blk-mq: clear stale request in tags->rq[] before freeing one request pool

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.

Tested-by: John Garry <john.garry@huawei.com>
Reviewed-by: David Jeffery <djeffery@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20210511152236.763464-4-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 41 insertions, 5 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index debfa5cd8025..dd371f321d35 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2307,6 +2307,45 @@ queue_exit:
 	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;
+
+	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);
+			}
+		}
+	}
+
+	/*
+	 * Wait until all pending iteration is done.
+	 *
+	 * Request reference is cleared and it is guaranteed to be observed
+	 * after the ->lock is released.
+	 */
+	spin_lock_irqsave(&drv_tags->lock, flags);
+	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)
 {
@@ -2325,6 +2364,8 @@ 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);
@@ -2384,11 +2425,6 @@ 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)
 {