1 files changed, 456 insertions, 206 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index c973249d68c..6f8dba161bf 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -16,6 +16,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/kernel_stat.h>
@@ -30,16 +31,19 @@
 #include <linux/list_sort.h>
 #include <linux/delay.h>
 #include <linux/ratelimit.h>
+#include <linux/pm_runtime.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
 
 #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);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 
 DEFINE_IDA(blk_queue_ida);
@@ -47,7 +51,7 @@ DEFINE_IDA(blk_queue_ida);
 /*
  * For the allocated request tables
  */
-static struct kmem_cache *request_cachep;
+struct kmem_cache *request_cachep = NULL;
 
 /*
  * For queue allocation
@@ -59,42 +63,6 @@ struct kmem_cache *blk_requestq_cachep;
  */
 static struct workqueue_struct *kblockd_workqueue;
 
-static void drive_stat_acct(struct request *rq, int new_io)
-{
-	struct hd_struct *part;
-	int rw = rq_data_dir(rq);
-	int cpu;
-
-	if (!blk_do_io_stat(rq))
-		return;
-
-	cpu = part_stat_lock();
-
-	if (!new_io) {
-		part = rq->part;
-		part_stat_inc(cpu, part, merges[rw]);
-	} else {
-		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
-		if (!hd_struct_try_get(part)) {
-			/*
-			 * The partition is already being removed,
-			 * the request will be accounted on the disk only
-			 *
-			 * We take a reference on disk->part0 although that
-			 * partition will never be deleted, so we can treat
-			 * it as any other partition.
-			 */
-			part = &rq->rq_disk->part0;
-			hd_struct_get(part);
-		}
-		part_round_stats(cpu, part);
-		part_inc_in_flight(part, rw);
-		rq->part = part;
-	}
-
-	part_stat_unlock();
-}
-
 void blk_queue_congestion_threshold(struct request_queue *q)
 {
 	int nr;
@@ -144,7 +112,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->cmd = rq->__cmd;
 	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
-	rq->ref_count = 1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
@@ -159,23 +126,13 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
 
-	if (unlikely(nbytes > bio->bi_size)) {
-		printk(KERN_ERR "%s: want %u bytes done, %u left\n",
-		       __func__, nbytes, bio->bi_size);
-		nbytes = bio->bi_size;
-	}
-
 	if (unlikely(rq->cmd_flags & REQ_QUIET))
 		set_bit(BIO_QUIET, &bio->bi_flags);
 
-	bio->bi_size -= nbytes;
-	bio->bi_sector += (nbytes >> 9);
-
-	if (bio_integrity(bio))
-		bio_integrity_advance(bio, nbytes);
+	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);
 }
 
@@ -183,15 +140,15 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 {
 	int bit;
 
-	printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
+	printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
 		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
-		rq->cmd_flags);
+		(unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
 	       (unsigned long long)blk_rq_pos(rq),
 	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
-	printk(KERN_INFO "  bio %p, biotail %p, buffer %p, len %u\n",
-	       rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
+	printk(KERN_INFO "  bio %p, biotail %p, len %u\n",
+	       rq->bio, rq->biotail, blk_rq_bytes(rq));
 
 	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		printk(KERN_INFO "  cdb: ");
@@ -290,7 +247,18 @@ 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->run_work);
+			cancel_delayed_work_sync(&hctx->delay_work);
+		}
+	} else {
+		cancel_delayed_work_sync(&q->delay_work);
+	}
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
@@ -542,8 +510,13 @@ 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);
 
@@ -653,11 +626,15 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	q->bypass_depth = 1;
 	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
 
+	init_waitqueue_head(&q->mq_freeze_wq);
+
 	if (blkcg_init_queue(q))
-		goto fail_id;
+		goto fail_bdi;
 
 	return q;
 
+fail_bdi:
+	bdi_destroy(&q->backing_dev_info);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
 fail_q:
@@ -729,9 +706,13 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!q->flush_rq)
 		return NULL;
 
+	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+		goto fail;
+
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -748,10 +729,22 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 
 	q->sg_reserved_size = INT_MAX;
 
+	/* Protect q->elevator from elevator_change */
+	mutex_lock(&q->sysfs_lock);
+
 	/* init elevator */
-	if (elevator_init(q, NULL))
-		return NULL;
+	if (elevator_init(q, NULL)) {
+		mutex_unlock(&q->sysfs_lock);
+		goto fail;
+	}
+
+	mutex_unlock(&q->sysfs_lock);
+
 	return q;
+
+fail:
+	kfree(q->flush_rq);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -851,6 +844,47 @@ static void freed_request(struct request_list *rl, unsigned int flags)
 		__freed_request(rl, sync ^ 1);
 }
 
+int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
+{
+	struct request_list *rl;
+
+	spin_lock_irq(q->queue_lock);
+	q->nr_requests = nr;
+	blk_queue_congestion_threshold(q);
+
+	/* congestion isn't cgroup aware and follows root blkcg for now */
+	rl = &q->root_rl;
+
+	if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_SYNC);
+	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_SYNC);
+
+	if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
+		blk_set_queue_congested(q, BLK_RW_ASYNC);
+	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
+		blk_clear_queue_congested(q, BLK_RW_ASYNC);
+
+	blk_queue_for_each_rl(rl, q) {
+		if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
+			blk_set_rl_full(rl, BLK_RW_SYNC);
+		} else {
+			blk_clear_rl_full(rl, BLK_RW_SYNC);
+			wake_up(&rl->wait[BLK_RW_SYNC]);
+		}
+
+		if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+			blk_set_rl_full(rl, BLK_RW_ASYNC);
+		} else {
+			blk_clear_rl_full(rl, BLK_RW_ASYNC);
+			wake_up(&rl->wait[BLK_RW_ASYNC]);
+		}
+	}
+
+	spin_unlock_irq(q->queue_lock);
+	return 0;
+}
+
 /*
  * Determine if elevator data should be initialized when allocating the
  * request associated with @bio.
@@ -1118,7 +1152,8 @@ retry:
 	goto retry;
 }
 
-struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+static struct request *blk_old_get_request(struct request_queue *q, int rw,
+		gfp_t gfp_mask)
 {
 	struct request *rq;
 
@@ -1135,6 +1170,14 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 
 	return rq;
 }
+
+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);
+	else
+		return blk_old_get_request(q, rw, gfp_mask);
+}
 EXPORT_SYMBOL(blk_get_request);
 
 /**
@@ -1176,6 +1219,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 	if (unlikely(!rq))
 		return ERR_PTR(-ENOMEM);
 
+	blk_rq_set_block_pc(rq);
+
 	for_each_bio(bio) {
 		struct bio *bounce_bio = bio;
 		int ret;
@@ -1193,6 +1238,22 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 EXPORT_SYMBOL(blk_make_request);
 
 /**
+ * blk_rq_set_block_pc - initialize a requeest to type BLOCK_PC
+ * @rq:		request to be initialized
+ *
+ */
+void blk_rq_set_block_pc(struct request *rq)
+{
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
+	memset(rq->__cmd, 0, sizeof(rq->__cmd));
+	rq->cmd = rq->__cmd;
+}
+EXPORT_SYMBOL(blk_rq_set_block_pc);
+
+/**
  * blk_requeue_request - put a request back on queue
  * @q:		request queue where request should be inserted
  * @rq:		request to be inserted
@@ -1220,19 +1281,22 @@ EXPORT_SYMBOL(blk_requeue_request);
 static void add_acct_request(struct request_queue *q, struct request *rq,
 			     int where)
 {
-	drive_stat_acct(rq, 1);
+	blk_account_io_start(rq, true);
 	__elv_add_request(q, rq, where);
 }
 
 static void part_round_stats_single(int cpu, struct hd_struct *part,
 				    unsigned long now)
 {
+	int inflight;
+
 	if (now == part->stamp)
 		return;
 
-	if (part_in_flight(part)) {
+	inflight = part_in_flight(part);
+	if (inflight) {
 		__part_stat_add(cpu, part, time_in_queue,
-				part_in_flight(part) * (now - part->stamp));
+				inflight * (now - part->stamp));
 		__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
 	}
 	part->stamp = now;
@@ -1264,6 +1328,16 @@ void part_round_stats(int cpu, struct hd_struct *part)
 }
 EXPORT_SYMBOL_GPL(part_round_stats);
 
+#ifdef CONFIG_PM_RUNTIME
+static void blk_pm_put_request(struct request *rq)
+{
+	if (rq->q->dev && !(rq->cmd_flags & REQ_PM) && !--rq->q->nr_pending)
+		pm_runtime_mark_last_busy(rq->q->dev);
+}
+#else
+static inline void blk_pm_put_request(struct request *rq) {}
+#endif
+
 /*
  * queue lock must be held
  */
@@ -1271,8 +1345,13 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 {
 	if (unlikely(!q))
 		return;
-	if (unlikely(--req->ref_count))
+
+	if (q->mq_ops) {
+		blk_mq_free_request(req);
 		return;
+	}
+
+	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
 
@@ -1288,7 +1367,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
-		BUG_ON(!hlist_unhashed(&req->hash));
+		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
 		freed_request(rl, flags);
@@ -1299,12 +1378,17 @@ EXPORT_SYMBOL_GPL(__blk_put_request);
 
 void blk_put_request(struct request *req)
 {
-	unsigned long flags;
 	struct request_queue *q = req->q;
 
-	spin_lock_irqsave(q->queue_lock, flags);
-	__blk_put_request(q, req);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	if (q->mq_ops)
+		blk_mq_free_request(req);
+	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		__blk_put_request(q, req);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
 }
 EXPORT_SYMBOL(blk_put_request);
 
@@ -1330,47 +1414,46 @@ 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;
 
 	rq->__data_len = rq->resid_len = len;
 	rq->nr_phys_segments = 1;
-	rq->buffer = bio_data(bio);
 }
 EXPORT_SYMBOL_GPL(blk_add_request_payload);
 
-static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
-				   struct bio *bio)
+bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
+			    struct bio *bio)
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
 	if (!ll_back_merge_fn(q, req, bio))
 		return false;
 
-	trace_block_bio_backmerge(q, bio);
+	trace_block_bio_backmerge(q, req, bio);
 
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(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));
 
-	drive_stat_acct(req, 0);
+	blk_account_io_start(req, false);
 	return true;
 }
 
-static bool bio_attempt_front_merge(struct request_queue *q,
-				    struct request *req, struct bio *bio)
+bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
+			     struct bio *bio)
 {
 	const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 
 	if (!ll_front_merge_fn(q, req, bio))
 		return false;
 
-	trace_block_bio_frontmerge(q, bio);
+	trace_block_bio_frontmerge(q, req, bio);
 
 	if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
 		blk_rq_set_mixed_merge(req);
@@ -1378,22 +1461,16 @@ static bool bio_attempt_front_merge(struct request_queue *q,
 	bio->bi_next = req->bio;
 	req->bio = bio;
 
-	/*
-	 * may not be valid. if the low level driver said
-	 * it didn't need a bounce buffer then it better
-	 * 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));
 
-	drive_stat_acct(req, 0);
+	blk_account_io_start(req, false);
 	return true;
 }
 
 /**
- * attempt_plug_merge - try to merge with %current's plugged list
+ * blk_attempt_plug_merge - try to merge with %current's plugged list
  * @q: request_queue new bio is being queued at
  * @bio: new bio being queued
  * @request_count: out parameter for number of traversed plugged requests
@@ -1408,20 +1485,28 @@ static bool bio_attempt_front_merge(struct request_queue *q,
  * added on the elevator at this point.  In addition, we don't have
  * reliable access to the elevator outside queue lock.  Only check basic
  * merging parameters without querying the elevator.
+ *
+ * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
-static bool attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			       unsigned int *request_count)
+bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
+			    unsigned int *request_count)
 {
 	struct blk_plug *plug;
 	struct request *rq;
 	bool ret = false;
+	struct list_head *plug_list;
 
 	plug = current->plug;
 	if (!plug)
 		goto out;
 	*request_count = 0;
 
-	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
+	if (q->mq_ops)
+		plug_list = &plug->mq_list;
+	else
+		plug_list = &plug->list;
+
+	list_for_each_entry_reverse(rq, plug_list, queuelist) {
 		int el_ret;
 
 		if (rq->q == q)
@@ -1454,7 +1539,7 @@ 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);
 }
@@ -1474,6 +1559,11 @@ void blk_queue_bio(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 (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
@@ -1484,7 +1574,8 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (attempt_plug_merge(q, bio, &request_count))
+	if (!blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1541,27 +1632,18 @@ get_rq:
 	if (plug) {
 		/*
 		 * If this is the first request added after a plug, fire
-		 * of a plug trace. If others have been added before, check
-		 * if we have multiple devices in this plug. If so, make a
-		 * note to sort the list before dispatch.
+		 * of a plug trace.
 		 */
-		if (list_empty(&plug->list))
+		if (!request_count)
 			trace_block_plug(q);
 		else {
-			if (!plug->should_sort) {
-				struct request *__rq;
-
-				__rq = list_entry_rq(plug->list.prev);
-				if (__rq->q != q)
-					plug->should_sort = 1;
-			}
 			if (request_count >= BLK_MAX_REQUEST_COUNT) {
 				blk_flush_plug_list(plug, false);
 				trace_block_plug(q);
 			}
 		}
 		list_add_tail(&req->queuelist, &plug->list);
-		drive_stat_acct(req, 1);
+		blk_account_io_start(req, true);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
@@ -1582,12 +1664,12 @@ 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);
 	}
 }
 
@@ -1599,7 +1681,7 @@ static void handle_bad_sector(struct bio *bio)
 	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
 			bio->bi_rw,
-			(unsigned long long)bio->bi_sector + bio_sectors(bio),
+			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 
 	set_bit(BIO_EOF, &bio->bi_flags);
@@ -1625,7 +1707,7 @@ static int __init fail_make_request_debugfs(void)
 	struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
 						NULL, &fail_make_request);
 
-	return IS_ERR(dir) ? PTR_ERR(dir) : 0;
+	return PTR_ERR_OR_ZERO(dir);
 }
 
 late_initcall(fail_make_request_debugfs);
@@ -1653,7 +1735,7 @@ 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) {
 			/*
@@ -1689,7 +1771,7 @@ 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;
 	}
 
@@ -1703,9 +1785,9 @@ 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;
 
 	/*
@@ -1714,9 +1796,6 @@ generic_make_request_checks(struct bio *bio)
 	 */
 	blk_partition_remap(bio);
 
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
-		goto end_io;
-
 	if (bio_check_eod(bio, nr_sectors))
 		goto end_io;
 
@@ -1867,7 +1946,7 @@ 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);
 		}
 
@@ -1876,7 +1955,7 @@ 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);
 		}
@@ -1902,7 +1981,7 @@ EXPORT_SYMBOL(submit_bio);
  *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
  *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests agaist
+ *    Such request stacking drivers should check those requests against
  *    the new queue limits again when they dispatch those requests,
  *    although such checkings are also done against the old queue limits
  *    when submitting requests.
@@ -2009,7 +2088,7 @@ 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 */
@@ -2018,7 +2097,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
-static void blk_account_io_completion(struct request *req, unsigned int bytes)
+void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
 		const int rw = rq_data_dir(req);
@@ -2032,7 +2111,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 	}
 }
 
-static void blk_account_io_done(struct request *req)
+void blk_account_io_done(struct request *req)
 {
 	/*
 	 * Account IO completion.  flush_rq isn't accounted as a
@@ -2058,6 +2137,64 @@ static void blk_account_io_done(struct request *req)
 	}
 }
 
+#ifdef CONFIG_PM_RUNTIME
+/*
+ * Don't process normal requests when queue is suspended
+ * or in the process of suspending/resuming
+ */
+static struct request *blk_pm_peek_request(struct request_queue *q,
+					   struct request *rq)
+{
+	if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
+	    (q->rpm_status != RPM_ACTIVE && !(rq->cmd_flags & REQ_PM))))
+		return NULL;
+	else
+		return rq;
+}
+#else
+static inline struct request *blk_pm_peek_request(struct request_queue *q,
+						  struct request *rq)
+{
+	return rq;
+}
+#endif
+
+void blk_account_io_start(struct request *rq, bool new_io)
+{
+	struct hd_struct *part;
+	int rw = rq_data_dir(rq);
+	int cpu;
+
+	if (!blk_do_io_stat(rq))
+		return;
+
+	cpu = part_stat_lock();
+
+	if (!new_io) {
+		part = rq->part;
+		part_stat_inc(cpu, part, merges[rw]);
+	} else {
+		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
+		if (!hd_struct_try_get(part)) {
+			/*
+			 * The partition is already being removed,
+			 * the request will be accounted on the disk only
+			 *
+			 * We take a reference on disk->part0 although that
+			 * partition will never be deleted, so we can treat
+			 * it as any other partition.
+			 */
+			part = &rq->rq_disk->part0;
+			hd_struct_get(part);
+		}
+		part_round_stats(cpu, part);
+		part_inc_in_flight(part, rw);
+		rq->part = part;
+	}
+
+	part_stat_unlock();
+}
+
 /**
  * blk_peek_request - peek at the top of a request queue
  * @q: request queue to peek at
@@ -2080,6 +2217,11 @@ struct request *blk_peek_request(struct request_queue *q)
 	int ret;
 
 	while ((rq = __elv_next_request(q)) != NULL) {
+
+		rq = blk_pm_peek_request(q, rq);
+		if (!rq)
+			break;
+
 		if (!(rq->cmd_flags & REQ_STARTED)) {
 			/*
 			 * This is the first time the device driver
@@ -2204,6 +2346,7 @@ void blk_start_request(struct request *req)
 	if (unlikely(blk_bidi_rq(req)))
 		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
 
+	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 	blk_add_timer(req);
 }
 EXPORT_SYMBOL(blk_start_request);
@@ -2258,13 +2401,12 @@ EXPORT_SYMBOL(blk_fetch_request);
  **/
 bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
-	int total_bytes, bio_nbytes, next_idx = 0;
-	struct bio *bio;
+	int total_bytes;
 
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's
@@ -2291,6 +2433,15 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		case -EBADE:
 			error_type = "critical nexus";
 			break;
+		case -ETIMEDOUT:
+			error_type = "timeout";
+			break;
+		case -ENOSPC:
+			error_type = "critical space allocation";
+			break;
+		case -ENODATA:
+			error_type = "critical medium";
+			break;
 		case -EIO:
 		default:
 			error_type = "I/O";
@@ -2305,56 +2456,21 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 
 	blk_account_io_completion(req, nr_bytes);
 
-	total_bytes = bio_nbytes = 0;
-	while ((bio = req->bio) != NULL) {
-		int nbytes;
+	total_bytes = 0;
+	while (req->bio) {
+		struct bio *bio = req->bio;
+		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (nr_bytes >= bio->bi_size) {
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
-			nbytes = bio->bi_size;
-			req_bio_endio(req, bio, nbytes, error);
-			next_idx = 0;
-			bio_nbytes = 0;
-		} else {
-			int idx = bio->bi_idx + next_idx;
 
-			if (unlikely(idx >= bio->bi_vcnt)) {
-				blk_dump_rq_flags(req, "__end_that");
-				printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
-				       __func__, idx, bio->bi_vcnt);
-				break;
-			}
+		req_bio_endio(req, bio, bio_bytes, error);
 
-			nbytes = bio_iovec_idx(bio, idx)->bv_len;
-			BIO_BUG_ON(nbytes > bio->bi_size);
-
-			/*
-			 * not a complete bvec done
-			 */
-			if (unlikely(nbytes > nr_bytes)) {
-				bio_nbytes += nr_bytes;
-				total_bytes += nr_bytes;
-				break;
-			}
+		total_bytes += bio_bytes;
+		nr_bytes -= bio_bytes;
 
-			/*
-			 * advance to the next vector
-			 */
-			next_idx++;
-			bio_nbytes += nbytes;
-		}
-
-		total_bytes += nbytes;
-		nr_bytes -= nbytes;
-
-		bio = req->bio;
-		if (bio) {
-			/*
-			 * end more in this run, or just return 'not-done'
-			 */
-			if (unlikely(nr_bytes <= 0))
-				break;
-		}
+		if (!nr_bytes)
+			break;
 	}
 
 	/*
@@ -2370,18 +2486,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		return false;
 	}
 
-	/*
-	 * if the request wasn't completed, update state
-	 */
-	if (bio_nbytes) {
-		req_bio_endio(req, bio, bio_nbytes, error);
-		bio->bi_idx += next_idx;
-		bio_iovec(bio)->bv_offset += nr_bytes;
-		bio_iovec(bio)->bv_len -= nr_bytes;
-	}
-
 	req->__data_len -= total_bytes;
-	req->buffer = bio_data(req->bio);
 
 	/* update sector only for requests with clear definition of sector */
 	if (req->cmd_type == REQ_TYPE_FS)
@@ -2450,7 +2555,7 @@ EXPORT_SYMBOL_GPL(blk_unprep_request);
 /*
  * queue lock must be held
  */
-static void blk_finish_request(struct request *req, int error)
+void blk_finish_request(struct request *req, int error)
 {
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
@@ -2465,7 +2570,6 @@ static void blk_finish_request(struct request *req, int error)
 	if (req->cmd_flags & REQ_DONTPREP)
 		blk_unprep_request(req);
 
-
 	blk_account_io_done(req);
 
 	if (req->end_io)
@@ -2477,6 +2581,7 @@ static void blk_finish_request(struct request *req, int error)
 		__blk_put_request(req->q, req);
 	}
 }
+EXPORT_SYMBOL(blk_finish_request);
 
 /**
  * blk_end_bidi_request - Complete a bidi request
@@ -2700,11 +2805,10 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
 	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
 
-	if (bio_has_data(bio)) {
+	if (bio_has_data(bio))
 		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)
@@ -2722,10 +2826,10 @@ 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
@@ -2779,7 +2883,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 
 /*
  * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
+ * The actual data parts (e.g. ->cmd, ->sense) are not copied.
  */
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
@@ -2805,7 +2909,7 @@ static void __blk_rq_prep_clone(struct request *dst, struct request *src)
  *
  * Description:
  *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- *     The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
+ *     The actual data parts of @rq_src (e.g. ->cmd, ->sense)
  *     are not copied, and copying such parts is the caller's responsibility.
  *     Also, pages which the original bios are pointing to are not copied
  *     and the cloned bios just point same pages.
@@ -2852,20 +2956,25 @@ free_and_out:
 }
 EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
 
-int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
+int kblockd_schedule_work(struct work_struct *work)
 {
 	return queue_work(kblockd_workqueue, work);
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
-int kblockd_schedule_delayed_work(struct request_queue *q,
-			struct delayed_work *dwork, unsigned long delay)
+int kblockd_schedule_delayed_work(struct delayed_work *dwork,
+				  unsigned long delay)
 {
 	return queue_delayed_work(kblockd_workqueue, dwork, delay);
 }
 EXPORT_SYMBOL(kblockd_schedule_delayed_work);
 
-#define PLUG_MAGIC	0x91827364
+int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork,
+				     unsigned long delay)
+{
+	return queue_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_schedule_delayed_work_on);
 
 /**
  * blk_start_plug - initialize blk_plug and track it inside the task_struct
@@ -2885,10 +2994,9 @@ void blk_start_plug(struct blk_plug *plug)
 {
 	struct task_struct *tsk = current;
 
-	plug->magic = PLUG_MAGIC;
 	INIT_LIST_HEAD(&plug->list);
+	INIT_LIST_HEAD(&plug->mq_list);
 	INIT_LIST_HEAD(&plug->cb_list);
-	plug->should_sort = 0;
 
 	/*
 	 * If this is a nested plug, don't actually assign it. It will be
@@ -2982,18 +3090,17 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	LIST_HEAD(list);
 	unsigned int depth;
 
-	BUG_ON(plug->magic != PLUG_MAGIC);
-
 	flush_plug_callbacks(plug, from_schedule);
+
+	if (!list_empty(&plug->mq_list))
+		blk_mq_flush_plug_list(plug, from_schedule);
+
 	if (list_empty(&plug->list))
 		return;
 
 	list_splice_init(&plug->list, &list);
 
-	if (plug->should_sort) {
-		list_sort(NULL, &list, plug_rq_cmp);
-		plug->should_sort = 0;
-	}
+	list_sort(NULL, &list, plug_rq_cmp);
 
 	q = NULL;
 	depth = 0;
@@ -3055,6 +3162,149 @@ void blk_finish_plug(struct blk_plug *plug)
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
+#ifdef CONFIG_PM_RUNTIME
+/**
+ * blk_pm_runtime_init - Block layer runtime PM initialization routine
+ * @q: the queue of the device
+ * @dev: the device the queue belongs to
+ *
+ * Description:
+ *    Initialize runtime-PM-related fields for @q and start auto suspend for
+ *    @dev. Drivers that want to take advantage of request-based runtime PM
+ *    should call this function after @dev has been initialized, and its
+ *    request queue @q has been allocated, and runtime PM for it can not happen
+ *    yet(either due to disabled/forbidden or its usage_count > 0). In most
+ *    cases, driver should call this function before any I/O has taken place.
+ *
+ *    This function takes care of setting up using auto suspend for the device,
+ *    the autosuspend delay is set to -1 to make runtime suspend impossible
+ *    until an updated value is either set by user or by driver. Drivers do
+ *    not need to touch other autosuspend settings.
+ *
+ *    The block layer runtime PM is request based, so only works for drivers
+ *    that use request as their IO unit instead of those directly use bio's.
+ */
+void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
+{
+	q->dev = dev;
+	q->rpm_status = RPM_ACTIVE;
+	pm_runtime_set_autosuspend_delay(q->dev, -1);
+	pm_runtime_use_autosuspend(q->dev);
+}
+EXPORT_SYMBOL(blk_pm_runtime_init);
+
+/**
+ * blk_pre_runtime_suspend - Pre runtime suspend check
+ * @q: the queue of the device
+ *
+ * Description:
+ *    This function will check if runtime suspend is allowed for the device
+ *    by examining if there are any requests pending in the queue. If there
+ *    are requests pending, the device can not be runtime suspended; otherwise,
+ *    the queue's status will be updated to SUSPENDING and the driver can
+ *    proceed to suspend the device.
+ *
+ *    For the not allowed case, we mark last busy for the device so that
+ *    runtime PM core will try to autosuspend it some time later.
+ *
+ *    This function should be called near the start of the device's
+ *    runtime_suspend callback.
+ *
+ * Return:
+ *    0		- OK to runtime suspend the device
+ *    -EBUSY	- Device should not be runtime suspended
+ */
+int blk_pre_runtime_suspend(struct request_queue *q)
+{
+	int ret = 0;
+
+	spin_lock_irq(q->queue_lock);
+	if (q->nr_pending) {
+		ret = -EBUSY;
+		pm_runtime_mark_last_busy(q->dev);
+	} else {
+		q->rpm_status = RPM_SUSPENDING;
+	}
+	spin_unlock_irq(q->queue_lock);
+	return ret;
+}
+EXPORT_SYMBOL(blk_pre_runtime_suspend);
+
+/**
+ * blk_post_runtime_suspend - Post runtime suspend processing
+ * @q: the queue of the device
+ * @err: return value of the device's runtime_suspend function
+ *
+ * Description:
+ *    Update the queue's runtime status according to the return value of the
+ *    device's runtime suspend function and mark last busy for the device so
+ *    that PM core will try to auto suspend the device at a later time.
+ *
+ *    This function should be called near the end of the device's
+ *    runtime_suspend callback.
+ */
+void blk_post_runtime_suspend(struct request_queue *q, int err)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!err) {
+		q->rpm_status = RPM_SUSPENDED;
+	} else {
+		q->rpm_status = RPM_ACTIVE;
+		pm_runtime_mark_last_busy(q->dev);
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_post_runtime_suspend);
+
+/**
+ * blk_pre_runtime_resume - Pre runtime resume processing
+ * @q: the queue of the device
+ *
+ * Description:
+ *    Update the queue's runtime status to RESUMING in preparation for the
+ *    runtime resume of the device.
+ *
+ *    This function should be called near the start of the device's
+ *    runtime_resume callback.
+ */
+void blk_pre_runtime_resume(struct request_queue *q)
+{
+	spin_lock_irq(q->queue_lock);
+	q->rpm_status = RPM_RESUMING;
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_pre_runtime_resume);
+
+/**
+ * blk_post_runtime_resume - Post runtime resume processing
+ * @q: the queue of the device
+ * @err: return value of the device's runtime_resume function
+ *
+ * Description:
+ *    Update the queue's runtime status according to the return value of the
+ *    device's runtime_resume function. If it is successfully resumed, process
+ *    the requests that are queued into the device's queue when it is resuming
+ *    and then mark last busy and initiate autosuspend for it.
+ *
+ *    This function should be called near the end of the device's
+ *    runtime_resume callback.
+ */
+void blk_post_runtime_resume(struct request_queue *q, int err)
+{
+	spin_lock_irq(q->queue_lock);
+	if (!err) {
+		q->rpm_status = RPM_ACTIVE;
+		__blk_run_queue(q);
+		pm_runtime_mark_last_busy(q->dev);
+		pm_request_autosuspend(q->dev);
+	} else {
+		q->rpm_status = RPM_SUSPENDED;
+	}
+	spin_unlock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL(blk_post_runtime_resume);
+#endif
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *