1 files changed, 40 insertions, 23 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 9321767470dc..9e5e0277a4d9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -283,12 +283,9 @@ static void blk_free_queue(struct request_queue *q)
  *
  * Decrements the refcount of the request_queue and free it when the refcount
  * reaches 0.
- *
- * Context: Can sleep.
  */
 void blk_put_queue(struct request_queue *q)
 {
-	might_sleep();
 	if (refcount_dec_and_test(&q->refs))
 		blk_free_queue(q);
 }
@@ -573,7 +570,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (bio->bi_iter.bi_sector & (bdev_zone_sectors(bio->bi_bdev) - 1) ||
+	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) ||
 	    !bio_zone_is_seq(bio))
 		return BLK_STS_IOERR;
 
@@ -687,6 +684,18 @@ static void __submit_bio_noacct_mq(struct bio *bio)
 
 void submit_bio_noacct_nocheck(struct bio *bio)
 {
+	blk_cgroup_bio_start(bio);
+	blkcg_bio_issue_init(bio);
+
+	if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+		trace_block_bio_queue(bio);
+		/*
+		 * Now that enqueuing has been traced, we need to trace
+		 * completion as well.
+		 */
+		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+	}
+
 	/*
 	 * We only want one ->submit_bio to be active at a time, else stack
 	 * usage with stacked devices could be a problem.  Use current->bio_list
@@ -744,12 +753,16 @@ void submit_bio_noacct(struct bio *bio)
 	 * Filter flush bio's early so that bio based drivers without flush
 	 * support don't have to worry about them.
 	 */
-	if (op_is_flush(bio->bi_opf) &&
-	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
-		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
-		if (!bio_sectors(bio)) {
-			status = BLK_STS_OK;
+	if (op_is_flush(bio->bi_opf)) {
+		if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE &&
+				 bio_op(bio) != REQ_OP_ZONE_APPEND))
 			goto end_io;
+		if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
+			bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
+			if (!bio_sectors(bio)) {
+				status = BLK_STS_OK;
+				goto end_io;
+			}
 		}
 	}
 
@@ -791,17 +804,6 @@ void submit_bio_noacct(struct bio *bio)
 
 	if (blk_throtl_bio(bio))
 		return;
-
-	blk_cgroup_bio_start(bio);
-	blkcg_bio_issue_init(bio);
-
-	if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
-		trace_block_bio_queue(bio);
-		/* Now that enqueuing has been traced, we need to trace
-		 * completion as well.
-		 */
-		bio_set_flag(bio, BIO_TRACE_COMPLETION);
-	}
 	submit_bio_noacct_nocheck(bio);
 	return;
 
@@ -856,10 +858,16 @@ EXPORT_SYMBOL(submit_bio);
  */
 int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 {
-	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
+	struct block_device *bdev;
+	struct request_queue *q;
 	int ret = 0;
 
+	bdev = READ_ONCE(bio->bi_bdev);
+	if (!bdev)
+		return 0;
+
+	q = bdev_get_queue(bdev);
 	if (cookie == BLK_QC_T_NONE ||
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
@@ -872,7 +880,16 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	 */
 	blk_flush_plug(current->plug, false);
 
-	if (bio_queue_enter(bio))
+	/*
+	 * We need to be able to enter a frozen queue, similar to how
+	 * timeouts also need to do that. If that is blocked, then we can
+	 * have pending IO when a queue freeze is started, and then the
+	 * wait for the freeze to finish will wait for polled requests to
+	 * timeout as the poller is preventer from entering the queue and
+	 * completing them. As long as we prevent new IO from being queued,
+	 * that should be all that matters.
+	 */
+	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return 0;
 	if (queue_is_mq(q)) {
 		ret = blk_mq_poll(q, cookie, iob, flags);
@@ -919,7 +936,7 @@ int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
 	 */
 	rcu_read_lock();
 	bio = READ_ONCE(kiocb->private);
-	if (bio && bio->bi_bdev)
+	if (bio)
 		ret = bio_poll(bio, iob, flags);
 	rcu_read_unlock();