blk-mq: allow software queue to map to multiple hardware queues

The mapping used to be dependent on just the CPU location, but
now it's a tuple of (type, cpu) instead. This is a prep patch
for allowing a single software queue to map to multiple hardware
queues. No functional changes in this patch.

This changes the software queue count to an unsigned short
to save a bit of space. We can still support 64K-1 CPUs,
which should be enough. Add a check to catch a wrap.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq-sched.c

@@ -109,7 +109,7 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
 					  struct blk_mq_ctx *ctx)
 {
-	unsigned idx = ctx->index_hw;
+	unsigned short idx = ctx->index_hw[hctx->type];
 
 	if (++idx == hctx->nr_ctx)
 		idx = 0;

block/blk-mq.c

@@ -75,14 +75,18 @@ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
 static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
 				     struct blk_mq_ctx *ctx)
 {
-	if (!sbitmap_test_bit(&hctx->ctx_map, ctx->index_hw))
+	const int bit = ctx->index_hw[hctx->type];
-		sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw);
+
+	if (!sbitmap_test_bit(&hctx->ctx_map, bit))
+		sbitmap_set_bit(&hctx->ctx_map, bit);
 }
 
 static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 				      struct blk_mq_ctx *ctx)
 {
-	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
+	const int bit = ctx->index_hw[hctx->type];
+
+	sbitmap_clear_bit(&hctx->ctx_map, bit);
 }
 
 struct mq_inflight {
@@ -955,7 +959,7 @@ static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr,
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start)
 {
-	unsigned off = start ? start->index_hw : 0;
+	unsigned off = start ? start->index_hw[hctx->type] : 0;
 	struct dispatch_rq_data data = {
 		.hctx = hctx,
 		.rq   = NULL,
@@ -2343,10 +2347,16 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = blk_mq_map_queue_type(q, 0, i);
-
+		hctx->type = 0;
 		cpumask_set_cpu(i, hctx->cpumask);
-		ctx->index_hw = hctx->nr_ctx;
+		ctx->index_hw[hctx->type] = hctx->nr_ctx;
 		hctx->ctxs[hctx->nr_ctx++] = ctx;
+
+		/*
+		 * If the nr_ctx type overflows, we have exceeded the
+		 * amount of sw queues we can support.
+		 */
+		BUG_ON(!hctx->nr_ctx);
 	}
 
 	mutex_unlock(&q->sysfs_lock);

block/blk-mq.h

@@ -17,7 +17,7 @@ struct blk_mq_ctx {
 	}  ____cacheline_aligned_in_smp;
 
 	unsigned int		cpu;
-	unsigned int		index_hw;
+	unsigned short		index_hw[HCTX_MAX_TYPES];
 
 	/* incremented at dispatch time */
 	unsigned long		rq_dispatched[2];

block/kyber-iosched.c

@@ -576,7 +576,7 @@ static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
 {
 	struct kyber_hctx_data *khd = hctx->sched_data;
 	struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue);
-	struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw];
+	struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw[hctx->type]];
 	unsigned int sched_domain = kyber_sched_domain(bio->bi_opf);
 	struct list_head *rq_list = &kcq->rq_list[sched_domain];
 	bool merged;
@@ -602,7 +602,7 @@ static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
 
 	list_for_each_entry_safe(rq, next, rq_list, queuelist) {
 		unsigned int sched_domain = kyber_sched_domain(rq->cmd_flags);
-		struct kyber_ctx_queue *kcq = &khd->kcqs[rq->mq_ctx->index_hw];
+		struct kyber_ctx_queue *kcq = &khd->kcqs[rq->mq_ctx->index_hw[hctx->type]];
 		struct list_head *head = &kcq->rq_list[sched_domain];
 
 		spin_lock(&kcq->lock);
@@ -611,7 +611,7 @@ static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx,
 		else
 			list_move_tail(&rq->queuelist, head);
 		sbitmap_set_bit(&khd->kcq_map[sched_domain],
-				rq->mq_ctx->index_hw);
+				rq->mq_ctx->index_hw[hctx->type]);
 		blk_mq_sched_request_inserted(rq);
 		spin_unlock(&kcq->lock);
 	}

include/linux/blk-mq.h

@@ -37,7 +37,8 @@ struct blk_mq_hw_ctx {
 	struct blk_mq_ctx	*dispatch_from;
 	unsigned int		dispatch_busy;
 
-	unsigned int		nr_ctx;
+	unsigned short		type;
+	unsigned short		nr_ctx;
 	struct blk_mq_ctx	**ctxs;
 
 	spinlock_t		dispatch_wait_lock;