12 files changed, 240 insertions, 103 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f13eb4ded95f..e68a8c4ac5a6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -279,14 +279,13 @@ static blk_status_t nvme_error_status(u16 status)
 
 static void nvme_retry_req(struct request *req)
 {
-	struct nvme_ns *ns = req->q->queuedata;
 	unsigned long delay = 0;
 	u16 crd;
 
 	/* The mask and shift result must be <= 3 */
 	crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
-	if (ns && crd)
-		delay = ns->ctrl->crdt[crd - 1] * 100;
+	if (crd)
+		delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
 
 	nvme_req(req)->retries++;
 	blk_mq_requeue_request(req, false);
@@ -356,6 +355,21 @@ void nvme_complete_rq(struct request *req)
 }
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
 
+/*
+ * Called to unwind from ->queue_rq on a failed command submission so that the
+ * multipathing code gets called to potentially failover to another path.
+ * The caller needs to unwind all transport specific resource allocations and
+ * must return propagate the return value.
+ */
+blk_status_t nvme_host_path_error(struct request *req)
+{
+	nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR;
+	blk_mq_set_request_complete(req);
+	nvme_complete_rq(req);
+	return BLK_STS_OK;
+}
+EXPORT_SYMBOL_GPL(nvme_host_path_error);
+
 bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 {
 	dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
@@ -371,6 +385,26 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
 
+void nvme_cancel_tagset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->tagset) {
+		blk_mq_tagset_busy_iter(ctrl->tagset,
+				nvme_cancel_request, ctrl);
+		blk_mq_tagset_wait_completed_request(ctrl->tagset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_tagset);
+
+void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->admin_tagset) {
+		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
+				nvme_cancel_request, ctrl);
+		blk_mq_tagset_wait_completed_request(ctrl->admin_tagset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cancel_admin_tagset);
+
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
 {
@@ -842,11 +876,11 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 void nvme_cleanup_cmd(struct request *req)
 {
 	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		struct nvme_ns *ns = req->rq_disk->private_data;
+		struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
 		struct page *page = req->special_vec.bv_page;
 
-		if (page == ns->ctrl->discard_page)
-			clear_bit_unlock(0, &ns->ctrl->discard_page_busy);
+		if (page == ctrl->discard_page)
+			clear_bit_unlock(0, &ctrl->discard_page_busy);
 		else
 			kfree(page_address(page) + req->special_vec.bv_offset);
 	}
@@ -925,7 +959,7 @@ static void nvme_execute_rq_polled(struct request_queue *q,
 
 	rq->cmd_flags |= REQ_HIPRI;
 	rq->end_io_data = &wait;
-	blk_execute_rq_nowait(q, bd_disk, rq, at_head, nvme_end_sync_rq);
+	blk_execute_rq_nowait(bd_disk, rq, at_head, nvme_end_sync_rq);
 
 	while (!completion_done(&wait)) {
 		blk_poll(q, request_to_qc_t(rq->mq_hctx, rq), true);
@@ -964,7 +998,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	if (poll)
 		nvme_execute_rq_polled(req->q, NULL, req, at_head);
 	else
-		blk_execute_rq(req->q, NULL, req, at_head);
+		blk_execute_rq(NULL, req, at_head);
 	if (result)
 		*result = nvme_req(req)->result;
 	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
@@ -1101,7 +1135,7 @@ void nvme_execute_passthru_rq(struct request *rq)
 	u32 effects;
 
 	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
-	blk_execute_rq(rq->q, disk, rq, 0);
+	blk_execute_rq(disk, rq, 0);
 	nvme_passthru_end(ctrl, effects);
 }
 EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU);
@@ -1113,7 +1147,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
-	struct gendisk *disk = ns ? ns->disk : NULL;
+	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
 	struct request *req;
 	struct bio *bio = NULL;
 	void *meta = NULL;
@@ -1133,8 +1167,9 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 		if (ret)
 			goto out;
 		bio = req->bio;
-		bio->bi_disk = disk;
-		if (disk && meta_buffer && meta_len) {
+		if (bdev)
+			bio_set_dev(bio, bdev);
+		if (bdev && meta_buffer && meta_len) {
 			meta = nvme_add_user_metadata(bio, meta_buffer, meta_len,
 					meta_seed, write);
 			if (IS_ERR(meta)) {
@@ -1202,7 +1237,7 @@ static int nvme_keep_alive(struct nvme_ctrl *ctrl)
 	rq->timeout = ctrl->kato * HZ;
 	rq->end_io_data = ctrl;
 
-	blk_execute_rq_nowait(rq->q, NULL, rq, 0, nvme_keep_alive_end_io);
+	blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
 
 	return 0;
 }
@@ -2125,9 +2160,8 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	nvme_config_discard(disk, ns);
 	nvme_config_write_zeroes(disk, ns);
 
-	if ((id->nsattr & NVME_NS_ATTR_RO) ||
-	    test_bit(NVME_NS_FORCE_RO, &ns->flags))
-		set_disk_ro(disk, true);
+	set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
+		test_bit(NVME_NS_FORCE_RO, &ns->flags));
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -2176,17 +2210,18 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
 	ns->lba_shift = id->lbaf[lbaf].ds;
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
+	ret = nvme_configure_metadata(ns, id);
+	if (ret)
+		goto out_unfreeze;
+	nvme_set_chunk_sectors(ns, id);
+	nvme_update_disk_info(ns->disk, ns, id);
+
 	if (ns->head->ids.csi == NVME_CSI_ZNS) {
 		ret = nvme_update_zone_info(ns, lbaf);
 		if (ret)
 			goto out_unfreeze;
 	}
 
-	ret = nvme_configure_metadata(ns, id);
-	if (ret)
-		goto out_unfreeze;
-	nvme_set_chunk_sectors(ns, id);
-	nvme_update_disk_info(ns->disk, ns, id);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
@@ -2830,7 +2865,7 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev,
 	struct nvme_subsystem *subsys =
 		container_of(dev, struct nvme_subsystem, dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", subsys->subnqn);
+	return sysfs_emit(buf, "%s\n", subsys->subnqn);
 }
 static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);
 
@@ -2860,7 +2895,7 @@ static struct attribute *nvme_subsys_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group nvme_subsys_attrs_group = {
+static const struct attribute_group nvme_subsys_attrs_group = {
 	.attrs = nvme_subsys_attrs,
 };
 
@@ -3523,7 +3558,7 @@ static ssize_t nvme_sysfs_show_transport(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name);
+	return sysfs_emit(buf, "%s\n", ctrl->ops->name);
 }
 static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);
 
@@ -3557,7 +3592,7 @@ static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subsys->subnqn);
+	return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn);
 }
 static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
 
@@ -3567,7 +3602,7 @@ static ssize_t nvme_sysfs_show_hostnqn(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn);
+	return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn);
 }
 static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL);
 
@@ -3577,7 +3612,7 @@ static ssize_t nvme_sysfs_show_hostid(struct device *dev,
 {
 	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
 
-	return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id);
+	return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id);
 }
 static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL);
 
@@ -3695,7 +3730,7 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static struct attribute_group nvme_dev_attrs_group = {
+static const struct attribute_group nvme_dev_attrs_group = {
 	.attrs		= nvme_dev_attrs,
 	.is_visible	= nvme_dev_attrs_are_visible,
 };
@@ -4438,6 +4473,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
 
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_hwmon_exit(ctrl);
 	nvme_fault_inject_fini(&ctrl->fault_inject);
 	dev_pm_qos_hide_latency_tolerance(ctrl->device);
 	cdev_device_del(&ctrl->cdev, ctrl->device);
@@ -4450,7 +4486,7 @@ static void nvme_free_cels(struct nvme_ctrl *ctrl)
 	struct nvme_effects_log	*cel;
 	unsigned long i;
 
-	xa_for_each (&ctrl->cels, i, cel) {
+	xa_for_each(&ctrl->cels, i, cel) {
 		xa_erase(&ctrl->cels, i);
 		kfree(cel);
 	}
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 72ac00173500..5dfd806fc2d2 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -552,11 +552,7 @@ blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
-
-	nvme_req(rq)->status = NVME_SC_HOST_PATH_ERROR;
-	blk_mq_start_request(rq);
-	nvme_complete_rq(rq);
-	return BLK_STS_OK;
+	return nvme_host_path_error(rq);
 }
 EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command);
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 5f36cfa8136c..20dadd86e981 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3789,7 +3789,7 @@ static struct attribute *nvme_fc_attrs[] = {
 	NULL
 };
 
-static struct attribute_group nvme_fc_attr_group = {
+static const struct attribute_group nvme_fc_attr_group = {
 	.attrs = nvme_fc_attrs,
 };
 
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index 552dbc04567b..8f9e96986780 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -223,12 +223,12 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = {
 
 int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 {
-	struct device *dev = ctrl->dev;
+	struct device *dev = ctrl->device;
 	struct nvme_hwmon_data *data;
 	struct device *hwmon;
 	int err;
 
-	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return 0;
 
@@ -237,19 +237,30 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 
 	err = nvme_hwmon_get_smart_log(data);
 	if (err) {
-		dev_warn(ctrl->device,
-			"Failed to read smart log (error %d)\n", err);
-		devm_kfree(dev, data);
+		dev_warn(dev, "Failed to read smart log (error %d)\n", err);
+		kfree(data);
 		return err;
 	}
 
-	hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data,
-						     &nvme_hwmon_chip_info,
-						     NULL);
+	hwmon = hwmon_device_register_with_info(dev, "nvme",
+						data, &nvme_hwmon_chip_info,
+						NULL);
 	if (IS_ERR(hwmon)) {
 		dev_warn(dev, "Failed to instantiate hwmon device\n");
-		devm_kfree(dev, data);
+		kfree(data);
 	}
-
+	ctrl->hwmon_device = hwmon;
 	return 0;
 }
+
+void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->hwmon_device) {
+		struct nvme_hwmon_data *data =
+			dev_get_drvdata(ctrl->hwmon_device);
+
+		hwmon_device_unregister(ctrl->hwmon_device);
+		ctrl->hwmon_device = NULL;
+		kfree(data);
+	}
+}
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 470cef3abec3..b705988629f2 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -695,7 +695,7 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd,
 
 	rq->end_io_data = rqd;
 
-	blk_execute_rq_nowait(q, NULL, rq, 0, nvme_nvm_end_io);
+	blk_execute_rq_nowait(NULL, rq, 0, nvme_nvm_end_io);
 
 	return 0;
 
@@ -757,7 +757,6 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q,
 {
 	bool write = nvme_is_write((struct nvme_command *)vcmd);
 	struct nvm_dev *dev = ns->ndev;
-	struct gendisk *disk = ns->disk;
 	struct request *rq;
 	struct bio *bio = NULL;
 	__le64 *ppa_list = NULL;
@@ -817,10 +816,10 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q,
 			vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma);
 		}
 
-		bio->bi_disk = disk;
+		bio_set_dev(bio, ns->disk->part0);
 	}
 
-	blk_execute_rq(q, NULL, rq, 0);
+	blk_execute_rq(NULL, rq, 0);
 
 	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
 		ret = -EINTR;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 282b7a4ea9a9..a1d476e1ac02 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -296,7 +296,7 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 
 blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 {
-	struct nvme_ns_head *head = bio->bi_disk->private_data;
+	struct nvme_ns_head *head = bio->bi_bdev->bd_disk->private_data;
 	struct device *dev = disk_to_dev(head->disk);
 	struct nvme_ns *ns;
 	blk_qc_t ret = BLK_QC_T_NONE;
@@ -312,7 +312,7 @@ blk_qc_t nvme_ns_head_submit_bio(struct bio *bio)
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
 	if (likely(ns)) {
-		bio->bi_disk = ns->disk;
+		bio_set_dev(bio, ns->disk->part0);
 		bio->bi_opf |= REQ_NVME_MPATH;
 		trace_block_bio_remap(bio, disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
@@ -352,7 +352,7 @@ static void nvme_requeue_work(struct work_struct *work)
 		 * Reset disk to the mpath node and resubmit to select a new
 		 * path.
 		 */
-		bio->bi_disk = head->disk;
+		bio_set_dev(bio, head->disk->part0);
 		submit_bio_noacct(bio);
 	}
 }
@@ -677,6 +677,10 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 	if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
 		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
 				   ns->head->disk->queue);
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
+		ns->head->disk->queue->nr_zones = ns->queue->nr_zones;
+#endif
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 88a6b97247f5..07b34175c6ce 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -144,6 +144,12 @@ enum nvme_quirks {
 	 * NVMe 1.3 compliance.
 	 */
 	NVME_QUIRK_NO_NS_DESC_LIST		= (1 << 15),
+
+	/*
+	 * The controller does not properly handle DMA addresses over
+	 * 48 bits.
+	 */
+	NVME_QUIRK_DMA_ADDRESS_BITS_48		= (1 << 16),
 };
 
 /*
@@ -246,6 +252,9 @@ struct nvme_ctrl {
 	struct rw_semaphore namespaces_rwsem;
 	struct device ctrl_device;
 	struct device *device;	/* char device */
+#ifdef CONFIG_NVME_HWMON
+	struct device *hwmon_device;
+#endif
 	struct cdev cdev;
 	struct work_struct reset_work;
 	struct work_struct delete_work;
@@ -575,7 +584,10 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
 }
 
 void nvme_complete_rq(struct request *req);
+blk_status_t nvme_host_path_error(struct request *req);
 bool nvme_cancel_request(struct request *req, void *data, bool reserved);
+void nvme_cancel_tagset(struct nvme_ctrl *ctrl);
+void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state);
 bool nvme_wait_reset(struct nvme_ctrl *ctrl);
@@ -809,11 +821,16 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 
 #ifdef CONFIG_NVME_HWMON
 int nvme_hwmon_init(struct nvme_ctrl *ctrl);
+void nvme_hwmon_exit(struct nvme_ctrl *ctrl);
 #else
 static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl)
 {
 	return 0;
 }
+
+static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
+{
+}
 #endif
 
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 6bad4d4dcdf0..7b6632c00ffd 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1357,7 +1357,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	}
 
 	abort_req->end_io_data = NULL;
-	blk_execute_rq_nowait(abort_req->q, NULL, abort_req, 0, abort_endio);
+	blk_execute_rq_nowait(NULL, abort_req, 0, abort_endio);
 
 	/*
 	 * The aborted req will be completed on receiving the abort req.
@@ -2281,7 +2281,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
 	req->end_io_data = nvmeq;
 
 	init_completion(&nvmeq->delete_done);
-	blk_execute_rq_nowait(q, NULL, req, false,
+	blk_execute_rq_nowait(NULL, req, false,
 			opcode == nvme_admin_delete_cq ?
 				nvme_del_cq_end : nvme_del_queue_end);
 	return 0;
@@ -2362,13 +2362,16 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 {
 	int result = -ENOMEM;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
+	int dma_address_bits = 64;
 
 	if (pci_enable_device_mem(pdev))
 		return result;
 
 	pci_set_master(pdev);
 
-	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)))
+	if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48)
+		dma_address_bits = 48;
+	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(dma_address_bits)))
 		goto disable;
 
 	if (readl(dev->bar + NVME_REG_CSTS) == -1) {
@@ -3263,6 +3266,18 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x2646, 0x2263),   /* KINGSTON A2000 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),
+		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x8061),
+		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd00),
+		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd01),
+		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd02),
+		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b7ce4f221d99..53ac4d7442ba 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -919,12 +919,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 
 	error = nvme_init_identify(&ctrl->ctrl);
 	if (error)
-		goto out_stop_queue;
+		goto out_quiesce_queue;
 
 	return 0;
 
+out_quiesce_queue:
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_sync_queue(ctrl->ctrl.admin_q);
 out_stop_queue:
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 out_cleanup_queue:
 	if (new)
 		blk_cleanup_queue(ctrl->ctrl.admin_q);
@@ -1001,8 +1005,10 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 out_wait_freeze_timed_out:
 	nvme_stop_queues(&ctrl->ctrl);
+	nvme_sync_io_queues(&ctrl->ctrl);
 	nvme_rdma_stop_io_queues(ctrl);
 out_cleanup_connect_q:
+	nvme_cancel_tagset(&ctrl->ctrl);
 	if (new)
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
 out_free_tag_set:
@@ -1019,11 +1025,7 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	if (ctrl->ctrl.admin_tagset) {
-		blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
-			nvme_cancel_request, &ctrl->ctrl);
-		blk_mq_tagset_wait_completed_request(ctrl->ctrl.admin_tagset);
-	}
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
@@ -1037,11 +1039,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		nvme_stop_queues(&ctrl->ctrl);
 		nvme_sync_io_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
-		if (ctrl->ctrl.tagset) {
-			blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
-				nvme_cancel_request, &ctrl->ctrl);
-			blk_mq_tagset_wait_completed_request(ctrl->ctrl.tagset);
-		}
+		nvme_cancel_tagset(&ctrl->ctrl);
 		if (remove)
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
@@ -1144,10 +1142,18 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 	return 0;
 
 destroy_io:
-	if (ctrl->ctrl.queue_count > 1)
+	if (ctrl->ctrl.queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		nvme_sync_io_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
+		nvme_cancel_tagset(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, new);
+	}
 destroy_admin:
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	nvme_cancel_admin_tagset(&ctrl->ctrl);
 	nvme_rdma_destroy_admin_queue(ctrl, new);
 	return ret;
 }
@@ -1468,7 +1474,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 	if (unlikely(nr))
 		goto mr_put;
 
-	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_disk), c,
+	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
 				req->mr->sig_attrs, ns->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
@@ -2092,7 +2098,9 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 err_unmap:
 	nvme_rdma_unmap_data(queue, rq);
 err:
-	if (err == -ENOMEM || err == -EAGAIN)
+	if (err == -EIO)
+		ret = nvme_host_path_error(rq);
+	else if (err == -ENOMEM || err == -EAGAIN)
 		ret = BLK_STS_RESOURCE;
 	else
 		ret = BLK_STS_IOERR;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 881d28eb15e9..69f59d2c5799 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -206,11 +206,6 @@ static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req)
 			req->pdu_len - req->pdu_sent);
 }
 
-static inline size_t nvme_tcp_req_offset(struct nvme_tcp_request *req)
-{
-	return req->iter.iov_offset;
-}
-
 static inline size_t nvme_tcp_pdu_data_left(struct nvme_tcp_request *req)
 {
 	return rq_data_dir(blk_mq_rq_from_pdu(req)) == WRITE ?
@@ -229,24 +224,29 @@ static void nvme_tcp_init_iter(struct nvme_tcp_request *req,
 	struct request *rq = blk_mq_rq_from_pdu(req);
 	struct bio_vec *vec;
 	unsigned int size;
-	int nsegs;
+	int nr_bvec;
 	size_t offset;
 
 	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) {
 		vec = &rq->special_vec;
-		nsegs = 1;
+		nr_bvec = 1;
 		size = blk_rq_payload_bytes(rq);
 		offset = 0;
 	} else {
 		struct bio *bio = req->curr_bio;
+		struct bvec_iter bi;
+		struct bio_vec bv;
 
 		vec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
-		nsegs = bio_segments(bio);
+		nr_bvec = 0;
+		bio_for_each_bvec(bv, bio, bi) {
+			nr_bvec++;
+		}
 		size = bio->bi_iter.bi_size;
 		offset = bio->bi_iter.bi_bvec_done;
 	}
 
-	iov_iter_bvec(&req->iter, dir, vec, nsegs, size);
+	iov_iter_bvec(&req->iter, dir, vec, nr_bvec, size);
 	req->iter.iov_offset = offset;
 }
 
@@ -983,7 +983,6 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 			req->state = NVME_TCP_SEND_DATA;
 			if (queue->data_digest)
 				crypto_ahash_init(queue->snd_hash);
-			nvme_tcp_init_iter(req, WRITE);
 		} else {
 			nvme_tcp_done_send_req(queue);
 		}
@@ -1016,8 +1015,6 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 		req->state = NVME_TCP_SEND_DATA;
 		if (queue->data_digest)
 			crypto_ahash_init(queue->snd_hash);
-		if (!req->data_sent)
-			nvme_tcp_init_iter(req, WRITE);
 		return 1;
 	}
 	req->offset += ret;
@@ -1815,8 +1812,10 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new)
 
 out_wait_freeze_timed_out:
 	nvme_stop_queues(ctrl);
+	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 out_cleanup_connect_q:
+	nvme_cancel_tagset(ctrl);
 	if (new)
 		blk_cleanup_queue(ctrl->connect_q);
 out_free_tag_set:
@@ -1878,12 +1877,16 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
 
 	error = nvme_init_identify(ctrl);
 	if (error)
-		goto out_stop_queue;
+		goto out_quiesce_queue;
 
 	return 0;
 
+out_quiesce_queue:
+	blk_mq_quiesce_queue(ctrl->admin_q);
+	blk_sync_queue(ctrl->admin_q);
 out_stop_queue:
 	nvme_tcp_stop_queue(ctrl, 0);
+	nvme_cancel_admin_tagset(ctrl);
 out_cleanup_queue:
 	if (new)
 		blk_cleanup_queue(ctrl->admin_q);
@@ -1904,11 +1907,7 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
-	if (ctrl->admin_tagset) {
-		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
-			nvme_cancel_request, ctrl);
-		blk_mq_tagset_wait_completed_request(ctrl->admin_tagset);
-	}
+	nvme_cancel_admin_tagset(ctrl);
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
@@ -1924,11 +1923,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	nvme_stop_queues(ctrl);
 	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
-	if (ctrl->tagset) {
-		blk_mq_tagset_busy_iter(ctrl->tagset,
-			nvme_cancel_request, ctrl);
-		blk_mq_tagset_wait_completed_request(ctrl->tagset);
-	}
+	nvme_cancel_tagset(ctrl);
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
@@ -2003,10 +1998,18 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
 	return 0;
 
 destroy_io:
-	if (ctrl->queue_count > 1)
+	if (ctrl->queue_count > 1) {
+		nvme_stop_queues(ctrl);
+		nvme_sync_io_queues(ctrl);
+		nvme_tcp_stop_io_queues(ctrl);
+		nvme_cancel_tagset(ctrl);
 		nvme_tcp_destroy_io_queues(ctrl, new);
+	}
 destroy_admin:
+	blk_mq_quiesce_queue(ctrl->admin_q);
+	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
+	nvme_cancel_admin_tagset(ctrl);
 	nvme_tcp_destroy_admin_queue(ctrl, new);
 	return ret;
 }
@@ -2268,12 +2271,12 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 	req->data_len = blk_rq_nr_phys_segments(rq) ?
 				blk_rq_payload_bytes(rq) : 0;
 	req->curr_bio = rq->bio;
+	if (req->curr_bio && req->data_len)
+		nvme_tcp_init_iter(req, rq_data_dir(rq));
 
 	if (rq_data_dir(rq) == WRITE &&
 	    req->data_len <= nvme_tcp_inline_data_size(queue))
 		req->pdu_len = req->data_len;
-	else if (req->curr_bio)
-		nvme_tcp_init_iter(req, READ);
 
 	pdu->hdr.type = nvme_tcp_cmd;
 	pdu->hdr.flags = 0;
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 5c3cb6928f3c..6543015b6121 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -102,6 +102,23 @@ static const char *nvme_trace_get_lba_status(struct trace_seq *p,
 	return ret;
 }
 
+static const char *nvme_trace_admin_format_nvm(struct trace_seq *p, u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u8 lbaf = cdw10[0] & 0xF;
+	u8 mset = (cdw10[0] >> 4) & 0x1;
+	u8 pi = (cdw10[0] >> 5) & 0x7;
+	u8 pil = cdw10[1] & 0x1;
+	u8 ses = (cdw10[1] >> 1) & 0x7;
+
+	trace_seq_printf(p, "lbaf=%u, mset=%u, pi=%u, pil=%u, ses=%u",
+			lbaf, mset, pi, pil, ses);
+
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvme_trace_read_write(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -131,6 +148,35 @@ static const char *nvme_trace_dsm(struct trace_seq *p, u8 *cdw10)
 	return ret;
 }
 
+static const char *nvme_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u64 slba = get_unaligned_le64(cdw10);
+	u8 zsa = cdw10[12];
+	u8 all = cdw10[13];
+
+	trace_seq_printf(p, "slba=%llu, zsa=%u, all=%u", slba, zsa, all);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
+static const char *nvme_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	u64 slba = get_unaligned_le64(cdw10);
+	u32 numd = get_unaligned_le32(cdw10 + 8);
+	u8 zra = cdw10[12];
+	u8 zrasf = cdw10[13];
+	u8 pr = cdw10[14];
+
+	trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u, pr=%u",
+			 slba, numd, zra, zrasf, pr);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+
 static const char *nvme_trace_common(struct trace_seq *p, u8 *cdw10)
 {
 	const char *ret = trace_seq_buffer_ptr(p);
@@ -159,6 +205,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p,
 		return nvme_trace_admin_get_features(p, cdw10);
 	case nvme_admin_get_lba_status:
 		return nvme_trace_get_lba_status(p, cdw10);
+	case nvme_admin_format_nvm:
+		return nvme_trace_admin_format_nvm(p, cdw10);
 	default:
 		return nvme_trace_common(p, cdw10);
 	}
@@ -171,9 +219,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
 	case nvme_cmd_read:
 	case nvme_cmd_write:
 	case nvme_cmd_write_zeroes:
+	case nvme_cmd_zone_append:
 		return nvme_trace_read_write(p, cdw10);
 	case nvme_cmd_dsm:
 		return nvme_trace_dsm(p, cdw10);
+	case nvme_cmd_zone_mgmt_send:
+		return nvme_trace_zone_mgmt_send(p, cdw10);
+	case nvme_cmd_zone_mgmt_recv:
+		return nvme_trace_zone_mgmt_recv(p, cdw10);
 	default:
 		return nvme_trace_common(p, cdw10);
 	}
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 1dfe9a3500e3..c7e3ec561ba0 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -9,13 +9,7 @@
 
 int nvme_revalidate_zones(struct nvme_ns *ns)
 {
-	struct request_queue *q = ns->queue;
-	int ret;
-
-	ret = blk_revalidate_disk_zones(ns->disk, NULL);
-	if (!ret)
-		blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
-	return ret;
+	return blk_revalidate_disk_zones(ns->disk, NULL);
 }
 
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
@@ -109,10 +103,11 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	q->limits.zoned = BLK_ZONED_HM;
+	blk_queue_set_zoned(ns->disk, BLK_ZONED_HM);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
 	blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
+	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
 free_data:
 	kfree(id);
 	return status;