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 711e4d8d..15d37b1 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 0e4aa42..848cd35 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 66e6f1a..dd38e5c 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 2475b1c7..3cfd67d 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 3fec8a2..7ea0432 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 b1c91d2..d308def 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 9e29dc3..9031d2a 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 b9f88b7..61733a6 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 2613531..5e4d93e 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/blk-mq.c
index f9b9049..2a1920c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -159,16 +159,17 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, unsigned int rw_flags)
+			       struct request *rq, int op,
+			       unsigned int op_flags)
 {
 	if (blk_queue_io_stat(q))
-		rw_flags |= REQ_IO_STAT;
+		op_flags |= REQ_IO_STAT;
 
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = q;
 	rq->mq_ctx = ctx;
-	rq->cmd_flags |= rw_flags;
+	req_set_op_attrs(rq, op, op_flags);
 	/* do not touch atomic flags, it needs atomic ops against the timer */
 	rq->cpu = -1;
 	INIT_HLIST_NODE(&rq->hash);
@@ -203,11 +204,11 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
+	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;
 }
 
 static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
+__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -222,7 +223,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int rw)
 		}
 
 		rq->tag = tag;
-		blk_mq_rq_ctx_init(data->q, data->ctx, rq, rw);
+		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags);
 		return rq;
 	}
 
@@ -246,7 +247,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
 
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
+	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
 	if (!rq && !(flags & BLK_MQ_REQ_NOWAIT)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
@@ -254,7 +255,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-		rq =  __blk_mq_alloc_request(&alloc_data, rw);
+		rq =  __blk_mq_alloc_request(&alloc_data, rw, 0);
 		ctx = alloc_data.ctx;
 	}
 	blk_mq_put_ctx(ctx);
@@ -784,7 +785,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
-			continue;
+			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
 			list_add(&rq->queuelist, &rq_list);
 			__blk_mq_requeue_request(rq);
@@ -1169,28 +1170,29 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct request *rq;
-	int rw = bio_data_dir(bio);
+	int op = bio_data_dir(bio);
+	int op_flags = 0;
 	struct blk_mq_alloc_data alloc_data;
 
 	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio->bi_rw))
-		rw |= REQ_SYNC;
+	if (rw_is_sync(bio_op(bio), bio->bi_rw))
+		op_flags |= REQ_SYNC;
 
-	trace_block_getrq(q, bio, rw);
+	trace_block_getrq(q, bio, op);
 	blk_mq_set_alloc_data(&alloc_data, q, BLK_MQ_REQ_NOWAIT, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
+	rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 	if (unlikely(!rq)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
-		trace_block_sleeprq(q, bio, rw);
+		trace_block_sleeprq(q, bio, op);
 
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
-		rq = __blk_mq_alloc_request(&alloc_data, rw);
+		rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
 		ctx = alloc_data.ctx;
 		hctx = alloc_data.hctx;
 	}
@@ -1244,8 +1246,8 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie)
  */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
+	const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
 	unsigned int request_count = 0;
@@ -1338,8 +1340,8 @@ done:
  */
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio->bi_rw);
-	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
+	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
+	const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
 	struct blk_map_ctx data;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 9920596..f87a7e7 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -379,6 +379,11 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page,
 	return count;
 }
 
+static ssize_t queue_dax_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_dax(q), page);
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -516,6 +521,11 @@ static struct queue_sysfs_entry queue_wc_entry = {
 	.store = queue_wc_store,
 };
 
+static struct queue_sysfs_entry queue_dax_entry = {
+	.attr = {.name = "dax", .mode = S_IRUGO },
+	.show = queue_dax_show,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -542,6 +552,7 @@ static struct attribute *default_attrs[] = {
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
+	&queue_dax_entry.attr,
 	NULL,
 };
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 4a34978..acabba1 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
-#include <linux/jiffies.h>
+#include <linux/ktime.h>
 #include <linux/rbtree.h>
 #include <linux/ioprio.h>
 #include <linux/blktrace_api.h>
@@ -22,28 +22,28 @@
  */
 /* max queue in one round of service */
 static const int cfq_quantum = 8;
-static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
+static const u64 cfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
 /* maximum backwards seek, in KiB */
 static const int cfq_back_max = 16 * 1024;
 /* penalty of a backwards seek */
 static const int cfq_back_penalty = 2;
-static const int cfq_slice_sync = HZ / 10;
-static int cfq_slice_async = HZ / 25;
+static const u64 cfq_slice_sync = NSEC_PER_SEC / 10;
+static u64 cfq_slice_async = NSEC_PER_SEC / 25;
 static const int cfq_slice_async_rq = 2;
-static int cfq_slice_idle = HZ / 125;
-static int cfq_group_idle = HZ / 125;
-static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
+static u64 cfq_slice_idle = NSEC_PER_SEC / 125;
+static u64 cfq_group_idle = NSEC_PER_SEC / 125;
+static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
  * offset from end of service tree
  */
-#define CFQ_IDLE_DELAY		(HZ / 5)
+#define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
  */
-#define CFQ_MIN_TT		(2)
+#define CFQ_MIN_TT		(2 * NSEC_PER_SEC / HZ)
 
 #define CFQ_SLICE_SCALE		(5)
 #define CFQ_HW_QUEUE_MIN	(5)
@@ -73,11 +73,11 @@ static struct kmem_cache *cfq_pool;
 #define CFQ_WEIGHT_LEGACY_MAX	1000
 
 struct cfq_ttime {
-	unsigned long last_end_request;
+	u64 last_end_request;
 
-	unsigned long ttime_total;
+	u64 ttime_total;
+	u64 ttime_mean;
 	unsigned long ttime_samples;
-	unsigned long ttime_mean;
 };
 
 /*
@@ -94,7 +94,7 @@ struct cfq_rb_root {
 	struct cfq_ttime ttime;
 };
 #define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, \
-			.ttime = {.last_end_request = jiffies,},}
+			.ttime = {.last_end_request = ktime_get_ns(),},}
 
 /*
  * Per process-grouping structure
@@ -109,7 +109,7 @@ struct cfq_queue {
 	/* service_tree member */
 	struct rb_node rb_node;
 	/* service_tree key */
-	unsigned long rb_key;
+	u64 rb_key;
 	/* prio tree member */
 	struct rb_node p_node;
 	/* prio tree root we belong to, if any */
@@ -126,13 +126,13 @@ struct cfq_queue {
 	struct list_head fifo;
 
 	/* time when queue got scheduled in to dispatch first request. */
-	unsigned long dispatch_start;
-	unsigned int allocated_slice;
-	unsigned int slice_dispatch;
+	u64 dispatch_start;
+	u64 allocated_slice;
+	u64 slice_dispatch;
 	/* time when first request from queue completed and slice started. */
-	unsigned long slice_start;
-	unsigned long slice_end;
-	long slice_resid;
+	u64 slice_start;
+	u64 slice_end;
+	s64 slice_resid;
 
 	/* pending priority requests */
 	int prio_pending;
@@ -141,7 +141,7 @@ struct cfq_queue {
 
 	/* io prio of this group */
 	unsigned short ioprio, org_ioprio;
-	unsigned short ioprio_class;
+	unsigned short ioprio_class, org_ioprio_class;
 
 	pid_t pid;
 
@@ -290,7 +290,7 @@ struct cfq_group {
 	struct cfq_rb_root service_trees[2][3];
 	struct cfq_rb_root service_tree_idle;
 
-	unsigned long saved_wl_slice;
+	u64 saved_wl_slice;
 	enum wl_type_t saved_wl_type;
 	enum wl_class_t saved_wl_class;
 
@@ -329,7 +329,7 @@ struct cfq_data {
 	 */
 	enum wl_class_t serving_wl_class;
 	enum wl_type_t serving_wl_type;
-	unsigned long workload_expires;
+	u64 workload_expires;
 	struct cfq_group *serving_group;
 
 	/*
@@ -362,7 +362,7 @@ struct cfq_data {
 	/*
 	 * idle window management
 	 */
-	struct timer_list idle_slice_timer;
+	struct hrtimer idle_slice_timer;
 	struct work_struct unplug_work;
 
 	struct cfq_queue *active_queue;
@@ -374,22 +374,22 @@ struct cfq_data {
 	 * tunables, see top of file
 	 */
 	unsigned int cfq_quantum;
-	unsigned int cfq_fifo_expire[2];
 	unsigned int cfq_back_penalty;
 	unsigned int cfq_back_max;
-	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
-	unsigned int cfq_slice_idle;
-	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
-	unsigned int cfq_target_latency;
+	u64 cfq_fifo_expire[2];
+	u64 cfq_slice[2];
+	u64 cfq_slice_idle;
+	u64 cfq_group_idle;
+	u64 cfq_target_latency;
 
 	/*
 	 * Fallback dummy cfqq for extreme OOM conditions
 	 */
 	struct cfq_queue oom_cfqq;
 
-	unsigned long last_delayed_sync;
+	u64 last_delayed_sync;
 };
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
@@ -667,15 +667,16 @@ static inline void cfqg_put(struct cfq_group *cfqg)
 } while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-					    struct cfq_group *curr_cfqg, int rw)
+					    struct cfq_group *curr_cfqg, int op,
+					    int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, rw, 1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, 1);
 	cfqg_stats_end_empty_time(&cfqg->stats);
 	cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg);
 }
 
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time)
+			uint64_t time, unsigned long unaccounted_time)
 {
 	blkg_stat_add(&cfqg->stats.time, time);
 #ifdef CONFIG_DEBUG_BLK_CGROUP
@@ -683,26 +684,30 @@ static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
 #endif
 }
 
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw)
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
+					       int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, rw, -1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, -1);
 }
 
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw)
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
+					       int op_flags)
 {
-	blkg_rwstat_add(&cfqg->stats.merged, rw, 1);
+	blkg_rwstat_add(&cfqg->stats.merged, op, op_flags, 1);
 }
 
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw)
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags)
 {
 	struct cfqg_stats *stats = &cfqg->stats;
 	unsigned long long now = sched_clock();
 
 	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, rw, now - io_start_time);
+		blkg_rwstat_add(&stats->service_time, op, op_flags,
+				now - io_start_time);
 	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, rw,
+		blkg_rwstat_add(&stats->wait_time, op, op_flags,
 				io_start_time - start_time);
 }
 
@@ -781,13 +786,16 @@ static inline void cfqg_put(struct cfq_group *cfqg) { }
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-			struct cfq_group *curr_cfqg, int rw) { }
+			struct cfq_group *curr_cfqg, int op, int op_flags) { }
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
-			unsigned long time, unsigned long unaccounted_time) { }
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int rw) { }
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int rw) { }
+			uint64_t time, unsigned long unaccounted_time) { }
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
+			int op_flags) { }
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
+			int op_flags) { }
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int rw) { }
+			uint64_t start_time, uint64_t io_start_time, int op,
+			int op_flags) { }
 
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -807,7 +815,7 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
 static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
 	struct cfq_ttime *ttime, bool group_idle)
 {
-	unsigned long slice;
+	u64 slice;
 	if (!sample_valid(ttime->ttime_samples))
 		return false;
 	if (group_idle)
@@ -930,17 +938,18 @@ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
  * if a queue is marked sync and has sync io queued. A sync queue with async
  * io only, should not get full sync slice length.
  */
-static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
+static inline u64 cfq_prio_slice(struct cfq_data *cfqd, bool sync,
 				 unsigned short prio)
 {
-	const int base_slice = cfqd->cfq_slice[sync];
+	u64 base_slice = cfqd->cfq_slice[sync];
+	u64 slice = div_u64(base_slice, CFQ_SLICE_SCALE);
 
 	WARN_ON(prio >= IOPRIO_BE_NR);
 
-	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
+	return base_slice + (slice * (4 - prio));
 }
 
-static inline int
+static inline u64
 cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
@@ -958,15 +967,14 @@ cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
  *
  * The result is also in fixed point w/ CFQ_SERVICE_SHIFT.
  */
-static inline u64 cfqg_scale_charge(unsigned long charge,
+static inline u64 cfqg_scale_charge(u64 charge,
 				    unsigned int vfraction)
 {
 	u64 c = charge << CFQ_SERVICE_SHIFT;	/* make it fixed point */
 
 	/* charge / vfraction */
 	c <<= CFQ_SERVICE_SHIFT;
-	do_div(c, vfraction);
-	return c;
+	return div_u64(c, vfraction);
 }
 
 static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
@@ -1019,16 +1027,16 @@ static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
 	return cfqg->busy_queues_avg[rt];
 }
 
-static inline unsigned
+static inline u64
 cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
 	return cfqd->cfq_target_latency * cfqg->vfraction >> CFQ_SERVICE_SHIFT;
 }
 
-static inline unsigned
+static inline u64
 cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
+	u64 slice = cfq_prio_to_slice(cfqd, cfqq);
 	if (cfqd->cfq_latency) {
 		/*
 		 * interested queues (we consider only the ones with the same
@@ -1036,20 +1044,22 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		 */
 		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
 						cfq_class_rt(cfqq));
-		unsigned sync_slice = cfqd->cfq_slice[1];
-		unsigned expect_latency = sync_slice * iq;
-		unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
+		u64 sync_slice = cfqd->cfq_slice[1];
+		u64 expect_latency = sync_slice * iq;
+		u64 group_slice = cfq_group_slice(cfqd, cfqq->cfqg);
 
 		if (expect_latency > group_slice) {
-			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
+			u64 base_low_slice = 2 * cfqd->cfq_slice_idle;
+			u64 low_slice;
+
 			/* scale low_slice according to IO priority
 			 * and sync vs async */
-			unsigned low_slice =
-				min(slice, base_low_slice * slice / sync_slice);
+			low_slice = div64_u64(base_low_slice*slice, sync_slice);
+			low_slice = min(slice, low_slice);
 			/* the adapted slice value is scaled to fit all iqs
 			 * into the target latency */
-			slice = max(slice * group_slice / expect_latency,
-				    low_slice);
+			slice = div64_u64(slice*group_slice, expect_latency);
+			slice = max(slice, low_slice);
 		}
 	}
 	return slice;
@@ -1058,12 +1068,13 @@ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 static inline void
 cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+	u64 slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+	u64 now = ktime_get_ns();
 
-	cfqq->slice_start = jiffies;
-	cfqq->slice_end = jiffies + slice;
+	cfqq->slice_start = now;
+	cfqq->slice_end = now + slice;
 	cfqq->allocated_slice = slice;
-	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
+	cfq_log_cfqq(cfqd, cfqq, "set_slice=%llu", cfqq->slice_end - now);
 }
 
 /*
@@ -1075,7 +1086,7 @@ static inline bool cfq_slice_used(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_slice_new(cfqq))
 		return false;
-	if (time_before(jiffies, cfqq->slice_end))
+	if (ktime_get_ns() < cfqq->slice_end)
 		return false;
 
 	return true;
@@ -1241,8 +1252,8 @@ cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
 }
 
-static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
-				      struct cfq_queue *cfqq)
+static u64 cfq_slice_offset(struct cfq_data *cfqd,
+			    struct cfq_queue *cfqq)
 {
 	/*
 	 * just an approximation, should be ok.
@@ -1435,31 +1446,32 @@ cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	cfqg_stats_update_dequeue(cfqg);
 }
 
-static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
-						unsigned int *unaccounted_time)
+static inline u64 cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
+				       u64 *unaccounted_time)
 {
-	unsigned int slice_used;
+	u64 slice_used;
+	u64 now = ktime_get_ns();
 
 	/*
 	 * Queue got expired before even a single request completed or
 	 * got expired immediately after first request completion.
 	 */
-	if (!cfqq->slice_start || cfqq->slice_start == jiffies) {
+	if (!cfqq->slice_start || cfqq->slice_start == now) {
 		/*
 		 * Also charge the seek time incurred to the group, otherwise
 		 * if there are mutiple queues in the group, each can dispatch
 		 * a single request on seeky media and cause lots of seek time
 		 * and group will never know it.
 		 */
-		slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start),
-					1);
+		slice_used = max_t(u64, (now - cfqq->dispatch_start),
+					jiffies_to_nsecs(1));
 	} else {
-		slice_used = jiffies - cfqq->slice_start;
+		slice_used = now - cfqq->slice_start;
 		if (slice_used > cfqq->allocated_slice) {
 			*unaccounted_time = slice_used - cfqq->allocated_slice;
 			slice_used = cfqq->allocated_slice;
 		}
-		if (time_after(cfqq->slice_start, cfqq->dispatch_start))
+		if (cfqq->slice_start > cfqq->dispatch_start)
 			*unaccounted_time += cfqq->slice_start -
 					cfqq->dispatch_start;
 	}
@@ -1471,10 +1483,11 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl, charge, unaccounted_sl = 0;
+	u64 used_sl, charge, unaccounted_sl = 0;
 	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
 			- cfqg->service_tree_idle.count;
 	unsigned int vfr;
+	u64 now = ktime_get_ns();
 
 	BUG_ON(nr_sync < 0);
 	used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl);
@@ -1496,9 +1509,8 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
-	if (time_after(cfqd->workload_expires, jiffies)) {
-		cfqg->saved_wl_slice = cfqd->workload_expires
-						- jiffies;
+	if (cfqd->workload_expires > now) {
+		cfqg->saved_wl_slice = cfqd->workload_expires - now;
 		cfqg->saved_wl_type = cfqd->serving_wl_type;
 		cfqg->saved_wl_class = cfqd->serving_wl_class;
 	} else
@@ -1507,7 +1519,7 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
 					st->min_vdisktime);
 	cfq_log_cfqq(cfqq->cfqd, cfqq,
-		     "sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
+		     "sl_used=%llu disp=%llu charge=%llu iops=%u sect=%lu",
 		     used_sl, cfqq->slice_dispatch, charge,
 		     iops_mode(cfqd), cfqq->nr_sectors);
 	cfqg_stats_update_timeslice_used(cfqg, used_sl, unaccounted_sl);
@@ -1530,7 +1542,7 @@ static void cfq_init_cfqg_base(struct cfq_group *cfqg)
 		*st = CFQ_RB_ROOT;
 	RB_CLEAR_NODE(&cfqg->rb_node);
 
-	cfqg->ttime.last_end_request = jiffies;
+	cfqg->ttime.last_end_request = ktime_get_ns();
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
@@ -2213,10 +2225,11 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 {
 	struct rb_node **p, *parent;
 	struct cfq_queue *__cfqq;
-	unsigned long rb_key;
+	u64 rb_key;
 	struct cfq_rb_root *st;
 	int left;
 	int new_cfqq = 1;
+	u64 now = ktime_get_ns();
 
 	st = st_for(cfqq->cfqg, cfqq_class(cfqq), cfqq_type(cfqq));
 	if (cfq_class_idle(cfqq)) {
@@ -2226,7 +2239,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
 			rb_key += __cfqq->rb_key;
 		} else
-			rb_key += jiffies;
+			rb_key += now;
 	} else if (!add_front) {
 		/*
 		 * Get our rb key offset. Subtract any residual slice
@@ -2234,13 +2247,13 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * count indicates slice overrun, and this should position
 		 * the next service time further away in the tree.
 		 */
-		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
+		rb_key = cfq_slice_offset(cfqd, cfqq) + now;
 		rb_key -= cfqq->slice_resid;
 		cfqq->slice_resid = 0;
 	} else {
-		rb_key = -HZ;
+		rb_key = -NSEC_PER_SEC;
 		__cfqq = cfq_rb_first(st);
-		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
+		rb_key += __cfqq ? __cfqq->rb_key : now;
 	}
 
 	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
@@ -2266,7 +2279,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * sort by key, that represents service time.
 		 */
-		if (time_before(rb_key, __cfqq->rb_key))
+		if (rb_key < __cfqq->rb_key)
 			p = &parent->rb_left;
 		else {
 			p = &parent->rb_right;
@@ -2461,10 +2474,10 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group,
-				 rq->cmd_flags);
+				 req_op(rq), rq->cmd_flags);
 }
 
 static struct request *
@@ -2517,7 +2530,7 @@ static void cfq_remove_request(struct request *rq)
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
 	if (rq->cmd_flags & REQ_PRIO) {
 		WARN_ON(!cfqq->prio_pending);
 		cfqq->prio_pending--;
@@ -2531,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 	struct request *__rq;
 
 	__rq = cfq_find_rq_fmerge(cfqd, bio);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_FRONT_MERGE;
 	}
@@ -2552,7 +2565,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req,
 static void cfq_bio_merged(struct request_queue *q, struct request *req,
 				struct bio *bio)
 {
-	cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_rw);
+	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_rw);
 }
 
 static void
@@ -2566,7 +2579,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(next->fifo_time, rq->fifo_time) &&
+	    next->fifo_time < rq->fifo_time &&
 	    cfqq == RQ_CFQQ(next)) {
 		list_move(&rq->queuelist, &next->queuelist);
 		rq->fifo_time = next->fifo_time;
@@ -2575,7 +2588,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
-	cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags);
+	cfqg_stats_update_io_merged(RQ_CFQG(rq), req_op(next), next->cmd_flags);
 
 	cfqq = RQ_CFQQ(next);
 	/*
@@ -2588,8 +2601,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 		cfq_del_cfqq_rr(cfqd, cfqq);
 }
 
-static int cfq_allow_merge(struct request_queue *q, struct request *rq,
-			   struct bio *bio)
+static int cfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+			       struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_io_cq *cic;
@@ -2613,9 +2626,15 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
 	return cfqq == RQ_CFQQ(rq);
 }
 
+static int cfq_allow_rq_merge(struct request_queue *q, struct request *rq,
+			      struct request *next)
+{
+	return RQ_CFQQ(rq) == RQ_CFQQ(next);
+}
+
 static inline void cfq_del_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
-	del_timer(&cfqd->idle_slice_timer);
+	hrtimer_try_to_cancel(&cfqd->idle_slice_timer);
 	cfqg_stats_update_idle_time(cfqq->cfqg);
 }
 
@@ -2627,7 +2646,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				cfqd->serving_wl_class, cfqd->serving_wl_type);
 		cfqg_stats_update_avg_queue_size(cfqq->cfqg);
 		cfqq->slice_start = 0;
-		cfqq->dispatch_start = jiffies;
+		cfqq->dispatch_start = ktime_get_ns();
 		cfqq->allocated_slice = 0;
 		cfqq->slice_end = 0;
 		cfqq->slice_dispatch = 0;
@@ -2676,8 +2695,8 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (cfq_cfqq_slice_new(cfqq))
 			cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
 		else
-			cfqq->slice_resid = cfqq->slice_end - jiffies;
-		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
+			cfqq->slice_resid = cfqq->slice_end - ktime_get_ns();
+		cfq_log_cfqq(cfqd, cfqq, "resid=%lld", cfqq->slice_resid);
 	}
 
 	cfq_group_served(cfqd, cfqq->cfqg, cfqq);
@@ -2911,7 +2930,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	struct cfq_rb_root *st = cfqq->service_tree;
 	struct cfq_io_cq *cic;
-	unsigned long sl, group_idle = 0;
+	u64 sl, group_idle = 0;
+	u64 now = ktime_get_ns();
 
 	/*
 	 * SSD device without seek penalty, disable idling. But only do so
@@ -2954,8 +2974,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime.ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime.ttime_mean)) {
-		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu",
+	    (cfqq->slice_end - now < cic->ttime.ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%llu",
 			     cic->ttime.ttime_mean);
 		return;
 	}
@@ -2976,9 +2996,10 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	else
 		sl = cfqd->cfq_slice_idle;
 
-	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
+	hrtimer_start(&cfqd->idle_slice_timer, ns_to_ktime(sl),
+		      HRTIMER_MODE_REL);
 	cfqg_stats_set_start_idle_time(cfqq->cfqg);
-	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %llu group_idle: %d", sl,
 			group_idle ? 1 : 0);
 }
 
@@ -3018,7 +3039,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 		return NULL;
 
 	rq = rq_entry_fifo(cfqq->fifo.next);
-	if (time_before(jiffies, rq->fifo_time))
+	if (ktime_get_ns() < rq->fifo_time)
 		rq = NULL;
 
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
@@ -3096,14 +3117,14 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 	struct cfq_queue *queue;
 	int i;
 	bool key_valid = false;
-	unsigned long lowest_key = 0;
+	u64 lowest_key = 0;
 	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
 	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
 		/* select the one with lowest rb_key */
 		queue = cfq_rb_first(st_for(cfqg, wl_class, i));
 		if (queue &&
-		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
+		    (!key_valid || queue->rb_key < lowest_key)) {
 			lowest_key = queue->rb_key;
 			cur_best = i;
 			key_valid = true;
@@ -3116,11 +3137,12 @@ static enum wl_type_t cfq_choose_wl_type(struct cfq_data *cfqd,
 static void
 choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
-	unsigned slice;
+	u64 slice;
 	unsigned count;
 	struct cfq_rb_root *st;
-	unsigned group_slice;
+	u64 group_slice;
 	enum wl_class_t original_class = cfqd->serving_wl_class;
+	u64 now = ktime_get_ns();
 
 	/* Choose next priority. RT > BE > IDLE */
 	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
@@ -3129,7 +3151,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		cfqd->serving_wl_class = BE_WORKLOAD;
 	else {
 		cfqd->serving_wl_class = IDLE_WORKLOAD;
-		cfqd->workload_expires = jiffies + 1;
+		cfqd->workload_expires = now + jiffies_to_nsecs(1);
 		return;
 	}
 
@@ -3147,7 +3169,7 @@ choose_wl_class_and_type(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	/*
 	 * check workload expiration, and that we still have other queues ready
 	 */
-	if (count && !time_after(jiffies, cfqd->workload_expires))
+	if (count && !(now > cfqd->workload_expires))
 		return;
 
 new_workload:
@@ -3164,13 +3186,13 @@ new_workload:
 	 */
 	group_slice = cfq_group_slice(cfqd, cfqg);
 
-	slice = group_slice * count /
+	slice = div_u64(group_slice * count,
 		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_wl_class],
 		      cfq_group_busy_queues_wl(cfqd->serving_wl_class, cfqd,
-					cfqg));
+					cfqg)));
 
 	if (cfqd->serving_wl_type == ASYNC_WORKLOAD) {
-		unsigned int tmp;
+		u64 tmp;
 
 		/*
 		 * Async queues are currently system wide. Just taking
@@ -3181,19 +3203,19 @@ new_workload:
 		 */
 		tmp = cfqd->cfq_target_latency *
 			cfqg_busy_async_queues(cfqd, cfqg);
-		tmp = tmp/cfqd->busy_queues;
-		slice = min_t(unsigned, slice, tmp);
+		tmp = div_u64(tmp, cfqd->busy_queues);
+		slice = min_t(u64, slice, tmp);
 
 		/* async workload slice is scaled down according to
 		 * the sync/async slice ratio. */
-		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
+		slice = div64_u64(slice*cfqd->cfq_slice[0], cfqd->cfq_slice[1]);
 	} else
 		/* sync workload slice is at least 2 * cfq_slice_idle */
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
-	slice = max_t(unsigned, slice, CFQ_MIN_TT);
-	cfq_log(cfqd, "workload slice:%d", slice);
-	cfqd->workload_expires = jiffies + slice;
+	slice = max_t(u64, slice, CFQ_MIN_TT);
+	cfq_log(cfqd, "workload slice:%llu", slice);
+	cfqd->workload_expires = now + slice;
 }
 
 static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
@@ -3211,16 +3233,17 @@ static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd)
 static void cfq_choose_cfqg(struct cfq_data *cfqd)
 {
 	struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);
+	u64 now = ktime_get_ns();
 
 	cfqd->serving_group = cfqg;
 
 	/* Restore the workload type data */
 	if (cfqg->saved_wl_slice) {
-		cfqd->workload_expires = jiffies + cfqg->saved_wl_slice;
+		cfqd->workload_expires = now + cfqg->saved_wl_slice;
 		cfqd->serving_wl_type = cfqg->saved_wl_type;
 		cfqd->serving_wl_class = cfqg->saved_wl_class;
 	} else
-		cfqd->workload_expires = jiffies - 1;
+		cfqd->workload_expires = now - 1;
 
 	choose_wl_class_and_type(cfqd, cfqg);
 }
@@ -3232,6 +3255,7 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
 static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq, *new_cfqq = NULL;
+	u64 now = ktime_get_ns();
 
 	cfqq = cfqd->active_queue;
 	if (!cfqq)
@@ -3292,7 +3316,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * flight or is idling for a new request, allow either of these
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
-	if (timer_pending(&cfqd->idle_slice_timer)) {
+	if (hrtimer_active(&cfqd->idle_slice_timer)) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
@@ -3303,7 +3327,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 **/
 	if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
 	    (cfq_cfqq_slice_new(cfqq) ||
-	    (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
+	    (cfqq->slice_end - now > now - cfqq->slice_start))) {
 		cfq_clear_cfqq_deep(cfqq);
 		cfq_clear_cfqq_idle_window(cfqq);
 	}
@@ -3381,11 +3405,12 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
 	struct cfq_queue *cfqq)
 {
+	u64 now = ktime_get_ns();
+
 	/* the queue hasn't finished any request, can't estimate */
 	if (cfq_cfqq_slice_new(cfqq))
 		return true;
-	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
-		cfqq->slice_end))
+	if (now + cfqd->cfq_slice_idle * cfqq->dispatched > cfqq->slice_end)
 		return true;
 
 	return false;
@@ -3460,10 +3485,10 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * based on the last sync IO we serviced
 	 */
 	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
-		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
+		u64 last_sync = ktime_get_ns() - cfqd->last_delayed_sync;
 		unsigned int depth;
 
-		depth = last_sync / cfqd->cfq_slice[1];
+		depth = div64_u64(last_sync, cfqd->cfq_slice[1]);
 		if (!depth && !cfqq->dispatched)
 			depth = 1;
 		if (depth < max_dispatch)
@@ -3546,7 +3571,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
 	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
 	    cfq_class_idle(cfqq))) {
-		cfqq->slice_end = jiffies + 1;
+		cfqq->slice_end = ktime_get_ns() + 1;
 		cfq_slice_expired(cfqd, 0);
 	}
 
@@ -3624,7 +3649,7 @@ static void cfq_init_icq(struct io_cq *icq)
 {
 	struct cfq_io_cq *cic = icq_to_cic(icq);
 
-	cic->ttime.last_end_request = jiffies;
+	cic->ttime.last_end_request = ktime_get_ns();
 }
 
 static void cfq_exit_icq(struct io_cq *icq)
@@ -3682,6 +3707,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	 * elevate the priority of this queue
 	 */
 	cfqq->org_ioprio = cfqq->ioprio;
+	cfqq->org_ioprio_class = cfqq->ioprio_class;
 	cfq_clear_cfqq_prio_changed(cfqq);
 }
 
@@ -3845,14 +3871,15 @@ out:
 }
 
 static void
-__cfq_update_io_thinktime(struct cfq_ttime *ttime, unsigned long slice_idle)
+__cfq_update_io_thinktime(struct cfq_ttime *ttime, u64 slice_idle)
 {
-	unsigned long elapsed = jiffies - ttime->last_end_request;
+	u64 elapsed = ktime_get_ns() - ttime->last_end_request;
 	elapsed = min(elapsed, 2UL * slice_idle);
 
 	ttime->ttime_samples = (7*ttime->ttime_samples + 256) / 8;
-	ttime->ttime_total = (7*ttime->ttime_total + 256*elapsed) / 8;
-	ttime->ttime_mean = (ttime->ttime_total + 128) / ttime->ttime_samples;
+	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
+	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+				     ttime->ttime_samples);
 }
 
 static void
@@ -4105,10 +4132,10 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq));
 
-	rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
+	rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
-	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
+	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
 				 rq->cmd_flags);
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
@@ -4153,6 +4180,7 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	struct cfq_io_cq *cic = cfqd->active_cic;
+	u64 now = ktime_get_ns();
 
 	/* If the queue already has requests, don't wait */
 	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
@@ -4171,7 +4199,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	/* if slice left is less than think time, wait busy */
 	if (cic && sample_valid(cic->ttime.ttime_samples)
-	    && (cfqq->slice_end - jiffies < cic->ttime.ttime_mean))
+	    && (cfqq->slice_end - now < cic->ttime.ttime_mean))
 		return true;
 
 	/*
@@ -4181,7 +4209,7 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * case where think time is less than a jiffy, mark the queue wait
 	 * busy if only 1 jiffy is left in the slice.
 	 */
-	if (cfqq->slice_end - jiffies == 1)
+	if (cfqq->slice_end - now <= jiffies_to_nsecs(1))
 		return true;
 
 	return false;
@@ -4192,9 +4220,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
 	struct cfq_data *cfqd = cfqq->cfqd;
 	const int sync = rq_is_sync(rq);
-	unsigned long now;
+	u64 now = ktime_get_ns();
 
-	now = jiffies;
 	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d",
 		     !!(rq->cmd_flags & REQ_NOIDLE));
 
@@ -4206,7 +4233,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	cfqq->dispatched--;
 	(RQ_CFQG(rq))->dispatched--;
 	cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), rq->cmd_flags);
+				     rq_io_start_time_ns(rq), req_op(rq),
+				     rq->cmd_flags);
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
@@ -4222,7 +4250,16 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 					cfqq_type(cfqq));
 
 		st->ttime.last_end_request = now;
-		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+		/*
+		 * We have to do this check in jiffies since start_time is in
+		 * jiffies and it is not trivial to convert to ns. If
+		 * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test
+		 * will become problematic but so far we are fine (the default
+		 * is 128 ms).
+		 */
+		if (!time_after(rq->start_time +
+				  nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]),
+				jiffies))
 			cfqd->last_delayed_sync = now;
 	}
 
@@ -4247,10 +4284,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		 * the queue.
 		 */
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
-			unsigned long extend_sl = cfqd->cfq_slice_idle;
+			u64 extend_sl = cfqd->cfq_slice_idle;
 			if (!cfqd->cfq_slice_idle)
 				extend_sl = cfqd->cfq_group_idle;
-			cfqq->slice_end = jiffies + extend_sl;
+			cfqq->slice_end = now + extend_sl;
 			cfq_mark_cfqq_wait_busy(cfqq);
 			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
@@ -4275,6 +4312,24 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		cfq_schedule_dispatch(cfqd);
 }
 
+static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags)
+{
+	/*
+	 * If REQ_PRIO is set, boost class and prio level, if it's below
+	 * BE/NORM. If prio is not set, restore the potentially boosted
+	 * class/prio level.
+	 */
+	if (!(op_flags & REQ_PRIO)) {
+		cfqq->ioprio_class = cfqq->org_ioprio_class;
+		cfqq->ioprio = cfqq->org_ioprio;
+	} else {
+		if (cfq_class_idle(cfqq))
+			cfqq->ioprio_class = IOPRIO_CLASS_BE;
+		if (cfqq->ioprio > IOPRIO_NORM)
+			cfqq->ioprio = IOPRIO_NORM;
+	}
+}
+
 static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 {
 	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
@@ -4285,7 +4340,7 @@ static inline int __cfq_may_queue(struct cfq_queue *cfqq)
 	return ELV_MQUEUE_MAY;
 }
 
-static int cfq_may_queue(struct request_queue *q, int rw)
+static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
@@ -4302,9 +4357,10 @@ static int cfq_may_queue(struct request_queue *q, int rw)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw_is_sync(rw));
+	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
+		cfqq_boost_on_prio(cfqq, op_flags);
 
 		return __cfq_may_queue(cfqq);
 	}
@@ -4435,9 +4491,10 @@ static void cfq_kick_queue(struct work_struct *work)
 /*
  * Timer running if the active_queue is currently idling inside its time slice
  */
-static void cfq_idle_slice_timer(unsigned long data)
+static enum hrtimer_restart cfq_idle_slice_timer(struct hrtimer *timer)
 {
-	struct cfq_data *cfqd = (struct cfq_data *) data;
+	struct cfq_data *cfqd = container_of(timer, struct cfq_data,
+					     idle_slice_timer);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
 	int timed_out = 1;
@@ -4486,11 +4543,12 @@ out_kick:
 	cfq_schedule_dispatch(cfqd);
 out_cont:
 	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
+	return HRTIMER_NORESTART;
 }
 
 static void cfq_shutdown_timer_wq(struct cfq_data *cfqd)
 {
-	del_timer_sync(&cfqd->idle_slice_timer);
+	hrtimer_cancel(&cfqd->idle_slice_timer);
 	cancel_work_sync(&cfqd->unplug_work);
 }
 
@@ -4586,9 +4644,9 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	cfqg_put(cfqd->root_group);
 	spin_unlock_irq(q->queue_lock);
 
-	init_timer(&cfqd->idle_slice_timer);
+	hrtimer_init(&cfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
 	cfqd->idle_slice_timer.function = cfq_idle_slice_timer;
-	cfqd->idle_slice_timer.data = (unsigned long) cfqd;
 
 	INIT_WORK(&cfqd->unplug_work, cfq_kick_queue);
 
@@ -4609,7 +4667,7 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	 * we optimistically start assuming sync ops weren't delayed in last
 	 * second, in order to have larger depth for async operations.
 	 */
-	cfqd->last_delayed_sync = jiffies - HZ;
+	cfqd->last_delayed_sync = ktime_get_ns() - NSEC_PER_SEC;
 	return 0;
 
 out_free:
@@ -4652,9 +4710,9 @@ cfq_var_store(unsigned int *var, const char *page, size_t count)
 static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data = __VAR;					\
+	u64 __data = __VAR;						\
 	if (__CONV)							\
-		__data = jiffies_to_msecs(__data);			\
+		__data = div_u64(__data, NSEC_PER_MSEC);			\
 	return cfq_var_show(__data, (page));				\
 }
 SHOW_FUNCTION(cfq_quantum_show, cfqd->cfq_quantum, 0);
@@ -4671,6 +4729,21 @@ SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
 SHOW_FUNCTION(cfq_target_latency_show, cfqd->cfq_target_latency, 1);
 #undef SHOW_FUNCTION
 
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	__data = div_u64(__data, NSEC_PER_USEC);			\
+	return cfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(cfq_slice_idle_us_show, cfqd->cfq_slice_idle);
+USEC_SHOW_FUNCTION(cfq_group_idle_us_show, cfqd->cfq_group_idle);
+USEC_SHOW_FUNCTION(cfq_slice_sync_us_show, cfqd->cfq_slice[1]);
+USEC_SHOW_FUNCTION(cfq_slice_async_us_show, cfqd->cfq_slice[0]);
+USEC_SHOW_FUNCTION(cfq_target_latency_us_show, cfqd->cfq_target_latency);
+#undef USEC_SHOW_FUNCTION
+
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
@@ -4682,7 +4755,7 @@ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)
 	else if (__data > (MAX))					\
 		__data = (MAX);						\
 	if (__CONV)							\
-		*(__PTR) = msecs_to_jiffies(__data);			\
+		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
 		*(__PTR) = __data;					\
 	return ret;							\
@@ -4705,6 +4778,26 @@ STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
 STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX, 1);
 #undef STORE_FUNCTION
 
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct cfq_data *cfqd = e->elevator_data;			\
+	unsigned int __data;						\
+	int ret = cfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(cfq_slice_idle_us_store, &cfqd->cfq_slice_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_group_idle_us_store, &cfqd->cfq_group_idle, 0, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_sync_us_store, &cfqd->cfq_slice[1], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_slice_async_us_store, &cfqd->cfq_slice[0], 1, UINT_MAX);
+USEC_STORE_FUNCTION(cfq_target_latency_us_store, &cfqd->cfq_target_latency, 1, UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
 #define CFQ_ATTR(name) \
 	__ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store)
 
@@ -4715,12 +4808,17 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(back_seek_max),
 	CFQ_ATTR(back_seek_penalty),
 	CFQ_ATTR(slice_sync),
+	CFQ_ATTR(slice_sync_us),
 	CFQ_ATTR(slice_async),
+	CFQ_ATTR(slice_async_us),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(slice_idle_us),
 	CFQ_ATTR(group_idle),
+	CFQ_ATTR(group_idle_us),
 	CFQ_ATTR(low_latency),
 	CFQ_ATTR(target_latency),
+	CFQ_ATTR(target_latency_us),
 	__ATTR_NULL
 };
 
@@ -4729,7 +4827,8 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
-		.elevator_allow_merge_fn =	cfq_allow_merge,
+		.elevator_allow_bio_merge_fn =	cfq_allow_bio_merge,
+		.elevator_allow_rq_merge_fn =	cfq_allow_rq_merge,
 		.elevator_bio_merged_fn =	cfq_bio_merged,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,
@@ -4776,18 +4875,7 @@ static int __init cfq_init(void)
 {
 	int ret;
 
-	/*
-	 * could be 0 on HZ < 1000 setups
-	 */
-	if (!cfq_slice_async)
-		cfq_slice_async = 1;
-	if (!cfq_slice_idle)
-		cfq_slice_idle = 1;
-
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-	if (!cfq_group_idle)
-		cfq_group_idle = 1;
-
 	ret = blkcg_policy_register(&blkcg_policy_cfq);
 	if (ret)
 		return ret;
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index d0dd788..55e0bb6 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -137,7 +137,7 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		if (__rq) {
 			BUG_ON(sector != blk_rq_pos(__rq));
 
-			if (elv_rq_merge_ok(__rq, bio)) {
+			if (elv_bio_merge_ok(__rq, bio)) {
 				ret = ELEVATOR_FRONT_MERGE;
 				goto out;
 			}
@@ -173,7 +173,8 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
 	 * and move into next position (next will be deleted) in fifo
 	 */
 	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(next->fifo_time, req->fifo_time)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
 			list_move(&req->queuelist, &next->queuelist);
 			req->fifo_time = next->fifo_time;
 		}
@@ -227,7 +228,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	/*
 	 * rq is expired!
 	 */
-	if (time_after_eq(jiffies, rq->fifo_time))
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
 		return 1;
 
 	return 0;
diff --git a/block/elevator.c b/block/elevator.c
index c3555c9..7096c22 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -53,13 +53,13 @@ static LIST_HEAD(elv_list);
  * Query io scheduler to see if the current process issuing bio may be
  * merged with rq.
  */
-static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
+static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 {
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_merge_fn)
-		return e->type->ops.elevator_allow_merge_fn(q, rq, bio);
+	if (e->type->ops.elevator_allow_bio_merge_fn)
+		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -67,17 +67,17 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
 /*
  * can we safely merge with this request?
  */
-bool elv_rq_merge_ok(struct request *rq, struct bio *bio)
+bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!blk_rq_merge_ok(rq, bio))
-		return 0;
+		return false;
 
-	if (!elv_iosched_allow_merge(rq, bio))
-		return 0;
+	if (!elv_iosched_allow_bio_merge(rq, bio))
+		return false;
 
-	return 1;
+	return true;
 }
-EXPORT_SYMBOL(elv_rq_merge_ok);
+EXPORT_SYMBOL(elv_bio_merge_ok);
 
 static struct elevator_type *elevator_find(const char *name)
 {
@@ -366,8 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
-		if ((rq->cmd_flags & REQ_DISCARD) !=
-		    (pos->cmd_flags & REQ_DISCARD))
+		if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
@@ -426,7 +425,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	/*
 	 * First try one-hit cache.
 	 */
-	if (q->last_merge && elv_rq_merge_ok(q->last_merge, bio)) {
+	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
 		ret = blk_try_merge(q->last_merge, bio);
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
@@ -441,7 +440,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * See if our hash lookup can find a potential backmerge.
 	 */
 	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
-	if (__rq && elv_rq_merge_ok(__rq, bio)) {
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_BACK_MERGE;
 	}
@@ -717,12 +716,12 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 		e->type->ops.elevator_put_req_fn(rq);
 }
 
-int elv_may_queue(struct request_queue *q, int rw)
+int elv_may_queue(struct request_queue *q, int op, int op_flags)
 {
 	struct elevator_queue *e = q->elevator;
 
 	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, rw);
+		return e->type->ops.elevator_may_queue_fn(q, op, op_flags);
 
 	return ELV_MQUEUE_MAY;
 }
diff --git a/block/partition-generic.c b/block/partition-generic.c
index d7eb77e..71d9ed9 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -495,7 +495,6 @@ rescan:
 	/* add partitions */
 	for (p = 1; p < state->limit; p++) {
 		sector_t size, from;
-		struct partition_meta_info *info = NULL;
 
 		size = state->parts[p].size;
 		if (!size)
@@ -530,8 +529,6 @@ rescan:
 			}
 		}
 
-		if (state->parts[p].has_info)
-			info = &state->parts[p].info;
 		part = add_partition(disk, p, from, size,
 				     state->parts[p].flags,
 				     &state->parts[p].info);
diff --git a/block/partitions/atari.c b/block/partitions/atari.c
index 9875b05..ff1fb93 100644
--- a/block/partitions/atari.c
+++ b/block/partitions/atari.c
@@ -42,6 +42,13 @@ int atari_partition(struct parsed_partitions *state)
 	int part_fmt = 0; /* 0:unknown, 1:AHDI, 2:ICD/Supra */
 #endif
 
+	/*
+	 * ATARI partition scheme supports 512 lba only.  If this is not
+	 * the case, bail early to avoid miscalculating hd_size.
+	 */
+	if (bdev_logical_block_size(state->bdev) != 512)
+		return 0;
+
 	rs = read_part_sector(state, 0, &sect);
 	if (!rs)
 		return -1;