Merge tag 'block-6.5-2023-07-14' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - Don't require quirk to use duplicate namespace identifiers
        (Christoph, Sagi)
      - One more BOGUS_NID quirk (Pankaj)
      - IO timeout and error hanlding fixes for PCI (Keith)
      - Enhanced metadata format mask fix (Ankit)
      - Association race condition fix for fibre channel (Michael)
      - Correct debugfs error checks (Minjie)
      - Use PAGE_SECTORS_SHIFT where needed (Damien)
      - Reduce kernel logs for legacy nguid attribute (Keith)
      - Use correct dma direction when unmapping metadata (Ming)

 - Fix for a flush handling regression in this release (Christoph)

 - Fix for batched request time stamping (Chengming)

 - Fix for a regression in the mq-deadline position calculation (Bart)

 - Lockdep fix for blk-crypto (Eric)

 - Fix for a regression in the Amiga partition handling changes
   (Michael)

* tag 'block-6.5-2023-07-14' of git://git.kernel.dk/linux:
  block: queue data commands from the flush state machine at the head
  blk-mq: fix start_time_ns and alloc_time_ns for pre-allocated rq
  nvme-pci: fix DMA direction of unmapping integrity data
  nvme: don't reject probe due to duplicate IDs for single-ported PCIe devices
  block/mq-deadline: Fix a bug in deadline_from_pos()
  nvme: ensure disabling pairs with unquiesce
  nvme-fc: fix race between error recovery and creating association
  nvme-fc: return non-zero status code when fails to create association
  nvme: fix parameter check in nvme_fault_inject_init()
  nvme: warn only once for legacy uuid attribute
  block: remove dead struc request->completion_data field
  nvme: fix the NVME_ID_NS_NVM_STS_MASK definition
  nvmet: use PAGE_SECTORS_SHIFT
  nvme: add BOGUS_NID quirk for Samsung SM953
  blk-crypto: use dynamic lock class for blk_crypto_profile::lock
  block/partition: fix signedness issue for Amiga partitions

block/blk-crypto-profile.c

@@ -79,7 +79,14 @@ int blk_crypto_profile_init(struct blk_crypto_profile *profile,
 	unsigned int slot_hashtable_size;
 
 	memset(profile, 0, sizeof(*profile));
-	init_rwsem(&profile->lock);
+
+	/*
+	 * profile->lock of an underlying device can nest inside profile->lock
+	 * of a device-mapper device, so use a dynamic lock class to avoid
+	 * false-positive lockdep reports.
+	 */
+	lockdep_register_key(&profile->lockdep_key);
+	__init_rwsem(&profile->lock, "&profile->lock", &profile->lockdep_key);
 
 	if (num_slots == 0)
 		return 0;
@@ -89,7 +96,7 @@ int blk_crypto_profile_init(struct blk_crypto_profile *profile,
 	profile->slots = kvcalloc(num_slots, sizeof(profile->slots[0]),
 				  GFP_KERNEL);
 	if (!profile->slots)
-		return -ENOMEM;
+		goto err_destroy;
 
 	profile->num_slots = num_slots;
 
@@ -435,6 +442,7 @@ void blk_crypto_profile_destroy(struct blk_crypto_profile *profile)
 {
 	if (!profile)
 		return;
+	lockdep_unregister_key(&profile->lockdep_key);
 	kvfree(profile->slot_hashtable);
 	kvfree_sensitive(profile->slots,
 			 sizeof(profile->slots[0]) * profile->num_slots);

block/blk-flush.c

@@ -189,7 +189,7 @@ static void blk_flush_complete_seq(struct request *rq,
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
 		spin_lock(&q->requeue_lock);
-		list_add_tail(&rq->queuelist, &q->flush_list);
+		list_add(&rq->queuelist, &q->requeue_list);
 		spin_unlock(&q->requeue_lock);
 		blk_mq_kick_requeue_list(q);
 		break;

block/blk-mq.c

@@ -328,8 +328,24 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_rq_init);
 
+/* Set start and alloc time when the allocated request is actually used */
+static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns)
+{
+	if (blk_mq_need_time_stamp(rq))
+		rq->start_time_ns = ktime_get_ns();
+	else
+		rq->start_time_ns = 0;
+
+#ifdef CONFIG_BLK_RQ_ALLOC_TIME
+	if (blk_queue_rq_alloc_time(rq->q))
+		rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns;
+	else
+		rq->alloc_time_ns = 0;
+#endif
+}
+
 static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
-		struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns)
+		struct blk_mq_tags *tags, unsigned int tag)
 {
 	struct blk_mq_ctx *ctx = data->ctx;
 	struct blk_mq_hw_ctx *hctx = data->hctx;
@@ -356,14 +372,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	}
 	rq->timeout = 0;
 
-	if (blk_mq_need_time_stamp(rq))
-		rq->start_time_ns = ktime_get_ns();
-	else
-		rq->start_time_ns = 0;
 	rq->part = NULL;
-#ifdef CONFIG_BLK_RQ_ALLOC_TIME
-	rq->alloc_time_ns = alloc_time_ns;
-#endif
 	rq->io_start_time_ns = 0;
 	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
@@ -393,8 +402,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 }
 
 static inline struct request *
-__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
-		u64 alloc_time_ns)
+__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 {
 	unsigned int tag, tag_offset;
 	struct blk_mq_tags *tags;
@@ -413,7 +421,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
 		tag = tag_offset + i;
 		prefetch(tags->static_rqs[tag]);
 		tag_mask &= ~(1UL << i);
-		rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
+		rq = blk_mq_rq_ctx_init(data, tags, tag);
 		rq_list_add(data->cached_rq, rq);
 		nr++;
 	}
@@ -474,9 +482,11 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 	 * Try batched alloc if we want more than 1 tag.
 	 */
 	if (data->nr_tags > 1) {
-		rq = __blk_mq_alloc_requests_batch(data, alloc_time_ns);
-		if (rq)
+		rq = __blk_mq_alloc_requests_batch(data);
+		if (rq) {
+			blk_mq_rq_time_init(rq, alloc_time_ns);
 			return rq;
+		}
 		data->nr_tags = 1;
 	}
 
@@ -499,8 +509,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 		goto retry;
 	}
 
-	return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag,
-					alloc_time_ns);
+	rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag);
+	blk_mq_rq_time_init(rq, alloc_time_ns);
+	return rq;
 }
 
 static struct request *blk_mq_rq_cache_fill(struct request_queue *q,
@@ -555,6 +566,7 @@ static struct request *blk_mq_alloc_cached_request(struct request_queue *q,
 			return NULL;
 
 		plug->cached_rq = rq_list_next(rq);
+		blk_mq_rq_time_init(rq, 0);
 	}
 
 	rq->cmd_flags = opf;
@@ -656,8 +668,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
-	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
-					alloc_time_ns);
+	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
+	blk_mq_rq_time_init(rq, alloc_time_ns);
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
 	rq->bio = rq->biotail = NULL;
@@ -2896,6 +2908,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
 	plug->cached_rq = rq_list_next(rq);
 	rq_qos_throttle(q, *bio);
 
+	blk_mq_rq_time_init(rq, 0);
 	rq->cmd_flags = (*bio)->bi_opf;
 	INIT_LIST_HEAD(&rq->queuelist);
 	return rq;

block/mq-deadline.c

@@ -176,7 +176,7 @@ static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
 	 * zoned writes, start searching from the start of a zone.
 	 */
 	if (blk_rq_is_seq_zoned_write(rq))
-		pos -= round_down(pos, rq->q->limits.chunk_sectors);
+		pos = round_down(pos, rq->q->limits.chunk_sectors);
 
 	while (node) {
 		rq = rb_entry_rq(node);

block/partitions/amiga.c

@@ -90,7 +90,7 @@ int amiga_partition(struct parsed_partitions *state)
 	}
 	blk = be32_to_cpu(rdb->rdb_PartitionList);
 	put_dev_sector(sect);
-	for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) {
+	for (part = 1; (s32) blk>0 && part<=16; part++, put_dev_sector(sect)) {
 		/* Read in terms partition table understands */
 		if (check_mul_overflow(blk, (sector_t) blksize, &blk)) {
 			pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n",

drivers/nvme/host/core.c

@@ -3431,12 +3431,42 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 
 	ret = nvme_global_check_duplicate_ids(ctrl->subsys, &info->ids);
 	if (ret) {
-		dev_err(ctrl->device,
-			"globally duplicate IDs for nsid %d\n", info->nsid);
+		/*
+		 * We've found two different namespaces on two different
+		 * subsystems that report the same ID.  This is pretty nasty
+		 * for anything that actually requires unique device
+		 * identification.  In the kernel we need this for multipathing,
+		 * and in user space the /dev/disk/by-id/ links rely on it.
+		 *
+		 * If the device also claims to be multi-path capable back off
+		 * here now and refuse the probe the second device as this is a
+		 * recipe for data corruption.  If not this is probably a
+		 * cheap consumer device if on the PCIe bus, so let the user
+		 * proceed and use the shiny toy, but warn that with changing
+		 * probing order (which due to our async probing could just be
+		 * device taking longer to startup) the other device could show
+		 * up at any time.
+		 */
 		nvme_print_device_info(ctrl);
+		if ((ns->ctrl->ops->flags & NVME_F_FABRICS) || /* !PCIe */
+		    ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) &&
+		     info->is_shared)) {
+			dev_err(ctrl->device,
+				"ignoring nsid %d because of duplicate IDs\n",
+				info->nsid);
 			return ret;
 		}
 
+		dev_err(ctrl->device,
+			"clearing duplicate IDs for nsid %d\n", info->nsid);
+		dev_err(ctrl->device,
+			"use of /dev/disk/by-id/ may cause data corruption\n");
+		memset(&info->ids.nguid, 0, sizeof(info->ids.nguid));
+		memset(&info->ids.uuid, 0, sizeof(info->ids.uuid));
+		memset(&info->ids.eui64, 0, sizeof(info->ids.eui64));
+		ctrl->quirks |= NVME_QUIRK_BOGUS_NID;
+	}
+
 	mutex_lock(&ctrl->subsys->lock);
 	head = nvme_find_ns_head(ctrl, info->nsid);
 	if (!head) {

drivers/nvme/host/fault_inject.c

@@ -27,7 +27,7 @@ void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
 
 	/* create debugfs directory and attribute */
 	parent = debugfs_create_dir(dev_name, NULL);
-	if (!parent) {
+	if (IS_ERR(parent)) {
 		pr_warn("%s: failed to create debugfs directory\n", dev_name);
 		return;
 	}

drivers/nvme/host/fc.c

@@ -2548,14 +2548,24 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 * the controller.  Abort any ios on the association and let the
 	 * create_association error path resolve things.
 	 */
-	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
-		__nvme_fc_abort_outstanding_ios(ctrl, true);
+	enum nvme_ctrl_state state;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	state = ctrl->ctrl.state;
+	if (state == NVME_CTRL_CONNECTING) {
 		set_bit(ASSOC_FAILED, &ctrl->flags);
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+		__nvme_fc_abort_outstanding_ios(ctrl, true);
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: transport error during (re)connect\n",
+			ctrl->cnum);
 		return;
 	}
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
+	if (state != NVME_CTRL_LIVE)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
@@ -3110,7 +3120,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	 */
 
 	ret = nvme_enable_ctrl(&ctrl->ctrl);
-	if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
+	if (ret)
 		goto out_disconnect_admin_queue;
 
 	ctrl->ctrl.max_segments = ctrl->lport->ops->max_sgl_segments;
@@ -3120,7 +3132,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	nvme_unquiesce_admin_queue(&ctrl->ctrl);
 
 	ret = nvme_init_ctrl_finish(&ctrl->ctrl, false);
-	if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
+	if (ret)
 		goto out_disconnect_admin_queue;
 
 	/* sanity checks */
@@ -3165,10 +3179,16 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
-	if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
-		goto out_term_aen_ops;
 
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
+	if (ret) {
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+		goto out_term_aen_ops;
+	}
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	ctrl->ctrl.nr_reconnects = 0;
 
@@ -3180,6 +3200,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 out_term_aen_ops:
 	nvme_fc_term_aen_ops(ctrl);
 out_disconnect_admin_queue:
+	dev_warn(ctrl->ctrl.device,
+		"NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n",
+		ctrl->cnum, ctrl->association_id, ret);
 	/* send a Disconnect(association) LS to fc-nvme target */
 	nvme_fc_xmt_disconnect_assoc(ctrl);
 	spin_lock_irqsave(&ctrl->lock, flags);

drivers/nvme/host/pci.c

@@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
 	        struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
 		dma_unmap_page(dev->dev, iod->meta_dma,
-			       rq_integrity_vec(req)->bv_len, rq_data_dir(req));
+			       rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
 	}
 
 	if (blk_rq_nr_phys_segments(req))
@@ -1298,9 +1298,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 */
 	if (nvme_should_reset(dev, csts)) {
 		nvme_warn_reset(dev, csts);
-		nvme_dev_disable(dev, false);
-		nvme_reset_ctrl(&dev->ctrl);
-		return BLK_EH_DONE;
+		goto disable;
 	}
 
 	/*
@@ -1351,10 +1349,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
-		nvme_dev_disable(dev, false);
-		nvme_reset_ctrl(&dev->ctrl);
-
-		return BLK_EH_DONE;
+		goto disable;
 	}
 
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
@@ -1391,6 +1386,15 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * as the device then is in a faulty state.
 	 */
 	return BLK_EH_RESET_TIMER;
+
+disable:
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+		return BLK_EH_DONE;
+
+	nvme_dev_disable(dev, false);
+	if (nvme_try_sched_reset(&dev->ctrl))
+		nvme_unquiesce_io_queues(&dev->ctrl);
+	return BLK_EH_DONE;
 }
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -3278,6 +3282,10 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
 	case pci_channel_io_frozen:
 		dev_warn(dev->ctrl.device,
 			"frozen state error detected, reset controller\n");
+		if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
+			nvme_dev_disable(dev, true);
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
 		nvme_dev_disable(dev, false);
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
@@ -3294,7 +3302,8 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	nvme_reset_ctrl(&dev->ctrl);
+	if (!nvme_try_sched_reset(&dev->ctrl))
+		nvme_unquiesce_io_queues(&dev->ctrl);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
@@ -3396,6 +3405,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x144d, 0xa809),   /* Samsung MZALQ256HBJD 256G */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x144d, 0xa802),   /* Samsung SM953 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc4, 0x6303),   /* UMIS RPJTJ512MGE1QDY 512G */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1cc4, 0x6302),   /* UMIS RPJTJ256MGE1QDY 256G */

drivers/nvme/host/sysfs.c

@@ -92,7 +92,7 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	 * we have no UUID set
 	 */
 	if (uuid_is_null(&ids->uuid)) {
-		dev_warn_ratelimited(dev,
+		dev_warn_once(dev,
 			"No UUID available providing old NGUID\n");
 		return sysfs_emit(buf, "%pU\n", ids->nguid);
 	}

drivers/nvme/target/loop.c

@@ -373,7 +373,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 		goto out_cleanup_tagset;
 
 	ctrl->ctrl.max_hw_sectors =
-		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
+		(NVME_LOOP_MAX_SEGMENTS - 1) << PAGE_SECTORS_SHIFT;
 
 	nvme_unquiesce_admin_queue(&ctrl->ctrl);
 

drivers/nvme/target/passthru.c

@@ -102,14 +102,14 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 	 * which depends on the host's memory fragementation. To solve this,
 	 * ensure mdts is limited to the pages equal to the number of segments.
 	 */
-	max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9),
+	max_hw_sectors = min_not_zero(pctrl->max_segments << PAGE_SECTORS_SHIFT,
 				      pctrl->max_hw_sectors);
 
 	/*
 	 * nvmet_passthru_map_sg is limitted to using a single bio so limit
 	 * the mdts based on BIO_MAX_VECS as well
 	 */
-	max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9),
+	max_hw_sectors = min_not_zero(BIO_MAX_VECS << PAGE_SECTORS_SHIFT,
 				      max_hw_sectors);
 
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;

include/linux/blk-crypto-profile.h

@@ -111,6 +111,7 @@ struct blk_crypto_profile {
 	 * keyslots while ensuring that they can't be changed concurrently.
 	 */
 	struct rw_semaphore lock;
+	struct lock_class_key lockdep_key;
 
 	/* List of idle slots, with least recently used slot at front */
 	wait_queue_head_t idle_slots_wait_queue;

include/linux/blk-mq.h

@@ -158,13 +158,13 @@ struct request {
 
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
-	 * are pruned when moved to the dispatch queue. So let the
-	 * completion_data share space with the rb_node.
+	 * are pruned when moved to the dispatch queue. special_vec must
+	 * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be
+	 * insert into an IO scheduler.
 	 */
 	union {
 		struct rb_node rb_node;	/* sort/lookup */
 		struct bio_vec special_vec;
-		void *completion_data;
 	};
 
 	/*

include/linux/nvme.h

@@ -473,7 +473,7 @@ struct nvme_id_ns_nvm {
 };
 
 enum {
-	NVME_ID_NS_NVM_STS_MASK		= 0x3f,
+	NVME_ID_NS_NVM_STS_MASK		= 0x7f,
 	NVME_ID_NS_NVM_GUARD_SHIFT	= 7,
 	NVME_ID_NS_NVM_GUARD_MASK	= 0x3,
 };