Merge tag 'nvme-6.13-2024-11-13' of git://git.infradead.org/nvme into…

… for-6.13/block

Pull NVMe updates from Keith:

"nvme updates for Linux 6.13

 - 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)"

* tag 'nvme-6.13-2024-11-13' of git://git.infradead.org/nvme: (22 commits)
  nvmet: add tracing of reservation commands
  nvme: parse reservation commands's action and rtype to string
  nvmet: report ns's vwc not present
  nvme: check ns's volatile write cache not present
  nvme: add rotational support
  nvme: use command set independent id ns if available
  nvmet: support for csi identify ns
  nvmet: implement rotational media information log
  nvmet: implement endurance groups
  nvmet: declare 2.1 version compliance
  nvmet: implement crto property
  nvmet: implement supported features log
  nvmet: implement supported log pages
  nvmet: implement active command set ns list
  nvmet: implement id ns for nvm command set
  nvmet: support reservation feature
  nvme: add reservation command's defines
  nvme-core: remove repeated wq flags
  nvmet: make nvmet_wq visible in sysfs
  nvme-pci: use dma_alloc_noncontigous if possible
  ...

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;
@@ -1615,6 +1617,8 @@ 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;
@@ -2157,11 +2161,14 @@ 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
@@ -3608,6 +3615,7 @@ 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);
@@ -3988,7 +3996,7 @@ 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;
@@ -4005,9 +4013,10 @@ 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)
@@ -5006,6 +5015,8 @@ 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);
@@ -5014,22 +5025,20 @@ 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;
 

drivers/nvme/host/ioctl.c

@@ -401,7 +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,
@@ -631,8 +631,6 @@ 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;

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;

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;
@@ -1951,7 +1953,7 @@ 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 +1968,54 @@ 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 +2028,9 @@ 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 +2059,7 @@ 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 +2074,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 
 	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 +2086,18 @@ 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 +2145,10 @@ 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);

drivers/nvme/host/trace.c

@@ -228,41 +228,87 @@ 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;
 }
 
 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;

drivers/nvme/target/Makefile

@@ -10,7 +10,7 @@ obj-$(CONFIG_NVME_TARGET_FCLOOP)	+= nvme-fcloop.o
 obj-$(CONFIG_NVME_TARGET_TCP)		+= nvmet-tcp.o
 
 nvmet-y		+= core.o configfs.o admin-cmd.o fabrics-cmd.o \
-			discovery.o io-cmd-file.o io-cmd-bdev.o
+			discovery.o io-cmd-file.o io-cmd-bdev.o pr.o
 nvmet-$(CONFIG_NVME_TARGET_DEBUGFS)	+= debugfs.o
 nvmet-$(CONFIG_NVME_TARGET_PASSTHRU)	+= passthru.o
 nvmet-$(CONFIG_BLK_DEV_ZONED)		+= zns.o