Merge branch 'for-4.8/core' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:

   - the big change is the cleanup from Mike Christie, cleaning up our
     uses of command types and modified flags.  This is what will throw
     some merge conflicts

   - regression fix for the above for btrfs, from Vincent

   - following up to the above, better packing of struct request from
     Christoph

   - a 2038 fix for blktrace from Arnd

   - a few trivial/spelling fixes from Bart Van Assche

   - a front merge check fix from Damien, which could cause issues on
     SMR drives

   - Atari partition fix from Gabriel

   - convert cfq to highres timers, since jiffies isn't granular enough
     for some devices these days.  From Jan and Jeff

   - CFQ priority boost fix idle classes, from me

   - cleanup series from Ming, improving our bio/bvec iteration

   - a direct issue fix for blk-mq from Omar

   - fix for plug merging not involving the IO scheduler, like we do for
     other types of merges.  From Tahsin

   - expose DAX type internally and through sysfs.  From Toshi and Yigal

* 'for-4.8/core' of git://git.kernel.dk/linux-block: (76 commits)
  block: Fix front merge check
  block: do not merge requests without consulting with io scheduler
  block: Fix spelling in a source code comment
  block: expose QUEUE_FLAG_DAX in sysfs
  block: add QUEUE_FLAG_DAX for devices to advertise their DAX support
  Btrfs: fix comparison in __btrfs_map_block()
  block: atari: Return early for unsupported sector size
  Doc: block: Fix a typo in queue-sysfs.txt
  cfq-iosched: Charge at least 1 jiffie instead of 1 ns
  cfq-iosched: Fix regression in bonnie++ rewrite performance
  cfq-iosched: Convert slice_resid from u64 to s64
  block: Convert fifo_time from ulong to u64
  blktrace: avoid using timespec
  block/blk-cgroup.c: Declare local symbols static
  block/bio-integrity.c: Add #include "blk.h"
  block/partition-generic.c: Remove a set-but-not-used variable
  block: bio: kill BIO_MAX_SIZE
  cfq-iosched: temporarily boost queue priority for idle classes
  block: drbd: avoid to use BIO_MAX_SIZE
  block: bio: remove BIO_MAX_SECTORS
  ...

16 files changed, 434 insertions, 312 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 711e4d8de6fa..15d37b1cd500 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -26,6 +26,7 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include <linux/slab.h>
+#include "blk.h"
 
 #define BIP_INLINE_VECS	4
 
diff --git a/block/bio.c b/block/bio.c
index 0e4aa42bc30d..848cd351513b 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -656,16 +656,15 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
 	if (!bio)
 		return NULL;
-
 	bio->bi_bdev		= bio_src->bi_bdev;
 	bio->bi_rw		= bio_src->bi_rw;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		goto integrity_clone;
 
-	if (bio->bi_rw & REQ_WRITE_SAME) {
+	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
 		goto integrity_clone;
 	}
@@ -854,21 +853,20 @@ static void submit_bio_wait_endio(struct bio *bio)
 
 /**
  * submit_bio_wait - submit a bio, and wait until it completes
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
  * @bio: The &struct bio which describes the I/O
  *
  * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
  * bio_endio() on failure.
  */
-int submit_bio_wait(int rw, struct bio *bio)
+int submit_bio_wait(struct bio *bio)
 {
 	struct submit_bio_ret ret;
 
-	rw |= REQ_SYNC;
 	init_completion(&ret.event);
 	bio->bi_private = &ret;
 	bio->bi_end_io = submit_bio_wait_endio;
-	submit_bio(rw, bio);
+	bio->bi_rw |= REQ_SYNC;
+	submit_bio(bio);
 	wait_for_completion_io(&ret.event);
 
 	return ret.error;
@@ -1167,7 +1165,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 		goto out_bmd;
 
 	if (iter->type & WRITE)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	ret = 0;
 
@@ -1337,7 +1335,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	 * set data direction, and check if mapped pages need bouncing
 	 */
 	if (iter->type & WRITE)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
@@ -1530,7 +1528,7 @@ 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->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	}
 
 	return bio;
@@ -1785,7 +1783,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 	 * Discards need a mutable bio_vec to accommodate the payload
 	 * required by the DSM TRIM and UNMAP commands.
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		split = bio_clone_bioset(bio, gfp, bs);
 	else
 		split = bio_clone_fast(bio, gfp, bs);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 66e6f1aae02e..dd38e5ced4a3 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -905,7 +905,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 	return 0;
 }
 
-struct cftype blkcg_files[] = {
+static struct cftype blkcg_files[] = {
 	{
 		.name = "stat",
 		.flags = CFTYPE_NOT_ON_ROOT,
@@ -914,7 +914,7 @@ struct cftype blkcg_files[] = {
 	{ }	/* terminate */
 };
 
-struct cftype blkcg_legacy_files[] = {
+static struct cftype blkcg_legacy_files[] = {
 	{
 		.name = "reset_stats",
 		.write_u64 = blkcg_reset_stats,
diff --git a/block/blk-core.c b/block/blk-core.c
index 2475b1c72773..3cfd67d006fb 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -959,10 +959,10 @@ static void __freed_request(struct request_list *rl, int sync)
  * A request has just been released.  Account for it, update the full and
  * congestion status, wake up any waiters.   Called under q->queue_lock.
  */
-static void freed_request(struct request_list *rl, unsigned int flags)
+static void freed_request(struct request_list *rl, int op, unsigned int flags)
 {
 	struct request_queue *q = rl->q;
-	int sync = rw_is_sync(flags);
+	int sync = rw_is_sync(op, flags);
 
 	q->nr_rqs[sync]--;
 	rl->count[sync]--;
@@ -1029,7 +1029,7 @@ static bool blk_rq_should_init_elevator(struct bio *bio)
 	 * Flush requests do not use the elevator so skip initialization.
 	 * This allows a request to share the flush and elevator data.
 	 */
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA))
 		return false;
 
 	return true;
@@ -1054,7 +1054,8 @@ static struct io_context *rq_ioc(struct bio *bio)
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
- * @rw_flags: RW and SYNC flags
+ * @op: REQ_OP_READ/REQ_OP_WRITE
+ * @op_flags: rq_flag_bits
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1065,21 +1066,22 @@ static struct io_context *rq_ioc(struct bio *bio)
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *__get_request(struct request_list *rl, int rw_flags,
-				     struct bio *bio, gfp_t gfp_mask)
+static struct request *__get_request(struct request_list *rl, int op,
+				     int op_flags, struct bio *bio,
+				     gfp_t gfp_mask)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
 	struct elevator_type *et = q->elevator->type;
 	struct io_context *ioc = rq_ioc(bio);
 	struct io_cq *icq = NULL;
-	const bool is_sync = rw_is_sync(rw_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	int may_queue;
 
 	if (unlikely(blk_queue_dying(q)))
 		return ERR_PTR(-ENODEV);
 
-	may_queue = elv_may_queue(q, rw_flags);
+	may_queue = elv_may_queue(q, op, op_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
@@ -1123,7 +1125,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 
 	/*
 	 * Decide whether the new request will be managed by elevator.  If
-	 * so, mark @rw_flags and increment elvpriv.  Non-zero elvpriv will
+	 * so, mark @op_flags and increment elvpriv.  Non-zero elvpriv will
 	 * prevent the current elevator from being destroyed until the new
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
@@ -1132,14 +1134,14 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	 * it will be created after releasing queue_lock.
 	 */
 	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
-		rw_flags |= REQ_ELVPRIV;
+		op_flags |= REQ_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
 			icq = ioc_lookup_icq(ioc, q);
 	}
 
 	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		op_flags |= REQ_IO_STAT;
 	spin_unlock_irq(q->queue_lock);
 
 	/* allocate and init request */
@@ -1149,10 +1151,10 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	rq->cmd_flags = rw_flags | REQ_ALLOCED;
+	req_set_op_attrs(rq, op, op_flags | REQ_ALLOCED);
 
 	/* init elvpriv */
-	if (rw_flags & REQ_ELVPRIV) {
+	if (op_flags & REQ_ELVPRIV) {
 		if (unlikely(et->icq_cache && !icq)) {
 			if (ioc)
 				icq = ioc_create_icq(ioc, q, gfp_mask);
@@ -1178,7 +1180,7 @@ out:
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	trace_block_getrq(q, bio, rw_flags & 1);
+	trace_block_getrq(q, bio, op);
 	return rq;
 
 fail_elvpriv:
@@ -1208,7 +1210,7 @@ fail_alloc:
 	 * queue, but this is pretty rare.
 	 */
 	spin_lock_irq(q->queue_lock);
-	freed_request(rl, rw_flags);
+	freed_request(rl, op, op_flags);
 
 	/*
 	 * in the very unlikely event that allocation failed and no
@@ -1226,7 +1228,8 @@ rq_starved:
 /**
  * get_request - get a free request
  * @q: request_queue to allocate request from
- * @rw_flags: RW and SYNC flags
+ * @op: REQ_OP_READ/REQ_OP_WRITE
+ * @op_flags: rq_flag_bits
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
@@ -1237,17 +1240,18 @@ rq_starved:
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *get_request(struct request_queue *q, int rw_flags,
-				   struct bio *bio, gfp_t gfp_mask)
+static struct request *get_request(struct request_queue *q, int op,
+				   int op_flags, struct bio *bio,
+				   gfp_t gfp_mask)
 {
-	const bool is_sync = rw_is_sync(rw_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	DEFINE_WAIT(wait);
 	struct request_list *rl;
 	struct request *rq;
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, rw_flags, bio, gfp_mask);
+	rq = __get_request(rl, op, op_flags, bio, gfp_mask);
 	if (!IS_ERR(rq))
 		return rq;
 
@@ -1260,7 +1264,7 @@ retry:
 	prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
 				  TASK_UNINTERRUPTIBLE);
 
-	trace_block_sleeprq(q, bio, rw_flags & 1);
+	trace_block_sleeprq(q, bio, op);
 
 	spin_unlock_irq(q->queue_lock);
 	io_schedule();
@@ -1289,7 +1293,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, NULL, gfp_mask);
+	rq = get_request(q, rw, 0, NULL, gfp_mask);
 	if (IS_ERR(rq))
 		spin_unlock_irq(q->queue_lock);
 	/* q->queue_lock is unlocked at this point */
@@ -1491,13 +1495,14 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 */
 	if (req->cmd_flags & REQ_ALLOCED) {
 		unsigned int flags = req->cmd_flags;
+		int op = req_op(req);
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
-		freed_request(rl, flags);
+		freed_request(rl, op, flags);
 		blk_put_rl(rl);
 	}
 }
@@ -1712,7 +1717,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
 	struct blk_plug *plug;
-	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
+	int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
 	unsigned int request_count = 0;
 
@@ -1731,7 +1736,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
+	if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1772,15 +1777,19 @@ get_rq:
 	 * but we need to set it earlier to expose the sync flag to the
 	 * rq allocator and io schedulers.
 	 */
-	rw_flags = bio_data_dir(bio);
 	if (sync)
 		rw_flags |= REQ_SYNC;
 
 	/*
+	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
+	 */
+	rw_flags |= (bio->bi_rw & (REQ_META | REQ_PRIO));
+
+	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request(q, rw_flags, bio, GFP_NOIO);
+	req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
 		bio->bi_error = PTR_ERR(req);
 		bio_endio(bio);
@@ -1849,7 +1858,7 @@ static void handle_bad_sector(struct bio *bio)
 	char b[BDEVNAME_SIZE];
 
 	printk(KERN_INFO "attempt to access beyond end of device\n");
-	printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
+	printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n",
 			bdevname(bio->bi_bdev, b),
 			bio->bi_rw,
 			(unsigned long long)bio_end_sector(bio),
@@ -1964,23 +1973,23 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) &&
+	if ((bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
-		bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+		bio->bi_rw &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
 			err = 0;
 			goto end_io;
 		}
 	}
 
-	if ((bio->bi_rw & REQ_DISCARD) &&
+	if ((bio_op(bio) == REQ_OP_DISCARD) &&
 	    (!blk_queue_discard(q) ||
 	     ((bio->bi_rw & REQ_SECURE) && !blk_queue_secdiscard(q)))) {
 		err = -EOPNOTSUPP;
 		goto end_io;
 	}
 
-	if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
+	if (bio_op(bio) == REQ_OP_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
 		err = -EOPNOTSUPP;
 		goto end_io;
 	}
@@ -2094,7 +2103,6 @@ EXPORT_SYMBOL(generic_make_request);
 
 /**
  * submit_bio - submit a bio to the block device layer for I/O
- * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
  * @bio: The &struct bio which describes the I/O
  *
  * submit_bio() is very similar in purpose to generic_make_request(), and
@@ -2102,10 +2110,8 @@ EXPORT_SYMBOL(generic_make_request);
  * interfaces; @bio must be presetup and ready for I/O.
  *
  */
-blk_qc_t submit_bio(int rw, struct bio *bio)
+blk_qc_t submit_bio(struct bio *bio)
 {
-	bio->bi_rw |= rw;
-
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.
@@ -2113,12 +2119,12 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 	if (bio_has_data(bio)) {
 		unsigned int count;
 
-		if (unlikely(rw & REQ_WRITE_SAME))
+		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
 			count = bdev_logical_block_size(bio->bi_bdev) >> 9;
 		else
 			count = bio_sectors(bio);
 
-		if (rw & WRITE) {
+		if (op_is_write(bio_op(bio))) {
 			count_vm_events(PGPGOUT, count);
 		} else {
 			task_io_account_read(bio->bi_iter.bi_size);
@@ -2129,7 +2135,7 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 			char b[BDEVNAME_SIZE];
 			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
-				(rw & WRITE) ? "WRITE" : "READ",
+				op_is_write(bio_op(bio)) ? "WRITE" : "READ",
 				(unsigned long long)bio->bi_iter.bi_sector,
 				bdevname(bio->bi_bdev, b),
 				count);
@@ -2160,7 +2166,7 @@ EXPORT_SYMBOL(submit_bio);
 static int blk_cloned_rq_check_limits(struct request_queue *q,
 				      struct request *rq)
 {
-	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
+	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -2216,7 +2222,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+	if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
@@ -2979,8 +2985,7 @@ EXPORT_SYMBOL_GPL(__blk_end_request_err);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
-	rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
+	req_set_op(rq, bio_op(bio));
 
 	if (bio_has_data(bio))
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
@@ -3065,7 +3070,8 @@ 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_CLONE_MASK) | REQ_NOMERGE;
+	req_set_op_attrs(dst, req_op(src),
+			 (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE);
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
@@ -3310,7 +3316,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA))
+		if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3fec8a29d0fa..7ea04325d02f 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -62,7 +62,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	/*
 	 * don't check dying flag for MQ because the request won't
-	 * be resued after dying flag is set
+	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
 		blk_mq_insert_request(rq, at_head, true, false);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index b1c91d229e5e..d308def812db 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -10,8 +10,8 @@
  * optional steps - PREFLUSH, DATA and POSTFLUSH - according to the request
  * properties and hardware capability.
  *
- * If a request doesn't have data, only REQ_FLUSH makes sense, which
- * indicates a simple flush request.  If there is data, REQ_FLUSH indicates
+ * If a request doesn't have data, only REQ_PREFLUSH makes sense, which
+ * indicates a simple flush request.  If there is data, REQ_PREFLUSH indicates
  * that the device cache should be flushed before the data is executed, and
  * REQ_FUA means that the data must be on non-volatile media on request
  * completion.
@@ -20,16 +20,16 @@
  * difference.  The requests are either completed immediately if there's no
  * data or executed as normal requests otherwise.
  *
- * If the device has writeback cache and supports FUA, REQ_FLUSH is
+ * If the device has writeback cache and supports FUA, REQ_PREFLUSH is
  * translated to PREFLUSH but REQ_FUA is passed down directly with DATA.
  *
- * If the device has writeback cache and doesn't support FUA, REQ_FLUSH is
- * translated to PREFLUSH and REQ_FUA to POSTFLUSH.
+ * If the device has writeback cache and doesn't support FUA, REQ_PREFLUSH
+ * is translated to PREFLUSH and REQ_FUA to POSTFLUSH.
  *
  * The actual execution of flush is double buffered.  Whenever a request
  * needs to execute PRE or POSTFLUSH, it queues at
  * fq->flush_queue[fq->flush_pending_idx].  Once certain criteria are met, a
- * flush is issued and the pending_idx is toggled.  When the flush
+ * REQ_OP_FLUSH is issued and the pending_idx is toggled.  When the flush
  * completes, all the requests which were pending are proceeded to the next
  * step.  This allows arbitrary merging of different types of FLUSH/FUA
  * requests.
@@ -103,7 +103,7 @@ static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 		policy |= REQ_FSEQ_DATA;
 
 	if (fflags & (1UL << QUEUE_FLAG_WC)) {
-		if (rq->cmd_flags & REQ_FLUSH)
+		if (rq->cmd_flags & REQ_PREFLUSH)
 			policy |= REQ_FSEQ_PREFLUSH;
 		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
 		    (rq->cmd_flags & REQ_FUA))
@@ -330,7 +330,7 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
-	flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH | REQ_FLUSH_SEQ);
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
 
@@ -391,9 +391,9 @@ void blk_insert_flush(struct request *rq)
 
 	/*
 	 * @policy now records what operations need to be done.  Adjust
-	 * REQ_FLUSH and FUA for the driver.
+	 * REQ_PREFLUSH and FUA for the driver.
 	 */
-	rq->cmd_flags &= ~REQ_FLUSH;
+	rq->cmd_flags &= ~REQ_PREFLUSH;
 	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
 		rq->cmd_flags &= ~REQ_FUA;
 
@@ -485,8 +485,9 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 
 	bio = bio_alloc(gfp_mask, 0);
 	bio->bi_bdev = bdev;
+	bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
 
-	ret = submit_bio_wait(WRITE_FLUSH, bio);
+	ret = submit_bio_wait(bio);
 
 	/*
 	 * The driver must store the error location in ->bi_sector, if
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 9e29dc351695..9031d2af0b47 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -9,21 +9,22 @@
 
 #include "blk.h"
 
-static struct bio *next_bio(struct bio *bio, int rw, unsigned int nr_pages,
+static struct bio *next_bio(struct bio *bio, unsigned int nr_pages,
 		gfp_t gfp)
 {
 	struct bio *new = bio_alloc(gfp, nr_pages);
 
 	if (bio) {
 		bio_chain(bio, new);
-		submit_bio(rw, bio);
+		submit_bio(bio);
 	}
 
 	return new;
 }
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop)
+		sector_t nr_sects, gfp_t gfp_mask, int op_flags,
+		struct bio **biop)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
@@ -34,7 +35,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -ENXIO;
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
-	if ((type & REQ_SECURE) && !blk_queue_secdiscard(q))
+	if ((op_flags & REQ_SECURE) && !blk_queue_secdiscard(q))
 		return -EOPNOTSUPP;
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
@@ -62,9 +63,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
-		bio = next_bio(bio, type, 1, gfp_mask);
+		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
+		bio_set_op_attrs(bio, REQ_OP_DISCARD, op_flags);
 
 		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
@@ -98,19 +100,19 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
 int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
 {
-	int type = REQ_WRITE | REQ_DISCARD;
+	int op_flags = 0;
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret;
 
 	if (flags & BLKDEV_DISCARD_SECURE)
-		type |= REQ_SECURE;
+		op_flags |= REQ_SECURE;
 
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, type,
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, op_flags,
 			&bio);
 	if (!ret && bio) {
-		ret = submit_bio_wait(type, bio);
+		ret = submit_bio_wait(bio);
 		if (ret == -EOPNOTSUPP)
 			ret = 0;
 		bio_put(bio);
@@ -148,13 +150,14 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	max_write_same_sectors = UINT_MAX >> 9;
 
 	while (nr_sects) {
-		bio = next_bio(bio, REQ_WRITE | REQ_WRITE_SAME, 1, gfp_mask);
+		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
 		bio->bi_vcnt = 1;
 		bio->bi_io_vec->bv_page = page;
 		bio->bi_io_vec->bv_offset = 0;
 		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
+		bio_set_op_attrs(bio, REQ_OP_WRITE_SAME, 0);
 
 		if (nr_sects > max_write_same_sectors) {
 			bio->bi_iter.bi_size = max_write_same_sectors << 9;
@@ -167,7 +170,7 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	}
 
 	if (bio) {
-		ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 	}
 	return ret != -EOPNOTSUPP ? ret : 0;
@@ -193,11 +196,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	unsigned int sz;
 
 	while (nr_sects != 0) {
-		bio = next_bio(bio, WRITE,
-				min(nr_sects, (sector_t)BIO_MAX_PAGES),
+		bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
 				gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev   = bdev;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 		while (nr_sects != 0) {
 			sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
@@ -210,7 +213,7 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	}
 
 	if (bio) {
-		ret = submit_bio_wait(WRITE, bio);
+		ret = submit_bio_wait(bio);
 		bio_put(bio);
 		return ret;
 	}
diff --git a/block/blk-map.c b/block/blk-map.c
index b9f88b7751fb..61733a660c3a 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -224,7 +224,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		return PTR_ERR(bio);
 
 	if (!reading)
-		bio->bi_rw |= REQ_WRITE;
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 261353166dcf..5e4d93edeaf7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -172,9 +172,9 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	struct bio *split, *res;
 	unsigned nsegs;
 
-	if ((*bio)->bi_rw & REQ_DISCARD)
+	if (bio_op(*bio) == REQ_OP_DISCARD)
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
-	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+	else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
 	else
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
@@ -213,10 +213,10 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	 * This should probably be returning 0, but blk_add_request_payload()
 	 * (Christoph!!!!)
 	 */
-	if (bio->bi_rw & REQ_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD)
 		return 1;
 
-	if (bio->bi_rw & REQ_WRITE_SAME)
+	if (bio_op(bio) == REQ_OP_WRITE_SAME)
 		return 1;
 
 	fbio = bio;
@@ -385,7 +385,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	if (bio->bi_rw & REQ_DISCARD) {
+	if (bio_op(bio) == REQ_OP_DISCARD) {
 		/*
 		 * This is a hack - drivers should be neither modifying the
 		 * biovec, nor relying on bi_vcnt - but because of
@@ -400,7 +400,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 		return 0;
 	}
 
-	if (bio->bi_rw & REQ_WRITE_SAME) {
+	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
 single_segment:
 		*sg = sglist;
 		bvec = bio_iovec(bio);
@@ -439,7 +439,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	}
 
 	if (q->dma_drain_size && q->dma_drain_needed(rq)) {
-		if (rq->cmd_flags & REQ_WRITE)
+		if (op_is_write(req_op(rq)))
 			memset(q->dma_drain_buffer, 0, q->dma_drain_size);
 
 		sg_unmark_end(sg);
@@ -500,7 +500,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 	    integrity_req_gap_back_merge(req, bio))
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
-	    blk_rq_get_max_sectors(req)) {
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -524,7 +524,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	    integrity_req_gap_front_merge(req, bio))
 		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
-	    blk_rq_get_max_sectors(req)) {
+	    blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -570,7 +570,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	 * Will it become too large?
 	 */
 	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
-	    blk_rq_get_max_sectors(req))
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -649,7 +649,8 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return 0;
 
-	if (!blk_check_merge_flags(req->cmd_flags, next->cmd_flags))
+	if (!blk_check_merge_flags(req->cmd_flags, req_op(req), next->cmd_flags,
+				   req_op(next)))
 		return 0;
 
 	/*
@@ -663,7 +664,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	    || req_no_special_merge(next))
 		return 0;
 
-	if (req->cmd_flags & REQ_WRITE_SAME &&
+	if (req_op(req) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(req->bio, next->bio))
 		return 0;
 
@@ -743,6 +744,12 @@ int 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)
 {
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+			return 0;
+
 	return attempt_merge(q, rq, next);
 }
 
@@ -751,7 +758,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
-	if (!blk_check_merge_flags(rq->cmd_flags, bio->bi_rw))
+	if (!blk_check_merge_flags(rq->cmd_flags, req_op(rq), bio->bi_rw,
+				   bio_op(bio)))
 		return false;
 
 	/* different data direction or already started, don't merge */
@@ -767,7 +775,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		return false;
 
 	/* must be using the same buffer */
-	if (rq->cmd_flags & REQ_WRITE_SAME &&
+	if (req_op(rq) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
diff --git a/block/blk-mq.c b/block/