Merge tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Another nice round of removing more code than what is added, mostly
  due to Christoph's relentless pursuit of tech debt removal/cleanups.
  This pull request contains:

   - Two series of BFQ improvements (Paolo, Jan, Jia)

   - Block iov_iter improvements (Pavel)

   - bsg error path fix (Pan)

   - blk-mq scheduler improvements (Jan)

   - -EBUSY discard fix (Jan)

   - bvec allocation improvements (Ming, Christoph)

   - bio allocation and init improvements (Christoph)

   - Store bdev pointer in bio instead of gendisk + partno (Christoph)

   - Block trace point cleanups (Christoph)

   - hard read-only vs read-only split (Christoph)

   - Block based swap cleanups (Christoph)

   - Zoned write granularity support (Damien)

   - Various fixes/tweaks (Chunguang, Guoqing, Lei, Lukas, Huhai)"

* tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block: (104 commits)
  mm: simplify swapdev_block
  sd_zbc: clear zone resources for non-zoned case
  block: introduce blk_queue_clear_zone_settings()
  zonefs: use zone write granularity as block size
  block: introduce zone_write_granularity limit
  block: use blk_queue_set_zoned in add_partition()
  nullb: use blk_queue_set_zoned() to setup zoned devices
  nvme: cleanup zone information initialization
  block: document zone_append_max_bytes attribute
  block: use bi_max_vecs to find the bvec pool
  md/raid10: remove dead code in reshape_request
  block: mark the bio as cloned in bio_iov_bvec_set
  block: set BIO_NO_PAGE_REF in bio_iov_bvec_set
  block: remove a layer of indentation in bio_iov_iter_get_pages
  block: turn the nr_iovecs argument to bio_alloc* into an unsigned short
  block: remove the 1 and 4 vec bvec_slabs entries
  block: streamline bvec_alloc
  block: factor out a bvec_alloc_gfp helper
  block: move struct biovec_slab to bio.c
  block: reuse BIO_INLINE_VECS for integrity bvecs
  ...

1 files changed, 61 insertions, 8 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index f285a9123a8b..f21d922ecfaf 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1646,6 +1646,42 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
+/*
+ * Is the request queue handled by an IO scheduler that does not respect
+ * hardware queues when dispatching?
+ */
+static bool blk_mq_has_sqsched(struct request_queue *q)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.dispatch_request &&
+	    !(e->type->elevator_features & ELEVATOR_F_MQ_AWARE))
+		return true;
+	return false;
+}
+
+/*
+ * Return prefered queue to dispatch from (if any) for non-mq aware IO
+ * scheduler.
+ */
+static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	/*
+	 * If the IO scheduler does not respect hardware queues when
+	 * dispatching, we just don't bother with multiple HW queues and
+	 * dispatch from hctx for the current CPU since running multiple queues
+	 * just causes lock contention inside the scheduler and pointless cache
+	 * bouncing.
+	 */
+	hctx = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT,
+				     raw_smp_processor_id());
+	if (!blk_mq_hctx_stopped(hctx))
+		return hctx;
+	return NULL;
+}
+
 /**
  * blk_mq_run_hw_queues - Run all hardware queues in a request queue.
  * @q: Pointer to the request queue to run.
@@ -1653,14 +1689,23 @@ EXPORT_SYMBOL(blk_mq_run_hw_queue);
  */
 void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_hw_ctx *hctx, *sq_hctx;
 	int i;
 
+	sq_hctx = NULL;
+	if (blk_mq_has_sqsched(q))
+		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
 			continue;
-
-		blk_mq_run_hw_queue(hctx, async);
+		/*
+		 * Dispatch from this hctx either if there's no hctx preferred
+		 * by IO scheduler or if it has requests that bypass the
+		 * scheduler.
+		 */
+		if (!sq_hctx || sq_hctx == hctx ||
+		    !list_empty_careful(&hctx->dispatch))
+			blk_mq_run_hw_queue(hctx, async);
 	}
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queues);
@@ -1672,14 +1717,23 @@ EXPORT_SYMBOL(blk_mq_run_hw_queues);
  */
 void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 {
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_hw_ctx *hctx, *sq_hctx;
 	int i;
 
+	sq_hctx = NULL;
+	if (blk_mq_has_sqsched(q))
+		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
 			continue;
-
-		blk_mq_delay_run_hw_queue(hctx, msecs);
+		/*
+		 * Dispatch from this hctx either if there's no hctx preferred
+		 * by IO scheduler or if it has requests that bypass the
+		 * scheduler.
+		 */
+		if (!sq_hctx || sq_hctx == hctx ||
+		    !list_empty_careful(&hctx->dispatch))
+			blk_mq_delay_run_hw_queue(hctx, msecs);
 	}
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queues);
@@ -2128,7 +2182,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
  */
 blk_qc_t blk_mq_submit_bio(struct bio *bio)
 {
-	struct request_queue *q = bio->bi_disk->queue;
+	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = op_is_flush(bio->bi_opf);
 	struct blk_mq_alloc_data data = {
@@ -2653,7 +2707,6 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 		goto free_hctx;
 
 	atomic_set(&hctx->nr_active, 0);
-	atomic_set(&hctx->elevator_queued, 0);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 	hctx->numa_node = node;