Merge tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
      - Use uring_cmd helper (Pavel)
      - Host Memory Buffer allocation enhancements (Christoph)
      - Target persistent reservation support (Guixin)
      - Persistent reservation tracing (Guixen)
      - NVMe 2.1 specification support (Keith)
      - Rotational Meta Support (Matias, Wang, Keith)
      - Volatile cache detection enhancment (Guixen)

 - MD updates via Song:
      - Maintainers update
      - raid5 sync IO fix
      - Enhance handling of faulty and blocked devices
      - raid5-ppl atomic improvement
      - md-bitmap fix

 - Support for manually defining embedded partition tables

 - Zone append fixes and cleanups

 - Stop sending the queued requests in the plug list to the driver
   ->queue_rqs() handle in reverse order.

 - Zoned write plug cleanups

 - Cleanups disk stats tracking and add support for disk stats for
   passthrough IO

 - Add preparatory support for file system atomic writes

 - Add lockdep support for queue freezing. Already found a bunch of
   issues, and some fixes for that are in here. More will be coming.

 - Fix race between queue stopping/quiescing and IO queueing

 - ublk recovery improvements

 - Fix ublk mmap for 64k pages

 - Various fixes and cleanups

* tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux: (118 commits)
  MAINTAINERS: Update git tree for mdraid subsystem
  block: make struct rq_list available for !CONFIG_BLOCK
  block/genhd: use seq_put_decimal_ull for diskstats decimal values
  block: don't reorder requests in blk_mq_add_to_batch
  block: don't reorder requests in blk_add_rq_to_plug
  block: add a rq_list type
  block: remove rq_list_move
  virtio_blk: reverse request order in virtio_queue_rqs
  nvme-pci: reverse request order in nvme_queue_rqs
  btrfs: validate queue limits
  block: export blk_validate_limits
  nvmet: add tracing of reservation commands
  nvme: parse reservation commands's action and rtype to string
  nvmet: report ns's vwc not present
  md/raid5: Increase r5conf.cache_name size
  block: remove the ioprio field from struct request
  block: remove the write_hint field from struct request
  nvme: check ns's volatile write cache not present
  nvme: add rotational support
  nvme: use command set independent id ns if available
  ...

8 files changed, 172 insertions, 72 deletions

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index b1387dc459a3..7cd1102a8d2c 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -649,7 +649,7 @@ static bool apple_nvme_handle_cq(struct apple_nvme_queue *q, bool force)
 
 	found = apple_nvme_poll_cq(q, &iob);
 
-	if (!rq_list_empty(iob.req_list))
+	if (!rq_list_empty(&iob.req_list))
 		apple_nvme_complete_batch(&iob);
 
 	return found;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 855b42c92284..1a8d32a4a5c3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -42,6 +42,8 @@ struct nvme_ns_info {
 	bool is_readonly;
 	bool is_ready;
 	bool is_removed;
+	bool is_rotational;
+	bool no_vwc;
 };
 
 unsigned int admin_timeout = 60;
@@ -1639,6 +1641,8 @@ static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
 		info->is_shared = id->nmic & NVME_NS_NMIC_SHARED;
 		info->is_readonly = id->nsattr & NVME_NS_ATTR_RO;
 		info->is_ready = id->nstat & NVME_NSTAT_NRDY;
+		info->is_rotational = id->nsfeat & NVME_NS_ROTATIONAL;
+		info->no_vwc = id->nsfeat & NVME_NS_VWC_NOT_PRESENT;
 	}
 	kfree(id);
 	return ret;
@@ -2185,11 +2189,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	    ns->head->ids.csi == NVME_CSI_ZNS)
 		nvme_update_zone_info(ns, &lim, &zi);
 
-	if (ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT)
+	if ((ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT) && !info->no_vwc)
 		lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA;
 	else
 		lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA);
 
+	if (info->is_rotational)
+		lim.features |= BLK_FEAT_ROTATIONAL;
+
 	/*
 	 * Register a metadata profile for PI, or the plain non-integrity NVMe
 	 * metadata masquerading as Type 0 if supported, otherwise reject block
@@ -3636,6 +3643,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->ns_id = info->nsid;
 	head->ids = info->ids;
 	head->shared = info->is_shared;
+	head->rotational = info->is_rotational;
 	ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
 	ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
 	kref_init(&head->ref);
@@ -4017,7 +4025,7 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns_info info = { .nsid = nsid };
 	struct nvme_ns *ns;
-	int ret;
+	int ret = 1;
 
 	if (nvme_identify_ns_descs(ctrl, &info))
 		return;
@@ -4034,9 +4042,10 @@ static void nvme_scan_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	 * set up a namespace.  If not fall back to the legacy version.
 	 */
 	if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) ||
-	    (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS))
+	    (info.ids.csi != NVME_CSI_NVM && info.ids.csi != NVME_CSI_ZNS) ||
+	    ctrl->vs >= NVME_VS(2, 0, 0))
 		ret = nvme_ns_info_from_id_cs_indep(ctrl, &info);
-	else
+	if (ret > 0)
 		ret = nvme_ns_info_from_identify(ctrl, &info);
 
 	if (info.is_removed)
@@ -4895,7 +4904,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 	srcu_idx = srcu_read_lock(&ctrl->srcu);
 	list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
 				 srcu_read_lock_held(&ctrl->srcu))
-		blk_mq_unfreeze_queue(ns->queue);
+		blk_mq_unfreeze_queue_non_owner(ns->queue);
 	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
@@ -4940,7 +4949,12 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 	srcu_idx = srcu_read_lock(&ctrl->srcu);
 	list_for_each_entry_srcu(ns, &ctrl->namespaces, list,
 				 srcu_read_lock_held(&ctrl->srcu))
-		blk_freeze_queue_start(ns->queue);
+		/*
+		 * Typical non_owner use case is from pci driver, in which
+		 * start_freeze is called from timeout work function, but
+		 * unfreeze is done in reset work context
+		 */
+		blk_freeze_queue_start_non_owner(ns->queue);
 	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_start_freeze);
@@ -5036,6 +5050,8 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_nvm) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
+	BUILD_BUG_ON(sizeof(struct nvme_endurance_group_log) != 512);
+	BUILD_BUG_ON(sizeof(struct nvme_rotational_media_log) != 512);
 	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_feat_host_behavior) != 512);
@@ -5044,22 +5060,20 @@ static inline void _nvme_check_size(void)
 
 static int __init nvme_core_init(void)
 {
+	unsigned int wq_flags = WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS;
 	int result = -ENOMEM;
 
 	_nvme_check_size();
 
-	nvme_wq = alloc_workqueue("nvme-wq",
-			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+	nvme_wq = alloc_workqueue("nvme-wq", wq_flags, 0);
 	if (!nvme_wq)
 		goto out;
 
-	nvme_reset_wq = alloc_workqueue("nvme-reset-wq",
-			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+	nvme_reset_wq = alloc_workqueue("nvme-reset-wq", wq_flags, 0);
 	if (!nvme_reset_wq)
 		goto destroy_wq;
 
-	nvme_delete_wq = alloc_workqueue("nvme-delete-wq",
-			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+	nvme_delete_wq = alloc_workqueue("nvme-delete-wq", wq_flags, 0);
 	if (!nvme_delete_wq)
 		goto destroy_reset_wq;
 
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index a96976b22fa7..6522ae16531c 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -114,7 +114,7 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
+		struct io_uring_cmd *ioucmd, unsigned int flags)
 {
 	struct request_queue *q = req->q;
 	struct nvme_ns *ns = q->queuedata;
@@ -152,8 +152,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		bio_set_dev(bio, bdev);
 
 	if (has_metadata) {
-		ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len,
-						meta_seed);
+		ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len);
 		if (ret)
 			goto out_unmap;
 	}
@@ -170,7 +169,7 @@ out:
 
 static int nvme_submit_user_cmd(struct request_queue *q,
 		struct nvme_command *cmd, u64 ubuffer, unsigned bufflen,
-		void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
+		void __user *meta_buffer, unsigned meta_len,
 		u64 *result, unsigned timeout, unsigned int flags)
 {
 	struct nvme_ns *ns = q->queuedata;
@@ -187,7 +186,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	req->timeout = timeout;
 	if (ubuffer && bufflen) {
 		ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
-				meta_len, meta_seed, NULL, flags);
+				meta_len, NULL, flags);
 		if (ret)
 			return ret;
 	}
@@ -268,7 +267,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.lbatm = cpu_to_le16(io.appmask);
 
 	return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
-			meta_len, lower_32_bits(io.slba), NULL, 0, 0);
+			meta_len, NULL, 0, 0);
 }
 
 static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
@@ -323,7 +322,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
-			cmd.metadata_len, 0, &result, timeout, 0);
+			cmd.metadata_len, &result, timeout, 0);
 
 	if (status >= 0) {
 		if (put_user(result, &ucmd->result))
@@ -370,7 +369,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
-			cmd.metadata_len, 0, &cmd.result, timeout, flags);
+			cmd.metadata_len, &cmd.result, timeout, flags);
 
 	if (status >= 0) {
 		if (put_user(cmd.result, &ucmd->result))
@@ -402,7 +401,7 @@ struct nvme_uring_cmd_pdu {
 static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
 		struct io_uring_cmd *ioucmd)
 {
-	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
+	return io_uring_cmd_to_pdu(ioucmd, struct nvme_uring_cmd_pdu);
 }
 
 static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
@@ -507,7 +506,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (d.addr && d.data_len) {
 		ret = nvme_map_user_request(req, d.addr,
 			d.data_len, nvme_to_user_ptr(d.metadata),
-			d.metadata_len, 0, ioucmd, vec);
+			d.metadata_len, ioucmd, vec);
 		if (ret)
 			return ret;
 	}
@@ -635,8 +634,6 @@ static int nvme_ns_uring_cmd(struct nvme_ns *ns, struct io_uring_cmd *ioucmd,
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
 
-	BUILD_BUG_ON(sizeof(struct nvme_uring_cmd_pdu) > sizeof(ioucmd->pdu));
-
 	ret = nvme_uring_cmd_checks(issue_flags);
 	if (ret)
 		return ret;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 6a15873055b9..f04cfe3fb936 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -635,8 +635,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL;
 	if (head->ids.csi == NVME_CSI_ZNS)
 		lim.features |= BLK_FEAT_ZONED;
-	else
-		lim.max_zone_append_sectors = 0;
 
 	head->disk = blk_alloc_disk(&lim, ctrl->numa_node);
 	if (IS_ERR(head->disk))
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 093cb423f536..900719c4c70c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -474,6 +474,7 @@ struct nvme_ns_head {
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
+	bool			rotational;
 	bool			passthru_err_log_enabled;
 	struct nvme_effects_log *effects;
 	u64			nuse;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4b9fda0b1d9a..5f2e3ad2cc52 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -141,6 +141,7 @@ struct nvme_dev {
 	struct nvme_ctrl ctrl;
 	u32 last_ps;
 	bool hmb;
+	struct sg_table *hmb_sgt;
 
 	mempool_t *iod_mempool;
 
@@ -153,6 +154,7 @@ struct nvme_dev {
 	/* host memory buffer support: */
 	u64 host_mem_size;
 	u32 nr_host_mem_descs;
+	u32 host_mem_descs_size;
 	dma_addr_t host_mem_descs_dma;
 	struct nvme_host_mem_buf_desc *host_mem_descs;
 	void **host_mem_desc_bufs;
@@ -902,11 +904,12 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
-static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct request **rqlist)
+static void nvme_submit_cmds(struct nvme_queue *nvmeq, struct rq_list *rqlist)
 {
+	struct request *req;
+
 	spin_lock(&nvmeq->sq_lock);
-	while (!rq_list_empty(*rqlist)) {
-		struct request *req = rq_list_pop(rqlist);
+	while ((req = rq_list_pop(rqlist))) {
 		struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
 		nvme_sq_copy_cmd(nvmeq, &iod->cmd);
@@ -929,33 +932,26 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
 	return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
 }
 
-static void nvme_queue_rqs(struct request **rqlist)
+static void nvme_queue_rqs(struct rq_list *rqlist)
 {
-	struct request *req, *next, *prev = NULL;
-	struct request *requeue_list = NULL;
-
-	rq_list_for_each_safe(rqlist, req, next) {
-		struct nvme_queue *nvmeq = req->mq_hctx->driver_data;
-
-		if (!nvme_prep_rq_batch(nvmeq, req)) {
-			/* detach 'req' and add to remainder list */
-			rq_list_move(rqlist, &requeue_list, req, prev);
+	struct rq_list submit_list = { };
+	struct rq_list requeue_list = { };
+	struct nvme_queue *nvmeq = NULL;
+	struct request *req;
 
-			req = prev;
-			if (!req)
-				continue;
-		}
+	while ((req = rq_list_pop(rqlist))) {
+		if (nvmeq && nvmeq != req->mq_hctx->driver_data)
+			nvme_submit_cmds(nvmeq, &submit_list);
+		nvmeq = req->mq_hctx->driver_data;
 
-		if (!next || req->mq_hctx != next->mq_hctx) {
-			/* detach rest of list, and submit */
-			req->rq_next = NULL;
-			nvme_submit_cmds(nvmeq, rqlist);
-			*rqlist = next;
-			prev = NULL;
-		} else
-			prev = req;
+		if (nvme_prep_rq_batch(nvmeq, req))
+			rq_list_add_tail(&submit_list, req);
+		else
+			rq_list_add_tail(&requeue_list, req);
 	}
 
+	if (nvmeq)
+		nvme_submit_cmds(nvmeq, &submit_list);
 	*rqlist = requeue_list;
 }
 
@@ -1083,7 +1079,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
 	DEFINE_IO_COMP_BATCH(iob);
 
 	if (nvme_poll_cq(nvmeq, &iob)) {
-		if (!rq_list_empty(iob.req_list))
+		if (!rq_list_empty(&iob.req_list))
 			nvme_pci_complete_batch(&iob);
 		return IRQ_HANDLED;
 	}
@@ -1951,7 +1947,7 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
 	return ret;
 }
 
-static void nvme_free_host_mem(struct nvme_dev *dev)
+static void nvme_free_host_mem_multi(struct nvme_dev *dev)
 {
 	int i;
 
@@ -1966,18 +1962,54 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
 
 	kfree(dev->host_mem_desc_bufs);
 	dev->host_mem_desc_bufs = NULL;
-	dma_free_coherent(dev->dev,
-			dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
+}
+
+static void nvme_free_host_mem(struct nvme_dev *dev)
+{
+	if (dev->hmb_sgt)
+		dma_free_noncontiguous(dev->dev, dev->host_mem_size,
+				dev->hmb_sgt, DMA_BIDIRECTIONAL);
+	else
+		nvme_free_host_mem_multi(dev);
+
+	dma_free_coherent(dev->dev, dev->host_mem_descs_size,
 			dev->host_mem_descs, dev->host_mem_descs_dma);
 	dev->host_mem_descs = NULL;
+	dev->host_mem_descs_size = 0;
 	dev->nr_host_mem_descs = 0;
 }
 
-static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
+static int nvme_alloc_host_mem_single(struct nvme_dev *dev, u64 size)
+{
+	dev->hmb_sgt = dma_alloc_noncontiguous(dev->dev, size,
+				DMA_BIDIRECTIONAL, GFP_KERNEL, 0);
+	if (!dev->hmb_sgt)
+		return -ENOMEM;
+
+	dev->host_mem_descs = dma_alloc_coherent(dev->dev,
+			sizeof(*dev->host_mem_descs), &dev->host_mem_descs_dma,
+			GFP_KERNEL);
+	if (!dev->host_mem_descs) {
+		dma_free_noncontiguous(dev->dev, dev->host_mem_size,
+				dev->hmb_sgt, DMA_BIDIRECTIONAL);
+		dev->hmb_sgt = NULL;
+		return -ENOMEM;
+	}
+	dev->host_mem_size = size;
+	dev->host_mem_descs_size = sizeof(*dev->host_mem_descs);
+	dev->nr_host_mem_descs = 1;
+
+	dev->host_mem_descs[0].addr =
+		cpu_to_le64(dev->hmb_sgt->sgl->dma_address);
+	dev->host_mem_descs[0].size = cpu_to_le32(size / NVME_CTRL_PAGE_SIZE);
+	return 0;
+}
+
+static int nvme_alloc_host_mem_multi(struct nvme_dev *dev, u64 preferred,
 		u32 chunk_size)
 {
 	struct nvme_host_mem_buf_desc *descs;
-	u32 max_entries, len;
+	u32 max_entries, len, descs_size;
 	dma_addr_t descs_dma;
 	int i = 0;
 	void **bufs;
@@ -1990,8 +2022,9 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 	if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
 		max_entries = dev->ctrl.hmmaxd;
 
-	descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs),
-				   &descs_dma, GFP_KERNEL);
+	descs_size = max_entries * sizeof(*descs);
+	descs = dma_alloc_coherent(dev->dev, descs_size, &descs_dma,
+			GFP_KERNEL);
 	if (!descs)
 		goto out;
 
@@ -2020,6 +2053,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 	dev->host_mem_size = size;
 	dev->host_mem_descs = descs;
 	dev->host_mem_descs_dma = descs_dma;
+	dev->host_mem_descs_size = descs_size;
 	dev->host_mem_desc_bufs = bufs;
 	return 0;
 
@@ -2034,8 +2068,7 @@ out_free_bufs:
 
 	kfree(bufs);
 out_free_descs:
-	dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
-			descs_dma);
+	dma_free_coherent(dev->dev, descs_size, descs, descs_dma);
 out:
 	dev->host_mem_descs = NULL;
 	return -ENOMEM;
@@ -2047,9 +2080,18 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 	u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
 	u64 chunk_size;
 
+	/*
+	 * If there is an IOMMU that can merge pages, try a virtually
+	 * non-contiguous allocation for a single segment first.
+	 */
+	if (!(PAGE_SIZE & dma_get_merge_boundary(dev->dev))) {
+		if (!nvme_alloc_host_mem_single(dev, preferred))
+			return 0;
+	}
+
 	/* start big and work our way down */
 	for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) {
-		if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
+		if (!nvme_alloc_host_mem_multi(dev, preferred, chunk_size)) {
 			if (!min || dev->host_mem_size >= min)
 				return 0;
 			nvme_free_host_mem(dev);
@@ -2097,8 +2139,10 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
 		}
 
 		dev_info(dev->ctrl.device,
-			"allocated %lld MiB host memory buffer.\n",
-			dev->host_mem_size >> ilog2(SZ_1M));
+			"allocated %lld MiB host memory buffer (%u segment%s).\n",
+			dev->host_mem_size >> ilog2(SZ_1M),
+			dev->nr_host_mem_descs,
+			str_plural(dev->nr_host_mem_descs));
 	}
 
 	ret = nvme_set_host_mem(dev, enable_bits);
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 87c437fc070d..ad25ad1e4041 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -228,27 +228,61 @@ static const char *nvme_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10)
 
 static const char *nvme_trace_resv_reg(struct trace_seq *p, u8 *cdw10)
 {
+	static const char * const rrega_strs[] = {
+		[0x00] = "register",
+		[0x01] = "unregister",
+		[0x02] = "replace",
+	};
 	const char *ret = trace_seq_buffer_ptr(p);
 	u8 rrega = cdw10[0] & 0x7;
 	u8 iekey = (cdw10[0] >> 3) & 0x1;
 	u8 ptpl = (cdw10[3] >> 6) & 0x3;
+	const char *rrega_str;
+
+	if (rrega < ARRAY_SIZE(rrega_strs) && rrega_strs[rrega])
+		rrega_str = rrega_strs[rrega];
+	else
+		rrega_str = "reserved";
 
-	trace_seq_printf(p, "rrega=%u, iekey=%u, ptpl=%u",
-			 rrega, iekey, ptpl);
+	trace_seq_printf(p, "rrega=%u:%s, iekey=%u, ptpl=%u",
+			 rrega, rrega_str, iekey, ptpl);
 	trace_seq_putc(p, 0);
 
 	return ret;
 }
 
+static const char * const rtype_strs[] = {
+	[0x00] = "reserved",
+	[0x01] = "write exclusive",
+	[0x02] = "exclusive access",
+	[0x03] = "write exclusive registrants only",
+	[0x04] = "exclusive access registrants only",
+	[0x05] = "write exclusive all registrants",
+	[0x06] = "exclusive access all registrants",
+};
+
 static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10)
 {
+	static const char * const racqa_strs[] = {
+		[0x00] = "acquire",
+		[0x01] = "preempt",
+		[0x02] = "preempt and abort",
+	};
 	const char *ret = trace_seq_buffer_ptr(p);
 	u8 racqa = cdw10[0] & 0x7;
 	u8 iekey = (cdw10[0] >> 3) & 0x1;
 	u8 rtype = cdw10[1];
+	const char *racqa_str = "reserved";
+	const char *rtype_str = "reserved";
 
-	trace_seq_printf(p, "racqa=%u, iekey=%u, rtype=%u",
-			 racqa, iekey, rtype);
+	if (racqa < ARRAY_SIZE(racqa_strs) && racqa_strs[racqa])
+		racqa_str = racqa_strs[racqa];
+
+	if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype])
+		rtype_str = rtype_strs[rtype];
+
+	trace_seq_printf(p, "racqa=%u:%s, iekey=%u, rtype=%u:%s",
+			 racqa, racqa_str, iekey, rtype, rtype_str);
 	trace_seq_putc(p, 0);
 
 	return ret;
@@ -256,13 +290,25 @@ static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10)
 
 static const char *nvme_trace_resv_rel(struct trace_seq *p, u8 *cdw10)
 {
+	static const char * const rrela_strs[] = {
+		[0x00] = "release",
+		[0x01] = "clear",
+	};
 	const char *ret = trace_seq_buffer_ptr(p);
 	u8 rrela = cdw10[0] & 0x7;
 	u8 iekey = (cdw10[0] >> 3) & 0x1;
 	u8 rtype = cdw10[1];
+	const char *rrela_str = "reserved";
+	const char *rtype_str = "reserved";
+
+	if (rrela < ARRAY_SIZE(rrela_strs) && rrela_strs[rrela])
+		rrela_str = rrela_strs[rrela];
+
+	if (rtype < ARRAY_SIZE(rtype_strs) && rtype_strs[rtype])
+		rtype_str = rtype_strs[rtype];
 
-	trace_seq_printf(p, "rrela=%u, iekey=%u, rtype=%u",
-			 rrela, iekey, rtype);
+	trace_seq_printf(p, "rrela=%u:%s, iekey=%u, rtype=%u:%s",
+			 rrela, rrela_str, iekey, rtype, rtype_str);
 	trace_seq_putc(p, 0);
 
 	return ret;
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 9a06f9d98cd6..382949e18c6a 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -111,7 +111,7 @@ void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
 	lim->features |= BLK_FEAT_ZONED;
 	lim->max_open_zones = zi->max_open_zones;
 	lim->max_active_zones = zi->max_active_zones;
-	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
+	lim->max_hw_zone_append_sectors = ns->ctrl->max_zone_append;
 	lim->chunk_sectors = ns->head->zsze =
 		nvme_lba_to_sect(ns->head, zi->zone_size);
 }