diff mbox series

[05/16] blk-mq: allow software queue to map to multiple hardware queues

Message ID 20181030183252.17857-6-axboe@kernel.dk (mailing list archive)
State New, archived
Headers show
Series blk-mq: Add support for multiple queue maps | expand

Commit Message

Jens Axboe Oct. 30, 2018, 6:32 p.m. UTC 
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.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c   |  2 +-
 block/blk-mq.c         | 22 ++++++++++++++++------
 block/blk-mq.h         |  2 +-
 block/kyber-iosched.c  |  6 +++---
 include/linux/blk-mq.h |  3 ++-
 5 files changed, 23 insertions(+), 12 deletions(-)

Comments

Sagi Grimberg Oct. 31, 2018, 12:49 a.m. UTC | #1 
> @@ -2342,10 +2346,16 @@ 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);

Was this added because nr_ctx became short? What was the motivation
for that? save space? structure alignment?

Perhaps this should be mentioned in the change log (as it contradicts
that no functional changes exist in this patch). Or, if this can happen
even when 32bit nr_ctx, it should be a separate small patch?
Jens Axboe Oct. 31, 2018, 2:19 p.m. UTC | #2 
On 10/30/18 6:49 PM, Sagi Grimberg wrote:
> 
> 
>> @@ -2342,10 +2346,16 @@ 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);
> 
> Was this added because nr_ctx became short? What was the motivation
> for that? save space? structure alignment?

Right, I made it smaller to not take up more space after this change.
And since it is now smaller, adding a check for wrap seemed like
a good idea.

> Perhaps this should be mentioned in the change log (as it contradicts
> that no functional changes exist in this patch). Or, if this can happen
> even when 32bit nr_ctx, it should be a separate small patch?

Could happen for any type, but more likely now of course. I'll
mention this in the changelog.
diff mbox series

Patch

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 8125e9393ec2..d232ecf3290c 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -110,7 +110,7 @@  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;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e3febb5691c4..34afbad0ebf6 100644
--- a/block/blk-mq.c
+++ b/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))
-		sbitmap_set_bit(&hctx->ctx_map, ctx->index_hw);
+	const int bit = ctx->index_hw[hctx->type];
+
+	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 {
@@ -954,7 +958,7 @@  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,
@@ -2342,10 +2346,16 @@  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);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 6a8f8b60d8ba..1821f448f7c4 100644
--- a/block/blk-mq.h
+++ b/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];
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 728757a34fa0..b824a639d5d4 100644
--- a/block/kyber-iosched.c
+++ b/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);
 	}
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index da88e539601b..466b9202b69c 100644
--- a/include/linux/blk-mq.h
+++ b/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;