Merge branch 'for-4.11/next' into for-4.11/linus-merge

Signed-off-by: Jens Axboe <axboe@fb.com>

block/Kconfig

@@ -49,9 +49,13 @@ config LBDAF
 
 	  If unsure, say Y.
 
+config BLK_SCSI_REQUEST
+	bool
+
 config BLK_DEV_BSG
 	bool "Block layer SG support v4"
 	default y
+	select BLK_SCSI_REQUEST
 	help
 	  Saying Y here will enable generic SG (SCSI generic) v4 support
 	  for any block device.
@@ -71,6 +75,7 @@ config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	default n
 	select BLK_DEV_BSG
+	select BLK_SCSI_REQUEST
 	help
 	  Subsystems will normally enable this if needed. Users will not
 	  normally need to manually enable this.

block/Makefile

@@ -7,10 +7,11 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
-			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
+			genhd.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
-obj-$(CONFIG_BOUNCE)	+= bounce.o
+obj-$(CONFIG_BOUNCE)		+= bounce.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o

block/bio.c

@@ -1227,9 +1227,6 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	if (!bio)
 		goto out_bmd;
 
-	if (iter->type & WRITE)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 	ret = 0;
 
 	if (map_data) {
@@ -1394,12 +1391,6 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 
 	kfree(pages);
 
-	/*
-	 * set data direction, and check if mapped pages need bouncing
-	 */
-	if (iter->type & WRITE)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
 	/*
@@ -1590,7 +1581,6 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 		bio->bi_private = data;
 	} else {
 		bio->bi_end_io = bio_copy_kern_endio;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	}
 
 	return bio;

block/blk-cgroup.c

@@ -184,7 +184,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 		goto err_free_blkg;
 	}
 
-	wb_congested = wb_congested_get_create(&q->backing_dev_info,
+	wb_congested = wb_congested_get_create(q->backing_dev_info,
 					       blkcg->css.id,
 					       GFP_NOWAIT | __GFP_NOWARN);
 	if (!wb_congested) {
@@ -469,8 +469,8 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
 	/* some drivers (floppy) instantiate a queue w/o disk registered */
-	if (blkg->q->backing_dev_info.dev)
+	if (blkg->q->backing_dev_info->dev)
-		return dev_name(blkg->q->backing_dev_info.dev);
+		return dev_name(blkg->q->backing_dev_info->dev);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(blkg_dev_name);
@@ -1079,10 +1079,8 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	if (IS_ERR(blkg)) {
+	if (IS_ERR(blkg))
-		blkg_free(new_blkg);
 		return PTR_ERR(blkg);
-	}
 
 	q->root_blkg = blkg;
 	q->root_rl.blkg = blkg;

block/blk-core.c

@@ -33,6 +33,7 @@
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -42,6 +43,10 @@
 #include "blk-mq-sched.h"
 #include "blk-wbt.h"
 
+#ifdef CONFIG_DEBUG_FS
+struct dentry *blk_debugfs_root;
+#endif
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
@@ -75,7 +80,7 @@ static void blk_clear_congested(struct request_list *rl, int sync)
 	 * flip its congestion state for events on other blkcgs.
 	 */
 	if (rl == &rl->q->root_rl)
-		clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+		clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
 #endif
 }
 
@@ -86,7 +91,7 @@ static void blk_set_congested(struct request_list *rl, int sync)
 #else
 	/* see blk_clear_congested() */
 	if (rl == &rl->q->root_rl)
-		set_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+		set_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
 #endif
 }
 
@@ -105,22 +110,6 @@ void blk_queue_congestion_threshold(struct request_queue *q)
 	q->nr_congestion_off = nr;
 }
 
-/**
- * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
- * @bdev:	device
- *
- * Locates the passed device's request queue and returns the address of its
- * backing_dev_info.  This function can only be called if @bdev is opened
- * and the return value is never NULL.
- */
-struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return &q->backing_dev_info;
-}
-EXPORT_SYMBOL(blk_get_backing_dev_info);
-
 void blk_rq_init(struct request_queue *q, struct request *rq)
 {
 	memset(rq, 0, sizeof(*rq));
@@ -132,8 +121,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->__sector = (sector_t) -1;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
-	rq->cmd = rq->__cmd;
-	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
 	rq->internal_tag = -1;
 	rq->start_time = jiffies;
@@ -160,10 +147,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
 {
-	int bit;
+	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
-
+		rq->rq_disk ? rq->rq_disk->disk_name : "?",
-	printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
-		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
 		(unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
@@ -171,13 +156,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 	       blk_rq_sectors(rq), blk_rq_cur_sectors(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: ");
-		for (bit = 0; bit < BLK_MAX_CDB; bit++)
-			printk("%02x ", rq->cmd[bit]);
-		printk("\n");
-	}
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
@@ -588,7 +566,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	blk_flush_integrity();
 
 	/* @q won't process any more request, flush async actions */
-	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
+	del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
 	if (q->mq_ops)
@@ -600,7 +578,8 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	bdi_unregister(&q->backing_dev_info);
+	bdi_unregister(q->backing_dev_info);
+	put_disk_devt(q->disk_devt);
 
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
@@ -608,17 +587,41 @@ void blk_cleanup_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_cleanup_queue);
 
 /* Allocate memory local to the request queue */
-static void *alloc_request_struct(gfp_t gfp_mask, void *data)
+static void *alloc_request_simple(gfp_t gfp_mask, void *data)
 {
-	int nid = (int)(long)data;
+	struct request_queue *q = data;
-	return kmem_cache_alloc_node(request_cachep, gfp_mask, nid);
+
+	return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node);
 }
 
-static void free_request_struct(void *element, void *unused)
+static void free_request_simple(void *element, void *data)
 {
 	kmem_cache_free(request_cachep, element);
 }
 
+static void *alloc_request_size(gfp_t gfp_mask, void *data)
+{
+	struct request_queue *q = data;
+	struct request *rq;
+
+	rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask,
+			q->node);
+	if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) {
+		kfree(rq);
+		rq = NULL;
+	}
+	return rq;
+}
+
+static void free_request_size(void *element, void *data)
+{
+	struct request_queue *q = data;
+
+	if (q->exit_rq_fn)
+		q->exit_rq_fn(q, element);
+	kfree(element);
+}
+
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask)
 {
@@ -631,10 +634,15 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q,
 	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
 	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
-	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, alloc_request_struct,
+	if (q->cmd_size) {
-					  free_request_struct,
+		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
-					  (void *)(long)q->node, gfp_mask,
+				alloc_request_size, free_request_size,
-					  q->node);
+				q, gfp_mask, q->node);
+	} else {
+		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
+				alloc_request_simple, free_request_simple,
+				q, gfp_mask, q->node);
+	}
 	if (!rl->rq_pool)
 		return -ENOMEM;
 
@@ -697,7 +705,6 @@ static void blk_rq_timed_out_timer(unsigned long data)
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
-	int err;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep,
 				gfp_mask | __GFP_ZERO, node_id);
@@ -712,17 +719,17 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q->bio_split)
 		goto fail_id;
 
-	q->backing_dev_info.ra_pages =
+	q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
-			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+	if (!q->backing_dev_info)
-	q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
-	q->backing_dev_info.name = "block";
-	q->node = node_id;
-
-	err = bdi_init(&q->backing_dev_info);
-	if (err)
 		goto fail_split;
 
-	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
+	q->backing_dev_info->ra_pages =
+			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
+	q->backing_dev_info->name = "block";
+	q->node = node_id;
+
+	setup_timer(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->queue_head);
@@ -772,7 +779,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 fail_ref:
 	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
-	bdi_destroy(&q->backing_dev_info);
+	bdi_put(q->backing_dev_info);
 fail_split:
 	bioset_free(q->bio_split);
 fail_id:
@@ -825,15 +832,19 @@ EXPORT_SYMBOL(blk_init_queue);
 struct request_queue *
 blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 {
-	struct request_queue *uninit_q, *q;
+	struct request_queue *q;
 
-	uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+	q = blk_alloc_queue_node(GFP_KERNEL, node_id);
-	if (!uninit_q)
+	if (!q)
 		return NULL;
 
-	q = blk_init_allocated_queue(uninit_q, rfn, lock);
+	q->request_fn = rfn;
-	if (!q)
+	if (lock)
-		blk_cleanup_queue(uninit_q);
+		q->queue_lock = lock;
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return NULL;
+	}
 
 	return q;
 }
@@ -841,30 +852,22 @@ EXPORT_SYMBOL(blk_init_queue_node);
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
 
-struct request_queue *
-blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
-			 spinlock_t *lock)
-{
-	if (!q)
-		return NULL;
 
-	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0);
+int blk_init_allocated_queue(struct request_queue *q)
+{
+	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);
 	if (!q->fq)
-		return NULL;
+		return -ENOMEM;
+
+	if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL))
+		goto out_free_flush_queue;
 
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
-		goto fail;
+		goto out_exit_flush_rq;
 
 	INIT_WORK(&q->timeout_work, blk_timeout_work);
-	q->request_fn		= rfn;
-	q->prep_rq_fn		= NULL;
-	q->unprep_rq_fn		= NULL;
 	q->queue_flags		|= QUEUE_FLAG_DEFAULT;
 
-	/* Override internal queue lock with supplied lock pointer */
-	if (lock)
-		q->queue_lock		= lock;
-
 	/*
 	 * This also sets hw/phys segments, boundary and size
 	 */
@@ -878,17 +881,19 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		goto fail;
+		goto out_exit_flush_rq;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
+	return 0;
 
-	return q;
+out_exit_flush_rq:
-
+	if (q->exit_rq_fn)
-fail:
+		q->exit_rq_fn(q, q->fq->flush_rq);
+out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
 	wbt_exit(q);
-	return NULL;
+	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -1024,25 +1029,6 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return 0;
 }
 
-/*
- * Determine if elevator data should be initialized when allocating the
- * request associated with @bio.
- */
-static bool blk_rq_should_init_elevator(struct bio *bio)
-{
-	if (!bio)
-		return true;
-
-	/*
-	 * Flush requests do not use the elevator so skip initialization.
-	 * This allows a request to share the flush and elevator data.
-	 */
-	if (op_is_flush(bio->bi_opf))
-		return false;
-
-	return true;
-}
-
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
@@ -1121,10 +1107,13 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
 	 *
+	 * Flush requests do not use the elevator so skip initialization.
+	 * This allows a request to share the flush and elevator data.
+	 *
 	 * Also, lookup icq while holding queue_lock.  If it doesn't exist,
 	 * it will be created after releasing queue_lock.
 	 */
-	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
+	if (!op_is_flush(op) && !blk_queue_bypass(q)) {
 		rq_flags |= RQF_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
@@ -1184,7 +1173,7 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	 * disturb iosched and blkcg but weird is bettern than dead.
 	 */
 	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n",
-			   __func__, dev_name(q->backing_dev_info.dev));
+			   __func__, dev_name(q->backing_dev_info->dev));
 
 	rq->rq_flags &= ~RQF_ELVPRIV;
 	rq->elv.icq = NULL;
@@ -1278,8 +1267,6 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 {
 	struct request *rq;
 
-	BUG_ON(rw != READ && rw != WRITE);
-
 	/* create ioc upfront */
 	create_io_context(gfp_mask, q->node);
 
@@ -1308,18 +1295,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_get_request);
 
-/**
- * blk_rq_set_block_pc - initialize a request 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;
-	memset(rq->__cmd, 0, sizeof(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
@@ -1510,6 +1485,30 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 	return true;
 }
 
+bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
+		struct bio *bio)
+{
+	unsigned short segments = blk_rq_nr_discard_segments(req);
+
+	if (segments >= queue_max_discard_segments(q))
+		goto no_merge;
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
+		goto no_merge;
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+	req->nr_phys_segments = segments + 1;
+
+	blk_account_io_start(req, false);
+	return true;
+no_merge:
+	req_set_nomerge(q, req);
+	return false;
+}
+
 /**
  * blk_attempt_plug_merge - try to merge with %current's plugged list
  * @q: request_queue new bio is being queued at
@@ -1538,12 +1537,11 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 {
 	struct blk_plug *plug;
 	struct request *rq;
-	bool ret = false;
 	struct list_head *plug_list;
 
 	plug = current->plug;
 	if (!plug)
-		goto out;
+		return false;
 	*request_count = 0;
 
 	if (q->mq_ops)
@@ -1552,7 +1550,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		plug_list = &plug->list;
 
 	list_for_each_entry_reverse(rq, plug_list, queuelist) {
-		int el_ret;
+		bool merged = false;
 
 		if (rq->q == q) {
 			(*request_count)++;
@@ -1568,19 +1566,25 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
 			continue;
 
-		el_ret = blk_try_merge(rq, bio);
+		switch (blk_try_merge(rq, bio)) {
-		if (el_ret == ELEVATOR_BACK_MERGE) {
+		case ELEVATOR_BACK_MERGE:
-			ret = bio_attempt_back_merge(q, rq, bio);
+			merged = bio_attempt_back_merge(q, rq, bio);
-			if (ret)
+			break;
-				break;
+		case ELEVATOR_FRONT_MERGE:
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+			merged = bio_attempt_front_merge(q, rq, bio);
-			ret = bio_attempt_front_merge(q, rq, bio);
+			break;
-			if (ret)
+		case ELEVATOR_DISCARD_MERGE:
-				break;
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			break;
 		}
+
+		if (merged)
+			return true;
 	}
-out:
+
-	return ret;
+	return false;
 }
 
 unsigned int blk_plug_queued_count(struct request_queue *q)
@@ -1609,7 +1613,6 @@ unsigned int blk_plug_queued_count(struct request_queue *q)
 
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
-	req->cmd_type = REQ_TYPE_FS;
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
@@ -1623,8 +1626,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	struct blk_plug *plug;
-	int el_ret, where = ELEVATOR_INSERT_SORT;
+	int where = ELEVATOR_INSERT_SORT;
-	struct request *req;
+	struct request *req, *free;
 	unsigned int request_count = 0;
 	unsigned int wb_acct;
 
@@ -1661,21 +1664,29 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	el_ret = elv_merge(q, &req, bio);
+	switch (elv_merge(q, &req, bio)) {
-	if (el_ret == ELEVATOR_BACK_MERGE) {
+	case ELEVATOR_BACK_MERGE:
-		if (bio_attempt_back_merge(q, req, bio)) {
+		if (!bio_attempt_back_merge(q, req, bio))
-			elv_bio_merged(q, req, bio);
+			break;
-			if (!attempt_back_merge(q, req))
+		elv_bio_merged(q, req, bio);
-				elv_merged_request(q, req, el_ret);
+		free = attempt_back_merge(q, req);
-			goto out_unlock;
+		if (free)
-		}
+			__blk_put_request(q, free);
-	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
+		else
-		if (bio_attempt_front_merge(q, req, bio)) {
+			elv_merged_request(q, req, ELEVATOR_BACK_MERGE);
-			elv_bio_merged(q, req, bio);
+		goto out_unlock;
-			if (!attempt_front_merge(q, req))
+	case ELEVATOR_FRONT_MERGE:
-				elv_merged_request(q, req, el_ret);
+		if (!bio_attempt_front_merge(q, req, bio))
-			goto out_unlock;
+			break;
-		}
+		elv_bio_merged(q, req, bio);
+		free = attempt_front_merge(q, req);
+		if (free)
+			__blk_put_request(q, free);
+		else
+			elv_merged_request(q, req, ELEVATOR_FRONT_MERGE);
+		goto out_unlock;
+	default:
+		break;
 	}
 
 get_rq:
@@ -2452,14 +2463,6 @@ void blk_start_request(struct request *req)
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
 
-	/*
-	 * We are now handing the request to the hardware, initialize
-	 * resid_len to full count and add the timeout handler.
-	 */
-	req->resid_len = blk_rq_bytes(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);
 }
@@ -2530,10 +2533,10 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	 * TODO: tj: This is too subtle.  It would be better to let
 	 * low level drivers do what they see fit.
 	 */
-	if (req->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(req))
 		req->errors = 0;
 
-	if (error && req->cmd_type == REQ_TYPE_FS &&
+	if (error && !blk_rq_is_passthrough(req) &&
 	    !(req->rq_flags & RQF_QUIET)) {
 		char *error_type;
 
@@ -2605,7 +2608,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	req->__data_len -= total_bytes;
 
 	/* update sector only for requests with clear definition of sector */
-	if (req->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(req))
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */
@@ -2683,8 +2686,8 @@ void blk_finish_request(struct request *req, int error)
 
 	BUG_ON(blk_queued_rq(req));
 
-	if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
+	if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req))
-		laptop_io_completion(&req->q->backing_dev_info);
+		laptop_io_completion(req->q->backing_dev_info);
 
 	blk_delete_timer(req);
 
@@ -3007,8 +3010,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = src->cmd_flags | REQ_NOMERGE;
-	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
 	dst->nr_phys_segments = src->nr_phys_segments;
@@ -3484,5 +3485,9 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
+#ifdef CONFIG_DEBUG_FS
+	blk_debugfs_root = debugfs_create_dir("block", NULL);
+#endif
+
 	return 0;
 }

block/blk-exec.c

@@ -11,11 +11,6 @@
 #include "blk.h"
 #include "blk-mq-sched.h"
 
-/*
- * for max sense size
- */
-#include <scsi/scsi_cmnd.h>
-
 /**
  * blk_end_sync_rq - executes a completion event on a request
  * @rq: request to complete
@@ -56,7 +51,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
 
 	WARN_ON(irqs_disabled());
-	WARN_ON(rq->cmd_type == REQ_TYPE_FS);
+	WARN_ON(!blk_rq_is_passthrough(rq));
 
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
@@ -101,16 +96,9 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		   struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	char sense[SCSI_SENSE_BUFFERSIZE];
 	int err = 0;
 	unsigned long hang_check;
 
-	if (!rq->sense) {
-		memset(sense, 0, sizeof(sense));
-		rq->sense = sense;
-		rq->sense_len = 0;
-	}
-
 	rq->end_io_data = &wait;
 	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
 
@@ -124,11 +112,6 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 	if (rq->errors)
 		err = -EIO;
 
-	if (rq->sense == sense)	{
-		rq->sense = NULL;
-		rq->sense_len = 0;
-	}
-
 	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);

block/blk-flush.c

@@ -297,8 +297,14 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
 		return false;
 
-	/* C2 and C3 */
+	/* C2 and C3
+	 *
+	 * For blk-mq + scheduling, we can risk having all driver tags
+	 * assigned to empty flushes, and we deadlock if we are expecting
+	 * other requests to make progress. Don't defer for that case.
+	 */
 	if (!list_empty(&fq->flush_data_in_flight) &&
+	    !(q->mq_ops && q->elevator) &&
 	    time_before(jiffies,
 			fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
 		return false;
@@ -327,7 +333,6 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
 	}
 
-	flush_rq->cmd_type = REQ_TYPE_FS;
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
@@ -547,11 +552,10 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
 	if (!fq)
 		goto fail;
 
-	if (q->mq_ops) {
+	if (q->mq_ops)
 		spin_lock_init(&fq->mq_flush_lock);
-		rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
-	}
 
+	rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
 	fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node);
 	if (!fq->flush_rq)
 		goto fail_rq;

block/blk-integrity.c

@@ -443,10 +443,10 @@ void blk_integrity_revalidate(struct gendisk *disk)
 		return;
 
 	if (bi->profile)
-		disk->queue->backing_dev_info.capabilities |=
+		disk->queue->backing_dev_info->capabilities |=
 			BDI_CAP_STABLE_WRITES;
 	else
-		disk->queue->backing_dev_info.capabilities &=
+		disk->queue->backing_dev_info->capabilities &=
 			~BDI_CAP_STABLE_WRITES;
 }
 

block/blk-ioc.c

@@ -35,7 +35,10 @@ static void icq_free_icq_rcu(struct rcu_head *head)
 	kmem_cache_free(icq->__rcu_icq_cache, icq);
 }
 
-/* Exit an icq. Called with both ioc and q locked. */
+/*
+ * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for
+ * mq.
+ */
 static void ioc_exit_icq(struct io_cq *icq)
 {
 	struct elevator_type *et = icq->q->elevator->type;
@@ -166,6 +169,7 @@ EXPORT_SYMBOL(put_io_context);
  */
 void put_io_context_active(struct io_context *ioc)
 {
+	struct elevator_type *et;
 	unsigned long flags;
 	struct io_cq *icq;
 
@@ -184,13 +188,19 @@ void put_io_context_active(struct io_context *ioc)
 	hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) {
 		if (icq->flags & ICQ_EXITED)
 			continue;
-		if (spin_trylock(icq->q->queue_lock)) {
+
+		et = icq->q->elevator->type;
+		if (et->uses_mq) {
 			ioc_exit_icq(icq);
-			spin_unlock(icq->q->queue_lock);
 		} else {
-			spin_unlock_irqrestore(&ioc->lock, flags);
+			if (spin_trylock(icq->q->queue_lock)) {
-			cpu_relax();
+				ioc_exit_icq(icq);
-			goto retry;
+				spin_unlock(icq->q->queue_lock);
+			} else {
+				spin_unlock_irqrestore(&ioc->lock, flags);
+				cpu_relax();
+				goto retry;
+			}
 		}
 	}
 	spin_unlock_irqrestore(&ioc->lock, flags);

block/blk-map.c

@@ -16,8 +16,6 @@
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
 	if (!rq->bio) {
-		rq->cmd_flags &= REQ_OP_MASK;
-		rq->cmd_flags |= (bio->bi_opf & REQ_OP_MASK);
 		blk_rq_bio_prep(rq->q, rq, bio);
 	} else {
 		if (!ll_back_merge_fn(rq->q, rq, bio))
@@ -62,6 +60,9 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
+	bio->bi_opf &= ~REQ_OP_MASK;
+	bio->bi_opf |= req_op(rq);
+
 	if (map_data && map_data->null_mapped)
 		bio_set_flag(bio, BIO_NULL_MAPPED);
 
@@ -90,7 +91,7 @@ static int __blk_rq_map_user_iov(struct request *rq,
 }
 
 /**
- * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
+ * blk_rq_map_user_iov - map user data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
  * @rq:		request to map data to
  * @map_data:   pointer to the rq_map_data holding pages (if necessary)
@@ -199,7 +200,7 @@ int blk_rq_unmap_user(struct bio *bio)
 EXPORT_SYMBOL(blk_rq_unmap_user);
 
 /**
- * blk_rq_map_kern - map kernel data to a request, for REQ_TYPE_BLOCK_PC usage
+ * blk_rq_map_kern - map kernel data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
  * @rq:		request to fill
  * @kbuf:	the kernel buffer
@@ -234,8 +235,8 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (!reading)
+	bio->bi_opf &= ~REQ_OP_MASK;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+	bio->bi_opf |= req_op(rq);
 
 	if (do_copy)
 		rq->rq_flags |= RQF_COPY_USER;

block/blk-merge.c

@@ -482,13 +482,6 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
-static void req_set_nomerge(struct request_queue *q, struct request *req)
-{
-	req->cmd_flags |= REQ_NOMERGE;
-	if (req == q->last_merge)
-		q->last_merge = NULL;
-}
-
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
@@ -659,31 +652,32 @@ static void blk_account_io_merge(struct request *req)
 }
 
 /*
- * Has to be called with the request spinlock acquired
+ * For non-mq, this has to be called with the request spinlock acquired.
+ * For mq with scheduling, the appropriate queue wide lock should be held.
  */
-static int attempt_merge(struct request_queue *q, struct request *req,
+static struct request *attempt_merge(struct request_queue *q,
-			  struct request *next)
+				     struct request *req, struct request *next)
 {
 	if (!rq_mergeable(req) || !rq_mergeable(next))
-		return 0;
+		return NULL;
 
 	if (req_op(req) != req_op(next))
-		return 0;
+		return NULL;
 
 	/*
 	 * not contiguous
 	 */
 	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
-		return 0;
+		return NULL;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
 	    || req->rq_disk != next->rq_disk
 	    || req_no_special_merge(next))
-		return 0;
+		return NULL;
 
 	if (req_op(req) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(req->bio, next->bio))
-		return 0;
+		return NULL;
 
 	/*
 	 * If we are allowed to merge, then append bio list
@@ -692,7 +686,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	 * counts here.
 	 */
 	if (!ll_merge_requests_fn(q, req, next))
-		return 0;
+		return NULL;
 
 	/*
 	 * If failfast settings disagree or any of the two is already
@@ -732,42 +726,51 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
-	/* owner-ship of bio passed from next to req */
+	/*
+	 * ownership of bio passed from next to req, return 'next' for
+	 * the caller to free
+	 */
 	next->bio = NULL;
-	__blk_put_request(q, next);
+	return next;
-	return 1;
 }
 
-int attempt_back_merge(struct request_queue *q, struct request *rq)
+struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *next = elv_latter_request(q, rq);
 
 	if (next)
 		return attempt_merge(q, rq, next);
 
-	return 0;
+	return NULL;
 }
 
-int attempt_front_merge(struct request_queue *q, struct request *rq)
+struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *prev = elv_former_request(q, rq);
 
 	if (prev)
 		return attempt_merge(q, prev, rq);
 
-	return 0;
+	return NULL;
 }
 
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 			  struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
+	struct request *free;
 
 	if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
 		if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
 			return 0;
 
-	return attempt_merge(q, rq, next);
+	free = attempt_merge(q, rq, next);
+	if (free) {
+		__blk_put_request(q, free);
+		return 1;
+	}
+
+	return 0;
 }
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
@@ -798,9 +801,12 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	return true;
 }
 
-int blk_try_merge(struct request *rq, struct bio *bio)
+enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 {
-	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
+	if (req_op(rq) == REQ_OP_DISCARD &&
+	    queue_max_discard_segments(rq->q) > 1)
+		return ELEVATOR_DISCARD_MERGE;
+	else 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_iter.bi_sector)
 		return ELEVATOR_FRONT_MERGE;

block/blk-mq-debugfs.c

@@ -19,6 +19,7 @@
 #include <linux/debugfs.h>
 
 #include <linux/blk-mq.h>
+#include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
@@ -28,8 +29,6 @@ struct blk_mq_debugfs_attr {
 	const struct file_operations *fops;
 };
 
-static struct dentry *block_debugfs_root;
-
 static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
 				   const struct seq_operations *ops)
 {
@@ -88,13 +87,14 @@ static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 {
 	struct request *rq = list_entry_rq(v);
 
-	seq_printf(m, "%p {.cmd_type=%u, .cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
+	seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
-		   rq, rq->cmd_type, rq->cmd_flags, (unsigned int)rq->rq_flags,
+		   rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags,
 		   rq->tag, rq->internal_tag);
 	return 0;
 }
 
 static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
+	__acquires(&hctx->lock)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 
@@ -110,6 +110,7 @@ static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
 }
 
 static void hctx_dispatch_stop(struct seq_file *m, void *v)
+	__releases(&hctx->lock)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 
@@ -176,13 +177,17 @@ static int hctx_tags_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 	struct request_queue *q = hctx->queue;
+	int res;
 
-	mutex_lock(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
 	if (hctx->tags)
 		blk_mq_debugfs_tags_show(m, hctx->tags);
 	mutex_unlock(&q->sysfs_lock);
 
-	return 0;
+out:
+	return res;
 }
 
 static int hctx_tags_open(struct inode *inode, struct file *file)
@@ -201,12 +206,17 @@ static int hctx_tags_bitmap_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 	struct request_queue *q = hctx->queue;
+	int res;
 
-	mutex_lock(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
 	if (hctx->tags)
 		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
 	mutex_unlock(&q->sysfs_lock);
-	return 0;
+
+out:
+	return res;
 }
 
 static int hctx_tags_bitmap_open(struct inode *inode, struct file *file)
@@ -225,13 +235,17 @@ static int hctx_sched_tags_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 	struct request_queue *q = hctx->queue;
+	int res;
 
-	mutex_lock(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
 	if (hctx->sched_tags)
 		blk_mq_debugfs_tags_show(m, hctx->sched_tags);
 	mutex_unlock(&q->sysfs_lock);
 
-	return 0;
+out:
+	return res;
 }
 
 static int hctx_sched_tags_open(struct inode *inode, struct file *file)
@@ -250,12 +264,17 @@ static int hctx_sched_tags_bitmap_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 	struct request_queue *q = hctx->queue;
+	int res;
 
-	mutex_lock(&q->sysfs_lock);
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
 	if (hctx->sched_tags)
 		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
 	mutex_unlock(&q->sysfs_lock);
-	return 0;
+
+out:
+	return res;
 }
 
 static int hctx_sched_tags_bitmap_open(struct inode *inode, struct file *file)
@@ -482,6 +501,7 @@ static const struct file_operations hctx_active_fops = {
 };
 
 static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
+	__acquires(&ctx->lock)
 {
 	struct blk_mq_ctx *ctx = m->private;
 
@@ -497,6 +517,7 @@ static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos)
 }
 
 static void ctx_rq_list_stop(struct seq_file *m, void *v)
+	__releases(&ctx->lock)
 {
 	struct blk_mq_ctx *ctx = m->private;
 
@@ -630,6 +651,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"queued", 0600, &hctx_queued_fops},
 	{"run", 0600, &hctx_run_fops},
 	{"active", 0400, &hctx_active_fops},
+	{},
 };
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
@@ -637,14 +659,15 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
 	{"dispatched", 0600, &ctx_dispatched_fops},
 	{"merged", 0600, &ctx_merged_fops},
 	{"completed", 0600, &ctx_completed_fops},
+	{},
 };
 
 int blk_mq_debugfs_register(struct request_queue *q, const char *name)
 {
-	if (!block_debugfs_root)
+	if (!blk_debugfs_root)
 		return -ENOENT;
 
-	q->debugfs_dir = debugfs_create_dir(name, block_debugfs_root);
+	q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
 	if (!q->debugfs_dir)
 		goto err;
 
@@ -665,27 +688,31 @@ void blk_mq_debugfs_unregister(struct request_queue *q)
 	q->debugfs_dir = NULL;
 }
 
+static bool debugfs_create_files(struct dentry *parent, void *data,
+				const struct blk_mq_debugfs_attr *attr)
+{
+	for (; attr->name; attr++) {
+		if (!debugfs_create_file(attr->name, attr->mode, parent,
+					 data, attr->fops))
+			return false;
+	}
+	return true;
+}
+
 static int blk_mq_debugfs_register_ctx(struct request_queue *q,
 				       struct blk_mq_ctx *ctx,
 				       struct dentry *hctx_dir)
 {
 	struct dentry *ctx_dir;
 	char name[20];
-	int i;
 
 	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
 	ctx_dir = debugfs_create_dir(name, hctx_dir);
 	if (!ctx_dir)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_ctx_attrs); i++) {
+	if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs))
-		const struct blk_mq_debugfs_attr *attr;
+		return -ENOMEM;
-
-		attr = &blk_mq_debugfs_ctx_attrs[i];
-		if (!debugfs_create_file(attr->name, attr->mode, ctx_dir, ctx,
-					 attr->fops))
-			return -ENOMEM;
-	}
 
 	return 0;
 }
@@ -703,14 +730,8 @@ static int blk_mq_debugfs_register_hctx(struct request_queue *q,
 	if (!hctx_dir)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(blk_mq_debugfs_hctx_attrs); i++) {
+	if (!debugfs_create_files(hctx_dir, hctx, blk_mq_debugfs_hctx_attrs))
-		const struct blk_mq_debugfs_attr *attr;
+		return -ENOMEM;
-
-		attr = &blk_mq_debugfs_hctx_attrs[i];
-		if (!debugfs_create_file(attr->name, attr->mode, hctx_dir, hctx,
-					 attr->fops))
-			return -ENOMEM;
-	}
 
 	hctx_for_each_ctx(hctx, ctx, i) {
 		if (blk_mq_debugfs_register_ctx(q, ctx, hctx_dir))
@@ -749,8 +770,3 @@ void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
 	debugfs_remove_recursive(q->mq_debugfs_dir);
 	q->mq_debugfs_dir = NULL;
 }
-
-void blk_mq_debugfs_init(void)
-{
-	block_debugfs_root = debugfs_create_dir("block", NULL);
-}

block/blk-mq-sched.c

@@ -68,7 +68,9 @@ int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
 EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
 
 static void __blk_mq_sched_assign_ioc(struct request_queue *q,
-				      struct request *rq, struct io_context *ioc)
+				      struct request *rq,
+				      struct bio *bio,
+				      struct io_context *ioc)
 {
 	struct io_cq *icq;
 
@@ -83,7 +85,7 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q,
 	}
 
 	rq->elv.icq = icq;
-	if (!blk_mq_sched_get_rq_priv(q, rq)) {
+	if (!blk_mq_sched_get_rq_priv(q, rq, bio)) {
 		rq->rq_flags |= RQF_ELVPRIV;
 		get_io_context(icq->ioc);
 		return;
@@ -99,7 +101,7 @@ static void blk_mq_sched_assign_ioc(struct request_queue *q,
 
 	ioc = rq_ioc(bio);
 	if (ioc)
-		__blk_mq_sched_assign_ioc(q, rq, ioc);
+		__blk_mq_sched_assign_ioc(q, rq, bio, ioc);
 }
 
 struct request *blk_mq_sched_get_request(struct request_queue *q,
@@ -173,6 +175,8 @@ void blk_mq_sched_put_request(struct request *rq)
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct elevator_queue *e = hctx->queue->elevator;
+	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
+	bool did_work = false;
 	LIST_HEAD(rq_list);
 
 	if (unlikely(blk_mq_hctx_stopped(hctx)))
@@ -202,11 +206,18 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart(hctx);
-		blk_mq_dispatch_rq_list(hctx, &rq_list);
+		did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
-	} else if (!e || !e->type->ops.mq.dispatch_request) {
+	} else if (!has_sched_dispatch) {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
 		blk_mq_dispatch_rq_list(hctx, &rq_list);
-	} else {
+	}
+
+	/*
+	 * We want to dispatch from the scheduler if we had no work left
+	 * on the dispatch list, OR if we did have work but weren't able
+	 * to make progress.
+	 */
+	if (!did_work && has_sched_dispatch) {
 		do {
 			struct request *rq;
 
@@ -234,31 +245,33 @@ void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
 
-bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio)
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
+			    struct request **merged_request)
 {
 	struct request *rq;
-	int ret;
 
-	ret = elv_merge(q, &rq, bio);
+	switch (elv_merge(q, &rq, bio)) {
-	if (ret == ELEVATOR_BACK_MERGE) {
+	case ELEVATOR_BACK_MERGE:
 		if (!blk_mq_sched_allow_merge(q, rq, bio))
 			return false;
-		if (bio_attempt_back_merge(q, rq, bio)) {
+		if (!bio_attempt_back_merge(q, rq, bio))
-			if (!attempt_back_merge(q, rq))
+			return false;
-				elv_merged_request(q, rq, ret);
+		*merged_request = attempt_back_merge(q, rq);
-			return true;
+		if (!*merged_request)
-		}
+			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
-	} else if (ret == ELEVATOR_FRONT_MERGE) {
+		return true;
+	case ELEVATOR_FRONT_MERGE:
 		if (!blk_mq_sched_allow_merge(q, rq, bio))
 			return false;
-		if (bio_attempt_front_merge(q, rq, bio)) {
+		if (!bio_attempt_front_merge(q, rq, bio))
-			if (!attempt_front_merge(q, rq))
+			return false;
-				elv_merged_request(q, rq, ret);
+		*merged_request = attempt_front_merge(q, rq);
-			return true;
+		if (!*merged_request)
-		}
+			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
+		return true;
+	default:
+		return false;
 	}
-
-	return false;
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
 
@@ -289,7 +302,8 @@ void blk_mq_sched_request_inserted(struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
 
-bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
+				       struct request *rq)
 {
 	if (rq->tag == -1) {
 		rq->rq_flags |= RQF_SORTED;
@@ -305,7 +319,6 @@ bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	spin_unlock(&hctx->lock);
 	return true;
 }
-EXPORT_SYMBOL_GPL(blk_mq_sched_bypass_insert);
 
 static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 {
@@ -347,7 +360,7 @@ static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx,
 		blk_insert_flush(rq);
 		blk_mq_run_hw_queue(hctx, true);
 	} else
-		blk_mq_add_to_requeue_list(rq, true, true);
+		blk_mq_add_to_requeue_list(rq, false, true);
 }
 
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
@@ -363,6 +376,9 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 		return;
 	}
 
+	if (e && blk_mq_sched_bypass_insert(hctx, rq))
+		goto run;
+
 	if (e && e->type->ops.mq.insert_requests) {
 		LIST_HEAD(list);
 
@@ -374,6 +390,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 		spin_unlock(&ctx->lock);
 	}
 
+run:
 	if (run_queue)
 		blk_mq_run_hw_queue(hctx, async);
 }
@@ -385,6 +402,23 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
 	struct elevator_queue *e = hctx->queue->elevator;
 
+	if (e) {
+		struct request *rq, *next;
+
+		/*
+		 * We bypass requests that already have a driver tag assigned,
+		 * which should only be flushes. Flushes are only ever inserted
+		 * as single requests, so we shouldn't ever hit the
+		 * WARN_ON_ONCE() below (but let's handle it just in case).
+		 */
+		list_for_each_entry_safe(rq, next, list, queuelist) {
+			if (WARN_ON_ONCE(rq->tag != -1)) {
+				list_del_init(&rq->queuelist);
+				blk_mq_sched_bypass_insert(hctx, rq);
+			}
+		}
+	}
+
 	if (e && e->type->ops.mq.insert_requests)
 		e->type->ops.mq.insert_requests(hctx, list, false);
 	else

block/blk-mq-sched.h

@@ -15,8 +15,8 @@ struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bi
 void blk_mq_sched_put_request(struct request *rq);
 
 void blk_mq_sched_request_inserted(struct request *rq);
-bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, struct request *rq);
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
-bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio);
+				struct request **merged_request);
 bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
 bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
 void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
@@ -49,12 +49,13 @@ blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 }
 
 static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
-					   struct request *rq)
+					   struct request *rq,
+					   struct bio *bio)
 {
 	struct elevator_queue *e = q->elevator;
 
 	if (e && e->type->ops.mq.get_rq_priv)
-		return e->type->ops.mq.get_rq_priv(q, rq);
+		return e->type->ops.mq.get_rq_priv(q, rq, bio);
 
 	return 0;
 }

block/blk-mq-sysfs.c

@@ -254,7 +254,7 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 		kobject_put(&hctx->kobj);
 	}
 
-	blk_mq_debugfs_unregister(q);
+	blk_mq_debugfs_unregister_hctxs(q);
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);

block/blk-mq.c

@@ -199,13 +199,7 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->special = NULL;
 	/* tag was already set */
 	rq->errors = 0;
-
-	rq->cmd = rq->__cmd;
-
 	rq->extra_len = 0;
-	rq->sense_len = 0;
-	rq->resid_len = 0;
-	rq->sense = NULL;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->timeout = 0;
@@ -487,10 +481,6 @@ void blk_mq_start_request(struct request *rq)
 
 	trace_block_rq_issue(q, rq);
 
-	rq->resid_len = blk_rq_bytes(rq);
-	if (unlikely(blk_bidi_rq(rq)))
-		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
-
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		blk_stat_set_issue_time(&rq->issue_stat);
 		rq->rq_flags |= RQF_STATS;
@@ -773,7 +763,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 	int checked = 8;
 
 	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
-		int el_ret;
+		bool merged = false;
 
 		if (!checked--)
 			break;
@@ -781,26 +771,25 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 		if (!blk_rq_merge_ok(rq, bio))
 			continue;
 
-		el_ret = blk_try_merge(rq, bio);
+		switch (blk_try_merge(rq, bio)) {
-		if (el_ret == ELEVATOR_NO_MERGE)
+		case ELEVATOR_BACK_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_back_merge(q, rq, bio);
+			break;
+		case ELEVATOR_FRONT_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_front_merge(q, rq, bio);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
 			continue;
-
-		if (!blk_mq_sched_allow_merge(q, rq, bio))
-			break;
-
-		if (el_ret == ELEVATOR_BACK_MERGE) {
-			if (bio_attempt_back_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
-			break;
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-			if (bio_attempt_front_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
-			break;
 		}
+
+		if (merged)
+			ctx->rq_merged++;
+		return merged;
 	}
 
 	return false;
@@ -1013,7 +1002,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 			blk_mq_run_hw_queue(hctx, true);
 	}
 
-	return ret != BLK_MQ_RQ_QUEUE_BUSY;
+	return queued != 0;
 }
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
@@ -1442,12 +1431,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
-		blk_mq_put_ctx(data.ctx);
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		blk_mq_run_hw_queue(data.hctx, true);
+		goto run_queue;
-		goto done;
 	}
 
 	plug = current->plug;
@@ -1497,6 +1485,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	if (q->elevator) {
+elv_insert:
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_sched_insert_request(rq, false, true,
@@ -1510,6 +1499,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
+run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 	blk_mq_put_ctx(data.ctx);
@@ -1565,12 +1555,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
-		blk_mq_put_ctx(data.ctx);
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_get_driver_tag(rq, NULL, true);
 		blk_insert_flush(rq);
-		blk_mq_run_hw_queue(data.hctx, true);
+		goto run_queue;
-		goto done;
 	}
 
 	/*
@@ -1608,6 +1597,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	if (q->elevator) {
+elv_insert:
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_sched_insert_request(rq, false, true,
@@ -1621,6 +1611,7 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		 * latter allows for merging opportunities and more efficient
 		 * dispatching.
 		 */
+run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
 
@@ -2637,10 +2628,14 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 
+		/*
+		 * Manually set the make_request_fn as blk_queue_make_request
+		 * resets a lot of the queue settings.
+		 */
 		if (q->nr_hw_queues > 1)
-			blk_queue_make_request(q, blk_mq_make_request);
+			q->make_request_fn = blk_mq_make_request;
 		else
-			blk_queue_make_request(q, blk_sq_make_request);
+			q->make_request_fn = blk_sq_make_request;
 
 		blk_mq_queue_reinit(q, cpu_online_mask);
 	}
@@ -2824,8 +2819,6 @@ void blk_mq_enable_hotplug(void)
 
 static int __init blk_mq_init(void)
 {
-	blk_mq_debugfs_init();
-
 	cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL,
 				blk_mq_hctx_notify_dead);
 

block/blk-mq.h

@@ -85,16 +85,11 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
  * debugfs helpers
  */
 #ifdef CONFIG_BLK_DEBUG_FS
-void blk_mq_debugfs_init(void);
 int blk_mq_debugfs_register(struct request_queue *q, const char *name);
 void blk_mq_debugfs_unregister(struct request_queue *q);
 int blk_mq_debugfs_register_hctxs(struct request_queue *q);
 void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
 #else
-static inline void blk_mq_debugfs_init(void)
-{
-}
-
 static inline int blk_mq_debugfs_register(struct request_queue *q,
 					  const char *name)
 {

block/blk-settings.c

@@ -88,6 +88,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
 void blk_set_default_limits(struct queue_limits *lim)
 {
 	lim->max_segments = BLK_MAX_SEGMENTS;
+	lim->max_discard_segments = 1;
 	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
@@ -128,6 +129,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	/* Inherit limits from component devices */
 	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
+	lim->max_discard_segments = 1;
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
@@ -253,7 +255,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
 	max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
 	limits->max_sectors = max_sectors;
-	q->backing_dev_info.io_pages = max_sectors >> (PAGE_SHIFT - 9);
+	q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -336,6 +338,22 @@ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments
 }
 EXPORT_SYMBOL(blk_queue_max_segments);
 
+/**
+ * blk_queue_max_discard_segments - set max segments for discard requests
+ * @q:  the request queue for the device
+ * @max_segments:  max number of segments
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the number of
+ *    segments in a discard request.
+ **/
+void blk_queue_max_discard_segments(struct request_queue *q,
+		unsigned short max_segments)
+{
+	q->limits.max_discard_segments = max_segments;
+}
+EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments);
+
 /**
  * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
  * @q:  the request queue for the device
@@ -553,6 +571,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 					    b->virt_boundary_mask);
 
 	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
+	t->max_discard_segments = min_not_zero(t->max_discard_segments,
+					       b->max_discard_segments);
 	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
 						 b->max_integrity_segments);
 

block/blk-sysfs.c

@@ -89,7 +89,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_ra_show(struct request_queue *q, char *page)
 {
-	unsigned long ra_kb = q->backing_dev_info.ra_pages <<
+	unsigned long ra_kb = q->backing_dev_info->ra_pages <<
 					(PAGE_SHIFT - 10);
 
 	return queue_var_show(ra_kb, (page));
@@ -104,7 +104,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
-	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_SHIFT - 10);
+	q->backing_dev_info->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
 
 	return ret;
 }
@@ -121,6 +121,12 @@ static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
 	return queue_var_show(queue_max_segments(q), (page));
 }
 
+static ssize_t queue_max_discard_segments_show(struct request_queue *q,
+		char *page)
+{
+	return queue_var_show(queue_max_discard_segments(q), (page));
+}
+
 static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(q->limits.max_integrity_segments, (page));
@@ -236,7 +242,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 
 	spin_lock_irq(q->queue_lock);
 	q->limits.max_sectors = max_sectors_kb << 1;
-	q->backing_dev_info.io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
+	q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -545,6 +551,11 @@ static struct queue_sysfs_entry queue_max_segments_entry = {
 	.show = queue_max_segments_show,
 };
 
+static struct queue_sysfs_entry queue_max_discard_segments_entry = {
+	.attr = {.name = "max_discard_segments", .mode = S_IRUGO },
+	.show = queue_max_discard_segments_show,
+};
+
 static struct queue_sysfs_entry queue_max_integrity_segments_entry = {
 	.attr = {.name = "max_integrity_segments", .mode = S_IRUGO },
 	.show = queue_max_integrity_segments_show,
@@ -697,6 +708,7 @@ static struct attribute *default_attrs[] = {
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
 	&queue_max_segments_entry.attr,
+	&queue_max_discard_segments_entry.attr,
 	&queue_max_integrity_segments_entry.attr,
 	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
@@ -799,7 +811,7 @@ static void blk_release_queue(struct kobject *kobj)
 		container_of(kobj, struct request_queue, kobj);
 
 	wbt_exit(q);
-	bdi_exit(&q->backing_dev_info);
+	bdi_put(q->backing_dev_info);
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
@@ -814,13 +826,19 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
-	if (!q->mq_ops)
+	if (!q->mq_ops) {
+		if (q->exit_rq_fn)
+			q->exit_rq_fn(q, q->fq->flush_rq);
 		blk_free_flush_queue(q->fq);
-	else
+	} else {
 		blk_mq_release(q);
+	}
 
 	blk_trace_shutdown(q);
 
+	if (q->mq_ops)
+		blk_mq_debugfs_unregister(q);
+
 	if (q->bio_split)
 		bioset_free(q->bio_split);
 
@@ -884,32 +902,36 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
+	if (q->mq_ops)
+		blk_mq_register_dev(dev, q);
+
+	/* Prevent changes through sysfs until registration is completed. */
+	mutex_lock(&q->sysfs_lock);
+
 	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0) {
 		blk_trace_remove_sysfs(dev);
-		return ret;
+		goto unlock;
 	}
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
-	if (q->mq_ops)
-		blk_mq_register_dev(dev, q);
-
 	blk_wb_init(q);
 
-	if (!q->request_fn)
+	if (q->request_fn || (q->mq_ops && q->elevator)) {
-		return 0;
+		ret = elv_register_queue(q);
-
+		if (ret) {
-	ret = elv_register_queue(q);
+			kobject_uevent(&q->kobj, KOBJ_REMOVE);
-	if (ret) {
+			kobject_del(&q->kobj);
-		kobject_uevent(&q->kobj, KOBJ_REMOVE);
+			blk_trace_remove_sysfs(dev);
-		kobject_del(&q->kobj);
+			kobject_put(&dev->kobj);
-		blk_trace_remove_sysfs(dev);
+			goto unlock;
-		kobject_put(&dev->kobj);
+		}
-		return ret;
 	}
-
+	ret = 0;
-	return 0;
+unlock:
+	mutex_unlock(&q->sysfs_lock);
+	return ret;
 }
 
 void blk_unregister_queue(struct gendisk *disk)
@@ -922,7 +944,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
 
-	if (q->request_fn)
+	if (q->request_fn || (q->mq_ops && q->elevator))
 		elv_unregister_queue(q);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);

block/blk-wbt.c

@@ -96,7 +96,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info.wb;
+	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -279,7 +279,7 @@ enum {
 
 static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 	u64 thislat;
 
 	/*
@@ -339,7 +339,7 @@ static int latency_exceeded(struct rq_wb *rwb)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 
 	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
 			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
@@ -423,7 +423,7 @@ static void wb_timer_fn(unsigned long data)
 
 	status = latency_exceeded(rwb);
 
-	trace_wbt_timer(&rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
 			inflight);
 
 	/*

block/blk.h

@@ -14,6 +14,10 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
+#ifdef CONFIG_DEBUG_FS
+extern struct dentry *blk_debugfs_root;
+#endif
+
 struct blk_flush_queue {
 	unsigned int		flush_queue_delayed:1;
 	unsigned int		flush_pending_idx:1;
@@ -96,6 +100,8 @@ bool bio_attempt_front_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);
+bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
+		struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 			    unsigned int *request_count,
 			    struct request **same_queue_rq);
@@ -204,14 +210,14 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		     struct bio *bio);
 int ll_front_merge_fn(struct request_queue *q, struct request *req, 
 		      struct bio *bio);
-int attempt_back_merge(struct request_queue *q, struct request *rq);
+struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
-int attempt_front_merge(struct request_queue *q, struct request *rq);
+struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 				struct request *next);
 void blk_recalc_rq_segments(struct request *rq);
 void blk_rq_set_mixed_merge(struct request *rq);
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
-int blk_try_merge(struct request *rq, struct bio *bio);
+enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
@@ -249,7 +255,14 @@ static inline int blk_do_io_stat(struct request *rq)
 {
 	return rq->rq_disk &&
 	       (rq->rq_flags & RQF_IO_STAT) &&
-		(rq->cmd_type == REQ_TYPE_FS);
+		!blk_rq_is_passthrough(rq);
+}
+
+static inline void req_set_nomerge(struct request_queue *q, struct request *req)
+{
+	req->cmd_flags |= REQ_NOMERGE;
+	if (req == q->last_merge)
+		q->last_merge = NULL;
 }
 
 /*

block/bsg-lib.c

@@ -71,22 +71,24 @@ void bsg_job_done(struct bsg_job *job, int result,
 {
 	struct request *req = job->req;
 	struct request *rsp = req->next_rq;
+	struct scsi_request *rq = scsi_req(req);
 	int err;
 
 	err = job->req->errors = result;
 	if (err < 0)
 		/* we're only returning the result field in the reply */
-		job->req->sense_len = sizeof(u32);
+		rq->sense_len = sizeof(u32);
 	else
-		job->req->sense_len = job->reply_len;
+		rq->sense_len = job->reply_len;
 	/* we assume all request payload was transferred, residual == 0 */
-	req->resid_len = 0;
+	rq->resid_len = 0;
 
 	if (rsp) {
-		WARN_ON(reply_payload_rcv_len > rsp->resid_len);
+		WARN_ON(reply_payload_rcv_len > scsi_req(rsp)->resid_len);
 
 		/* set reply (bidi) residual */
-		rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len);
+		scsi_req(rsp)->resid_len -=
+			min(reply_payload_rcv_len, scsi_req(rsp)->resid_len);
 	}
 	blk_complete_request(req);
 }
@@ -113,6 +115,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
 	if (!buf->sg_list)
 		return -ENOMEM;
 	sg_init_table(buf->sg_list, req->nr_phys_segments);
+	scsi_req(req)->resid_len = blk_rq_bytes(req);
 	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
 	buf->payload_len = blk_rq_bytes(req);
 	return 0;
@@ -127,6 +130,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
 {
 	struct request *rsp = req->next_rq;
 	struct request_queue *q = req->q;
+	struct scsi_request *rq = scsi_req(req);
 	struct bsg_job *job;
 	int ret;
 
@@ -140,9 +144,9 @@ static int bsg_create_job(struct device *dev, struct request *req)
 	job->req = req;
 	if (q->bsg_job_size)
 		job->dd_data = (void *)&job[1];
-	job->request = req->cmd;
+	job->request = rq->cmd;
-	job->request_len = req->cmd_len;
+	job->request_len = rq->cmd_len;
-	job->reply = req->sense;
+	job->reply = rq->sense;
 	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
 						 * allocated */
 	if (req->bio) {
@@ -177,7 +181,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
  *
  * Drivers/subsys should pass this to the queue init function.
  */
-void bsg_request_fn(struct request_queue *q)
+static void bsg_request_fn(struct request_queue *q)
 	__releases(q->queue_lock)
 	__acquires(q->queue_lock)
 {
@@ -214,24 +218,30 @@ void bsg_request_fn(struct request_queue *q)
 	put_device(dev);
 	spin_lock_irq(q->queue_lock);
 }
-EXPORT_SYMBOL_GPL(bsg_request_fn);
 
 /**
  * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
  * @dev: device to attach bsg device to
- * @q: request queue setup by caller
  * @name: device to give bsg device
  * @job_fn: bsg job handler
  * @dd_job_size: size of LLD data needed for each job
- *
- * The caller should have setup the reuqest queue with bsg_request_fn
- * as the request_fn.
  */
-int bsg_setup_queue(struct device *dev, struct request_queue *q,
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
-		    char *name, bsg_job_fn *job_fn, int dd_job_size)
+		bsg_job_fn *job_fn, int dd_job_size)
 {
+	struct request_queue *q;
 	int ret;
 
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
+		return ERR_PTR(-ENOMEM);
+	q->cmd_size = sizeof(struct scsi_request);
+	q->request_fn = bsg_request_fn;
+
+	ret = blk_init_allocated_queue(q);
+	if (ret)
+		goto out_cleanup_queue;
+
 	q->queuedata = dev;
 	q->bsg_job_size = dd_job_size;
 	q->bsg_job_fn = job_fn;
@@ -243,9 +253,12 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q,
 	if (ret) {
 		printk(KERN_ERR "%s: bsg interface failed to "
 		       "initialize - register queue\n", dev->kobj.name);
-		return ret;
+		goto out_cleanup_queue;
 	}
 
-	return 0;
+	return q;
+out_cleanup_queue:
+	blk_cleanup_queue(q);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(bsg_setup_queue);

block/bsg.c

@@ -85,7 +85,6 @@ struct bsg_command {
 	struct bio *bidi_bio;
 	int err;
 	struct sg_io_v4 hdr;
-	char sense[SCSI_SENSE_BUFFERSIZE];
 };
 
 static void bsg_free_command(struct bsg_command *bc)
@@ -140,18 +139,20 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
 				fmode_t has_write_perm)
 {
+	struct scsi_request *req = scsi_req(rq);
+
 	if (hdr->request_len > BLK_MAX_CDB) {
-		rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
+		req->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
-		if (!rq->cmd)
+		if (!req->cmd)
 			return -ENOMEM;
 	}
 
-	if (copy_from_user(rq->cmd, (void __user *)(unsigned long)hdr->request,
+	if (copy_from_user(req->cmd, (void __user *)(unsigned long)hdr->request,
 			   hdr->request_len))
 		return -EFAULT;
 
 	if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
-		if (blk_verify_command(rq->cmd, has_write_perm))
+		if (blk_verify_command(req->cmd, has_write_perm))
 			return -EPERM;
 	} else if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
@@ -159,7 +160,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 	/*
 	 * fill in request structure
 	 */
-	rq->cmd_len = hdr->request_len;
+	req->cmd_len = hdr->request_len;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -176,7 +177,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
  * Check if sg_io_v4 from user is allowed and valid
  */
 static int
-bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
+bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *op)
 {
 	int ret = 0;
 
@@ -197,7 +198,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
 		ret = -EINVAL;
 	}
 
-	*rw = hdr->dout_xfer_len ? WRITE : READ;
+	*op = hdr->dout_xfer_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN;
 	return ret;
 }
 
@@ -205,13 +206,12 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
-	    u8 *sense)
 {
 	struct request_queue *q = bd->queue;
 	struct request *rq, *next_rq = NULL;
-	int ret, rw;
+	int ret;
-	unsigned int dxfer_len;
+	unsigned int op, dxfer_len;
 	void __user *dxferp = NULL;
 	struct bsg_class_device *bcd = &q->bsg_dev;
 
@@ -226,36 +226,35 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
 		hdr->din_xfer_len);
 
-	ret = bsg_validate_sgv4_hdr(hdr, &rw);
+	ret = bsg_validate_sgv4_hdr(hdr, &op);
 	if (ret)
 		return ERR_PTR(ret);
 
 	/*
 	 * map scatter-gather elements separately and string them to request
 	 */
-	rq = blk_get_request(q, rw, GFP_KERNEL);
+	rq = blk_get_request(q, op, GFP_KERNEL);
 	if (IS_ERR(rq))
 		return rq;
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
 	if (ret)
 		goto out;
 
-	if (rw == WRITE && hdr->din_xfer_len) {
+	if (op == REQ_OP_SCSI_OUT && hdr->din_xfer_len) {
 		if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) {
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
 
-		next_rq = blk_get_request(q, READ, GFP_KERNEL);
+		next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 		if (IS_ERR(next_rq)) {
 			ret = PTR_ERR(next_rq);
 			next_rq = NULL;
 			goto out;
 		}
 		rq->next_rq = next_rq;
-		next_rq->cmd_type = rq->cmd_type;
 
 		dxferp = (void __user *)(unsigned long)hdr->din_xferp;
 		ret =  blk_rq_map_user(q, next_rq, NULL, dxferp,
@@ -280,13 +279,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 			goto out;
 	}
 
-	rq->sense = sense;
-	rq->sense_len = 0;
-
 	return rq;
 out:
-	if (rq->cmd != rq->__cmd)
+	scsi_req_free_cmd(scsi_req(rq));
-		kfree(rq->cmd);
 	blk_put_request(rq);
 	if (next_rq) {
 		blk_rq_unmap_user(next_rq->bio);
@@ -393,6 +388,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
 static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 				    struct bio *bio, struct bio *bidi_bio)
 {
+	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
 	dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
@@ -407,12 +403,12 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		hdr->info |= SG_INFO_CHECK;
 	hdr->response_len = 0;
 
-	if (rq->sense_len && hdr->response) {
+	if (req->sense_len && hdr->response) {
 		int len = min_t(unsigned int, hdr->max_response_len,
-					rq->sense_len);
+					req->sense_len);
 
 		ret = copy_to_user((void __user *)(unsigned long)hdr->response,
-				   rq->sense, len);
+				   req->sense, len);
 		if (!ret)
 			hdr->response_len = len;
 		else
@@ -420,14 +416,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	}
 
 	if (rq->next_rq) {
-		hdr->dout_resid = rq->resid_len;
+		hdr->dout_resid = req->resid_len;
-		hdr->din_resid = rq->next_rq->resid_len;
+		hdr->din_resid = scsi_req(rq->next_rq)->resid_len;
 		blk_rq_unmap_user(bidi_bio);
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
-		hdr->din_resid = rq->resid_len;
+		hdr->din_resid = req->resid_len;
 	else
-		hdr->dout_resid = rq->resid_len;
+		hdr->dout_resid = req->resid_len;
 
 	/*
 	 * If the request generated a negative error number, return it
@@ -439,8 +435,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		ret = rq->errors;
 
 	blk_rq_unmap_user(bio);
-	if (rq->cmd != rq->__cmd)
+	scsi_req_free_cmd(req);
-		kfree(rq->cmd);
 	blk_put_request(rq);
 
 	return ret;
@@ -625,7 +620,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf,
 		/*
 		 * get a request, fill in the blanks, and add to request queue
 		 */
-		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm, bc->sense);
+		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			rq = NULL;
@@ -911,12 +906,11 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
 		int at_head;
-		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
 			return -EFAULT;
 
-		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE, sense);
+		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 

block/cfq-iosched.c

@@ -2528,7 +2528,7 @@ static void cfq_remove_request(struct request *rq)
 	}
 }
 
-static int cfq_merge(struct request_queue *q, struct request **req,
+static enum elv_merge cfq_merge(struct request_queue *q, struct request **req,
 		     struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
@@ -2544,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 }
 
 static void cfq_merged_request(struct request_queue *q, struct request *req,
-			       int type)
+			       enum elv_merge type)
 {
 	if (type == ELEVATOR_FRONT_MERGE) {
 		struct cfq_queue *cfqq = RQ_CFQQ(req);

block/compat_ioctl.c

@@ -661,7 +661,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct block_device *bdev = inode->i_bdev;
 	struct gendisk *disk = bdev->bd_disk;
 	fmode_t mode = file->f_mode;
-	struct backing_dev_info *bdi;
 	loff_t size;
 	unsigned int max_sectors;
 
@@ -708,9 +707,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFRAGET:
 		if (!arg)
 			return -EINVAL;
-		bdi = blk_get_backing_dev_info(bdev);
 		return compat_put_long(arg,
-				       (bdi->ra_pages * PAGE_SIZE) / 512);
+			       (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKROGET: /* compatible */
 		return compat_put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
@@ -728,8 +726,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdi = blk_get_backing_dev_info(bdev);
+		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
-		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKGETSIZE:
 		size = i_size_read(bdev->bd_inode);

block/deadline-iosched.c

@@ -120,12 +120,11 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq)
 	deadline_del_rq_rb(dd, rq);
 }
 
-static int
+static enum elv_merge
 deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct request *__rq;
-	int ret;
 
 	/*
 	 * check for front merge
@@ -138,20 +137,17 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 			BUG_ON(sector != blk_rq_pos(__rq));
 
 			if (elv_bio_merge_ok(__rq, bio)) {
-				ret = ELEVATOR_FRONT_MERGE;
+				*req = __rq;
-				goto out;
+				return ELEVATOR_FRONT_MERGE;
 			}
 		}
 	}
 
 	return ELEVATOR_NO_MERGE;
-out:
-	*req = __rq;
-	return ret;
 }
 
 static void deadline_merged_request(struct request_queue *q,
-				    struct request *req, int type)
+				    struct request *req, enum elv_merge type)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 

block/elevator.c

@@ -428,11 +428,11 @@ void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(elv_dispatch_add_tail);
 
-int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
+enum elv_merge elv_merge(struct request_queue *q, struct request **req,
+		struct bio *bio)
 {
 	struct elevator_queue *e = q->elevator;
 	struct request *__rq;
-	int ret;
 
 	/*
 	 * Levels of merges:
@@ -447,7 +447,8 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * First try one-hit cache.
 	 */
 	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
-		ret = blk_try_merge(q->last_merge, bio);
+		enum elv_merge ret = blk_try_merge(q->last_merge, bio);
+
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
 			return ret;
@@ -515,7 +516,8 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq)
 	return ret;
 }
 
-void elv_merged_request(struct request_queue *q, struct request *rq, int type)
+void elv_merged_request(struct request_queue *q, struct request *rq,
+		enum elv_merge type)
 {
 	struct elevator_queue *e = q->elevator;
 
@@ -539,7 +541,7 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 	if (e->uses_mq && e->type->ops.mq.requests_merged)
 		e->type->ops.mq.requests_merged(q, rq, next);
 	else if (e->type->ops.sq.elevator_merge_req_fn) {
-		next_sorted = next->rq_flags & RQF_SORTED;
+		next_sorted = (__force bool)(next->rq_flags & RQF_SORTED);
 		if (next_sorted)
 			e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
 	}
@@ -635,7 +637,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
 	if (rq->rq_flags & RQF_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(rq)) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}
@@ -677,7 +679,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		if (elv_attempt_insert_merge(q, rq))
 			break;
 	case ELEVATOR_INSERT_SORT:
-		BUG_ON(rq->cmd_type != REQ_TYPE_FS);
+		BUG_ON(blk_rq_is_passthrough(rq));
 		rq->rq_flags |= RQF_SORTED;
 		q->nr_sorted++;
 		if (rq_mergeable(rq)) {

block/genhd.c

@@ -572,6 +572,20 @@ static void register_disk(struct device *parent, struct gendisk *disk)
 	disk_part_iter_exit(&piter);
 }
 
+void put_disk_devt(struct disk_devt *disk_devt)
+{
+	if (disk_devt && atomic_dec_and_test(&disk_devt->count))
+		disk_devt->release(disk_devt);
+}
+EXPORT_SYMBOL(put_disk_devt);
+
+void get_disk_devt(struct disk_devt *disk_devt)
+{
+	if (disk_devt)
+		atomic_inc(&disk_devt->count);
+}
+EXPORT_SYMBOL(get_disk_devt);
+
 /**
  * device_add_disk - add partitioning information to kernel list
  * @parent: parent device for the disk
@@ -612,8 +626,15 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 
 	disk_alloc_events(disk);
 
+	/*
+	 * Take a reference on the devt and assign it to queue since it
+	 * must not be reallocated while the bdi is registered
+	 */
+	disk->queue->disk_devt = disk->disk_devt;
+	get_disk_devt(disk->disk_devt);
+
 	/* Register BDI before referencing it from bdev */
-	bdi = &disk->queue->backing_dev_info;
+	bdi = disk->queue->backing_dev_info;
 	bdi_register_owner(bdi, disk_to_dev(disk));
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
@@ -648,6 +669,8 @@ void del_gendisk(struct gendisk *disk)
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
+		bdev_unhash_inode(MKDEV(disk->major,
+					disk->first_minor + part->partno));
 		invalidate_partition(disk, part->partno);
 		delete_partition(disk, part->partno);
 	}

block/ioctl.c

@@ -505,7 +505,6 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			unsigned long arg)
 {
-	struct backing_dev_info *bdi;
 	void __user *argp = (void __user *)arg;
 	loff_t size;
 	unsigned int max_sectors;
@@ -532,8 +531,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFRAGET:
 		if (!arg)
 			return -EINVAL;
-		bdi = blk_get_backing_dev_info(bdev);
+		return put_long(arg, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
-		return put_long(arg, (bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
@@ -560,8 +558,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdi = blk_get_backing_dev_info(bdev);
+		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
-		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKBSZSET:
 		return blkdev_bszset(bdev, mode, argp);

block/mq-deadline.c

@@ -121,7 +121,7 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq)
 }
 
 static void dd_request_merged(struct request_queue *q, struct request *req,
-			      int type)
+			      enum elv_merge type)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 
@@ -371,12 +371,16 @@ static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
 {
 	struct request_queue *q = hctx->queue;
 	struct deadline_data *dd = q->elevator->elevator_data;
-	int ret;
+	struct request *free = NULL;
+	bool ret;
 
 	spin_lock(&dd->lock);
-	ret = blk_mq_sched_try_merge(q, bio);
+	ret = blk_mq_sched_try_merge(q, bio, &free);
 	spin_unlock(&dd->lock);
 
+	if (free)
+		blk_mq_free_request(free);
+
 	return ret;
 }
 
@@ -395,10 +399,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	blk_mq_sched_request_inserted(rq);
 
-	if (blk_mq_sched_bypass_insert(hctx, rq))
+	if (at_head || blk_rq_is_passthrough(rq)) {
-		return;
-
-	if (at_head || rq->cmd_type != REQ_TYPE_FS) {
 		if (at_head)
 			list_add(&rq->queuelist, &dd->dispatch);
 		else

block/scsi_ioctl.c

@@ -230,15 +230,17 @@ EXPORT_SYMBOL(blk_verify_command);
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 			     struct sg_io_hdr *hdr, fmode_t mode)
 {
-	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
+	struct scsi_request *req = scsi_req(rq);
+
+	if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
-	if (blk_verify_command(rq->cmd, mode & FMODE_WRITE))
+	if (blk_verify_command(req->cmd, mode & FMODE_WRITE))
 		return -EPERM;
 
 	/*
 	 * fill in request structure
 	 */
-	rq->cmd_len = hdr->cmd_len;
+	req->cmd_len = hdr->cmd_len;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -254,6 +256,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
+	struct scsi_request *req = scsi_req(rq);
 	int r, ret = 0;
 
 	/*
@@ -267,13 +270,13 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->resid_len;
+	hdr->resid = req->resid_len;
 	hdr->sb_len_wr = 0;
 
-	if (rq->sense_len && hdr->sbp) {
+	if (req->sense_len && hdr->sbp) {
-		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+		int len = min((unsigned int) hdr->mx_sb_len, req->sense_len);
 
-		if (!copy_to_user(hdr->sbp, rq->sense, len))
+		if (!copy_to_user(hdr->sbp, req->sense, len))
 			hdr->sb_len_wr = len;
 		else
 			ret = -EFAULT;
@@ -294,7 +297,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	int writing = 0;
 	int at_head = 0;
 	struct request *rq;
-	char sense[SCSI_SENSE_BUFFERSIZE];
+	struct scsi_request *req;
 	struct bio *bio;
 
 	if (hdr->interface_id != 'S')
@@ -318,14 +321,16 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		at_head = 1;
 
 	ret = -ENOMEM;
-	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
+	rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			GFP_KERNEL);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	if (hdr->cmd_len > BLK_MAX_CDB) {
-		rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
+		req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
-		if (!rq->cmd)
+		if (!req->cmd)
 			goto out_put_request;
 	}
 
@@ -357,9 +362,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		goto out_free_cdb;
 
 	bio = rq->bio;
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
 	rq->retries = 0;
 
 	start_time = jiffies;
@@ -375,8 +377,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	ret = blk_complete_sghdr_rq(rq, hdr, bio);
 
 out_free_cdb:
-	if (rq->cmd != rq->__cmd)
+	scsi_req_free_cmd(req);
-		kfree(rq->cmd);
 out_put_request:
 	blk_put_request(rq);
 	return ret;
@@ -420,9 +421,10 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		struct scsi_ioctl_command __user *sic)
 {
 	struct request *rq;
+	struct scsi_request *req;
 	int err;
 	unsigned int in_len, out_len, bytes, opcode, cmdlen;
-	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
+	char *buffer = NULL;
 
 	if (!sic)
 		return -EINVAL;
@@ -447,12 +449,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM);
+	rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			__GFP_RECLAIM);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
 	}
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	cmdlen = COMMAND_SIZE(opcode);
 
@@ -460,14 +464,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	 * get command and data to send to device, if any
 	 */
 	err = -EFAULT;
-	rq->cmd_len = cmdlen;
+	req->cmd_len = cmdlen;
-	if (copy_from_user(rq->cmd, sic->data, cmdlen))
+	if (copy_from_user(req->cmd, sic->data, cmdlen))
 		goto error;
 
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = blk_verify_command(rq->cmd, mode & FMODE_WRITE);
+	err = blk_verify_command(req->cmd, mode & FMODE_WRITE);
 	if (err)
 		goto error;
 
@@ -503,18 +507,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		goto error;
 	}
 
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
-
 	blk_execute_rq(q, disk, rq, 0);
 
 	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
-		if (rq->sense_len && rq->sense) {
+		if (req->sense_len && req->sense) {
-			bytes = (OMAX_SB_LEN > rq->sense_len) ?
+			bytes = (OMAX_SB_LEN > req->sense_len) ?
-				rq->sense_len : OMAX_SB_LEN;
+				req->sense_len : OMAX_SB_LEN;
-			if (copy_to_user(sic->data, rq->sense, bytes))
+			if (copy_to_user(sic->data, req->sense, bytes))
 				err = -EFAULT;
 		}
 	} else {
@@ -539,14 +539,14 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, WRITE, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
-	rq->cmd[0] = cmd;
+	scsi_req(rq)->cmd[0] = cmd;
-	rq->cmd[4] = data;
+	scsi_req(rq)->cmd[4] = data;
-	rq->cmd_len = 6;
+	scsi_req(rq)->cmd_len = 6;
 	err = blk_execute_rq(q, bd_disk, rq, 0);
 	blk_put_request(rq);
 
@@ -743,6 +743,17 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
 }
 EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
 
+void scsi_req_init(struct request *rq)
+{
+	struct scsi_request *req = scsi_req(rq);
+
+	memset(req->__cmd, 0, sizeof(req->__cmd));
+	req->cmd = req->__cmd;
+	req->cmd_len = BLK_MAX_CDB;
+	req->sense_len = 0;
+}
+EXPORT_SYMBOL(scsi_req_init);
+
 static int __init blk_scsi_ioctl_init(void)
 {
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);

drivers/ata/libata-scsi.c

@@ -1265,13 +1265,13 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
  */
 static int atapi_drain_needed(struct request *rq)
 {
-	if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC))
+	if (likely(!blk_rq_is_passthrough(rq)))
 		return 0;
 
 	if (!blk_rq_bytes(rq) || op_is_write(req_op(rq)))
 		return 0;
 
-	return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC;
+	return atapi_cmd_type(scsi_req(rq)->cmd[0]) == ATAPI_MISC;
 }
 
 static int ata_scsi_dev_config(struct scsi_device *sdev,

drivers/block/Kconfig

@@ -69,6 +69,7 @@ config AMIGA_Z2RAM
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
+	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
@@ -114,6 +115,7 @@ config BLK_CPQ_CISS_DA
 	tristate "Compaq Smart Array 5xxx support"
 	depends on PCI
 	select CHECK_SIGNATURE
+	select BLK_SCSI_REQUEST
 	help
 	  This is the driver for Compaq Smart Array 5xxx controllers.
 	  Everyone using these boards should say Y here.
@@ -386,6 +388,7 @@ config BLK_DEV_RAM_DAX
 config CDROM_PKTCDVD
 	tristate "Packet writing on CD/DVD media (DEPRECATED)"
 	depends on !UML
+	select BLK_SCSI_REQUEST
 	help
 	  Note: This driver is deprecated and will be removed from the
 	  kernel in the near future!
@@ -501,6 +504,16 @@ config VIRTIO_BLK
 	  This is the virtual block driver for virtio.  It can be used with
           lguest or QEMU based VMMs (like KVM or Xen).  Say Y or M.
 
+config VIRTIO_BLK_SCSI
+	bool "SCSI passthrough request for the Virtio block driver"
+	depends on VIRTIO_BLK
+	select BLK_SCSI_REQUEST
+	---help---
+	  Enable support for SCSI passthrough (e.g. the SG_IO ioctl) on
+	  virtio-blk devices.  This is only supported for the legacy
+	  virtio protocol and not enabled by default by any hypervisor.
+	  Your probably want to virtio-scsi instead.
+
 config BLK_DEV_HD
 	bool "Very old hard disk (MFM/RLL/IDE) driver"
 	depends on HAVE_IDE

drivers/block/aoe/aoeblk.c

@@ -396,8 +396,8 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
 	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
-	q->backing_dev_info.name = "aoe";
+	q->backing_dev_info->name = "aoe";
-	q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_SIZE;
+	q->backing_dev_info->ra_pages = READ_AHEAD / PAGE_SIZE;
 	d->bufpool = mp;
 	d->blkq = gd->queue = q;
 	q->queuedata = d;

drivers/block/cciss.c

@@ -52,6 +52,7 @@
 #include <scsi/scsi.h>
 #include <scsi/sg.h>
 #include <scsi/scsi_ioctl.h>
+#include <scsi/scsi_request.h>
 #include <linux/cdrom.h>
 #include <linux/scatterlist.h>
 #include <linux/kthread.h>
@@ -1853,8 +1854,8 @@ static void cciss_softirq_done(struct request *rq)
 	dev_dbg(&h->pdev->dev, "Done with %p\n", rq);
 
 	/* set the residual count for pc requests */
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	if (blk_rq_is_passthrough(rq))
-		rq->resid_len = c->err_info->ResidualCnt;
+		scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
 
 	blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
 
@@ -1941,9 +1942,16 @@ static void cciss_get_serial_no(ctlr_info_t *h, int logvol,
 static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 				int drv_index)
 {
-	disk->queue = blk_init_queue(do_cciss_request, &h->lock);
+	disk->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!disk->queue)
 		goto init_queue_failure;
+
+	disk->queue->cmd_size = sizeof(struct scsi_request);
+	disk->queue->request_fn = do_cciss_request;
+	disk->queue->queue_lock = &h->lock;
+	if (blk_init_allocated_queue(disk->queue) < 0)
+		goto cleanup_queue;
+
 	sprintf(disk->disk_name, "cciss/c%dd%d", h->ctlr, drv_index);
 	disk->major = h->major;
 	disk->first_minor = drv_index << NWD_SHIFT;
@@ -3075,7 +3083,7 @@ static inline int evaluate_target_status(ctlr_info_t *h,
 	driver_byte = DRIVER_OK;
 	msg_byte = cmd->err_info->CommandStatus; /* correct?  seems too device specific */
 
-	if (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	if (blk_rq_is_passthrough(cmd->rq))
 		host_byte = DID_PASSTHROUGH;
 	else
 		host_byte = DID_OK;
@@ -3084,7 +3092,7 @@ static inline int evaluate_target_status(ctlr_info_t *h,
 		host_byte, driver_byte);
 
 	if (cmd->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION) {
-		if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC)
+		if (!blk_rq_is_passthrough(cmd->rq))
 			dev_warn(&h->pdev->dev, "cmd %p "
 			       "has SCSI Status 0x%x\n",
 			       cmd, cmd->err_info->ScsiStatus);
@@ -3095,31 +3103,23 @@ static inline int evaluate_target_status(ctlr_info_t *h,
 	sense_key = 0xf & cmd->err_info->SenseInfo[2];
 	/* no status or recovered error */
 	if (((sense_key == 0x0) || (sense_key == 0x1)) &&
-	    (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC))
+	    !blk_rq_is_passthrough(cmd->rq))
 		error_value = 0;
 
 	if (check_for_unit_attention(h, cmd)) {
-		*retry_cmd = !(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC);
+		*retry_cmd = !blk_rq_is_passthrough(cmd->rq);
 		return 0;
 	}
 
 	/* Not SG_IO or similar? */
-	if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) {
+	if (!blk_rq_is_passthrough(cmd->rq)) {
 		if (error_value != 0)
 			dev_warn(&h->pdev->dev, "cmd %p has CHECK CONDITION"
 			       " sense key = 0x%x\n", cmd, sense_key);
 		return error_value;
 	}
 
-	/* SG_IO or similar, copy sense data back */
+	scsi_req(cmd->rq)->sense_len = cmd->err_info->SenseLen;
-	if (cmd->rq->sense) {
-		if (cmd->rq->sense_len > cmd->err_info->SenseLen)
-			cmd->rq->sense_len = cmd->err_info->SenseLen;
-		memcpy(cmd->rq->sense, cmd->err_info->SenseInfo,
-			cmd->rq->sense_len);
-	} else
-		cmd->rq->sense_len = 0;
-
 	return error_value;
 }
 
@@ -3146,15 +3146,14 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
 		break;
 	case CMD_DATA_UNDERRUN:
-		if (cmd->rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(cmd->rq)) {
 			dev_warn(&h->pdev->dev, "cmd %p has"
 			       " completed with data underrun "
 			       "reported\n", cmd);
-			cmd->rq->resid_len = cmd->err_info->ResidualCnt;
 		}
 		break;
 	case CMD_DATA_OVERRUN:
-		if (cmd->rq->cmd_type == REQ_TYPE_FS)
+		if (!blk_rq_is_passthrough(cmd->rq))
 			dev_warn(&h->pdev->dev, "cciss: cmd %p has"
 			       " completed with data overrun "
 			       "reported\n", cmd);
@@ -3164,7 +3163,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "reported invalid\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_PROTOCOL_ERR:
@@ -3172,7 +3171,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "protocol error\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_HARDWARE_ERR:
@@ -3180,7 +3179,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       " hardware error\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_CONNECTION_LOST:
@@ -3188,7 +3187,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "connection lost\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_ABORTED:
@@ -3196,7 +3195,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "aborted\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
 		break;
 	case CMD_ABORT_FAILED:
@@ -3204,7 +3203,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "abort failed\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_UNSOLICITED_ABORT:
@@ -3219,21 +3218,21 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 				"%p retried too many times\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
 		break;
 	case CMD_TIMEOUT:
 		dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_UNABORTABLE:
 		dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	default:
@@ -3242,7 +3241,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       cmd->err_info->CommandStatus);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 	}
 
@@ -3395,7 +3394,9 @@ static void do_cciss_request(struct request_queue *q)
 		c->Header.SGList = h->max_cmd_sgentries;
 	set_performant_mode(h, c);
 
-	if (likely(creq->cmd_type == REQ_TYPE_FS)) {
+	switch (req_op(creq)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
 		if(h->cciss_read == CCISS_READ_10) {
 			c->Request.CDB[1] = 0;
 			c->Request.CDB[2] = (start_blk >> 24) & 0xff; /* MSB */
@@ -3425,12 +3426,16 @@ static void do_cciss_request(struct request_queue *q)
 			c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[14] = c->Request.CDB[15] = 0;
 		}
-	} else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) {
+		break;
-		c->Request.CDBLen = creq->cmd_len;
+	case REQ_OP_SCSI_IN:
-		memcpy(c->Request.CDB, creq->cmd, BLK_MAX_CDB);
+	case REQ_OP_SCSI_OUT:
-	} else {
+		c->Request.CDBLen = scsi_req(creq)->cmd_len;
+		memcpy(c->Request.CDB, scsi_req(creq)->cmd, BLK_MAX_CDB);
+		scsi_req(creq)->sense = c->err_info->SenseInfo;
+		break;
+	default:
 		dev_warn(&h->pdev->dev, "bad request type %d\n",
-			creq->cmd_type);
+			creq->cmd_flags);
 		BUG();
 	}
 

drivers/block/drbd/drbd_main.c

@@ -2462,7 +2462,7 @@ static int drbd_congested(void *congested_data, int bdi_bits)
 
 	if (get_ldev(device)) {
 		q = bdev_get_queue(device->ldev->backing_bdev);
-		r = bdi_congested(&q->backing_dev_info, bdi_bits);
+		r = bdi_congested(q->backing_dev_info, bdi_bits);
 		put_ldev(device);
 		if (r)
 			reason = 'b';
@@ -2834,8 +2834,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	/* we have no partitions. we contain only ourselves. */
 	device->this_bdev->bd_contains = device->this_bdev;
 
-	q->backing_dev_info.congested_fn = drbd_congested;
+	q->backing_dev_info->congested_fn = drbd_congested;
-	q->backing_dev_info.congested_data = device;
+	q->backing_dev_info->congested_data = device;
 
 	blk_queue_make_request(q, drbd_make_request);
 	blk_queue_write_cache(q, true, true);

drivers/block/drbd/drbd_nl.c

@@ -1328,11 +1328,13 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 	if (b) {
 		blk_queue_stack_limits(q, b);
 
-		if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
+		if (q->backing_dev_info->ra_pages !=
+		    b->backing_dev_info->ra_pages) {
 			drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
-				 q->backing_dev_info.ra_pages,
+				 q->backing_dev_info->ra_pages,
-				 b->backing_dev_info.ra_pages);
+				 b->backing_dev_info->ra_pages);
-			q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
+			q->backing_dev_info->ra_pages =
+						b->backing_dev_info->ra_pages;
 		}
 	}
 	fixup_discard_if_not_supported(q);
@@ -3345,7 +3347,7 @@ static void device_to_statistics(struct device_statistics *s,
 		s->dev_disk_flags = md->flags;
 		q = bdev_get_queue(device->ldev->backing_bdev);
 		s->dev_lower_blocked =
-			bdi_congested(&q->backing_dev_info,
+			bdi_congested(q->backing_dev_info,
 				      (1 << WB_async_congested) |
 				      (1 << WB_sync_congested));
 		put_ldev(device);

drivers/block/drbd/drbd_proc.c

@@ -288,7 +288,7 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
 		} else {
 			/* reset device->congestion_reason */
-			bdi_rw_congested(&device->rq_queue->backing_dev_info);
+			bdi_rw_congested(device->rq_queue->backing_dev_info);
 
 			nc = rcu_dereference(first_peer_device(device)->connection->net_conf);
 			wp = nc ? nc->wire_protocol - DRBD_PROT_A + 'A' : ' ';

drivers/block/drbd/drbd_req.c

@@ -938,7 +938,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se
 
 	switch (rbm) {
 	case RB_CONGESTED_REMOTE:
-		bdi = &device->ldev->backing_bdev->bd_disk->queue->backing_dev_info;
+		bdi = device->ldev->backing_bdev->bd_disk->queue->backing_dev_info;
 		return bdi_read_congested(bdi);
 	case RB_LEAST_PENDING:
 		return atomic_read(&device->local_cnt) >

drivers/block/floppy.c

@@ -2900,8 +2900,8 @@ static void do_fd_request(struct request_queue *q)
 		return;
 
 	if (WARN(atomic_read(&usage_count) == 0,
-		 "warning: usage count=0, current_req=%p sect=%ld type=%x flags=%llx\n",
+		 "warning: usage count=0, current_req=%p sect=%ld flags=%llx\n",
-		 current_req, (long)blk_rq_pos(current_req), current_req->cmd_type,
+		 current_req, (long)blk_rq_pos(current_req),
 		 (unsigned long long) current_req->cmd_flags))
 		return;
 

drivers/block/hd.c

@@ -626,30 +626,29 @@ static void hd_request(void)
 		req_data_dir(req) == READ ? "read" : "writ",
 		cyl, head, sec, nsect, bio_data(req->bio));
 #endif
-	if (req->cmd_type == REQ_TYPE_FS) {
+
-		switch (rq_data_dir(req)) {
+	switch (req_op(req)) {
-		case READ:
+	case REQ_OP_READ:
-			hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
+		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
-				&read_intr);
+			&read_intr);
-			if (reset)
+		if (reset)
-				goto repeat;
+			goto repeat;
-			break;
+		break;
-		case WRITE:
+	case REQ_OP_WRITE:
-			hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
+		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
-				&write_intr);
+			&write_intr);
-			if (reset)
+		if (reset)
-				goto repeat;
+			goto repeat;
-			if (wait_DRQ()) {
+		if (wait_DRQ()) {
-				bad_rw_intr();
+			bad_rw_intr();
-				goto repeat;
+			goto repeat;
-			}
-			outsw(HD_DATA, bio_data(req->bio), 256);
-			break;
-		default:
-			printk("unknown hd-command\n");
-			hd_end_request_cur(-EIO);
-			break;
 		}
+		outsw(HD_DATA, bio_data(req->bio), 256);
+		break;
+	default:
+		printk("unknown hd-command\n");
+		hd_end_request_cur(-EIO);
+		break;
 	}
 }
 

drivers/block/mg_disk.c

@@ -670,15 +670,17 @@ static void mg_request_poll(struct request_queue *q)
 				break;
 		}
 
-		if (unlikely(host->req->cmd_type != REQ_TYPE_FS)) {
+		switch (req_op(host->req)) {
-			mg_end_request_cur(host, -EIO);
+		case REQ_OP_READ:
-			continue;
-		}
-
-		if (rq_data_dir(host->req) == READ)
 			mg_read(host->req);
-		else
+			break;
+		case REQ_OP_WRITE:
 			mg_write(host->req);
+			break;
+		default:
+			mg_end_request_cur(host, -EIO);
+			break;
+		}
 	}
 }
 
@@ -687,13 +689,15 @@ static unsigned int mg_issue_req(struct request *req,
 		unsigned int sect_num,
 		unsigned int sect_cnt)
 {
-	if (rq_data_dir(req) == READ) {
+	switch (req_op(host->req)) {
+	case REQ_OP_READ:
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
 				!= MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return host->error;
 		}
-	} else {
+		break;
+	case REQ_OP_WRITE:
 		/* TODO : handler */
 		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
@@ -712,6 +716,10 @@ static unsigned int mg_issue_req(struct request *req,
 		mod_timer(&host->timer, jiffies + 3 * HZ);
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
+		break;
+	default:
+		mg_end_request_cur(host, -EIO);
+		break;
 	}
 	return MG_ERR_NONE;
 }
@@ -753,11 +761,6 @@ static void mg_request(struct request_queue *q)
 			continue;
 		}
 
-		if (unlikely(req->cmd_type != REQ_TYPE_FS)) {
-			mg_end_request_cur(host, -EIO);
-			continue;
-		}
-
 		if (!mg_issue_req(req, host, sect_num, sect_cnt))
 			return;
 	}

drivers/block/nbd.c

@@ -41,6 +41,9 @@
 
 #include <linux/nbd.h>
 
+static DEFINE_IDR(nbd_index_idr);
+static DEFINE_MUTEX(nbd_index_mutex);
+
 struct nbd_sock {
 	struct socket *sock;
 	struct mutex tx_lock;
@@ -89,8 +92,9 @@ static struct dentry *nbd_dbg_dir;
 #define NBD_MAGIC 0x68797548
 
 static unsigned int nbds_max = 16;
-static struct nbd_device *nbd_dev;
 static int max_part;
+static struct workqueue_struct *recv_workqueue;
+static int part_shift;
 
 static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 {
@@ -193,13 +197,6 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
 	req->errors++;
 
-	/*
-	 * If our disconnect packet times out then we're already holding the
-	 * config_lock and could deadlock here, so just set an error and return,
-	 * we'll handle shutting everything down later.
-	 */
-	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
-		return BLK_EH_HANDLED;
 	mutex_lock(&nbd->config_lock);
 	sock_shutdown(nbd);
 	mutex_unlock(&nbd->config_lock);
@@ -278,14 +275,29 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	u32 type;
 	u32 tag = blk_mq_unique_tag(req);
 
-	if (req_op(req) == REQ_OP_DISCARD)
+	switch (req_op(req)) {
+	case REQ_OP_DISCARD:
 		type = NBD_CMD_TRIM;
-	else if (req_op(req) == REQ_OP_FLUSH)
+		break;
+	case REQ_OP_FLUSH:
 		type = NBD_CMD_FLUSH;
-	else if (rq_data_dir(req) == WRITE)
+		break;
+	case REQ_OP_WRITE:
 		type = NBD_CMD_WRITE;
-	else
+		break;
+	case REQ_OP_READ:
 		type = NBD_CMD_READ;
+		break;
+	default:
+		return -EIO;
+	}
+
+	if (rq_data_dir(req) == WRITE &&
+	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
+		dev_err_ratelimited(disk_to_dev(nbd->disk),
+				    "Write on read-only\n");
+		return -EIO;
+	}
 
 	memset(&request, 0, sizeof(request));
 	request.magic = htonl(NBD_REQUEST_MAGIC);
@@ -510,18 +522,6 @@ static void nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 		goto error_out;
 	}
 
-	if (req->cmd_type != REQ_TYPE_FS &&
-	    req->cmd_type != REQ_TYPE_DRV_PRIV)
-		goto error_out;
-
-	if (req->cmd_type == REQ_TYPE_FS &&
-	    rq_data_dir(req) == WRITE &&
-	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
-		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Write on read-only\n");
-		goto error_out;
-	}
-
 	req->errors = 0;
 
 	nsock = nbd->socks[index];
@@ -785,7 +785,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 			INIT_WORK(&args[i].work, recv_work);
 			args[i].nbd = nbd;
 			args[i].index = i;
-			queue_work(system_long_wq, &args[i].work);
+			queue_work(recv_workqueue, &args[i].work);
 		}
 		wait_event_interruptible(nbd->recv_wq,
 					 atomic_read(&nbd->recv_threads) == 0);
@@ -996,6 +996,103 @@ static struct blk_mq_ops nbd_mq_ops = {
 	.timeout	= nbd_xmit_timeout,
 };
 
+static void nbd_dev_remove(struct nbd_device *nbd)
+{
+	struct gendisk *disk = nbd->disk;
+	nbd->magic = 0;
+	if (disk) {
+		del_gendisk(disk);
+		blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&nbd->tag_set);
+		put_disk(disk);
+	}
+	kfree(nbd);
+}
+
+static int nbd_dev_add(int index)
+{
+	struct nbd_device *nbd;
+	struct gendisk *disk;
+	struct request_queue *q;
+	int err = -ENOMEM;
+
+	nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL);
+	if (!nbd)
+		goto out;
+
+	disk = alloc_disk(1 << part_shift);
+	if (!disk)
+		goto out_free_nbd;
+
+	if (index >= 0) {
+		err = idr_alloc(&nbd_index_idr, nbd, index, index + 1,
+				GFP_KERNEL);
+		if (err == -ENOSPC)
+			err = -EEXIST;
+	} else {
+		err = idr_alloc(&nbd_index_idr, nbd, 0, 0, GFP_KERNEL);
+		if (err >= 0)
+			index = err;
+	}
+	if (err < 0)
+		goto out_free_disk;
+
+	nbd->disk = disk;
+	nbd->tag_set.ops = &nbd_mq_ops;
+	nbd->tag_set.nr_hw_queues = 1;
+	nbd->tag_set.queue_depth = 128;
+	nbd->tag_set.numa_node = NUMA_NO_NODE;
+	nbd->tag_set.cmd_size = sizeof(struct nbd_cmd);
+	nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE |
+		BLK_MQ_F_SG_MERGE | BLK_MQ_F_BLOCKING;
+	nbd->tag_set.driver_data = nbd;
+
+	err = blk_mq_alloc_tag_set(&nbd->tag_set);
+	if (err)
+		goto out_free_idr;
+
+	q = blk_mq_init_queue(&nbd->tag_set);
+	if (IS_ERR(q)) {
+		err = PTR_ERR(q);
+		goto out_free_tags;
+	}
+	disk->queue = q;
+
+	/*
+	 * Tell the block layer that we are not a rotational device
+	 */
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
+	disk->queue->limits.discard_granularity = 512;
+	blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
+	disk->queue->limits.discard_zeroes_data = 0;
+	blk_queue_max_hw_sectors(disk->queue, 65536);
+	disk->queue->limits.max_sectors = 256;
+
+	nbd->magic = NBD_MAGIC;
+	mutex_init(&nbd->config_lock);
+	disk->major = NBD_MAJOR;
+	disk->first_minor = index << part_shift;
+	disk->fops = &nbd_fops;
+	disk->private_data = nbd;
+	sprintf(disk->disk_name, "nbd%d", index);
+	init_waitqueue_head(&nbd->recv_wq);
+	nbd_reset(nbd);
+	add_disk(disk);
+	return index;
+
+out_free_tags:
+	blk_mq_free_tag_set(&nbd->tag_set);
+out_free_idr:
+	idr_remove(&nbd_index_idr, index);
+out_free_disk:
+	put_disk(disk);
+out_free_nbd:
+	kfree(nbd);
+out:
+	return err;
+}
+
 /*
  * And here should be modules and kernel interface 
  *  (Just smiley confuses emacs :-)
@@ -1003,9 +1100,7 @@ static struct blk_mq_ops nbd_mq_ops = {
 
 static int __init nbd_init(void)
 {
-	int err = -ENOMEM;
 	int i;
-	int part_shift;
 
 	BUILD_BUG_ON(sizeof(struct nbd_request) != 28);
 
@@ -1034,111 +1129,38 @@ static int __init nbd_init(void)
 
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
-
+	recv_workqueue = alloc_workqueue("knbd-recv",
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+					 WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
-	if (!nbd_dev)
+	if (!recv_workqueue)
 		return -ENOMEM;
 
-	for (i = 0; i < nbds_max; i++) {
+	if (register_blkdev(NBD_MAJOR, "nbd"))
-		struct request_queue *q;
+		return -EIO;
-		struct gendisk *disk = alloc_disk(1 << part_shift);
-		if (!disk)
-			goto out;
-		nbd_dev[i].disk = disk;
-
-		nbd_dev[i].tag_set.ops = &nbd_mq_ops;
-		nbd_dev[i].tag_set.nr_hw_queues = 1;
-		nbd_dev[i].tag_set.queue_depth = 128;
-		nbd_dev[i].tag_set.numa_node = NUMA_NO_NODE;
-		nbd_dev[i].tag_set.cmd_size = sizeof(struct nbd_cmd);
-		nbd_dev[i].tag_set.flags = BLK_MQ_F_SHOULD_MERGE |
-			BLK_MQ_F_SG_MERGE | BLK_MQ_F_BLOCKING;
-		nbd_dev[i].tag_set.driver_data = &nbd_dev[i];
-
-		err = blk_mq_alloc_tag_set(&nbd_dev[i].tag_set);
-		if (err) {
-			put_disk(disk);
-			goto out;
-		}
-
-		/*
-		 * The new linux 2.5 block layer implementation requires
-		 * every gendisk to have its very own request_queue struct.
-		 * These structs are big so we dynamically allocate them.
-		 */
-		q = blk_mq_init_queue(&nbd_dev[i].tag_set);
-		if (IS_ERR(q)) {
-			blk_mq_free_tag_set(&nbd_dev[i].tag_set);
-			put_disk(disk);
-			goto out;
-		}
-		disk->queue = q;
-
-		/*
-		 * Tell the block layer that we are not a rotational device
-		 */
-		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
-		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
-		disk->queue->limits.discard_granularity = 512;
-		blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
-		disk->queue->limits.discard_zeroes_data = 0;
-		blk_queue_max_hw_sectors(disk->queue, 65536);
-		disk->queue->limits.max_sectors = 256;
-	}
-
-	if (register_blkdev(NBD_MAJOR, "nbd")) {
-		err = -EIO;
-		goto out;
-	}
-
-	printk(KERN_INFO "nbd: registered device at major %d\n", NBD_MAJOR);
 
 	nbd_dbg_init();
 
-	for (i = 0; i < nbds_max; i++) {
+	mutex_lock(&nbd_index_mutex);
-		struct gendisk *disk = nbd_dev[i].disk;
+	for (i = 0; i < nbds_max; i++)
-		nbd_dev[i].magic = NBD_MAGIC;
+		nbd_dev_add(i);
-		mutex_init(&nbd_dev[i].config_lock);
+	mutex_unlock(&nbd_index_mutex);
-		disk->major = NBD_MAJOR;
+	return 0;
-		disk->first_minor = i << part_shift;
+}
-		disk->fops = &nbd_fops;
+
-		disk->private_data = &nbd_dev[i];
+static int nbd_exit_cb(int id, void *ptr, void *data)
-		sprintf(disk->disk_name, "nbd%d", i);
+{
-		init_waitqueue_head(&nbd_dev[i].recv_wq);
+	struct nbd_device *nbd = ptr;
-		nbd_reset(&nbd_dev[i]);
+	nbd_dev_remove(nbd);
-		add_disk(disk);
-	}
-
 	return 0;
-out:
-	while (i--) {
-		blk_mq_free_tag_set(&nbd_dev[i].tag_set);
-		blk_cleanup_queue(nbd_dev[i].disk->queue);
-		put_disk(nbd_dev[i].disk);
-	}
-	kfree(nbd_dev);
-	return err;
 }
 
 static void __exit nbd_cleanup(void)
 {
-	int i;
-
 	nbd_dbg_close();
 
-	for (i = 0; i < nbds_max; i++) {
+	idr_for_each(&nbd_index_idr, &nbd_exit_cb, NULL);
-		struct gendisk *disk = nbd_dev[i].disk;
+	idr_destroy(&nbd_index_idr);
-		nbd_dev[i].magic = 0;
+	destroy_workqueue(recv_workqueue);
-		if (disk) {
-			del_gendisk(disk);
-			blk_cleanup_queue(disk->queue);
-			blk_mq_free_tag_set(&nbd_dev[i].tag_set);
-			put_disk(disk);
-		}
-	}
 	unregister_blkdev(NBD_MAJOR, "nbd");
-	kfree(nbd_dev);
-	printk(KERN_INFO "nbd: unregistered device at major %d\n", NBD_MAJOR);
 }
 
 module_init(nbd_init);

drivers/block/null_blk.c

@@ -432,11 +432,11 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	struct request *rq;
 	struct bio *bio = rqd->bio;
 
-	rq = blk_mq_alloc_request(q, bio_data_dir(bio), 0);
+	rq = blk_mq_alloc_request(q,
+		op_is_write(bio_op(bio)) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->__sector = bio->bi_iter.bi_sector;
 	rq->ioprio = bio_prio(bio);
 

drivers/block/osdblk.c

@@ -308,12 +308,6 @@ static void osdblk_rq_fn(struct request_queue *q)
 		if (!rq)
 			break;
 
-		/* filter out block requests we don't understand */
-		if (rq->cmd_type != REQ_TYPE_FS) {
-			blk_end_request_all(rq, 0);
-			continue;
-		}
-
 		/* deduce our operation (read, write, flush) */
 		/* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
 		 * into a clearly defined set of RPC commands:

drivers/block/paride/Kconfig

@@ -25,6 +25,7 @@ config PARIDE_PD
 config PARIDE_PCD
 	tristate "Parallel port ATAPI CD-ROMs"
 	depends on PARIDE
+	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	---help---
 	  This option enables the high-level driver for ATAPI CD-ROM devices
 	  connected through a parallel port. If you chose to build PARIDE

drivers/block/paride/pd.c

@@ -439,18 +439,16 @@ static int pd_retries = 0;	/* i/o error retry count */
 static int pd_block;		/* address of next requested block */
 static int pd_count;		/* number of blocks still to do */
 static int pd_run;		/* sectors in current cluster */
-static int pd_cmd;		/* current command READ/WRITE */
 static char *pd_buf;		/* buffer for request in progress */
 
 static enum action do_pd_io_start(void)
 {
-	if (pd_req->cmd_type == REQ_TYPE_DRV_PRIV) {
+	switch (req_op(pd_req)) {
+	case REQ_OP_DRV_IN:
 		phase = pd_special;
 		return pd_special();
-	}
+	case REQ_OP_READ:
-
+	case REQ_OP_WRITE:
-	pd_cmd = rq_data_dir(pd_req);
-	if (pd_cmd == READ || pd_cmd == WRITE) {
 		pd_block = blk_rq_pos(pd_req);
 		pd_count = blk_rq_cur_sectors(pd_req);
 		if (pd_block + pd_count > get_capacity(pd_req->rq_disk))
@@ -458,7 +456,7 @@ static enum action do_pd_io_start(void)
 		pd_run = blk_rq_sectors(pd_req);
 		pd_buf = bio_data(pd_req->bio);
 		pd_retries = 0;
-		if (pd_cmd == READ)
+		if (req_op(pd_req) == REQ_OP_READ)
 			return do_pd_read_start();
 		else
 			return do_pd_write_start();
@@ -723,11 +721,10 @@ static int pd_special_command(struct pd_unit *disk,
 	struct request *rq;
 	int err = 0;
 
-	rq = blk_get_request(disk->gd->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = func;
 
 	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);

drivers/block/pktcdvd.c

@@ -704,10 +704,10 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 	int ret = 0;
 
 	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
-			     WRITE : READ, __GFP_RECLAIM);
+			     REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 
 	if (cgc->buflen) {
 		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
@@ -716,8 +716,8 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 			goto out;
 	}
 
-	rq->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+	scsi_req(rq)->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
-	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
+	memcpy(scsi_req(rq)->cmd, cgc->cmd, CDROM_PACKET_SIZE);
 
 	rq->timeout = 60*HZ;
 	if (cgc->quiet)
@@ -1243,7 +1243,7 @@ static int pkt_handle_queue(struct pktcdvd_device *pd)
 	 		&& pd->bio_queue_size <= pd->write_congestion_off);
 	spin_unlock(&pd->lock);
 	if (wakeup) {
-		clear_bdi_congested(&pd->disk->queue->backing_dev_info,
+		clear_bdi_congested(pd->disk->queue->backing_dev_info,
 					BLK_RW_ASYNC);
 	}
 
@@ -2370,7 +2370,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 	spin_lock(&pd->lock);
 	if (pd->write_congestion_on > 0
 	    && pd->bio_queue_size >= pd->write_congestion_on) {
-		set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC);
+		set_bdi_congested(q->backing_dev_info, BLK_RW_ASYNC);
 		do {
 			spin_unlock(&pd->lock);
 			congestion_wait(BLK_RW_ASYNC, HZ);

drivers/block/ps3disk.c

@@ -196,16 +196,19 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
 	while ((req = blk_fetch_request(q))) {
-		if (req_op(req) == REQ_OP_FLUSH) {
+		switch (req_op(req)) {
+		case REQ_OP_FLUSH:
 			if (ps3disk_submit_flush_request(dev, req))
-				break;
+				return;
-		} else if (req->cmd_type == REQ_TYPE_FS) {
+			break;
+		case REQ_OP_READ:
+		case REQ_OP_WRITE:
 			if (ps3disk_submit_request_sg(dev, req))
-				break;
+				return;
-		} else {
+			break;
+		default:
 			blk_dump_rq_flags(req, DEVICE_NAME " bad request");
 			__blk_end_request_all(req, -EIO);
-			continue;
 		}
 	}
 }

drivers/block/rbd.c

@@ -4099,20 +4099,22 @@ static void rbd_queue_workfn(struct work_struct *work)
 	bool must_be_locked;
 	int result;
 
-	if (rq->cmd_type != REQ_TYPE_FS) {
+	switch (req_op(rq)) {
-		dout("%s: non-fs request type %d\n", __func__,
+	case REQ_OP_DISCARD:
-			(int) rq->cmd_type);
+		op_type = OBJ_OP_DISCARD;
+		break;
+	case REQ_OP_WRITE:
+		op_type = OBJ_OP_WRITE;
+		break;
+	case REQ_OP_READ:
+		op_type = OBJ_OP_READ;
+		break;
+	default:
+		dout("%s: non-fs request type %d\n", __func__, req_op(rq));
 		result = -EIO;
 		goto err;
 	}
 
-	if (req_op(rq) == REQ_OP_DISCARD)
-		op_type = OBJ_OP_DISCARD;
-	else if (req_op(rq) == REQ_OP_WRITE)
-		op_type = OBJ_OP_WRITE;
-	else
-		op_type = OBJ_OP_READ;
-
 	/* Ignore/skip any zero-length requests */
 
 	if (!length) {
@@ -4524,7 +4526,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	q->limits.discard_zeroes_data = 1;
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
-		q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
+		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
 
 	disk->queue = q;
 

drivers/block/skd_main.c

@@ -1204,10 +1204,11 @@ static void skd_complete_special(struct skd_device *skdev,
 static int skd_bdev_ioctl(struct block_device *bdev, fmode_t mode,
 			  uint cmd_in, ulong arg)
 {
-	int rc = 0;
+	static const int sg_version_num = 30527;
+	int rc = 0, timeout;
 	struct gendisk *disk = bdev->bd_disk;
 	struct skd_device *skdev = disk->private_data;
-	void __user *p = (void *)arg;
+	int __user *p = (int __user *)arg;
 
 	pr_debug("%s:%s:%d %s: CMD[%s] ioctl  mode 0x%x, cmd 0x%x arg %0lx\n",
 		 skdev->name, __func__, __LINE__,
@@ -1218,12 +1219,18 @@ static int skd_bdev_ioctl(struct block_device *bdev, fmode_t mode,
 
 	switch (cmd_in) {
 	case SG_SET_TIMEOUT:
+		rc = get_user(timeout, p);
+		if (!rc)
+			disk->queue->sg_timeout = clock_t_to_jiffies(timeout);
+		break;
 	case SG_GET_TIMEOUT:
+		rc = jiffies_to_clock_t(disk->queue->sg_timeout);
+		break;
 	case SG_GET_VERSION_NUM:
-		rc = scsi_cmd_ioctl(disk->queue, disk, mode, cmd_in, p);
+		rc = put_user(sg_version_num, p);
 		break;
 	case SG_IO:
-		rc = skd_ioctl_sg_io(skdev, mode, p);
+		rc = skd_ioctl_sg_io(skdev, mode, (void __user *)arg);
 		break;
 
 	default:

drivers/block/sx8.c

@@ -567,7 +567,7 @@ static struct carm_request *carm_get_special(struct carm_host *host)
 	if (!crq)
 		return NULL;
 
-	rq = blk_get_request(host->oob_q, WRITE /* bogus */, GFP_KERNEL);
+	rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		spin_lock_irqsave(&host->lock, flags);
 		carm_put_request(host, crq);
@@ -620,7 +620,6 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	spin_unlock_irq(&host->lock);
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
@@ -661,7 +660,6 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	crq->msg_bucket = (u32) rc;
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 

drivers/block/virtio_blk.c

@@ -52,11 +52,13 @@ struct virtio_blk {
 };
 
 struct virtblk_req {
-	struct request *req;
+#ifdef CONFIG_VIRTIO_BLK_SCSI
-	struct virtio_blk_outhdr out_hdr;
+	struct scsi_request sreq;	/* for SCSI passthrough, must be first */
-	struct virtio_scsi_inhdr in_hdr;
-	u8 status;
 	u8 sense[SCSI_SENSE_BUFFERSIZE];
+	struct virtio_scsi_inhdr in_hdr;
+#endif
+	struct virtio_blk_outhdr out_hdr;
+	u8 status;
 	struct scatterlist sg[];
 };
 
@@ -72,28 +74,23 @@ static inline int virtblk_result(struct virtblk_req *vbr)
 	}
 }
 
-static int __virtblk_add_req(struct virtqueue *vq,
+/*
-			     struct virtblk_req *vbr,
+ * If this is a packet command we need a couple of additional headers.  Behind
-			     struct scatterlist *data_sg,
+ * the normal outhdr we put a segment with the scsi command block, and before
-			     bool have_data)
+ * the normal inhdr we put the sense data and the inhdr with additional status
+ * information.
+ */
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
+		struct scatterlist *data_sg, bool have_data)
 {
 	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
 	unsigned int num_out = 0, num_in = 0;
-	__virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
 
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
-
+	sg_init_one(&cmd, vbr->sreq.cmd, vbr->sreq.cmd_len);
-	/*
+	sgs[num_out++] = &cmd;
-	 * If this is a packet command we need a couple of additional headers.
-	 * Behind the normal outhdr we put a segment with the scsi command
-	 * block, and before the normal inhdr we put the sense data and the
-	 * inhdr with additional status information.
-	 */
-	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
-		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
-		sgs[num_out++] = &cmd;
-	}
 
 	if (have_data) {
 		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
@@ -102,12 +99,69 @@ static int __virtblk_add_req(struct virtqueue *vq,
 			sgs[num_out + num_in++] = data_sg;
 	}
 
-	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
+	sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
-		memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
+	sgs[num_out + num_in++] = &sense;
-		sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
+	sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
-		sgs[num_out + num_in++] = &sense;
+	sgs[num_out + num_in++] = &inhdr;
-		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
+	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
-		sgs[num_out + num_in++] = &inhdr;
+	sgs[num_out + num_in++] = &status;
+
+	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
+}
+
+static inline void virtblk_scsi_reques_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	struct virtio_blk *vblk = req->q->queuedata;
+	struct scsi_request *sreq = &vbr->sreq;
+
+	sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+	sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+	req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+}
+
+static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long data)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct virtio_blk *vblk = disk->private_data;
+
+	/*
+	 * Only allow the generic SCSI ioctls if the host can support it.
+	 */
+	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
+		return -ENOTTY;
+
+	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
+				  (void __user *)data);
+}
+#else
+static inline int virtblk_add_req_scsi(struct virtqueue *vq,
+		struct virtblk_req *vbr, struct scatterlist *data_sg,
+		bool have_data)
+{
+	return -EIO;
+}
+static inline void virtblk_scsi_reques_done(struct request *req)
+{
+}
+#define virtblk_ioctl	NULL
+#endif /* CONFIG_VIRTIO_BLK_SCSI */
+
+static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
+		struct scatterlist *data_sg, bool have_data)
+{
+	struct scatterlist hdr, status, *sgs[3];
+	unsigned int num_out = 0, num_in = 0;
+
+	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
+	sgs[num_out++] = &hdr;
+
+	if (have_data) {
+		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
+			sgs[num_out++] = data_sg;
+		else
+			sgs[num_out + num_in++] = data_sg;
 	}
 
 	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
@@ -119,15 +173,16 @@ static int __virtblk_add_req(struct virtqueue *vq,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
-	struct virtio_blk *vblk = req->q->queuedata;
 	int error = virtblk_result(vbr);
 
-	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
+	switch (req_op(req)) {
-		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+	case REQ_OP_SCSI_IN:
-		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+	case REQ_OP_SCSI_OUT:
-		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+		virtblk_scsi_reques_done(req);
-	} else if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+		break;
+	case REQ_OP_DRV_IN:
 		req->errors = (error != 0);
+		break;
 	}
 
 	blk_mq_end_request(req, error);
@@ -146,7 +201,9 @@ static void virtblk_done(struct virtqueue *vq)
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
-			blk_mq_complete_request(vbr->req, vbr->req->errors);
+			struct request *req = blk_mq_rq_from_pdu(vbr);
+
+			blk_mq_complete_request(req, req->errors);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -170,49 +227,50 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int qid = hctx->queue_num;
 	int err;
 	bool notify = false;
+	u32 type;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
-	vbr->req = req;
+	switch (req_op(req)) {
-	if (req_op(req) == REQ_OP_FLUSH) {
+	case REQ_OP_READ:
-		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
+	case REQ_OP_WRITE:
-		vbr->out_hdr.sector = 0;
+		type = 0;
-		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
+		break;
-	} else {
+	case REQ_OP_FLUSH:
-		switch (req->cmd_type) {
+		type = VIRTIO_BLK_T_FLUSH;
-		case REQ_TYPE_FS:
+		break;
-			vbr->out_hdr.type = 0;
+	case REQ_OP_SCSI_IN:
-			vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
+	case REQ_OP_SCSI_OUT:
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
+		type = VIRTIO_BLK_T_SCSI_CMD;
-			break;
+		break;
-		case REQ_TYPE_BLOCK_PC:
+	case REQ_OP_DRV_IN:
-			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
+		type = VIRTIO_BLK_T_GET_ID;
-			vbr->out_hdr.sector = 0;
+		break;
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
+	default:
-			break;
+		WARN_ON_ONCE(1);
-		case REQ_TYPE_DRV_PRIV:
+		return BLK_MQ_RQ_QUEUE_ERROR;
-			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
-			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		default:
-			/* We don't put anything else in the queue. */
-			BUG();
-		}
 	}
 
+	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
+	vbr->out_hdr.sector = type ?
+		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
+	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
+
 	blk_mq_start_request(req);
 
-	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
+	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
 	if (num) {
-		if (rq_data_dir(vbr->req) == WRITE)
+		if (rq_data_dir(req) == WRITE)
 			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
 		else
 			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = __virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	if (req_op(req) == REQ_OP_SCSI_IN || req_op(req) == REQ_OP_SCSI_OUT)
+		err = virtblk_add_req_scsi(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	else
+		err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		blk_mq_stop_hw_queue(hctx);
@@ -242,10 +300,9 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	struct request *req;
 	int err;
 
-	req = blk_get_request(q, READ, GFP_KERNEL);
+	req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->cmd_type = REQ_TYPE_DRV_PRIV;
 
 	err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
 	if (err)
@@ -257,22 +314,6 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	return err;
 }
 
-static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long data)
-{
-	struct gendisk *disk = bdev->bd_disk;
-	struct virtio_blk *vblk = disk->private_data;
-
-	/*
-	 * Only allow the generic SCSI ioctls if the host can support it.
-	 */
-	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
-		return -ENOTTY;
-
-	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
-				  (void __user *)data);
-}
-
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
@@ -538,6 +579,9 @@ static int virtblk_init_request(void *data, struct request *rq,
 	struct virtio_blk *vblk = data;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
 
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	vbr->sreq.sense = vbr->sense;
+#endif
 	sg_init_table(vbr->sg, vblk->sg_elems);
 	return 0;
 }
@@ -821,7 +865,10 @@ static const struct virtio_device_id id_table[] = {
 
 static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
-	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	VIRTIO_BLK_F_SCSI,
+#endif
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
 }

drivers/block/xen-blkfront.c

@@ -865,7 +865,7 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo)
 static inline bool blkif_request_flush_invalid(struct request *req,
 					       struct blkfront_info *info)
 {
-	return ((req->cmd_type != REQ_TYPE_FS) ||
+	return (blk_rq_is_passthrough(req) ||
 		((req_op(req) == REQ_OP_FLUSH) &&
 		 !info->feature_flush) ||
 		((req->cmd_flags & REQ_FUA) &&

drivers/block/xsysace.c

@@ -468,7 +468,7 @@ static struct request *ace_get_next_request(struct request_queue *q)
 	struct request *req;
 
 	while ((req = blk_peek_request(q)) != NULL) {
-		if (req->cmd_type == REQ_TYPE_FS)
+		if (!blk_rq_is_passthrough(req))
 			break;
 		blk_start_request(req);
 		__blk_end_request_all(req, -EIO);

drivers/block/zram/zram_drv.c

@@ -117,7 +117,7 @@ static void zram_revalidate_disk(struct zram *zram)
 {
 	revalidate_disk(zram->disk);
 	/* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
-	zram->disk->queue->backing_dev_info.capabilities |=
+	zram->disk->queue->backing_dev_info->capabilities |=
 		BDI_CAP_STABLE_WRITES;
 }
 

drivers/cdrom/cdrom.c

@@ -281,8 +281,8 @@
 #include <linux/fcntl.h>
 #include <linux/blkdev.h>
 #include <linux/times.h>
-
 #include <linux/uaccess.h>
+#include <scsi/scsi_request.h>
 
 /* used to tell the module to turn on full debugging messages */
 static bool debug;
@@ -2170,6 +2170,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 {
 	struct request_queue *q = cdi->disk->queue;
 	struct request *rq;
+	struct scsi_request *req;
 	struct bio *bio;
 	unsigned int len;
 	int nr, ret = 0;
@@ -2188,12 +2189,13 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		len = nr * CD_FRAMESIZE_RAW;
 
-		rq = blk_get_request(q, READ, GFP_KERNEL);
+		rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			break;
 		}
-		blk_rq_set_block_pc(rq);
+		req = scsi_req(rq);
+		scsi_req_init(rq);
 
 		ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL);
 		if (ret) {
@@ -2201,23 +2203,23 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 			break;
 		}
 
-		rq->cmd[0] = GPCMD_READ_CD;
+		req->cmd[0] = GPCMD_READ_CD;
-		rq->cmd[1] = 1 << 2;
+		req->cmd[1] = 1 << 2;
-		rq->cmd[2] = (lba >> 24) & 0xff;
+		req->cmd[2] = (lba >> 24) & 0xff;
-		rq->cmd[3] = (lba >> 16) & 0xff;
+		req->cmd[3] = (lba >> 16) & 0xff;
-		rq->cmd[4] = (lba >>  8) & 0xff;
+		req->cmd[4] = (lba >>  8) & 0xff;
-		rq->cmd[5] = lba & 0xff;
+		req->cmd[5] = lba & 0xff;
-		rq->cmd[6] = (nr >> 16) & 0xff;
+		req->cmd[6] = (nr >> 16) & 0xff;
-		rq->cmd[7] = (nr >>  8) & 0xff;
+		req->cmd[7] = (nr >>  8) & 0xff;
-		rq->cmd[8] = nr & 0xff;
+		req->cmd[8] = nr & 0xff;
-		rq->cmd[9] = 0xf8;
+		req->cmd[9] = 0xf8;
 
-		rq->cmd_len = 12;
+		req->cmd_len = 12;
 		rq->timeout = 60 * HZ;
 		bio = rq->bio;
 
 		if (blk_execute_rq(q, cdi->disk, rq, 0)) {
-			struct request_sense *s = rq->sense;
+			struct request_sense *s = req->sense;
 			ret = -EIO;
 			cdi->last_sense = s->sense_key;
 		}

drivers/cdrom/gdrom.c

@@ -659,23 +659,24 @@ static void gdrom_request(struct request_queue *rq)
 	struct request *req;
 
 	while ((req = blk_fetch_request(rq)) != NULL) {
-		if (req->cmd_type != REQ_TYPE_FS) {
+		switch (req_op(req)) {
-			printk(KERN_DEBUG "gdrom: Non-fs request ignored\n");
+		case REQ_OP_READ:
-			__blk_end_request_all(req, -EIO);
+			/*
-			continue;
+			 * Add to list of deferred work and then schedule
-		}
+			 * workqueue.
-		if (rq_data_dir(req) != READ) {
+			 */
+			list_add_tail(&req->queuelist, &gdrom_deferred);
+			schedule_work(&work);
+			break;
+		case REQ_OP_WRITE:
 			pr_notice("Read only device - write request ignored\n");
 			__blk_end_request_all(req, -EIO);
-			continue;
+			break;
+		default:
+			printk(KERN_DEBUG "gdrom: Non-fs request ignored\n");
+			__blk_end_request_all(req, -EIO);
+			break;
 		}
-
-		/*
-		 * Add to list of deferred work and then schedule
-		 * workqueue.
-		 */
-		list_add_tail(&req->queuelist, &gdrom_deferred);
-		schedule_work(&work);
 	}
 }
 

drivers/ide/Kconfig

@@ -10,6 +10,7 @@ menuconfig IDE
 	tristate "ATA/ATAPI/MFM/RLL support (DEPRECATED)"
 	depends on HAVE_IDE
 	depends on BLOCK
+	select BLK_SCSI_REQUEST
 	---help---
 	  If you say Y here, your kernel will be able to manage ATA/(E)IDE and
 	  ATAPI units. The most common cases are IDE hard drives and ATAPI

drivers/ide/ide-atapi.c

@@ -92,8 +92,9 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	struct request *rq;
 	int error;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = (char *)pc;
 
 	if (buf && bufflen) {
@@ -103,9 +104,9 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 			goto put_req;
 	}
 
-	memcpy(rq->cmd, pc->c, 12);
+	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 	if (drive->media == ide_tape)
-		rq->cmd[13] = REQ_IDETAPE_PC1;
+		scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
 	error = blk_execute_rq(drive->queue, disk, rq, 0);
 put_req:
 	blk_put_request(rq);
@@ -171,7 +172,8 @@ EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd);
 void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 {
 	struct request_sense *sense = &drive->sense_data;
-	struct request *sense_rq = &drive->sense_rq;
+	struct request *sense_rq = drive->sense_rq;
+	struct scsi_request *req = scsi_req(sense_rq);
 	unsigned int cmd_len, sense_len;
 	int err;
 
@@ -191,12 +193,13 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 
 	BUG_ON(sense_len > sizeof(*sense));
 
-	if (rq->cmd_type == REQ_TYPE_ATA_SENSE || drive->sense_rq_armed)
+	if (ata_sense_request(rq) || drive->sense_rq_armed)
 		return;
 
 	memset(sense, 0, sizeof(*sense));
 
 	blk_rq_init(rq->q, sense_rq);
+	scsi_req_init(sense_rq);
 
 	err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
 			      GFP_NOIO);
@@ -208,13 +211,14 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	}
 
 	sense_rq->rq_disk = rq->rq_disk;
-	sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
+	sense_rq->cmd_flags = REQ_OP_DRV_IN;
-	sense_rq->cmd[4] = cmd_len;
+	ide_req(sense_rq)->type = ATA_PRIV_SENSE;
-	sense_rq->cmd_type = REQ_TYPE_ATA_SENSE;
 	sense_rq->rq_flags |= RQF_PREEMPT;
 
+	req->cmd[0] = GPCMD_REQUEST_SENSE;
+	req->cmd[4] = cmd_len;
 	if (drive->media == ide_tape)
-		sense_rq->cmd[13] = REQ_IDETAPE_PC1;
+		req->cmd[13] = REQ_IDETAPE_PC1;
 
 	drive->sense_rq_armed = true;
 }
@@ -229,12 +233,12 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special)
 		return -ENOMEM;
 	}
 
-	drive->sense_rq.special = special;
+	drive->sense_rq->special = special;
 	drive->sense_rq_armed = false;
 
 	drive->hwif->rq = NULL;
 
-	elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT);
+	elv_add_request(drive->queue, drive->sense_rq, ELEVATOR_INSERT_FRONT);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
@@ -247,14 +251,14 @@ EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
 void ide_retry_pc(ide_drive_t *drive)
 {
 	struct request *failed_rq = drive->hwif->rq;
-	struct request *sense_rq = &drive->sense_rq;
+	struct request *sense_rq = drive->sense_rq;
 	struct ide_atapi_pc *pc = &drive->request_sense_pc;
 
 	(void)ide_read_error(drive);
 
 	/* init pc from sense_rq */
 	ide_init_pc(pc);
-	memcpy(pc->c, sense_rq->cmd, 12);
+	memcpy(pc->c, scsi_req(sense_rq)->cmd, 12);
 
 	if (drive->media == ide_tape)
 		drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC;
@@ -286,7 +290,7 @@ int ide_cd_expiry(ide_drive_t *drive)
 	 * commands/drives support that. Let ide_timer_expiry keep polling us
 	 * for these.
 	 */
-	switch (rq->cmd[0]) {
+	switch (scsi_req(rq)->cmd[0]) {
 	case GPCMD_BLANK:
 	case GPCMD_FORMAT_UNIT:
 	case GPCMD_RESERVE_RZONE_TRACK:
@@ -297,7 +301,7 @@ int ide_cd_expiry(ide_drive_t *drive)
 	default:
 		if (!(rq->rq_flags & RQF_QUIET))
 			printk(KERN_INFO PFX "cmd 0x%x timed out\n",
-					 rq->cmd[0]);
+					 scsi_req(rq)->cmd[0]);
 		wait = 0;
 		break;
 	}
@@ -307,15 +311,21 @@ EXPORT_SYMBOL_GPL(ide_cd_expiry);
 
 int ide_cd_get_xferlen(struct request *rq)
 {
-	switch (rq->cmd_type) {
+	switch (req_op(rq)) {
-	case REQ_TYPE_FS:
-		return 32768;
-	case REQ_TYPE_ATA_SENSE:
-	case REQ_TYPE_BLOCK_PC:
-	case REQ_TYPE_ATA_PC:
-		return blk_rq_bytes(rq);
 	default:
-		return 0;
+		return 32768;
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+		return blk_rq_bytes(rq);
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		switch (ide_req(rq)->type) {
+		case ATA_PRIV_PC:
+		case ATA_PRIV_SENSE:
+			return blk_rq_bytes(rq);
+		default:
+			return 0;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(ide_cd_get_xferlen);
@@ -374,7 +384,7 @@ int ide_check_ireason(ide_drive_t *drive, struct request *rq, int len,
 				drive->name, __func__, ireason);
 	}
 
-	if (dev_is_idecd(drive) && rq->cmd_type == REQ_TYPE_ATA_PC)
+	if (dev_is_idecd(drive) && ata_pc_request(rq))
 		rq->rq_flags |= RQF_FAILED;
 
 	return 1;
@@ -420,7 +430,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 						     ? "write" : "read");
 			pc->flags |= PC_FLAG_DMA_ERROR;
 		} else
-			rq->resid_len = 0;
+			scsi_req(rq)->resid_len = 0;
 		debug_log("%s: DMA finished\n", drive->name);
 	}
 
@@ -436,7 +446,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		local_irq_enable_in_hardirq();
 
 		if (drive->media == ide_tape &&
-		    (stat & ATA_ERR) && rq->cmd[0] == REQUEST_SENSE)
+		    (stat & ATA_ERR) && scsi_req(rq)->cmd[0] == REQUEST_SENSE)
 			stat &= ~ATA_ERR;
 
 		if ((stat & ATA_ERR) || (pc->flags & PC_FLAG_DMA_ERROR)) {
@@ -446,7 +456,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			if (drive->media != ide_tape)
 				pc->rq->errors++;
 
-			if (rq->cmd[0] == REQUEST_SENSE) {
+			if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
 				printk(KERN_ERR PFX "%s: I/O error in request "
 						"sense command\n", drive->name);
 				return ide_do_reset(drive);
@@ -477,12 +487,12 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		if (uptodate == 0)
 			drive->failed_pc = NULL;
 
-		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
+		if (ata_misc_request(rq)) {
 			rq->errors = 0;
 			error = 0;
 		} else {
 
-			if (rq->cmd_type != REQ_TYPE_FS && uptodate <= 0) {
+			if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
 				if (rq->errors == 0)
 					rq->errors = -EIO;
 			}
@@ -512,7 +522,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 	ide_pio_bytes(drive, cmd, write, done);
 
 	/* Update transferred byte count */
-	rq->resid_len -= done;
+	scsi_req(rq)->resid_len -= done;
 
 	bcount -= done;
 
@@ -520,7 +530,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		ide_pad_transfer(drive, write, bcount);
 
 	debug_log("[cmd %x] transferred %d bytes, padded %d bytes, resid: %u\n",
-		  rq->cmd[0], done, bcount, rq->resid_len);
+		  rq->cmd[0], done, bcount, scsi_req(rq)->resid_len);
 
 	/* And set the interrupt handler again */
 	ide_set_handler(drive, ide_pc_intr, timeout);
@@ -603,7 +613,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
 
 	if (dev_is_idecd(drive)) {
 		/* ATAPI commands get padded out to 12 bytes minimum */
-		cmd_len = COMMAND_SIZE(rq->cmd[0]);
+		cmd_len = COMMAND_SIZE(scsi_req(rq)->cmd[0]);
 		if (cmd_len < ATAPI_MIN_CDB_BYTES)
 			cmd_len = ATAPI_MIN_CDB_BYTES;
 
@@ -650,7 +660,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
 
 	/* Send the actual packet */
 	if ((drive->atapi_flags & IDE_AFLAG_ZIP_DRIVE) == 0)
-		hwif->tp_ops->output_data(drive, NULL, rq->cmd, cmd_len);
+		hwif->tp_ops->output_data(drive, NULL, scsi_req(rq)->cmd, cmd_len);
 
 	/* Begin DMA, if necessary */
 	if (dev_is_idecd(drive)) {
@@ -695,7 +705,7 @@ ide_startstop_t ide_issue_pc(ide_drive_t *drive, struct ide_cmd *cmd)
 							     bytes, 63 * 1024));
 
 		/* We haven't transferred any data yet */
-		rq->resid_len = bcount;
+		scsi_req(rq)->resid_len = bcount;
 
 		if (pc->flags & PC_FLAG_DMA_ERROR) {
 			pc->flags &= ~PC_FLAG_DMA_ERROR;

drivers/ide/ide-cd.c

@@ -121,7 +121,7 @@ static int cdrom_log_sense(ide_drive_t *drive, struct request *rq)
 		 * don't log START_STOP unit with LoEj set, since we cannot
 		 * reliably check if drive can auto-close
 		 */
-		if (rq->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24)
+		if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24)
 			break;
 		log = 1;
 		break;
@@ -163,7 +163,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 	 * toc has not been recorded yet, it will fail with 05/24/00 (which is a
 	 * confusing error)
 	 */
-	if (failed_command && failed_command->cmd[0] == GPCMD_READ_TOC_PMA_ATIP)
+	if (failed_command && scsi_req(failed_command)->cmd[0] == GPCMD_READ_TOC_PMA_ATIP)
 		if (sense->sense_key == 0x05 && sense->asc == 0x24)
 			return;
 
@@ -176,7 +176,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 			if (!sense->valid)
 				break;
 			if (failed_command == NULL ||
-			    failed_command->cmd_type != REQ_TYPE_FS)
+			    blk_rq_is_passthrough(failed_command))
 				break;
 			sector = (sense->information[0] << 24) |
 				 (sense->information[1] << 16) |
@@ -210,7 +210,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 {
 	/*
-	 * For REQ_TYPE_ATA_SENSE, "rq->special" points to the original
+	 * For ATA_PRIV_SENSE, "rq->special" points to the original
 	 * failed request.  Also, the sense data should be read
 	 * directly from rq which might be different from the original
 	 * sense buffer if it got copied during mapping.
@@ -219,15 +219,12 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 	void *sense = bio_data(rq->bio);
 
 	if (failed) {
-		if (failed->sense) {
+		/*
-			/*
+		 * Sense is always read into drive->sense_data, copy back to the
-			 * Sense is always read into drive->sense_data.
+		 * original request.
-			 * Copy back if the failed request has its
+		 */
-			 * sense pointer set.
+		memcpy(scsi_req(failed)->sense, sense, 18);
-			 */
+		scsi_req(failed)->sense_len = scsi_req(rq)->sense_len;
-			memcpy(failed->sense, sense, 18);
-			failed->sense_len = rq->sense_len;
-		}
 		cdrom_analyze_sense_data(drive, failed);
 
 		if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed)))
@@ -285,7 +282,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 				  "stat 0x%x",
 				  rq->cmd[0], rq->cmd_type, err, stat);
 
-	if (rq->cmd_type == REQ_TYPE_ATA_SENSE) {
+	if (ata_sense_request(rq)) {
 		/*
 		 * We got an error trying to get sense info from the drive
 		 * (probably while trying to recover from a former error).
@@ -296,7 +293,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 	}
 
 	/* if we have an error, pass CHECK_CONDITION as the SCSI status byte */
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !rq->errors)
+	if (blk_rq_is_scsi(rq) && !rq->errors)
 		rq->errors = SAM_STAT_CHECK_CONDITION;
 
 	if (blk_noretry_request(rq))
@@ -304,13 +301,13 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 
 	switch (sense_key) {
 	case NOT_READY:
-		if (rq->cmd_type == REQ_TYPE_FS && rq_data_dir(rq) == WRITE) {
+		if (req_op(rq) == REQ_OP_WRITE) {
 			if (ide_cd_breathe(drive, rq))
 				return 1;
 		} else {
 			cdrom_saw_media_change(drive);
 
-			if (rq->cmd_type == REQ_TYPE_FS &&
+			if (!blk_rq_is_passthrough(rq) &&
 			    !(rq->rq_flags & RQF_QUIET))
 				printk(KERN_ERR PFX "%s: tray open\n",
 					drive->name);
@@ -320,7 +317,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 	case UNIT_ATTENTION:
 		cdrom_saw_media_change(drive);
 
-		if (rq->cmd_type != REQ_TYPE_FS)
+		if (blk_rq_is_passthrough(rq))
 			return 0;
 
 		/*
@@ -338,7 +335,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		 *
 		 * cdrom_log_sense() knows this!
 		 */
-		if (rq->cmd[0] == GPCMD_START_STOP_UNIT)
+		if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT)
 			break;
 		/* fall-through */
 	case DATA_PROTECT:
@@ -368,7 +365,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		do_end_request = 1;
 		break;
 	default:
-		if (rq->cmd_type != REQ_TYPE_FS)
+		if (blk_rq_is_passthrough(rq))
 			break;
 		if (err & ~ATA_ABORTED) {
 			/* go to the default handler for other errors */
@@ -379,7 +376,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 			do_end_request = 1;
 	}
 
-	if (rq->cmd_type != REQ_TYPE_FS) {
+	if (blk_rq_is_passthrough(rq)) {
 		rq->rq_flags |= RQF_FAILED;
 		do_end_request = 1;
 	}
@@ -414,7 +411,7 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 	 * Some of the trailing request sense fields are optional,
 	 * and some drives don't send them.  Sigh.
 	 */
-	if (rq->cmd[0] == GPCMD_REQUEST_SENSE &&
+	if (scsi_req(rq)->cmd[0] == GPCMD_REQUEST_SENSE &&
 	    cmd->nleft > 0 && cmd->nleft <= 5)
 		cmd->nleft = 0;
 }
@@ -425,12 +422,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
-	struct request_sense local_sense;
 	int retries = 10;
-	req_flags_t flags = 0;
+	bool failed;
-
-	if (!sense)
-		sense = &local_sense;
 
 	ide_debug_log(IDE_DBG_PC, "cmd[0]: 0x%x, write: 0x%x, timeout: %d, "
 				  "rq_flags: 0x%x",
@@ -440,12 +433,13 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 	do {
 		struct request *rq;
 		int error;
+		bool delay = false;
 
-		rq = blk_get_request(drive->queue, write, __GFP_RECLAIM);
+		rq = blk_get_request(drive->queue,
-
+			write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,  __GFP_RECLAIM);
-		memcpy(rq->cmd, cmd, BLK_MAX_CDB);
+		scsi_req_init(rq);
-		rq->cmd_type = REQ_TYPE_ATA_PC;
+		memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
-		rq->sense = sense;
+		ide_req(rq)->type = ATA_PRIV_PC;
 		rq->rq_flags |= rq_flags;
 		rq->timeout = timeout;
 		if (buffer) {
@@ -460,21 +454,21 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		error = blk_execute_rq(drive->queue, info->disk, rq, 0);
 
 		if (buffer)
-			*bufflen = rq->resid_len;
+			*bufflen = scsi_req(rq)->resid_len;
-
+		if (sense)
-		flags = rq->rq_flags;
+			memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
-		blk_put_request(rq);
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
 		 * failure.
 		 */
-		if (flags & RQF_FAILED) {
+		failed = (rq->rq_flags & RQF_FAILED) != 0;
+		if (failed) {
 			/*
 			 * The request failed.  Retry if it was due to a unit
 			 * attention status (usually means media was changed).
 			 */
-			struct request_sense *reqbuf = sense;
+			struct request_sense *reqbuf = scsi_req(rq)->sense;
 
 			if (reqbuf->sense_key == UNIT_ATTENTION)
 				cdrom_saw_media_change(drive);
@@ -485,19 +479,20 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 				 * a disk.  Retry, but wait a little to give
 				 * the drive time to complete the load.
 				 */
-				ssleep(2);
+				delay = true;
 			} else {
 				/* otherwise, don't retry */
 				retries = 0;
 			}
 			--retries;
 		}
-
+		blk_put_request(rq);
-		/* end of retry loop */
+		if (delay)
-	} while ((flags & RQF_FAILED) && retries >= 0);
+			ssleep(2);
+	} while (failed && retries >= 0);
 
 	/* return an error if the command failed */
-	return (flags & RQF_FAILED) ? -EIO : 0;
+	return failed ? -EIO : 0;
 }
 
 /*
@@ -526,7 +521,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	ide_expiry_t *expiry = NULL;
 	int dma_error = 0, dma, thislen, uptodate = 0;
 	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0;
-	int sense = (rq->cmd_type == REQ_TYPE_ATA_SENSE);
+	int sense = ata_sense_request(rq);
 	unsigned int timeout;
 	u16 len;
 	u8 ireason, stat;
@@ -569,7 +564,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 	ide_read_bcount_and_ireason(drive, &len, &ireason);
 
-	thislen = (rq->cmd_type == REQ_TYPE_FS) ? len : cmd->nleft;
+	thislen = !blk_rq_is_passthrough(rq) ? len : cmd->nleft;
 	if (thislen > len)
 		thislen = len;
 
@@ -578,7 +573,8 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 	/* If DRQ is clear, the command has completed. */
 	if ((stat & ATA_DRQ) == 0) {
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		switch (req_op(rq)) {
+		default:
 			/*
 			 * If we're not done reading/writing, complain.
 			 * Otherwise, complete the command normally.
@@ -592,7 +588,9 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 					rq->rq_flags |= RQF_FAILED;
 				uptodate = 0;
 			}
-		} else if (rq->cmd_type != REQ_TYPE_BLOCK_PC) {
+			goto out_end;
+		case REQ_OP_DRV_IN:
+		case REQ_OP_DRV_OUT:
 			ide_cd_request_sense_fixup(drive, cmd);
 
 			uptodate = cmd->nleft ? 0 : 1;
@@ -608,8 +606,11 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 			if (!uptodate)
 				rq->rq_flags |= RQF_FAILED;
+			goto out_end;
+		case REQ_OP_SCSI_IN:
+		case REQ_OP_SCSI_OUT:
+			goto out_end;
 		}
-		goto out_end;
 	}
 
 	rc = ide_check_ireason(drive, rq, len, ireason, write);
@@ -636,12 +637,12 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 		len -= blen;
 
 		if (sense && write == 0)
-			rq->sense_len += blen;
+			scsi_req(rq)->sense_len += blen;
 	}
 
 	/* pad, if necessary */
 	if (len > 0) {
-		if (rq->cmd_type != REQ_TYPE_FS || write == 0)
+		if (blk_rq_is_passthrough(rq) || write == 0)
 			ide_pad_transfer(drive, write, len);
 		else {
 			printk(KERN_ERR PFX "%s: confused, missing data\n",
@@ -650,12 +651,18 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 		}
 	}
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+	switch (req_op(rq)) {
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
 		timeout = rq->timeout;
-	} else {
+		break;
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		expiry = ide_cd_expiry;
+		/*FALLTHRU*/
+	default:
 		timeout = ATAPI_WAIT_PC;
-		if (rq->cmd_type != REQ_TYPE_FS)
+		break;
-			expiry = ide_cd_expiry;
 	}
 
 	hwif->expiry = expiry;
@@ -663,15 +670,15 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	return ide_started;
 
 out_end:
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) {
+	if (blk_rq_is_scsi(rq) && rc == 0) {
-		rq->resid_len = 0;
+		scsi_req(rq)->resid_len = 0;
 		blk_end_request_all(rq, 0);
 		hwif->rq = NULL;
 	} else {
 		if (sense && uptodate)
 			ide_cd_complete_failed_rq(drive, rq);
 
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(rq)) {
 			if (cmd->nleft == 0)
 				uptodate = 1;
 		} else {
@@ -684,10 +691,10 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 				return ide_stopped;
 
 		/* make sure it's fully ended */
-		if (rq->cmd_type != REQ_TYPE_FS) {
+		if (blk_rq_is_passthrough(rq)) {
-			rq->resid_len -= cmd->nbytes - cmd->nleft;
+			scsi_req(rq)->resid_len -= cmd->nbytes - cmd->nleft;
 			if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE))
-				rq->resid_len += cmd->last_xfer_len;
+				scsi_req(rq)->resid_len += cmd->last_xfer_len;
 		}
 
 		ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
@@ -744,7 +751,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq)
 	ide_debug_log(IDE_DBG_PC, "rq->cmd[0]: 0x%x, rq->cmd_type: 0x%x",
 				  rq->cmd[0], rq->cmd_type);
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	if (blk_rq_is_scsi(rq))
 		rq->rq_flags |= RQF_QUIET;
 	else
 		rq->rq_flags &= ~RQF_FAILED;
@@ -786,25 +793,31 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 	if (drive->debug_mask & IDE_DBG_RQ)
 		blk_dump_rq_flags(rq, "ide_cd_do_request");
 
-	switch (rq->cmd_type) {
+	switch (req_op(rq)) {
-	case REQ_TYPE_FS:
+	default:
 		if (cdrom_start_rw(drive, rq) == ide_stopped)
 			goto out_end;
 		break;
-	case REQ_TYPE_ATA_SENSE:
+	case REQ_OP_SCSI_IN:
-	case REQ_TYPE_BLOCK_PC:
+	case REQ_OP_SCSI_OUT:
-	case REQ_TYPE_ATA_PC:
+	handle_pc:
 		if (!rq->timeout)
 			rq->timeout = ATAPI_WAIT_PC;
-
 		cdrom_do_block_pc(drive, rq);
 		break;
-	case REQ_TYPE_DRV_PRIV:
+	case REQ_OP_DRV_IN:
-		/* right now this can only be a reset... */
+	case REQ_OP_DRV_OUT:
-		uptodate = 1;
+		switch (ide_req(rq)->type) {
-		goto out_end;
+		case ATA_PRIV_MISC:
-	default:
+			/* right now this can only be a reset... */
-		BUG();
+			uptodate = 1;
+			goto out_end;
+		case ATA_PRIV_SENSE:
+		case ATA_PRIV_PC:
+			goto handle_pc;
+		default:
+			BUG();
+		}
 	}
 
 	/* prepare sense request for this command */
@@ -817,7 +830,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 
 	cmd.rq = rq;
 
-	if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) {
+	if (!blk_rq_is_passthrough(rq) || blk_rq_bytes(rq)) {
 		ide_init_sg_cmd(&cmd, blk_rq_bytes(rq));
 		ide_map_sg(drive, &cmd);
 	}
@@ -1312,28 +1325,29 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
 	int hard_sect = queue_logical_block_size(q);
 	long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
 	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
+	struct scsi_request *req = scsi_req(rq);
 
-	memset(rq->cmd, 0, BLK_MAX_CDB);
+	memset(req->cmd, 0, BLK_MAX_CDB);
 
 	if (rq_data_dir(rq) == READ)
-		rq->cmd[0] = GPCMD_READ_10;
+		req->cmd[0] = GPCMD_READ_10;
 	else
-		rq->cmd[0] = GPCMD_WRITE_10;
+		req->cmd[0] = GPCMD_WRITE_10;
 
 	/*
 	 * fill in lba
 	 */
-	rq->cmd[2] = (block >> 24) & 0xff;
+	req->cmd[2] = (block >> 24) & 0xff;
-	rq->cmd[3] = (block >> 16) & 0xff;
+	req->cmd[3] = (block >> 16) & 0xff;
-	rq->cmd[4] = (block >>  8) & 0xff;
+	req->cmd[4] = (block >>  8) & 0xff;
-	rq->cmd[5] = block & 0xff;
+	req->cmd[5] = block & 0xff;
 
 	/*
 	 * and transfer length
 	 */
-	rq->cmd[7] = (blocks >> 8) & 0xff;
+	req->cmd[7] = (blocks >> 8) & 0xff;
-	rq->cmd[8] = blocks & 0xff;
+	req->cmd[8] = blocks & 0xff;
-	rq->cmd_len = 10;
+	req->cmd_len = 10;
 	return BLKPREP_OK;
 }
 
@@ -1343,7 +1357,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
  */
 static int ide_cdrom_prep_pc(struct request *rq)
 {
-	u8 *c = rq->cmd;
+	u8 *c = scsi_req(rq)->cmd;
 
 	/* transform 6-byte read/write commands to the 10-byte version */
 	if (c[0] == READ_6 || c[0] == WRITE_6) {
@@ -1354,7 +1368,7 @@ static int ide_cdrom_prep_pc(struct request *rq)
 		c[2] = 0;
 		c[1] &= 0xe0;
 		c[0] += (READ_10 - READ_6);
-		rq->cmd_len = 10;
+		scsi_req(rq)->cmd_len = 10;
 		return BLKPREP_OK;
 	}
 
@@ -1373,9 +1387,9 @@ static int ide_cdrom_prep_pc(struct request *rq)
 
 static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq)
 {
-	if (rq->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(rq))
 		return ide_cdrom_prep_fs(q, rq);
-	else if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	else if (blk_rq_is_scsi(rq))
 		return ide_cdrom_prep_pc(rq);
 
 	return 0;

drivers/ide/ide-cd_ioctl.c

@@ -303,8 +303,9 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	struct request *rq;
 	int ret;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->rq_flags = RQF_QUIET;
 	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
 	blk_put_request(rq);

drivers/ide/ide-cd_verbose.c

@@ -315,12 +315,12 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
 		while (hi > lo) {
 			mid = (lo + hi) / 2;
 			if (packet_command_texts[mid].packet_command ==
-			    failed_command->cmd[0]) {
+			    scsi_req(failed_command)->cmd[0]) {
 				s = packet_command_texts[mid].text;
 				break;
 			}
 			if (packet_command_texts[mid].packet_command >
-			    failed_command->cmd[0])
+			    scsi_req(failed_command)->cmd[0])
 				hi = mid;
 			else
 				lo = mid + 1;
@@ -329,7 +329,7 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
 		printk(KERN_ERR "  The failed \"%s\" packet command "
 				"was: \n  \"", s);
 		for (i = 0; i < BLK_MAX_CDB; i++)
-			printk(KERN_CONT "%02x ", failed_command->cmd[i]);
+			printk(KERN_CONT "%02x ", scsi_req(failed_command)->cmd[i]);
 		printk(KERN_CONT "\"\n");
 	}
 

drivers/ide/ide-devsets.c

@@ -165,11 +165,12 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	if (!(setting->flags & DS_SYNC))
 		return setting->set(drive, arg);
 
-	rq = blk_get_request(q, READ, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req_init(rq);
-	rq->cmd_len = 5;
+	ide_req(rq)->type = ATA_PRIV_MISC;
-	rq->cmd[0] = REQ_DEVSET_EXEC;
+	scsi_req(rq)->cmd_len = 5;
-	*(int *)&rq->cmd[1] = arg;
+	scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
+	*(int *)&scsi_req(rq)->cmd[1] = arg;
 	rq->special = setting->set;
 
 	if (blk_execute_rq(q, NULL, rq, 0))
@@ -183,7 +184,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
 {
 	int err, (*setfunc)(ide_drive_t *, int) = rq->special;
 
-	err = setfunc(drive, *(int *)&rq->cmd[1]);
+	err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
 	if (err)
 		rq->errors = err;
 	ide_complete_rq(drive, err, blk_rq_bytes(rq));

drivers/ide/ide-disk.c

@@ -184,7 +184,7 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 	ide_hwif_t *hwif = drive->hwif;
 
 	BUG_ON(drive->dev_flags & IDE_DFLAG_BLOCKED);
-	BUG_ON(rq->cmd_type != REQ_TYPE_FS);
+	BUG_ON(blk_rq_is_passthrough(rq));
 
 	ledtrig_disk_activity();
 
@@ -452,8 +452,9 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
 	cmd->valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE;
 	cmd->tf_flags = IDE_TFLAG_DYN;
 	cmd->protocol = ATA_PROT_NODATA;
-
+	rq->cmd_flags &= ~REQ_OP_MASK;
-	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+	rq->cmd_flags |= REQ_OP_DRV_OUT;
+	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 	rq->special = cmd;
 	cmd->rq = rq;
 
@@ -477,8 +478,9 @@ static int set_multcount(ide_drive_t *drive, int arg)
 	if (drive->special_flags & IDE_SFLAG_SET_MULTMODE)
 		return -EBUSY;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	drive->mult_req = arg;
 	drive->special_flags |= IDE_SFLAG_SET_MULTMODE;

drivers/ide/ide-eh.c

@@ -123,8 +123,8 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 		return ide_stopped;
 
 	/* retry only "normal" I/O: */
-	if (rq->cmd_type != REQ_TYPE_FS) {
+	if (blk_rq_is_passthrough(rq)) {
-		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) {
+		if (ata_taskfile_request(rq)) {
 			struct ide_cmd *cmd = rq->special;
 
 			if (cmd)
@@ -147,8 +147,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 {
 	struct request *rq = drive->hwif->rq;
 
-	if (rq && rq->cmd_type == REQ_TYPE_DRV_PRIV &&
+	if (rq && ata_misc_request(rq) &&
-	    rq->cmd[0] == REQ_DRIVE_RESET) {
+	    scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
 		if (err <= 0 && rq->errors == 0)
 			rq->errors = -EIO;
 		ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));

drivers/ide/ide-floppy.c

@@ -72,7 +72,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 		drive->failed_pc = NULL;
 
 	if (pc->c[0] == GPCMD_READ_10 || pc->c[0] == GPCMD_WRITE_10 ||
-	    rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	    (req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT))
 		uptodate = 1; /* FIXME */
 	else if (pc->c[0] == GPCMD_REQUEST_SENSE) {
 
@@ -97,7 +97,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 			       "Aborting request!\n");
 	}
 
-	if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+	if (ata_misc_request(rq))
 		rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
 
 	return uptodate;
@@ -203,7 +203,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive,
 	put_unaligned(cpu_to_be16(blocks), (unsigned short *)&pc->c[7]);
 	put_unaligned(cpu_to_be32(block), (unsigned int *) &pc->c[2]);
 
-	memcpy(rq->cmd, pc->c, 12);
+	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 
 	pc->rq = rq;
 	if (cmd == WRITE)
@@ -216,7 +216,7 @@ static void idefloppy_blockpc_cmd(struct ide_disk_obj *floppy,
 		struct ide_atapi_pc *pc, struct request *rq)
 {
 	ide_init_pc(pc);
-	memcpy(pc->c, rq->cmd, sizeof(pc->c));
+	memcpy(pc->c, scsi_req(rq)->cmd, sizeof(pc->c));
 	pc->rq = rq;
 	if (blk_rq_bytes(rq)) {
 		pc->flags |= PC_FLAG_DMA_OK;
@@ -246,7 +246,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		} else
 			printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
 
-		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
+		if (ata_misc_request(rq)) {
 			rq->errors = 0;
 			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 			return ide_stopped;
@@ -254,8 +254,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 			goto out_end;
 	}
 
-	switch (rq->cmd_type) {
+	switch (req_op(rq)) {
-	case REQ_TYPE_FS:
+	default:
 		if (((long)blk_rq_pos(rq) % floppy->bs_factor) ||
 		    (blk_rq_sectors(rq) % floppy->bs_factor)) {
 			printk(KERN_ERR PFX "%s: unsupported r/w rq size\n",
@@ -265,16 +265,21 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		pc = &floppy->queued_pc;
 		idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
 		break;
-	case REQ_TYPE_DRV_PRIV:
+	case REQ_OP_SCSI_IN:
-	case REQ_TYPE_ATA_SENSE:
+	case REQ_OP_SCSI_OUT:
-		pc = (struct ide_atapi_pc *)rq->special;
-		break;
-	case REQ_TYPE_BLOCK_PC:
 		pc = &floppy->queued_pc;
 		idefloppy_blockpc_cmd(floppy, pc, rq);
 		break;
-	default:
+	case REQ_OP_DRV_IN:
-		BUG();
+	case REQ_OP_DRV_OUT:
+		switch (ide_req(rq)->type) {
+		case ATA_PRIV_MISC:
+		case ATA_PRIV_SENSE:
+			pc = (struct ide_atapi_pc *)rq->special;
+			break;
+		default:
+			BUG();
+		}
 	}
 
 	ide_prep_sense(drive, rq);
@@ -286,7 +291,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 
 	cmd.rq = rq;
 
-	if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) {
+	if (!blk_rq_is_passthrough(rq) || blk_rq_bytes(rq)) {
 		ide_init_sg_cmd(&cmd, blk_rq_bytes(rq));
 		ide_map_sg(drive, &cmd);
 	}
@@ -296,7 +301,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 	return ide_floppy_issue_pc(drive, &cmd, pc);
 out_end:
 	drive->failed_pc = NULL;
-	if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0)
+	if (blk_rq_is_passthrough(rq) && rq->errors == 0)
 		rq->errors = -EIO;
 	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 	return ide_stopped;

drivers/ide/ide-io.c

@@ -102,7 +102,7 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 			drive->dev_flags |= IDE_DFLAG_PARKED;
 	}
 
-	if (rq && rq->cmd_type == REQ_TYPE_ATA_TASKFILE) {
+	if (rq && ata_taskfile_request(rq)) {
 		struct ide_cmd *orig_cmd = rq->special;
 
 		if (cmd->tf_flags & IDE_TFLAG_DYN)
@@ -135,7 +135,7 @@ EXPORT_SYMBOL(ide_complete_rq);
 
 void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 {
-	u8 drv_req = (rq->cmd_type == REQ_TYPE_DRV_PRIV) && rq->rq_disk;
+	u8 drv_req = ata_misc_request(rq) && rq->rq_disk;
 	u8 media = drive->media;
 
 	drive->failed_pc = NULL;
@@ -145,7 +145,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 	} else {
 		if (media == ide_tape)
 			rq->errors = IDE_DRV_ERROR_GENERAL;
-		else if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0)
+		else if (blk_rq_is_passthrough(rq) && rq->errors == 0)
 			rq->errors = -EIO;
 	}
 
@@ -279,7 +279,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 
 static ide_startstop_t ide_special_rq(ide_drive_t *drive, struct request *rq)
 {
-	u8 cmd = rq->cmd[0];
+	u8 cmd = scsi_req(rq)->cmd[0];
 
 	switch (cmd) {
 	case REQ_PARK_HEADS:
@@ -340,7 +340,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		if (drive->current_speed == 0xff)
 			ide_config_drive_speed(drive, drive->desired_speed);
 
-		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)
+		if (ata_taskfile_request(rq))
 			return execute_drive_cmd(drive, rq);
 		else if (ata_pm_request(rq)) {
 			struct ide_pm_state *pm = rq->special;
@@ -353,7 +353,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 			    pm->pm_step == IDE_PM_COMPLETED)
 				ide_complete_pm_rq(drive, rq);
 			return startstop;
-		} else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_DRV_PRIV)
+		} else if (!rq->rq_disk && ata_misc_request(rq))
 			/*
 			 * TODO: Once all ULDs have been modified to
 			 * check for specific op codes rather than
@@ -545,6 +545,7 @@ void do_ide_request(struct request_queue *q)
 			goto plug_device;
 		}
 
+		scsi_req(rq)->resid_len = blk_rq_bytes(rq);
 		hwif->rq = rq;
 
 		spin_unlock_irq(&hwif->lock);

drivers/ide/ide-ioctls.c

@@ -125,8 +125,9 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 	if (NULL == (void *) arg) {
 		struct request *rq;
 
-		rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-		rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+		scsi_req_init(rq);
+		ide_req(rq)->type = ATA_PRIV_TASKFILE;
 		err = blk_execute_rq(drive->queue, NULL, rq, 0);
 		blk_put_request(rq);
 
@@ -221,10 +222,11 @@ static int generic_drive_reset(ide_drive_t *drive)
 	struct request *rq;
 	int ret = 0;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req_init(rq);
-	rq->cmd_len = 1;
+	ide_req(rq)->type = ATA_PRIV_MISC;
-	rq->cmd[0] = REQ_DRIVE_RESET;
+	scsi_req(rq)->cmd_len = 1;
+	scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
 	if (blk_execute_rq(drive->queue, NULL, rq, 1))
 		ret = rq->errors;
 	blk_put_request(rq);

drivers/ide/ide-park.c

@@ -31,10 +31,11 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	}
 	spin_unlock_irq(&hwif->lock);
 
-	rq = blk_get_request(q, READ, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd[0] = REQ_PARK_HEADS;
+	scsi_req_init(rq);
-	rq->cmd_len = 1;
+	scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req(rq)->cmd_len = 1;
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = &timeout;
 	rc = blk_execute_rq(q, NULL, rq, 1);
 	blk_put_request(rq);
@@ -45,13 +46,14 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	 * Make sure that *some* command is sent to the drive after the
 	 * timeout has expired, so power management will be reenabled.
 	 */
-	rq = blk_get_request(q, READ, GFP_NOWAIT);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT);
+	scsi_req_init(rq);
 	if (IS_ERR(rq))
 		goto out;
 
-	rq->cmd[0] = REQ_UNPARK_HEADS;
+	scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS;
-	rq->cmd_len = 1;
+	scsi_req(rq)->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
 
 out:
@@ -64,7 +66,7 @@ ide_startstop_t ide_do_park_unpark(ide_drive_t *drive, struct request *rq)
 	struct ide_taskfile *tf = &cmd.tf;
 
 	memset(&cmd, 0, sizeof(cmd));
-	if (rq->cmd[0] == REQ_PARK_HEADS) {
+	if (scsi_req(rq)->cmd[0] == REQ_PARK_HEADS) {
 		drive->sleep = *(unsigned long *)rq->special;
 		drive->dev_flags |= IDE_DFLAG_SLEEPING;
 		tf->command = ATA_CMD_IDLEIMMEDIATE;

drivers/ide/ide-pm.c

@@ -18,8 +18,9 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND;
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
 	if (mesg.event == PM_EVENT_PRETHAW)
@@ -88,8 +89,9 @@ int generic_ide_resume(struct device *dev)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_PM_RESUME;
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_PM_RESUME;
 	rq->rq_flags |= RQF_PREEMPT;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
@@ -221,10 +223,10 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 #ifdef DEBUG_PM
 	printk("%s: completing PM request, %s\n", drive->name,
-	       (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND) ? "suspend" : "resume");
+	       (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND) ? "suspend" : "resume");
 #endif
 	spin_lock_irqsave(q->queue_lock, flags);
-	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND)
+	if (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND)
 		blk_stop_queue(q);
 	else
 		drive->dev_flags &= ~IDE_DFLAG_BLOCKED;
@@ -240,11 +242,13 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 {
 	struct ide_pm_state *pm = rq->special;
 
-	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND &&
+	if (blk_rq_is_private(rq) &&
+	    ide_req(rq)->type == ATA_PRIV_PM_SUSPEND &&
 	    pm->pm_step == IDE_PM_START_SUSPEND)
 		/* Mark drive blocked when starting the suspend sequence. */
 		drive->dev_flags |= IDE_DFLAG_BLOCKED;
-	else if (rq->cmd_type == REQ_TYPE_ATA_PM_RESUME &&
+	else if (blk_rq_is_private(rq) &&
+	         ide_req(rq)->type == ATA_PRIV_PM_RESUME &&
 		 pm->pm_step == IDE_PM_START_RESUME) {
 		/*
 		 * The first thing we do on wakeup is to wait for BSY bit to

drivers/ide/ide-probe.c

@@ -741,6 +741,14 @@ static void ide_port_tune_devices(ide_hwif_t *hwif)
 	}
 }
 
+static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+	struct ide_request *req = blk_mq_rq_to_pdu(rq);
+
+	req->sreq.sense = req->sense;
+	return 0;
+}
+
 /*
  * init request queue
  */
@@ -758,11 +766,18 @@ static int ide_init_queue(ide_drive_t *drive)
 	 *	limits and LBA48 we could raise it but as yet
 	 *	do not.
 	 */
-
+	q = blk_alloc_queue_node(GFP_KERNEL, hwif_to_node(hwif));
-	q = blk_init_queue_node(do_ide_request, NULL, hwif_to_node(hwif));
 	if (!q)
 		return 1;
 
+	q->request_fn = do_ide_request;
+	q->init_rq_fn = ide_init_rq;
+	q->cmd_size = sizeof(struct ide_request);
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return 1;
+	}
+
 	q->queuedata = drive;
 	blk_queue_segment_boundary(q, 0xffff);
 
@@ -1131,10 +1146,12 @@ static void ide_port_init_devices_data(ide_hwif_t *hwif)
 	ide_port_for_each_dev(i, drive, hwif) {
 		u8 j = (hwif->index * MAX_DRIVES) + i;
 		u16 *saved_id = drive->id;
+		struct request *saved_sense_rq = drive->sense_rq;
 
 		memset(drive, 0, sizeof(*drive));
 		memset(saved_id, 0, SECTOR_SIZE);
 		drive->id = saved_id;
+		drive->sense_rq = saved_sense_rq;
 
 		drive->media			= ide_disk;
 		drive->select			= (i << 4) | ATA_DEVICE_OBS;
@@ -1241,6 +1258,7 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
 	int i;
 
 	ide_port_for_each_dev(i, drive, hwif) {
+		kfree(drive->sense_rq);
 		kfree(drive->id);
 		kfree(drive);
 	}
@@ -1248,11 +1266,10 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
 
 static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
 {
+	ide_drive_t *drive;
 	int i;
 
 	for (i = 0; i < MAX_DRIVES; i++) {
-		ide_drive_t *drive;
-
 		drive = kzalloc_node(sizeof(*drive), GFP_KERNEL, node);
 		if (drive == NULL)
 			goto out_nomem;
@@ -1267,12 +1284,21 @@ static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
 		 */
 		drive->id = kzalloc_node(SECTOR_SIZE, GFP_KERNEL, node);
 		if (drive->id == NULL)
-			goto out_nomem;
+			goto out_free_drive;
+
+		drive->sense_rq = kmalloc(sizeof(struct request) +
+				sizeof(struct ide_request), GFP_KERNEL);
+		if (!drive->sense_rq)
+			goto out_free_id;
 
 		hwif->devices[i] = drive;
 	}
 	return 0;
 
+out_free_id:
+	kfree(drive->id);
+out_free_drive:
+	kfree(drive);
 out_nomem:
 	ide_port_free_devices(hwif);
 	return -ENOMEM;

drivers/ide/ide-tape.c

@@ -282,7 +282,7 @@ static void idetape_analyze_error(ide_drive_t *drive)
 
 	/* correct remaining bytes to transfer */
 	if (pc->flags & PC_FLAG_DMA_ERROR)
-		rq->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]);
+		scsi_req(rq)->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]);
 
 	/*
 	 * If error was the result of a zero-length read or write command,
@@ -316,7 +316,7 @@ static void idetape_analyze_error(ide_drive_t *drive)
 			pc->flags |= PC_FLAG_ABORT;
 		}
 		if (!(pc->flags & PC_FLAG_ABORT) &&
-		    (blk_rq_bytes(rq) - rq->resid_len))
+		    (blk_rq_bytes(rq) - scsi_req(rq)->resid_len))
 			pc->retries = IDETAPE_MAX_PC_RETRIES + 1;
 	}
 }
@@ -348,7 +348,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
 					"itself - Aborting request!\n");
 	} else if (pc->c[0] == READ_6 || pc->c[0] == WRITE_6) {
 		unsigned int blocks =
-			(blk_rq_bytes(rq) - rq->resid_len) / tape->blk_size;
+			(blk_rq_bytes(rq) - scsi_req(rq)->resid_len) / tape->blk_size;
 
 		tape->avg_size += blocks * tape->blk_size;
 
@@ -560,7 +560,7 @@ static void ide_tape_create_rw_cmd(idetape_tape_t *tape,
 		pc->flags |= PC_FLAG_WRITING;
 	}
 
-	memcpy(rq->cmd, pc->c, 12);
+	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 }
 
 static ide_startstop_t idetape_do_request(ide_drive_t *drive,
@@ -570,14 +570,16 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	idetape_tape_t *tape = drive->driver_data;
 	struct ide_atapi_pc *pc = NULL;
 	struct ide_cmd cmd;
+	struct scsi_request *req = scsi_req(rq);
 	u8 stat;
 
 	ide_debug_log(IDE_DBG_RQ, "cmd: 0x%x, sector: %llu, nr_sectors: %u",
-		      rq->cmd[0], (unsigned long long)blk_rq_pos(rq),
+		      req->cmd[0], (unsigned long long)blk_rq_pos(rq),
 		      blk_rq_sectors(rq));
 
-	BUG_ON(!(rq->cmd_type == REQ_TYPE_DRV_PRIV ||
+	BUG_ON(!blk_rq_is_private(rq));
-		 rq->cmd_type == REQ_TYPE_ATA_SENSE));
+	BUG_ON(ide_req(rq)->type != ATA_PRIV_MISC &&
+	       ide_req(rq)->type != ATA_PRIV_SENSE);
 
 	/* Retry a failed packet command */
 	if (drive->failed_pc && drive->pc->c[0] == REQUEST_SENSE) {
@@ -592,7 +594,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	stat = hwif->tp_ops->read_status(hwif);
 
 	if ((drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) == 0 &&
-	    (rq->cmd[13] & REQ_IDETAPE_PC2) == 0)
+	    (req->cmd[13] & REQ_IDETAPE_PC2) == 0)
 		drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC;
 
 	if (drive->dev_flags & IDE_DFLAG_POST_RESET) {
@@ -609,7 +611,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		} else if (time_after(jiffies, tape->dsc_timeout)) {
 			printk(KERN_ERR "ide-tape: %s: DSC timeout\n",
 				tape->name);
-			if (rq->cmd[13] & REQ_IDETAPE_PC2) {
+			if (req->cmd[13] & REQ_IDETAPE_PC2) {
 				idetape_media_access_finished(drive);
 				return ide_stopped;
 			} else {
@@ -626,23 +628,23 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		tape->postponed_rq = false;
 	}
 
-	if (rq->cmd[13] & REQ_IDETAPE_READ) {
+	if (req->cmd[13] & REQ_IDETAPE_READ) {
 		pc = &tape->queued_pc;
 		ide_tape_create_rw_cmd(tape, pc, rq, READ_6);
 		goto out;
 	}
-	if (rq->cmd[13] & REQ_IDETAPE_WRITE) {
+	if (req->cmd[13] & REQ_IDETAPE_WRITE) {
 		pc = &tape->queued_pc;
 		ide_tape_create_rw_cmd(tape, pc, rq, WRITE_6);
 		goto out;
 	}
-	if (rq->cmd[13] & REQ_IDETAPE_PC1) {
+	if (req->cmd[13] & REQ_IDETAPE_PC1) {
 		pc = (struct ide_atapi_pc *)rq->special;
-		rq->cmd[13] &= ~(REQ_IDETAPE_PC1);
+		req->cmd[13] &= ~(REQ_IDETAPE_PC1);
-		rq->cmd[13] |= REQ_IDETAPE_PC2;
+		req->cmd[13] |= REQ_IDETAPE_PC2;
 		goto out;
 	}
-	if (rq->cmd[13] & REQ_IDETAPE_PC2) {
+	if (req->cmd[13] & REQ_IDETAPE_PC2) {
 		idetape_media_access_finished(drive);
 		return ide_stopped;
 	}
@@ -852,9 +854,10 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
 	BUG_ON(size < 0 || size % tape->blk_size);
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req_init(rq);
-	rq->cmd[13] = cmd;
+	ide_req(rq)->type = ATA_PRIV_MISC;
+	scsi_req(rq)->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
 	rq->__sector = tape->first_frame;
 
@@ -868,7 +871,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	blk_execute_rq(drive->queue, tape->disk, rq, 0);
 
 	/* calculate the number of transferred bytes and update buffer state */
-	size -= rq->resid_len;
+	size -= scsi_req(rq)->resid_len;
 	tape->cur = tape->buf;
 	if (cmd == REQ_IDETAPE_READ)
 		tape->valid = size;

drivers/ide/ide-taskfile.c

@@ -428,10 +428,12 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 {
 	struct request *rq;
 	int error;
-	int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE;
 
-	rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM);
+	rq = blk_get_request(drive->queue,
-	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+		(cmd->tf_flags & IDE_TFLAG_WRITE) ?
+			REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	/*
 	 * (ks) We transfer currently only whole sectors.

drivers/ide/sis5513.c

@@ -54,7 +54,7 @@
 #define DRV_NAME "sis5513"
 
 /* registers layout and init values are chipset family dependent */
-
+#undef ATA_16
 #define ATA_16		0x01
 #define ATA_33		0x02
 #define ATA_66		0x03

drivers/md/bcache/request.c

@@ -1009,7 +1009,7 @@ static int cached_dev_congested(void *data, int bits)
 	struct request_queue *q = bdev_get_queue(dc->bdev);
 	int ret = 0;
 
-	if (bdi_congested(&q->backing_dev_info, bits))
+	if (bdi_congested(q->backing_dev_info, bits))
 		return 1;
 
 	if (cached_dev_get(dc)) {
@@ -1018,7 +1018,7 @@ static int cached_dev_congested(void *data, int bits)
 
 		for_each_cache(ca, d->c, i) {
 			q = bdev_get_queue(ca->bdev);
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= bdi_congested(q->backing_dev_info, bits);
 		}
 
 		cached_dev_put(dc);
@@ -1032,7 +1032,7 @@ void bch_cached_dev_request_init(struct cached_dev *dc)
 	struct gendisk *g = dc->disk.disk;
 
 	g->queue->make_request_fn		= cached_dev_make_request;
-	g->queue->backing_dev_info.congested_fn = cached_dev_congested;
+	g->queue->backing_dev_info->congested_fn = cached_dev_congested;
 	dc->disk.cache_miss			= cached_dev_cache_miss;
 	dc->disk.ioctl				= cached_dev_ioctl;
 }
@@ -1125,7 +1125,7 @@ static int flash_dev_congested(void *data, int bits)
 
 	for_each_cache(ca, d->c, i) {
 		q = bdev_get_queue(ca->bdev);
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 
 	return ret;
@@ -1136,7 +1136,7 @@ void bch_flash_dev_request_init(struct bcache_device *d)
 	struct gendisk *g = d->disk;
 
 	g->queue->make_request_fn		= flash_dev_make_request;
-	g->queue->backing_dev_info.congested_fn = flash_dev_congested;
+	g->queue->backing_dev_info->congested_fn = flash_dev_congested;
 	d->cache_miss				= flash_dev_cache_miss;
 	d->ioctl				= flash_dev_ioctl;
 }

drivers/md/bcache/super.c

@@ -807,7 +807,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	blk_queue_make_request(q, NULL);
 	d->disk->queue			= q;
 	q->queuedata			= d;
-	q->backing_dev_info.congested_data = d;
+	q->backing_dev_info->congested_data = d;
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
@@ -1132,9 +1132,9 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
 	set_capacity(dc->disk.disk,
 		     dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
 
-	dc->disk.disk->queue->backing_dev_info.ra_pages =
+	dc->disk.disk->queue->backing_dev_info->ra_pages =
-		max(dc->disk.disk->queue->backing_dev_info.ra_pages,
+		max(dc->disk.disk->queue->backing_dev_info->ra_pages,
-		    q->backing_dev_info.ra_pages);
+		    q->backing_dev_info->ra_pages);
 
 	bch_cached_dev_request_init(dc);
 	bch_cached_dev_writeback_init(dc);

drivers/md/dm-cache-target.c

@@ -2284,7 +2284,7 @@ static void do_waker(struct work_struct *ws)
 static int is_congested(struct dm_dev *dev, int bdi_bits)
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(&q->backing_dev_info, bdi_bits);
+	return bdi_congested(q->backing_dev_info, bdi_bits);
 }
 
 static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits)

drivers/md/dm-core.h

@@ -92,7 +92,6 @@ struct mapped_device {
 	 * io objects are allocated from here.
 	 */
 	mempool_t *io_pool;
-	mempool_t *rq_pool;
 
 	struct bio_set *bs;
 

drivers/md/dm-era-target.c

@@ -1379,7 +1379,7 @@ static void stop_worker(struct era *era)
 static int dev_is_congested(struct dm_dev *dev, int bdi_bits)
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(&q->backing_dev_info, bdi_bits);
+	return bdi_congested(q->backing_dev_info, bdi_bits);
 }
 
 static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits)

drivers/md/dm-mpath.c

@@ -92,12 +92,6 @@ struct multipath {
 
 	unsigned queue_mode;
 
-	/*
-	 * We must use a mempool of dm_mpath_io structs so that we
-	 * can resubmit bios on error.
-	 */
-	mempool_t *mpio_pool;
-
 	struct mutex work_mutex;
 	struct work_struct trigger_event;
 
@@ -115,8 +109,6 @@ struct dm_mpath_io {
 
 typedef int (*action_fn) (struct pgpath *pgpath);
 
-static struct kmem_cache *_mpio_cache;
-
 static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
 static void trigger_event(struct work_struct *work);
 static void activate_path(struct work_struct *work);
@@ -209,7 +201,6 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 		init_waitqueue_head(&m->pg_init_wait);
 		mutex_init(&m->work_mutex);
 
-		m->mpio_pool = NULL;
 		m->queue_mode = DM_TYPE_NONE;
 
 		m->ti = ti;
@@ -229,16 +220,7 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
 			m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
 		else
 			m->queue_mode = DM_TYPE_REQUEST_BASED;
-	}
+	} else if (m->queue_mode == DM_TYPE_BIO_BASED) {
-
-	if (m->queue_mode == DM_TYPE_REQUEST_BASED) {
-		unsigned min_ios = dm_get_reserved_rq_based_ios();
-
-		m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
-		if (!m->mpio_pool)
-			return -ENOMEM;
-	}
-	else if (m->queue_mode == DM_TYPE_BIO_BASED) {
 		INIT_WORK(&m->process_queued_bios, process_queued_bios);
 		/*
 		 * bio-based doesn't support any direct scsi_dh management;
@@ -263,7 +245,6 @@ static void free_multipath(struct multipath *m)
 
 	kfree(m->hw_handler_name);
 	kfree(m->hw_handler_params);
-	mempool_destroy(m->mpio_pool);
 	kfree(m);
 }
 
@@ -272,38 +253,6 @@ static struct dm_mpath_io *get_mpio(union map_info *info)
 	return info->ptr;
 }
 
-static struct dm_mpath_io *set_mpio(struct multipath *m, union map_info *info)
-{
-	struct dm_mpath_io *mpio;
-
-	if (!m->mpio_pool) {
-		/* Use blk-mq pdu memory requested via per_io_data_size */
-		mpio = get_mpio(info);
-		memset(mpio, 0, sizeof(*mpio));
-		return mpio;
-	}
-
-	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
-	if (!mpio)
-		return NULL;
-
-	memset(mpio, 0, sizeof(*mpio));
-	info->ptr = mpio;
-
-	return mpio;
-}
-
-static void clear_request_fn_mpio(struct multipath *m, union map_info *info)
-{
-	/* Only needed for non blk-mq (.request_fn) multipath */
-	if (m->mpio_pool) {
-		struct dm_mpath_io *mpio = info->ptr;
-
-		info->ptr = NULL;
-		mempool_free(mpio, m->mpio_pool);
-	}
-}
-
 static size_t multipath_per_bio_data_size(void)
 {
 	return sizeof(struct dm_mpath_io) + sizeof(struct dm_bio_details);
@@ -530,16 +479,17 @@ static bool must_push_back_bio(struct multipath *m)
 /*
  * Map cloned requests (request-based multipath)
  */
-static int __multipath_map(struct dm_target *ti, struct request *clone,
+static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
-			   union map_info *map_context,
+				   union map_info *map_context,
-			   struct request *rq, struct request **__clone)
+				   struct request **__clone)
 {
 	struct multipath *m = ti->private;
 	int r = DM_MAPIO_REQUEUE;
-	size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
+	size_t nr_bytes = blk_rq_bytes(rq);
 	struct pgpath *pgpath;
 	struct block_device *bdev;
-	struct dm_mpath_io *mpio;
+	struct dm_mpath_io *mpio = get_mpio(map_context);
+	struct request *clone;
 
 	/* Do we need to select a new pgpath? */
 	pgpath = lockless_dereference(m->current_pgpath);
@@ -556,42 +506,23 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		return r;
 	}
 
-	mpio = set_mpio(m, map_context);
+	memset(mpio, 0, sizeof(*mpio));
-	if (!mpio)
-		/* ENOMEM, requeue */
-		return r;
-
 	mpio->pgpath = pgpath;
 	mpio->nr_bytes = nr_bytes;
 
 	bdev = pgpath->path.dev->bdev;
 
-	if (clone) {
+	clone = blk_get_request(bdev_get_queue(bdev),
-		/*
+			rq->cmd_flags | REQ_NOMERGE,
-		 * Old request-based interface: allocated clone is passed in.
+			GFP_ATOMIC);
-		 * Used by: .request_fn stacked on .request_fn path(s).
+	if (IS_ERR(clone)) {
-		 */
+		/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
-		clone->q = bdev_get_queue(bdev);
+		return r;
-		clone->rq_disk = bdev->bd_disk;
-		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	} else {
-		/*
-		 * blk-mq request-based interface; used by both:
-		 * .request_fn stacked on blk-mq path(s) and
-		 * blk-mq stacked on blk-mq path(s).
-		 */
-		clone = blk_mq_alloc_request(bdev_get_queue(bdev),
-					     rq_data_dir(rq), BLK_MQ_REQ_NOWAIT);
-		if (IS_ERR(clone)) {
-			/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
-			clear_request_fn_mpio(m, map_context);
-			return r;
-		}
-		clone->bio = clone->biotail = NULL;
-		clone->rq_disk = bdev->bd_disk;
-		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-		*__clone = clone;
 	}
+	clone->bio = clone->biotail = NULL;
+	clone->rq_disk = bdev->bd_disk;
+	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	*__clone = clone;
 
 	if (pgpath->pg->ps.type->start_io)
 		pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
@@ -600,22 +531,9 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 	return DM_MAPIO_REMAPPED;
 }
 
-static int multipath_map(struct dm_target *ti, struct request *clone,
-			 union map_info *map_context)
-{
-	return __multipath_map(ti, clone, map_context, NULL, NULL);
-}
-
-static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
-				   union map_info *map_context,
-				   struct request **clone)
-{
-	return __multipath_map(ti, NULL, map_context, rq, clone);
-}
-
 static void multipath_release_clone(struct request *clone)
 {
-	blk_mq_free_request(clone);
+	blk_put_request(clone);
 }
 
 /*
@@ -1187,7 +1105,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->num_write_same_bios = 1;
 	if (m->queue_mode == DM_TYPE_BIO_BASED)
 		ti->per_io_data_size = multipath_per_bio_data_size();
-	else if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED)
+	else
 		ti->per_io_data_size = sizeof(struct dm_mpath_io);
 
 	return 0;
@@ -1610,7 +1528,6 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}
-	clear_request_fn_mpio(m, map_context);
 
 	return r;
 }
@@ -2060,7 +1977,6 @@ static struct target_type multipath_target = {
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
-	.map_rq = multipath_map,
 	.clone_and_map_rq = multipath_clone_and_map,
 	.release_clone_rq = multipath_release_clone,
 	.rq_end_io = multipath_end_io,
@@ -2080,11 +1996,6 @@ static int __init dm_multipath_init(void)
 {
 	int r;
 
-	/* allocate a slab for the dm_mpath_ios */
-	_mpio_cache = KMEM_CACHE(dm_mpath_io, 0);
-	if (!_mpio_cache)
-		return -ENOMEM;
-
 	r = dm_register_target(&multipath_target);
 	if (r < 0) {
 		DMERR("request-based register failed %d", r);
@@ -2120,8 +2031,6 @@ static int __init dm_multipath_init(void)
 bad_alloc_kmultipathd:
 	dm_unregister_target(&multipath_target);
 bad_register_target:
-	kmem_cache_destroy(_mpio_cache);
-
 	return r;
 }
 
@@ -2131,7 +2040,6 @@ static void __exit dm_multipath_exit(void)
 	destroy_workqueue(kmultipathd);
 
 	dm_unregister_target(&multipath_target);
-	kmem_cache_destroy(_mpio_cache);
 }
 
 module_init(dm_multipath_init);

drivers/md/dm-rq.c

@@ -109,28 +109,6 @@ void dm_stop_queue(struct request_queue *q)
 		dm_mq_stop_queue(q);
 }
 
-static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
-						gfp_t gfp_mask)
-{
-	return mempool_alloc(md->io_pool, gfp_mask);
-}
-
-static void free_old_rq_tio(struct dm_rq_target_io *tio)
-{
-	mempool_free(tio, tio->md->io_pool);
-}
-
-static struct request *alloc_old_clone_request(struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	return mempool_alloc(md->rq_pool, gfp_mask);
-}
-
-static void free_old_clone_request(struct mapped_device *md, struct request *rq)
-{
-	mempool_free(rq, md->rq_pool);
-}
-
 /*
  * Partial completion handling for request-based dm
  */
@@ -185,7 +163,7 @@ static void end_clone_bio(struct bio *clone)
 
 static struct dm_rq_target_io *tio_from_request(struct request *rq)
 {
-	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
+	return blk_mq_rq_to_pdu(rq);
 }
 
 static void rq_end_stats(struct mapped_device *md, struct request *orig)
@@ -233,31 +211,6 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	dm_put(md);
 }
 
-static void free_rq_clone(struct request *clone)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-
-	blk_rq_unprep_clone(clone);
-
-	/*
-	 * It is possible for a clone_old_rq() allocated clone to
-	 * get passed in -- it may not yet have a request_queue.
-	 * This is known to occur if the error target replaces
-	 * a multipath target that has a request_fn queue stacked
-	 * on blk-mq queue(s).
-	 */
-	if (clone->q && clone->q->mq_ops)
-		/* stacked on blk-mq queue(s) */
-		tio->ti->type->release_clone_rq(clone);
-	else if (!md->queue->mq_ops)
-		/* request_fn queue stacked on request_fn queue(s) */
-		free_old_clone_request(md, clone);
-
-	if (!md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
 /*
  * Complete the clone and the original request.
  * Must be called without clone's queue lock held,
@@ -270,20 +223,9 @@ static void dm_end_request(struct request *clone, int error)
 	struct mapped_device *md = tio->md;
 	struct request *rq = tio->orig;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+	blk_rq_unprep_clone(clone);
-		rq->errors = clone->errors;
+	tio->ti->type->release_clone_rq(clone);
-		rq->resid_len = clone->resid_len;
 
-		if (rq->sense)
-			/*
-			 * We are using the sense buffer of the original
-			 * request.
-			 * So setting the length of the sense data is enough.
-			 */
-			rq->sense_len = clone->sense_len;
-	}
-
-	free_rq_clone(clone);
 	rq_end_stats(md, rq);
 	if (!rq->q->mq_ops)
 		blk_end_request_all(rq, error);
@@ -292,22 +234,6 @@ static void dm_end_request(struct request *clone, int error)
 	rq_completed(md, rw, true);
 }
 
-static void dm_unprep_request(struct request *rq)
-{
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-	struct request *clone = tio->clone;
-
-	if (!rq->q->mq_ops) {
-		rq->special = NULL;
-		rq->rq_flags &= ~RQF_DONTPREP;
-	}
-
-	if (clone)
-		free_rq_clone(clone);
-	else if (!tio->md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
 /*
  * Requeue the original request of a clone.
  */
@@ -346,7 +272,10 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_
 	int rw = rq_data_dir(rq);
 
 	rq_end_stats(md, rq);
-	dm_unprep_request(rq);
+	if (tio->clone) {
+		blk_rq_unprep_clone(tio->clone);
+		tio->ti->type->release_clone_rq(tio->clone);
+	}
 
 	if (!rq->q->mq_ops)
 		dm_old_requeue_request(rq);
@@ -401,14 +330,11 @@ static void dm_softirq_done(struct request *rq)
 	if (!clone) {
 		rq_end_stats(tio->md, rq);
 		rw = rq_data_dir(rq);
-		if (!rq->q->mq_ops) {
+		if (!rq->q->mq_ops)
 			blk_end_request_all(rq, tio->error);
-			rq_completed(tio->md, rw, false);
+		else
-			free_old_rq_tio(tio);
-		} else {
 			blk_mq_end_request(rq, tio->error);
-			rq_completed(tio->md, rw, false);
+		rq_completed(tio->md, rw, false);
-		}
 		return;
 	}
 
@@ -452,16 +378,6 @@ static void end_clone_request(struct request *clone, int error)
 {
 	struct dm_rq_target_io *tio = clone->end_io_data;
 
-	if (!clone->q->mq_ops) {
-		/*
-		 * For just cleaning up the information of the queue in which
-		 * the clone was dispatched.
-		 * The clone is *NOT* freed actually here because it is alloced
-		 * from dm own mempool (RQF_ALLOCED isn't set).
-		 */
-		__blk_put_request(clone->q, clone);
-	}
-
 	/*
 	 * Actual request completion is done in a softirq context which doesn't
 	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
@@ -511,9 +427,6 @@ static int setup_clone(struct request *clone, struct request *rq,
 	if (r)
 		return r;
 
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
@@ -522,28 +435,6 @@ static int setup_clone(struct request *clone, struct request *rq,
 	return 0;
 }
 
-static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
-				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	/*
-	 * Create clone for use with .request_fn request_queue
-	 */
-	struct request *clone;
-
-	clone = alloc_old_clone_request(md, gfp_mask);
-	if (!clone)
-		return NULL;
-
-	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
-		/* -ENOMEM */
-		free_old_clone_request(md, clone);
-		return NULL;
-	}
-
-	return clone;
-}
-
 static void map_tio_request(struct kthread_work *work);
 
 static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
@@ -565,60 +456,6 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
 		kthread_init_work(&tio->work, map_tio_request);
 }
 
-static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
-					       struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	struct dm_rq_target_io *tio;
-	int srcu_idx;
-	struct dm_table *table;
-
-	tio = alloc_old_rq_tio(md, gfp_mask);
-	if (!tio)
-		return NULL;
-
-	init_tio(tio, rq, md);
-
-	table = dm_get_live_table(md, &srcu_idx);
-	/*
-	 * Must clone a request if this .request_fn DM device
-	 * is stacked on .request_fn device(s).
-	 */
-	if (!dm_table_all_blk_mq_devices(table)) {
-		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
-			dm_put_live_table(md, srcu_idx);
-			free_old_rq_tio(tio);
-			return NULL;
-		}
-	}
-	dm_put_live_table(md, srcu_idx);
-
-	return tio;
-}
-
-/*
- * Called with the queue lock held.
- */
-static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_rq_target_io *tio;
-
-	if (unlikely(rq->special)) {
-		DMWARN("Already has something in rq->special.");
-		return BLKPREP_KILL;
-	}
-
-	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
-	if (!tio)
-		return BLKPREP_DEFER;
-
-	rq->special = tio;
-	rq->rq_flags |= RQF_DONTPREP;
-
-	return BLKPREP_OK;
-}
-
 /*
  * Returns:
  * DM_MAPIO_*       : the request has been processed as indicated
@@ -633,31 +470,18 @@ static int map_request(struct dm_rq_target_io *tio)
 	struct request *rq = tio->orig;
 	struct request *clone = NULL;
 
-	if (tio->clone) {
+	r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
-		clone = tio->clone;
-		r = ti->type->map_rq(ti, clone, &tio->info);
-		if (r == DM_MAPIO_DELAY_REQUEUE)
-			return DM_MAPIO_REQUEUE; /* .request_fn requeue is always immediate */
-	} else {
-		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
-		if (r < 0) {
-			/* The target wants to complete the I/O */
-			dm_kill_unmapped_request(rq, r);
-			return r;
-		}
-		if (r == DM_MAPIO_REMAPPED &&
-		    setup_clone(clone, rq, tio, GFP_ATOMIC)) {
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
-	}
-
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
 		/* The target has taken the I/O to submit by itself later */
 		break;
 	case DM_MAPIO_REMAPPED:
+		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+			/* -ENOMEM */
+			ti->type->release_clone_rq(clone);
+			return DM_MAPIO_REQUEUE;
+		}
+
 		/* The target has remapped the I/O so dispatch it */
 		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
 				     blk_rq_pos(rq));
@@ -716,6 +540,29 @@ static void dm_start_request(struct mapped_device *md, struct request *orig)
 	dm_get(md);
 }
 
+static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq)
+{
+	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+
+	/*
+	 * Must initialize md member of tio, otherwise it won't
+	 * be available in dm_mq_queue_rq.
+	 */
+	tio->md = md;
+
+	if (md->init_tio_pdu) {
+		/* target-specific per-io data is immediately after the tio */
+		tio->info.ptr = tio + 1;
+	}
+
+	return 0;
+}
+
+static int dm_rq_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+	return __dm_rq_init_rq(q->rq_alloc_data, rq);
+}
+
 static void map_tio_request(struct kthread_work *work)
 {
 	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
@@ -814,6 +661,7 @@ static void dm_old_request_fn(struct request_queue *q)
 		dm_start_request(md, rq);
 
 		tio = tio_from_request(rq);
+		init_tio(tio, rq, md);
 		/* Establish tio->ti before queuing work (map_tio_request) */
 		tio->ti = ti;
 		kthread_queue_work(&md->kworker, &tio->work);
@@ -824,10 +672,23 @@ static void dm_old_request_fn(struct request_queue *q)
 /*
  * Fully initialize a .request_fn request-based queue.
  */
-int dm_old_init_request_queue(struct mapped_device *md)
+int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t)
 {
+	struct dm_target *immutable_tgt;
+
 	/* Fully initialize the queue */
-	if (!blk_init_allocated_queue(md->queue, dm_old_request_fn, NULL))
+	md->queue->cmd_size = sizeof(struct dm_rq_target_io);
+	md->queue->rq_alloc_data = md;
+	md->queue->request_fn = dm_old_request_fn;
+	md->queue->init_rq_fn = dm_rq_init_rq;
+
+	immutable_tgt = dm_table_get_immutable_target(t);
+	if (immutable_tgt && immutable_tgt->per_io_data_size) {
+		/* any target-specific per-io data is immediately after the tio */
+		md->queue->cmd_size += immutable_tgt->per_io_data_size;
+		md->init_tio_pdu = true;
+	}
+	if (blk_init_allocated_queue(md->queue) < 0)
 		return -EINVAL;
 
 	/* disable dm_old_request_fn's merge heuristic by default */
@@ -835,7 +696,6 @@ int dm_old_init_request_queue(struct mapped_device *md)
 
 	dm_init_normal_md_queue(md);
 	blk_queue_softirq_done(md->queue, dm_softirq_done);
-	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
 
 	/* Initialize the request-based DM worker thread */
 	kthread_init_worker(&md->kworker);
@@ -856,21 +716,7 @@ static int dm_mq_init_request(void *data, struct request *rq,
 		       unsigned int hctx_idx, unsigned int request_idx,
 		       unsigned int numa_node)
 {
-	struct mapped_device *md = data;
+	return __dm_rq_init_rq(data, rq);
-	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-
-	/*
-	 * Must initialize md member of tio, otherwise it won't
-	 * be available in dm_mq_queue_rq.
-	 */
-	tio->md = md;
-
-	if (md->init_tio_pdu) {
-		/* target-specific per-io data is immediately after the tio */
-		tio->info.ptr = tio + 1;
-	}
-
-	return 0;
 }
 
 static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,

drivers/md/dm-rq.h

@@ -48,7 +48,7 @@ struct dm_rq_clone_bio_info {
 bool dm_use_blk_mq_default(void);
 bool dm_use_blk_mq(struct mapped_device *md);
 
-int dm_old_init_request_queue(struct mapped_device *md);
+int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t);
 int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t);
 void dm_mq_cleanup_mapped_device(struct mapped_device *md);
 

drivers/md/dm-table.c

@@ -1750,7 +1750,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 		char b[BDEVNAME_SIZE];
 
 		if (likely(q))
-			r |= bdi_congested(&q->backing_dev_info, bdi_bits);
+			r |= bdi_congested(q->backing_dev_info, bdi_bits);
 		else
 			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
 				     dm_device_name(t->md),

drivers/md/dm-target.c

@@ -131,12 +131,6 @@ static int io_err_map(struct dm_target *tt, struct bio *bio)
 	return -EIO;
 }
 
-static int io_err_map_rq(struct dm_target *ti, struct request *clone,
-			 union map_info *map_context)
-{
-	return -EIO;
-}
-
 static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
 				   union map_info *map_context,
 				   struct request **clone)
@@ -161,7 +155,6 @@ static struct target_type error_target = {
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
-	.map_rq = io_err_map_rq,
 	.clone_and_map_rq = io_err_clone_and_map_rq,
 	.release_clone_rq = io_err_release_clone_rq,
 	.direct_access = io_err_direct_access,

drivers/md/dm-thin.c

@@ -2711,7 +2711,7 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
 		return 1;
 
 	q = bdev_get_queue(pt->data_dev->bdev);
-	return bdi_congested(&q->backing_dev_info, bdi_bits);
+	return bdi_congested(q->backing_dev_info, bdi_bits);
 }
 
 static void requeue_bios(struct pool *pool)

drivers/md/dm.c

@@ -91,7 +91,6 @@ static int dm_numa_node = DM_NUMA_NODE;
  */
 struct dm_md_mempools {
 	mempool_t *io_pool;
-	mempool_t *rq_pool;
 	struct bio_set *bs;
 };
 
@@ -466,13 +465,16 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 
 	if (r > 0) {
 		/*
-		 * Target determined this ioctl is being issued against
+		 * Target determined this ioctl is being issued against a
-		 * a logical partition of the parent bdev; so extra
+		 * subset of the parent bdev; require extra privileges.
-		 * validation is needed.
 		 */
-		r = scsi_verify_blk_ioctl(NULL, cmd);
+		if (!capable(CAP_SYS_RAWIO)) {
-		if (r)
+			DMWARN_LIMIT(
+	"%s: sending ioctl %x to DM device without required privilege.",
+				current->comm, cmd);
+			r = -ENOIOCTLCMD;
 			goto out;
+		}
 	}
 
 	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
@@ -1314,7 +1316,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 			 * With request-based DM we only need to check the
 			 * top-level queue for congestion.
 			 */
-			r = md->queue->backing_dev_info.wb.state & bdi_bits;
+			r = md->queue->backing_dev_info->wb.state & bdi_bits;
 		} else {
 			map = dm_get_live_table_fast(md);
 			if (map)
@@ -1397,7 +1399,7 @@ void dm_init_md_queue(struct mapped_device *md)
 	 * - must do so here (in alloc_dev callchain) before queue is used
 	 */
 	md->queue->queuedata = md;
-	md->queue->backing_dev_info.congested_data = md;
+	md->queue->backing_dev_info->congested_data = md;
 }
 
 void dm_init_normal_md_queue(struct mapped_device *md)
@@ -1408,7 +1410,7 @@ void dm_init_normal_md_queue(struct mapped_device *md)
 	/*
 	 * Initialize aspects of queue that aren't relevant for blk-mq
 	 */
-	md->queue->backing_dev_info.congested_fn = dm_any_congested;
+	md->queue->backing_dev_info->congested_fn = dm_any_congested;
 	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
 }
 
@@ -1419,7 +1421,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->kworker_task)
 		kthread_stop(md->kworker_task);
 	mempool_destroy(md->io_pool);
-	mempool_destroy(md->rq_pool);
 	if (md->bs)
 		bioset_free(md->bs);
 
@@ -1595,12 +1596,10 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		goto out;
 	}
 
-	BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
+	BUG_ON(!p || md->io_pool || md->bs);
 
 	md->io_pool = p->io_pool;
 	p->io_pool = NULL;
-	md->rq_pool = p->rq_pool;
-	p->rq_pool = NULL;
 	md->bs = p->bs;
 	p->bs = NULL;
 
@@ -1777,7 +1776,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 
 	switch (type) {
 	case DM_TYPE_REQUEST_BASED:
-		r = dm_old_init_request_queue(md);
+		r = dm_old_init_request_queue(md, t);
 		if (r) {
 			DMERR("Cannot initialize queue for request-based mapped device");
 			return r;
@@ -2493,7 +2492,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 					    unsigned integrity, unsigned per_io_data_size)
 {
 	struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
-	struct kmem_cache *cachep = NULL;
 	unsigned int pool_size = 0;
 	unsigned int front_pad;
 
@@ -2503,20 +2501,16 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 	switch (type) {
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-		cachep = _io_cache;
 		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
+	
+		pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
+		if (!pools->io_pool)
+			goto out;
 		break;
 	case DM_TYPE_REQUEST_BASED:
-		cachep = _rq_tio_cache;
-		pool_size = dm_get_reserved_rq_based_ios();
-		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
-		if (!pools->rq_pool)
-			goto out;
-		/* fall through to setup remaining rq-based pools */
 	case DM_TYPE_MQ_REQUEST_BASED:
-		if (!pool_size)
+		pool_size = dm_get_reserved_rq_based_ios();
-			pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
 		/* per_io_data_size is used for blk-mq pdu at queue allocation */
 		break;
@@ -2524,12 +2518,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		BUG();
 	}
 
-	if (cachep) {
-		pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
-		if (!pools->io_pool)
-			goto out;
-	}
-
 	pools->bs = bioset_create_nobvec(pool_size, front_pad);
 	if (!pools->bs)
 		goto out;
@@ -2551,7 +2539,6 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 		return;
 
 	mempool_destroy(pools->io_pool);
-	mempool_destroy(pools->rq_pool);
 
 	if (pools->bs)
 		bioset_free(pools->bs);

drivers/md/dm.h

@@ -95,8 +95,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 /*
  * To check whether the target type is request-based or not (bio-based).
  */
-#define dm_target_request_based(t) (((t)->type->map_rq != NULL) || \
+#define dm_target_request_based(t) ((t)->type->clone_and_map_rq != NULL)
-				    ((t)->type->clone_and_map_rq != NULL))
 
 /*
  * To check whether the target type is a hybrid (capable of being

drivers/md/linear.c

@@ -62,7 +62,7 @@ static int linear_congested(struct mddev *mddev, int bits)
 
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 
 	return ret;

drivers/md/md.c

@@ -5346,8 +5346,8 @@ int md_run(struct mddev *mddev)
 			queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
-		mddev->queue->backing_dev_info.congested_data = mddev;
+		mddev->queue->backing_dev_info->congested_data = mddev;
-		mddev->queue->backing_dev_info.congested_fn = md_congested;
+		mddev->queue->backing_dev_info->congested_fn = md_congested;
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -5704,7 +5704,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->backing_dev_info.congested_fn = NULL;
+		mddev->queue->backing_dev_info->congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
 		sysfs_notify_dirent_safe(mddev->sysfs_state);

drivers/md/multipath.c

@@ -169,7 +169,7 @@ static int multipath_congested(struct mddev *mddev, int bits)
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= bdi_congested(q->backing_dev_info, bits);
 			/* Just like multipath_map, we just check the
 			 * first available device
 			 */

drivers/md/raid0.c

@@ -41,7 +41,7 @@ static int raid0_congested(struct mddev *mddev, int bits)
 	for (i = 0; i < raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
 
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 	return ret;
 }
@@ -420,8 +420,8 @@ static int raid0_run(struct mddev *mddev)
 		 */
 		int stripe = mddev->raid_disks *
 			(mddev->chunk_sectors << 9) / PAGE_SIZE;
-		if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
+		if (mddev->queue->backing_dev_info->ra_pages < 2* stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
+			mddev->queue->backing_dev_info->ra_pages = 2* stripe;
 	}
 
 	dump_zones(mddev);

drivers/md/raid1.c

@@ -744,9 +744,9 @@ static int raid1_congested(struct mddev *mddev, int bits)
 			 * non-congested targets, it can be removed
 			 */
 			if ((bits & (1 << WB_async_congested)) || 1)
-				ret |= bdi_congested(&q->backing_dev_info, bits);
+				ret |= bdi_congested(q->backing_dev_info, bits);
 			else
-				ret &= bdi_congested(&q->backing_dev_info, bits);
+				ret &= bdi_congested(q->backing_dev_info, bits);
 		}
 	}
 	rcu_read_unlock();
@@ -1170,10 +1170,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	int i, disks;
 	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
-	const int op = bio_op(bio);
-	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
-	const unsigned long do_flush_fua = (bio->bi_opf &
-						(REQ_PREFLUSH | REQ_FUA));
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
 	struct raid1_plug_cb *plug = NULL;
@@ -1389,7 +1385,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				   conf->mirrors[i].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		bio_set_op_attrs(mbio, op, do_flush_fua | do_sync);
+		mbio->bi_opf = bio_op(bio) |
+			(bio->bi_opf & (REQ_SYNC | REQ_PREFLUSH | REQ_FUA));
 		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
 		    !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
 		    conf->raid_disks - mddev->degraded > 1)

drivers/md/raid10.c

@@ -860,7 +860,7 @@ static int raid10_congested(struct mddev *mddev, int bits)
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= bdi_congested(q->backing_dev_info, bits);
 		}
 	}
 	rcu_read_unlock();
@@ -3841,8 +3841,8 @@ static int raid10_run(struct mddev *mddev)
 		 * maybe...
 		 */
 		stripe /= conf->geo.near_copies;
-		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 	}
 
 	if (md_integrity_register(mddev))
@@ -4643,8 +4643,8 @@ static void end_reshape(struct r10conf *conf)
 		int stripe = conf->geo.raid_disks *
 			((conf->mddev->chunk_sectors << 9) / PAGE_SIZE);
 		stripe /= conf->geo.near_copies;
-		if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+		if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+			conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 	}
 	conf->fullsync = 0;
 }

drivers/md/raid5.c

@@ -6331,10 +6331,10 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 		mddev_suspend(mddev);
 		conf->skip_copy = new;
 		if (new)
-			mddev->queue->backing_dev_info.capabilities |=
+			mddev->queue->backing_dev_info->capabilities |=
 				BDI_CAP_STABLE_WRITES;
 		else
-			mddev->queue->backing_dev_info.capabilities &=
+			mddev->queue->backing_dev_info->capabilities &=
 				~BDI_CAP_STABLE_WRITES;
 		mddev_resume(mddev);
 	}
@@ -7153,8 +7153,8 @@ static int raid5_run(struct mddev *mddev)
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);
@@ -7763,8 +7763,8 @@ static void end_reshape(struct r5conf *conf)
 			int data_disks = conf->raid_disks - conf->max_degraded;
 			int stripe = data_disks * ((conf->chunk_sectors << 9)
 						   / PAGE_SIZE);
-			if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+			if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-				conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+				conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 		}
 	}
 }

drivers/memstick/core/ms_block.c

@@ -2000,16 +2000,6 @@ static int msb_bd_getgeo(struct block_device *bdev,
 	return 0;
 }
 
-static int msb_prepare_req(struct request_queue *q, struct request *req)
-{
-	if (req->cmd_type != REQ_TYPE_FS) {
-		blk_dump_rq_flags(req, "MS unsupported request");
-		return BLKPREP_KILL;
-	}
-	req->rq_flags |= RQF_DONTPREP;
-	return BLKPREP_OK;
-}
-
 static void msb_submit_req(struct request_queue *q)
 {
 	struct memstick_dev *card = q->queuedata;
@@ -2132,7 +2122,6 @@ static int msb_init_disk(struct memstick_dev *card)
 	}
 
 	msb->queue->queuedata = card;
-	blk_queue_prep_rq(msb->queue, msb_prepare_req);
 
 	blk_queue_bounce_limit(msb->queue, limit);
 	blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);

drivers/memstick/core/mspro_block.c

@@ -827,18 +827,6 @@ static void mspro_block_start(struct memstick_dev *card)
 	spin_unlock_irqrestore(&msb->q_lock, flags);
 }
 
-static int mspro_block_prepare_req(struct request_queue *q, struct request *req)
-{
-	if (req->cmd_type != REQ_TYPE_FS) {
-		blk_dump_rq_flags(req, "MSPro unsupported request");
-		return BLKPREP_KILL;
-	}
-
-	req->rq_flags |= RQF_DONTPREP;
-
-	return BLKPREP_OK;
-}
-
 static void mspro_block_submit_req(struct request_queue *q)
 {
 	struct memstick_dev *card = q->queuedata;
@@ -1228,7 +1216,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	}
 
 	msb->queue->queuedata = card;
-	blk_queue_prep_rq(msb->queue, mspro_block_prepare_req);
 
 	blk_queue_bounce_limit(msb->queue, limit);
 	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);

drivers/message/fusion/mptsas.c

@@ -2320,10 +2320,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		SmpPassthroughReply_t *smprep;
 
 		smprep = (SmpPassthroughReply_t *)ioc->sas_mgmt.reply;
-		memcpy(req->sense, smprep, sizeof(*smprep));
+		memcpy(scsi_req(req)->sense, smprep, sizeof(*smprep));
-		req->sense_len = sizeof(*smprep);
+		scsi_req(req)->sense_len = sizeof(*smprep);
-		req->resid_len = 0;
+		scsi_req(req)->resid_len = 0;
-		rsp->resid_len -= smprep->ResponseDataLength;
+		scsi_req(rsp)->resid_len -= smprep->ResponseDataLength;
 	} else {
 		printk(MYIOC_s_ERR_FMT
 		    "%s: smp passthru reply failed to be returned\n",

drivers/mmc/core/queue.c

@@ -30,15 +30,6 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 {
 	struct mmc_queue *mq = q->queuedata;
 
-	/*
-	 * We only like normal block requests and discards.
-	 */
-	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
-	    req_op(req) != REQ_OP_SECURE_ERASE) {
-		blk_dump_rq_flags(req, "MMC bad request");
-		return BLKPREP_KILL;
-	}
-
 	if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq)))
 		return BLKPREP_KILL;
 

drivers/mtd/mtd_blkdevs.c

@@ -84,9 +84,6 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
 	buf = bio_data(req->bio);
 
-	if (req->cmd_type != REQ_TYPE_FS)
-		return -EIO;
-
 	if (req_op(req) == REQ_OP_FLUSH)
 		return tr->flush(dev);
 
@@ -94,16 +91,16 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	    get_capacity(req->rq_disk))
 		return -EIO;
 
-	if (req_op(req) == REQ_OP_DISCARD)
+	switch (req_op(req)) {
+	case REQ_OP_DISCARD:
 		return tr->discard(dev, block, nsect);
-
+	case REQ_OP_READ:
-	if (rq_data_dir(req) == READ) {
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
 			if (tr->readsect(dev, block, buf))
 				return -EIO;
 		rq_flush_dcache_pages(req);
 		return 0;
-	} else {
+	case REQ_OP_WRITE:
 		if (!tr->writesect)
 			return -EIO;
 
@@ -112,6 +109,8 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 			if (tr->writesect(dev, block, buf))
 				return -EIO;
 		return 0;
+	default:
+		return -EIO;
 	}
 }