bfq: Remove merged request already in bfq_requests_merged()

mainline inclusion
from mainline-v5.14-rc1
commit  a921c655
category: bugfix
bugzilla: 185777 https://gitee.com/openeuler/kernel/issues/I4LM14
CVE: NA

---------------------------

Currently, bfq does very little in bfq_requests_merged() and handles all
the request cleanup in bfq_finish_requeue_request() called from
blk_mq_free_request(). That is currently safe only because
blk_mq_free_request() is called shortly after bfq_requests_merged()
while bfqd->lock is still held. However to fix a lock inversion between
bfqd->lock and ioc->lock, we need to call blk_mq_free_request() after
dropping bfqd->lock. That would mean that already merged request could
be seen by other processes inside bfq queues and possibly dispatched to
the device which is wrong. So move cleanup of the request from
bfq_finish_requeue_request() to bfq_requests_merged().
Acked-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210623093634.27879-2-jack@suse.czSigned-off-by: NJens Axboe <axboe@kernel.dk>

conflict: in bfq_finish_requeue_request, code in hulk have the line
              atomic_dec(&rq->mq_hctx->elevator_queued); that is conflicted;
Signed-off-by: Nzhangwensheng <zhangwensheng5@huawei.com>
Reviewed-by: Nqiulaibin <qiulaibin@huawei.com>
Reviewed-by: NJason Yan <yanaijie@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

block/bfq-iosched.c

@@ -2326,7 +2326,7 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 		*next_bfqq = bfq_init_rq(next);
 
 	if (!bfqq)
-		return;
+		goto remove;
 
 	/*
 	 * If next and rq belong to the same bfq_queue and next is older
@@ -2349,6 +2349,14 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq,
 		bfqq->next_rq = rq;
 
 	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+remove:
+	/* Merged request may be in the IO scheduler. Remove it. */
+	if (!RB_EMPTY_NODE(&next->rb_node)) {
+		bfq_remove_request(next->q, next);
+		if (next_bfqq)
+			bfqg_stats_update_io_remove(bfqq_group(next_bfqq),
+						    next->cmd_flags);
+	}
 }
 
 /* Must be called with bfqq != NULL */
@@ -5901,6 +5909,7 @@ static void bfq_finish_requeue_request(struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq);
 	struct bfq_data *bfqd;
+	unsigned long flags;
 
 	/*
 	 * rq either is not associated with any icq, or is an already
@@ -5918,40 +5927,16 @@ static void bfq_finish_requeue_request(struct request *rq)
 					     rq->io_start_time_ns,
 					     rq->cmd_flags);
 
+	spin_lock_irqsave(&bfqd->lock, flags);
 	if (likely(rq->rq_flags & RQF_STARTED)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&bfqd->lock, flags);
-
 		if (rq == bfqd->waited_rq)
 			bfq_update_inject_limit(bfqd, bfqq);
 
 		bfq_completed_request(bfqq, bfqd);
-		bfq_finish_requeue_request_body(bfqq);
 		atomic_dec(&rq->mq_hctx->elevator_queued);
-
-		spin_unlock_irqrestore(&bfqd->lock, flags);
-	} else {
-		/*
-		 * Request rq may be still/already in the scheduler,
-		 * in which case we need to remove it (this should
-		 * never happen in case of requeue). And we cannot
-		 * defer such a check and removal, to avoid
-		 * inconsistencies in the time interval from the end
-		 * of this function to the start of the deferred work.
-		 * This situation seems to occur only in process
-		 * context, as a consequence of a merge. In the
-		 * current version of the code, this implies that the
-		 * lock is held.
-		 */
-
-		if (!RB_EMPTY_NODE(&rq->rb_node)) {
-			bfq_remove_request(rq->q, rq);
-			bfqg_stats_update_io_remove(bfqq_group(bfqq),
-						    rq->cmd_flags);
-		}
-		bfq_finish_requeue_request_body(bfqq);
 	}
+	bfq_finish_requeue_request_body(bfqq);
+	spin_unlock_irqrestore(&bfqd->lock, flags);
 
 	/*
 	 * Reset private fields. In case of a requeue, this allows