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 <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

Documentation/block/biodoc.txt

@@ -553,8 +553,8 @@ struct request {
 	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

@@ -1056,8 +1056,7 @@ static struct io_context *rq_ioc(struct bio *bio)
 /**
  * __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
  *
@@ -1068,23 +1067,22 @@ static struct io_context *rq_ioc(struct bio *bio)
  * Returns ERR_PTR on failure, with @q->queue_lock held.
  * Returns request pointer on success, with @q->queue_lock *not held*.
  */
-static struct request *__get_request(struct request_list *rl, int 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;
 
@@ -1154,7 +1152,7 @@ static struct request *__get_request(struct request_list *rl, int op,
 
 	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 */
@@ -1232,8 +1230,7 @@ static struct request *__get_request(struct request_list *rl, int op,
 /**
  * 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
  *
@@ -1244,18 +1241,17 @@ static struct request *__get_request(struct request_list *rl, int op,
  * 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;
 
@@ -1297,7 +1293,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, 0, NULL, gfp_mask);
+	rq = get_request(q, rw, NULL, gfp_mask);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
 		return rq;
@@ -1446,7 +1442,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	 */
 	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));
@@ -1652,8 +1648,6 @@ unsigned int blk_plug_queued_count(struct request_queue *q)
 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;
 
@@ -1665,9 +1659,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 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;
 
@@ -1722,24 +1715,11 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 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);
@@ -2946,8 +2926,6 @@ EXPORT_SYMBOL_GPL(__blk_end_request_err);
 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);
 
@@ -3031,8 +3009,7 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 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);
@@ -3537,8 +3514,11 @@ EXPORT_SYMBOL(blk_set_runtime_active);
 
 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

@@ -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;
-	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

@@ -29,7 +29,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 	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

@@ -16,6 +16,8 @@
 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

@@ -139,14 +139,13 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 EXPORT_SYMBOL(blk_mq_can_queue);
 
 static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, 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 */
@@ -183,11 +182,11 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[rw_is_sync(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;
@@ -202,7 +201,7 @@ __blk_mq_alloc_request(struct blk_mq_alloc_data *data, int op, int op_flags)
 		}
 
 		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;
 	}
 
@@ -225,7 +224,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 	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) {
@@ -277,7 +276,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 	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;
@@ -1196,19 +1195,14 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
 	struct request *rq;
-	int 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;
@@ -1256,7 +1250,7 @@ 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_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;
@@ -1350,7 +1344,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
  */
 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;