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;
+	struct bio_vec bvec;
-	int i, dir, len, shift;
+	struct bvec_iter iter;
-	sector_t sec = bio->bi_sector;
+	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) {
+	bio_for_each_segment(bvec, bio, iter) {
-		len = bvec->bv_len;
+		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) {
+	bio_for_each_segment(vec, bio, iter) {
-		if (unlikely(phys_mem + vec->bv_len > phys_end)) {
+		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;
+		phys_mem += vec.bv_len;
-		transfered += 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;
-	struct bio_vec *bvec;
+	struct bvec_iter iter;
-	sector_t sector = bio->bi_sector;
+	sector_t sector = bio->bi_iter.bi_sector;
 
-	bio_for_each_segment(bvec, bio, i) {
+	bio_for_each_segment(bvec, bio, iter) {
-		char *buffer = __bio_kmap_atomic(bio, i);
+		char *buffer = __bio_kmap_atomic(bio, iter);
-		unsigned len = bvec->bv_len >> SECTOR_SHIFT;
+		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);
+	if (q->mq_ops) {
-	__blk_drain_queue(q, true);
+		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->__sector = bio->bi_iter.bi_sector;
-	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);
@@ -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 (prev) {
-			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+			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 (prev) {
-			if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
+			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;
+	struct bio_vec bv, bvprv = { NULL };
-	int cluster, i, high, highprv = 1;
+	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);
+			high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q);
-			if (high || highprv)
+			if (!high && !highprv && cluster) {
-				goto new_segment;
+				if (seg_size + bv.bv_len
-			if (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) {
+	bio_for_each_segment(bvec, bio, iter) {
-		__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+		__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);
+	hotcpu_notifier(blk_mq_main_cpu_notify, 0);
-	blk_mq_register_cpu_notifier(&cpu_notifier);
 }

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)
+	if (drain)
-		return;
+		__blk_mq_drain_queue(q);
+}
 
-	while (true) {
+void blk_mq_drain_queue(struct request_queue *q)
-		s64 count;
+{
-
+	__blk_mq_drain_queue(q);
-		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);
-	}
 }
 
 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;
 	}
@@ -326,56 +337,13 @@ void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_complete_request(rq, error);
 }
 
-#if defined(CONFIG_SMP)
+static void blk_mq_end_io_remote(void *data)
-
-/*
- * Called with interrupts disabled.
- */
-static void ipi_end_io(void *data)
 {
-	struct llist_head *list = &per_cpu(ipi_lists, smp_processor_id());
+	struct request *rq = data;
-	struct llist_node *entry, *next;
-	struct request *rq;
 
-	entry = llist_del_all(list);
+	__blk_mq_end_io(rq, rq->errors);
-
-	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)
-{
-	struct call_single_data *data = &rq->csd;
-
-	rq->errors = error;
-	rq->ll_list.next = NULL;
-
-	/*
-	 * 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;
-}
-#endif
-
 /*
  * End IO on this request on a multiqueue enabled driver. We'll either do
  * it directly inline, or punt to a local IPI handler on the matching
@@ -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)) {
-	if (cpu == ctx->cpu || !cpu_online(ctx->cpu) ||
+		rq->errors = error;
-	    !ipi_remote_cpu(ctx, cpu, rq, 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);
+		page = list_first_entry(&hctx->page_list, struct page, lru);
-		list_del_init(&page->list);
+		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,
+		throtl_update_dispatch_stats(tg_to_blkg(tg),
-					     bio->bi_rw);
+					     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/export.h>
-#include <linux/module.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 cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size,
-		       int slot,
+		      int slot,
-		       int (*add_part)(int, struct cmdline_subpart *, void *),
+		      int (*add_part)(int, struct cmdline_subpart *, void *),
-		       void *param)
+		      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;