *data = bvec_kmap_irq(bv, &flags);
-		memset(data, 0, bv->bv_len);
-		flush_dcache_page(bv->bv_page);
+	bio_for_each_segment(bv, bio, iter) {
+		char *data = bvec_kmap_irq(&bv, &flags);
+		memset(data, 0, bv.bv_len);
+		flush_dcache_page(bv.bv_page);
 		bvec_kunmap_irq(data, &flags);
 	}
 }
@@ -515,51 +540,49 @@ inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
 EXPORT_SYMBOL(bio_phys_segments);
 
 /**
- * 	__bio_clone	-	clone a bio
+ * 	__bio_clone_fast - clone a bio that shares the original bio's biovec
  * 	@bio: destination bio
  * 	@bio_src: bio to clone
  *
  *	Clone a &bio. Caller will own the returned bio, but not
  *	the actual data it points to. Reference count of returned
  * 	bio will be one.
+ *
+ * 	Caller must ensure that @bio_src is not freed before @bio.
  */
-void __bio_clone(struct bio *bio, struct bio *bio_src)
+void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 {
-	memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
-		bio_src->bi_max_vecs * sizeof(struct bio_vec));
+	BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);
 
 	/*
 	 * most users will be overriding ->bi_bdev with a new target,
 	 * so we don't set nor calculate new physical/hw segment counts here
 	 */
-	bio->bi_sector = bio_src->bi_sector;
 	bio->bi_bdev = bio_src->bi_bdev;
 	bio->bi_flags |= 1 << BIO_CLONED;
 	bio->bi_rw = bio_src->bi_rw;
-	bio->bi_vcnt = bio_src->bi_vcnt;
-	bio->bi_size = bio_src->bi_size;
-	bio->bi_idx = bio_src->bi_idx;
+	bio->bi_iter = bio_src->bi_iter;
+	bio->bi_io_vec = bio_src->bi_io_vec;
 }
-EXPORT_SYMBOL(__bio_clone);
+EXPORT_SYMBOL(__bio_clone_fast);
 
 /**
- *	bio_clone_bioset -	clone a bio
+ *	bio_clone_fast - clone a bio that shares the original bio's biovec
  *	@bio: bio to clone
  *	@gfp_mask: allocation priority
  *	@bs: bio_set to allocate from
  *
- * 	Like __bio_clone, only also allocates the returned bio
+ * 	Like __bio_clone_fast, only also allocates the returned bio
  */
-struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
-			     struct bio_set *bs)
+struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 {
 	struct bio *b;
 
-	b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, bs);
+	b = bio_alloc_bioset(gfp_mask, 0, bs);
 	if (!b)
 		return NULL;
 
-	__bio_clone(b, bio);
+	__bio_clone_fast(b, bio);
 
 	if (bio_integrity(bio)) {
 		int ret;
@@ -574,6 +597,74 @@ struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
 
 	return b;
 }
+EXPORT_SYMBOL(bio_clone_fast);
+
+/**
+ * 	bio_clone_bioset - clone a bio
+ * 	@bio_src: bio to clone
+ *	@gfp_mask: allocation priority
+ *	@bs: bio_set to allocate from
+ *
+ *	Clone bio. Caller will own the returned bio, but not the actual data it
+ *	points to. Reference count of returned bio will be one.
+ */
+struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
+			     struct bio_set *bs)
+{
+	unsigned nr_iovecs = 0;
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	struct bio *bio;
+
+	/*
+	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
+	 * bio_src->bi_io_vec to bio->bi_io_vec.
+	 *
+	 * We can't do that anymore, because:
+	 *
+	 *  - The point of cloning the biovec is to produce a bio with a biovec
+	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
+	 *
+	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
+	 *    But the clone should succeed as long as the number of biovecs we
+	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
+	 *
+	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
+	 *    that does not own the bio - reason being drivers don't use it for
+	 *    iterating over the biovec anymore, so expecting it to be kept up
+	 *    to date (i.e. for clones that share the parent biovec) is just
+	 *    asking for trouble and would force extra work on
+	 *    __bio_clone_fast() anyways.
+	 */
+
+	bio_for_each_segment(bv, bio_src, iter)
+		nr_iovecs++;
+
+	bio = bio_alloc_bioset(gfp_mask, nr_iovecs, bs);
+	if (!bio)
+		return NULL;
+
+	bio->bi_bdev		= bio_src->bi_bdev;
+	bio->bi_rw		= bio_src->bi_rw;
+	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
+	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
+
+	bio_for_each_segment(bv, bio_src, iter)
+		bio->bi_io_vec[bio->bi_vcnt++] = bv;
+
+	if (bio_integrity(bio_src)) {
+		int ret;
+
+		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
+		if (ret < 0) {
+			bio_put(bio);
+			return NULL;
+		}
+	}
+
+	return bio;
+}
 EXPORT_SYMBOL(bio_clone_bioset);
 
 /**
@@ -612,7 +703,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	if (unlikely(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
-	if (((bio->bi_size + len) >> 9) > max_sectors)
+	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
 		return 0;
 
 	/*
@@ -635,8 +726,9 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 					   simulate merging updated prev_bvec
 					   as new bvec. */
 					.bi_bdev = bio->bi_bdev,
-					.bi_sector = bio->bi_sector,
-					.bi_size = bio->bi_size - prev_bv_len,
+					.bi_sector = bio->bi_iter.bi_sector,
+					.bi_size = bio->bi_iter.bi_size -
+						prev_bv_len,
 					.bi_rw = bio->bi_rw,
 				};
 
@@ -684,8 +776,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	if (q->merge_bvec_fn) {
 		struct bvec_merge_data bvm = {
 			.bi_bdev = bio->bi_bdev,
-			.bi_sector = bio->bi_sector,
-			.bi_size = bio->bi_size,
+			.bi_sector = bio->bi_iter.bi_sector,
+			.bi_size = bio->bi_iter.bi_size,
 			.bi_rw = bio->bi_rw,
 		};
 
@@ -708,7 +800,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	bio->bi_vcnt++;
 	bio->bi_phys_segments++;
  done:
-	bio->bi_size += len;
+	bio->bi_iter.bi_size += len;
 	return len;
 }
 
@@ -807,28 +899,7 @@ void bio_advance(struct bio *bio, unsigned bytes)
 	if (bio_integrity(bio))
 		bio_integrity_advance(bio, bytes);
 
-	bio->bi_sector += bytes >> 9;
-	bio->bi_size -= bytes;
-
-	if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
-		return;
-
-	while (bytes) {
-		if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
-			WARN_ONCE(1, "bio idx %d >= vcnt %d\n",
-				  bio->bi_idx, bio->bi_vcnt);
-			break;
-		}
-
-		if (bytes >= bio_iovec(bio)->bv_len) {
-			bytes -= bio_iovec(bio)->bv_len;
-			bio->bi_idx++;
-		} else {
-			bio_iovec(bio)->bv_len -= bytes;
-			bio_iovec(bio)->bv_offset += bytes;
-			bytes = 0;
-		}
-	}
+	bio_advance_iter(bio, &bio->bi_iter, bytes);
 }
 EXPORT_SYMBOL(bio_advance);
 
@@ -874,117 +945,80 @@ EXPORT_SYMBOL(bio_alloc_pages);
  */
 void bio_copy_data(struct bio *dst, struct bio *src)
 {
-	struct bio_vec *src_bv, *dst_bv;
-	unsigned src_offset, dst_offset, bytes;
+	struct bvec_iter src_iter, dst_iter;
+	struct bio_vec src_bv, dst_bv;
 	void *src_p, *dst_p;
+	unsigned bytes;
 
-	src_bv = bio_iovec(src);
-	dst_bv = bio_iovec(dst);
-
-	src_offset = src_bv->bv_offset;
-	dst_offset = dst_bv->bv_offset;
+	src_iter = src->bi_iter;
+	dst_iter = dst->bi_iter;
 
 	while (1) {
-		if (src_offset == src_bv->bv_offset + src_bv->bv_len) {
-			src_bv++;
-			if (src_bv == bio_iovec_idx(src, src->bi_vcnt)) {
-				src = src->bi_next;
-				if (!src)
-					break;
-
-				src_bv = bio_iovec(src);
-			}
+		if (!src_iter.bi_size) {
+			src = src->bi_next;
+			if (!src)
+				break;
 
-			src_offset = src_bv->bv_offset;
+			src_iter = src->bi_iter;
 		}
 
-		if (dst_offset == dst_bv->bv_offset + dst_bv->bv_len) {
-			dst_bv++;
-			if (dst_bv == bio_iovec_idx(dst, dst->bi_vcnt)) {
-				dst = dst->bi_next;
-				if (!dst)
-					break;
-
-				dst_bv = bio_iovec(dst);
-			}
+		if (!dst_iter.bi_size) {
+			dst = dst->bi_next;
+			if (!dst)
+				break;
 
-			dst_offset = dst_bv->bv_offset;
+			dst_iter = dst->bi_iter;
 		}
 
-		bytes = min(dst_bv->bv_offset + dst_bv->bv_len - dst_offset,
-			    src_bv->bv_offset + src_bv->bv_len - src_offset);
+		src_bv = bio_iter_iovec(src, src_iter);
+		dst_bv = bio_iter_iovec(dst, dst_iter);
+
+		bytes = min(src_bv.bv_len, dst_bv.bv_len);
 
-		src_p = kmap_atomic(src_bv->bv_page);
-		dst_p = kmap_atomic(dst_bv->bv_page);
+		src_p = kmap_atomic(src_bv.bv_page);
+		dst_p = kmap_atomic(dst_bv.bv_page);
 
-		memcpy(dst_p + dst_offset,
-		       src_p + src_offset,
+		memcpy(dst_p + dst_bv.bv_offset,
+		       src_p + src_bv.bv_offset,
 		       bytes);
 
 		kunmap_atomic(dst_p);
 		kunmap_atomic(src_p);
 
-		src_offset += bytes;
-		dst_offset += bytes;
+		bio_advance_iter(src, &src_iter, bytes);
+		bio_advance_iter(dst, &dst_iter, bytes);
 	}
 }
 EXPORT_SYMBOL(bio_copy_data);
 
 struct bio_map_data {
-	struct bio_vec *iovecs;
-	struct sg_iovec *sgvecs;
 	int nr_sgvecs;
 	int is_our_pages;
+	struct sg_iovec sgvecs[];
 };
 
 static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
 			     struct sg_iovec *iov, int iov_count,
 			     int is_our_pages)
 {
-	memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
 	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
 	bmd->nr_sgvecs = iov_count;
 	bmd->is_our_pages = is_our_pages;
 	bio->bi_private = bmd;
 }
 
-static void bio_free_map_data(struct bio_map_data *bmd)
-{
-	kfree(bmd->iovecs);
-	kfree(bmd->sgvecs);
-	kfree(bmd);
-}
-
 static struct bio_map_data *bio_alloc_map_data(int nr_segs,
 					       unsigned int iov_count,
 					       gfp_t gfp_mask)
 {
-	struct bio_map_data *bmd;
-
 	if (iov_count > UIO_MAXIOV)
 		return NULL;
 
-	bmd = kmalloc(sizeof(*bmd), gfp_mask);
-	if (!bmd)
-		return NULL;
-
-	bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, gfp_mask);
-	if (!bmd->iovecs) {
-		kfree(bmd);
-		return NULL;
-	}
-
-	bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, gfp_mask);
-	if (bmd->sgvecs)
-		return bmd;
-
-	kfree(bmd->iovecs);
-	kfree(bmd);
-	return NULL;
+	return kmalloc(sizeof(struct bio_map_data) +
+		       sizeof(struct sg_iovec) * iov_count, gfp_mask);
 }
 
-static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
-			  struct sg_iovec *iov, int iov_count,
+static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
 			  int to_user, int from_user, int do_free_page)
 {
 	int ret = 0, i;
@@ -994,7 +1028,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		char *bv_addr = page_address(bvec->bv_page);
-		unsigned int bv_len = iovecs[i].bv_len;
+		unsigned int bv_len = bvec->bv_len;
 
 		while (bv_len && iov_idx < iov_count) {
 			unsigned int bytes;
@@ -1054,14 +1088,14 @@ int bio_uncopy_user(struct bio *bio)
 		 * don't copy into a random user address space, just free.
 		 */
 		if (current->mm)
-			ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
-					     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+			ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
+					     bio_data_dir(bio) == READ,
 					     0, bmd->is_our_pages);
 		else if (bmd->is_our_pages)
 			bio_for_each_segment_all(bvec, bio, i)
 				__free_page(bvec->bv_page);
 	}
-	bio_free_map_data(bmd);
+	kfree(bmd);
 	bio_put(bio);
 	return ret;
 }
@@ -1175,7 +1209,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	 */
 	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
 	    (map_data && map_data->from_user)) {
-		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 1, 0);
+		ret = __bio_copy_iov(bio, iov, iov_count, 0, 1, 0);
 		if (ret)
 			goto cleanup;
 	}
@@ -1189,7 +1223,7 @@ cleanup:
 
 	bio_put(bio);
 out_bmd:
-	bio_free_map_data(bmd);
+	kfree(bmd);
 	return ERR_PTR(ret);
 }
 
@@ -1485,7 +1519,7 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 	if (IS_ERR(bio))
 		return bio;
 
-	if (bio->bi_size == len)
+	if (bio->bi_iter.bi_size == len)
 		return bio;
 
 	/*
@@ -1506,16 +1540,15 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		char *addr = page_address(bvec->bv_page);
-		int len = bmd->iovecs[i].bv_len;
 
 		if (read)
-			memcpy(p, addr, len);
+			memcpy(p, addr, bvec->bv_len);
 
 		__free_page(bvec->bv_page);
-		p += len;
+		p += bvec->bv_len;
 	}
 
-	bio_free_map_data(bmd);
+	kfree(bmd);
 	bio_put(bio);
 }
 
@@ -1686,11 +1719,11 @@ void bio_check_pages_dirty(struct bio *bio)
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 void bio_flush_dcache_pages(struct bio *bi)
 {
-	int i;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 
-	bio_for_each_segment(bvec, bi, i)
-		flush_dcache_page(bvec->bv_page);
+	bio_for_each_segment(bvec, bi, iter)
+		flush_dcache_page(bvec.bv_page);
 }
 EXPORT_SYMBOL(bio_flush_dcache_pages);
 #endif
@@ -1711,96 +1744,86 @@ EXPORT_SYMBOL(bio_flush_dcache_pages);
  **/
 void bio_endio(struct bio *bio, int error)
 {
-	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
+	while (bio) {
+		BUG_ON(atomic_read(&bio->bi_remaining) <= 0);
 
-	if (bio->bi_end_io)
-		bio->bi_end_io(bio, error);
-}
-EXPORT_SYMBOL(bio_endio);
+		if (error)
+			clear_bit(BIO_UPTODATE, &bio->bi_flags);
+		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+			error = -EIO;
 
-void bio_pair_release(struct bio_pair *bp)
-{
-	if (atomic_dec_and_test(&bp->cnt)) {
-		struct bio *master = bp->bio1.bi_private;
+		if (!atomic_dec_and_test(&bio->bi_remaining))
+			return;
 
-		bio_endio(master, bp->error);
-		mempool_free(bp, bp->bio2.bi_private);
+		/*
+		 * Need to have a real endio function for chained bios,
+		 * otherwise various corner cases will break (like stacking
+		 * block devices that save/restore bi_end_io) - however, we want
+		 * to avoid unbounded recursion and blowing the stack. Tail call
+		 * optimization would handle this, but compiling with frame
+		 * pointers also disables gcc's sibling call optimization.
+		 */
+		if (bio->bi_end_io == bio_chain_endio) {
+			struct bio *parent = bio->bi_private;
+			bio_put(bio);
+			bio = parent;
+		} else {
+			if (bio->bi_end_io)
+				bio->bi_end_io(bio, error);
+			bio = NULL;
+		}
 	}
 }
-EXPORT_SYMBOL(bio_pair_release);
+EXPORT_SYMBOL(bio_endio);
 
-static void bio_pair_end_1(struct bio *bi, int err)
+/**
+ * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining
+ * @bio:	bio
+ * @error:	error, if any
+ *
+ * For code that has saved and restored bi_end_io; thing hard before using this
+ * function, probably you should've cloned the entire bio.
+ **/
+void bio_endio_nodec(struct bio *bio, int error)
 {
-	struct bio_pair *bp = container_of(bi, struct bio_pair, bio1);
-
-	if (err)
-		bp->error = err;
-
-	bio_pair_release(bp);
+	atomic_inc(&bio->bi_remaining);
+	bio_endio(bio, error);
 }
+EXPORT_SYMBOL(bio_endio_nodec);
 
-static void bio_pair_end_2(struct bio *bi, int err)
-{
-	struct bio_pair *bp = container_of(bi, struct bio_pair, bio2);
-
-	if (err)
-		bp->error = err;
-
-	bio_pair_release(bp);
-}
-
-/*
- * split a bio - only worry about a bio with a single page in its iovec
+/**
+ * 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.
+ *
+ * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
+ * responsibility to ensure that @bio is not freed before the split.
  */
-struct bio_pair *bio_split(struct bio *bi, int first_sectors)
+struct bio *bio_split(struct bio *bio, int sectors,
+		      gfp_t gfp, struct bio_set *bs)
 {
-	struct bio_pair *bp = mempool_alloc(bio_split_pool, GFP_NOIO);
-
-	if (!bp)
-		return bp;
-
-	trace_block_split(bdev_get_queue(bi->bi_bdev), bi,
-				bi->bi_sector + first_sectors);
-
-	BUG_ON(bio_segments(bi) > 1);
-	atomic_set(&bp->cnt, 3);
-	bp->error = 0;
-	bp->bio1 = *bi;
-	bp->bio2 = *bi;
-	bp->bio2.bi_sector += first_sectors;
-	bp->bio2.bi_size -= first_sectors << 9;
-	bp->bio1.bi_size = first_sectors << 9;
-
-	if (bi->bi_vcnt != 0) {
-		bp->bv1 = *bio_iovec(bi);
-		bp->bv2 = *bio_iovec(bi);
-
-		if (bio_is_rw(bi)) {
-			bp->bv2.bv_offset += first_sectors << 9;
-			bp->bv2.bv_len -= first_sectors << 9;
-			bp->bv1.bv_len = first_sectors << 9;
-		}
+	struct bio *split = NULL;
 
-		bp->bio1.bi_io_vec = &bp->bv1;
-		bp->bio2.bi_io_vec = &bp->bv2;
+	BUG_ON(sectors <= 0);
+	BUG_ON(sectors >= bio_sectors(bio));
 
-		bp->bio1.bi_max_vecs = 1;
-		bp->bio2.bi_max_vecs = 1;
-	}
+	split = bio_clone_fast(bio, gfp, bs);
+	if (!split)
+		return NULL;
 
-	bp->bio1.bi_end_io = bio_pair_end_1;
-	bp->bio2.bi_end_io = bio_pair_end_2;
+	split->bi_iter.bi_size = sectors << 9;
 
-	bp->bio1.bi_private = bi;
-	bp->bio2.bi_private = bio_split_pool;
+	if (bio_integrity(split))
+		bio_integrity_trim(split, 0, sectors);
 
-	if (bio_integrity(bi))
-		bio_integrity_split(bi, bp, first_sectors);
+	bio_advance(bio, split->bi_iter.bi_size);
 
-	return bp;
+	return split;
 }
 EXPORT_SYMBOL(bio_split);
 
@@ -1814,80 +1837,20 @@ void bio_trim(struct bio *bio, int offset, int size)
 {
 	/* 'bio' is a cloned bio which we need to trim to match
 	 * the given offset and size.
-	 * This requires adjusting bi_sector, bi_size, and bi_io_vec
 	 */
-	int i;
-	struct bio_vec *bvec;
-	int sofar = 0;
 
 	size <<= 9;
-	if (offset == 0 && size == bio->bi_size)
+	if (offset == 0 && size == bio->bi_iter.bi_size)
 		return;
 
 	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
 
 	bio_advance(bio, offset << 9);
 
-	bio->bi_size = size;
-
-	/* avoid any complications with bi_idx being non-zero*/
-	if (bio->bi_idx) {
-		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
-			(bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
-		bio->bi_vcnt -= bio->bi_idx;
-		bio->bi_idx = 0;
-	}
-	/* Make sure vcnt and last bv are not too big */
-	bio_for_each_segment(bvec, bio, i) {
-		if (sofar + bvec->bv_len > size)
-			bvec->bv_len = size - sofar;
-		if (bvec->bv_len == 0) {
-			bio->bi_vcnt = i;
-			break;
-		}
-		sofar += bvec->bv_len;
-	}
+	bio->bi_iter.bi_size = size;
 }
 EXPORT_SYMBOL_GPL(bio_trim);
 
-/**
- *      bio_sector_offset - Find hardware sector offset in bio
- *      @bio:           bio to inspect
- *      @index:         bio_vec index
- *      @offset:        offset in bv_page
- *
- *      Return the number of hardware sectors between beginning of bio
- *      and an end point indicated by a bio_vec index and an offset
- *      within that vector's page.
- */
-sector_t bio_sector_offset(struct bio *bio, unsigned short index,
-			   unsigned int offset)
-{
-	unsigned int sector_sz;
-	struct bio_vec *bv;
-	sector_t sectors;
-	int i;
-
-	sector_sz = queue_logical_block_size(bio->bi_bdev->bd_disk->queue);
-	sectors = 0;
-
-	if (index >= bio->bi_idx)
-		index = bio->bi_vcnt - 1;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		if (i == index) {
-			if (offset > bv->bv_offset)
-				sectors += (offset - bv->bv_offset) / sector_sz;
-			break;
-		}
-
-		sectors += bv->bv_len / sector_sz;
-	}
-
-	return sectors;
-}
-EXPORT_SYMBOL(bio_sector_offset);
-
 /*
  * create memory pools for biovec's in a bio_set.
  * use the global biovec slabs created for general use.
@@ -2065,11 +2028,6 @@ static int __init init_bio(void)
 	if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
 		panic("bio: can't create integrity pool\n");
 
-	bio_split_pool = mempool_create_kmalloc_pool(BIO_SPLIT_ENTRIES,
-						     sizeof(struct bio_pair));
-	if (!bio_split_pool)
-		panic("bio: can't create split pool\n");
-
 	return 0;
 }
 subsys_initcall(init_bio);

fs/btrfs/check-integrity.c

@@ -1695,7 +1695,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 			return -1;
 		}
 		bio->bi_bdev = block_ctx->dev->bdev;
-		bio->bi_sector = dev_bytenr >> 9;
+		bio->bi_iter.bi_sector = dev_bytenr >> 9;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
@@ -3013,7 +3013,7 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 		int bio_is_patched;
 		char **mapped_datav;
 
-		dev_bytenr = 512 * bio->bi_sector;
+		dev_bytenr = 512 * bio->bi_iter.bi_sector;
 		bio_is_patched = 0;
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
@@ -3021,8 +3021,8 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 			       "submit_bio(rw=0x%x, bi_vcnt=%u,"
 			       " bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
 			       rw, bio->bi_vcnt,
-			       (unsigned long long)bio->bi_sector, dev_bytenr,
-			       bio->bi_bdev);
+			       (unsigned long long)bio->bi_iter.bi_sector,
+			       dev_bytenr, bio->bi_bdev);
 
 		mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt,
 				       GFP_NOFS);