1 files changed, 69 insertions, 104 deletions

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 2cafcf11ee8b..33946cdb5716 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -8,6 +8,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <linux/delay.h>
 #include "blk.h"
@@ -190,8 +193,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		sbitmap_finish_wait(bt, ws, &wait);
 
 		data->ctx = blk_mq_get_ctx(data->q);
-		data->hctx = blk_mq_map_queue(data->q, data->cmd_flags,
-						data->ctx);
+		data->hctx = blk_mq_map_queue(data->cmd_flags, data->ctx);
 		tags = blk_mq_tags_from_data(data);
 		if (data->flags & BLK_MQ_REQ_RESERVED)
 			bt = &tags->breserved_tags;
@@ -254,13 +256,10 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 		unsigned int bitnr)
 {
 	struct request *rq;
-	unsigned long flags;
 
-	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
 	if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq))
 		rq = NULL;
-	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;
 }
 
@@ -298,15 +297,15 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 /**
  * bt_for_each - iterate over the requests associated with a hardware queue
  * @hctx:	Hardware queue to examine.
- * @q:		Request queue to examine.
+ * @q:		Request queue @hctx is associated with (@hctx->queue).
  * @bt:		sbitmap to examine. This is either the breserved_tags member
  *		or the bitmap_tags member of struct blk_mq_tags.
  * @fn:		Pointer to the function that will be called for each request
  *		associated with @hctx that has been assigned a driver tag.
- *		@fn will be called as follows: @fn(@hctx, rq, @data, @reserved)
- *		where rq is a pointer to a request. Return true to continue
- *		iterating tags, false to stop.
- * @data:	Will be passed as third argument to @fn.
+ *		@fn will be called as follows: @fn(rq, @data) where rq is a
+ *		pointer to a request. Return %true to continue iterating tags;
+ *		%false to stop.
+ * @data:	Will be passed as second argument to @fn.
  * @reserved:	Indicates whether @bt is the breserved_tags member or the
  *		bitmap_tags member of struct blk_mq_tags.
  */
@@ -372,9 +371,9 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
  * @bt:		sbitmap to examine. This is either the breserved_tags member
  *		or the bitmap_tags member of struct blk_mq_tags.
  * @fn:		Pointer to the function that will be called for each started
- *		request. @fn will be called as follows: @fn(rq, @data,
- *		@reserved) where rq is a pointer to a request. Return true
- *		to continue iterating tags, false to stop.
+ *		request. @fn will be called as follows: @fn(rq, @data) where rq
+ *		is a pointer to a request. Return %true to continue iterating
+ *		tags; %false to stop.
  * @data:	Will be passed as second argument to @fn.
  * @flags:	BT_TAG_ITER_*
  */
@@ -407,10 +406,9 @@ static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags,
  * blk_mq_all_tag_iter - iterate over all requests in a tag map
  * @tags:	Tag map to iterate over.
  * @fn:		Pointer to the function that will be called for each
- *		request. @fn will be called as follows: @fn(rq, @priv,
- *		reserved) where rq is a pointer to a request. 'reserved'
- *		indicates whether or not @rq is a reserved request. Return
- *		true to continue iterating tags, false to stop.
+ *		request. @fn will be called as follows: @fn(rq, @priv) where rq
+ *		is a pointer to a request. Return %true to continue iterating
+ *		tags; %false to stop.
  * @priv:	Will be passed as second argument to @fn.
  *
  * Caller has to pass the tag map from which requests are allocated.
@@ -425,10 +423,9 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
  * blk_mq_tagset_busy_iter - iterate over all started requests in a tag set
  * @tagset:	Tag set to iterate over.
  * @fn:		Pointer to the function that will be called for each started
- *		request. @fn will be called as follows: @fn(rq, @priv,
- *		reserved) where rq is a pointer to a request. 'reserved'
- *		indicates whether or not @rq is a reserved request. Return
- *		true to continue iterating tags, false to stop.
+ *		request. @fn will be called as follows: @fn(rq, @priv) where
+ *		rq is a pointer to a request. Return true to continue iterating
+ *		tags, false to stop.
  * @priv:	Will be passed as second argument to @fn.
  *
  * We grab one request reference before calling @fn and release it after
@@ -438,7 +435,9 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv)
 {
 	unsigned int flags = tagset->flags;
-	int i, nr_tags;
+	int i, nr_tags, srcu_idx;
+
+	srcu_idx = srcu_read_lock(&tagset->tags_srcu);
 
 	nr_tags = blk_mq_is_shared_tags(flags) ? 1 : tagset->nr_hw_queues;
 
@@ -447,6 +446,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 			__blk_mq_all_tag_iter(tagset->tags[i], fn, priv,
 					      BT_TAG_ITER_STARTED);
 	}
+	srcu_read_unlock(&tagset->tags_srcu, srcu_idx);
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
@@ -484,11 +484,10 @@ EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
  * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag
  * @q:		Request queue to examine.
  * @fn:		Pointer to the function that will be called for each request
- *		on @q. @fn will be called as follows: @fn(hctx, rq, @priv,
- *		reserved) where rq is a pointer to a request and hctx points
- *		to the hardware queue associated with the request. 'reserved'
- *		indicates whether or not @rq is a reserved request.
- * @priv:	Will be passed as third argument to @fn.
+ *		on @q. @fn will be called as follows: @fn(rq, @priv) where rq
+ *		is a pointer to a request and hctx points to the hardware queue
+ *		associated with the request.
+ * @priv:	Will be passed as second argument to @fn.
  *
  * Note: if @q->tag_set is shared with other request queues then @fn will be
  * called for all requests on all queues that share that tag set and not only
@@ -497,14 +496,17 @@ EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 		void *priv)
 {
+	int srcu_idx;
+
 	/*
-	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and hctx_table
+	 * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx
 	 * while the queue is frozen. So we can use q_usage_counter to avoid
 	 * racing with it.
 	 */
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
+	srcu_idx = srcu_read_lock(&q->tag_set->tags_srcu);
 	if (blk_mq_is_shared_tags(q->tag_set->flags)) {
 		struct blk_mq_tags *tags = q->tag_set->shared_tags;
 		struct sbitmap_queue *bresv = &tags->breserved_tags;
@@ -534,6 +536,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn,
 			bt_for_each(hctx, q, btags, fn, priv, false);
 		}
 	}
+	srcu_read_unlock(&q->tag_set->tags_srcu, srcu_idx);
 	blk_queue_exit(q);
 }
 
@@ -544,30 +547,11 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
 				       node);
 }
 
-int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags,
-			struct sbitmap_queue *breserved_tags,
-			unsigned int queue_depth, unsigned int reserved,
-			int node, int alloc_policy)
-{
-	unsigned int depth = queue_depth - reserved;
-	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
-
-	if (bt_alloc(bitmap_tags, depth, round_robin, node))
-		return -ENOMEM;
-	if (bt_alloc(breserved_tags, reserved, round_robin, node))
-		goto free_bitmap_tags;
-
-	return 0;
-
-free_bitmap_tags:
-	sbitmap_queue_free(bitmap_tags);
-	return -ENOMEM;
-}
-
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
-				     unsigned int reserved_tags,
-				     int node, int alloc_policy)
+		unsigned int reserved_tags, unsigned int flags, int node)
 {
+	unsigned int depth = total_tags - reserved_tags;
+	bool round_robin = flags & BLK_MQ_F_TAG_RR;
 	struct blk_mq_tags *tags;
 
 	if (total_tags > BLK_MQ_TAG_MAX) {
@@ -582,73 +566,53 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 	spin_lock_init(&tags->lock);
+	INIT_LIST_HEAD(&tags->page_list);
+
+	if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node))
+		goto out_free_tags;
+	if (bt_alloc(&tags->breserved_tags, reserved_tags, round_robin, node))
+		goto out_free_bitmap_tags;
 
-	if (blk_mq_init_bitmaps(&tags->bitmap_tags, &tags->breserved_tags,
-				total_tags, reserved_tags, node,
-				alloc_policy) < 0) {
-		kfree(tags);
-		return NULL;
-	}
 	return tags;
-}
 
-void blk_mq_free_tags(struct blk_mq_tags *tags)
-{
+out_free_bitmap_tags:
 	sbitmap_queue_free(&tags->bitmap_tags);
-	sbitmap_queue_free(&tags->breserved_tags);
+out_free_tags:
 	kfree(tags);
+	return NULL;
 }
 
-int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
-			    struct blk_mq_tags **tagsptr, unsigned int tdepth,
-			    bool can_grow)
+static void blk_mq_free_tags_callback(struct rcu_head *head)
 {
-	struct blk_mq_tags *tags = *tagsptr;
-
-	if (tdepth <= tags->nr_reserved_tags)
-		return -EINVAL;
-
-	/*
-	 * If we are allowed to grow beyond the original size, allocate
-	 * a new set of tags before freeing the old one.
-	 */
-	if (tdepth > tags->nr_tags) {
-		struct blk_mq_tag_set *set = hctx->queue->tag_set;
-		struct blk_mq_tags *new;
-
-		if (!can_grow)
-			return -EINVAL;
+	struct blk_mq_tags *tags = container_of(head, struct blk_mq_tags,
+						rcu_head);
+	struct page *page;
 
+	while (!list_empty(&tags->page_list)) {
+		page = list_first_entry(&tags->page_list, struct page, lru);
+		list_del_init(&page->lru);
 		/*
-		 * We need some sort of upper limit, set it high enough that
-		 * no valid use cases should require more.
+		 * Remove kmemleak object previously allocated in
+		 * blk_mq_alloc_rqs().
 		 */
-		if (tdepth > MAX_SCHED_RQ)
-			return -EINVAL;
-
-		/*
-		 * Only the sbitmap needs resizing since we allocated the max
-		 * initially.
-		 */
-		if (blk_mq_is_shared_tags(set->flags))
-			return 0;
+		kmemleak_free(page_address(page));
+		__free_pages(page, page->private);
+	}
+	kfree(tags);
+}
 
-		new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth);
-		if (!new)
-			return -ENOMEM;
+void blk_mq_free_tags(struct blk_mq_tag_set *set, struct blk_mq_tags *tags)
+{
+	sbitmap_queue_free(&tags->bitmap_tags);
+	sbitmap_queue_free(&tags->breserved_tags);
 
-		blk_mq_free_map_and_rqs(set, *tagsptr, hctx->queue_num);
-		*tagsptr = new;
-	} else {
-		/*
-		 * Don't need (or can't) update reserved tags here, they
-		 * remain static and should never need resizing.
-		 */
-		sbitmap_queue_resize(&tags->bitmap_tags,
-				tdepth - tags->nr_reserved_tags);
+	/* if tags pages is not allocated yet, free tags directly */
+	if (list_empty(&tags->page_list)) {
+		kfree(tags);
+		return;
 	}
 
-	return 0;
+	call_srcu(&set->tags_srcu, &tags->rcu_head, blk_mq_free_tags_callback);
 }
 
 void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size)
@@ -658,10 +622,11 @@ void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size
 	sbitmap_queue_resize(&tags->bitmap_tags, size - set->reserved_tags);
 }
 
-void blk_mq_tag_update_sched_shared_tags(struct request_queue *q)
+void blk_mq_tag_update_sched_shared_tags(struct request_queue *q,
+					 unsigned int nr)
 {
 	sbitmap_queue_resize(&q->sched_shared_tags->bitmap_tags,
-			     q->nr_requests - q->tag_set->reserved_tags);
+			     nr - q->tag_set->reserved_tags);
 }
 
 /**