block: remove debugfs blk_mq_ctx dispatched/merged/completed attributes

These were added as part of early days debugging for blk-mq, and they
are not really useful anymore. Rather than spend cycles updating them,
just get rid of them.

As a bonus, this shrinks the per-cpu software queue size from 256b
to 192b. That's a whole cacheline less.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq-debugfs.c

@@ -663,57 +663,6 @@ CTX_RQ_SEQ_OPS(default, HCTX_TYPE_DEFAULT);
 CTX_RQ_SEQ_OPS(read, HCTX_TYPE_READ);
 CTX_RQ_SEQ_OPS(poll, HCTX_TYPE_POLL);
 
-static int ctx_dispatched_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
-	return 0;
-}
-
-static ssize_t ctx_dispatched_write(void *data, const char __user *buf,
-				    size_t count, loff_t *ppos)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
-	return count;
-}
-
-static int ctx_merged_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	seq_printf(m, "%lu\n", ctx->rq_merged);
-	return 0;
-}
-
-static ssize_t ctx_merged_write(void *data, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	ctx->rq_merged = 0;
-	return count;
-}
-
-static int ctx_completed_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
-	return 0;
-}
-
-static ssize_t ctx_completed_write(void *data, const char __user *buf,
-				   size_t count, loff_t *ppos)
-{
-	struct blk_mq_ctx *ctx = data;
-
-	ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
-	return count;
-}
-
 static int blk_mq_debugfs_show(struct seq_file *m, void *v)
 {
 	const struct blk_mq_debugfs_attr *attr = m->private;
@@ -803,9 +752,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
 	{"default_rq_list", 0400, .seq_ops = &ctx_default_rq_list_seq_ops},
 	{"read_rq_list", 0400, .seq_ops = &ctx_read_rq_list_seq_ops},
 	{"poll_rq_list", 0400, .seq_ops = &ctx_poll_rq_list_seq_ops},
-	{"dispatched", 0600, ctx_dispatched_show, ctx_dispatched_write},
-	{"merged", 0600, ctx_merged_show, ctx_merged_write},
-	{"completed", 0600, ctx_completed_show, ctx_completed_write},
 	{},
 };
 

block/blk-mq-sched.c

@@ -387,13 +387,10 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 	 * potentially merge with. Currently includes a hand-wavy stop
 	 * count of 8, to not spend too much time checking for merges.
 	 */
-	if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
-		ctx->rq_merged++;
+	if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs))
 		ret = true;
-	}
 
 	spin_unlock(&ctx->lock);
-
 	return ret;
 }
 

block/blk-mq.c

@@ -359,7 +359,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->end_io = NULL;
 	rq->end_io_data = NULL;
 
-	data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++;
 	blk_crypto_rq_set_defaults(rq);
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* tag was already set */
@@ -595,7 +594,6 @@ static void __blk_mq_free_request(struct request *rq)
 void blk_mq_free_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	if (rq->rq_flags & (RQF_ELVPRIV | RQF_ELV)) {
@@ -609,7 +607,6 @@ void blk_mq_free_request(struct request *rq)
 		}
 	}
 
-	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
 		__blk_mq_dec_active_requests(hctx);
 

block/blk-mq.h

@@ -25,13 +25,6 @@ struct blk_mq_ctx {
 	unsigned short		index_hw[HCTX_MAX_TYPES];
 	struct blk_mq_hw_ctx 	*hctxs[HCTX_MAX_TYPES];
 
-	/* incremented at dispatch time */
-	unsigned long		rq_dispatched[2];
-	unsigned long		rq_merged;
-
-	/* incremented at completion time */
-	unsigned long		____cacheline_aligned_in_smp rq_completed[2];
-
 	struct request_queue	*queue;
 	struct blk_mq_ctxs      *ctxs;
 	struct kobject		kobj;