blk-mq: Use shared tags for shared sbitmap support

Currently we use separate sbitmap pairs and active_queues atomic_t for
shared sbitmap support.

However a full sets of static requests are used per HW queue, which is
quite wasteful, considering that the total number of requests usable at
any given time across all HW queues is limited by the shared sbitmap depth.

As such, it is considerably more memory efficient in the case of shared
sbitmap to allocate a set of static rqs per tag set or request queue, and
not per HW queue.

So replace the sbitmap pairs and active_queues atomic_t with a shared
tags per tagset and request queue, which will hold a set of shared static
rqs.

Since there is now no valid HW queue index to be passed to the blk_mq_ops
.init and .exit_request callbacks, pass an invalid index token. This
changes the semantics of the APIs, such that the callback would need to
validate the HW queue index before using it. Currently no user of shared
sbitmap actually uses the HW queue index (as would be expected).

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/1633429419-228500-13-git-send-email-john.garry@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 19 insertions, 44 deletions

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index a0ecc6d88f84..0e10e8404bf0 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -26,11 +26,10 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
 	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
 		struct request_queue *q = hctx->queue;
-		struct blk_mq_tag_set *set = q->tag_set;
 
 		if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
 		    !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
-			atomic_inc(&set->active_queues_shared_sbitmap);
+			atomic_inc(&hctx->tags->active_queues);
 	} else {
 		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
 		    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
@@ -57,14 +56,14 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_tags *tags = hctx->tags;
-	struct request_queue *q = hctx->queue;
-	struct blk_mq_tag_set *set = q->tag_set;
 
 	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+
 		if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
 					&q->queue_flags))
 			return;
-		atomic_dec(&set->active_queues_shared_sbitmap);
+		atomic_dec(&tags->active_queues);
 	} else {
 		if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
 			return;
@@ -510,38 +509,10 @@ static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
 	return 0;
 }
 
-int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set)
-{
-	int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags);
-	int i, ret;
-
-	ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags,
-				  set->queue_depth, set->reserved_tags,
-				  set->numa_node, alloc_policy);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		struct blk_mq_tags *tags = set->tags[i];
-
-		tags->bitmap_tags = &set->__bitmap_tags;
-		tags->breserved_tags = &set->__breserved_tags;
-	}
-
-	return 0;
-}
-
-void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set)
-{
-	sbitmap_queue_free(&set->__bitmap_tags);
-	sbitmap_queue_free(&set->__breserved_tags);
-}
-
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 				     unsigned int reserved_tags,
-				     int node, unsigned int flags)
+				     int node, int alloc_policy)
 {
-	int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags);
 	struct blk_mq_tags *tags;
 
 	if (total_tags > BLK_MQ_TAG_MAX) {
@@ -557,9 +528,6 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_reserved_tags = reserved_tags;
 	spin_lock_init(&tags->lock);
 
-	if (blk_mq_is_sbitmap_shared(flags))
-		return tags;
-
 	if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) {
 		kfree(tags);
 		return NULL;
@@ -567,12 +535,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	return tags;
 }
 
-void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags)
+void blk_mq_free_tags(struct blk_mq_tags *tags)
 {
-	if (!blk_mq_is_sbitmap_shared(flags)) {
-		sbitmap_queue_free(tags->bitmap_tags);
-		sbitmap_queue_free(tags->breserved_tags);
-	}
+	sbitmap_queue_free(tags->bitmap_tags);
+	sbitmap_queue_free(tags->breserved_tags);
 	kfree(tags);
 }
 
@@ -603,6 +569,13 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		if (tdepth > MAX_SCHED_RQ)
 			return -EINVAL;
 
+		/*
+		 * Only the sbitmap needs resizing since we allocated the max
+		 * initially.
+		 */
+		if (blk_mq_is_sbitmap_shared(set->flags))
+			return 0;
+
 		new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth);
 		if (!new)
 			return -ENOMEM;
@@ -623,12 +596,14 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 
 void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size)
 {
-	sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags);
+	struct blk_mq_tags *tags = set->shared_sbitmap_tags;
+
+	sbitmap_queue_resize(&tags->__bitmap_tags, size - set->reserved_tags);
 }
 
 void blk_mq_tag_update_sched_shared_sbitmap(struct request_queue *q)
 {
-	sbitmap_queue_resize(&q->sched_bitmap_tags,
+	sbitmap_queue_resize(q->shared_sbitmap_tags->bitmap_tags,
 			     q->nr_requests - q->tag_set->reserved_tags);
 }