Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 37 insertions, 33 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6041e17492..a02d3d922c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -426,6 +426,8 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 		rq_list_add(data->cached_rq, rq);
 		nr++;
 	}
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
+		blk_mq_add_active_requests(data->hctx, nr);
 	/* caller already holds a reference, add for remainder */
 	percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
 	data->nr_tags -= nr;
@@ -510,6 +512,8 @@ retry:
 		goto retry;
 	}
 
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
+		blk_mq_inc_active_requests(data->hctx);
 	rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag);
 	blk_mq_rq_time_init(rq, alloc_time_ns);
 	return rq;
@@ -669,6 +673,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
+	if (!(data.rq_flags & RQF_SCHED_TAGS))
+		blk_mq_inc_active_requests(data.hctx);
 	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
 	blk_mq_rq_time_init(rq, alloc_time_ns);
 	rq->__data_len = 0;
@@ -708,11 +714,10 @@ static void __blk_mq_free_request(struct request *rq)
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
 
-	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		__blk_mq_dec_active_requests(hctx);
-
-	if (rq->tag != BLK_MQ_NO_TAG)
+	if (rq->tag != BLK_MQ_NO_TAG) {
+		blk_mq_dec_active_requests(hctx);
 		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
+	}
 	if (sched_tag != BLK_MQ_NO_TAG)
 		blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
@@ -767,11 +772,16 @@ 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);
@@ -1061,12 +1071,7 @@ static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
 {
 	struct request_queue *q = hctx->queue;
 
-	/*
-	 * All requests should have been marked as RQF_MQ_INFLIGHT, so
-	 * update hctx->nr_active in batch
-	 */
-	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
-		__blk_mq_sub_active_requests(hctx, nr_tags);
+	blk_mq_sub_active_requests(hctx, nr_tags);
 
 	blk_mq_put_tags(hctx->tags, tag_array, nr_tags);
 	percpu_ref_put_many(&q->q_usage_counter, nr_tags);
@@ -1259,6 +1264,7 @@ void blk_mq_start_request(struct request *rq)
 
 	blk_add_timer(rq);
 	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
+	rq->mq_hctx->tags->rqs[rq->tag] = rq;
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
@@ -1760,7 +1766,7 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 	return data.rq;
 }
 
-static bool __blk_mq_alloc_driver_tag(struct request *rq)
+bool __blk_mq_alloc_driver_tag(struct request *rq)
 {
 	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
 	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
@@ -1781,20 +1787,7 @@ static bool __blk_mq_alloc_driver_tag(struct request *rq)
 		return false;
 
 	rq->tag = tag + tag_offset;
-	return true;
-}
-
-bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq)
-{
-	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
-		return false;
-
-	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
-			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
-		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		__blk_mq_inc_active_requests(hctx);
-	}
-	hctx->tags->rqs[rq->tag] = rq;
+	blk_mq_inc_active_requests(rq->mq_hctx);
 	return true;
 }
 
@@ -1871,6 +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.
@@ -2806,13 +2815,8 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		 * If we do, we can dispatch the whole plug list in one go. We
 		 * already know at this point that all requests belong to the
 		 * same queue, caller must ensure that's the case.
-		 *
-		 * Since we pass off the full list to the driver at this point,
-		 * we do not increment the active request count for the queue.
-		 * Bypass shared tags for now because of that.
 		 */
-		if (q->mq_ops->queue_rqs &&
-		    !(rq->mq_hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		if (q->mq_ops->queue_rqs) {
 			blk_mq_run_dispatch_ops(q,
 				__blk_mq_flush_plug_list(q, plug));
 			if (rq_list_empty(plug->mq_list))