Merge tag 'for-4.19/post-20180822' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:

 - Set of bcache fixes and changes (Coly)

 - The flush warn fix (me)

 - Small series of BFQ fixes (Paolo)

 - wbt hang fix (Ming)

 - blktrace fix (Steven)

 - blk-mq hardware queue count update fix (Jianchao)

 - Various little fixes

* tag 'for-4.19/post-20180822' of git://git.kernel.dk/linux-block: (31 commits)
  block/DAC960.c: make some arrays static const, shrinks object size
  blk-mq: sync the update nr_hw_queues with blk_mq_queue_tag_busy_iter
  blk-mq: init hctx sched after update ctx and hctx mapping
  block: remove duplicate initialization
  tracing/blktrace: Fix to allow setting same value
  pktcdvd: fix setting of 'ret' error return for a few cases
  block: change return type to bool
  block, bfq: return nbytes and not zero from struct cftype .write() method
  block, bfq: improve code of bfq_bfqq_charge_time
  block, bfq: reduce write overcharge
  block, bfq: always update the budget of an entity when needed
  block, bfq: readd missing reset of parent-entity service
  blk-wbt: fix IO hang in wbt_wait()
  block: don't warn for flush on read-only device
  bcache: add the missing comments for smp_mb()/smp_wmb()
  bcache: remove unnecessary space before ioctl function pointer arguments
  bcache: add missing SPDX header
  bcache: move open brace at end of function definitions to next line
  bcache: add static const prefix to char * array declarations
  bcache: fix code comments style
  ...

block/bfq-cgroup.c

@@ -913,7 +913,8 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
 	if (ret)
 		return ret;
 
-	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+	ret = bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+	return ret ?: nbytes;
 }
 
 #ifdef CONFIG_DEBUG_BLK_CGROUP

block/bfq-iosched.c

@@ -187,11 +187,25 @@ static const int bfq_stats_min_budgets = 194;
 static const int bfq_default_max_budget = 16 * 1024;
 
 /*
- * Async to sync throughput distribution is controlled as follows:
- * when an async request is served, the entity is charged the number
- * of sectors of the request, multiplied by the factor below
+ * When a sync request is dispatched, the queue that contains that
+ * request, and all the ancestor entities of that queue, are charged
+ * with the number of sectors of the request. In constrast, if the
+ * request is async, then the queue and its ancestor entities are
+ * charged with the number of sectors of the request, multiplied by
+ * the factor below. This throttles the bandwidth for async I/O,
+ * w.r.t. to sync I/O, and it is done to counter the tendency of async
+ * writes to steal I/O throughput to reads.
+ *
+ * The current value of this parameter is the result of a tuning with
+ * several hardware and software configurations. We tried to find the
+ * lowest value for which writes do not cause noticeable problems to
+ * reads. In fact, the lower this parameter, the stabler I/O control,
+ * in the following respect.  The lower this parameter is, the less
+ * the bandwidth enjoyed by a group decreases
+ * - when the group does writes, w.r.t. to when it does reads;
+ * - when other groups do reads, w.r.t. to when they do writes.
  */
-static const int bfq_async_charge_factor = 10;
+static const int bfq_async_charge_factor = 3;
 
 /* Default timeout values, in jiffies, approximating CFQ defaults. */
 const int bfq_timeout = HZ / 8;
@@ -853,16 +867,7 @@ static unsigned long bfq_serv_to_charge(struct request *rq,
 	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
 		return blk_rq_sectors(rq);
 
-	/*
-	 * If there are no weight-raised queues, then amplify service
-	 * by just the async charge factor; otherwise amplify service
-	 * by twice the async charge factor, to further reduce latency
-	 * for weight-raised queues.
-	 */
-	if (bfqq->bfqd->wr_busy_queues == 0)
-		return blk_rq_sectors(rq) * bfq_async_charge_factor;
-
-	return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
+	return blk_rq_sectors(rq) * bfq_async_charge_factor;
 }
 
 /**
@@ -3298,6 +3303,27 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 		 */
 	} else
 		entity->service = 0;
+
+	/*
+	 * Reset the received-service counter for every parent entity.
+	 * Differently from what happens with bfqq->entity.service,
+	 * the resetting of this counter never needs to be postponed
+	 * for parent entities. In fact, in case bfqq may have a
+	 * chance to go on being served using the last, partially
+	 * consumed budget, bfqq->entity.service needs to be kept,
+	 * because if bfqq then actually goes on being served using
+	 * the same budget, the last value of bfqq->entity.service is
+	 * needed to properly decrement bfqq->entity.budget by the
+	 * portion already consumed. In contrast, it is not necessary
+	 * to keep entity->service for parent entities too, because
+	 * the bubble up of the new value of bfqq->entity.budget will
+	 * make sure that the budgets of parent entities are correct,
+	 * even in case bfqq and thus parent entities go on receiving
+	 * service with the same budget.
+	 */
+	entity = entity->parent;
+	for_each_entity(entity)
+		entity->service = 0;
 }
 
 /*

block/bfq-wf2q.c

@@ -130,10 +130,14 @@ static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
 	if (!change_without_lookup) /* lookup needed */
 		next_in_service = bfq_lookup_next_entity(sd, expiration);
 
-	if (next_in_service)
-		parent_sched_may_change = !sd->next_in_service ||
+	if (next_in_service) {
+		bool new_budget_triggers_change =
 			bfq_update_parent_budget(next_in_service);
 
+		parent_sched_may_change = !sd->next_in_service ||
+			new_budget_triggers_change;
+	}
+
 	sd->next_in_service = next_in_service;
 
 	if (!next_in_service)
@@ -877,15 +881,11 @@ void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			  unsigned long time_ms)
 {
 	struct bfq_entity *entity = &bfqq->entity;
-	int tot_serv_to_charge = entity->service;
-	unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
-
-	if (time_ms > 0 && time_ms < timeout_ms)
-		tot_serv_to_charge =
-			(bfqd->bfq_max_budget * time_ms) / timeout_ms;
-
-	if (tot_serv_to_charge < entity->service)
-		tot_serv_to_charge = entity->service;
+	unsigned long timeout_ms = jiffies_to_msecs(bfq_timeout);
+	unsigned long bounded_time_ms = min(time_ms, timeout_ms);
+	int serv_to_charge_for_time =
+		(bfqd->bfq_max_budget * bounded_time_ms) / timeout_ms;
+	int tot_serv_to_charge = max(serv_to_charge_for_time, entity->service);
 
 	/* Increase budget to avoid inconsistencies */
 	if (tot_serv_to_charge > entity->budget)

block/blk-core.c

@@ -1036,7 +1036,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
 		    laptop_mode_timer_fn, 0);
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
 	INIT_WORK(&q->timeout_work, NULL);
-	INIT_LIST_HEAD(&q->queue_head);
 	INIT_LIST_HEAD(&q->timeout_list);
 	INIT_LIST_HEAD(&q->icq_list);
 #ifdef CONFIG_BLK_CGROUP
@@ -2162,7 +2161,9 @@ static inline bool should_fail_request(struct hd_struct *part,
 
 static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 {
-	if (part->policy && op_is_write(bio_op(bio))) {
+	const int op = bio_op(bio);
+
+	if (part->policy && (op_is_write(op) && !op_is_flush(op))) {
 		char b[BDEVNAME_SIZE];
 
 		WARN_ONCE(1,

block/blk-mq-sched.c

@@ -462,50 +462,6 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q)
 		blk_mq_sched_free_tags(set, hctx, i);
 }
 
-int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
-			   unsigned int hctx_idx)
-{
-	struct elevator_queue *e = q->elevator;
-	int ret;
-
-	if (!e)
-		return 0;
-
-	ret = blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
-	if (ret)
-		return ret;
-
-	if (e->type->ops.mq.init_hctx) {
-		ret = e->type->ops.mq.init_hctx(hctx, hctx_idx);
-		if (ret) {
-			blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
-			return ret;
-		}
-	}
-
-	blk_mq_debugfs_register_sched_hctx(q, hctx);
-
-	return 0;
-}
-
-void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
-			    unsigned int hctx_idx)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (!e)
-		return;
-
-	blk_mq_debugfs_unregister_sched_hctx(hctx);
-
-	if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
-		e->type->ops.mq.exit_hctx(hctx, hctx_idx);
-		hctx->sched_data = NULL;
-	}
-
-	blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
-}
-
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 {
 	struct blk_mq_hw_ctx *hctx;

block/blk-mq-sched.h

@@ -28,11 +28,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
 
-int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
-			   unsigned int hctx_idx);
-void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
-			    unsigned int hctx_idx);
-
 static inline bool
 blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {

block/blk-mq-tag.c

@@ -320,6 +320,18 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	/*
+	 * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
+	 * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
+	 * to avoid race with it. __blk_mq_update_nr_hw_queues will users
+	 * synchronize_rcu to ensure all of the users go out of the critical
+	 * section below and see zeroed q_usage_counter.
+	 */
+	rcu_read_lock();
+	if (percpu_ref_is_zero(&q->q_usage_counter)) {
+		rcu_read_unlock();
+		return;
+	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_tags *tags = hctx->tags;
@@ -335,7 +347,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
 		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
 	}
-
+	rcu_read_unlock();
 }
 
 static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,

block/blk-mq.c

@@ -2145,8 +2145,6 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_request)
 		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
 
-	blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
-
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
@@ -2214,12 +2212,9 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
 		goto free_bitmap;
 
-	if (blk_mq_sched_init_hctx(q, hctx, hctx_idx))
-		goto exit_hctx;
-
 	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
 	if (!hctx->fq)
-		goto sched_exit_hctx;
+		goto exit_hctx;
 
 	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, node))
 		goto free_fq;
@@ -2233,8 +2228,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
 
  free_fq:
 	kfree(hctx->fq);
- sched_exit_hctx:
-	blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
@@ -2896,10 +2889,81 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return ret;
 }
 
+/*
+ * request_queue and elevator_type pair.
+ * It is just used by __blk_mq_update_nr_hw_queues to cache
+ * the elevator_type associated with a request_queue.
+ */
+struct blk_mq_qe_pair {
+	struct list_head node;
+	struct request_queue *q;
+	struct elevator_type *type;
+};
+
+/*
+ * Cache the elevator_type in qe pair list and switch the
+ * io scheduler to 'none'
+ */
+static bool blk_mq_elv_switch_none(struct list_head *head,
+		struct request_queue *q)
+{
+	struct blk_mq_qe_pair *qe;
+
+	if (!q->elevator)
+		return true;
+
+	qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY);
+	if (!qe)
+		return false;
+
+	INIT_LIST_HEAD(&qe->node);
+	qe->q = q;
+	qe->type = q->elevator->type;
+	list_add(&qe->node, head);
+
+	mutex_lock(&q->sysfs_lock);
+	/*
+	 * After elevator_switch_mq, the previous elevator_queue will be
+	 * released by elevator_release. The reference of the io scheduler
+	 * module get by elevator_get will also be put. So we need to get
+	 * a reference of the io scheduler module here to prevent it to be
+	 * removed.
+	 */
+	__module_get(qe->type->elevator_owner);
+	elevator_switch_mq(q, NULL);
+	mutex_unlock(&q->sysfs_lock);
+
+	return true;
+}
+
+static void blk_mq_elv_switch_back(struct list_head *head,
+		struct request_queue *q)
+{
+	struct blk_mq_qe_pair *qe;
+	struct elevator_type *t = NULL;
+
+	list_for_each_entry(qe, head, node)
+		if (qe->q == q) {
+			t = qe->type;
+			break;
+		}
+
+	if (!t)
+		return;
+
+	list_del(&qe->node);
+	kfree(qe);
+
+	mutex_lock(&q->sysfs_lock);
+	elevator_switch_mq(q, t);
+	mutex_unlock(&q->sysfs_lock);
+}
+
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 							int nr_hw_queues)
 {
 	struct request_queue *q;
+	LIST_HEAD(head);
 
 	lockdep_assert_held(&set->tag_list_lock);
 
@@ -2910,6 +2974,18 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
+	/*
+	 * Sync with blk_mq_queue_tag_busy_iter.
+	 */
+	synchronize_rcu();
+	/*
+	 * Switch IO scheduler to 'none', cleaning up the data associated
+	 * with the previous scheduler. We will switch back once we are done
+	 * updating the new sw to hw queue mappings.
+	 */
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		if (!blk_mq_elv_switch_none(&head, q))
+			goto switch_back;
 
 	set->nr_hw_queues = nr_hw_queues;
 	blk_mq_update_queue_map(set);
@@ -2918,6 +2994,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_queue_reinit(q);
 	}
 
+switch_back:
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_elv_switch_back(&head, q);
+
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
 }

block/blk-wbt.c

@@ -576,12 +576,8 @@ static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
 	struct rq_wb *rwb = RQWB(rqos);
 	enum wbt_flags flags;
 
-	if (!rwb_enabled(rwb))
-		return;
-
 	flags = bio_to_wbt_flags(rwb, bio);
-
-	if (!wbt_should_throttle(rwb, bio)) {
+	if (!(flags & WBT_TRACKED)) {
 		if (flags & WBT_READ)
 			wb_timestamp(rwb, &rwb->last_issue);
 		return;