block: better op and flags encoding

Now that we don't need the common flags to overflow outside the range
of a 32-bit type we can encode them the same way for both the bio and
request fields. This in addition allows us to place the operation
first (and make some room for more ops while we're at it) and to
stop having to shift around the operation values.

In addition this allows passing around only one value in the block layer
instead of two (and eventuall also in the file systems, but we can do
that later) and thus clean up a lot of code.

Last but not least this allows decreasing the size of the cmd_flags
field in struct request to 32-bits. Various functions passing this
value could also be updated, but I'd like to avoid the churn for now.

Signed-off-by: Christoph Hellwig <[e-mail]>
Signed-off-by: Jens Axboe <[e-mail]>

Documentation/block/biodoc.txt

···
 	struct request_list *rl;
 }
 	
-See the rq_flag_bits definitions for an explanation of the various flags
-available. Some bits are used by the block layer or i/o scheduler.
+See the req_ops and req_flag_bits definitions for an explanation of the various
+flags available. Some bits are used by the block layer or i/o scheduler.
 	
 The behaviour of the various sector counts are almost the same as before,
 except that since we have multi-segment bios, current_nr_sectors refers

block/blk-core.c

···
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
- * @op: REQ_OP_READ/REQ_OP_WRITE
- * @op_flags: rq_flag_bits
+ * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
···
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *__get_request(struct request_list *rl, int op,
-				     int op_flags, struct bio *bio,
-				     gfp_t gfp_mask)
+static struct request *__get_request(struct request_list *rl, unsigned int op,
+		struct bio *bio, gfp_t gfp_mask)
 {
 	struct request_queue *q = rl->q;
 	struct request *rq;
 	struct elevator_type *et = q->elevator->type;
 	struct io_context *ioc = rq_ioc(bio);
 	struct io_cq *icq = NULL;
-	const bool is_sync = rw_is_sync(op, op_flags) != 0;
+	const bool is_sync = op_is_sync(op);
 	int may_queue;
 	req_flags_t rq_flags = RQF_ALLOCED;
 
 	if (unlikely(blk_queue_dying(q)))
 		return ERR_PTR(-ENODEV);
 
-	may_queue = elv_may_queue(q, op, op_flags);
+	may_queue = elv_may_queue(q, op);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
···
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	req_set_op_attrs(rq, op, op_flags);
+	rq->cmd_flags = op;
 	rq->rq_flags = rq_flags;
 
 	/* init elvpriv */
···
 /**
  * get_request - get a free request
  * @q: request_queue to allocate request from
- * @op: REQ_OP_READ/REQ_OP_WRITE
- * @op_flags: rq_flag_bits
+ * @op: operation and flags
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
···
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *get_request(struct request_queue *q, int op,
-				   int op_flags, struct bio *bio,
-				   gfp_t gfp_mask)
+static struct request *get_request(struct request_queue *q, unsigned int op,
+		struct bio *bio, gfp_t gfp_mask)
 {
-	const bool is_sync = rw_is_sync(op, op_flags) != 0;
+	const bool is_sync = op_is_sync(op);
 	DEFINE_WAIT(wait);
 	struct request_list *rl;
 	struct request *rq;
 
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
-	rq = __get_request(rl, op, op_flags, bio, gfp_mask);
+	rq = __get_request(rl, op, bio, gfp_mask);
 	if (!IS_ERR(rq))
 		return rq;
 
···
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, 0, NULL, gfp_mask);
+	rq = get_request(q, rw, NULL, gfp_mask);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
 		return rq;
···
 	 */
 	if (rq_flags & RQF_ALLOCED) {
 		struct request_list *rl = blk_rq_rl(req);
-		bool sync = rw_is_sync(req_op(req), req->cmd_flags);
+		bool sync = op_is_sync(req->cmd_flags);
 
 		BUG_ON(!list_empty(&req->queuelist));
 		BUG_ON(ELV_ON_HASH(req));
···
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
 	req->cmd_type = REQ_TYPE_FS;
-
-	req->cmd_flags |= bio->bi_opf & REQ_COMMON_MASK;
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
···
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
-	const bool sync = !!(bio->bi_opf & REQ_SYNC);
 	struct blk_plug *plug;
-	int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT;
+	int el_ret, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
 	unsigned int request_count = 0;
 
···
 
 get_rq:
 	/*
-	 * This sync check and mask will be re-done in init_request_from_bio(),
-	 * but we need to set it earlier to expose the sync flag to the
-	 * rq allocator and io schedulers.
-	 */
-	if (sync)
-		rw_flags |= REQ_SYNC;
-
-	/*
-	 * Add in META/PRIO flags, if set, before we get to the IO scheduler
-	 */
-	rw_flags |= (bio->bi_opf & (REQ_META | REQ_PRIO));
-
-	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request(q, bio_data_dir(bio), rw_flags, bio, GFP_NOIO);
+	req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
 		bio->bi_error = PTR_ERR(req);
 		bio_endio(bio);
···
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
-	req_set_op(rq, bio_op(bio));
-
 	if (bio_has_data(bio))
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
 
···
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	req_set_op_attrs(dst, req_op(src),
-			 (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE);
+	dst->cmd_flags = src->cmd_flags | REQ_NOMERGE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
···
 
 int __init blk_dev_init(void)
 {
-	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
+	BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS));
+	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
 			FIELD_SIZEOF(struct request, cmd_flags));
+	BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 *
+			FIELD_SIZEOF(struct bio, bi_opf));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",

block/blk-flush.c

···
 	}
 
 	flush_rq->cmd_type = REQ_TYPE_FS;
-	req_set_op_attrs(flush_rq, REQ_OP_FLUSH, WRITE_FLUSH);
+	flush_rq->cmd_flags = REQ_OP_FLUSH | WRITE_FLUSH;
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;

block/blk-lib.c

···
 	struct request_queue *q = bdev_get_queue(bdev);
 	struct bio *bio = *biop;
 	unsigned int granularity;
-	enum req_op op;
+	unsigned int op;
 	int alignment;
 	sector_t bs_mask;
 

block/blk-map.c

···
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
 	if (!rq->bio) {
+		rq->cmd_flags &= REQ_OP_MASK;
+		rq->cmd_flags |= (bio->bi_opf & REQ_OP_MASK);
 		blk_rq_bio_prep(rq->q, rq, bio);
 	} else {
 		if (!ll_back_merge_fn(rq->q, rq, bio))

block/blk-mq.c

···
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, int op,
-			       unsigned int op_flags)
+			       struct request *rq, unsigned int op)
 {
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
 	rq->q = q;
 	rq->mq_ctx = ctx;
-	req_set_op_attrs(rq, op, op_flags);
+	rq->cmd_flags = op;
 	if (blk_queue_io_stat(q))
 		rq->rq_flags |= RQF_IO_STAT;
 	/* do not touch atomic flags, it needs atomic ops against the timer */
···
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[rw_is_sync(op, op_flags)]++;
+	ctx->rq_dispatched[op_is_sync(op)]++;
 }
 
 static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
+__blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op)
 {
 	struct request *rq;
 	unsigned int tag;
···
 		}
 
 		rq->tag = tag;
-		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op, op_flags);
+		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
 		return rq;
 	}
 
···
 	ctx = blk_mq_get_ctx(q);
 	hctx = blk_mq_map_queue(q, ctx->cpu);
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
+	rq = __blk_mq_alloc_request(&alloc_data, rw);
 	blk_mq_put_ctx(ctx);
 
 	if (!rq) {
···
 	ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
 
 	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
+	rq = __blk_mq_alloc_request(&alloc_data, rw);
 	if (!rq) {
 		ret = -EWOULDBLOCK;
 		goto out_queue_exit;
···
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct request *rq;
-	int op = bio_data_dir(bio);
-	int op_flags = 0;
 
 	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
 	hctx = blk_mq_map_queue(q, ctx->cpu);
 
-	if (rw_is_sync(bio_op(bio), bio->bi_opf))
-		op_flags |= REQ_SYNC;
-
-	trace_block_getrq(q, bio, op);
+	trace_block_getrq(q, bio, bio->bi_opf);
 	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
-	rq = __blk_mq_alloc_request(data, op, op_flags);
+	rq = __blk_mq_alloc_request(data, bio->bi_opf);
 
 	data->hctx->queued++;
 	return rq;
···
  */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_mq_alloc_data data;
 	struct request *rq;
···
  */
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
-	const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf);
+	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;

block/cfq-iosched.c

···
 } while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-					    struct cfq_group *curr_cfqg, int op,
-					    int op_flags)
+					    struct cfq_group *curr_cfqg,
+					    unsigned int op)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, 1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, 1);
 	cfqg_stats_end_empty_time(&cfqg->stats);
 	cfqg_stats_set_start_group_wait_time(cfqg, curr_cfqg);
 }
···
 #endif
 }
 
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
-					       int op_flags)
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
+					       unsigned int op)
 {
-	blkg_rwstat_add(&cfqg->stats.queued, op, op_flags, -1);
+	blkg_rwstat_add(&cfqg->stats.queued, op, -1);
 }
 
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
-					       int op_flags)
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
+					       unsigned int op)
 {
-	blkg_rwstat_add(&cfqg->stats.merged, op, op_flags, 1);
+	blkg_rwstat_add(&cfqg->stats.merged, op, 1);
 }
 
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int op,
-			int op_flags)
+			uint64_t start_time, uint64_t io_start_time,
+			unsigned int op)
 {
 	struct cfqg_stats *stats = &cfqg->stats;
 	unsigned long long now = sched_clock();
 
 	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, op, op_flags,
-				now - io_start_time);
+		blkg_rwstat_add(&stats->service_time, op, now - io_start_time);
 	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, op, op_flags,
+		blkg_rwstat_add(&stats->wait_time, op,
 				io_start_time - start_time);
 }
 
···
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 
 static inline void cfqg_stats_update_io_add(struct cfq_group *cfqg,
-			struct cfq_group *curr_cfqg, int op, int op_flags) { }
+			struct cfq_group *curr_cfqg, unsigned int op) { }
 static inline void cfqg_stats_update_timeslice_used(struct cfq_group *cfqg,
 			uint64_t time, unsigned long unaccounted_time) { }
-static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, int op,
-			int op_flags) { }
-static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, int op,
-			int op_flags) { }
+static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg,
+			unsigned int op) { }
+static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg,
+			unsigned int op) { }
 static inline void cfqg_stats_update_completion(struct cfq_group *cfqg,
-			uint64_t start_time, uint64_t io_start_time, int op,
-			int op_flags) { }
+			uint64_t start_time, uint64_t io_start_time,
+			unsigned int op) { }
 
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 
···
 {
 	elv_rb_del(&cfqq->sort_list, rq);
 	cfqq->queued[rq_is_sync(rq)]--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqq->cfqd->serving_group,
-				 req_op(rq), rq->cmd_flags);
+				 rq->cmd_flags);
 }
 
 static struct request *
···
 	cfq_del_rq_rb(rq);
 
 	cfqq->cfqd->rq_queued--;
-	cfqg_stats_update_io_remove(RQ_CFQG(rq), req_op(rq), rq->cmd_flags);
+	cfqg_stats_update_io_remove(RQ_CFQG(rq), rq->cmd_flags);
 	if (rq->cmd_flags & REQ_PRIO) {
 		WARN_ON(!cfqq->prio_pending);
 		cfqq->prio_pending--;
···
 static void cfq_bio_merged(struct request_queue *q, struct request *req,
 				struct bio *bio)
 {
-	cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_opf);
+	cfqg_stats_update_io_merged(RQ_CFQG(req), bio->bi_opf);
 }
 
 static void
···
 	if (cfqq->next_rq == next)
 		cfqq->next_rq = rq;
 	cfq_remove_request(next);
-	cfqg_stats_update_io_merged(RQ_CFQG(rq), req_op(next), next->cmd_flags);
+	cfqg_stats_update_io_merged(RQ_CFQG(rq), next->cmd_flags);
 
 	cfqq = RQ_CFQQ(next);
 	/*
···
 	rq->fifo_time = ktime_get_ns() + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
-	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group, req_op(rq),
+	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
 				 rq->cmd_flags);
 	cfq_rq_enqueued(cfqd, cfqq, rq);
 }
···
 	cfqq->dispatched--;
 	(RQ_CFQG(rq))->dispatched--;
 	cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq),
-				     rq_io_start_time_ns(rq), req_op(rq),
-				     rq->cmd_flags);
+				     rq_io_start_time_ns(rq), rq->cmd_flags);
 
 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;
 
···
 		cfq_schedule_dispatch(cfqd);
 }
 
-static void cfqq_boost_on_prio(struct cfq_queue *cfqq, int op_flags)
+static void cfqq_boost_on_prio(struct cfq_queue *cfqq, unsigned int op)
 {
 	/*
 	 * If REQ_PRIO is set, boost class and prio level, if it's below
 	 * BE/NORM. If prio is not set, restore the potentially boosted
 	 * class/prio level.
 	 */
-	if (!(op_flags & REQ_PRIO)) {
+	if (!(op & REQ_PRIO)) {
 		cfqq->ioprio_class = cfqq->org_ioprio_class;
 		cfqq->ioprio = cfqq->org_ioprio;
 	} else {
···
 	return ELV_MQUEUE_MAY;
 }
 
-static int cfq_may_queue(struct request_queue *q, int op, int op_flags)
+static int cfq_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
···
 	if (!cic)
 		return ELV_MQUEUE_MAY;
 
-	cfqq = cic_to_cfqq(cic, rw_is_sync(op, op_flags));
+	cfqq = cic_to_cfqq(cic, op_is_sync(op));
 	if (cfqq) {
 		cfq_init_prio_data(cfqq, cic);
-		cfqq_boost_on_prio(cfqq, op_flags);
+		cfqq_boost_on_prio(cfqq, op);
 
 		return __cfq_may_queue(cfqq);
 	}

block/elevator.c

···
 		e->type->ops.elevator_put_req_fn(rq);
 }
 
-int elv_may_queue(struct request_queue *q, int op, int op_flags)
+int elv_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct elevator_queue *e = q->elevator;
 
 	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, op, op_flags);
+		return e->type->ops.elevator_may_queue_fn(q, op);
 
 	return ELV_MQUEUE_MAY;
 }

drivers/md/dm-crypt.c

···
 	clone->bi_private = io;
 	clone->bi_end_io  = crypt_endio;
 	clone->bi_bdev    = cc->dev->bdev;
-	bio_set_op_attrs(clone, bio_op(io->base_bio), bio_flags(io->base_bio));
+	clone->bi_opf	  = io->base_bio->bi_opf;
 }
 
 static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)

drivers/scsi/sd.c

···
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
 	} else {
-		scmd_printk(KERN_ERR, SCpnt, "Unknown command %llu,%llx\n",
-			    req_op(rq), (unsigned long long) rq->cmd_flags);
+		scmd_printk(KERN_ERR, SCpnt, "Unknown command %d\n", req_op(rq));
 		goto out;
 	}
 

fs/btrfs/inode.c

···
 	if (!bio)
 		return -ENOMEM;
 
-	bio_set_op_attrs(bio, bio_op(orig_bio), bio_flags(orig_bio));
+	bio->bi_opf = orig_bio->bi_opf;
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
 	btrfs_io_bio(bio)->logical = file_offset;
···
 						  start_sector, GFP_NOFS);
 			if (!bio)
 				goto out_err;
-			bio_set_op_attrs(bio, bio_op(orig_bio),
-					 bio_flags(orig_bio));
+			bio->bi_opf = orig_bio->bi_opf;
 			bio->bi_private = dip;
 			bio->bi_end_io = btrfs_end_dio_bio;
 			btrfs_io_bio(bio)->logical = file_offset;

fs/buffer.c

···
 /**
  * ll_rw_block: low-level access to block devices (DEPRECATED)
  * @op: whether to %READ or %WRITE
- * @op_flags: rq_flag_bits
+ * @op_flags: req_flag_bits
  * @nr: number of &struct buffer_heads in the array
  * @bhs: array of pointers to &struct buffer_head
  *

fs/f2fs/f2fs.h

···
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int op;			/* contains REQ_OP_ */
-	int op_flags;		/* rq_flag_bits */
+	int op_flags;		/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */

fs/gfs2/lops.c

···
  * gfs2_log_flush_bio - Submit any pending log bio
  * @sdp: The superblock
  * @op: REQ_OP
- * @op_flags: rq_flag_bits
+ * @op_flags: req_flag_bits
  *
  * Submit any pending part-built or full bio to the block device. If
  * there is no pending bio, then this is a no-op.

include/linux/blk-cgroup.h

···
 /**
  * blkg_rwstat_add - add a value to a blkg_rwstat
  * @rwstat: target blkg_rwstat
- * @op: REQ_OP
- * @op_flags: rq_flag_bits
+ * @op: REQ_OP and flags
  * @val: value to add
  *
  * Add @val to @rwstat.  The counters are chosen according to @rw.  The
  * caller is responsible for synchronizing calls to this function.
  */
 static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
-				   int op, int op_flags, uint64_t val)
+				   unsigned int op, uint64_t val)
 {
 	struct percpu_counter *cnt;
 
···
 
 	__percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH);
 
-	if (op_flags & REQ_SYNC)
+	if (op & REQ_SYNC)
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC];
···
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_opf,
+		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
 				bio->bi_iter.bi_size);
-		blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_opf, 1);
+		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
 	rcu_read_unlock();

include/linux/blk_types.h

···
 	struct bio_vec		bi_inline_vecs[0];
 };
 
-#define BIO_OP_SHIFT	(8 * FIELD_SIZEOF(struct bio, bi_opf) - REQ_OP_BITS)
-#define bio_flags(bio)	((bio)->bi_opf & ((1 << BIO_OP_SHIFT) - 1))
-#define bio_op(bio)	((bio)->bi_opf >> BIO_OP_SHIFT)
-
-#define bio_set_op_attrs(bio, op, op_flags) do {			\
-	if (__builtin_constant_p(op))					\
-		BUILD_BUG_ON((op) + 0U >= (1U << REQ_OP_BITS));		\
-	else								\
-		WARN_ON_ONCE((op) + 0U >= (1U << REQ_OP_BITS));		\
-	if (__builtin_constant_p(op_flags))				\
-		BUILD_BUG_ON((op_flags) + 0U >= (1U << BIO_OP_SHIFT));	\
-	else								\
-		WARN_ON_ONCE((op_flags) + 0U >= (1U << BIO_OP_SHIFT));	\
-	(bio)->bi_opf = bio_flags(bio);					\
-	(bio)->bi_opf |= (((op) + 0U) << BIO_OP_SHIFT);			\
-	(bio)->bi_opf |= (op_flags);					\
-} while (0)
-
 #define BIO_RESET_BYTES		offsetof(struct bio, bi_max_vecs)
 
 /*
···
 #endif /* CONFIG_BLOCK */
 
 /*
- * Request flags.  For use in the cmd_flags field of struct request, and in
- * bi_opf of struct bio.  Note that some flags are only valid in either one.
+ * Operations and flags common to the bio and request structures.
+ * We use 8 bits for encoding the operation, and the remaining 24 for flags.
  */
-enum rq_flag_bits {
-	/* common flags */
-	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
+#define REQ_OP_BITS	8
+#define REQ_OP_MASK	((1 << REQ_OP_BITS) - 1)
+#define REQ_FLAG_BITS	24
+
+enum req_opf {
+	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 */
+	REQ_OP_ZONE_REPORT,	/* Get zone information */
+	REQ_OP_ZONE_RESET,	/* Reset a zone write pointer */
+
+	REQ_OP_LAST,
+};
+
+enum req_flag_bits {
+	__REQ_FAILFAST_DEV =	/* no driver retries of device errors */
+		REQ_OP_BITS,
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
-
 	__REQ_SYNC,		/* request is sync (sync write or read) */
 	__REQ_META,		/* metadata io request */
 	__REQ_PRIO,		/* boost priority in cfq */
-
 	__REQ_NOMERGE,		/* don't touch this for merging */
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
 	__REQ_INTEGRITY,	/* I/O includes block integrity payload */
 	__REQ_FUA,		/* forced unit access */
 	__REQ_PREFLUSH,		/* request for cache flush */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
-
 	__REQ_NR_BITS,		/* stops here */
 };
 
···
 #define REQ_SYNC		(1ULL << __REQ_SYNC)
 #define REQ_META		(1ULL << __REQ_META)
 #define REQ_PRIO		(1ULL << __REQ_PRIO)
+#define REQ_NOMERGE		(1ULL << __REQ_NOMERGE)
 #define REQ_NOIDLE		(1ULL << __REQ_NOIDLE)
 #define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
+#define REQ_FUA			(1ULL << __REQ_FUA)
+#define REQ_PREFLUSH		(1ULL << __REQ_PREFLUSH)
+#define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
 
 #define REQ_FAILFAST_MASK \
 	(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_INTEGRITY | REQ_NOMERGE | REQ_RAHEAD)
-#define REQ_CLONE_MASK		REQ_COMMON_MASK
 
-/* This mask is used for both bio and request merge checking */
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)
 
-#define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
-#define REQ_FUA			(1ULL << __REQ_FUA)
-#define REQ_NOMERGE		(1ULL << __REQ_NOMERGE)
-#define REQ_PREFLUSH		(1ULL << __REQ_PREFLUSH)
+#define bio_op(bio) \
+	((bio)->bi_opf & REQ_OP_MASK)
+#define req_op(req) \
+	((req)->cmd_flags & REQ_OP_MASK)
 
-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 */
-	REQ_OP_ZONE_REPORT,	/* Get zone information */
-	REQ_OP_ZONE_RESET,	/* Reset a zone write pointer */
-};
+/* obsolete, don't use in new code */
+#define bio_set_op_attrs(bio, op, op_flags) \
+	((bio)->bi_opf |= (op | op_flags))
 
-#define REQ_OP_BITS 3
+static inline bool op_is_sync(unsigned int op)
+{
+	return (op & REQ_OP_MASK) == REQ_OP_READ || (op & REQ_SYNC);
+}
 
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE	-1U

include/linux/blkdev.h

···
 
 	int cpu;
 	unsigned cmd_type;
-	u64 cmd_flags;
+	unsigned int cmd_flags;		/* op and common flags */
 	req_flags_t rq_flags;
 	unsigned long atomic_flags;
 
···
 	/* for bidi */
 	struct request *next_rq;
 };
-
-#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;		\
-} while (0)
 
 static inline unsigned short req_get_ioprio(struct request *req)
 {
···
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
-/*
- * We regard a request as sync, if either a read or a sync write
- */
-static inline bool rw_is_sync(int op, unsigned int rw_flags)
-{
-	return op == REQ_OP_READ || (rw_flags & REQ_SYNC);
-}
-
 static inline bool rq_is_sync(struct request *rq)
 {
-	return rw_is_sync(req_op(rq), rq->cmd_flags);
+	return op_is_sync(rq->cmd_flags);
 }
 
 static inline bool blk_rl_full(struct request_list *rl, bool sync)

include/linux/blktrace_api.h

···
 }
 
 extern void blk_dump_cmd(char *buf, struct request *rq);
-extern void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes);
+extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
 
 #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
 

include/linux/dm-io.h

···
 struct dm_io_client;
 struct dm_io_request {
 	int bi_op;			/* REQ_OP */
-	int bi_op_flags;		/* rq_flag_bits */
+	int bi_op_flags;		/* req_flag_bits */
 	struct dm_io_memory mem;	/* Memory to use for io */
 	struct dm_io_notify notify;	/* Synchronous if notify.fn is NULL */
 	struct dm_io_client *client;	/* Client memory handler */

include/linux/elevator.h

···
 typedef void (elevator_add_req_fn) (struct request_queue *, struct request *);
 typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *);
 typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *);
-typedef int (elevator_may_queue_fn) (struct request_queue *, int, int);
+typedef int (elevator_may_queue_fn) (struct request_queue *, unsigned int);
 
 typedef void (elevator_init_icq_fn) (struct io_cq *);
 typedef void (elevator_exit_icq_fn) (struct io_cq *);
···
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
 extern int elv_register_queue(struct request_queue *q);
 extern void elv_unregister_queue(struct request_queue *q);
-extern int elv_may_queue(struct request_queue *, int, int);
+extern int elv_may_queue(struct request_queue *, unsigned int);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *q, struct request *rq,
 			   struct bio *bio, gfp_t gfp_mask);

include/trace/events/bcache.h

···
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->orig_sector	= bio->bi_iter.bi_sector - 16;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u (from %d,%d @ %llu)",
···
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d  %s %llu + %u",
···
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 		__entry->cache_hit = hit;
 		__entry->bypass = bypass;
 	),
···
 		__entry->inode		= inode;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 		__entry->writeback = writeback;
 		__entry->bypass = bypass;
 	),

include/trace/events/block.h

···
 					0 : blk_rq_sectors(rq);
 		__entry->errors    = rq->errors;
 
-		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags,
-			      blk_rq_bytes(rq));
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 		blk_dump_cmd(__get_str(cmd), rq);
 	),
 
···
 		__entry->nr_sector = nr_bytes >> 9;
 		__entry->errors    = rq->errors;
 
-		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, nr_bytes);
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
 		blk_dump_cmd(__get_str(cmd), rq);
 	),
 
···
 		__entry->bytes     = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
 					blk_rq_bytes(rq) : 0;
 
-		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags,
-			      blk_rq_bytes(rq));
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 		blk_dump_cmd(__get_str(cmd), rq);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
···
 					  bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
···
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->error		= error;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u [%d]",
···
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
···
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
···
 		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio ? bio->bi_iter.bi_sector : 0;
 		__entry->nr_sector	= bio ? bio_sectors(bio) : 0;
-		blk_fill_rwbs(__entry->rwbs, bio ? bio_op(bio) : 0,
+		blk_fill_rwbs(__entry->rwbs,
 			      bio ? bio->bi_opf : 0, __entry->nr_sector);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
         ),
···
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->new_sector	= new_sector;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
···
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
-		blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf,
-			      bio->bi_iter.bi_size);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
 	),
 
 	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
···
 		__entry->old_dev	= dev;
 		__entry->old_sector	= from;
 		__entry->nr_bios	= blk_rq_count_bios(rq);
-		blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags,
-			      blk_rq_bytes(rq));
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
 	),
 
 	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u",

kernel/trace/blktrace.c

···
 	}
 }
 
-void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes)
+void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes)
 {
 	int i = 0;
 
-	if (rw & REQ_PREFLUSH)
+	if (op & REQ_PREFLUSH)
 		rwbs[i++] = 'F';
 
-	switch (op) {
+	switch (op & REQ_OP_MASK) {
 	case REQ_OP_WRITE:
 	case REQ_OP_WRITE_SAME:
 		rwbs[i++] = 'W';
···
 		rwbs[i++] = 'N';
 	}
 
-	if (rw & REQ_FUA)
+	if (op & REQ_FUA)
 		rwbs[i++] = 'F';
-	if (rw & REQ_RAHEAD)
+	if (op & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (rw & REQ_SYNC)
+	if (op & REQ_SYNC)
 		rwbs[i++] = 'S';
-	if (rw & REQ_META)
+	if (op & REQ_META)
 		rwbs[i++] = 'M';
 
 	rwbs[i] = '\0';