blk-mq: fix deadlock when reading cpu_list

CPU hotplug handling for blk-mq (blk_mq_queue_reinit) acquires
all_q_mutex in blk_mq_queue_reinit_notify() and then removes sysfs
entries by blk_mq_sysfs_unregister().  Removing sysfs entry needs to
be blocked until the active reference of the kernfs_node to be zero.

On the other hand, reading blk_mq_hw_sysfs_cpu sysfs entry (e.g.
/sys/block/nullb0/mq/0/cpu_list) acquires all_q_mutex in
blk_mq_hw_sysfs_cpus_show().

If these happen at the same time, a deadlock can happen.  Because one
can wait for the active reference to be zero with holding all_q_mutex,
and the other tries to acquire all_q_mutex with holding the active
reference.

The reason that all_q_mutex is acquired in blk_mq_hw_sysfs_cpus_show()
is to avoid reading an imcomplete hctx->cpumask.  Since reading sysfs
entry for blk-mq needs to acquire q->sysfs_lock, we can avoid deadlock
and reading an imcomplete hctx->cpumask by protecting q->sysfs_lock
while hctx->cpumask is being updated.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Cc: Ming Lei <tom.leiming@gmail.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

block/blk-mq-sysfs.c

@@ -229,8 +229,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 	unsigned int i, first = 1;
 	ssize_t ret = 0;
 
-	blk_mq_disable_hotplug();
-
 	for_each_cpu(i, hctx->cpumask) {
 		if (first)
 			ret += sprintf(ret + page, "%u", i);
@@ -240,8 +238,6 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 		first = 0;
 	}
 
-	blk_mq_enable_hotplug();
-
 	ret += sprintf(ret + page, "\n");
 	return ret;
 }

block/blk-mq.c

@@ -1797,6 +1797,11 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 	struct blk_mq_ctx *ctx;
 	struct blk_mq_tag_set *set = q->tag_set;
 
+	/*
+	 * Avoid others reading imcomplete hctx->cpumask through sysfs
+	 */
+	mutex_lock(&q->sysfs_lock);
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		cpumask_clear(hctx->cpumask);
 		hctx->nr_ctx = 0;
@@ -1816,6 +1821,8 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 		hctx->ctxs[hctx->nr_ctx++] = ctx;
 	}
 
+	mutex_unlock(&q->sysfs_lock);
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_ctxmap *map = &hctx->ctx_map;