block-5.19-2022-06-24

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmK19ZkQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpsyBD/9whWHSyTpVftMJHJC64E+orbjeu2jFOg3P
 XjrwQ6caqCu+JjsnZWi7EzQv/UyJrWgjX3blPOl+1kiiM4LyPkzHlaFTJFZWNmUz
 6JFmAGWybOywUauwynIPT32Jc7ccbqGMy7QbEUWNiAxa384F57fPx2rUcEgD8nSB
 GGr+ljZdEcfdJ6BRrwBexfS07aVrt8SYwnluO6h1YHbxlO9cw+6ga8Y0z6ncBVFW
 XDqkzwH3oqUaGlHqu879rtQpedaB2zz/sUvWiy+KbBTyN4K/vE5ja3/x8OyIcfIU
 8LWwOCSOZeo1i7juXNFr7Ay1ldGsn6D5QeT0oNGDUh893JUz4kVI+iyoIqvVkLTE
 4MQohMddahlsf95sH/xuvJQ2WMXmy1ZjkaaDCws55zqIr6baRuI44jOFElKy2Peu
 0X7qWwri9Uk/zzCo6LhOKbcvLBriy89YchY9I3thSWIrSTx9QoIbgs8z2kG2qYx8
 pbfSKASUfyXcdgOIanCmS2+On7T7lDLEflCm/WvTDoc07OI+CpsjnIFv1CtB/sy2
 bwC35rCuo+EukDZiFDtsNsvbeVnCo3l0WC+rozean5j6zz64hdpC/eofwJmn2RfZ
 U9Ob0aDl4P+8Jta6Iqlfae78ZPAPcCzyvLb0k0l3ceMIY65x3Ss85JEFF7SA/VwJ
 /Dn12frm4Q==
 =3uDs
 -----END PGP SIGNATURE-----

Merge tag 'block-5.19-2022-06-24' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Series fixing issues with sysfs locking and name reuse (Christoph)

 - NVMe pull request via Christoph:
      - Fix the mixed up CRIMS/CRWMS constants (Joel Granados)
      - Add another broken identifier quirk (Leo Savernik)
      - Fix up a quirk because Samsung reuses PCI IDs over different
        products (Christoph Hellwig)

 - Remove old WARN_ON() that doesn't apply anymore (Li)

 - Fix for using a stale cached request value for rq-qos throttling
   mechanisms that may schedule(), like iocost (me)

 - Remove unused parameter to blk_independent_access_range() (Damien)

* tag 'block-5.19-2022-06-24' of git://git.kernel.dk/linux-block:
  block: remove WARN_ON() from bd_link_disk_holder
  nvme: move the Samsung X5 quirk entry to the core quirks
  nvme: fix the CRIMS and CRWMS definitions to match the spec
  nvme: add a bogus subsystem NQN quirk for Micron MTFDKBA2T0TFH
  block: pop cached rq before potentially blocking rq_qos_throttle()
  block: remove queue from struct blk_independent_access_range
  block: freeze the queue earlier in del_gendisk
  block: remove per-disk debugfs files in blk_unregister_queue
  block: serialize all debugfs operations using q->debugfs_mutex
  block: disable the elevator int del_gendisk

block/blk-core.c

@@ -322,19 +322,6 @@ void blk_cleanup_queue(struct request_queue *q)
 		blk_mq_exit_queue(q);
 	}
 
-	/*
-	 * In theory, request pool of sched_tags belongs to request queue.
-	 * However, the current implementation requires tag_set for freeing
-	 * requests, so free the pool now.
-	 *
-	 * Queue has become frozen, there can't be any in-queue requests, so
-	 * it is safe to free requests now.
-	 */
-	mutex_lock(&q->sysfs_lock);
-	if (q->elevator)
-		blk_mq_sched_free_rqs(q);
-	mutex_unlock(&q->sysfs_lock);
-
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }

block/blk-ia-ranges.c

@@ -144,7 +144,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk,
 	}
 
 	for (i = 0; i < iars->nr_ia_ranges; i++) {
-		iars->ia_range[i].queue = q;
 		ret = kobject_init_and_add(&iars->ia_range[i].kobj,
 					   &blk_ia_range_ktype, &iars->kobj,
 					   "%d", i);

block/blk-mq-debugfs.c

@@ -711,11 +711,6 @@ void blk_mq_debugfs_register(struct request_queue *q)
 	}
 }
 
-void blk_mq_debugfs_unregister(struct request_queue *q)
-{
-	q->sched_debugfs_dir = NULL;
-}
-
 static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *ctx)
 {
@@ -746,6 +741,8 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q,
 
 void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
 {
+	if (!hctx->queue->debugfs_dir)
+		return;
 	debugfs_remove_recursive(hctx->debugfs_dir);
 	hctx->sched_debugfs_dir = NULL;
 	hctx->debugfs_dir = NULL;
@@ -773,6 +770,8 @@ void blk_mq_debugfs_register_sched(struct request_queue *q)
 {
 	struct elevator_type *e = q->elevator->type;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	/*
 	 * If the parent directory has not been created yet, return, we will be
 	 * called again later on and the directory/files will be created then.
@@ -790,6 +789,8 @@ void blk_mq_debugfs_register_sched(struct request_queue *q)
 
 void blk_mq_debugfs_unregister_sched(struct request_queue *q)
 {
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	debugfs_remove_recursive(q->sched_debugfs_dir);
 	q->sched_debugfs_dir = NULL;
 }
@@ -811,6 +812,10 @@ static const char *rq_qos_id_to_name(enum rq_qos_id id)
 
 void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
 {
+	lockdep_assert_held(&rqos->q->debugfs_mutex);
+
+	if (!rqos->q->debugfs_dir)
+		return;
 	debugfs_remove_recursive(rqos->debugfs_dir);
 	rqos->debugfs_dir = NULL;
 }
@@ -820,6 +825,8 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos)
 	struct request_queue *q = rqos->q;
 	const char *dir_name = rq_qos_id_to_name(rqos->id);
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	if (rqos->debugfs_dir || !rqos->ops->debugfs_attrs)
 		return;
 
@@ -833,17 +840,13 @@ void blk_mq_debugfs_register_rqos(struct rq_qos *rqos)
 	debugfs_create_files(rqos->debugfs_dir, rqos, rqos->ops->debugfs_attrs);
 }
 
-void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q)
-{
-	debugfs_remove_recursive(q->rqos_debugfs_dir);
-	q->rqos_debugfs_dir = NULL;
-}
-
 void blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
 					struct blk_mq_hw_ctx *hctx)
 {
 	struct elevator_type *e = q->elevator->type;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	/*
 	 * If the parent debugfs directory has not been created yet, return;
 	 * We will be called again later on with appropriate parent debugfs
@@ -863,6 +866,10 @@ void blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
 
 void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx)
 {
+	lockdep_assert_held(&hctx->queue->debugfs_mutex);
+
+	if (!hctx->queue->debugfs_dir)
+		return;
 	debugfs_remove_recursive(hctx->sched_debugfs_dir);
 	hctx->sched_debugfs_dir = NULL;
 }

block/blk-mq-debugfs.h

@@ -21,7 +21,6 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq);
 int blk_mq_debugfs_rq_show(struct seq_file *m, void *v);
 
 void blk_mq_debugfs_register(struct request_queue *q);
-void blk_mq_debugfs_unregister(struct request_queue *q);
 void blk_mq_debugfs_register_hctx(struct request_queue *q,
 				  struct blk_mq_hw_ctx *hctx);
 void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx);
@@ -36,16 +35,11 @@ void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_debugfs_register_rqos(struct rq_qos *rqos);
 void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos);
-void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q);
 #else
 static inline void blk_mq_debugfs_register(struct request_queue *q)
 {
 }
 
-static inline void blk_mq_debugfs_unregister(struct request_queue *q)
-{
-}
-
 static inline void blk_mq_debugfs_register_hctx(struct request_queue *q,
 						struct blk_mq_hw_ctx *hctx)
 {
@@ -87,10 +81,6 @@ static inline void blk_mq_debugfs_register_rqos(struct rq_qos *rqos)
 static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
 {
 }
-
-static inline void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q)
-{
-}
 #endif
 
 #ifdef CONFIG_BLK_DEBUG_FS_ZONED

block/blk-mq-sched.c

@@ -594,7 +594,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	if (ret)
 		goto err_free_map_and_rqs;
 
+	mutex_lock(&q->debugfs_mutex);
 	blk_mq_debugfs_register_sched(q);
+	mutex_unlock(&q->debugfs_mutex);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (e->ops.init_hctx) {
@@ -607,7 +609,9 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 				return ret;
 			}
 		}
+		mutex_lock(&q->debugfs_mutex);
 		blk_mq_debugfs_register_sched_hctx(q, hctx);
+		mutex_unlock(&q->debugfs_mutex);
 	}
 
 	return 0;
@@ -648,14 +652,21 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 	unsigned int flags = 0;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
+		mutex_lock(&q->debugfs_mutex);
 		blk_mq_debugfs_unregister_sched_hctx(hctx);
+		mutex_unlock(&q->debugfs_mutex);
+
 		if (e->type->ops.exit_hctx && hctx->sched_data) {
 			e->type->ops.exit_hctx(hctx, i);
 			hctx->sched_data = NULL;
 		}
 		flags = hctx->flags;
 	}
+
+	mutex_lock(&q->debugfs_mutex);
 	blk_mq_debugfs_unregister_sched(q);
+	mutex_unlock(&q->debugfs_mutex);
+
 	if (e->type->ops.exit_sched)
 		e->type->ops.exit_sched(e);
 	blk_mq_sched_tags_teardown(q, flags);

block/blk-mq.c

@@ -2765,15 +2765,20 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 		return NULL;
 	}
 
-	rq_qos_throttle(q, *bio);
-
 	if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type)
 		return NULL;
 	if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
 		return NULL;
 
-	rq->cmd_flags = (*bio)->bi_opf;
+	/*
+	 * If any qos ->throttle() end up blocking, we will have flushed the
+	 * plug and hence killed the cached_rq list as well. Pop this entry
+	 * before we throttle.
+	 */
 	plug->cached_rq = rq_list_next(rq);
+	rq_qos_throttle(q, *bio);
+
+	rq->cmd_flags = (*bio)->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
 	return rq;
 }

block/blk-rq-qos.c

@@ -294,8 +294,6 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
 
 void rq_qos_exit(struct request_queue *q)
 {
-	blk_mq_debugfs_unregister_queue_rqos(q);
-
 	while (q->rq_qos) {
 		struct rq_qos *rqos = q->rq_qos;
 		q->rq_qos = rqos->next;

block/blk-rq-qos.h

@@ -104,8 +104,11 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 
 	blk_mq_unfreeze_queue(q);
 
-	if (rqos->ops->debugfs_attrs)
+	if (rqos->ops->debugfs_attrs) {
+		mutex_lock(&q->debugfs_mutex);
 		blk_mq_debugfs_register_rqos(rqos);
+		mutex_unlock(&q->debugfs_mutex);
+	}
 }
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
@@ -129,7 +132,9 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
 
 	blk_mq_unfreeze_queue(q);
 
+	mutex_lock(&q->debugfs_mutex);
 	blk_mq_debugfs_unregister_rqos(rqos);
+	mutex_unlock(&q->debugfs_mutex);
 }
 
 typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data);

block/blk-sysfs.c

@@ -779,14 +779,6 @@ static void blk_release_queue(struct kobject *kobj)
 	if (queue_is_mq(q))
 		blk_mq_release(q);
 
-	blk_trace_shutdown(q);
-	mutex_lock(&q->debugfs_mutex);
-	debugfs_remove_recursive(q->debugfs_dir);
-	mutex_unlock(&q->debugfs_mutex);
-
-	if (queue_is_mq(q))
-		blk_mq_debugfs_unregister(q);
-
 	bioset_exit(&q->bio_split);
 
 	if (blk_queue_has_srcu(q))
@@ -836,17 +828,16 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	if (queue_is_mq(q))
+		__blk_mq_register_dev(dev, q);
+	mutex_lock(&q->sysfs_lock);
+
 	mutex_lock(&q->debugfs_mutex);
 	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
 					    blk_debugfs_root);
-	mutex_unlock(&q->debugfs_mutex);
-
-	if (queue_is_mq(q)) {
-		__blk_mq_register_dev(dev, q);
+	if (queue_is_mq(q))
 		blk_mq_debugfs_register(q);
-	}
-
-	mutex_lock(&q->sysfs_lock);
+	mutex_unlock(&q->debugfs_mutex);
 
 	ret = disk_register_independent_access_ranges(disk, NULL);
 	if (ret)
@@ -948,8 +939,15 @@ void blk_unregister_queue(struct gendisk *disk)
 	/* Now that we've deleted all child objects, we can delete the queue. */
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
 	kobject_del(&q->kobj);
-
 	mutex_unlock(&q->sysfs_dir_lock);
 
+	mutex_lock(&q->debugfs_mutex);
+	blk_trace_shutdown(q);
+	debugfs_remove_recursive(q->debugfs_dir);
+	q->debugfs_dir = NULL;
+	q->sched_debugfs_dir = NULL;
+	q->rqos_debugfs_dir = NULL;
+	mutex_unlock(&q->debugfs_mutex);
+
 	kobject_put(&disk_to_dev(disk)->kobj);
 }

block/genhd.c

@@ -623,6 +623,7 @@ void del_gendisk(struct gendisk *disk)
 	 * Prevent new I/O from crossing bio_queue_enter().
 	 */
 	blk_queue_start_drain(q);
+	blk_mq_freeze_queue_wait(q);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -646,12 +647,21 @@ void del_gendisk(struct gendisk *disk)
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
 
-	blk_mq_freeze_queue_wait(q);
-
 	blk_throtl_cancel_bios(disk->queue);
 
 	blk_sync_queue(q);
 	blk_flush_integrity();
+	blk_mq_cancel_work_sync(q);
+
+	blk_mq_quiesce_queue(q);
+	if (q->elevator) {
+		mutex_lock(&q->sysfs_lock);
+		elevator_exit(q);
+		mutex_unlock(&q->sysfs_lock);
+	}
+	rq_qos_exit(q);
+	blk_mq_unquiesce_queue(q);
+
 	/*
 	 * Allow using passthrough request again after the queue is torn down.
 	 */
@@ -1120,31 +1130,6 @@ static const struct attribute_group *disk_attr_groups[] = {
 	NULL
 };
 
-static void disk_release_mq(struct request_queue *q)
-{
-	blk_mq_cancel_work_sync(q);
-
-	/*
-	 * There can't be any non non-passthrough bios in flight here, but
-	 * requests stay around longer, including passthrough ones so we
-	 * still need to freeze the queue here.
-	 */
-	blk_mq_freeze_queue(q);
-
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		mutex_lock(&q->sysfs_lock);
-		elevator_exit(q);
-		mutex_unlock(&q->sysfs_lock);
-	}
-	rq_qos_exit(q);
-	__blk_mq_unfreeze_queue(q, true);
-}
-
 /**
  * disk_release - releases all allocated resources of the gendisk
  * @dev: the device representing this disk
@@ -1166,9 +1151,6 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
-	if (queue_is_mq(disk->queue))
-		disk_release_mq(disk->queue);
-
 	blkcg_exit_queue(disk->queue);
 
 	disk_release_events(disk);

block/holder.c

@@ -79,10 +79,6 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
 
 	WARN_ON_ONCE(!bdev->bd_holder);
 
-	/* FIXME: remove the following once add_disk() handles errors */
-	if (WARN_ON(!bdev->bd_holder_dir))
-		goto out_unlock;
-
 	holder = bd_find_holder_disk(bdev, disk);
 	if (holder) {
 		holder->refcnt++;

drivers/nvme/host/core.c

@@ -2546,6 +2546,20 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
 		.vid = 0x1e0f,
 		.mn = "KCD6XVUL6T40",
 		.quirks = NVME_QUIRK_NO_APST,
+	},
+	{
+		/*
+		 * The external Samsung X5 SSD fails initialization without a
+		 * delay before checking if it is ready and has a whole set of
+		 * other problems.  To make this even more interesting, it
+		 * shares the PCI ID with internal Samsung 970 Evo Plus that
+		 * does not need or want these quirks.
+		 */
+		.vid = 0x144d,
+		.mn = "Samsung Portable SSD X5",
+		.quirks = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+			  NVME_QUIRK_NO_DEEPEST_PS |
+			  NVME_QUIRK_IGNORE_DEV_SUBNQN,
 	}
 };
 

drivers/nvme/host/pci.c

@@ -3474,6 +3474,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	 { PCI_DEVICE(0x1344, 0x5407), /* Micron Technology Inc NVMe SSD */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN },
 	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1c5c, 0x174a),   /* SK Hynix P31 SSD */
@@ -3524,10 +3526,6 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_128_BYTES_SQES |
 				NVME_QUIRK_SHARED_TAGS |
 				NVME_QUIRK_SKIP_CID_GEN },
-	{ PCI_DEVICE(0x144d, 0xa808),   /* Samsung X5 */
-		.driver_data =  NVME_QUIRK_DELAY_BEFORE_CHK_RDY|
-				NVME_QUIRK_NO_DEEPEST_PS |
-				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };

include/linux/blkdev.h

@@ -342,7 +342,6 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
  */
 struct blk_independent_access_range {
 	struct kobject		kobj;
-	struct request_queue	*queue;
 	sector_t		sector;
 	sector_t		nr_sectors;
 };
@@ -482,7 +481,6 @@ struct request_queue {
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 	int			node;
-	struct mutex		debugfs_mutex;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
 #endif
@@ -526,11 +524,12 @@ struct request_queue {
 	struct bio_set		bio_split;
 
 	struct dentry		*debugfs_dir;
-
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
-#endif
+	/*
+	 * Serializes all debugfs metadata operations using the above dentries.
+	 */
+	struct mutex		debugfs_mutex;
 
 	bool			mq_sysfs_init_done;
 

include/linux/nvme.h

@@ -233,8 +233,8 @@ enum {
 };
 
 enum {
-	NVME_CAP_CRMS_CRIMS	= 1ULL << 59,
-	NVME_CAP_CRMS_CRWMS	= 1ULL << 60,
+	NVME_CAP_CRMS_CRWMS	= 1ULL << 59,
+	NVME_CAP_CRMS_CRIMS	= 1ULL << 60,
 };
 
 struct nvme_id_power_state {

kernel/trace/blktrace.c

@@ -770,14 +770,11 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
-	mutex_lock(&q->debugfs_mutex);
 	if (rcu_dereference_protected(q->blk_trace,
 				      lockdep_is_held(&q->debugfs_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
-
-	mutex_unlock(&q->debugfs_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP