Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit f198e0a1 authored by Ming Lei's avatar Ming Lei Committed by Treehugger Robot
Browse files

BACKPORT: 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: default avatarJohn Garry <john.garry@huawei.com>
Reviewed-by: default avatarDavid Jeffery <djeffery@redhat.com>
Reviewed-by: default avatarBart Van Assche <bvanassche@acm.org>
Signed-off-by: default avatarMing Lei <ming.lei@redhat.com>

Bug: 197804811
Change-Id: If49478d7b05d3f5b0a26966ddf9ae764cf2fb6b0
(cherry picked from commit bd63141d585bef14f4caf111f6d0e27fe2300ec6)
[ refactored to avoid breaking KMI ]
Signed-off-by: default avatarPradeep P V K <pragalla@codeaurora.org>
Signed-off-by: default avatarTodd Kjos <tkjos@google.com>
(cherry picked from commit bb96e7f45dc6ac1d6ec12190f1f286e3014fb068)
Signed-off-by: default avatarLee Jones <joneslee@google.com>
parent b8d378e9

block/blk-mq-tag.c

+5 −2
Original line number Diff line number Diff line
@@ -377,18 +377,21 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, 
				     int node, int alloc_policy)

{

	struct blk_mq_tags *tags;

	struct ext_blk_mq_tags *etags;



	if (total_tags > BLK_MQ_TAG_MAX) {

		pr_err("blk-mq: tag depth too large\n");

		return NULL;

	}



	tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node);

	if (!tags)

	etags = kzalloc_node(sizeof(*etags), GFP_KERNEL, node);

	if (!etags)

		return NULL;



	tags = &etags->tags;

	tags->nr_tags = total_tags;

	tags->nr_reserved_tags = reserved_tags;

	spin_lock_init(&etags->lock);



	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);

}

block/blk-mq-tag.h

+15 −0
Original line number Diff line number Diff line
@@ -21,6 +21,21 @@ struct blk_mq_tags { 
	struct list_head page_list;

};



/*

 * Extended tag address space map. This was needed

 * to add a spinlock to blk_mq_tags in a KMI compliant

 * way (no changes could be made to struct blk_mq_tags).

 */

struct ext_blk_mq_tags {

	struct blk_mq_tags tags;



	 /*

	  * used to clear request reference in rqs[] before freeing one

	  * request pool

	  */

	spinlock_t lock;

};





extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);

extern void blk_mq_free_tags(struct blk_mq_tags *tags);

block/blk-mq.c

+43 −5
Original line number Diff line number Diff line
@@ -1834,6 +1834,47 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, 
	}

}



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 ext_blk_mq_tags *drv_etags;

	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.

	 */

	drv_etags = container_of(drv_tags, struct ext_blk_mq_tags, tags);

	spin_lock_irqsave(&drv_etags->lock, flags);

	spin_unlock_irqrestore(&drv_etags->lock, flags);

}



static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)

{

	const int is_sync = op_is_sync(bio->bi_opf);
@@ -1966,6 +2007,8 @@ 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);
@@ -2025,11 +2068,6 @@ 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)

{