Merge tag 'block-5.15-2021-10-17' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Bigger than usual for this point in time, the majority is fixing some
  issues around BDI lifetimes with the move from the request_queue to
  the disk in this release. In detail:

   - Series on draining fs IO for del_gendisk() (Christoph)

   - NVMe pull request via Christoph:
        - fix the abort command id (Keith Busch)
        - nvme: fix per-namespace chardev deletion (Adam Manzanares)

   - brd locking scope fix (Tetsuo)

   - BFQ fix (Paolo)"

* tag 'block-5.15-2021-10-17' of git://git.kernel.dk/linux-block:
  block, bfq: reset last_bfqq_created on group change
  block: warn when putting the final reference on a registered disk
  brd: reduce the brd_devices_mutex scope
  kyber: avoid q->disk dereferences in trace points
  block: keep q_usage_counter in atomic mode after del_gendisk
  block: drain file system I/O on del_gendisk
  block: split bio_queue_enter from blk_queue_enter
  block: factor out a blk_try_enter_queue helper
  block: call submit_bio_checks under q_usage_counter
  nvme: fix per-namespace chardev deletion
  block/rnbd-clt-sysfs: fix a couple uninitialized variable bugs
  nvme-pci: Fix abort command id

6 files changed, 123 insertions, 75 deletions

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index e2f14508f2d6..85b8e1c3a762 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -666,6 +666,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
 	bfqg_and_blkg_put(bfqq_group(bfqq));
 
+	if (entity->parent &&
+	    entity->parent->last_bfqq_created == bfqq)
+		entity->parent->last_bfqq_created = NULL;
+	else if (bfqd->last_bfqq_created == bfqq)
+		bfqd->last_bfqq_created = NULL;
+
 	entity->parent = bfqg->my_entity;
 	entity->sched_data = &bfqg->sched_data;
 	/* pin down bfqg and its associated blkg  */
diff --git a/block/blk-core.c b/block/blk-core.c
index 5454db2fa263..4d8f5fe91588 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -49,7 +49,6 @@
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
 #include "blk-pm.h"
-#include "blk-rq-qos.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -337,23 +336,25 @@ void blk_put_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_put_queue);
 
-void blk_set_queue_dying(struct request_queue *q)
+void blk_queue_start_drain(struct request_queue *q)
 {
-	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-
 	/*
 	 * When queue DYING flag is set, we need to block new req
 	 * entering queue, so we call blk_freeze_queue_start() to
 	 * prevent I/O from crossing blk_queue_enter().
 	 */
 	blk_freeze_queue_start(q);
-
 	if (queue_is_mq(q))
 		blk_mq_wake_waiters(q);
-
 	/* Make blk_queue_enter() reexamine the DYING flag. */
 	wake_up_all(&q->mq_freeze_wq);
 }
+
+void blk_set_queue_dying(struct request_queue *q)
+{
+	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+	blk_queue_start_drain(q);
+}
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
 /**
@@ -385,13 +386,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	blk_freeze_queue(q);
 
-	rq_qos_exit(q);
-
 	blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
 
-	/* for synchronous bio-based driver finish in-flight integrity i/o */
-	blk_flush_integrity();
-
 	blk_sync_queue(q);
 	if (queue_is_mq(q))
 		blk_mq_exit_queue(q);
@@ -416,6 +412,30 @@ void blk_cleanup_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
 
+static bool blk_try_enter_queue(struct request_queue *q, bool pm)
+{
+	rcu_read_lock();
+	if (!percpu_ref_tryget_live(&q->q_usage_counter))
+		goto fail;
+
+	/*
+	 * The code that increments the pm_only counter must ensure that the
+	 * counter is globally visible before the queue is unfrozen.
+	 */
+	if (blk_queue_pm_only(q) &&
+	    (!pm || queue_rpm_status(q) == RPM_SUSPENDED))
+		goto fail_put;
+
+	rcu_read_unlock();
+	return true;
+
+fail_put:
+	percpu_ref_put(&q->q_usage_counter);
+fail:
+	rcu_read_unlock();
+	return false;
+}
+
 /**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
@@ -425,40 +445,18 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
 	const bool pm = flags & BLK_MQ_REQ_PM;
 
-	while (true) {
-		bool success = false;
-
-		rcu_read_lock();
-		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
-			/*
-			 * The code that increments the pm_only counter is
-			 * responsible for ensuring that that counter is
-			 * globally visible before the queue is unfrozen.
-			 */
-			if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) ||
-			    !blk_queue_pm_only(q)) {
-				success = true;
-			} else {
-				percpu_ref_put(&q->q_usage_counter);
-			}
-		}
-		rcu_read_unlock();
-
-		if (success)
-			return 0;
-
+	while (!blk_try_enter_queue(q, pm)) {
 		if (flags & BLK_MQ_REQ_NOWAIT)
 			return -EBUSY;
 
 		/*
-		 * read pair of barrier in blk_freeze_queue_start(),
-		 * we need to order reading __PERCPU_REF_DEAD flag of
-		 * .q_usage_counter and reading .mq_freeze_depth or
-		 * queue dying flag, otherwise the following wait may
-		 * never return if the two reads are reordered.
+		 * read pair of barrier in blk_freeze_queue_start(), we need to
+		 * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and
+		 * reading .mq_freeze_depth or queue dying flag, otherwise the
+		 * following wait may never return if the two reads are
+		 * reordered.
 		 */
 		smp_rmb();
-
 		wait_event(q->mq_freeze_wq,
 			   (!q->mq_freeze_depth &&
 			    blk_pm_resume_queue(pm, q)) ||
@@ -466,23 +464,43 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 		if (blk_queue_dying(q))
 			return -ENODEV;
 	}
+
+	return 0;
 }
 
 static inline int bio_queue_enter(struct bio *bio)
 {
-	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
-	bool nowait = bio->bi_opf & REQ_NOWAIT;
-	int ret;
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	struct request_queue *q = disk->queue;
 
-	ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0);
-	if (unlikely(ret)) {
-		if (nowait && !blk_queue_dying(q))
+	while (!blk_try_enter_queue(q, false)) {
+		if (bio->bi_opf & REQ_NOWAIT) {
+			if (test_bit(GD_DEAD, &disk->state))
+				goto dead;
 			bio_wouldblock_error(bio);
-		else
-			bio_io_error(bio);
+			return -EBUSY;
+		}
+
+		/*
+		 * read pair of barrier in blk_freeze_queue_start(), we need to
+		 * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and
+		 * reading .mq_freeze_depth or queue dying flag, otherwise the
+		 * following wait may never return if the two reads are
+		 * reordered.
+		 */
+		smp_rmb();
+		wait_event(q->mq_freeze_wq,
+			   (!q->mq_freeze_depth &&
+			    blk_pm_resume_queue(false, q)) ||
+			   test_bit(GD_DEAD, &disk->state));
+		if (test_bit(GD_DEAD, &disk->state))
+			goto dead;
 	}
 
-	return ret;
+	return 0;
+dead:
+	bio_io_error(bio);
+	return -ENODEV;
 }
 
 void blk_queue_exit(struct request_queue *q)
@@ -899,11 +917,18 @@ static blk_qc_t __submit_bio(struct bio *bio)
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
 	blk_qc_t ret = BLK_QC_T_NONE;
 
-	if (blk_crypto_bio_prep(&bio)) {
-		if (!disk->fops->submit_bio)
-			return blk_mq_submit_bio(bio);
+	if (unlikely(bio_queue_enter(bio) != 0))
+		return BLK_QC_T_NONE;
+
+	if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio))
+		goto queue_exit;
+	if (disk->fops->submit_bio) {
 		ret = disk->fops->submit_bio(bio);
+		goto queue_exit;
 	}
+	return blk_mq_submit_bio(bio);
+
+queue_exit:
 	blk_queue_exit(disk->queue);
 	return ret;
 }
@@ -941,9 +966,6 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 		struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 		struct bio_list lower, same;
 
-		if (unlikely(bio_queue_enter(bio) != 0))
-			continue;
-
 		/*
 		 * Create a fresh bio_list for all subordinate requests.
 		 */
@@ -979,23 +1001,12 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
-	blk_qc_t ret = BLK_QC_T_NONE;
+	blk_qc_t ret;
 
 	current->bio_list = bio_list;
 
 	do {
-		struct gendisk *disk = bio->bi_bdev->bd_disk;
-
-		if (unlikely(bio_queue_enter(bio) != 0))
-			continue;
-
-		if (!blk_crypto_bio_prep(&bio)) {
-			blk_queue_exit(disk->queue);
-			ret = BLK_QC_T_NONE;
-			continue;
-		}
-
-		ret = blk_mq_submit_bio(bio);
+		ret = __submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
 	current->bio_list = NULL;
@@ -1013,9 +1024,6 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
  */
 blk_qc_t submit_bio_noacct(struct bio *bio)
 {
-	if (!submit_bio_checks(bio))
-		return BLK_QC_T_NONE;
-
 	/*
 	 * We only want one ->submit_bio to be active at a time, else stack
 	 * usage with stacked devices could be a problem.  Use current->bio_list
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 108a352051be..bc026372de43 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -188,9 +188,11 @@ void blk_mq_freeze_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
-void blk_mq_unfreeze_queue(struct request_queue *q)
+void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 {
 	mutex_lock(&q->mq_freeze_lock);
+	if (force_atomic)
+		q->q_usage_counter.data->force_atomic = true;
 	q->mq_freeze_depth--;
 	WARN_ON_ONCE(q->mq_freeze_depth < 0);
 	if (!q->mq_freeze_depth) {
@@ -199,6 +201,11 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 	}
 	mutex_unlock(&q->mq_freeze_lock);
 }
+
+void blk_mq_unfreeze_queue(struct request_queue *q)
+{
+	__blk_mq_unfreeze_queue(q, false);
+}
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
 /*
diff --git a/block/blk.h b/block/blk.h
index 7d2a0ba7ed21..6c3c00a8fe19 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -51,6 +51,8 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
 void blk_free_flush_queue(struct blk_flush_queue *q);
 
 void blk_freeze_queue(struct request_queue *q);
+void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic);
+void blk_queue_start_drain(struct request_queue *q);
 
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
diff --git a/block/genhd.c b/block/genhd.c
index 496e8458c357..b49858550fa6 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -26,6 +26,7 @@
 #include <linux/badblocks.h>
 
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 static struct kobject *block_depr;
 
@@ -559,6 +560,8 @@ EXPORT_SYMBOL(device_add_disk);
  */
 void del_gendisk(struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
+
 	might_sleep();
 
 	if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN)))
@@ -575,8 +578,27 @@ void del_gendisk(struct gendisk *disk)
 	fsync_bdev(disk->part0);
 	__invalidate_device(disk->part0, true);
 
+	/*
+	 * Fail any new I/O.
+	 */
+	set_bit(GD_DEAD, &disk->state);
 	set_capacity(disk, 0);
 
+	/*
+	 * Prevent new I/O from crossing bio_queue_enter().
+	 */
+	blk_queue_start_drain(q);
+	blk_mq_freeze_queue_wait(q);
+
+	rq_qos_exit(q);
+	blk_sync_queue(q);
+	blk_flush_integrity();
+	/*
+	 * Allow using passthrough request again after the queue is torn down.
+	 */
+	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+	__blk_mq_unfreeze_queue(q, true);
+
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
 
@@ -1056,6 +1078,7 @@ static void disk_release(struct device *dev)
 	struct gendisk *disk = dev_to_disk(dev);
 
 	might_sleep();
+	WARN_ON_ONCE(disk_live(disk));
 
 	disk_release_events(disk);
 	kfree(disk->random);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 15a8be57203d..a0ffbabfac2c 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -151,6 +151,7 @@ struct kyber_ctx_queue {
 
 struct kyber_queue_data {
 	struct request_queue *q;
+	dev_t dev;
 
 	/*
 	 * Each scheduling domain has a limited number of in-flight requests
@@ -257,7 +258,7 @@ static int calculate_percentile(struct kyber_queue_data *kqd,
 	}
 	memset(buckets, 0, sizeof(kqd->latency_buckets[sched_domain][type]));
 
-	trace_kyber_latency(kqd->q, kyber_domain_names[sched_domain],
+	trace_kyber_latency(kqd->dev, kyber_domain_names[sched_domain],
 			    kyber_latency_type_names[type], percentile,
 			    bucket + 1, 1 << KYBER_LATENCY_SHIFT, samples);
 
@@ -270,7 +271,7 @@ static void kyber_resize_domain(struct kyber_queue_data *kqd,
 	depth = clamp(depth, 1U, kyber_depth[sched_domain]);
 	if (depth != kqd->domain_tokens[sched_domain].sb.depth) {
 		sbitmap_queue_resize(&kqd->domain_tokens[sched_domain], depth);
-		trace_kyber_adjust(kqd->q, kyber_domain_names[sched_domain],
+		trace_kyber_adjust(kqd->dev, kyber_domain_names[sched_domain],
 				   depth);
 	}
 }
@@ -366,6 +367,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
 		goto err;
 
 	kqd->q = q;
+	kqd->dev = disk_devt(q->disk);
 
 	kqd->cpu_latency = alloc_percpu_gfp(struct kyber_cpu_latency,
 					    GFP_KERNEL | __GFP_ZERO);
@@ -774,7 +776,7 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
 			list_del_init(&rq->queuelist);
 			return rq;
 		} else {
-			trace_kyber_throttled(kqd->q,
+			trace_kyber_throttled(kqd->dev,
 					      kyber_domain_names[khd->cur_domain]);
 		}
 	} else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) {
@@ -787,7 +789,7 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
 			list_del_init(&rq->queuelist);
 			return rq;
 		} else {
-			trace_kyber_throttled(kqd->q,
+			trace_kyber_throttled(kqd->dev,
 					      kyber_domain_names[khd->cur_domain]);
 		}
 	}