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 288dab8a35a0bde426a09870943c8d3ee3a50dab Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 9 Jun 2016 16:00:36 +0200
Subject: block: add a separate operation type for secure erase

Instead of overloading the discard support with the REQ_SECURE flag.
Use the opportunity to rename the queue flag as well, and remove the
dead checks for this flag in the RAID 1 and RAID 10 drivers that don't
claim support for secure erase.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c                   | 27 +++++++++++++++++----------
 block/blk-lib.c                    | 25 ++++++++++++++-----------
 block/blk-merge.c                  |  6 ++----
 drivers/block/xen-blkback/xenbus.c |  2 +-
 drivers/block/xen-blkfront.c       | 14 +++++++++-----
 drivers/md/raid1.c                 |  3 +--
 drivers/md/raid10.c                |  5 ++---
 drivers/mmc/card/block.c           | 10 ++++++----
 drivers/mmc/card/queue.c           |  2 +-
 include/linux/blk_types.h          |  5 ++---
 include/linux/blkdev.h             | 23 ++++-------------------
 kernel/trace/blktrace.c            |  6 ++++--
 12 files changed, 63 insertions(+), 65 deletions(-)

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

diff --git a/block/blk-core.c b/block/blk-core.c
index 32a283eb7274..db31a2981223 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1977,16 +1977,21 @@ generic_make_request_checks(struct bio *bio)
 		}
 	}
 
-	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_op(bio) == REQ_OP_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
-		err = -EOPNOTSUPP;
-		goto end_io;
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+		if (!blk_queue_discard(q))
+			goto not_supported;
+		break;
+	case REQ_OP_SECURE_ERASE:
+		if (!blk_queue_secure_erase(q))
+			goto not_supported;
+		break;
+	case REQ_OP_WRITE_SAME:
+		if (!bdev_write_same(bio->bi_bdev))
+			goto not_supported;
+		break;
+	default:
+		break;
 	}
 
 	/*
@@ -2003,6 +2008,8 @@ generic_make_request_checks(struct bio *bio)
 	trace_block_bio_queue(q, bio);
 	return true;
 
+not_supported:
+	err = -EOPNOTSUPP;
 end_io:
 	bio->bi_error = err;
 	bio_endio(bio);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index ff2a7f04af4d..78626c2fde33 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -23,20 +23,27 @@ 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 op_flags,
+		sector_t nr_sects, gfp_t gfp_mask, int flags,
 		struct bio **biop)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
 	unsigned int granularity;
+	enum req_op op;
 	int alignment;
 
 	if (!q)
 		return -ENXIO;
-	if (!blk_queue_discard(q))
-		return -EOPNOTSUPP;
-	if ((op_flags & REQ_SECURE) && !blk_queue_secdiscard(q))
-		return -EOPNOTSUPP;
+
+	if (flags & BLKDEV_DISCARD_SECURE) {
+		if (!blk_queue_secure_erase(q))
+			return -EOPNOTSUPP;
+		op = REQ_OP_SECURE_ERASE;
+	} else {
+		if (!blk_queue_discard(q))
+			return -EOPNOTSUPP;
+		op = REQ_OP_DISCARD;
+	}
 
 	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(q->limits.discard_granularity >> 9, 1U);
@@ -66,7 +73,7 @@ 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_set_op_attrs(bio, REQ_OP_DISCARD, op_flags);
+		bio_set_op_attrs(bio, op, 0);
 
 		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
@@ -100,16 +107,12 @@ 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 op_flags = 0;
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret;
 
-	if (flags & BLKDEV_DISCARD_SECURE)
-		op_flags |= REQ_SECURE;
-
 	blk_start_plug(&plug);
-	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, op_flags,
+	ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
 			&bio);
 	if (!ret && bio) {
 		ret = submit_bio_wait(bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index c265348b75d1..9772308a8391 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -649,8 +649,7 @@ 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, req_op(req), next->cmd_flags,
-				   req_op(next)))
+	if (req_op(req) != req_op(next))
 		return 0;
 
 	/*
@@ -752,8 +751,7 @@ 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, req_op(rq), bio->bi_rw,
-				   bio_op(bio)))
+	if (req_op(rq) != bio_op(bio))
 		return false;
 
 	/* different data direction or already started, don't merge */
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 3355f1cdd4e5..2994cfa44c8a 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -480,7 +480,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags))
 		vbd->flush_support = true;
 
-	if (q && blk_queue_secdiscard(q))
+	if (q && blk_queue_secure_erase(q))
 		vbd->discard_secure = true;
 
 	pr_debug("Successful creation of handle=%04x (dom=%u)\n",
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 343ef7abe5fd..10711292da2c 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -545,7 +545,7 @@ static int blkif_queue_discard_req(struct request *req, struct blkfront_ring_inf
 	ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
 	ring_req->u.discard.id = id;
 	ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
-	if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+	if (req_op(req) == REQ_OP_SECURE_ERASE && info->feature_secdiscard)
 		ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
 	else
 		ring_req->u.discard.flag = 0;
@@ -841,7 +841,7 @@ static int blkif_queue_request(struct request *req, struct blkfront_ring_info *r
 		return 1;
 
 	if (unlikely(req_op(req) == REQ_OP_DISCARD ||
-		     req->cmd_flags & REQ_SECURE))
+		     req_op(req) == REQ_OP_SECURE_ERASE))
 		return blkif_queue_discard_req(req, rinfo);
 	else
 		return blkif_queue_rw_req(req, rinfo);
@@ -955,7 +955,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 		rq->limits.discard_granularity = info->discard_granularity;
 		rq->limits.discard_alignment = info->discard_alignment;
 		if (info->feature_secdiscard)
-			queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, rq);
+			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
 	}
 
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
@@ -1595,7 +1595,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
-				queue_flag_clear(QUEUE_FLAG_SECDISCARD, rq);
+				queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
 			}
 			blk_mq_complete_request(req, error);
 			break;
@@ -2052,10 +2052,14 @@ static int blkif_recover(struct blkfront_info *info)
 			 */
 			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)) {
+			    req_op(copy[i].request) == REQ_OP_SECURE_ERASE ||
+			    copy[i].request->cmd_flags & REQ_FUA) {
 				/*
 				 * Flush operations don't contain bios, so
 				 * we need to requeue the whole request
+				 *
+				 * XXX: but this doesn't make any sense for a
+				 * write with the FUA flag set..
 				 */
 				list_add(&copy[i].request->queuelist, &requests);
 				continue;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 10e53cd6a995..41d9c31da3b3 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1058,7 +1058,6 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio)
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_flush_fua = (bio->bi_rw &
 						(REQ_PREFLUSH | REQ_FUA));
-	const unsigned long do_sec = (bio->bi_rw & REQ_SECURE);
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
 	struct raid1_plug_cb *plug = NULL;
@@ -1376,7 +1375,7 @@ read_again:
 				   conf->mirrors[i].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		bio_set_op_attrs(mbio, op, do_flush_fua | do_sync | do_sec);
+		bio_set_op_attrs(mbio, op, do_flush_fua | do_sync);
 		mbio->bi_private = r1_bio;
 
 		atomic_inc(&r1_bio->remaining);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 245640b50153..26ae74fd0d01 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1062,7 +1062,6 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
-	const unsigned long do_sec = (bio->bi_rw & REQ_SECURE);
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
@@ -1362,7 +1361,7 @@ retry_write:
 							      rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
-			bio_set_op_attrs(mbio, op, do_sync | do_fua | do_sec);
+			bio_set_op_attrs(mbio, op, do_sync | do_fua);
 			mbio->bi_private = r10_bio;
 
 			atomic_inc(&r10_bio->remaining);
@@ -1404,7 +1403,7 @@ retry_write:
 						   r10_bio, rdev));
 			mbio->bi_bdev = rdev->bdev;
 			mbio->bi_end_io	= raid10_end_write_request;
-			bio_set_op_attrs(mbio, op, do_sync | do_fua | do_sec);
+			bio_set_op_attrs(mbio, op, do_sync | do_fua);
 			mbio->bi_private = r10_bio;
 
 			atomic_inc(&r10_bio->remaining);
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index bca20f88a8b2..383184743f9a 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -2167,10 +2167,12 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		/* complete ongoing async transfer before issuing discard */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
-		if (req->cmd_flags & REQ_SECURE)
-			ret = mmc_blk_issue_secdiscard_rq(mq, req);
-		else
-			ret = mmc_blk_issue_discard_rq(mq, req);
+		ret = mmc_blk_issue_discard_rq(mq, req);
+	} else if (req && req_op(req) == REQ_OP_SECURE_ERASE) {
+		/* complete ongoing async transfer before issuing secure erase*/
+		if (card->host->areq)
+			mmc_blk_issue_rw_rq(mq, NULL);
+		ret = mmc_blk_issue_secdiscard_rq(mq, req);
 	} else if (req && req_op(req) == REQ_OP_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
 		if (card->host->areq)
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index c2d5f6f35145..bf14642a576a 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -171,7 +171,7 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 	if (card->pref_erase > max_discard)
 		q->limits.discard_granularity = 0;
 	if (mmc_can_secure_erase_trim(card))
-		queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q);
+		queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
 }
 
 /**
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 562ab8301217..efba1f2ace2e 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -163,7 +163,6 @@ 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_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 */
@@ -212,7 +211,7 @@ enum rq_flag_bits {
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \
-	 REQ_PREFLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE)
+	 REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 /* This mask is used for both bio and request merge checking */
@@ -239,7 +238,6 @@ enum rq_flag_bits {
 #define REQ_FLUSH_SEQ		(1ULL << __REQ_FLUSH_SEQ)
 #define REQ_IO_STAT		(1ULL << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1ULL << __REQ_MIXED_MERGE)
-#define REQ_SECURE		(1ULL << __REQ_SECURE)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
@@ -248,6 +246,7 @@ enum req_op {
 	REQ_OP_READ,
 	REQ_OP_WRITE,
 	REQ_OP_DISCARD,		/* request to discard sectors */
+	REQ_OP_SECURE_ERASE,	/* request to securely erase sectors */
 	REQ_OP_WRITE_SAME,	/* write same block many times */
 	REQ_OP_FLUSH,		/* request for cache flush */
 };
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0c9f8793c87e..53fee6123893 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -497,7 +497,7 @@ struct request_queue {
 #define QUEUE_FLAG_DISCARD     14	/* supports DISCARD */
 #define QUEUE_FLAG_NOXMERGES   15	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM  16	/* Contributes to random pool */
-#define QUEUE_FLAG_SECDISCARD  17	/* supports SECDISCARD */
+#define QUEUE_FLAG_SECERASE    17	/* supports secure erase */
 #define QUEUE_FLAG_SAME_FORCE  18	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE   20	/* queue is initialized */
@@ -593,8 +593,8 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #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_secure_erase(q) \
+	(test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags))
 
 #define blk_noretry_request(rq) \
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
@@ -675,21 +675,6 @@ static inline bool rq_mergeable(struct request *rq)
 	return true;
 }
 
-static inline bool blk_check_merge_flags(unsigned int flags1, unsigned int op1,
-					 unsigned int flags2, unsigned int op2)
-{
-	if ((op1 == REQ_OP_DISCARD) != (op2 == REQ_OP_DISCARD))
-		return false;
-
-	if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
-		return false;
-
-	if ((op1 == REQ_OP_WRITE_SAME) != (op2 == REQ_OP_WRITE_SAME))
-		return false;
-
-	return true;
-}
-
 static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
 {
 	if (bio_data(a) == bio_data(b))
@@ -1158,7 +1143,7 @@ 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 op_flags,
+		sector_t nr_sects, gfp_t gfp_mask, int 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);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 03b0dd98ff0e..af49caf973eb 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1791,6 +1791,10 @@ void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes)
 	case REQ_OP_DISCARD:
 		rwbs[i++] = 'D';
 		break;
+	case REQ_OP_SECURE_ERASE:
+		rwbs[i++] = 'D';
+		rwbs[i++] = 'E';
+		break;
 	case REQ_OP_FLUSH:
 		rwbs[i++] = 'F';
 		break;
@@ -1809,8 +1813,6 @@ void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes)
 		rwbs[i++] = 'S';
 	if (rw & REQ_META)
 		rwbs[i++] = 'M';
-	if (rw & REQ_SECURE)
-		rwbs[i++] = 'E';
 
 	rwbs[i] = '\0';
 }
-- 
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 7a9eb20666317794d0279843fbd091af93907780 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 3 Jun 2016 18:06:47 -0700
Subject: pmem: kill __pmem address space

The __pmem address space was meant to annotate codepaths that touch
persistent memory and need to coordinate a call to wmb_pmem().  Now that
wmb_pmem() is gone, there is little need to keep this annotation.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 Documentation/filesystems/Locking |  2 +-
 arch/powerpc/sysdev/axonram.c     |  4 +--
 arch/x86/include/asm/pmem.h       | 41 ++++++++++-------------
 drivers/acpi/nfit.h               |  2 +-
 drivers/block/brd.c               |  4 +--
 drivers/nvdimm/pmem.c             |  6 ++--
 drivers/nvdimm/pmem.h             |  4 +--
 drivers/s390/block/dcssblk.c      |  6 ++--
 fs/dax.c                          |  6 ++--
 include/linux/blkdev.h            |  6 ++--
 include/linux/compiler.h          |  2 --
 include/linux/nd.h                |  2 +-
 include/linux/pmem.h              | 70 ++++++++++-----------------------------
 scripts/checkpatch.pl             |  1 -
 tools/testing/nvdimm/pmem-dax.c   |  2 +-
 15 files changed, 56 insertions(+), 102 deletions(-)

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

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 75eea7ce3d7c..d9c37ec4c760 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -395,7 +395,7 @@ prototypes:
 	int (*release) (struct gendisk *, fmode_t);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t, void __pmem **,
+	int (*direct_access) (struct block_device *, sector_t, void **,
 				unsigned long *);
 	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ff75d70f7285..a87489d007dc 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -143,12 +143,12 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  */
 static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void __pmem **kaddr, pfn_t *pfn, long size)
+		       void **kaddr, pfn_t *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
 	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
 
-	*kaddr = (void __pmem __force *) bank->io_addr + offset;
+	*kaddr = (void *) bank->io_addr + offset;
 	*pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV);
 	return bank->size - offset;
 }
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index a8cf2a6b14d9..643eba42d620 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -28,10 +28,9 @@
  * Copy data to persistent memory media via non-temporal stores so that
  * a subsequent pmem driver flush operation will drain posted write queues.
  */
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t n)
+static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
 {
-	int unwritten;
+	int rem;
 
 	/*
 	 * We are copying between two kernel buffers, if
@@ -39,19 +38,17 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
 	 * fault) we would have already reported a general protection fault
 	 * before the WARN+BUG.
 	 */
-	unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
-			(void __user *) src, n);
-	if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
-				__func__, dst, src, unwritten))
+	rem = __copy_from_user_inatomic_nocache(dst, (void __user *) src, n);
+	if (WARN(rem, "%s: fault copying %p <- %p unwritten: %d\n",
+				__func__, dst, src, rem))
 		BUG();
 }
 
-static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src,
-		size_t n)
+static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
 {
 	if (static_cpu_has(X86_FEATURE_MCE_RECOVERY))
-		return memcpy_mcsafe(dst, (void __force *) src, n);
-	memcpy(dst, (void __force *) src, n);
+		return memcpy_mcsafe(dst, src, n);
+	memcpy(dst, src, n);
 	return 0;
 }
 
@@ -63,15 +60,14 @@ static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src,
  * Write back a cache range using the CLWB (cache line write back)
  * instruction.
  */
-static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
+static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
 	unsigned long clflush_mask = x86_clflush_size - 1;
-	void *vaddr = (void __force *)addr;
-	void *vend = vaddr + size;
+	void *vend = addr + size;
 	void *p;
 
-	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	for (p = (void *)((unsigned long)addr & ~clflush_mask);
 	     p < vend; p += x86_clflush_size)
 		clwb(p);
 }
@@ -93,14 +89,13 @@ static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
  *
  * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
  */
-static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 		struct iov_iter *i)
 {
-	void *vaddr = (void __force *)addr;
 	size_t len;
 
 	/* TODO: skip the write-back by always using non-temporal stores */
-	len = copy_from_iter_nocache(vaddr, bytes, i);
+	len = copy_from_iter_nocache(addr, bytes, i);
 
 	if (__iter_needs_pmem_wb(i))
 		arch_wb_cache_pmem(addr, bytes);
@@ -115,17 +110,15 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
  *
  * Write zeros into the memory range starting at 'addr' for 'size' bytes.
  */
-static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+static inline void arch_clear_pmem(void *addr, size_t size)
 {
-	void *vaddr = (void __force *)addr;
-
-	memset(vaddr, 0, size);
+	memset(addr, 0, size);
 	arch_wb_cache_pmem(addr, size);
 }
 
-static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+static inline void arch_invalidate_pmem(void *addr, size_t size)
 {
-	clflush_cache_range((void __force *) addr, size);
+	clflush_cache_range(addr, size);
 }
 #endif /* CONFIG_ARCH_HAS_PMEM_API */
 #endif /* __ASM_X86_PMEM_H__ */
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 9fda77cf81da..80fb2c0ac8bf 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -164,7 +164,7 @@ enum nd_blk_mmio_selector {
 struct nd_blk_addr {
 	union {
 		void __iomem *base;
-		void __pmem  *aperture;
+		void *aperture;
 	};
 };
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c04bd9bc39fd..5f1fe4e6208d 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -381,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 static long brd_direct_access(struct block_device *bdev, sector_t sector,
-			void __pmem **kaddr, pfn_t *pfn, long size)
+			void **kaddr, pfn_t *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
@@ -391,7 +391,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
-	*kaddr = (void __pmem *)page_address(page);
+	*kaddr = page_address(page);
 	*pfn = page_to_pfn_t(page);
 
 	return PAGE_SIZE;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8bfc6acc2e43..7251b4b6da84 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -74,7 +74,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	bool bad_pmem = false;
 	void *mem = kmap_atomic(page);
 	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
-	void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
+	void *pmem_addr = pmem->virt_addr + pmem_off;
 
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
@@ -173,7 +173,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 
 /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
 __weak long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		      void __pmem **kaddr, pfn_t *pfn, long size)
+		      void **kaddr, pfn_t *pfn, long size)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	resource_size_t offset = sector * 512 + pmem->data_offset;
@@ -284,7 +284,7 @@ static int pmem_attach_disk(struct device *dev,
 
 	if (IS_ERR(addr))
 		return PTR_ERR(addr);
-	pmem->virt_addr = (void __pmem *) addr;
+	pmem->virt_addr = addr;
 
 	blk_queue_write_cache(q, true, true);
 	blk_queue_make_request(q, pmem_make_request);
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index c48d4e3aa346..b4ee4f71b4a1 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -6,7 +6,7 @@
 #include <linux/fs.h>
 
 long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		      void __pmem **kaddr, pfn_t *pfn, long size);
+		      void **kaddr, pfn_t *pfn, long size);
 /* this definition is in it's own header for tools/testing/nvdimm to consume */
 struct pmem_device {
 	/* One contiguous memory region per device */
@@ -14,7 +14,7 @@ struct pmem_device {
 	/* when non-zero this device is hosting a 'pfn' instance */
 	phys_addr_t		data_offset;
 	u64			pfn_flags;
-	void __pmem		*virt_addr;
+	void			*virt_addr;
 	/* immutable base size of the namespace */
 	size_t			size;
 	/* trim size when namespace capacity has been section aligned */
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index bed53c46dd90..023c5c975dc0 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -31,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static blk_qc_t dcssblk_make_request(struct request_queue *q,
 						struct bio *bio);
 static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-			 void __pmem **kaddr, pfn_t *pfn, long size);
+			 void **kaddr, pfn_t *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -884,7 +884,7 @@ fail:
 
 static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void __pmem **kaddr, pfn_t *pfn, long size)
+			void **kaddr, pfn_t *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
 	unsigned long offset, dev_sz;
@@ -894,7 +894,7 @@ dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
 		return -ENODEV;
 	dev_sz = dev_info->end - dev_info->start;
 	offset = secnum * 512;
-	*kaddr = (void __pmem *) (dev_info->start + offset);
+	*kaddr = (void *) dev_info->start + offset;
 	*pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), PFN_DEV);
 
 	return dev_sz - offset;
diff --git a/fs/dax.c b/fs/dax.c
index 434f421da660..c8312f6441bc 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -75,13 +75,13 @@ static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
 	struct request_queue *q = bdev->bd_queue;
 	long rc = -EIO;
 
-	dax->addr = (void __pmem *) ERR_PTR(-EIO);
+	dax->addr = ERR_PTR(-EIO);
 	if (blk_queue_enter(q, true) != 0)
 		return rc;
 
 	rc = bdev_direct_access(bdev, dax);
 	if (rc < 0) {
-		dax->addr = (void __pmem *) ERR_PTR(rc);
+		dax->addr = ERR_PTR(rc);
 		blk_queue_exit(q);
 		return rc;
 	}
@@ -152,7 +152,7 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 	int rw = iov_iter_rw(iter), rc;
 	long map_len = 0;
 	struct blk_dax_ctl dax = {
-		.addr = (void __pmem *) ERR_PTR(-EIO),
+		.addr = ERR_PTR(-EIO),
 	};
 	unsigned blkbits = inode->i_blkbits;
 	sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3d9cf326574f..fde908b2836b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1659,7 +1659,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
  */
 struct blk_dax_ctl {
 	sector_t sector;
-	void __pmem *addr;
+	void *addr;
 	long size;
 	pfn_t pfn;
 };
@@ -1670,8 +1670,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	long (*direct_access)(struct block_device *, sector_t, void __pmem **,
-			pfn_t *, long);
+	long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *,
+			long);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 793c0829e3a3..b966974938ed 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -17,7 +17,6 @@
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu	__attribute__((noderef, address_space(3)))
-# define __pmem		__attribute__((noderef, address_space(5)))
 #ifdef CONFIG_SPARSE_RCU_POINTER
 # define __rcu		__attribute__((noderef, address_space(4)))
 #else /* CONFIG_SPARSE_RCU_POINTER */
@@ -45,7 +44,6 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __cond_lock(x,c) (c)
 # define __percpu
 # define __rcu
-# define __pmem
 # define __private
 # define ACCESS_PRIVATE(p, member) ((p)->member)
 #endif /* __CHECKER__ */
diff --git a/include/linux/nd.h b/include/linux/nd.h
index 1ecd64643512..f1ea426d6a5e 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -68,7 +68,7 @@ struct nd_namespace_io {
 	struct nd_namespace_common common;
 	struct resource res;
 	resource_size_t size;
-	void __pmem *addr;
+	void *addr;
 	struct badblocks bb;
 };
 
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index 9e3ea94b8157..e856c2cb0fe8 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -26,37 +26,35 @@
  * calling these symbols with arch_has_pmem_api() and redirect to the
  * implementation in asm/pmem.h.
  */
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t n)
+static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
 {
 	BUG();
 }
 
-static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src,
-		size_t n)
+static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
 {
 	BUG();
 	return -EFAULT;
 }
 
-static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 		struct iov_iter *i)
 {
 	BUG();
 	return 0;
 }
 
-static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+static inline void arch_clear_pmem(void *addr, size_t size)
 {
 	BUG();
 }
 
-static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
+static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	BUG();
 }
 
-static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+static inline void arch_invalidate_pmem(void *addr, size_t size)
 {
 	BUG();
 }
@@ -67,13 +65,6 @@ static inline bool arch_has_pmem_api(void)
 	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API);
 }
 
-static inline int default_memcpy_from_pmem(void *dst, void __pmem const *src,
-		size_t size)
-{
-	memcpy(dst, (void __force *) src, size);
-	return 0;
-}
-
 /*
  * memcpy_from_pmem - read from persistent memory with error handling
  * @dst: destination buffer
@@ -82,40 +73,13 @@ static inline int default_memcpy_from_pmem(void *dst, void __pmem const *src,
  *
  * Returns 0 on success negative error code on failure.
  */
-static inline int memcpy_from_pmem(void *dst, void __pmem const *src,
-		size_t size)
+static inline int memcpy_from_pmem(void *dst, void const *src, size_t size)
 {
 	if (arch_has_pmem_api())
 		return arch_memcpy_from_pmem(dst, src, size);
 	else
-		return default_memcpy_from_pmem(dst, src, size);
-}
-
-/*
- * These defaults seek to offer decent performance and minimize the
- * window between i/o completion and writes being durable on media.
- * However, it is undefined / architecture specific whether
- * ARCH_MEMREMAP_PMEM + default_memcpy_to_pmem is sufficient for
- * making data durable relative to i/o completion.
- */
-static inline void default_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t size)
-{
-	memcpy((void __force *) dst, src, size);
-}
-
-static inline size_t default_copy_from_iter_pmem(void __pmem *addr,
-		size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter_nocache((void __force *)addr, bytes, i);
-}
-
-static inline void default_clear_pmem(void __pmem *addr, size_t size)
-{
-	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
-		clear_page((void __force *)addr);
-	else
-		memset((void __force *)addr, 0, size);
+		memcpy(dst, src, size);
+	return 0;
 }
 
 /**
@@ -130,12 +94,12 @@ static inline void default_clear_pmem(void __pmem *addr, size_t size)
  * data may still reside in cpu or platform buffers, so this operation
  * must be followed by a blkdev_issue_flush() on the pmem block device.
  */
-static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n)
+static inline void memcpy_to_pmem(void *dst, const void *src, size_t n)
 {
 	if (arch_has_pmem_api())
 		arch_memcpy_to_pmem(dst, src, n);
 	else
-		default_memcpy_to_pmem(dst, src, n);
+		memcpy(dst, src, n);
 }
 
 /**
@@ -147,12 +111,12 @@ static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n)
  * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
  * See blkdev_issue_flush() note for memcpy_to_pmem().
  */
-static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+static inline size_t copy_from_iter_pmem(void *addr, size_t bytes,
 		struct iov_iter *i)
 {
 	if (arch_has_pmem_api())
 		return arch_copy_from_iter_pmem(addr, bytes, i);
-	return default_copy_from_iter_pmem(addr, bytes, i);
+	return copy_from_iter_nocache(addr, bytes, i);
 }
 
 /**
@@ -163,12 +127,12 @@ static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes,
  * Write zeros into the memory range starting at 'addr' for 'size' bytes.
  * See blkdev_issue_flush() note for memcpy_to_pmem().
  */
-static inline void clear_pmem(void __pmem *addr, size_t size)
+static inline void clear_pmem(void *addr, size_t size)
 {
 	if (arch_has_pmem_api())
 		arch_clear_pmem(addr, size);
 	else
-		default_clear_pmem(addr, size);
+		memset(addr, 0, size);
 }
 
 /**
@@ -179,7 +143,7 @@ static inline void clear_pmem(void __pmem *addr, size_t size)
  * For platforms that support clearing poison this flushes any poisoned
  * ranges out of the cache
  */
-static inline void invalidate_pmem(void __pmem *addr, size_t size)
+static inline void invalidate_pmem(void *addr, size_t size)
 {
 	if (arch_has_pmem_api())
 		arch_invalidate_pmem(addr, size);
@@ -193,7 +157,7 @@ static inline void invalidate_pmem(void __pmem *addr, size_t size)
  * Write back the processor cache range starting at 'addr' for 'size' bytes.
  * See blkdev_issue_flush() note for memcpy_to_pmem().
  */
-static inline void wb_cache_pmem(void __pmem *addr, size_t size)
+static inline void wb_cache_pmem(void *addr, size_t size)
 {
 	if (arch_has_pmem_api())
 		arch_wb_cache_pmem(addr, size);
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4904ced676d4..24a08363995a 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -313,7 +313,6 @@ our $Sparse	= qr{
 			__kernel|
 			__force|
 			__iomem|
-			__pmem|
 			__must_check|
 			__init_refok|
 			__kprobes|
diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
index 1e0218ce6a8b..c9b8c48f85fc 100644
--- a/tools/testing/nvdimm/pmem-dax.c
+++ b/tools/testing/nvdimm/pmem-dax.c
@@ -16,7 +16,7 @@
 #include <nd.h>
 
 long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		void __pmem **kaddr, pfn_t *pfn, long size)
+		void **kaddr, pfn_t *pfn, long size)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	resource_size_t offset = sector * 512 + pmem->data_offset;
-- 
cgit v1.2.3


From e950fdf71c9b4a6b63b58fed78956a96cc907402 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jul 2016 11:23:33 +0200
Subject: block: introduce BLKDEV_DISCARD_ZERO to fix zeroout

Currently blkdev_issue_zeroout cascades down from discards (if the driver
guarantees that discards zero data), to WRITE SAME and then to a loop
writing zeroes.  Unfortunately we ignore run-time EOPNOTSUPP errors in the
block layer blkdev_issue_discard helper to work around DM volumes that
may have mixed discard support underneath.

This patch intoroduces a new BLKDEV_DISCARD_ZERO flag to
blkdev_issue_discard that indicates we are called for zeroing operation.
This allows both to ignore the EOPNOTSUPP hack and actually consolidating
the discard_zeroes_data check into the function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-lib.c        | 17 +++++++++++------
 include/linux/blkdev.h |  4 +++-
 2 files changed, 14 insertions(+), 7 deletions(-)

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

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 78626c2fde33..45b35b15496f 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -36,12 +36,17 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -ENXIO;
 
 	if (flags & BLKDEV_DISCARD_SECURE) {
+		if (flags & BLKDEV_DISCARD_ZERO)
+			return -EOPNOTSUPP;
 		if (!blk_queue_secure_erase(q))
 			return -EOPNOTSUPP;
 		op = REQ_OP_SECURE_ERASE;
 	} else {
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
+		if ((flags & BLKDEV_DISCARD_ZERO) &&
+		    !q->limits.discard_zeroes_data)
+			return -EOPNOTSUPP;
 		op = REQ_OP_DISCARD;
 	}
 
@@ -116,7 +121,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			&bio);
 	if (!ret && bio) {
 		ret = submit_bio_wait(bio);
-		if (ret == -EOPNOTSUPP)
+		if (ret == -EOPNOTSUPP && !(flags & BLKDEV_DISCARD_ZERO))
 			ret = 0;
 	}
 	blk_finish_plug(&plug);
@@ -241,11 +246,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data &&
-	    blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0) == 0)
-		return 0;
+	if (discard) {
+		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
+				BLKDEV_DISCARD_ZERO))
+			return 0;
+	}
 
 	if (bdev_write_same(bdev) &&
 	    blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 53fee6123893..156455cb07ad 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1137,7 +1137,9 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 	return bqt->tag_index[tag];
 }
 
-#define BLKDEV_DISCARD_SECURE  0x01    /* secure discard */
+
+#define BLKDEV_DISCARD_SECURE	(1 << 0)	/* issue a secure erase */
+#define BLKDEV_DISCARD_ZERO	(1 << 1)	/* must reliably zero data */
 
 extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
-- 
cgit v1.2.3


From 98d61d5b1a65a9df7cb3d9605f5d37d3dbbb4b5e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jul 2016 11:31:51 +0200
Subject: block: simplify and export blk_rq_append_bio

The target SCSI passthrough backend is much better served with the low-level
blk_rq_append_bio construct then the helpers built on top of it, so export it.

Also use the opportunity to remove the pointless request_queue argument and
make the code flow a little more readable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c       |  2 +-
 block/blk-map.c        | 25 +++++++++++++++----------
 block/blk.h            |  2 --
 include/linux/blkdev.h |  1 +
 4 files changed, 17 insertions(+), 13 deletions(-)

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

diff --git a/block/blk-core.c b/block/blk-core.c
index 4d8794925fe9..a2230186c36d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1363,7 +1363,7 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 		int ret;
 
 		blk_queue_bounce(q, &bounce_bio);
-		ret = blk_rq_append_bio(q, rq, bounce_bio);
+		ret = blk_rq_append_bio(rq, bounce_bio);
 		if (unlikely(ret)) {
 			blk_put_request(rq);
 			return ERR_PTR(ret);
diff --git a/block/blk-map.c b/block/blk-map.c
index 61733a660c3a..b8657fa8dc9a 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -9,21 +9,26 @@
 
 #include "blk.h"
 
-int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-		      struct bio *bio)
+/*
+ * Append a bio to a passthrough request.  Only works can be merged into
+ * the request based on the driver constraints.
+ */
+int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
-	if (!rq->bio)
-		blk_rq_bio_prep(q, rq, bio);
-	else if (!ll_back_merge_fn(q, rq, bio))
-		return -EINVAL;
-	else {
+	if (!rq->bio) {
+		blk_rq_bio_prep(rq->q, rq, bio);
+	} else {
+		if (!ll_back_merge_fn(rq->q, rq, bio))
+			return -EINVAL;
+
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
-
 		rq->__data_len += bio->bi_iter.bi_size;
 	}
+
 	return 0;
 }
+EXPORT_SYMBOL(blk_rq_append_bio);
 
 static int __blk_rq_unmap_user(struct bio *bio)
 {
@@ -71,7 +76,7 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	 */
 	bio_get(bio);
 
-	ret = blk_rq_append_bio(q, rq, bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (ret) {
 		bio_endio(bio);
 		__blk_rq_unmap_user(orig_bio);
@@ -229,7 +234,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (do_copy)
 		rq->cmd_flags |= REQ_COPY_USER;
 
-	ret = blk_rq_append_bio(q, rq, bio);
+	ret = blk_rq_append_bio(rq, bio);
 	if (unlikely(ret)) {
 		/* request is too big */
 		bio_put(bio);
diff --git a/block/blk.h b/block/blk.h
index 70e4aee9cdcb..c37492f5edaa 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -64,8 +64,6 @@ void blk_exit_rl(struct request_list *rl);
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
-int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-		      struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
 void blk_queue_bypass_end(struct request_queue *q);
 void blk_dequeue_request(struct request *rq);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 156455cb07ad..706c8bf61c84 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -802,6 +802,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
+extern int blk_rq_append_bio(struct request *rq, struct bio *bio);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
 extern void blk_queue_split(struct request_queue *, struct bio **,
 			    struct bio_set *);
-- 
cgit v1.2.3


From 4613c5f1df92f3cb5a8f89c7dfefc37402c16bd8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jul 2016 11:31:53 +0200
Subject: scsi/osd: open code blk_make_request

I wish the OSD code could simply use blk_rq_map_* helpers like
everyone else, but the complex nature of deciding if we have
DATA IN and/or DATA OUT buffers might make this impossible
(at least for a mere human like me).

But using blk_rq_append_bio at least allows sharing the setup code
between request with or without dat a buffers, and given that this
is the last user of blk_make_request it allows getting rid of that
somewhat awkward interface.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Boaz Harrosh <ooo@electrozaur.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c                 | 57 ----------------------------------------
 drivers/scsi/osd/osd_initiator.c | 25 +++++++++++-------
 include/linux/blkdev.h           |  2 --
 3 files changed, 16 insertions(+), 68 deletions(-)

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

diff --git a/block/blk-core.c b/block/blk-core.c
index a2230186c36d..91b339f4d2ad 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1317,63 +1317,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_get_request);
 
-/**
- * blk_make_request - given a bio, allocate a corresponding struct request.
- * @q: target request queue
- * @bio:  The bio describing the memory mappings that will be submitted for IO.
- *        It may be a chained-bio properly constructed by block/bio layer.
- * @gfp_mask: gfp flags to be used for memory allocation
- *
- * blk_make_request is the parallel of generic_make_request for BLOCK_PC
- * type commands. Where the struct request needs to be farther initialized by
- * the caller. It is passed a &struct bio, which describes the memory info of
- * the I/O transfer.
- *
- * The caller of blk_make_request must make sure that bi_io_vec
- * are set to describe the memory buffers. That bio_data_dir() will return
- * the needed direction of the request. (And all bio's in the passed bio-chain
- * are properly set accordingly)
- *
- * If called under none-sleepable conditions, mapped bio buffers must not
- * need bouncing, by calling the appropriate masked or flagged allocator,
- * suitable for the target device. Otherwise the call to blk_queue_bounce will
- * BUG.
- *
- * WARNING: When allocating/cloning a bio-chain, careful consideration should be
- * given to how you allocate bios. In particular, you cannot use
- * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
- * you risk waiting for IO completion of a bio that hasn't been submitted yet,
- * thus resulting in a deadlock. Alternatively bios should be allocated using
- * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock.
- * If possible a big IO should be split into smaller parts when allocation
- * fails. Partial allocation should not be an error, or you risk a live-lock.
- */
-struct request *blk_make_request(struct request_queue *q, struct bio *bio,
-				 gfp_t gfp_mask)
-{
-	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
-
-	if (IS_ERR(rq))
-		return rq;
-
-	blk_rq_set_block_pc(rq);
-
-	for_each_bio(bio) {
-		struct bio *bounce_bio = bio;
-		int ret;
-
-		blk_queue_bounce(q, &bounce_bio);
-		ret = blk_rq_append_bio(rq, bounce_bio);
-		if (unlikely(ret)) {
-			blk_put_request(rq);
-			return ERR_PTR(ret);
-		}
-	}
-
-	return rq;
-}
-EXPORT_SYMBOL(blk_make_request);
-
 /**
  * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
  * @rq:		request to be initialized
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index daa4dc17f172..2f2a9910e30e 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1558,18 +1558,25 @@ static int _osd_req_finalize_data_integrity(struct osd_request *or,
 static struct request *_make_request(struct request_queue *q, bool has_write,
 			      struct _osd_io_info *oii, gfp_t flags)
 {
-	if (oii->bio)
-		return blk_make_request(q, oii->bio, flags);
-	else {
-		struct request *req;
-
-		req = blk_get_request(q, has_write ? WRITE : READ, flags);
-		if (IS_ERR(req))
-			return req;
+	struct request *req;
+	struct bio *bio = oii->bio;
+	int ret;
 
-		blk_rq_set_block_pc(req);
+	req = blk_get_request(q, has_write ? WRITE : READ, flags);
+	if (IS_ERR(req))
 		return req;
+	blk_rq_set_block_pc(req);
+
+	for_each_bio(bio) {
+		struct bio *bounce_bio = bio;
+
+		blk_queue_bounce(req->q, &bounce_bio);
+		ret = blk_rq_append_bio(req, bounce_bio);
+		if (ret)
+			return ERR_PTR(ret);
 	}
+
+	return req;
 }
 
 static int _init_blk_request(struct osd_request *or,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 706c8bf61c84..0cdea75a6614 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -788,8 +788,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
-extern struct request *blk_make_request(struct request_queue *, struct bio *,
-					gfp_t);
 extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
-- 
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


From 6d25ec147e3a71858bed5439c92accd7f739a0a3 Mon Sep 17 00:00:00 2001
From: John Pittman <jpittman@redhat.com>
Date: Mon, 1 Aug 2016 16:35:53 -0400
Subject: Include: blkdev: Removed duplicate 'struct request;' declaration.

In include/linux/blkdev.h duplicate declarations of the request
struct exist.  Cleaned up by removing the second, unneeded
declaration.

Signed-off-by: John Pittman <jpittman@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/blkdev.h | 1 -
 1 file changed, 1 deletion(-)

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

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index adf33079771e..de7935961c27 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -47,7 +47,6 @@ struct pr_ops;
  */
 #define BLKCG_MAX_POLS		2
 
-struct request;
 typedef void (rq_end_io_fn)(struct request *, int);
 
 #define BLK_RL_SYNCFULL		(1U << 0)
-- 
cgit v1.2.3


From abf545484d31b68777a85c5c8f5b4bcde08283eb Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 4 Aug 2016 14:23:34 -0600
Subject: mm/block: convert rw_page users to bio op use

The rw_page users were not converted to use bio/req ops. As a result
bdev_write_page is not passing down REQ_OP_WRITE and the IOs will
be sent down as reads.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Fixes: 4e1b2d52a80d ("block, fs, drivers: remove REQ_OP compat defs and related code")

Modified by me to:

1) Drop op_flags passing into ->rw_page(), as we don't use it.
2) Make op_is_write() and friends safe to use for !CONFIG_BLOCK

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/brd.c           | 17 +++++++----------
 drivers/block/zram/zram_drv.c | 28 +++++++++++++++-------------
 drivers/nvdimm/btt.c          | 18 +++++++++---------
 drivers/nvdimm/pmem.c         | 12 ++++++------
 fs/block_dev.c                |  7 ++++---
 fs/mpage.c                    |  2 +-
 include/linux/blk_types.h     | 22 +++++++++++-----------
 include/linux/blkdev.h        |  2 +-
 include/linux/fs.h            |  3 ++-
 include/linux/pagemap.h       |  2 +-
 mm/filemap.c                  |  6 +++---
 11 files changed, 60 insertions(+), 59 deletions(-)

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

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 3022dad24071..3439b28cce8b 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -300,20 +300,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, int rw,
+			unsigned int len, unsigned int off, int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (rw != READ) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (rw == READ) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -330,7 +330,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
 	struct brd_device *brd = bdev->bd_disk->private_data;
-	int rw;
 	struct bio_vec bvec;
 	sector_t sector;
 	struct bvec_iter iter;
@@ -347,14 +346,12 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		goto out;
 	}
 
-	rw = bio_data_dir(bio);
-
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len,
-					bvec.bv_offset, rw, sector);
+					bvec.bv_offset, bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -369,11 +366,11 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, int rw)
+		       struct page *page, int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
-	int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, rw, sector);
-	page_endio(page, rw & WRITE, err);
+	int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op, err);
 	return err;
 }
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7454cf188c8e..ca29649c4b08 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -843,15 +843,15 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 }
 
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, int rw)
+			int offset, int op)
 {
 	unsigned long start_time = jiffies;
 	int ret;
 
-	generic_start_io_acct(rw, bvec->bv_len >> SECTOR_SHIFT,
+	generic_start_io_acct(op, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (rw == READ) {
+	if (!op_is_write(op)) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset);
 	} else {
@@ -859,10 +859,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = zram_bvec_write(zram, bvec, index, offset);
 	}
 
-	generic_end_io_acct(rw, &zram->disk->part0, start_time);
+	generic_end_io_acct(op, &zram->disk->part0, start_time);
 
 	if (unlikely(ret)) {
-		if (rw == READ)
+		if (!op_is_write(op))
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -873,7 +873,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 static void __zram_make_request(struct zram *zram, struct bio *bio)
 {
-	int offset, rw;
+	int offset;
 	u32 index;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
@@ -888,7 +888,6 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 		return;
 	}
 
-	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		int max_transfer_size = PAGE_SIZE - offset;
 
@@ -903,15 +902,18 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = max_transfer_size;
 			bv.bv_offset = bvec.bv_offset;
 
-			if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0)
+			if (zram_bvec_rw(zram, &bv, index, offset,
+					 bio_op(bio)) < 0)
 				goto out;
 
 			bv.bv_len = bvec.bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
-			if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
+			if (zram_bvec_rw(zram, &bv, index + 1, 0,
+					 bio_op(bio)) < 0)
 				goto out;
 		} else
-			if (zram_bvec_rw(zram, &bvec, index, offset, rw) < 0)
+			if (zram_bvec_rw(zram, &bvec, index, offset,
+					 bio_op(bio)) < 0)
 				goto out;
 
 		update_position(&index, &offset, &bvec);
@@ -968,7 +970,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, int rw)
+		       struct page *page, int op)
 {
 	int offset, err = -EIO;
 	u32 index;
@@ -992,7 +994,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	err = zram_bvec_rw(zram, &bv, index, offset, rw);
+	err = zram_bvec_rw(zram, &bv, index, offset, op);
 put_zram:
 	zram_meta_put(zram);
 out:
@@ -1005,7 +1007,7 @@ out:
 	 * (e.g., SetPageError, set_page_dirty and extra works).
 	 */
 	if (err == 0)
-		page_endio(page, rw, 0);
+		page_endio(page, op, 0);
 	return err;
 }
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 9dce03f420eb..7cf3bdfaf809 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1133,11 +1133,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			int rw, sector_t sector)
+			int op, sector_t sector)
 {
 	int ret;
 
-	if (rw == READ) {
+	if (!op_is_write(op)) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1155,7 +1155,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 	struct bvec_iter iter;
 	unsigned long start;
 	struct bio_vec bvec;
-	int err = 0, rw;
+	int err = 0;
 	bool do_acct;
 
 	/*
@@ -1170,7 +1170,6 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	do_acct = nd_iostat_start(bio, &start);
-	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 
@@ -1181,11 +1180,12 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		BUG_ON(len % btt->sector_size);
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				rw, iter.bi_sector);
+				  bio_op(bio), iter.bi_sector);
 		if (err) {
 			dev_info(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
-					(rw == READ) ? "READ" : "WRITE",
+					(op_is_write(bio_op(bio))) ? "WRITE" :
+					"READ",
 					(unsigned long long) iter.bi_sector, len);
 			bio->bi_error = err;
 			break;
@@ -1200,12 +1200,12 @@ out:
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, int rw)
+		struct page *page, int op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 
-	btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, rw, sector);
-	page_endio(page, rw & WRITE, 0);
+	btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op, 0);
 	return 0;
 }
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index b511099457db..d64d92481c1d 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -67,7 +67,7 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 }
 
 static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, int rw,
+			unsigned int len, unsigned int off, int op,
 			sector_t sector)
 {
 	int rc = 0;
@@ -79,7 +79,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (rw == READ) {
+	if (!op_is_write(op)) {
 		if (unlikely(bad_pmem))
 			rc = -EIO;
 		else {
@@ -134,7 +134,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, bio_data_dir(bio),
+				bvec.bv_offset, bio_op(bio),
 				iter.bi_sector);
 		if (rc) {
 			bio->bi_error = rc;
@@ -152,12 +152,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, int rw)
+		       struct page *page, int op)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	int rc;
 
-	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, rw, sector);
+	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, op, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -166,7 +166,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, rw & WRITE, 0);
+		page_endio(page, op, 0);
 
 	return rc;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2033a3f91d58..d402899ba135 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -416,7 +416,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	result = blk_queue_enter(bdev->bd_queue, false);
 	if (result)
 		return result;
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_READ);
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
@@ -445,7 +446,6 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 			struct page *page, struct writeback_control *wbc)
 {
 	int result;
-	int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
 
 	if (!ops->rw_page || bdev_get_integrity(bdev))
@@ -455,7 +455,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		return result;
 
 	set_page_writeback(page);
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_WRITE);
 	if (result)
 		end_page_writeback(page);
 	else
diff --git a/fs/mpage.c b/fs/mpage.c
index 2ca1f39c8cba..7a09c55b4bd0 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -50,7 +50,7 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, bio_data_dir(bio), bio->bi_error);
+		page_endio(page, bio_op(bio), bio->bi_error);
 	}
 
 	bio_put(bio);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f254eb264924..14b28ff2caf8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -18,6 +18,17 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 typedef void (bio_destructor_t) (struct bio *);
 
+enum req_op {
+	REQ_OP_READ,
+	REQ_OP_WRITE,
+	REQ_OP_DISCARD,		/* request to discard sectors */
+	REQ_OP_SECURE_ERASE,	/* request to securely erase sectors */
+	REQ_OP_WRITE_SAME,	/* write same block many times */
+	REQ_OP_FLUSH,		/* request for cache flush */
+};
+
+#define REQ_OP_BITS 3
+
 #ifdef CONFIG_BLOCK
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
@@ -228,17 +239,6 @@ enum rq_flag_bits {
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
 
-enum req_op {
-	REQ_OP_READ,
-	REQ_OP_WRITE,
-	REQ_OP_DISCARD,		/* request to discard sectors */
-	REQ_OP_SECURE_ERASE,	/* request to securely erase sectors */
-	REQ_OP_WRITE_SAME,	/* write same block many times */
-	REQ_OP_FLUSH,		/* request for cache flush */
-};
-
-#define REQ_OP_BITS 3
-
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U
 #define BLK_QC_T_SHIFT	16
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index de7935961c27..ccd68c0d01de 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1672,7 +1672,7 @@ struct blk_dax_ctl {
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, int op);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f3f0b4c8e8ac..498255e6914e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2480,12 +2480,13 @@ extern void init_special_inode(struct inode *, umode_t, dev_t);
 extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
-#ifdef CONFIG_BLOCK
 static inline bool op_is_write(unsigned int op)
 {
 	return op == REQ_OP_READ ? false : true;
 }
 
+#ifdef CONFIG_BLOCK
+
 /*
  * return data direction, READ or WRITE
  */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 81363b834900..45786374abbd 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page)
 extern void end_page_writeback(struct page *page);
 void wait_for_stable_page(struct page *page);
 
-void page_endio(struct page *page, int rw, int err);
+void page_endio(struct page *page, int op, int err);
 
 /*
  * Add an arbitrary waiter to a page's wait queue
diff --git a/mm/filemap.c b/mm/filemap.c
index 3083ded98b15..daef091d4c50 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -887,9 +887,9 @@ EXPORT_SYMBOL(end_page_writeback);
  * After completing I/O on a page, call this routine to update the page
  * flags appropriately
  */
-void page_endio(struct page *page, int rw, int err)
+void page_endio(struct page *page, int op, int err)
 {
-	if (rw == READ) {
+	if (!op_is_write(op)) {
 		if (!err) {
 			SetPageUptodate(page);
 		} else {
@@ -897,7 +897,7 @@ void page_endio(struct page *page, int rw, int err)
 			SetPageError(page);
 		}
 		unlock_page(page);
-	} else { /* rw == WRITE */
+	} else {
 		if (err) {
 			SetPageError(page);
 			if (page->mapping)
-- 
cgit v1.2.3


From c11f0c0b5bb949673e4fc16c742f0316ae4ced20 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Fri, 5 Aug 2016 08:11:04 -0600
Subject: block/mm: make bdev_ops->rw_page() take a bool for read/write

Commit abf545484d31 changed it from an 'rw' flags type to the
newer ops based interface, but now we're effectively leaking
some bdev internals to the rest of the kernel. Since we only
care about whether it's a read or a write at that level, just
pass in a bool 'is_write' parameter instead.

Then we can also move op_is_write() and friends back under
CONFIG_BLOCK protection.

Reviewed-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/block/brd.c           | 16 ++++++++--------
 drivers/block/zram/zram_drv.c | 23 ++++++++++++-----------
 drivers/nvdimm/btt.c          | 12 ++++++------
 drivers/nvdimm/pmem.c         | 12 ++++++------
 fs/block_dev.c                |  6 ++----
 fs/mpage.c                    |  2 +-
 include/linux/blk_types.h     | 22 +++++++++++-----------
 include/linux/blkdev.h        |  2 +-
 include/linux/fs.h            |  3 +--
 include/linux/pagemap.h       |  2 +-
 mm/filemap.c                  |  4 ++--
 11 files changed, 51 insertions(+), 53 deletions(-)

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

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 3439b28cce8b..0c76d4016eeb 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -300,20 +300,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, int op,
+			unsigned int len, unsigned int off, bool is_write,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (op_is_write(op)) {
+	if (is_write) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!op_is_write(op)) {
+	if (!is_write) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -350,8 +350,8 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		unsigned int len = bvec.bv_len;
 		int err;
 
-		err = brd_do_bvec(brd, bvec.bv_page, len,
-					bvec.bv_offset, bio_op(bio), sector);
+		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
+					op_is_write(bio_op(bio)), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -366,11 +366,11 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, int op)
+		       struct page *page, bool is_write)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
-	int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
-	page_endio(page, op, err);
+	int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
+	page_endio(page, is_write, err);
 	return err;
 }
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index ca29649c4b08..04365b17ee67 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -843,15 +843,16 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 }
 
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, int op)
+			int offset, bool is_write)
 {
 	unsigned long start_time = jiffies;
+	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
 	int ret;
 
-	generic_start_io_acct(op, bvec->bv_len >> SECTOR_SHIFT,
+	generic_start_io_acct(rw_acct, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (!op_is_write(op)) {
+	if (!is_write) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset);
 	} else {
@@ -859,10 +860,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = zram_bvec_write(zram, bvec, index, offset);
 	}
 
-	generic_end_io_acct(op, &zram->disk->part0, start_time);
+	generic_end_io_acct(rw_acct, &zram->disk->part0, start_time);
 
 	if (unlikely(ret)) {
-		if (!op_is_write(op))
+		if (!is_write)
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -903,17 +904,17 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_offset = bvec.bv_offset;
 
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					 bio_op(bio)) < 0)
+					 op_is_write(bio_op(bio))) < 0)
 				goto out;
 
 			bv.bv_len = bvec.bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
 			if (zram_bvec_rw(zram, &bv, index + 1, 0,
-					 bio_op(bio)) < 0)
+					 op_is_write(bio_op(bio))) < 0)
 				goto out;
 		} else
 			if (zram_bvec_rw(zram, &bvec, index, offset,
-					 bio_op(bio)) < 0)
+					 op_is_write(bio_op(bio))) < 0)
 				goto out;
 
 		update_position(&index, &offset, &bvec);
@@ -970,7 +971,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, int op)
+		       struct page *page, bool is_write)
 {
 	int offset, err = -EIO;
 	u32 index;
@@ -994,7 +995,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	err = zram_bvec_rw(zram, &bv, index, offset, op);
+	err = zram_bvec_rw(zram, &bv, index, offset, is_write);
 put_zram:
 	zram_meta_put(zram);
 out:
@@ -1007,7 +1008,7 @@ out:
 	 * (e.g., SetPageError, set_page_dirty and extra works).
 	 */
 	if (err == 0)
-		page_endio(page, op, 0);
+		page_endio(page, is_write, 0);
 	return err;
 }
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 7cf3bdfaf809..88e91666f145 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1133,11 +1133,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			int op, sector_t sector)
+			bool is_write, sector_t sector)
 {
 	int ret;
 
-	if (!op_is_write(op)) {
+	if (!is_write) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1180,7 +1180,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		BUG_ON(len % btt->sector_size);
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				  bio_op(bio), iter.bi_sector);
+				  op_is_write(bio_op(bio)), iter.bi_sector);
 		if (err) {
 			dev_info(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
@@ -1200,12 +1200,12 @@ out:
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, int op)
+		struct page *page, bool is_write)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 
-	btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, op, sector);
-	page_endio(page, op, 0);
+	btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector);
+	page_endio(page, is_write, 0);
 	return 0;
 }
 
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index d64d92481c1d..20bae50c231d 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -67,7 +67,7 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 }
 
 static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, int op,
+			unsigned int len, unsigned int off, bool is_write,
 			sector_t sector)
 {
 	int rc = 0;
@@ -79,7 +79,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!op_is_write(op)) {
+	if (!is_write) {
 		if (unlikely(bad_pmem))
 			rc = -EIO;
 		else {
@@ -134,7 +134,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, bio_op(bio),
+				bvec.bv_offset, op_is_write(bio_op(bio)),
 				iter.bi_sector);
 		if (rc) {
 			bio->bi_error = rc;
@@ -152,12 +152,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, int op)
+		       struct page *page, bool is_write)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	int rc;
 
-	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, op, sector);
+	rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -166,7 +166,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, op, 0);
+		page_endio(page, is_write, 0);
 
 	return rc;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index d402899ba135..c3cdde87cc8c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -416,8 +416,7 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	result = blk_queue_enter(bdev->bd_queue, false);
 	if (result)
 		return result;
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
-			      REQ_OP_READ);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
@@ -455,8 +454,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		return result;
 
 	set_page_writeback(page);
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
-			      REQ_OP_WRITE);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
 	if (result)
 		end_page_writeback(page);
 	else
diff --git a/fs/mpage.c b/fs/mpage.c
index 7a09c55b4bd0..d2413af0823a 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -50,7 +50,7 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, bio_op(bio), bio->bi_error);
+		page_endio(page, op_is_write(bio_op(bio)), bio->bi_error);
 	}
 
 	bio_put(bio);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 14b28ff2caf8..f254eb264924 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -18,17 +18,6 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 typedef void (bio_destructor_t) (struct bio *);
 
-enum req_op {
-	REQ_OP_READ,
-	REQ_OP_WRITE,
-	REQ_OP_DISCARD,		/* request to discard sectors */
-	REQ_OP_SECURE_ERASE,	/* request to securely erase sectors */
-	REQ_OP_WRITE_SAME,	/* write same block many times */
-	REQ_OP_FLUSH,		/* request for cache flush */
-};
-
-#define REQ_OP_BITS 3
-
 #ifdef CONFIG_BLOCK
 /*
  * main unit of I/O for the block layer and lower layers (ie drivers and
@@ -239,6 +228,17 @@ enum rq_flag_bits {
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
 
+enum req_op {
+	REQ_OP_READ,
+	REQ_OP_WRITE,
+	REQ_OP_DISCARD,		/* request to discard sectors */
+	REQ_OP_SECURE_ERASE,	/* request to securely erase sectors */
+	REQ_OP_WRITE_SAME,	/* write same block many times */
+	REQ_OP_FLUSH,		/* request for cache flush */
+};
+
+#define REQ_OP_BITS 3
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U
 #define BLK_QC_T_SHIFT	16
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ccd68c0d01de..2c210b6a7bcf 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1672,7 +1672,7 @@ struct blk_dax_ctl {
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, int op);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 33f0e96db06f..3523bf62f328 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2480,13 +2480,12 @@ extern void init_special_inode(struct inode *, umode_t, dev_t);
 extern void make_bad_inode(struct inode *);
 extern bool is_bad_inode(struct inode *);
 
+#ifdef CONFIG_BLOCK
 static inline bool op_is_write(unsigned int op)
 {
 	return op == REQ_OP_READ ? false : true;
 }
 
-#ifdef CONFIG_BLOCK
-
 /*
  * return data direction, READ or WRITE
  */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 45786374abbd..66a1260b33de 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page)
 extern void end_page_writeback(struct page *page);
 void wait_for_stable_page(struct page *page);
 
-void page_endio(struct page *page, int op, int err);
+void page_endio(struct page *page, bool is_write, int err);
 
 /*
  * Add an arbitrary waiter to a page's wait queue
diff --git a/mm/filemap.c b/mm/filemap.c
index daef091d4c50..8a287dfc5372 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -887,9 +887,9 @@ EXPORT_SYMBOL(end_page_writeback);
  * After completing I/O on a page, call this routine to update the page
  * flags appropriately
  */
-void page_endio(struct page *page, int op, int err)
+void page_endio(struct page *page, bool is_write, int err)
 {
-	if (!op_is_write(op)) {
+	if (!is_write) {
 		if (!err) {
 			SetPageUptodate(page);
 		} else {
-- 
cgit v1.2.3


From 7afafc8a44bf0ab841b17d450b02aedb3a138985 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 16 Aug 2016 10:59:35 +0300
Subject: block: Fix secure erase

Commit 288dab8a35a0 ("block: add a separate operation type for secure
erase") split REQ_OP_SECURE_ERASE from REQ_OP_DISCARD without considering
all the places REQ_OP_DISCARD was being used to mean either. Fix those.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Fixes: 288dab8a35a0 ("block: add a separate operation type for secure erase")
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/bio.c              | 21 +++++++++++----------
 block/blk-merge.c        | 33 +++++++++++++++++++--------------
 block/elevator.c         |  2 +-
 drivers/mmc/card/block.c |  1 +
 drivers/mmc/card/queue.c |  3 ++-
 drivers/mmc/card/queue.h |  4 +++-
 include/linux/bio.h      | 10 ++++++++--
 include/linux/blkdev.h   |  6 ++++--
 kernel/trace/blktrace.c  |  2 +-
 9 files changed, 50 insertions(+), 32 deletions(-)

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

diff --git a/block/bio.c b/block/bio.c
index f39477538fef..aa7354088008 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
-	if (bio_op(bio) == REQ_OP_DISCARD)
-		goto integrity_clone;
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+		break;
+	case REQ_OP_WRITE_SAME:
 		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		goto integrity_clone;
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
 	}
 
-	bio_for_each_segment(bv, bio_src, iter)
-		bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
 	if (bio_integrity(bio_src)) {
 		int ret;
 
@@ -1788,7 +1789,7 @@ 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_op(bio) == REQ_OP_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		split = bio_clone_bioset(bio, gfp, bs);
 	else
 		split = bio_clone_fast(bio, gfp, bs);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3eec75a9e91d..72627e3cf91e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -172,12 +172,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	struct bio *split, *res;
 	unsigned nsegs;
 
-	if (bio_op(*bio) == REQ_OP_DISCARD)
+	switch (bio_op(*bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
-	else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
+		break;
+	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
-	else
+		break;
+	default:
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+		break;
+	}
 
 	/* physical segments can be figured out during splitting */
 	res = split ? split : *bio;
@@ -213,7 +219,7 @@ 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_op(bio) == REQ_OP_DISCARD)
+	if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
 		return 1;
 
 	if (bio_op(bio) == REQ_OP_WRITE_SAME)
@@ -385,7 +391,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	nsegs = 0;
 	cluster = blk_queue_cluster(q);
 
-	if (bio_op(bio) == REQ_OP_DISCARD) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		/*
 		 * This is a hack - drivers should be neither modifying the
 		 * biovec, nor relying on bi_vcnt - but because of
@@ -393,19 +401,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 		 * a payload we need to set up here (thank you Christoph) and
 		 * bi_vcnt is really the only way of telling if we need to.
 		 */
-
-		if (bio->bi_vcnt)
-			goto single_segment;
-
-		return 0;
-	}
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME) {
-single_segment:
+		if (!bio->bi_vcnt)
+			return 0;
+		/* Fall through */
+	case REQ_OP_WRITE_SAME:
 		*sg = sglist;
 		bvec = bio_iovec(bio);
 		sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
 		return 1;
+	default:
+		break;
 	}
 
 	for_each_bio(bio)
diff --git a/block/elevator.c b/block/elevator.c
index 7096c22041e7..f7d973a56fd7 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -366,7 +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 ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
+		if (req_op(rq) != req_op(pos))
 			break;
 		if (rq_data_dir(rq) != rq_data_dir(pos))
 			break;
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 48a5dd740f3b..82503e6f04b3 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req)
 			break;
 
 		if (req_op(next) == REQ_OP_DISCARD ||
+		    req_op(next) == REQ_OP_SECURE_ERASE ||
 		    req_op(next) == REQ_OP_FLUSH)
 			break;
 
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index bf14642a576a..29578e98603d 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 	/*
 	 * We only like normal block requests and discards.
 	 */
-	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) {
+	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
+	    req_op(req) != REQ_OP_SECURE_ERASE) {
 		blk_dump_rq_flags(req, "MMC bad request");
 		return BLKPREP_KILL;
 	}
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index d62531124d54..fee5e1271465 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -4,7 +4,9 @@
 static inline bool mmc_req_is_special(struct request *req)
 {
 	return req &&
-		(req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
+		(req_op(req) == REQ_OP_FLUSH ||
+		 req_op(req) == REQ_OP_DISCARD ||
+		 req_op(req) == REQ_OP_SECURE_ERASE);
 }
 
 struct request;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 59ffaa68b11b..23ddf4b46a9b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -71,7 +71,8 @@ static inline bool bio_has_data(struct bio *bio)
 {
 	if (bio &&
 	    bio->bi_iter.bi_size &&
-	    bio_op(bio) != REQ_OP_DISCARD)
+	    bio_op(bio) != REQ_OP_DISCARD &&
+	    bio_op(bio) != REQ_OP_SECURE_ERASE)
 		return true;
 
 	return false;
@@ -79,7 +80,9 @@ static inline bool bio_has_data(struct bio *bio)
 
 static inline bool bio_no_advance_iter(struct bio *bio)
 {
-	return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME;
+	return bio_op(bio) == REQ_OP_DISCARD ||
+	       bio_op(bio) == REQ_OP_SECURE_ERASE ||
+	       bio_op(bio) == REQ_OP_WRITE_SAME;
 }
 
 static inline bool bio_is_rw(struct bio *bio)
@@ -199,6 +202,9 @@ static inline unsigned bio_segments(struct bio *bio)
 	if (bio_op(bio) == REQ_OP_DISCARD)
 		return 1;
 
+	if (bio_op(bio) == REQ_OP_SECURE_ERASE)
+		return 1;
+
 	if (bio_op(bio) == REQ_OP_WRITE_SAME)
 		return 1;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2c210b6a7bcf..e79055c8b577 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -882,7 +882,7 @@ 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,
 						     int op)
 {
-	if (unlikely(op == REQ_OP_DISCARD))
+	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
 		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
 	if (unlikely(op == REQ_OP_WRITE_SAME))
@@ -913,7 +913,9 @@ 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 || (req_op(rq) == REQ_OP_DISCARD))
+	if (!q->limits.chunk_sectors ||
+	    req_op(rq) == REQ_OP_DISCARD ||
+	    req_op(rq) == REQ_OP_SECURE_ERASE)
 		return blk_queue_get_max_sectors(q, req_op(rq));
 
 	return min(blk_max_size_offset(q, offset),
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7598e6ca817a..dbafc5df03f3 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(op_flags, META);
 	what |= MASK_TC_BIT(op_flags, PREFLUSH);
 	what |= MASK_TC_BIT(op_flags, FUA);
-	if (op == REQ_OP_DISCARD)
+	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
 		what |= BLK_TC_ACT(BLK_TC_FLUSH);
-- 
cgit v1.2.3