21 files changed, 484 insertions, 457 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index cd0158163fe0..4db2b32b70e0 100644
--- a/block/blk-core.c
+++ b/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);
 
@@ -678,11 +693,20 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	if (!uninit_q)
 		return NULL;
 
+	uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!uninit_q->flush_rq)
+		goto out_cleanup_queue;
+
 	q = blk_init_allocated_queue(uninit_q, rfn, lock);
 	if (!q)
-		blk_cleanup_queue(uninit_q);
-
+		goto out_free_flush_rq;
 	return q;
+
+out_free_flush_rq:
+	kfree(uninit_q->flush_rq);
+out_cleanup_queue:
+	blk_cleanup_queue(uninit_q);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
@@ -1112,7 +1136,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 {
 	if (q->mq_ops)
-		return blk_mq_alloc_request(q, rw, gfp_mask, false);
+		return blk_mq_alloc_request(q, rw, gfp_mask);
 	else
 		return blk_old_get_request(q, rw, gfp_mask);
 }
@@ -1263,6 +1287,11 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	if (unlikely(!q))
 		return;
 
+	if (q->mq_ops) {
+		blk_mq_free_request(req);
+		return;
+	}
+
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
@@ -1326,7 +1355,7 @@ 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 +1380,7 @@ 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 +1409,8 @@ 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 +1488,7 @@ 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 +1612,12 @@ 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 +1683,7 @@ 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 +1719,7 @@ 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 +1733,9 @@ 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 +1894,7 @@ 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 +1903,7 @@ 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 +2036,7 @@ 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 +2407,9 @@ 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 +2757,7 @@ 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 +2775,10 @@ 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
diff --git a/block/blk-exec.c b/block/blk-exec.c
index c3edf9dff566..c68613bb4c79 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -60,8 +60,12 @@ 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);
+		blk_mq_insert_request(q, rq, at_head, true);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index fb6f3c0ffa49..66e2b697f5db 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -130,20 +130,26 @@ static void blk_flush_restore_request(struct request *rq)
 	blk_clear_rq_complete(rq);
 }
 
-static void mq_flush_data_run(struct work_struct *work)
+static void mq_flush_run(struct work_struct *work)
 {
 	struct request *rq;
 
-	rq = container_of(work, struct request, mq_flush_data);
+	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
 	blk_mq_run_request(rq, true, false);
 }
 
-static void blk_mq_flush_data_insert(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq)
 {
-	INIT_WORK(&rq->mq_flush_data, mq_flush_data_run);
-	kblockd_schedule_work(rq->q, &rq->mq_flush_data);
+	if (rq->q->mq_ops) {
+		INIT_WORK(&rq->mq_flush_work, mq_flush_run);
+		kblockd_schedule_work(rq->q, &rq->mq_flush_work);
+		return false;
+	} else {
+		list_add_tail(&rq->queuelist, &rq->q->queue_head);
+		return true;
+	}
 }
 
 /**
@@ -187,12 +193,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		if (q->mq_ops)
-			blk_mq_flush_data_insert(rq);
-		else {
-			list_add(&rq->queuelist, &q->queue_head);
-			queued = true;
-		}
+		queued = blk_flush_queue_rq(rq);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -216,9 +217,6 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 	}
 
 	kicked = blk_kick_flush(q);
-	/* blk_mq_run_flush will run queue */
-	if (q->mq_ops)
-		return queued;
 	return kicked | queued;
 }
 
@@ -230,10 +228,9 @@ static void flush_end_io(struct request *flush_rq, int error)
 	struct request *rq, *n;
 	unsigned long flags = 0;
 
-	if (q->mq_ops) {
-		blk_mq_free_request(flush_rq);
+	if (q->mq_ops)
 		spin_lock_irqsave(&q->mq_flush_lock, flags);
-	}
+
 	running = &q->flush_queue[q->flush_running_idx];
 	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
 
@@ -263,49 +260,14 @@ static void flush_end_io(struct request *flush_rq, int error)
 	 * kblockd.
 	 */
 	if (queued || q->flush_queue_delayed) {
-		if (!q->mq_ops)
-			blk_run_queue_async(q);
-		else
-		/*
-		 * This can be optimized to only run queues with requests
-		 * queued if necessary.
-		 */
-			blk_mq_run_queues(q, true);
+		WARN_ON(q->mq_ops);
+		blk_run_queue_async(q);
 	}
 	q->flush_queue_delayed = 0;
 	if (q->mq_ops)
 		spin_unlock_irqrestore(&q->mq_flush_lock, flags);
 }
 
-static void mq_flush_work(struct work_struct *work)
-{
-	struct request_queue *q;
-	struct request *rq;
-
-	q = container_of(work, struct request_queue, mq_flush_work);
-
-	/* We don't need set REQ_FLUSH_SEQ, it's for consistency */
-	rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ,
-		__GFP_WAIT|GFP_ATOMIC, true);
-	rq->cmd_type = REQ_TYPE_FS;
-	rq->end_io = flush_end_io;
-
-	blk_mq_run_request(rq, true, false);
-}
-
-/*
- * We can't directly use q->flush_rq, because it doesn't have tag and is not in
- * hctx->rqs[]. so we must allocate a new request, since we can't sleep here,
- * so offload the work to workqueue.
- *
- * Note: we assume a flush request finished in any hardware queue will flush
- * the whole disk cache.
- */
-static void mq_run_flush(struct request_queue *q)
-{
-	kblockd_schedule_work(q, &q->mq_flush_work);
-}
-
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
@@ -340,19 +302,31 @@ static bool blk_kick_flush(struct request_queue *q)
 	 * different from running_idx, which means flush is in flight.
 	 */
 	q->flush_pending_idx ^= 1;
+
 	if (q->mq_ops) {
-		mq_run_flush(q);
-		return true;
+		struct blk_mq_ctx *ctx = first_rq->mq_ctx;
+		struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+		blk_mq_rq_init(hctx, q->flush_rq);
+		q->flush_rq->mq_ctx = ctx;
+
+		/*
+		 * Reuse the tag value from the fist waiting request,
+		 * with blk-mq the tag is generated during request
+		 * allocation and drivers can rely on it being inside
+		 * the range they asked for.
+		 */
+		q->flush_rq->tag = first_rq->tag;
+	} else {
+		blk_rq_init(q, q->flush_rq);
 	}
 
-	blk_rq_init(q, &q->flush_rq);
-	q->flush_rq.cmd_type = REQ_TYPE_FS;
-	q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
-	q->flush_rq.rq_disk = first_rq->rq_disk;
-	q->flush_rq.end_io = flush_end_io;
+	q->flush_rq->cmd_type = REQ_TYPE_FS;
+	q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	q->flush_rq->rq_disk = first_rq->rq_disk;
+	q->flush_rq->end_io = flush_end_io;
 
-	list_add_tail(&q->flush_rq.queuelist, &q->queue_head);
-	return true;
+	return blk_flush_queue_rq(q->flush_rq);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
@@ -548,7 +522,7 @@ 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;
@@ -558,5 +532,4 @@ EXPORT_SYMBOL(blkdev_issue_flush);
 void blk_mq_init_flush(struct request_queue *q)
 {
 	spin_lock_init(&q->mq_flush_lock);
-	INIT_WORK(&q->mq_flush_work, mq_flush_work);
 }
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 03cf7179e8ef..7fbab84399e6 100644
--- a/block/blk-integrity.c
+++ b/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;
 	}
 
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9b5b561cb928..97a733cf3d5f 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -108,17 +108,25 @@ 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;
 
 		atomic_inc(&bb.done);
 		submit_bio(type, bio);
+
+		/*
+		 * We can loop for a long time in here, if someone does
+		 * full device discards (like mkfs). Be nice and allow
+		 * us to schedule out to avoid softlocking if preempt
+		 * is disabled.
+		 */
+		cond_resched();
 	}
 	blk_finish_plug(&plug);
 
@@ -174,7 +182,7 @@ 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 +192,11 @@ 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 +248,7 @@ 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;
diff --git a/block/blk-map.c b/block/blk-map.c
index 62382ad5b010..cca6356d216d 100644
--- a/block/blk-map.c
+++ b/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
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 1ffc58977835..6c583f9c5b65 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -12,38 +12,47 @@
 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;
 
+	/*
+	 * This should probably be returning 0, but blk_add_request_payload()
+	 * (Christoph!!!!)
+	 */
+	if (bio->bi_rw & REQ_DISCARD)
+		return 1;
+
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return 1;
+
 	fbio = bio;
 	cluster = blk_queue_cluster(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 +63,7 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
-			seg_size = bv->bv_len;
+			seg_size = bv.bv_len;
 			highprv = high;
 		}
 		bbio = bio;
@@ -87,6 +96,9 @@ 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 +109,40 @@ 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 +168,49 @@ new_segment:
 		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
 		(*nsegs)++;
 	}
-	*bvprv = bvec;
+	*bvprv = *bvec;
+}
+
+static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
+			     struct scatterlist *sglist,
+			     struct scatterlist **sg)
+{
+	struct bio_vec bvec, bvprv = { NULL };
+	struct bvec_iter iter;
+	int nsegs, cluster;
+
+	nsegs = 0;
+	cluster = blk_queue_cluster(q);
+
+	if (bio->bi_rw & REQ_DISCARD) {
+		/*
+		 * This is a hack - drivers should be neither modifying the
+		 * biovec, nor relying on bi_vcnt - but because of
+		 * blk_add_request_payload(), a discard bio may or may not have
+		 * a payload we need to set up here (thank you Christoph) and
+		 * bi_vcnt is really the only way of telling if we need to.
+		 */
+
+		if (bio->bi_vcnt)
+			goto single_segment;
+
+		return 0;
+	}
+
+	if (bio->bi_rw & REQ_WRITE_SAME) {
+single_segment:
+		*sg = sglist;
+		bvec = bio_iovec(bio);
+		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
+		return 1;
+	}
+
+	for_each_bio(bio)
+		bio_for_each_segment(bvec, bio, iter)
+			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
+					     &nsegs, &cluster);
+
+	return nsegs;
 }
 
 /*
@@ -160,24 +220,11 @@ new_segment:
 int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		  struct scatterlist *sglist)
 {
-	struct bio_vec *bvec, *bvprv;
-	struct req_iterator iter;
-	struct scatterlist *sg;
-	int nsegs, cluster;
-
-	nsegs = 0;
-	cluster = blk_queue_cluster(q);
-
-	/*
-	 * 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,
-				     &nsegs, &cluster);
-	} /* segments in rq */
+	struct scatterlist *sg = NULL;
+	int nsegs = 0;
 
+	if (rq->bio)
+		nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
 
 	if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
 	    (blk_rq_bytes(rq) & q->dma_pad_mask)) {
@@ -223,21 +270,13 @@ 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 scatterlist *sg;
-	int nsegs, cluster;
-	unsigned long i;
-
-	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,
-				     &nsegs, &cluster);
-	} /* segments in bio */
+	struct scatterlist *sg = NULL;
+	int nsegs;
+	struct bio *next = bio->bi_next;
+	bio->bi_next = NULL;
 
+	nsegs = __blk_bios_map_sg(q, bio, sglist, &sg);
+	bio->bi_next = next;
 	if (sg)
 		sg_mark_end(sg);
 
@@ -543,9 +582,9 @@ 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;
 }
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 0045ace9bdf0..3146befb56aa 100644
--- a/block/blk-mq-cpu.c
+++ b/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);
 }
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index ba6cf8e9aa0a..b91ce75bd35d 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -335,9 +335,22 @@ static struct kobj_type blk_mq_hw_ktype = {
 void blk_mq_unregister_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	int i, j;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx_for_each_ctx(hctx, ctx, j) {
+			kobject_del(&ctx->kobj);
+			kobject_put(&ctx->kobj);
+		}
+		kobject_del(&hctx->kobj);
+		kobject_put(&hctx->kobj);
+	}
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
+	kobject_put(&q->mq_kobj);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
 }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d64a02fb1f73..83ae96c51a27 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -36,7 +36,8 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
 {
 	int tag;
 
-	tag = percpu_ida_alloc(&tags->free_tags, gfp);
+	tag = percpu_ida_alloc(&tags->free_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag + tags->nr_reserved_tags;
@@ -52,7 +53,8 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = percpu_ida_alloc(&tags->reserved_tags, gfp);
+	tag = percpu_ida_alloc(&tags->reserved_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag;
@@ -182,7 +184,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
 {
 	char *orig_page = page;
-	int cpu;
+	unsigned int cpu;
 
 	if (!tags)
 		return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c79126e11030..1fa9dd153fde 100644
--- a/block/blk-mq.c
+++ b/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)]++;
 }
 
@@ -215,15 +226,14 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 	return rq;
 }
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
-		gfp_t gfp, bool reserved)
+struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp)
 {
 	struct request *rq;
 
 	if (blk_mq_queue_enter(q))
 		return NULL;
 
-	rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved);
+	rq = blk_mq_alloc_request_pinned(q, rw, gfp, false);
 	if (rq)
 		blk_mq_put_ctx(rq->mq_ctx);
 	return rq;
@@ -247,7 +257,7 @@ EXPORT_SYMBOL(blk_mq_alloc_reserved_request);
 /*
  * Re-init and set pdu, if we have it
  */
-static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	blk_rq_init(hctx->queue, rq);
 
@@ -294,7 +304,7 @@ static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
 		bio_endio(bio, error);
 }
 
-void blk_mq_complete_request(struct request *rq, int error)
+void blk_mq_end_io(struct request *rq, int error)
 {
 	struct bio *bio = rq->bio;
 	unsigned int bytes = 0;
@@ -305,7 +315,7 @@ 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;
 	}
@@ -319,87 +329,55 @@ void blk_mq_complete_request(struct request *rq, int error)
 	else
 		blk_mq_free_request(rq);
 }
+EXPORT_SYMBOL(blk_mq_end_io);
 
-void __blk_mq_end_io(struct request *rq, int error)
-{
-	if (!blk_mark_rq_complete(rq))
-		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_complete_request_remote(void *data)
 {
-	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);
-	}
+	struct request *rq = data;
 
-	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;
+	rq->q->softirq_done_fn(rq);
 }
-#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
- * remote CPU.
- */
-void blk_mq_end_io(struct request *rq, int error)
+void __blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	int cpu;
 
-	if (!ctx->ipi_redirect)
-		return __blk_mq_end_io(rq, error);
+	if (!ctx->ipi_redirect) {
+		rq->q->softirq_done_fn(rq);
+		return;
+	}
 
 	cpu = get_cpu();
-
-	if (cpu == ctx->cpu || !cpu_online(ctx->cpu) ||
-	    !ipi_remote_cpu(ctx, cpu, rq, error))
-		__blk_mq_end_io(rq, error);
-
+	if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
+		rq->csd.func = __blk_mq_complete_request_remote;
+		rq->csd.info = rq;
+		rq->csd.flags = 0;
+		__smp_call_function_single(ctx->cpu, &rq->csd, 0);
+	} else {
+		rq->q->softirq_done_fn(rq);
+	}
 	put_cpu();
 }
-EXPORT_SYMBOL(blk_mq_end_io);
 
-static void blk_mq_start_request(struct request *rq)
+/**
+ * blk_mq_complete_request - end I/O on a request
+ * @rq:		the request being processed
+ *
+ * Description:
+ *	Ends all I/O on a request. It does not handle partial completions.
+ *	The actual completion happens out-of-order, through a IPI handler.
+ **/
+void blk_mq_complete_request(struct request *rq)
+{
+	if (unlikely(blk_should_fake_timeout(rq->q)))
+		return;
+	if (!blk_mark_rq_complete(rq))
+		__blk_mq_complete_request(rq);
+}
+EXPORT_SYMBOL(blk_mq_complete_request);
+
+static void blk_mq_start_request(struct request *rq, bool last)
 {
 	struct request_queue *q = rq->q;
 
@@ -412,6 +390,25 @@ static void blk_mq_start_request(struct request *rq)
 	 */
 	rq->deadline = jiffies + q->rq_timeout;
 	set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+	if (q->dma_drain_size && blk_rq_bytes(rq)) {
+		/*
+		 * Make sure space for the drain appears.  We know we can do
+		 * this because max_hw_segments has been adjusted to be one
+		 * fewer than the device can handle.
+		 */
+		rq->nr_phys_segments++;
+	}
+
+	/*
+	 * Flag the last request in the series so that drivers know when IO
+	 * should be kicked off, if they don't do it on a per-request basis.
+	 *
+	 * Note: the flag isn't the only condition drivers should do kick off.
+	 * If drive is busy, the last request might not have the bit set.
+	 */
+	if (last)
+		rq->cmd_flags |= REQ_END;
 }
 
 static void blk_mq_requeue_request(struct request *rq)
@@ -420,6 +417,11 @@ static void blk_mq_requeue_request(struct request *rq)
 
 	trace_block_rq_requeue(q, rq);
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
+
+	rq->cmd_flags &= ~REQ_END;
+
+	if (q->dma_drain_size && blk_rq_bytes(rq))
+		rq->nr_phys_segments--;
 }
 
 struct blk_mq_timeout_data {
@@ -587,19 +589,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_start_request(rq);
 
-		/*
-		 * Last request in the series. Flag it as such, this
-		 * enables drivers to know when IO should be kicked off,
-		 * if they don't do it on a per-request basis.
-		 *
-		 * Note: the flag isn't the only condition drivers
-		 * should do kick off. If drive is busy, the last
-		 * request might not have the bit set.
-		 */
-		if (list_empty(&rq_list))
-			rq->cmd_flags |= REQ_END;
+		blk_mq_start_request(rq, list_empty(&rq_list));
 
 		ret = q->mq_ops->queue_rq(hctx, rq);
 		switch (ret) {
@@ -617,8 +608,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 			break;
 		default:
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
-			rq->errors = -EIO;
 		case BLK_MQ_RQ_QUEUE_ERROR:
+			rq->errors = -EIO;
 			blk_mq_end_io(rq, rq->errors);
 			break;
 		}
@@ -721,13 +712,16 @@ static void blk_mq_work_fn(struct work_struct *work)
 }
 
 static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq)
+				    struct request *rq, bool at_head)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
 	trace_block_rq_insert(hctx->queue, rq);
 
-	list_add_tail(&rq->queuelist, &ctx->rq_list);
+	if (at_head)
+		list_add(&rq->queuelist, &ctx->rq_list);
+	else
+		list_add_tail(&rq->queuelist, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 
 	/*
@@ -737,7 +731,7 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 }
 
 void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool run_queue)
+			   bool at_head, bool run_queue)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx, *current_ctx;
@@ -756,7 +750,7 @@ void blk_mq_insert_request(struct request_queue *q, struct request *rq,
 			rq->mq_ctx = ctx;
 		}
 		spin_lock(&ctx->lock);
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, at_head);
 		spin_unlock(&ctx->lock);
 
 		blk_mq_put_ctx(current_ctx);
@@ -788,7 +782,7 @@ void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
 
 	/* ctx->cpu might be offline */
 	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq);
+	__blk_mq_insert_request(hctx, rq, false);
 	spin_unlock(&ctx->lock);
 
 	blk_mq_put_ctx(current_ctx);
@@ -826,7 +820,7 @@ static void blk_mq_insert_requests(struct request_queue *q,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		rq->mq_ctx = ctx;
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, false);
 	}
 	spin_unlock(&ctx->lock);
 
@@ -916,6 +910,11 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_bounce(q, &bio);
 
+	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
+		bio_endio(bio, -EIO);
+		return;
+	}
+
 	if (use_plug && blk_attempt_plug_merge(q, bio, &request_count))
 		return;
 
@@ -978,7 +977,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		__blk_mq_free_request(hctx, ctx, rq);
 	else {
 		blk_mq_bio_to_request(rq, bio);
-		__blk_mq_insert_request(hctx, rq);
+		__blk_mq_insert_request(hctx, rq, false);
 	}
 
 	spin_unlock(&ctx->lock);
@@ -1091,8 +1090,8 @@ 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 +1155,7 @@ 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;
@@ -1337,15 +1336,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 		reg->queue_depth = BLK_MQ_MAX_DEPTH;
 	}
 
-	/*
-	 * Set aside a tag for flush requests.  It will only be used while
-	 * another flush request is in progress but outside the driver.
-	 *
-	 * TODO: only allocate if flushes are supported
-	 */
-	reg->queue_depth++;
-	reg->reserved_tags++;
-
 	if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN))
 		return ERR_PTR(-EINVAL);
 
@@ -1388,17 +1378,27 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 	q->mq_ops = reg->ops;
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 
+	q->sg_reserved_size = INT_MAX;
+
 	blk_queue_make_request(q, blk_mq_make_request);
 	blk_queue_rq_timed_out(q, reg->ops->timeout);
 	if (reg->timeout)
 		blk_queue_rq_timeout(q, reg->timeout);
 
+	if (reg->ops->complete)
+		blk_queue_softirq_done(q, reg->ops->complete);
+
 	blk_mq_init_flush(q);
 	blk_mq_init_cpu_queues(q, reg->nr_hw_queues);
 
-	if (blk_mq_init_hw_queues(q, reg, driver_data))
+	q->flush_rq = kzalloc(round_up(sizeof(struct request) + reg->cmd_size,
+				cache_line_size()), GFP_KERNEL);
+	if (!q->flush_rq)
 		goto err_hw;
 
+	if (blk_mq_init_hw_queues(q, reg, driver_data))
+		goto err_flush_rq;
+
 	blk_mq_map_swqueue(q);
 
 	mutex_lock(&all_q_mutex);
@@ -1406,6 +1406,9 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg,
 	mutex_unlock(&all_q_mutex);
 
 	return q;
+
+err_flush_rq:
+	kfree(q->flush_rq);
 err_hw:
 	kfree(q->mq_map);
 err_map:
@@ -1429,7 +1432,6 @@ 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 +1453,6 @@ 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 +1496,6 @@ 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() */
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 52bf1f96a2c2..ed0035cd458e 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -22,11 +22,13 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 };
 
-void __blk_mq_end_io(struct request *rq, int error);
-void blk_mq_complete_request(struct request *rq, int error);
+void __blk_mq_complete_request(struct request *rq);
 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);
+void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq);
 
 /*
  * 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
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 05e826793e4e..5d21239bc859 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -592,6 +592,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		ret = -1;
 	}
 
+	t->raid_partial_stripes_expensive =
+		max(t->raid_partial_stripes_expensive,
+		    b->raid_partial_stripes_expensive);
+
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm(t->alignment_offset, alignment)
 		& (max(t->physical_block_size, t->io_min) - 1);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 97779522472f..7500f876dae4 100644
--- a/block/blk-sysfs.c
+++ b/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;
@@ -548,6 +549,8 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
 
+	kfree(q->flush_rq);
+
 	blk_trace_shutdown(q);
 
 	bdi_destroy(&q->backing_dev_info);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 06534049afba..1474c3ab7e72 100644
--- a/block/blk-throttle.c
+++ b/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);
 	}
 }
 
@@ -1303,13 +1303,10 @@ static u64 tg_prfill_cpu_rwstat(struct seq_file *sf,
 	return __blkg_prfill_rwstat(sf, pd, &rwstat);
 }
 
-static int tg_print_cpu_rwstat(struct cgroup_subsys_state *css,
-			       struct cftype *cft, struct seq_file *sf)
+static int tg_print_cpu_rwstat(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, tg_prfill_cpu_rwstat, &blkcg_policy_throtl,
-			  cft->private, true);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_cpu_rwstat,
+			  &blkcg_policy_throtl, seq_cft(sf)->private, true);
 	return 0;
 }
 
@@ -1335,19 +1332,17 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
 	return __blkg_prfill_u64(sf, pd, v);
 }
 
-static int tg_print_conf_u64(struct cgroup_subsys_state *css,
-			     struct cftype *cft, struct seq_file *sf)
+static int tg_print_conf_u64(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_u64,
-			  &blkcg_policy_throtl, cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_u64,
+			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static int tg_print_conf_uint(struct cgroup_subsys_state *css,
-			      struct cftype *cft, struct seq_file *sf)
+static int tg_print_conf_uint(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), tg_prfill_conf_uint,
-			  &blkcg_policy_throtl, cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_uint,
+			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
@@ -1428,40 +1423,40 @@ static struct cftype throtl_files[] = {
 	{
 		.name = "throttle.read_bps_device",
 		.private = offsetof(struct throtl_grp, bps[READ]),
-		.read_seq_string = tg_print_conf_u64,
+		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
-		.read_seq_string = tg_print_conf_u64,
+		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
-		.read_seq_string = tg_print_conf_uint,
+		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
-		.read_seq_string = tg_print_conf_uint,
+		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
 		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.io_service_bytes",
 		.private = offsetof(struct tg_stats_cpu, service_bytes),
-		.read_seq_string = tg_print_cpu_rwstat,
+		.seq_show = tg_print_cpu_rwstat,
 	},
 	{
 		.name = "throttle.io_serviced",
 		.private = offsetof(struct tg_stats_cpu, serviced),
-		.read_seq_string = tg_print_cpu_rwstat,
+		.seq_show = tg_print_cpu_rwstat,
 	},
 	{ }	/* terminate */
 };
@@ -1508,7 +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;
 		}
 	}
@@ -1564,7 +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]);
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index bba81c9348e1..d96f7061c6fd 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -91,7 +91,7 @@ static void blk_rq_timed_out(struct request *req)
 	case BLK_EH_HANDLED:
 		/* Can we use req->errors here? */
 		if (q->mq_ops)
-			blk_mq_complete_request(req, req->errors);
+			__blk_mq_complete_request(req);
 		else
 			__blk_complete_request(req);
 		break;
diff --git a/block/blk.h b/block/blk.h
index c90e1d8f7a2b..d23b415b8a28 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -113,7 +113,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			q->flush_queue_delayed = 1;
 			return NULL;
 		}
-		if (unlikely(blk_queue_dying(q)) ||
+		if (unlikely(blk_queue_bypass(q)) ||
 		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4d5cec1ad80d..744833b630c6 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1632,11 +1632,11 @@ static u64 cfqg_prfill_weight_device(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, cfqg->dev_weight);
 }
 
-static int cfqg_print_weight_device(struct cgroup_subsys_state *css,
-				    struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_weight_device(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_weight_device,
-			  &blkcg_policy_cfq, 0, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_weight_device, &blkcg_policy_cfq,
+			  0, false);
 	return 0;
 }
 
@@ -1650,26 +1650,23 @@ static u64 cfqg_prfill_leaf_weight_device(struct seq_file *sf,
 	return __blkg_prfill_u64(sf, pd, cfqg->dev_leaf_weight);
 }
 
-static int cfqg_print_leaf_weight_device(struct cgroup_subsys_state *css,
-					 struct cftype *cft,
-					 struct seq_file *sf)
+static int cfqg_print_leaf_weight_device(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(css), cfqg_prfill_leaf_weight_device,
-			  &blkcg_policy_cfq, 0, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_leaf_weight_device, &blkcg_policy_cfq,
+			  0, false);
 	return 0;
 }
 
-static int cfq_print_weight(struct cgroup_subsys_state *css, struct cftype *cft,
-			    struct seq_file *sf)
+static int cfq_print_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_weight);
+	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_weight);
 	return 0;
 }
 
-static int cfq_print_leaf_weight(struct cgroup_subsys_state *css,
-				 struct cftype *cft, struct seq_file *sf)
+static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(css)->cfq_leaf_weight);
+	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_leaf_weight);
 	return 0;
 }
 
@@ -1762,23 +1759,17 @@ static int cfq_set_leaf_weight(struct cgroup_subsys_state *css,
 	return __cfq_set_weight(css, cft, val, true);
 }
 
-static int cfqg_print_stat(struct cgroup_subsys_state *css, struct cftype *cft,
-			   struct seq_file *sf)
+static int cfqg_print_stat(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, blkg_prfill_stat, &blkcg_policy_cfq,
-			  cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_cfq, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static int cfqg_print_rwstat(struct cgroup_subsys_state *css,
-			     struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_rwstat(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, blkg_prfill_rwstat, &blkcg_policy_cfq,
-			  cft->private, true);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_cfq, seq_cft(sf)->private, true);
 	return 0;
 }
 
@@ -1798,23 +1789,19 @@ static u64 cfqg_prfill_rwstat_recursive(struct seq_file *sf,
 	return __blkg_prfill_rwstat(sf, pd, &sum);
 }
 
-static int cfqg_print_stat_recursive(struct cgroup_subsys_state *css,
-				     struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_stat_recursive(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_stat_recursive,
-			  &blkcg_policy_cfq, cft->private, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_stat_recursive, &blkcg_policy_cfq,
+			  seq_cft(sf)->private, false);
 	return 0;
 }
 
-static int cfqg_print_rwstat_recursive(struct cgroup_subsys_state *css,
-				       struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_rwstat_recursive,
-			  &blkcg_policy_cfq, cft->private, true);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_rwstat_recursive, &blkcg_policy_cfq,
+			  seq_cft(sf)->private, true);
 	return 0;
 }
 
@@ -1835,13 +1822,11 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf,
 }
 
 /* print avg_queue_size */
-static int cfqg_print_avg_queue_size(struct cgroup_subsys_state *css,
-				     struct cftype *cft, struct seq_file *sf)
+static int cfqg_print_avg_queue_size(struct seq_file *sf, void *v)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
-
-	blkcg_print_blkgs(sf, blkcg, cfqg_prfill_avg_queue_size,
-			  &blkcg_policy_cfq, 0, false);
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  cfqg_prfill_avg_queue_size, &blkcg_policy_cfq,
+			  0, false);
 	return 0;
 }
 #endif	/* CONFIG_DEBUG_BLK_CGROUP */
@@ -1851,14 +1836,14 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "weight_device",
 		.flags = CFTYPE_ONLY_ON_ROOT,
-		.read_seq_string = cfqg_print_leaf_weight_device,
+		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
 		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
 		.flags = CFTYPE_ONLY_ON_ROOT,
-		.read_seq_string = cfq_print_leaf_weight,
+		.seq_show = cfq_print_leaf_weight,
 		.write_u64 = cfq_set_leaf_weight,
 	},
 
@@ -1866,26 +1851,26 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "weight_device",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.read_seq_string = cfqg_print_weight_device,
+		.seq_show = cfqg_print_weight_device,
 		.write_string = cfqg_set_weight_device,
 		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.read_seq_string = cfq_print_weight,
+		.seq_show = cfq_print_weight,
 		.write_u64 = cfq_set_weight,
 	},
 
 	{
 		.name = "leaf_weight_device",
-		.read_seq_string = cfqg_print_leaf_weight_device,
+		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
 		.max_write_len = 256,
 	},
 	{
 		.name = "leaf_weight",
-		.read_seq_string = cfq_print_leaf_weight,
+		.seq_show = cfq_print_leaf_weight,
 		.write_u64 = cfq_set_leaf_weight,
 	},
 
@@ -1893,114 +1878,114 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "time",
 		.private = offsetof(struct cfq_group, stats.time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "sectors",
 		.private = offsetof(struct cfq_group, stats.sectors),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "io_service_bytes",
 		.private = offsetof(struct cfq_group, stats.service_bytes),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_serviced",
 		.private = offsetof(struct cfq_group, stats.serviced),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_service_time",
 		.private = offsetof(struct cfq_group, stats.service_time),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_wait_time",
 		.private = offsetof(struct cfq_group, stats.wait_time),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_merged",
 		.private = offsetof(struct cfq_group, stats.merged),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 	{
 		.name = "io_queued",
 		.private = offsetof(struct cfq_group, stats.queued),
-		.read_seq_string = cfqg_print_rwstat,
+		.seq_show = cfqg_print_rwstat,
 	},
 
 	/* the same statictics which cover the cfqg and its descendants */
 	{
 		.name = "time_recursive",
 		.private = offsetof(struct cfq_group, stats.time),
-		.read_seq_string = cfqg_print_stat_recursive,
+		.seq_show = cfqg_print_stat_recursive,
 	},
 	{
 		.name = "sectors_recursive",
 		.private = offsetof(struct cfq_group, stats.sectors),
-		.read_seq_string = cfqg_print_stat_recursive,
+		.seq_show = cfqg_print_stat_recursive,
 	},
 	{
 		.name = "io_service_bytes_recursive",
 		.private = offsetof(struct cfq_group, stats.service_bytes),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_serviced_recursive",
 		.private = offsetof(struct cfq_group, stats.serviced),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_service_time_recursive",
 		.private = offsetof(struct cfq_group, stats.service_time),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_wait_time_recursive",
 		.private = offsetof(struct cfq_group, stats.wait_time),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_merged_recursive",
 		.private = offsetof(struct cfq_group, stats.merged),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 	{
 		.name = "io_queued_recursive",
 		.private = offsetof(struct cfq_group, stats.queued),
-		.read_seq_string = cfqg_print_rwstat_recursive,
+		.seq_show = cfqg_print_rwstat_recursive,
 	},
 #ifdef CONFIG_DEBUG_BLK_CGROUP
 	{
 		.name = "avg_queue_size",
-		.read_seq_string = cfqg_print_avg_queue_size,
+		.seq_show = cfqg_print_avg_queue_size,
 	},
 	{
 		.name = "group_wait_time",
 		.private = offsetof(struct cfq_group, stats.group_wait_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "idle_time",
 		.private = offsetof(struct cfq_group, stats.idle_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "empty_time",
 		.private = offsetof(struct cfq_group, stats.empty_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "dequeue",
 		.private = offsetof(struct cfq_group, stats.dequeue),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 	{
 		.name = "unaccounted_time",
 		.private = offsetof(struct cfq_group, stats.unaccounted_time),
-		.read_seq_string = cfqg_print_stat,
+		.seq_show = cfqg_print_stat,
 	},
 #endif	/* CONFIG_DEBUG_BLK_CGROUP */
 	{ }	/* terminate */
diff --git a/block/cmdline-parser.c b/block/cmdline-parser.c
index cc2637f8674e..9dbc67e42a99 100644
--- a/block/cmdline-parser.c
+++ b/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);
diff --git a/block/elevator.c b/block/elevator.c
index b7ff2861b6bd..42c45a7d6714 100644
--- a/block/elevator.c
+++ b/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;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 625e3e471d65..26487972ac54 100644
--- a/block/scsi_ioctl.c
+++ b/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;