blk-mq: fix potential uaf for 'queue_hw_ctx'

This is just apply Kuai's patch in [1] with mirror changes.

blk_mq_realloc_hw_ctxs() will free the 'queue_hw_ctx'(e.g. undate
submit_queues through configfs for null_blk), while it might still be
used from other context(e.g. switch elevator to none):

t1					t2
elevator_switch
 blk_mq_unquiesce_queue
  blk_mq_run_hw_queues
   queue_for_each_hw_ctx
    // assembly code for hctx = (q)->queue_hw_ctx[i]
    mov    0x48(%rbp),%rdx -> read old queue_hw_ctx

					__blk_mq_update_nr_hw_queues
					 blk_mq_realloc_hw_ctxs
					  hctxs = q->queue_hw_ctx
					  q->queue_hw_ctx = new_hctxs
					  kfree(hctxs)
    movslq %ebx,%rax
    mov    (%rdx,%rax,8),%rdi ->uaf

This problem was found by code review, and I comfirmed that the concurrent
scenario do exist(specifically 'q->queue_hw_ctx' can be changed during
blk_mq_run_hw_queues()), however, the uaf problem hasn't been repoduced yet
without hacking the kernel.

Sicne the queue is freezed in __blk_mq_update_nr_hw_queues(), fix the
problem by protecting 'queue_hw_ctx' through rcu where it can be accessed
without grabbing 'q_usage_counter'.

[1] https://lore.kernel.org/all/20220225072053.2472431-1-yukuai3@huawei.com/

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Fengnan Chang <changfengnan@bytedance.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: poluo

block/blk-mq.c

@@ -4535,7 +4535,12 @@ static void __blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		if (hctxs)
 			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
 			       sizeof(*hctxs));
-		q->queue_hw_ctx = new_hctxs;
+		rcu_assign_pointer(q->queue_hw_ctx, new_hctxs);
+		/*
+		 * Make sure reading the old queue_hw_ctx from other
+		 * context concurrently won't trigger uaf.
+		 */
+		synchronize_rcu_expedited();
 		kfree(hctxs);
 		hctxs = new_hctxs;
 	}

include/linux/blk-mq.h

@@ -1015,9 +1015,20 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
 	return rq + 1;
 }
 
+static inline struct blk_mq_hw_ctx *queue_hctx(struct request_queue *q, int id)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	rcu_read_lock();
+	hctx = rcu_dereference(q->queue_hw_ctx)[id];
+	rcu_read_unlock();
+
+	return hctx;
+}
+
 #define queue_for_each_hw_ctx(q, hctx, i)				\
 	for ((i) = 0; (i) < (q)->nr_hw_queues &&			\
-	     ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)
+	     ({ hctx = queue_hctx((q), i); 1; }); (i)++)
 
 #define hctx_for_each_ctx(hctx, ctx, i)					\
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\

include/linux/blkdev.h

@@ -503,7 +503,7 @@ struct request_queue {
 
 	/* hw dispatch queues */
 	unsigned int		nr_hw_queues;
-	struct blk_mq_hw_ctx	**queue_hw_ctx;
+	struct blk_mq_hw_ctx * __rcu *queue_hw_ctx;
 
 	struct percpu_ref	q_usage_counter;
 	struct lock_class_key	io_lock_cls_key;