blk-mq.c

			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
					&cookie, false, true);
		}
	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
			!data.hctx->dispatch_busy)) {
		blk_mq_put_ctx(data.ctx);
		blk_mq_bio_to_request(rq, bio);
		blk_mq_try_issue_directly(data.hctx, rq, &cookie, false, true);
	} else {
		blk_mq_put_ctx(data.ctx);
		blk_mq_bio_to_request(rq, bio);
		blk_mq_sched_insert_request(rq, false, true, true);
	}

	return cookie;
}

void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
		     unsigned int hctx_idx)
{
	struct page *page;

	if (tags->rqs && set->ops->exit_request) {
		int i;

		for (i = 0; i < tags->nr_tags; i++) {
			struct request *rq = tags->static_rqs[i];

			if (!rq)
				continue;
			set->ops->exit_request(set, rq, hctx_idx);
			tags->static_rqs[i] = NULL;
		}
	}

	while (!list_empty(&tags->page_list)) {
		page = list_first_entry(&tags->page_list, struct page, lru);
		list_del_init(&page->lru);
		/*
		 * Remove kmemleak object previously allocated in
		 * blk_mq_init_rq_map().
		 */
		kmemleak_free(page_address(page));
		__free_pages(page, page->private);
	}
}

void blk_mq_free_rq_map(struct blk_mq_tags *tags)
{
	kfree(tags->rqs);
	tags->rqs = NULL;
	kfree(tags->static_rqs);
	tags->static_rqs = NULL;

	blk_mq_free_tags(tags);
}

struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
					unsigned int hctx_idx,
					unsigned int nr_tags,
					unsigned int reserved_tags)
{
	struct blk_mq_tags *tags;
	int node;

	node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx);
	if (node == NUMA_NO_NODE)
		node = set->numa_node;

	tags = blk_mq_init_tags(nr_tags, reserved_tags, node,
				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
	if (!tags)
		return NULL;

	tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *),
				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
				 node);
	if (!tags->rqs) {
		blk_mq_free_tags(tags);
		return NULL;
	}

	tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *),
					GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
					node);
	if (!tags->static_rqs) {
		kfree(tags->rqs);
		blk_mq_free_tags(tags);
		return NULL;
	}

	return tags;
}

static size_t order_to_size(unsigned int order)
{
	return (size_t)PAGE_SIZE << order;
}

static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
			       unsigned int hctx_idx, int node)
{
	int ret;

	if (set->ops->init_request) {
		ret = set->ops->init_request(set, rq, hctx_idx, node);
		if (ret)
			return ret;
	}

	WRITE_ONCE(rq->state, MQ_RQ_IDLE);
	return 0;
}

int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
		     unsigned int hctx_idx, unsigned int depth)
{
	unsigned int i, j, entries_per_page, max_order = 4;
	size_t rq_size, left;
	int node;

	node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], hctx_idx);
	if (node == NUMA_NO_NODE)
		node = set->numa_node;

	INIT_LIST_HEAD(&tags->page_list);

	/*
	 * rq_size is the size of the request plus driver payload, rounded
	 * to the cacheline size
	 */
	rq_size = round_up(sizeof(struct request) + set->cmd_size,
				cache_line_size());
	left = rq_size * depth;

	for (i = 0; i < depth; ) {
		int this_order = max_order;
		struct page *page;
		int to_do;
		void *p;

		while (this_order && left < order_to_size(this_order - 1))
			this_order--;

		do {
			page = alloc_pages_node(node,
				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
				this_order);
			if (page)
				break;
			if (!this_order--)
				break;
			if (order_to_size(this_order) < rq_size)
				break;
		} while (1);

		if (!page)
			goto fail;

		page->private = this_order;
		list_add_tail(&page->lru, &tags->page_list);

		p = page_address(page);
		/*
		 * Allow kmemleak to scan these pages as they contain pointers
		 * to additional allocations like via ops->init_request().
		 */
		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
		entries_per_page = order_to_size(this_order) / rq_size;
		to_do = min(entries_per_page, depth - i);
		left -= to_do * rq_size;
		for (j = 0; j < to_do; j++) {
			struct request *rq = p;

			tags->static_rqs[i] = rq;
			if (blk_mq_init_request(set, rq, hctx_idx, node)) {
				tags->static_rqs[i] = NULL;
				goto fail;
			}

			p += rq_size;
			i++;
		}
	}
	return 0;

fail:
	blk_mq_free_rqs(set, tags, hctx_idx);
	return -ENOMEM;
}

/*
 * 'cpu' is going away. splice any existing rq_list entries from this
 * software queue to the hw queue dispatch list, and ensure that it
 * gets run.
 */
static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
{
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;
	LIST_HEAD(tmp);
	enum hctx_type type;

	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
	type = hctx->type;

	spin_lock(&ctx->lock);
	if (!list_empty(&ctx->rq_lists[type])) {
		list_splice_init(&ctx->rq_lists[type], &tmp);
		blk_mq_hctx_clear_pending(hctx, ctx);
	}
	spin_unlock(&ctx->lock);

	if (list_empty(&tmp))
		return 0;

	spin_lock(&hctx->lock);
	list_splice_tail_init(&tmp, &hctx->dispatch);
	spin_unlock(&hctx->lock);

	blk_mq_run_hw_queue(hctx, true);
	return 0;
}

static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
{
	cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
					    &hctx->cpuhp_dead);
}

/* hctx->ctxs will be freed in queue's release handler */
static void blk_mq_exit_hctx(struct request_queue *q,
		struct blk_mq_tag_set *set,
		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
	if (blk_mq_hw_queue_mapped(hctx))
		blk_mq_tag_idle(hctx);

	if (set->ops->exit_request)
		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);

	if (set->ops->exit_hctx)
		set->ops->exit_hctx(hctx, hctx_idx);

	if (hctx->flags & BLK_MQ_F_BLOCKING)
		cleanup_srcu_struct(hctx->srcu);

	blk_mq_remove_cpuhp(hctx);
	blk_free_flush_queue(hctx->fq);
	sbitmap_free(&hctx->ctx_map);
}

static void blk_mq_exit_hw_queues(struct request_queue *q,
		struct blk_mq_tag_set *set, int nr_queue)
{
	struct blk_mq_hw_ctx *hctx;
	unsigned int i;

	queue_for_each_hw_ctx(q, hctx, i) {
		if (i == nr_queue)
			break;
		blk_mq_debugfs_unregister_hctx(hctx);
		blk_mq_exit_hctx(q, set, hctx, i);
	}
}

static int blk_mq_init_hctx(struct request_queue *q,
		struct blk_mq_tag_set *set,
		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
{
	int node;

	node = hctx->numa_node;
	if (node == NUMA_NO_NODE)
		node = hctx->numa_node = set->numa_node;

	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
	spin_lock_init(&hctx->lock);
	INIT_LIST_HEAD(&hctx->dispatch);
	hctx->queue = q;
	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;

	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);

	hctx->tags = set->tags[hctx_idx];

	/*
	 * Allocate space for all possible cpus to avoid allocation at
	 * runtime
	 */
	hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *),
			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node);
	if (!hctx->ctxs)
		goto unregister_cpu_notifier;

	if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8),
				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node))
		goto free_ctxs;

	hctx->nr_ctx = 0;

	spin_lock_init(&hctx->dispatch_wait_lock);
	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);

	if (set->ops->init_hctx &&
	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
		goto free_bitmap;

	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
	if (!hctx->fq)
		goto exit_hctx;

	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
		goto free_fq;

	if (hctx->flags & BLK_MQ_F_BLOCKING)
		init_srcu_struct(hctx->srcu);

	return 0;

 free_fq:
	kfree(hctx->fq);
 exit_hctx:
	if (set->ops->exit_hctx)
		set->ops->exit_hctx(hctx, hctx_idx);
 free_bitmap:
	sbitmap_free(&hctx->ctx_map);
 free_ctxs:
	kfree(hctx->ctxs);
 unregister_cpu_notifier:
	blk_mq_remove_cpuhp(hctx);
	return -1;
}

static void blk_mq_init_cpu_queues(struct request_queue *q,
				   unsigned int nr_hw_queues)
{
	struct blk_mq_tag_set *set = q->tag_set;
	unsigned int i, j;

	for_each_possible_cpu(i) {
		struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i);
		struct blk_mq_hw_ctx *hctx;
		int k;

		__ctx->cpu = i;
		spin_lock_init(&__ctx->lock);
		for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++)
			INIT_LIST_HEAD(&__ctx->rq_lists[k]);

		__ctx->queue = q;

		/*
		 * Set local node, IFF we have more than one hw queue. If
		 * not, we remain on the home node of the device
		 */
		for (j = 0; j < set->nr_maps; j++) {
			hctx = blk_mq_map_queue_type(q, j, i);
			if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
				hctx->numa_node = local_memory_node(cpu_to_node(i));
		}
	}
}

static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
{
	int ret = 0;

	set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
					set->queue_depth, set->reserved_tags);
	if (!set->tags[hctx_idx])
		return false;

	ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx,
				set->queue_depth);
	if (!ret)
		return true;

	blk_mq_free_rq_map(set->tags[hctx_idx]);
	set->tags[hctx_idx] = NULL;
	return false;
}

static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
					 unsigned int hctx_idx)
{
	if (set->tags && set->tags[hctx_idx]) {
		blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
		blk_mq_free_rq_map(set->tags[hctx_idx]);
		set->tags[hctx_idx] = NULL;
	}
}

static void blk_mq_map_swqueue(struct request_queue *q)
{
	unsigned int i, j, hctx_idx;
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;
	struct blk_mq_tag_set *set = q->tag_set;

	/*
	 * Avoid others reading imcomplete hctx->cpumask through sysfs
	 */
	mutex_lock(&q->sysfs_lock);

	queue_for_each_hw_ctx(q, hctx, i) {
		cpumask_clear(hctx->cpumask);
		hctx->nr_ctx = 0;
		hctx->dispatch_from = NULL;
	}

	/*
	 * Map software to hardware queues.
	 *
	 * If the cpu isn't present, the cpu is mapped to first hctx.
	 */
	for_each_possible_cpu(i) {
		hctx_idx = set->map[HCTX_TYPE_DEFAULT].mq_map[i];
		/* unmapped hw queue can be remapped after CPU topo changed */
		if (!set->tags[hctx_idx] &&
		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
			/*
			 * If tags initialization fail for some hctx,
			 * that hctx won't be brought online.  In this
			 * case, remap the current ctx to hctx[0] which
			 * is guaranteed to always have tags allocated
			 */
			set->map[HCTX_TYPE_DEFAULT].mq_map[i] = 0;
		}

		ctx = per_cpu_ptr(q->queue_ctx, i);
		for (j = 0; j < set->nr_maps; j++) {
			if (!set->map[j].nr_queues) {
				ctx->hctxs[j] = blk_mq_map_queue_type(q,
						HCTX_TYPE_DEFAULT, i);
				continue;
			}

			hctx = blk_mq_map_queue_type(q, j, i);
			ctx->hctxs[j] = hctx;
			/*
			 * If the CPU is already set in the mask, then we've
			 * mapped this one already. This can happen if
			 * devices share queues across queue maps.
			 */
			if (cpumask_test_cpu(i, hctx->cpumask))
				continue;

			cpumask_set_cpu(i, hctx->cpumask);
			hctx->type = j;
			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);
		}

		for (; j < HCTX_MAX_TYPES; j++)
			ctx->hctxs[j] = blk_mq_map_queue_type(q,
					HCTX_TYPE_DEFAULT, i);
	}

	mutex_unlock(&q->sysfs_lock);

	queue_for_each_hw_ctx(q, hctx, i) {
		/*
		 * If no software queues are mapped to this hardware queue,
		 * disable it and free the request entries.
		 */
		if (!hctx->nr_ctx) {
			/* Never unmap queue 0.  We need it as a
			 * fallback in case of a new remap fails
			 * allocation
			 */
			if (i && set->tags[i])
				blk_mq_free_map_and_requests(set, i);

			hctx->tags = NULL;
			continue;
		}

		hctx->tags = set->tags[i];
		WARN_ON(!hctx->tags);

		/*
		 * Set the map size to the number of mapped software queues.
		 * This is more accurate and more efficient than looping
		 * over all possibly mapped software queues.
		 */
		sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);

		/*
		 * Initialize batch roundrobin counts
		 */
		hctx->next_cpu = blk_mq_first_mapped_cpu(hctx);
		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
	}
}

/*
 * Caller needs to ensure that we're either frozen/quiesced, or that
 * the queue isn't live yet.
 */
static void queue_set_hctx_shared(struct request_queue *q, bool shared)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i) {
		if (shared)
			hctx->flags |= BLK_MQ_F_TAG_SHARED;
		else
			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
	}
}

static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set,
					bool shared)
{
	struct request_queue *q;

	lockdep_assert_held(&set->tag_list_lock);

	list_for_each_entry(q, &set->tag_list, tag_set_list) {
		blk_mq_freeze_queue(q);
		queue_set_hctx_shared(q, shared);
		blk_mq_unfreeze_queue(q);
	}
}

static void blk_mq_del_queue_tag_set(struct request_queue *q)
{
	struct blk_mq_tag_set *set = q->tag_set;

	mutex_lock(&set->tag_list_lock);
	list_del_rcu(&q->tag_set_list);
	if (list_is_singular(&set->tag_list)) {
		/* just transitioned to unshared */
		set->flags &= ~BLK_MQ_F_TAG_SHARED;
		/* update existing queue */
		blk_mq_update_tag_set_depth(set, false);
	}
	mutex_unlock(&set->tag_list_lock);
	INIT_LIST_HEAD(&q->tag_set_list);
}

static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
				     struct request_queue *q)
{
	mutex_lock(&set->tag_list_lock);

	/*
	 * Check to see if we're transitioning to shared (from 1 to 2 queues).
	 */
	if (!list_empty(&set->tag_list) &&
	    !(set->flags & BLK_MQ_F_TAG_SHARED)) {
		set->flags |= BLK_MQ_F_TAG_SHARED;
		/* update existing queue */
		blk_mq_update_tag_set_depth(set, true);
	}
	if (set->flags & BLK_MQ_F_TAG_SHARED)
		queue_set_hctx_shared(q, true);
	list_add_tail_rcu(&q->tag_set_list, &set->tag_list);

	mutex_unlock(&set->tag_list_lock);
}

/* All allocations will be freed in release handler of q->mq_kobj */
static int blk_mq_alloc_ctxs(struct request_queue *q)
{
	struct blk_mq_ctxs *ctxs;
	int cpu;

	ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL);
	if (!ctxs)
		return -ENOMEM;

	ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx);
	if (!ctxs->queue_ctx)
		goto fail;

	for_each_possible_cpu(cpu) {
		struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu);
		ctx->ctxs = ctxs;
	}

	q->mq_kobj = &ctxs->kobj;
	q->queue_ctx = ctxs->queue_ctx;

	return 0;
 fail:
	kfree(ctxs);
	return -ENOMEM;
}

/*
 * It is the actual release handler for mq, but we do it from
 * request queue's release handler for avoiding use-after-free
 * and headache because q->mq_kobj shouldn't have been introduced,
 * but we can't group ctx/kctx kobj without it.
 */
void blk_mq_release(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	unsigned int i;

	/* hctx kobj stays in hctx */
	queue_for_each_hw_ctx(q, hctx, i) {
		if (!hctx)
			continue;
		kobject_put(&hctx->kobj);
	}

	kfree(q->queue_hw_ctx);

	/*
	 * release .mq_kobj and sw queue's kobject now because
	 * both share lifetime with request queue.
	 */
	blk_mq_sysfs_deinit(q);
}

struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
{
	struct request_queue *uninit_q, *q;

	uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
	if (!uninit_q)
		return ERR_PTR(-ENOMEM);

	q = blk_mq_init_allocated_queue(set, uninit_q);
	if (IS_ERR(q))
		blk_cleanup_queue(uninit_q);

	return q;
}
EXPORT_SYMBOL(blk_mq_init_queue);

/*
 * Helper for setting up a queue with mq ops, given queue depth, and
 * the passed in mq ops flags.
 */
struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set,
					   const struct blk_mq_ops *ops,
					   unsigned int queue_depth,
					   unsigned int set_flags)
{
	struct request_queue *q;
	int ret;

	memset(set, 0, sizeof(*set));
	set->ops = ops;
	set->nr_hw_queues = 1;
	set->nr_maps = 1;
	set->queue_depth = queue_depth;
	set->numa_node = NUMA_NO_NODE;
	set->flags = set_flags;

	ret = blk_mq_alloc_tag_set(set);
	if (ret)
		return ERR_PTR(ret);

	q = blk_mq_init_queue(set);
	if (IS_ERR(q)) {
		blk_mq_free_tag_set(set);
		return q;
	}

	return q;
}
EXPORT_SYMBOL(blk_mq_init_sq_queue);

static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
{
	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);

	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu),
			   __alignof__(struct blk_mq_hw_ctx)) !=
		     sizeof(struct blk_mq_hw_ctx));

	if (tag_set->flags & BLK_MQ_F_BLOCKING)
		hw_ctx_size += sizeof(struct srcu_struct);

	return hw_ctx_size;
}

static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx(
		struct blk_mq_tag_set *set, struct request_queue *q,
		int hctx_idx, int node)
{
	struct blk_mq_hw_ctx *hctx;

	hctx = kzalloc_node(blk_mq_hw_ctx_size(set),
			GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
			node);
	if (!hctx)
		return NULL;

	if (!zalloc_cpumask_var_node(&hctx->cpumask,
				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
				node)) {
		kfree(hctx);
		return NULL;
	}

	atomic_set(&hctx->nr_active, 0);
	hctx->numa_node = node;
	hctx->queue_num = hctx_idx;

	if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) {
		free_cpumask_var(hctx->cpumask);
		kfree(hctx);
		return NULL;
	}
	blk_mq_hctx_kobj_init(hctx);

	return hctx;
}

static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
						struct request_queue *q)
{
	int i, j, end;
	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;

	/* protect against switching io scheduler  */
	mutex_lock(&q->sysfs_lock);
	for (i = 0; i < set->nr_hw_queues; i++) {
		int node;
		struct blk_mq_hw_ctx *hctx;

		node = blk_mq_hw_queue_to_node(&set->map[HCTX_TYPE_DEFAULT], i);
		/*
		 * If the hw queue has been mapped to another numa node,
		 * we need to realloc the hctx. If allocation fails, fallback
		 * to use the previous one.
		 */
		if (hctxs[i] && (hctxs[i]->numa_node == node))
			continue;

		hctx = blk_mq_alloc_and_init_hctx(set, q, i, node);
		if (hctx) {
			if (hctxs[i]) {
				blk_mq_exit_hctx(q, set, hctxs[i], i);
				kobject_put(&hctxs[i]->kobj);
			}
			hctxs[i] = hctx;
		} else {
			if (hctxs[i])
				pr_warn("Allocate new hctx on node %d fails,\
						fallback to previous one on node %d\n",
						node, hctxs[i]->numa_node);
			else
				break;
		}
	}
	/*
	 * Increasing nr_hw_queues fails. Free the newly allocated
	 * hctxs and keep the previous q->nr_hw_queues.
	 */
	if (i != set->nr_hw_queues) {
		j = q->nr_hw_queues;
		end = i;
	} else {
		j = i;
		end = q->nr_hw_queues;
		q->nr_hw_queues = set->nr_hw_queues;
	}

	for (; j < end; j++) {
		struct blk_mq_hw_ctx *hctx = hctxs[j];

		if (hctx) {
			if (hctx->tags)
				blk_mq_free_map_and_requests(set, j);
			blk_mq_exit_hctx(q, set, hctx, j);
			kobject_put(&hctx->kobj);
			hctxs[j] = NULL;

		}
	}
	mutex_unlock(&q->sysfs_lock);
}

/*
 * Maximum number of hardware queues we support. For single sets, we'll never
 * have more than the CPUs (software queues). For multiple sets, the tag_set
 * user may have set ->nr_hw_queues larger.
 */
static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
{
	if (set->nr_maps == 1)
		return nr_cpu_ids;

	return max(set->nr_hw_queues, nr_cpu_ids);
}

struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
						  struct request_queue *q)
{
	/* mark the queue as mq asap */
	q->mq_ops = set->ops;

	q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
					     blk_mq_poll_stats_bkt,
					     BLK_MQ_POLL_STATS_BKTS, q);
	if (!q->poll_cb)
		goto err_exit;

	if (blk_mq_alloc_ctxs(q))
		goto err_exit;

	/* init q->mq_kobj and sw queues' kobjects */
	blk_mq_sysfs_init(q);

	q->nr_queues = nr_hw_queues(set);
	q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)),
						GFP_KERNEL, set->numa_node);
	if (!q->queue_hw_ctx)
		goto err_sys_init;

	blk_mq_realloc_hw_ctxs(set, q);
	if (!q->nr_hw_queues)
		goto err_hctxs;

	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);

	q->tag_set = set;

	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
	if (set->nr_maps > HCTX_TYPE_POLL &&
	    set->map[HCTX_TYPE_POLL].nr_queues)
		blk_queue_flag_set(QUEUE_FLAG_POLL, q);

	q->sg_reserved_size = INT_MAX;

	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
	INIT_LIST_HEAD(&q->requeue_list);
	spin_lock_init(&q->requeue_lock);

	blk_queue_make_request(q, blk_mq_make_request);

	/*
	 * Do this after blk_queue_make_request() overrides it...
	 */
	q->nr_requests = set->queue_depth;

	/*
	 * Default to classic polling
	 */
	q->poll_nsec = BLK_MQ_POLL_CLASSIC;

	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
	blk_mq_add_queue_tag_set(set, q);
	blk_mq_map_swqueue(q);

	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
		int ret;

		ret = elevator_init_mq(q);
		if (ret)
			return ERR_PTR(ret);
	}

	return q;

err_hctxs:
	kfree(q->queue_hw_ctx);
err_sys_init:
	blk_mq_sysfs_deinit(q);
err_exit:
	q->mq_ops = NULL;
	return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(blk_mq_init_allocated_queue);

void blk_mq_free_queue(struct request_queue *q)
{
	struct blk_mq_tag_set	*set = q->tag_set;

	blk_mq_del_queue_tag_set(q);
	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
}

static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
{
	int i;

	for (i = 0; i < set->nr_hw_queues; i++)
		if (!__blk_mq_alloc_rq_map(set, i))
			goto out_unwind;

	return 0;

out_unwind:
	while (--i >= 0)
		blk_mq_free_rq_map(set->tags[i]);

	return -ENOMEM;
}

/*
 * Allocate the request maps associated with this tag_set. Note that this
 * may reduce the depth asked for, if memory is tight. set->queue_depth
 * will be updated to reflect the allocated depth.
 */
static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
{
	unsigned int depth;
	int err;

	depth = set->queue_depth;
	do {
		err = __blk_mq_alloc_rq_maps(set);
		if (!err)
			break;

		set->queue_depth >>= 1;
		if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) {
			err = -ENOMEM;
			break;
		}
	} while (set->queue_depth);

	if (!set->queue_depth || err) {
		pr_err("blk-mq: failed to allocate request map\n");
		return -ENOMEM;
	}

	if (depth != set->queue_depth)
		pr_info("blk-mq: reduced tag depth (%u -> %u)\n",
						depth, set->queue_depth);

	return 0;
}

static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
{
	if (set->ops->map_queues && !is_kdump_kernel()) {
		int i;

		/*
		 * transport .map_queues is usually done in the following
		 * way:
		 *
		 * for (queue = 0; queue < set->nr_hw_queues; queue++) {
		 * 	mask = get_cpu_mask(queue)
		 * 	for_each_cpu(cpu, mask)
		 * 		set->map[x].mq_map[cpu] = queue;
		 * }
		 *
		 * When we need to remap, the table has to be cleared for
		 * killing stale mapping since one CPU may not be mapped
		 * to any hw queue.
		 */
		for (i = 0; i < set->nr_maps; i++)
			blk_mq_clear_mq_map(&set->map[i]);

		return set->ops->map_queues(set);
	} else {
		BUG_ON(set->nr_maps > 1);
		return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
	}
}

/*
 * Alloc a tag set to be associated with one or more request queues.
 * May fail with EINVAL for various error conditions. May adjust the
 * requested depth down, if it's too large. In that case, the set
 * value will be stored in set->queue_depth.
 */
int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
{
	int i, ret;

	BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS);

	if (!set->nr_hw_queues)
		return -EINVAL;
	if (!set->queue_depth)
		return -EINVAL;
	if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
		return -EINVAL;

	if (!set->ops->queue_rq)
		return -EINVAL;

	if (!set->ops->get_budget ^ !set->ops->put_budget)
		return -EINVAL;

	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
		pr_info("blk-mq: reduced tag depth to %u\n",
			BLK_MQ_MAX_DEPTH);