blk-mq.c

		__blk_mq_insert_request(hctx, rq, false);
	}
	spin_unlock(&ctx->lock);

	blk_mq_run_hw_queue(hctx, from_schedule);
	blk_mq_put_ctx(current_ctx);
}

static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct request *rqa = container_of(a, struct request, queuelist);
	struct request *rqb = container_of(b, struct request, queuelist);

	return !(rqa->mq_ctx < rqb->mq_ctx ||
		 (rqa->mq_ctx == rqb->mq_ctx &&
		  blk_rq_pos(rqa) < blk_rq_pos(rqb)));
}

void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
	struct blk_mq_ctx *this_ctx;
	struct request_queue *this_q;
	struct request *rq;
	LIST_HEAD(list);
	LIST_HEAD(ctx_list);
	unsigned int depth;

	list_splice_init(&plug->mq_list, &list);

	list_sort(NULL, &list, plug_ctx_cmp);

	this_q = NULL;
	this_ctx = NULL;
	depth = 0;

	while (!list_empty(&list)) {
		rq = list_entry_rq(list.next);
		list_del_init(&rq->queuelist);
		BUG_ON(!rq->q);
		if (rq->mq_ctx != this_ctx) {
			if (this_ctx) {
				blk_mq_insert_requests(this_q, this_ctx,
							&ctx_list, depth,
							from_schedule);
			}

			this_ctx = rq->mq_ctx;
			this_q = rq->q;
			depth = 0;
		}

		depth++;
		list_add_tail(&rq->queuelist, &ctx_list);
	}

	/*
	 * If 'this_ctx' is set, we know we have entries to complete
	 * on 'ctx_list'. Do those.
	 */
	if (this_ctx) {
		blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
				       from_schedule);
	}
}

static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
{
	init_request_from_bio(rq, bio);

	if (blk_do_io_stat(rq))
		blk_account_io_start(rq, 1);
}

static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
{
	return (hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
		!blk_queue_nomerges(hctx->queue);
}

static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
					 struct blk_mq_ctx *ctx,
					 struct request *rq, struct bio *bio)
{
	if (!hctx_allow_merges(hctx)) {
		blk_mq_bio_to_request(rq, bio);
		spin_lock(&ctx->lock);
insert_rq:
		__blk_mq_insert_request(hctx, rq, false);
		spin_unlock(&ctx->lock);
		return false;
	} else {
		struct request_queue *q = hctx->queue;

		spin_lock(&ctx->lock);
		if (!blk_mq_attempt_merge(q, ctx, bio)) {
			blk_mq_bio_to_request(rq, bio);
			goto insert_rq;
		}

		spin_unlock(&ctx->lock);
		__blk_mq_free_request(hctx, ctx, rq);
		return true;
	}
}

struct blk_map_ctx {
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;
};

static struct request *blk_mq_map_request(struct request_queue *q,
					  struct bio *bio,
					  struct blk_map_ctx *data)
{
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;
	struct request *rq;
	int rw = bio_data_dir(bio);
	struct blk_mq_alloc_data alloc_data;

	if (unlikely(blk_mq_queue_enter(q))) {
		bio_endio(bio, -EIO);
		return NULL;
	}

	ctx = blk_mq_get_ctx(q);
	hctx = q->mq_ops->map_queue(q, ctx->cpu);

	if (rw_is_sync(bio->bi_rw))
		rw |= REQ_SYNC;

	trace_block_getrq(q, bio, rw);
	blk_mq_set_alloc_data(&alloc_data, q, GFP_ATOMIC, false, ctx,
			hctx);
	rq = __blk_mq_alloc_request(&alloc_data, rw);
	if (unlikely(!rq)) {
		__blk_mq_run_hw_queue(hctx);
		blk_mq_put_ctx(ctx);
		trace_block_sleeprq(q, bio, rw);

		ctx = blk_mq_get_ctx(q);
		hctx = q->mq_ops->map_queue(q, ctx->cpu);
		blk_mq_set_alloc_data(&alloc_data, q,
				__GFP_WAIT|GFP_ATOMIC, false, ctx, hctx);
		rq = __blk_mq_alloc_request(&alloc_data, rw);
		ctx = alloc_data.ctx;
		hctx = alloc_data.hctx;
	}

	hctx->queued++;
	data->hctx = hctx;
	data->ctx = ctx;
	return rq;
}

/*
 * Multiple hardware queue variant. This will not use per-process plugs,
 * but will attempt to bypass the hctx queueing if we can go straight to
 * hardware for SYNC IO.
 */
static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
{
	const int is_sync = rw_is_sync(bio->bi_rw);
	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
	struct blk_map_ctx data;
	struct request *rq;

	blk_queue_bounce(q, &bio);

	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
		bio_endio(bio, -EIO);
		return;
	}

	rq = blk_mq_map_request(q, bio, &data);
	if (unlikely(!rq))
		return;

	if (unlikely(is_flush_fua)) {
		blk_mq_bio_to_request(rq, bio);
		blk_insert_flush(rq);
		goto run_queue;
	}

	if (is_sync) {
		int ret;

		blk_mq_bio_to_request(rq, bio);

		/*
		 * For OK queue, we are done. For error, kill it. Any other
		 * error (busy), just add it to our list as we previously
		 * would have done
		 */
		ret = q->mq_ops->queue_rq(data.hctx, rq, true);
		if (ret == BLK_MQ_RQ_QUEUE_OK)
			goto done;
		else {
			__blk_mq_requeue_request(rq);

			if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
				rq->errors = -EIO;
				blk_mq_end_io(rq, rq->errors);
				goto done;
			}
		}
	}

	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
		/*
		 * For a SYNC request, send it to the hardware immediately. For
		 * an ASYNC request, just ensure that we run it later on. The
		 * latter allows for merging opportunities and more efficient
		 * dispatching.
		 */
run_queue:
		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
	}
done:
	blk_mq_put_ctx(data.ctx);
}

/*
 * Single hardware queue variant. This will attempt to use any per-process
 * plug for merging and IO deferral.
 */
static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
{
	const int is_sync = rw_is_sync(bio->bi_rw);
	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
	unsigned int use_plug, request_count = 0;
	struct blk_map_ctx data;
	struct request *rq;

	/*
	 * If we have multiple hardware queues, just go directly to
	 * one of those for sync IO.
	 */
	use_plug = !is_flush_fua && !is_sync;

	blk_queue_bounce(q, &bio);

	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
		bio_endio(bio, -EIO);
		return;
	}

	if (use_plug && !blk_queue_nomerges(q) &&
	    blk_attempt_plug_merge(q, bio, &request_count))
		return;

	rq = blk_mq_map_request(q, bio, &data);
	if (unlikely(!rq))
		return;

	if (unlikely(is_flush_fua)) {
		blk_mq_bio_to_request(rq, bio);
		blk_insert_flush(rq);
		goto run_queue;
	}

	/*
	 * A task plug currently exists. Since this is completely lockless,
	 * utilize that to temporarily store requests until the task is
	 * either done or scheduled away.
	 */
	if (use_plug) {
		struct blk_plug *plug = current->plug;

		if (plug) {
			blk_mq_bio_to_request(rq, bio);
			if (list_empty(&plug->mq_list))
				trace_block_plug(q);
			else if (request_count >= BLK_MAX_REQUEST_COUNT) {
				blk_flush_plug_list(plug, false);
				trace_block_plug(q);
			}
			list_add_tail(&rq->queuelist, &plug->mq_list);
			blk_mq_put_ctx(data.ctx);
			return;
		}
	}

	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
		/*
		 * For a SYNC request, send it to the hardware immediately. For
		 * an ASYNC request, just ensure that we run it later on. The
		 * latter allows for merging opportunities and more efficient
		 * dispatching.
		 */
run_queue:
		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
	}

	blk_mq_put_ctx(data.ctx);
}

/*
 * Default mapping to a software queue, since we use one per CPU.
 */
struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, const int cpu)
{
	return q->queue_hw_ctx[q->mq_map[cpu]];
}
EXPORT_SYMBOL(blk_mq_map_queue);

static void blk_mq_free_rq_map(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++) {
			if (!tags->rqs[i])
				continue;
			set->ops->exit_request(set->driver_data, tags->rqs[i],
						hctx_idx, i);
			tags->rqs[i] = NULL;
		}
	}

	while (!list_empty(&tags->page_list)) {
		page = list_first_entry(&tags->page_list, struct page, lru);
		list_del_init(&page->lru);
		__free_pages(page, page->private);
	}

	kfree(tags->rqs);

	blk_mq_free_tags(tags);
}

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

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

	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,
				set->numa_node);
	if (!tags)
		return NULL;

	INIT_LIST_HEAD(&tags->page_list);

	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
				 GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
				 set->numa_node);
	if (!tags->rqs) {
		blk_mq_free_tags(tags);
		return NULL;
	}

	/*
	 * 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 * set->queue_depth;

	for (i = 0; i < set->queue_depth; ) {
		int this_order = max_order;
		struct page *page;
		int to_do;
		void *p;

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

		do {
			page = alloc_pages_node(set->numa_node,
				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
				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);
		entries_per_page = order_to_size(this_order) / rq_size;
		to_do = min(entries_per_page, set->queue_depth - i);
		left -= to_do * rq_size;
		for (j = 0; j < to_do; j++) {
			tags->rqs[i] = p;
			tags->rqs[i]->atomic_flags = 0;
			tags->rqs[i]->cmd_flags = 0;
			if (set->ops->init_request) {
				if (set->ops->init_request(set->driver_data,
						tags->rqs[i], hctx_idx, i,
						set->numa_node)) {
					tags->rqs[i] = NULL;
					goto fail;
				}
			}

			p += rq_size;
			i++;
		}
	}

	return tags;

fail:
	blk_mq_free_rq_map(set, tags, hctx_idx);
	return NULL;
}

static void blk_mq_free_bitmap(struct blk_mq_ctxmap *bitmap)
{
	kfree(bitmap->map);
}

static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node)
{
	unsigned int bpw = 8, total, num_maps, i;

	bitmap->bits_per_word = bpw;

	num_maps = ALIGN(nr_cpu_ids, bpw) / bpw;
	bitmap->map = kzalloc_node(num_maps * sizeof(struct blk_align_bitmap),
					GFP_KERNEL, node);
	if (!bitmap->map)
		return -ENOMEM;

	bitmap->map_size = num_maps;

	total = nr_cpu_ids;
	for (i = 0; i < num_maps; i++) {
		bitmap->map[i].depth = min(total, bitmap->bits_per_word);
		total -= bitmap->map[i].depth;
	}

	return 0;
}

static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
{
	struct request_queue *q = hctx->queue;
	struct blk_mq_ctx *ctx;
	LIST_HEAD(tmp);

	/*
	 * Move ctx entries to new CPU, if this one is going away.
	 */
	ctx = __blk_mq_get_ctx(q, cpu);

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

	if (list_empty(&tmp))
		return NOTIFY_OK;

	ctx = blk_mq_get_ctx(q);
	spin_lock(&ctx->lock);

	while (!list_empty(&tmp)) {
		struct request *rq;

		rq = list_first_entry(&tmp, struct request, queuelist);
		rq->mq_ctx = ctx;
		list_move_tail(&rq->queuelist, &ctx->rq_list);
	}

	hctx = q->mq_ops->map_queue(q, ctx->cpu);
	blk_mq_hctx_mark_pending(hctx, ctx);

	spin_unlock(&ctx->lock);

	blk_mq_run_hw_queue(hctx, true);
	blk_mq_put_ctx(ctx);
	return NOTIFY_OK;
}

static int blk_mq_hctx_cpu_online(struct blk_mq_hw_ctx *hctx, int cpu)
{
	struct request_queue *q = hctx->queue;
	struct blk_mq_tag_set *set = q->tag_set;

	if (set->tags[hctx->queue_num])
		return NOTIFY_OK;

	set->tags[hctx->queue_num] = blk_mq_init_rq_map(set, hctx->queue_num);
	if (!set->tags[hctx->queue_num])
		return NOTIFY_STOP;

	hctx->tags = set->tags[hctx->queue_num];
	return NOTIFY_OK;
}

static int blk_mq_hctx_notify(void *data, unsigned long action,
			      unsigned int cpu)
{
	struct blk_mq_hw_ctx *hctx = data;

	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
		return blk_mq_hctx_cpu_offline(hctx, cpu);
	else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
		return blk_mq_hctx_cpu_online(hctx, cpu);

	return NOTIFY_OK;
}

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_tag_idle(hctx);

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

		blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
		kfree(hctx->ctxs);
		blk_mq_free_bitmap(&hctx->ctx_map);
	}

}

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

	queue_for_each_hw_ctx(q, hctx, i) {
		free_cpumask_var(hctx->cpumask);
		kfree(hctx);
	}
}

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

	/*
	 * Initialize hardware queues
	 */
	queue_for_each_hw_ctx(q, hctx, i) {
		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);
		INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
		spin_lock_init(&hctx->lock);
		INIT_LIST_HEAD(&hctx->dispatch);
		hctx->queue = q;
		hctx->queue_num = i;
		hctx->flags = set->flags;
		hctx->cmd_size = set->cmd_size;

		blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
						blk_mq_hctx_notify, hctx);
		blk_mq_register_cpu_notifier(&hctx->cpu_notifier);

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

		/*
		 * Allocate space for all possible cpus to avoid allocation at
		 * runtime
		 */
		hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
						GFP_KERNEL, node);
		if (!hctx->ctxs)
			break;

		if (blk_mq_alloc_bitmap(&hctx->ctx_map, node))
			break;

		hctx->nr_ctx = 0;

		if (set->ops->init_hctx &&
		    set->ops->init_hctx(hctx, set->driver_data, i))
			break;
	}

	if (i == q->nr_hw_queues)
		return 0;

	/*
	 * Init failed
	 */
	blk_mq_exit_hw_queues(q, set, i);

	return 1;
}

static void blk_mq_init_cpu_queues(struct request_queue *q,
				   unsigned int nr_hw_queues)
{
	unsigned int i;

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

		memset(__ctx, 0, sizeof(*__ctx));
		__ctx->cpu = i;
		spin_lock_init(&__ctx->lock);
		INIT_LIST_HEAD(&__ctx->rq_list);
		__ctx->queue = q;

		/* If the cpu isn't online, the cpu is mapped to first hctx */
		if (!cpu_online(i))
			continue;

		hctx = q->mq_ops->map_queue(q, i);
		cpumask_set_cpu(i, hctx->cpumask);
		hctx->nr_ctx++;

		/*
		 * Set local node, IFF we have more than one hw queue. If
		 * not, we remain on the home node of the device
		 */
		if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE)
			hctx->numa_node = cpu_to_node(i);
	}
}

static void blk_mq_map_swqueue(struct request_queue *q)
{
	unsigned int i;
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;

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

	/*
	 * Map software to hardware queues
	 */
	queue_for_each_ctx(q, ctx, i) {
		/* If the cpu isn't online, the cpu is mapped to first hctx */
		if (!cpu_online(i))
			continue;

		hctx = q->mq_ops->map_queue(q, i);
		cpumask_set_cpu(i, hctx->cpumask);
		ctx->index_hw = hctx->nr_ctx;
		hctx->ctxs[hctx->nr_ctx++] = ctx;
	}

	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) {
			struct blk_mq_tag_set *set = q->tag_set;

			if (set->tags[i]) {
				blk_mq_free_rq_map(set, set->tags[i], i);
				set->tags[i] = NULL;
				hctx->tags = NULL;
			}
			continue;
		}

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

static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set)
{
	struct blk_mq_hw_ctx *hctx;
	struct request_queue *q;
	bool shared;
	int i;

	if (set->tag_list.next == set->tag_list.prev)
		shared = false;
	else
		shared = true;

	list_for_each_entry(q, &set->tag_list, tag_set_list) {
		blk_mq_freeze_queue(q);

		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;
		}
		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_init(&q->tag_set_list);
	blk_mq_update_tag_set_depth(set);
	mutex_unlock(&set->tag_list_lock);
}

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

	mutex_lock(&set->tag_list_lock);
	list_add_tail(&q->tag_set_list, &set->tag_list);
	blk_mq_update_tag_set_depth(set);
	mutex_unlock(&set->tag_list_lock);
}

struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
{
	struct blk_mq_hw_ctx **hctxs;
	struct blk_mq_ctx __percpu *ctx;
	struct request_queue *q;
	unsigned int *map;
	int i;

	ctx = alloc_percpu(struct blk_mq_ctx);
	if (!ctx)
		return ERR_PTR(-ENOMEM);

	hctxs = kmalloc_node(set->nr_hw_queues * sizeof(*hctxs), GFP_KERNEL,
			set->numa_node);

	if (!hctxs)
		goto err_percpu;

	map = blk_mq_make_queue_map(set);
	if (!map)
		goto err_map;

	for (i = 0; i < set->nr_hw_queues; i++) {
		int node = blk_mq_hw_queue_to_node(map, i);

		hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx),
					GFP_KERNEL, node);
		if (!hctxs[i])
			goto err_hctxs;

		if (!zalloc_cpumask_var(&hctxs[i]->cpumask, GFP_KERNEL))
			goto err_hctxs;

		atomic_set(&hctxs[i]->nr_active, 0);
		hctxs[i]->numa_node = node;
		hctxs[i]->queue_num = i;
	}

	q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
	if (!q)
		goto err_hctxs;

	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release))
		goto err_map;

	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
	blk_queue_rq_timeout(q, 30000);

	q->nr_queues = nr_cpu_ids;
	q->nr_hw_queues = set->nr_hw_queues;
	q->mq_map = map;

	q->queue_ctx = ctx;
	q->queue_hw_ctx = hctxs;

	q->mq_ops = set->ops;
	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;

	if (!(set->flags & BLK_MQ_F_SG_MERGE))
		q->queue_flags |= 1 << QUEUE_FLAG_NO_SG_MERGE;

	q->sg_reserved_size = INT_MAX;

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

	if (q->nr_hw_queues > 1)
		blk_queue_make_request(q, blk_mq_make_request);
	else
		blk_queue_make_request(q, blk_sq_make_request);

	blk_queue_rq_timed_out(q, blk_mq_rq_timed_out);
	if (set->timeout)
		blk_queue_rq_timeout(q, set->timeout);

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

	if (set->ops->complete)
		blk_queue_softirq_done(q, set->ops->complete);

	blk_mq_init_flush(q);
	blk_mq_init_cpu_queues(q, set->nr_hw_queues);

	q->flush_rq = kzalloc(round_up(sizeof(struct request) +
				set->cmd_size, cache_line_size()),
				GFP_KERNEL);
	if (!q->flush_rq)
		goto err_hw;

	if (blk_mq_init_hw_queues(q, set))
		goto err_flush_rq;

	mutex_lock(&all_q_mutex);
	list_add_tail(&q->all_q_node, &all_q_list);
	mutex_unlock(&all_q_mutex);

	blk_mq_add_queue_tag_set(set, q);

	blk_mq_map_swqueue(q);

	return q;

err_flush_rq:
	kfree(q->flush_rq);
err_hw:
	blk_cleanup_queue(q);
err_hctxs:
	kfree(map);
	for (i = 0; i < set->nr_hw_queues; i++) {
		if (!hctxs[i])
			break;
		free_cpumask_var(hctxs[i]->cpumask);
		kfree(hctxs[i]);
	}
err_map:
	kfree(hctxs);
err_percpu:
	free_percpu(ctx);
	return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(blk_mq_init_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);
	blk_mq_free_hw_queues(q, set);

	percpu_ref_exit(&q->mq_usage_counter);

	free_percpu(q->queue_ctx);
	kfree(q->queue_hw_ctx);
	kfree(q->mq_map);

	q->queue_ctx = NULL;
	q->queue_hw_ctx = NULL;
	q->mq_map = NULL;

	mutex_lock(&all_q_mutex);
	list_del_init(&q->all_q_node);
	mutex_unlock(&all_q_mutex);
}

/* Basically redo blk_mq_init_queue with queue frozen */
static void blk_mq_queue_reinit(struct request_queue *q)
{
	blk_mq_freeze_queue(q);

	blk_mq_sysfs_unregister(q);

	blk_mq_update_queue_map(q->mq_map, q->nr_hw_queues);

	/*
	 * redo blk_mq_init_cpu_queues and blk_mq_init_hw_queues. FIXME: maybe
	 * we should change hctx numa_node according to new topology (this
	 * involves free and re-allocate memory, worthy doing?)
	 */

	blk_mq_map_swqueue(q);

	blk_mq_sysfs_register(q);

	blk_mq_unfreeze_queue(q);
}

static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
				      unsigned long action, void *hcpu)
{
	struct request_queue *q;

	/*
	 * Before new mappings are established, hotadded cpu might already
	 * start handling requests. This doesn't break anything as we map
	 * offline CPUs to first hardware queue. We will re-init the queue
	 * below to get optimal settings.
	 */
	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN &&
	    action != CPU_ONLINE && action != CPU_ONLINE_FROZEN)
		return NOTIFY_OK;

	mutex_lock(&all_q_mutex);
	list_for_each_entry(q, &all_q_list, all_q_node)
		blk_mq_queue_reinit(q);
	mutex_unlock(&all_q_mutex);
	return NOTIFY_OK;
}

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

	for (i = 0; i < set->nr_hw_queues; i++) {
		set->tags[i] = blk_mq_init_rq_map(set, i);
		if (!set->tags[i])
			goto out_unwind;
	}

	return 0;

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

/*
 * 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 if it too large. In that case, the set
 * value will be stored in set->queue_depth.
 */