Merge tag 'block-5.19-2022-06-16' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Christoph
      - Quirks, quirks, quirks to work around buggy consumer grade
        devices (Keith Bush, Ning Wang, Stefan Reiter, Rasheed Hsueh)
      - Better kernel messages for devices that need quirking (Keith
        Bush)
      - Make a kernel message more useful (Thomas Weißschuh)

 - MD pull request from Song, with a few fixes

 - blk-mq sysfs locking fixes (Ming)

 - BFQ stats fix (Bart)

 - blk-mq offline queue fix (Bart)

 - blk-mq flush request tag fix (Ming)

* tag 'block-5.19-2022-06-16' of git://git.kernel.dk/linux-block:
  block/bfq: Enable I/O statistics
  blk-mq: don't clear flush_rq from tags->rqs[]
  blk-mq: avoid to touch q->elevator without any protection
  blk-mq: protect q->elevator by ->sysfs_lock in blk_mq_elv_switch_none
  block: Fix handling of offline queues in blk_mq_alloc_request_hctx()
  md/raid5-ppl: Fix argument order in bio_alloc_bioset()
  Revert "md: don't unregister sync_thread with reconfig_mutex held"
  nvme-pci: disable write zeros support on UMIC and Samsung SSDs
  nvme-pci: avoid the deepest sleep state on ZHITAI TiPro7000 SSDs
  nvme-pci: sk hynix p31 has bogus namespace ids
  nvme-pci: smi has bogus namespace ids
  nvme-pci: phison e12 has bogus namespace ids
  nvme-pci: add NVME_QUIRK_BOGUS_NID for ADATA XPG GAMMIX S50
  nvme-pci: add trouble shooting steps for timeouts
  nvme: add bug report info for global duplicate id
  nvme: add device name to warning in uuid_show()

block/bfq-iosched.c

@@ -7046,6 +7046,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 	spin_unlock_irq(&bfqd->lock);
 #endif
 
+	blk_stat_disable_accounting(bfqd->queue);
 	wbt_enable_default(bfqd->queue);
 
 	kfree(bfqd);
@@ -7188,7 +7189,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfq_init_root_group(bfqd->root_group, bfqd);
 	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
 
+	/* We dispatch from request queue wide instead of hw queue */
+	blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q);
+
 	wbt_disable_default(q);
+	blk_stat_enable_accounting(q);
+
 	return 0;
 
 out_free:

block/blk-mq-sched.c

@@ -564,6 +564,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	int ret;
 
 	if (!e) {
+		blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
 		q->elevator = NULL;
 		q->nr_requests = q->tag_set->queue_depth;
 		return 0;

block/blk-mq.c

@@ -579,6 +579,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	if (!blk_mq_hw_queue_mapped(data.hctx))
 		goto out_queue_exit;
 	cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
+	if (cpu >= nr_cpu_ids)
+		goto out_queue_exit;
 	data.ctx = __blk_mq_get_ctx(q, cpu);
 
 	if (!q->elevator)
@@ -2140,20 +2142,6 @@ 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.
@@ -2186,7 +2174,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 	unsigned long i;
 
 	sq_hctx = NULL;
-	if (blk_mq_has_sqsched(q))
+	if (blk_queue_sq_sched(q))
 		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
@@ -2214,7 +2202,7 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 	unsigned long i;
 
 	sq_hctx = NULL;
-	if (blk_mq_has_sqsched(q))
+	if (blk_queue_sq_sched(q))
 		sq_hctx = blk_mq_get_sq_hctx(q);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_hctx_stopped(hctx))
@@ -3443,8 +3431,9 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (blk_mq_hw_queue_mapped(hctx))
 		blk_mq_tag_idle(hctx);
 
-	blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
-			set->queue_depth, flush_rq);
+	if (blk_queue_init_done(q))
+		blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
+				set->queue_depth, flush_rq);
 	if (set->ops->exit_request)
 		set->ops->exit_request(set, flush_rq, hctx_idx);
 
@@ -4438,12 +4427,14 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	if (!qe)
 		return false;
 
+	/* q->elevator needs protection from ->sysfs_lock */
+	mutex_lock(&q->sysfs_lock);
+
 	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

block/kyber-iosched.c

@@ -421,6 +421,8 @@ static int kyber_init_sched(struct request_queue *q, struct elevator_type *e)
 
 	blk_stat_enable_accounting(q);
 
+	blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
+
 	eq->elevator_data = kqd;
 	q->elevator = eq;
 
@@ -1033,7 +1035,6 @@ static struct elevator_type kyber_sched = {
 #endif
 	.elevator_attrs = kyber_sched_attrs,
 	.elevator_name = "kyber",
-	.elevator_features = ELEVATOR_F_MQ_AWARE,
 	.elevator_owner = THIS_MODULE,
 };
 

block/mq-deadline.c

@@ -642,6 +642,9 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
 	spin_lock_init(&dd->lock);
 	spin_lock_init(&dd->zone_lock);
 
+	/* We dispatch from request queue wide instead of hw queue */
+	blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q);
+
 	q->elevator = eq;
 	return 0;
 

drivers/md/dm-raid.c

@@ -3725,7 +3725,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev, false);
+			md_reap_sync_thread(mddev);
 		}
 	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;

drivers/md/md.c

@@ -4831,7 +4831,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 				flush_workqueue(md_misc_wq);
 			if (mddev->sync_thread) {
 				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_reap_sync_thread(mddev, true);
+				md_reap_sync_thread(mddev);
 			}
 			mddev_unlock(mddev);
 		}
@@ -6197,7 +6197,7 @@ static void __md_stop_writes(struct mddev *mddev)
 		flush_workqueue(md_misc_wq);
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		md_reap_sync_thread(mddev, true);
+		md_reap_sync_thread(mddev);
 	}
 
 	del_timer_sync(&mddev->safemode_timer);
@@ -9303,7 +9303,7 @@ void md_check_recovery(struct mddev *mddev)
 			 * ->spare_active and clear saved_raid_disk
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev, true);
+			md_reap_sync_thread(mddev);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
@@ -9338,7 +9338,7 @@ void md_check_recovery(struct mddev *mddev)
 			goto unlock;
 		}
 		if (mddev->sync_thread) {
-			md_reap_sync_thread(mddev, true);
+			md_reap_sync_thread(mddev);
 			goto unlock;
 		}
 		/* Set RUNNING before clearing NEEDED to avoid
@@ -9411,18 +9411,14 @@ void md_check_recovery(struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_check_recovery);
 
-void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held)
+void md_reap_sync_thread(struct mddev *mddev)
 {
 	struct md_rdev *rdev;
 	sector_t old_dev_sectors = mddev->dev_sectors;
 	bool is_reshaped = false;
 
-	if (reconfig_mutex_held)
-		mddev_unlock(mddev);
 	/* resync has finished, collect result */
 	md_unregister_thread(&mddev->sync_thread);
-	if (reconfig_mutex_held)
-		mddev_lock_nointr(mddev);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
 	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
 	    mddev->degraded != mddev->raid_disks) {

drivers/md/md.h

@@ -719,7 +719,7 @@ extern struct md_thread *md_register_thread(
 extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
-extern void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held);
+extern void md_reap_sync_thread(struct mddev *mddev);
 extern int mddev_init_writes_pending(struct mddev *mddev);
 extern bool md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);

drivers/md/raid5-ppl.c

@@ -629,9 +629,9 @@ static void ppl_do_flush(struct ppl_io_unit *io)
 		if (bdev) {
 			struct bio *bio;
 
-			bio = bio_alloc_bioset(bdev, 0, GFP_NOIO,
+			bio = bio_alloc_bioset(bdev, 0,
 					       REQ_OP_WRITE | REQ_PREFLUSH,
-					       &ppl_conf->flush_bs);
+					       GFP_NOIO, &ppl_conf->flush_bs);
 			bio->bi_private = io;
 			bio->bi_end_io = ppl_flush_endio;
 

drivers/nvme/host/core.c

@@ -3285,8 +3285,8 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	 * we have no UUID set
 	 */
 	if (uuid_is_null(&ids->uuid)) {
-		printk_ratelimited(KERN_WARNING
-				   "No UUID available providing old NGUID\n");
+		dev_warn_ratelimited(dev,
+			"No UUID available providing old NGUID\n");
 		return sysfs_emit(buf, "%pU\n", ids->nguid);
 	}
 	return sysfs_emit(buf, "%pU\n", &ids->uuid);
@@ -3863,6 +3863,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 	if (ret) {
 		dev_err(ctrl->device,
 			"globally duplicate IDs for nsid %d\n", nsid);
+		nvme_print_device_info(ctrl);
 		return ret;
 	}
 

drivers/nvme/host/nvme.h

@@ -503,6 +503,7 @@ struct nvme_ctrl_ops {
 	void (*submit_async_event)(struct nvme_ctrl *ctrl);
 	void (*delete_ctrl)(struct nvme_ctrl *ctrl);
 	int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
+	void (*print_device_info)(struct nvme_ctrl *ctrl);
 };
 
 /*
@@ -548,6 +549,33 @@ static inline struct request *nvme_cid_to_rq(struct blk_mq_tags *tags,
 	return blk_mq_tag_to_rq(tags, nvme_tag_from_cid(command_id));
 }
 
+/*
+ * Return the length of the string without the space padding
+ */
+static inline int nvme_strlen(char *s, int len)
+{
+	while (s[len - 1] == ' ')
+		len--;
+	return len;
+}
+
+static inline void nvme_print_device_info(struct nvme_ctrl *ctrl)
+{
+	struct nvme_subsystem *subsys = ctrl->subsys;
+
+	if (ctrl->ops->print_device_info) {
+		ctrl->ops->print_device_info(ctrl);
+		return;
+	}
+
+	dev_err(ctrl->device,
+		"VID:%04x model:%.*s firmware:%.*s\n", subsys->vendor_id,
+		nvme_strlen(subsys->model, sizeof(subsys->model)),
+		subsys->model, nvme_strlen(subsys->firmware_rev,
+					   sizeof(subsys->firmware_rev)),
+		subsys->firmware_rev);
+}
+
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
 			    const char *dev_name);

drivers/nvme/host/pci.c

@@ -1334,6 +1334,14 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
 		dev_warn(dev->ctrl.device,
 			 "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n",
 			 csts, result);
+
+	if (csts != ~0)
+		return;
+
+	dev_warn(dev->ctrl.device,
+		 "Does your device have a faulty power saving mode enabled?\n");
+	dev_warn(dev->ctrl.device,
+		 "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
 }
 
 static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
@@ -2976,6 +2984,21 @@ static int nvme_pci_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 	return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
 }
 
+
+static void nvme_pci_print_device_info(struct nvme_ctrl *ctrl)
+{
+	struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
+	struct nvme_subsystem *subsys = ctrl->subsys;
+
+	dev_err(ctrl->device,
+		"VID:DID %04x:%04x model:%.*s firmware:%.*s\n",
+		pdev->vendor, pdev->device,
+		nvme_strlen(subsys->model, sizeof(subsys->model)),
+		subsys->model, nvme_strlen(subsys->firmware_rev,
+					   sizeof(subsys->firmware_rev)),
+		subsys->firmware_rev);
+}
+
 static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.name			= "pcie",
 	.module			= THIS_MODULE,
@@ -2987,6 +3010,7 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
 	.free_ctrl		= nvme_pci_free_ctrl,
 	.submit_async_event	= nvme_pci_submit_async_event,
 	.get_address		= nvme_pci_get_address,
+	.print_device_info	= nvme_pci_print_device_info,
 };
 
 static int nvme_dev_map(struct nvme_dev *dev)
@@ -3421,7 +3445,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_VDEVICE(REDHAT, 0x0010),	/* Qemu emulated controller */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x126f, 0x2263),	/* Silicon Motion unidentified */
-		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST, },
+		.driver_data = NVME_QUIRK_NO_NS_DESC_LIST |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1bb1, 0x0100),   /* Seagate Nytro Flash Storage */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
 				NVME_QUIRK_NO_NS_DESC_LIST, },
@@ -3437,6 +3462,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
 				NVME_QUIRK_DISABLE_WRITE_ZEROES|
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1987, 0x5012),	/* Phison E12 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1b4b, 0x1092),	/* Lexar 256 GB SSD */
@@ -3449,10 +3476,20 @@ static const struct pci_device_id nvme_id_table[] = {
 				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 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x144d, 0xa80b),   /* Samsung PM9B1 256G and 512G */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x144d, 0xa809),   /* Samsung MZALQ256HBJD 256G */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x1cc4, 0x6303),   /* UMIS RPJTJ512MGE1QDY 512G */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x1cc4, 0x6302),   /* UMIS RPJTJ256MGE1QDY 256G */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x2646, 0x2262),   /* KINGSTON SKC2000 NVMe SSD */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(0x2646, 0x2263),   /* KINGSTON A2000 NVMe SSD  */
@@ -3463,6 +3500,10 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1e4B, 0x1202),   /* MAXIO MAP1202 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1cc1, 0x5350),   /* ADATA XPG GAMMIX S50 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1e49, 0x0041),   /* ZHITAI TiPro7000 NVMe SSD */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061),
 		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),

include/linux/blkdev.h

@@ -575,6 +575,7 @@ struct request_queue {
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
 #define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
+#define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP) |		\
@@ -616,6 +617,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
+#define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -1006,8 +1008,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk,
  */
 /* Supports zoned block devices sequential write constraint */
 #define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
-/* Supports scheduling on multiple hardware queues */
-#define ELEVATOR_F_MQ_AWARE		(1U << 1)
 
 extern void blk_queue_required_elevator_features(struct request_queue *q,
 						 unsigned int features);