[PATCH V4 3/4] blk-mq: clear stale request in tags->rq[] before freeing one request pool

[Ming Lei <ming.lei@redhat.com>]

refcount_inc_not_zero() in bt_tags_iter() still may read one freed
request.

Fix the issue by the following approach:

1) hold a per-tags spinlock when reading ->rqs[tag] and calling
refcount_inc_not_zero in bt_tags_iter()

2) clearing stale request referred via ->rqs[tag] before freeing
request pool, the per-tags spinlock is held for clearing stale
->rq[tag]

So after we cleared stale requests, bt_tags_iter() won't observe
freed request any more, also the clearing will wait for pending
request reference.

The idea of clearing ->rqs[] is borrowed from John Garry's previous
patch and one recent David's patch.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Cc: John Garry <john.garry@huawei.com>
Cc: David Jeffery <djeffery@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq-tag.c |  9 ++++++++-
 block/blk-mq-tag.h |  3 +++
 block/blk-mq.c     | 39 ++++++++++++++++++++++++++++++++++-----
 3 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 9329b94a9743..a3be267212b9 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -277,9 +277,15 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	if (iter_static_rqs)
 		rq = tags->static_rqs[bitnr];
 	else {
+		unsigned long flags;
+
+		spin_lock_irqsave(&tags->lock, flags);
 		rq = tags->rqs[bitnr];
-		if (!rq || !refcount_inc_not_zero(&rq->ref))
+		if (!rq || !refcount_inc_not_zero(&rq->ref)) {
+			spin_unlock_irqrestore(&tags->lock, flags);
 			return true;
+		}
+		spin_unlock_irqrestore(&tags->lock, flags);
 	}
 	if ((iter_data->flags & BT_TAG_ITER_STARTED) &&
 	    !blk_mq_request_started(rq))
@@ -526,6 +532,7 @@ 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);
 
 	if (blk_mq_is_sbitmap_shared(flags))
 		return tags;
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 7d3e6b333a4a..f942a601b5ef 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -20,6 +20,9 @@ struct blk_mq_tags {
 	struct request **rqs;
 	struct request **static_rqs;
 	struct list_head page_list;
+
+	/* used to clear rqs[] before one request pool is freed */
+	spinlock_t lock;
 };
 
 extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4bd6c11bd8bc..abd0f7a9d052 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2291,6 +2291,38 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 	return BLK_QC_T_NONE;
 }
 
+static size_t order_to_size(unsigned int order)
+{
+	return (size_t)PAGE_SIZE << order;
+}
+
+/* called before freeing request pool in @tags */
+static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set,
+		struct blk_mq_tags *tags, unsigned int hctx_idx)
+{
+	struct blk_mq_tags *drv_tags = set->tags[hctx_idx];
+	struct page *page;
+	unsigned long flags;
+
+	spin_lock_irqsave(&drv_tags->lock, flags);
+	list_for_each_entry(page, &tags->page_list, lru) {
+		unsigned long start = (unsigned long)page_address(page);
+		unsigned long end = start + order_to_size(page->private);
+		int i;
+
+		for (i = 0; i < set->queue_depth; i++) {
+			struct request *rq = drv_tags->rqs[i];
+			unsigned long rq_addr = (unsigned long)rq;
+
+			if (rq_addr >= start && rq_addr < end) {
+				WARN_ON_ONCE(refcount_read(&rq->ref) != 0);
+				cmpxchg(&drv_tags->rqs[i], rq, NULL);
+			}
+		}
+	}
+	spin_unlock_irqrestore(&drv_tags->lock, flags);
+}
+
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx)
 {
@@ -2309,6 +2341,8 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		}
 	}
 
+	blk_mq_clear_rq_mapping(set, tags, hctx_idx);
+
 	while (!list_empty(&tags->page_list)) {
 		page = list_first_entry(&tags->page_list, struct page, lru);
 		list_del_init(&page->lru);
@@ -2368,11 +2402,6 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
 	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)
 {
-- 
2.29.2