1 files changed, 41 insertions, 22 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ac18f802c027..2dc01551e27c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -40,7 +40,6 @@
 #include "blk-stat.h"
 #include "blk-mq-sched.h"
 #include "blk-rq-qos.h"
-#include "blk-ioprio.h"
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
@@ -772,11 +771,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}
 
 	bio_advance(bio, nbytes);
@@ -1248,7 +1252,8 @@ void blk_mq_start_request(struct request *rq)
 
 	trace_block_rq_issue(rq);
 
-	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
+	    !blk_rq_is_passthrough(rq)) {
 		rq->io_start_time_ns = ktime_get_ns();
 		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
@@ -1859,6 +1864,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	__add_wait_queue(wq, wait);
 
 	/*
+	 * Add one explicit barrier since blk_mq_get_driver_tag() may
+	 * not imply barrier in case of failure.
+	 *
+	 * Order adding us to wait queue and allocating driver tag.
+	 *
+	 * The pair is the one implied in sbitmap_queue_wake_up() which
+	 * orders clearing sbitmap tag bits and waitqueue_active() in
+	 * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+	 *
+	 * Otherwise, re-order of adding wait queue and getting driver tag
+	 * may cause __sbitmap_queue_wake_up() to wake up nothing because
+	 * the waitqueue_active() may not observe us in wait queue.
+	 */
+	smp_mb();
+
+	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
@@ -2890,8 +2911,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	return NULL;
 }
 
-/* return true if this @rq can be used for @bio */
-static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+/*
+ * Check if we can use the passed on request for submitting the passed in bio,
+ * and remove it from the request list if it can be used.
+ */
+static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 		struct bio *bio)
 {
 	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
@@ -2919,14 +2943,6 @@ static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	return true;
 }
 
-static void bio_set_ioprio(struct bio *bio)
-{
-	/* Nobody set ioprio so far? Initialize it based on task's nice value */
-	if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE)
-		bio->bi_ioprio = get_current_ioprio();
-	blkcg_set_ioprio(bio);
-}
-
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
@@ -2951,13 +2967,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits)) {
-		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-		if (!bio)
-			return;
-	}
-
-	bio_set_ioprio(bio);
 
 	if (plug) {
 		rq = rq_list_peek(&plug->cached_rq);
@@ -2965,16 +2974,26 @@ void blk_mq_submit_bio(struct bio *bio)
 			rq = NULL;
 	}
 	if (rq) {
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				return;
+		}
 		if (!bio_integrity_prep(bio))
 			return;
 		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 			return;
-		if (blk_mq_can_use_cached_rq(rq, plug, bio))
+		if (blk_mq_use_cached_rq(rq, plug, bio))
 			goto done;
 		percpu_ref_get(&q->q_usage_counter);
 	} else {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				goto fail;
+		}
 		if (!bio_integrity_prep(bio))
 			goto fail;
 	}