From f21508211d2b16e65821abd171378fa6ece126fe Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 5 Jun 2016 14:31:42 -0500
Subject: block: add REQ_OP definitions and helpers

The following patches separate the operation (WRITE, READ, DISCARD,
etc) from the rq_flag_bits flags. This patch adds definitions for
request/bio operations (REQ_OPs) and adds request/bio accessors to
get/set the op.

In this patch the REQ_OPs match the REQ rq_flag_bits ones
for compat reasons while all the code is converted to use the
op accessors in the set. In the last patches the op will become a
number and the accessors and helpers in this patch will be dropped
or updated.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/blkdev.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3d9cf326574f..49c2dbcad583 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -200,6 +200,13 @@ struct request {
 	struct request *next_rq;
 };
 
+#define req_op(req)		(op_from_rq_bits((req)->cmd_flags))
+#define req_set_op(req, op)	((req)->cmd_flags |= op)
+#define req_set_op_attrs(req, op, flags) do {	\
+	req_set_op(req, op);			\
+	(req)->cmd_flags |= flags;		\
+} while (0)
+
 static inline unsigned short req_get_ioprio(struct request *req)
 {
 	return req->ioprio;
@@ -597,7 +604,8 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
-#define rq_data_dir(rq)		((int)((rq)->cmd_flags & 1))
+#define rq_data_dir(rq) \
+	(op_is_write(op_from_rq_bits(rq->cmd_flags)) ? WRITE : READ)
 
 /*
  * Driver can handle struct request, if it either has an old style
-- 
cgit v1.2.3


From 469e3216e20a3946a292ff0414ab86de408d465e Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 5 Jun 2016 14:31:49 -0500
Subject: block discard: use bio set op accessor

This converts the block issue discard helper and users to use
the bio_set_op_attrs accessor and only pass in the operation flags
like REQ_SEQURE.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-lib.c        | 13 +++++++------
 drivers/md/dm-thin.c   |  2 +-
 include/linux/blkdev.h |  3 ++-
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-lib.c b/block/blk-lib.c
index c614eaa7b853..ff2a7f04af4d 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -23,7 +23,8 @@ static struct bio *next_bio(struct bio *bio, unsigned int nr_pages,
 }
 
 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.  */
@@ -65,7 +66,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		bio = next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
-		bio->bi_rw = type;
+		bio_set_op_attrs(bio, REQ_OP_DISCARD, op_flags);
 
 		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
@@ -99,16 +100,16 @@ 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(bio);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 8c070eed982c..e8661c25d3ea 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -360,7 +360,7 @@ static int issue_discard(struct discard_op *op, dm_block_t data_b, dm_block_t da
 	sector_t len = block_to_sectors(tc->pool, data_e - data_b);
 
 	return __blkdev_issue_discard(tc->pool_dev->bdev, s, len,
-				      GFP_NOWAIT, REQ_WRITE | REQ_DISCARD, &op->bio);
+				      GFP_NOWAIT, 0, &op->bio);
 }
 
 static void end_discard(struct discard_op *op, int r)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 49c2dbcad583..8c78aca080af 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1149,7 +1149,8 @@ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern 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);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-- 
cgit v1.2.3


From 8fe0d473f5477e9916d3ac581a226acfe83142be Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 5 Jun 2016 14:32:15 -0500
Subject: block: convert merge/insert code to check for REQ_OPs.

This patch converts the block layer merging code to use separate variables
for the operation and flags, and to check req_op for the REQ_OP.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       |  2 +-
 block/blk-merge.c      | 10 ++++++----
 include/linux/blkdev.h | 20 ++++++++++----------
 3 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 090e55d7cad7..1333bb764b28 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2161,7 +2161,7 @@ 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;
 	}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 5a03f967557a..c265348b75d1 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -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;
 
@@ -751,7 +752,8 @@ 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 +769,7 @@ 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/include/linux/blkdev.h b/include/linux/blkdev.h
index 8c78aca080af..25f01ff19780 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -666,16 +666,16 @@ static inline bool rq_mergeable(struct request *rq)
 	return true;
 }
 
-static inline bool blk_check_merge_flags(unsigned int flags1,
-					 unsigned int flags2)
+static inline bool blk_check_merge_flags(unsigned int flags1, unsigned int op1,
+					 unsigned int flags2, unsigned int op2)
 {
-	if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD))
+	if ((op1 == REQ_OP_DISCARD) != (op2 == REQ_OP_DISCARD))
 		return false;
 
 	if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
 		return false;
 
-	if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME))
+	if ((op1 == REQ_OP_WRITE_SAME) != (op2 == REQ_OP_WRITE_SAME))
 		return false;
 
 	return true;
@@ -887,12 +887,12 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 }
 
 static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
-						     unsigned int cmd_flags)
+						     int op)
 {
-	if (unlikely(cmd_flags & REQ_DISCARD))
+	if (unlikely(op == REQ_OP_DISCARD))
 		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
-	if (unlikely(cmd_flags & REQ_WRITE_SAME))
+	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
 
 	return q->limits.max_sectors;
@@ -919,11 +919,11 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
 		return q->limits.max_hw_sectors;
 
-	if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD))
-		return blk_queue_get_max_sectors(q, rq->cmd_flags);
+	if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD))
+		return blk_queue_get_max_sectors(q, req_op(rq));
 
 	return min(blk_max_size_offset(q, blk_rq_pos(rq)),
-			blk_queue_get_max_sectors(q, rq->cmd_flags));
+			blk_queue_get_max_sectors(q, req_op(rq)));
 }
 
 static inline unsigned int blk_rq_count_bios(struct request *rq)
-- 
cgit v1.2.3


From d9d8c5c489f4969667a05727e9c2c4f78cffef1a Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 5 Jun 2016 14:32:16 -0500
Subject: block: convert is_sync helpers to use REQ_OPs.

This patch converts the is_sync helpers to use separate variables
for the operation and flags.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       | 6 +++---
 block/blk-mq.c         | 8 ++++----
 block/cfq-iosched.c    | 2 +-
 include/linux/blkdev.h | 6 +++---
 4 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-core.c b/block/blk-core.c
index 1333bb764b28..f9f422837cea 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -962,7 +962,7 @@ static void __freed_request(struct request_list *rl, int sync)
 static void freed_request(struct request_list *rl, int op, unsigned int flags)
 {
 	struct request_queue *q = rl->q;
-	int sync = rw_is_sync(op | flags);
+	int sync = rw_is_sync(op, flags);
 
 	q->nr_rqs[sync]--;
 	rl->count[sync]--;
@@ -1075,7 +1075,7 @@ static struct request *__get_request(struct request_list *rl, int op,
 	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(op | op_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	int may_queue;
 
 	if (unlikely(blk_queue_dying(q)))
@@ -1244,7 +1244,7 @@ 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(op | op_flags) != 0;
+	const bool is_sync = rw_is_sync(op, op_flags) != 0;
 	DEFINE_WAIT(wait);
 	struct request_list *rl;
 	struct request *rq;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3393f29faa9e..29bcd9c07a34 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -204,7 +204,7 @@ 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(op | op_flags)]++;
+	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;
 }
 
 static struct request *
@@ -1178,7 +1178,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio->bi_rw))
+	if (rw_is_sync(bio_op(bio), bio->bi_rw))
 		op_flags |= REQ_SYNC;
 
 	trace_block_getrq(q, bio, op);
@@ -1246,7 +1246,7 @@ 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_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
@@ -1343,7 +1343,7 @@ 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_sync = rw_is_sync(bio_op(bio), bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3dafdbad8f9c..b1154861f4c9 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -4311,7 +4311,7 @@ static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw_is_sync(op | op_flags));
+	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 25f01ff19780..4937c056fcbd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -624,14 +624,14 @@ static inline unsigned int blk_queue_cluster(struct request_queue *q)
 /*
  * We regard a request as sync, if either a read or a sync write
  */
-static inline bool rw_is_sync(unsigned int rw_flags)
+static inline bool rw_is_sync(int op, unsigned int rw_flags)
 {
-	return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC);
+	return op == REQ_OP_READ || (rw_flags & REQ_SYNC);
 }
 
 static inline bool rq_is_sync(struct request *rq)
 {
-	return rw_is_sync(rq->cmd_flags);
+	return rw_is_sync(req_op(rq), rq->cmd_flags);
 }
 
 static inline bool blk_rl_full(struct request_list *rl, bool sync)
-- 
cgit v1.2.3


From 4e1b2d52a80d79296a5d899d73249748dea71a53 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 5 Jun 2016 14:32:22 -0500
Subject: block, fs, drivers: remove REQ_OP compat defs and related code

This patch drops the compat definition of req_op where it matches
the rq_flag_bits definitions, and drops the related old and compat
code that allowed users to set either the op or flags for the operation.

We also then store the operation in the bi_rw/cmd_flags field similar
to how we used to store the bio ioprio where it sat in the upper bits
of the field.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/scsi/sd.c           |  2 +-
 include/linux/bio.h         |  3 ---
 include/linux/blk_types.h   | 52 +++++++++++++++++----------------------------
 include/linux/blkdev.h      | 14 ++++++++----
 include/linux/fs.h          | 37 +++++++++++++-------------------
 include/trace/events/f2fs.h |  1 -
 6 files changed, 46 insertions(+), 63 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c8dc2217d386..fad86ad89e64 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1012,7 +1012,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
 	} else {
-		scmd_printk(KERN_ERR, SCpnt, "Unknown command %d,%llx\n",
+		scmd_printk(KERN_ERR, SCpnt, "Unknown command %llu,%llx\n",
 			    req_op(rq), (unsigned long long) rq->cmd_flags);
 		goto out;
 	}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 35108c2f8ea9..0bbb2e332410 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -44,9 +44,6 @@
 #define BIO_MAX_SIZE		(BIO_MAX_PAGES << PAGE_SHIFT)
 #define BIO_MAX_SECTORS		(BIO_MAX_SIZE >> 9)
 
-#define bio_op(bio)				(op_from_rq_bits((bio)->bi_rw))
-#define bio_set_op_attrs(bio, op, flags)	((bio)->bi_rw |= (op | flags))
-
 #define bio_prio(bio)			(bio)->bi_ioprio
 #define bio_set_prio(bio, prio)		((bio)->bi_ioprio = prio)
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 5efb6f12d2f5..23c1ab2a9475 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -48,7 +48,9 @@ struct bio {
 	struct block_device	*bi_bdev;
 	unsigned int		bi_flags;	/* status, command, etc */
 	int			bi_error;
-	unsigned int		bi_rw;		/* READ/WRITE */
+	unsigned int		bi_rw;		/* bottom bits req flags,
+						 * top bits REQ_OP
+						 */
 	unsigned short		bi_ioprio;
 
 	struct bvec_iter	bi_iter;
@@ -106,6 +108,16 @@ struct bio {
 	struct bio_vec		bi_inline_vecs[0];
 };
 
+#define BIO_OP_SHIFT	(8 * sizeof(unsigned int) - REQ_OP_BITS)
+#define bio_op(bio)	((bio)->bi_rw >> BIO_OP_SHIFT)
+
+#define bio_set_op_attrs(bio, op, op_flags) do {		\
+	WARN_ON(op >= (1 << REQ_OP_BITS));			\
+	(bio)->bi_rw &= ((1 << BIO_OP_SHIFT) - 1);		\
+	(bio)->bi_rw |= ((unsigned int) (op) << BIO_OP_SHIFT);	\
+	(bio)->bi_rw |= op_flags;				\
+} while (0)
+
 #define BIO_RESET_BYTES		offsetof(struct bio, bi_max_vecs)
 
 /*
@@ -144,7 +156,6 @@ struct bio {
  */
 enum rq_flag_bits {
 	/* common flags */
-	__REQ_WRITE,		/* not set, read. set, write */
 	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
@@ -152,9 +163,7 @@ enum rq_flag_bits {
 	__REQ_SYNC,		/* request is sync (sync write or read) */
 	__REQ_META,		/* metadata io request */
 	__REQ_PRIO,		/* boost priority in cfq */
-	__REQ_DISCARD,		/* request to discard sectors */
-	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
-	__REQ_WRITE_SAME,	/* write same block many times */
+	__REQ_SECURE,		/* secure discard (used with REQ_OP_DISCARD) */
 
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
 	__REQ_INTEGRITY,	/* I/O includes block integrity payload */
@@ -190,28 +199,22 @@ enum rq_flag_bits {
 	__REQ_NR_BITS,		/* stops here */
 };
 
-#define REQ_WRITE		(1ULL << __REQ_WRITE)
 #define REQ_FAILFAST_DEV	(1ULL << __REQ_FAILFAST_DEV)
 #define REQ_FAILFAST_TRANSPORT	(1ULL << __REQ_FAILFAST_TRANSPORT)
 #define REQ_FAILFAST_DRIVER	(1ULL << __REQ_FAILFAST_DRIVER)
 #define REQ_SYNC		(1ULL << __REQ_SYNC)
 #define REQ_META		(1ULL << __REQ_META)
 #define REQ_PRIO		(1ULL << __REQ_PRIO)
-#define REQ_DISCARD		(1ULL << __REQ_DISCARD)
-#define REQ_WRITE_SAME		(1ULL << __REQ_WRITE_SAME)
 #define REQ_NOIDLE		(1ULL << __REQ_NOIDLE)
 #define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
-	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
-	 REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
-	 REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE)
+	(REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \
+	 REQ_FLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
-#define BIO_NO_ADVANCE_ITER_MASK	(REQ_DISCARD|REQ_WRITE_SAME)
-
 /* This mask is used for both bio and request merge checking */
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_FLUSH_SEQ)
@@ -243,27 +246,12 @@ enum rq_flag_bits {
 
 enum req_op {
 	REQ_OP_READ,
-	REQ_OP_WRITE		= REQ_WRITE,
-	REQ_OP_DISCARD		= REQ_DISCARD,
-	REQ_OP_WRITE_SAME	= REQ_WRITE_SAME,
+	REQ_OP_WRITE,
+	REQ_OP_DISCARD,		/* request to discard sectors */
+	REQ_OP_WRITE_SAME,	/* write same block many times */
 };
 
-/*
- * tmp cpmpat. Users used to set the write bit for all non reads, but
- * we will be dropping the bitmap use for ops. Support both until
- * the end of the patchset.
- */
-static inline int op_from_rq_bits(u64 flags)
-{
-	if (flags & REQ_OP_DISCARD)
-		return REQ_OP_DISCARD;
-	else if (flags & REQ_OP_WRITE_SAME)
-		return REQ_OP_WRITE_SAME;
-	else if (flags & REQ_OP_WRITE)
-		return REQ_OP_WRITE;
-	else
-		return REQ_OP_READ;
-}
+#define REQ_OP_BITS 2
 
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4937c056fcbd..78ae3dbf2de1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -200,8 +200,15 @@ struct request {
 	struct request *next_rq;
 };
 
-#define req_op(req)		(op_from_rq_bits((req)->cmd_flags))
-#define req_set_op(req, op)	((req)->cmd_flags |= op)
+#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS)
+#define req_op(req)  ((req)->cmd_flags >> REQ_OP_SHIFT)
+
+#define req_set_op(req, op) do {				\
+	WARN_ON(op >= (1 << REQ_OP_BITS));			\
+	(req)->cmd_flags &= ((1ULL << REQ_OP_SHIFT) - 1);	\
+	(req)->cmd_flags |= ((u64) (op) << REQ_OP_SHIFT);	\
+} while (0)
+
 #define req_set_op_attrs(req, op, flags) do {	\
 	req_set_op(req, op);			\
 	(req)->cmd_flags |= flags;		\
@@ -604,8 +611,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
-#define rq_data_dir(rq) \
-	(op_is_write(op_from_rq_bits(rq->cmd_flags)) ? WRITE : READ)
+#define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
 
 /*
  * Driver can handle struct request, if it either has an old style
diff --git a/include/linux/fs.h b/include/linux/fs.h
index af6f3c7e4822..ccd166477487 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -152,9 +152,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define CHECK_IOVEC_ONLY -1
 
 /*
- * The below are the various read and write types that we support. Some of
+ * The below are the various read and write flags that we support. Some of
  * them include behavioral modifiers that send information down to the
- * block layer and IO scheduler. Terminology:
+ * block layer and IO scheduler. They should be used along with a req_op.
+ * Terminology:
  *
  *	The block layer uses device plugging to defer IO a little bit, in
  *	the hope that we will see more IO very shortly. This increases
@@ -193,19 +194,19 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
  *			non-volatile media on completion.
  *
  */
-#define RW_MASK			REQ_WRITE
+#define RW_MASK			REQ_OP_WRITE
 #define RWA_MASK		REQ_RAHEAD
 
-#define READ			0
+#define READ			REQ_OP_READ
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
 
-#define READ_SYNC		(READ | REQ_SYNC)
-#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_ODIRECT		(WRITE | REQ_SYNC)
-#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
-#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
-#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
+#define READ_SYNC		REQ_SYNC
+#define WRITE_SYNC		(REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT		REQ_SYNC
+#define WRITE_FLUSH		(REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
+#define WRITE_FUA		(REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA		(REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 /*
  * Attribute flags.  These should be or-ed together to figure out what
@@ -2464,17 +2465,9 @@ extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
 #ifdef CONFIG_BLOCK
-/*
- * tmp cpmpat. Users used to set the write bit for all non reads, but
- * we will be dropping the bitmap use for ops. Support both until
- * the end of the patchset.
- */
-static inline bool op_is_write(unsigned long flags)
+static inline bool op_is_write(unsigned int op)
 {
-	if (flags & (REQ_OP_WRITE | REQ_OP_WRITE_SAME | REQ_OP_DISCARD))
-		return true;
-	else
-		return false;
+	return op == REQ_OP_READ ? false : true;
 }
 
 /*
@@ -2482,7 +2475,7 @@ static inline bool op_is_write(unsigned long flags)
  */
 static inline int bio_rw(struct bio *bio)
 {
-	if (op_is_write(op_from_rq_bits(bio->bi_rw)))
+	if (op_is_write(bio_op(bio)))
 		return WRITE;
 
 	return bio->bi_rw & RWA_MASK;
@@ -2493,7 +2486,7 @@ static inline int bio_rw(struct bio *bio)
  */
 static inline int bio_data_dir(struct bio *bio)
 {
-	return op_is_write(op_from_rq_bits(bio->bi_rw)) ? WRITE : READ;
+	return op_is_write(bio_op(bio)) ? WRITE : READ;
 }
 
 extern void check_disk_size_change(struct gendisk *disk,
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 733b896fd44f..30efa44a473c 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -31,7 +31,6 @@ TRACE_DEFINE_ENUM(BG_GC);
 TRACE_DEFINE_ENUM(LFS);
 TRACE_DEFINE_ENUM(SSR);
 TRACE_DEFINE_ENUM(__REQ_RAHEAD);
-TRACE_DEFINE_ENUM(__REQ_WRITE);
 TRACE_DEFINE_ENUM(__REQ_SYNC);
 TRACE_DEFINE_ENUM(__REQ_NOIDLE);
 TRACE_DEFINE_ENUM(__REQ_FLUSH);
-- 
cgit v1.2.3


From 3a5e02ced11e22ecd9da3d6710afe15bcfee1d10 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 5 Jun 2016 14:32:23 -0500
Subject: block, drivers: add REQ_OP_FLUSH operation

This adds a REQ_OP_FLUSH operation that is sent to request_fn
based drivers by the block layer's flush code, instead of
sending requests with the request->cmd_flags REQ_FLUSH bit set.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 Documentation/block/writeback_cache_control.txt | 6 +++---
 arch/um/drivers/ubd_kern.c                      | 2 +-
 block/blk-flush.c                               | 4 ++--
 drivers/block/loop.c                            | 4 ++--
 drivers/block/nbd.c                             | 2 +-
 drivers/block/osdblk.c                          | 2 +-
 drivers/block/ps3disk.c                         | 4 ++--
 drivers/block/skd_main.c                        | 2 +-
 drivers/block/virtio_blk.c                      | 2 +-
 drivers/block/xen-blkfront.c                    | 8 ++++----
 drivers/ide/ide-disk.c                          | 2 +-
 drivers/md/dm.c                                 | 2 +-
 drivers/mmc/card/block.c                        | 6 +++---
 drivers/mmc/card/queue.h                        | 3 ++-
 drivers/mtd/mtd_blkdevs.c                       | 2 +-
 drivers/nvme/host/core.c                        | 2 +-
 drivers/scsi/sd.c                               | 7 +++----
 include/linux/blk_types.h                       | 3 ++-
 include/linux/blkdev.h                          | 3 +++
 kernel/trace/blktrace.c                         | 5 +++++
 20 files changed, 40 insertions(+), 31 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/Documentation/block/writeback_cache_control.txt b/Documentation/block/writeback_cache_control.txt
index 59e0516cbf6b..da70bdacd503 100644
--- a/Documentation/block/writeback_cache_control.txt
+++ b/Documentation/block/writeback_cache_control.txt
@@ -73,9 +73,9 @@ doing:
 
 	blk_queue_write_cache(sdkp->disk->queue, true, false);
 
-and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
+and handle empty REQ_OP_FLUSH requests in its prep_fn/request_fn.  Note that
 REQ_FLUSH requests with a payload are automatically turned into a sequence
-of an empty REQ_FLUSH request followed by the actual write by the block
+of an empty REQ_OP_FLUSH request followed by the actual write by the block
 layer.  For devices that also support the FUA bit the block layer needs
 to be told to pass through the REQ_FUA bit using:
 
@@ -83,4 +83,4 @@ to be told to pass through the REQ_FUA bit using:
 
 and the driver must handle write requests that have the REQ_FUA bit set
 in prep_fn/request_fn.  If the FUA bit is not natively supported the block
-layer turns it into an empty REQ_FLUSH request after the actual write.
+layer turns it into an empty REQ_OP_FLUSH request after the actual write.
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 17e96dc29596..ef6b4d960bad 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1286,7 +1286,7 @@ static void do_ubd_request(struct request_queue *q)
 
 		req = dev->request;
 
-		if (req->cmd_flags & REQ_FLUSH) {
+		if (req_op(req) == REQ_OP_FLUSH) {
 			io_req = kmalloc(sizeof(struct io_thread_req),
 					 GFP_ATOMIC);
 			if (io_req == NULL) {
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 9fd1f63a6348..21f0d5b0d2ca 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -29,7 +29,7 @@
  * 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.
@@ -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;
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index b9b737cafd5f..364d491d4bdd 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -542,7 +542,7 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;
 
 	if (op_is_write(req_op(rq))) {
-		if (rq->cmd_flags & REQ_FLUSH)
+		if (req_op(rq) == REQ_OP_FLUSH)
 			ret = lo_req_flush(lo, rq);
 		else if (req_op(rq) == REQ_OP_DISCARD)
 			ret = lo_discard(lo, rq, pos);
@@ -1659,7 +1659,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (lo->lo_state != Lo_bound)
 		return -EIO;
 
-	if (lo->use_dio && (!(cmd->rq->cmd_flags & REQ_FLUSH) ||
+	if (lo->use_dio && (req_op(cmd->rq) != REQ_OP_FLUSH ||
 	    req_op(cmd->rq) == REQ_OP_DISCARD))
 		cmd->use_aio = true;
 	else
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 6c2c28d124d0..d6f3c9336f29 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -284,7 +284,7 @@ static int nbd_send_req(struct nbd_device *nbd, struct request *req)
 		type = NBD_CMD_DISC;
 	else if (req_op(req) == REQ_OP_DISCARD)
 		type = NBD_CMD_TRIM;
-	else if (req->cmd_flags & REQ_FLUSH)
+	else if (req_op(req) == REQ_OP_FLUSH)
 		type = NBD_CMD_FLUSH;
 	else if (rq_data_dir(req) == WRITE)
 		type = NBD_CMD_WRITE;
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index c2854a2bfdb0..92900f5f0b47 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -321,7 +321,7 @@ static void osdblk_rq_fn(struct request_queue *q)
 		 * driver-specific, etc.
 		 */
 
-		do_flush = rq->cmd_flags & REQ_FLUSH;
+		do_flush = (req_op(rq) == REQ_OP_FLUSH);
 		do_write = (rq_data_dir(rq) == WRITE);
 
 		if (!do_flush) { /* osd_flush does not use a bio */
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 4b7e405830d7..acb44529c05e 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -196,7 +196,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
 	while ((req = blk_fetch_request(q))) {
-		if (req->cmd_flags & REQ_FLUSH) {
+		if (req_op(req) == REQ_OP_FLUSH) {
 			if (ps3disk_submit_flush_request(dev, req))
 				break;
 		} else if (req->cmd_type == REQ_TYPE_FS) {
@@ -256,7 +256,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 		return IRQ_HANDLED;
 	}
 
-	if (req->cmd_flags & REQ_FLUSH) {
+	if (req_op(req) == REQ_OP_FLUSH) {
 		read = 0;
 		op = "flush";
 	} else {
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 910e065918af..5c07a23e2ada 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -597,7 +597,7 @@ static void skd_request_fn(struct request_queue *q)
 		data_dir = rq_data_dir(req);
 		io_flags = req->cmd_flags;
 
-		if (io_flags & REQ_FLUSH)
+		if (req_op(req) == REQ_OP_FLUSH)
 			flush++;
 
 		if (io_flags & REQ_FUA)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 42758b52768c..18e4069dd24b 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -172,7 +172,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
 	vbr->req = req;
-	if (req->cmd_flags & REQ_FLUSH) {
+	if (req_op(req) == REQ_OP_FLUSH) {
 		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
 		vbr->out_hdr.sector = 0;
 		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 6fd160197b7a..3aeb25bd5057 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -743,7 +743,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		 * The indirect operation can only be a BLKIF_OP_READ or
 		 * BLKIF_OP_WRITE
 		 */
-		BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+		BUG_ON(req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA);
 		ring_req->operation = BLKIF_OP_INDIRECT;
 		ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
 			BLKIF_OP_WRITE : BLKIF_OP_READ;
@@ -755,7 +755,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		ring_req->u.rw.handle = info->handle;
 		ring_req->operation = rq_data_dir(req) ?
 			BLKIF_OP_WRITE : BLKIF_OP_READ;
-		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+		if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) {
 			/*
 			 * Ideally we can do an unordered flush-to-disk.
 			 * In case the backend onlysupports barriers, use that.
@@ -865,7 +865,7 @@ static inline bool blkif_request_flush_invalid(struct request *req,
 					       struct blkfront_info *info)
 {
 	return ((req->cmd_type != REQ_TYPE_FS) ||
-		((req->cmd_flags & REQ_FLUSH) &&
+		((req_op(req) == REQ_OP_FLUSH) &&
 		 !(info->feature_flush & REQ_FLUSH)) ||
 		((req->cmd_flags & REQ_FUA) &&
 		 !(info->feature_flush & REQ_FUA)));
@@ -2055,7 +2055,7 @@ static int blkif_recover(struct blkfront_info *info)
 			/*
 			 * Get the bios in the request so we can re-queue them.
 			 */
-			if (copy[i].request->cmd_flags & REQ_FLUSH ||
+			if (req_op(copy[i].request) == REQ_OP_FLUSH ||
 			    req_op(copy[i].request) == REQ_OP_DISCARD ||
 			    copy[i].request->cmd_flags & (REQ_FUA | REQ_SECURE)) {
 				/*
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 05dbcce70b0e..e378ef70ed63 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -431,7 +431,7 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
 	ide_drive_t *drive = q->queuedata;
 	struct ide_cmd *cmd;
 
-	if (!(rq->cmd_flags & REQ_FLUSH))
+	if (req_op(rq) != REQ_OP_FLUSH)
 		return BLKPREP_OK;
 
 	if (rq->special) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f6b104c77b6d..fcc68c8edba0 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2171,7 +2171,7 @@ static void dm_request_fn(struct request_queue *q)
 
 		/* always use block 0 to find the target for flushes for now */
 		pos = 0;
-		if (!(rq->cmd_flags & REQ_FLUSH))
+		if (req_op(rq) != REQ_OP_FLUSH)
 			pos = blk_rq_pos(rq);
 
 		if ((dm_request_peeked_before_merge_deadline(md) &&
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 201a8719f6c4..bca20f88a8b2 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1722,7 +1722,8 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req)
 		    !IS_ALIGNED(blk_rq_sectors(next), 8))
 			break;
 
-		if (req_op(next) == REQ_OP_DISCARD || next->cmd_flags & REQ_FLUSH)
+		if (req_op(next) == REQ_OP_DISCARD ||
+		    req_op(next) == REQ_OP_FLUSH)
 			break;
 
 		if (rq_data_dir(cur) != rq_data_dir(next))
@@ -2147,7 +2148,6 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_card *card = md->queue.card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
-	unsigned int cmd_flags = req ? req->cmd_flags : 0;
 
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
@@ -2171,7 +2171,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 			ret = mmc_blk_issue_secdiscard_rq(mq, req);
 		else
 			ret = mmc_blk_issue_discard_rq(mq, req);
-	} else if (cmd_flags & REQ_FLUSH) {
+	} else if (req && req_op(req) == REQ_OP_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 9fb26f20a44d..d62531124d54 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -3,7 +3,8 @@
 
 static inline bool mmc_req_is_special(struct request *req)
 {
-	return req && (req->cmd_flags & REQ_FLUSH || req_op(req) == REQ_OP_DISCARD);
+	return req &&
+		(req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
 }
 
 struct request;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 4eb9a5fb151c..78b3eb45faf6 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -87,7 +87,7 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	if (req->cmd_type != REQ_TYPE_FS)
 		return -EIO;
 
-	if (req->cmd_flags & REQ_FLUSH)
+	if (req_op(req) == REQ_OP_FLUSH)
 		return tr->flush(dev);
 
 	if (blk_rq_pos(req) + blk_rq_cur_sectors(req) >
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 089b8b8aad4f..abdfdcfb66f4 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -290,7 +290,7 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 
 	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
 		memcpy(cmd, req->cmd, sizeof(*cmd));
-	else if (req->cmd_flags & REQ_FLUSH)
+	else if (req_op(req) == REQ_OP_FLUSH)
 		nvme_setup_flush(ns, cmd);
 	else if (req_op(req) == REQ_OP_DISCARD)
 		ret = nvme_setup_discard(ns, req, cmd);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index fad86ad89e64..5a9db0fe1ee0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1143,12 +1143,11 @@ static int sd_init_command(struct scsi_cmnd *cmd)
 		return sd_setup_discard_cmnd(cmd);
 	case REQ_OP_WRITE_SAME:
 		return sd_setup_write_same_cmnd(cmd);
+	case REQ_OP_FLUSH:
+		return sd_setup_flush_cmnd(cmd);
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
-		if (rq->cmd_flags & REQ_FLUSH)
-			return sd_setup_flush_cmnd(cmd);
-		else
-			return sd_setup_read_write_cmnd(cmd);
+		return sd_setup_read_write_cmnd(cmd);
 	default:
 		BUG();
 	}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 23c1ab2a9475..32d87522f349 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -249,9 +249,10 @@ enum req_op {
 	REQ_OP_WRITE,
 	REQ_OP_DISCARD,		/* request to discard sectors */
 	REQ_OP_WRITE_SAME,	/* write same block many times */
+	REQ_OP_FLUSH,		/* request for cache flush */
 };
 
-#define REQ_OP_BITS 2
+#define REQ_OP_BITS 3
 
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 78ae3dbf2de1..0c9f8793c87e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -666,6 +666,9 @@ static inline bool rq_mergeable(struct request *rq)
 	if (rq->cmd_type != REQ_TYPE_FS)
 		return false;
 
+	if (req_op(rq) == REQ_OP_FLUSH)
+		return false;
+
 	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
 		return false;
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2d16fad519b2..0c70fbb6ea8d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -223,6 +223,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(op_flags, FUA);
 	if (op == REQ_OP_DISCARD)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
+	if (op == REQ_OP_FLUSH)
+		what |= BLK_TC_ACT(BLK_TC_FLUSH);
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -1788,6 +1790,9 @@ void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes)
 	case REQ_OP_DISCARD:
 		rwbs[i++] = 'D';
 		break;
+	case REQ_OP_FLUSH:
+		rwbs[i++] = 'F';
+		break;
 	case REQ_OP_READ:
 		rwbs[i++] = 'R';
 		break;
-- 
cgit v1.2.3


From ca93e45347e61cd85e5d71961f6c94fad143593d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 9 Jun 2016 16:00:35 +0200
Subject: block: better packing for struct request

Keep the 32-bit CPU and cmd_type flags together to avoid holes on 64-bit
architectures.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/blkdev.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0c9f8793c87e..9746d223494c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -96,12 +96,11 @@ struct request {
 	struct request_queue *q;
 	struct blk_mq_ctx *mq_ctx;
 
-	u64 cmd_flags;
+	int cpu;
 	unsigned cmd_type;
+	u64 cmd_flags;
 	unsigned long atomic_flags;
 
-	int cpu;
-
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
 	sector_t __sector;		/* sector cursor */
-- 
cgit v1.2.3


From 9828c2c6c1048c61034a8b94e6376aeff6d2284f Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 28 Jun 2016 09:03:59 +0200
Subject: block: Convert fifo_time from ulong to u64

Currently rq->fifo_time is unsigned long but CFQ stores nanosecond
timestamp in it which would overflow on 32-bit archs. Convert it to u64
to avoid the overflow. Since the rq->fifo_time is unioned with struct
call_single_data(), this does not change the size of struct request in
any way.

We have to slightly fixup block/deadline-iosched.c so that comparison
happens in the right types.

Fixes: 9a7f38c42c2b92391d9dabaf9f51df7cfe5608e4
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/deadline-iosched.c | 5 +++--
 include/linux/blkdev.h   | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index d0dd7882d8c7..26a9d3c8057a 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -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/include/linux/blkdev.h b/include/linux/blkdev.h
index 9746d223494c..d116d3b52c73 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -90,7 +90,7 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
-		unsigned long fifo_time;
+		u64 fifo_time;
 	};
 
 	struct request_queue *q;
-- 
cgit v1.2.3


From 163d4baaebe39c0e56d9c08597eab7b3ae0bf334 Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Thu, 23 Jun 2016 17:05:50 -0400
Subject: block: add QUEUE_FLAG_DAX for devices to advertise their DAX support

Currently, presence of direct_access() in block_device_operations
indicates support of DAX on its block device.  Because
block_device_operations is instantiated with 'const', this DAX
capablity may not be enabled conditinally.

In preparation for supporting DAX to device-mapper devices, add
QUEUE_FLAG_DAX to request_queue flags to advertise their DAX
support.  This will allow to set the DAX capability based on how
mapped device is composed.

Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: <linux-s390@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/brd.c          | 4 +++-
 drivers/nvdimm/pmem.c        | 1 +
 drivers/s390/block/dcssblk.c | 1 +
 fs/block_dev.c               | 5 +++--
 include/linux/blkdev.h       | 2 ++
 5 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index f5b0d6f4e09f..dd96a935fba0 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -509,7 +509,9 @@ static struct brd_device *brd_alloc(int i)
 	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
 	brd->brd_queue->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
-
+#ifdef CONFIG_BLK_DEV_RAM_DAX
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
+#endif
 	disk = brd->brd_disk = alloc_disk(max_part);
 	if (!disk)
 		goto out_free_queue;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 608fc4464574..53b701b2f73e 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -283,6 +283,7 @@ static int pmem_attach_disk(struct device *dev,
 	blk_queue_max_hw_sectors(q, UINT_MAX);
 	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, q);
 	q->queuedata = pmem;
 
 	disk = alloc_disk_node(0, nid);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index bed53c46dd90..093e9e18e7e7 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -618,6 +618,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->gd->driverfs_dev = &dev_info->dev;
 	blk_queue_make_request(dev_info->dcssblk_queue, dcssblk_make_request);
 	blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
+	queue_flag_set_unlocked(QUEUE_FLAG_DAX, dev_info->dcssblk_queue);
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
 	set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 71ccab1d22c6..d012be4ab977 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -493,7 +493,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 
 	if (size < 0)
 		return size;
-	if (!ops->direct_access)
+	if (!blk_queue_dax(bdev_get_queue(bdev)) || !ops->direct_access)
 		return -EOPNOTSUPP;
 	if ((sector + DIV_ROUND_UP(size, 512)) >
 					part_nr_sects_read(bdev->bd_part))
@@ -1287,7 +1287,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
-		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
+		if (IS_ENABLED(CONFIG_BLK_DEV_DAX) &&
+		    blk_queue_dax(disk->queue))
 			bdev->bd_inode->i_flags = S_DAX;
 		else
 			bdev->bd_inode->i_flags = 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d116d3b52c73..9d84c98b5c79 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -505,6 +505,7 @@ struct request_queue {
 #define QUEUE_FLAG_WC	       23	/* Write back caching */
 #define QUEUE_FLAG_FUA	       24	/* device supports FUA writes */
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
+#define QUEUE_FLAG_DAX         26	/* device supports DAX */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -594,6 +595,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
 #define blk_queue_secdiscard(q)	(blk_queue_discard(q) && \
 	test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags))
+#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
-- 
cgit v1.2.3


From 17007f3994cdb4643355c73f54f0adad006cf59e Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@hgst.com>
Date: Wed, 20 Jul 2016 21:40:47 -0600
Subject: block: Fix front merge check

For a front merge, the maximum number of sectors of the
request must be checked against the front merge BIO sector,
not the current sector of the request.

Signed-off-by: Damien Le Moal <damien.lemoal@hgst.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-merge.c      | 6 +++---
 include/linux/blkdev.h | 5 +++--
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux/blkdev.h')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index e7c2fbc3f656..5e4d93edeaf7 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -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;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9d84c98b5c79..48f05d768a53 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -922,7 +922,8 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q,
 			(offset & (q->limits.chunk_sectors - 1));
 }
 
-static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
+static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
+						  sector_t offset)
 {
 	struct request_queue *q = rq->q;
 
@@ -932,7 +933,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 	if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD))
 		return blk_queue_get_max_sectors(q, req_op(rq));
 
-	return min(blk_max_size_offset(q, blk_rq_pos(rq)),
+	return min(blk_max_size_offset(q, offset),
 			blk_queue_get_max_sectors(q, req_op(rq)));
 }
 
-- 
cgit v1.2.3