Merge tag 'for-linus-2019-09-27' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes/changes to round off this merge window. This contains:

   - Small series making some functional tweaks to blk-iocost (Tejun)

   - Elevator switch locking fix (Ming)

   - Kill redundant call in blk-wbt (Yufen)

   - Fix flush timeout handling (Yufen)"

* tag 'for-linus-2019-09-27' of git://git.kernel.dk/linux-block:
  block: fix null pointer dereference in blk_mq_rq_timed_out()
  rq-qos: get rid of redundant wbt_update_limits()
  iocost: bump up default latency targets for hard disks
  iocost: improve nr_lagging handling
  iocost: better trace vrate changes
  block: don't release queue's sysfs lock during switching elevator
  blk-mq: move lockdep_assert_held() into elevator_exit

7 files changed, 47 insertions, 54 deletions

diff --git a/block/blk-flush.c b/block/blk-flush.c
index aedd9320e605db..1eec9cbe5a0a1b 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -214,6 +214,16 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 
 	/* release the tag's ownership to the req cloned from */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
+
+	if (!refcount_dec_and_test(&flush_rq->ref)) {
+		fq->rq_status = error;
+		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
+		return;
+	}
+
+	if (fq->rq_status != BLK_STS_OK)
+		error = fq->rq_status;
+
 	hctx = flush_rq->mq_hctx;
 	if (!q->elevator) {
 		blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 3b39deb8b9f820..2a3db80c1dce7f 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -529,8 +529,8 @@ struct iocg_wake_ctx {
 static const struct ioc_params autop[] = {
 	[AUTOP_HDD] = {
 		.qos				= {
-			[QOS_RLAT]		=         50000, /* 50ms */
-			[QOS_WLAT]		=         50000,
+			[QOS_RLAT]		=        250000, /* 250ms */
+			[QOS_WLAT]		=        250000,
 			[QOS_MIN]		= VRATE_MIN_PPM,
 			[QOS_MAX]		= VRATE_MAX_PPM,
 		},
@@ -1343,7 +1343,7 @@ static void ioc_timer_fn(struct timer_list *timer)
 	u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM];
 	u32 missed_ppm[2], rq_wait_pct;
 	u64 period_vtime;
-	int i;
+	int prev_busy_level, i;
 
 	/* how were the latencies during the period? */
 	ioc_lat_stat(ioc, missed_ppm, &rq_wait_pct);
@@ -1407,7 +1407,8 @@ static void ioc_timer_fn(struct timer_list *timer)
 		 * comparing vdone against period start.  If lagging behind
 		 * IOs from past periods, don't increase vrate.
 		 */
-		if (!atomic_read(&iocg_to_blkg(iocg)->use_delay) &&
+		if ((ppm_rthr != MILLION || ppm_wthr != MILLION) &&
+		    !atomic_read(&iocg_to_blkg(iocg)->use_delay) &&
 		    time_after64(vtime, vdone) &&
 		    time_after64(vtime, now.vnow -
 				 MAX_LAGGING_PERIODS * period_vtime) &&
@@ -1531,26 +1532,29 @@ skip_surplus_transfers:
 	 * and experiencing shortages but not surpluses, we're too stingy
 	 * and should increase vtime rate.
 	 */
+	prev_busy_level = ioc->busy_level;
 	if (rq_wait_pct > RQ_WAIT_BUSY_PCT ||
 	    missed_ppm[READ] > ppm_rthr ||
 	    missed_ppm[WRITE] > ppm_wthr) {
 		ioc->busy_level = max(ioc->busy_level, 0);
 		ioc->busy_level++;
-	} else if (nr_lagging) {
-		ioc->busy_level = max(ioc->busy_level, 0);
-	} else if (nr_shortages && !nr_surpluses &&
-		   rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 &&
+	} else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 &&
 		   missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 &&
 		   missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) {
-		ioc->busy_level = min(ioc->busy_level, 0);
-		ioc->busy_level--;
+		/* take action iff there is contention */
+		if (nr_shortages && !nr_lagging) {
+			ioc->busy_level = min(ioc->busy_level, 0);
+			/* redistribute surpluses first */
+			if (!nr_surpluses)
+				ioc->busy_level--;
+		}
 	} else {
 		ioc->busy_level = 0;
 	}
 
 	ioc->busy_level = clamp(ioc->busy_level, -1000, 1000);
 
-	if (ioc->busy_level) {
+	if (ioc->busy_level > 0 || (ioc->busy_level < 0 && !nr_lagging)) {
 		u64 vrate = atomic64_read(&ioc->vtime_rate);
 		u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max;
 
@@ -1592,6 +1596,10 @@ skip_surplus_transfers:
 		atomic64_set(&ioc->vtime_rate, vrate);
 		ioc->inuse_margin_vtime = DIV64_U64_ROUND_UP(
 			ioc->period_us * vrate * INUSE_MARGIN_PCT, 100);
+	} else if (ioc->busy_level != prev_busy_level || nr_lagging) {
+		trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate),
+					   &missed_ppm, rq_wait_pct, nr_lagging,
+					   nr_shortages, nr_surpluses);
 	}
 
 	ioc_refresh_params(ioc, false);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index c9d183d6c49995..ca22afd47b3dcc 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -555,8 +555,6 @@ void blk_mq_sched_free_requests(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	lockdep_assert_held(&q->sysfs_lock);
-
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->sched_tags)
 			blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 29275f5a996f3d..6e3b15f70cd7ae 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -918,7 +918,10 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	 */
 	if (blk_mq_req_expired(rq, next))
 		blk_mq_rq_timed_out(rq, reserved);
-	if (refcount_dec_and_test(&rq->ref))
+
+	if (is_flush_rq(rq, hctx))
+		rq->end_io(rq, 0);
+	else if (refcount_dec_and_test(&rq->ref))
 		__blk_mq_free_request(rq);
 
 	return true;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index b82736c781c517..46f5198be01732 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -482,7 +482,6 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	blk_mq_quiesce_queue(q);
 
 	wbt_set_min_lat(q, val);
-	wbt_update_limits(q);
 
 	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
@@ -989,13 +988,11 @@ int blk_register_queue(struct gendisk *disk)
 		blk_mq_debugfs_register(q);
 	}
 
-	/*
-	 * The flag of QUEUE_FLAG_REGISTERED isn't set yet, so elevator
-	 * switch won't happen at all.
-	 */
+	mutex_lock(&q->sysfs_lock);
 	if (q->elevator) {
 		ret = elv_register_queue(q, false);
 		if (ret) {
+			mutex_unlock(&q->sysfs_lock);
 			mutex_unlock(&q->sysfs_dir_lock);
 			kobject_del(&q->kobj);
 			blk_trace_remove_sysfs(dev);
@@ -1005,7 +1002,6 @@ int blk_register_queue(struct gendisk *disk)
 		has_elevator = true;
 	}
 
-	mutex_lock(&q->sysfs_lock);
 	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 	wbt_enable_default(q);
 	blk_throtl_register_queue(q);
@@ -1062,12 +1058,10 @@ void blk_unregister_queue(struct gendisk *disk)
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	/*
-	 * q->kobj has been removed, so it is safe to check if elevator
-	 * exists without holding q->sysfs_lock.
-	 */
+	mutex_lock(&q->sysfs_lock);
 	if (q->elevator)
 		elv_unregister_queue(q);
+	mutex_unlock(&q->sysfs_lock);
 	mutex_unlock(&q->sysfs_dir_lock);
 
 	kobject_put(&disk_to_dev(disk)->kobj);
diff --git a/block/blk.h b/block/blk.h
index ed347f7a97b138..47fba9362e60dd 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -19,6 +19,7 @@ struct blk_flush_queue {
 	unsigned int		flush_queue_delayed:1;
 	unsigned int		flush_pending_idx:1;
 	unsigned int		flush_running_idx:1;
+	blk_status_t 		rq_status;
 	unsigned long		flush_pending_since;
 	struct list_head	flush_queue[2];
 	struct list_head	flush_data_in_flight;
@@ -47,6 +48,12 @@ static inline void __blk_get_queue(struct request_queue *q)
 	kobject_get(&q->kobj);
 }
 
+static inline bool
+is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
+{
+	return hctx->fq->flush_rq == req;
+}
+
 struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
 		int node, int cmd_size, gfp_t flags);
 void blk_free_flush_queue(struct blk_flush_queue *q);
@@ -194,6 +201,8 @@ void elv_unregister_queue(struct request_queue *q);
 static inline void elevator_exit(struct request_queue *q,
 		struct elevator_queue *e)
 {
+	lockdep_assert_held(&q->sysfs_lock);
+
 	blk_mq_sched_free_requests(q);
 	__elevator_exit(q, e);
 }
diff --git a/block/elevator.c b/block/elevator.c
index bba10e83478a09..5437059c92615e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -503,9 +503,7 @@ int elv_register_queue(struct request_queue *q, bool uevent)
 		if (uevent)
 			kobject_uevent(&e->kobj, KOBJ_ADD);
 
-		mutex_lock(&q->sysfs_lock);
 		e->registered = 1;
-		mutex_unlock(&q->sysfs_lock);
 	}
 	return error;
 }
@@ -523,11 +521,9 @@ void elv_unregister_queue(struct request_queue *q)
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
 		kobject_del(&e->kobj);
 
-		mutex_lock(&q->sysfs_lock);
 		e->registered = 0;
 		/* Re-enable throttling in case elevator disabled it */
 		wbt_enable_default(q);
-		mutex_unlock(&q->sysfs_lock);
 	}
 }
 
@@ -590,32 +586,11 @@ int elevator_switch_mq(struct request_queue *q,
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (q->elevator) {
-		if (q->elevator->registered) {
-			mutex_unlock(&q->sysfs_lock);
-
-			/*
-			 * Concurrent elevator switch can't happen becasue
-			 * sysfs write is always exclusively on same file.
-			 *
-			 * Also the elevator queue won't be freed after
-			 * sysfs_lock is released becasue kobject_del() in
-			 * blk_unregister_queue() waits for completion of
-			 * .store & .show on its attributes.
-			 */
+		if (q->elevator->registered)
 			elv_unregister_queue(q);
 
-			mutex_lock(&q->sysfs_lock);
-		}
 		ioc_clear_queue(q);
 		elevator_exit(q, q->elevator);
-
-		/*
-		 * sysfs_lock may be dropped, so re-check if queue is
-		 * unregistered. If yes, don't switch to new elevator
-		 * any more
-		 */
-		if (!blk_queue_registered(q))
-			return 0;
 	}
 
 	ret = blk_mq_init_sched(q, new_e);
@@ -623,11 +598,7 @@ int elevator_switch_mq(struct request_queue *q,
 		goto out;
 
 	if (new_e) {
-		mutex_unlock(&q->sysfs_lock);
-
 		ret = elv_register_queue(q, true);
-
-		mutex_lock(&q->sysfs_lock);
 		if (ret) {
 			elevator_exit(q, q->elevator);
 			goto out;