Merge tag 'nvme-6.8-2023-12-21' of git://git.infradead.org/nvme into for-6.8/block

Pull NVMe updates from Keith:

"nvme updates for Linux 6.8

 - nvme fabrics spec updates (Guixin, Max)
 - nvme target udpates (Guixin, Evan)
 - nvme attribute refactoring (Daniel)
 - nvme-fc numa fix (Keith)"

* tag 'nvme-6.8-2023-12-21' of git://git.infradead.org/nvme:
  nvme-fc: set numa_node after nvme_init_ctrl
  nvme-fabrics: don't check discovery ioccsz/iorcsz
  nvmet: configfs: use ctrl->instance to track passthru subsystems
  nvme: repack struct nvme_ns_head
  nvme: add csi, ms and nuse to sysfs
  nvme: rename ns attribute group
  nvme: refactor ns info setup function
  nvme: refactor ns info helpers
  nvme: move ns id info to struct nvme_ns_head
  nvmet: remove cntlid_min and cntlid_max check in nvmet_alloc_ctrl
  nvmet: allow identical cntlid_min and cntlid_max settings
  nvme-fabrics: check ioccsz and iorcsz
  nvme: introduce nvme_check_ctrl_fabric_info helper

drivers/nvme/host/fc.c

@@ -3509,10 +3509,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	ctrl->ctrl.opts = opts;
 	ctrl->ctrl.nr_reconnects = 0;
-	if (lport->dev)
-		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
-	else
-		ctrl->ctrl.numa_node = NUMA_NO_NODE;
 	INIT_LIST_HEAD(&ctrl->ctrl_list);
 	ctrl->lport = lport;
 	ctrl->rport = rport;
@@ -3557,6 +3553,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
 	if (ret)
 		goto out_free_queues;
+	if (lport->dev)
+		ctrl->ctrl.numa_node = dev_to_node(lport->dev);
 
 	/* at this point, teardown path changes to ref counting on nvme ctrl */
 

drivers/nvme/host/ioctl.c

@@ -224,10 +224,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		return -EINVAL;
 	}
 
-	length = (io.nblocks + 1) << ns->lba_shift;
+	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->ms == sizeof(struct t10_pi_tuple)) {
+	    ns->head->ms == sizeof(struct t10_pi_tuple)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
@@ -237,11 +237,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		meta_len = 0;
 		metadata = NULL;
 	} else {
-		meta_len = (io.nblocks + 1) * ns->ms;
+		meta_len = (io.nblocks + 1) * ns->head->ms;
 		metadata = nvme_to_user_ptr(io.metadata);
 	}
 
-	if (ns->features & NVME_NS_EXT_LBAS) {
+	if (ns->head->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {

drivers/nvme/host/multipath.c

@@ -579,7 +579,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	 */
 	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		rc = device_add_disk(&head->subsys->dev, head->disk,
-				     nvme_ns_id_attr_groups);
+				     nvme_ns_attr_groups);
 		if (rc) {
 			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
 			return;

drivers/nvme/host/nvme.h

@@ -16,6 +16,7 @@
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
 #include <linux/t10-pi.h>
+#include <linux/ratelimit_types.h>
 
 #include <trace/events/block.h>
 
@@ -439,13 +440,27 @@ struct nvme_ns_head {
 	struct list_head	list;
 	struct srcu_struct      srcu;
 	struct nvme_subsystem	*subsys;
-	unsigned		ns_id;
 	struct nvme_ns_ids	ids;
 	struct list_head	entry;
 	struct kref		ref;
 	bool			shared;
 	int			instance;
 	struct nvme_effects_log *effects;
+	u64			nuse;
+	unsigned		ns_id;
+	int			lba_shift;
+	u16			ms;
+	u16			pi_size;
+	u8			pi_type;
+	u8			guard_type;
+	u16			sgs;
+	u32			sws;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u64			zsze;
+#endif
+	unsigned long		features;
+
+	struct ratelimit_state	rs_nuse;
 
 	struct cdev		cdev;
 	struct device		cdev_device;
@@ -487,17 +502,6 @@ struct nvme_ns {
 	struct kref kref;
 	struct nvme_ns_head *head;
 
-	int lba_shift;
-	u16 ms;
-	u16 pi_size;
-	u16 sgs;
-	u32 sws;
-	u8 pi_type;
-	u8 guard_type;
-#ifdef CONFIG_BLK_DEV_ZONED
-	u64 zsze;
-#endif
-	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
 #define NVME_NS_ANA_PENDING	2
@@ -512,9 +516,9 @@ struct nvme_ns {
 };
 
 /* NVMe ns supports metadata actions by the controller (generate/strip) */
-static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
+static inline bool nvme_ns_has_pi(struct nvme_ns_head *head)
 {
-	return ns->pi_type && ns->ms == ns->pi_size;
+	return head->pi_type && head->ms == head->pi_size;
 }
 
 struct nvme_ctrl_ops {
@@ -646,17 +650,17 @@ static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
 /*
  * Convert a 512B sector number to a device logical block number.
  */
-static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector)
+static inline u64 nvme_sect_to_lba(struct nvme_ns_head *head, sector_t sector)
 {
-	return sector >> (ns->lba_shift - SECTOR_SHIFT);
+	return sector >> (head->lba_shift - SECTOR_SHIFT);
 }
 
 /*
  * Convert a device logical block number to a 512B sector number.
  */
-static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba)
+static inline sector_t nvme_lba_to_sect(struct nvme_ns_head *head, u64 lba)
 {
-	return lba << (ns->lba_shift - SECTOR_SHIFT);
+	return lba << (head->lba_shift - SECTOR_SHIFT);
 }
 
 /*
@@ -862,10 +866,12 @@ int nvme_ns_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
 int nvme_ns_head_chr_uring_cmd(struct io_uring_cmd *ioucmd,
 		unsigned int issue_flags);
+int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
+		struct nvme_id_ns **id);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 
-extern const struct attribute_group *nvme_ns_id_attr_groups[];
+extern const struct attribute_group *nvme_ns_attr_groups[];
 extern const struct pr_ops nvme_pr_ops;
 extern const struct block_device_operations nvme_ns_head_ops;
 extern const struct attribute_group nvme_dev_attrs_group;

drivers/nvme/host/rdma.c

@@ -1418,7 +1418,7 @@ static int nvme_rdma_map_sg_pi(struct nvme_rdma_queue *queue,
 		goto mr_put;
 
 	nvme_rdma_set_sig_attrs(blk_get_integrity(bio->bi_bdev->bd_disk), c,
-				req->mr->sig_attrs, ns->pi_type);
+				req->mr->sig_attrs, ns->head->pi_type);
 	nvme_rdma_set_prot_checks(c, &req->mr->sig_attrs->check_mask);
 
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
@@ -2012,7 +2012,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	    queue->pi_support &&
 	    (c->common.opcode == nvme_cmd_write ||
 	     c->common.opcode == nvme_cmd_read) &&
-	    nvme_ns_has_pi(ns))
+	    nvme_ns_has_pi(ns->head))
 		req->use_sig_mr = true;
 	else
 		req->use_sig_mr = false;

drivers/nvme/host/sysfs.c

@@ -114,12 +114,97 @@ static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(nsid);
 
-static struct attribute *nvme_ns_id_attrs[] = {
+static ssize_t csi_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ids.csi);
+}
+static DEVICE_ATTR_RO(csi);
+
+static ssize_t metadata_bytes_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", dev_to_ns_head(dev)->ms);
+}
+static DEVICE_ATTR_RO(metadata_bytes);
+
+static int ns_head_update_nuse(struct nvme_ns_head *head)
+{
+	struct nvme_id_ns *id;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	/* Avoid issuing commands too often by rate limiting the update */
+	if (!__ratelimit(&head->rs_nuse))
+		return 0;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns)
+		goto out_unlock;
+
+	ret = nvme_identify_ns(ns->ctrl, head->ns_id, &id);
+	if (ret)
+		goto out_unlock;
+
+	head->nuse = le64_to_cpu(id->nuse);
+	kfree(id);
+
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+
+static int ns_update_nuse(struct nvme_ns *ns)
+{
+	struct nvme_id_ns *id;
+	int ret;
+
+	/* Avoid issuing commands too often by rate limiting the update. */
+	if (!__ratelimit(&ns->head->rs_nuse))
+		return 0;
+
+	ret = nvme_identify_ns(ns->ctrl, ns->head->ns_id, &id);
+	if (ret)
+		goto out_free_id;
+
+	ns->head->nuse = le64_to_cpu(id->nuse);
+
+out_free_id:
+	kfree(id);
+
+	return ret;
+}
+
+static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns_head *head = dev_to_ns_head(dev);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct block_device *bdev = disk->part0;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
+	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+		ret = ns_head_update_nuse(head);
+	else
+		ret = ns_update_nuse(bdev->bd_disk->private_data);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu\n", head->nuse);
+}
+static DEVICE_ATTR_RO(nuse);
+
+static struct attribute *nvme_ns_attrs[] = {
 	&dev_attr_wwid.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
+	&dev_attr_csi.attr,
 	&dev_attr_nsid.attr,
+	&dev_attr_metadata_bytes.attr,
+	&dev_attr_nuse.attr,
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
@@ -127,7 +212,7 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	NULL,
 };
 
-static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
+static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 		struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -157,13 +242,13 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static const struct attribute_group nvme_ns_id_attr_group = {
-	.attrs		= nvme_ns_id_attrs,
-	.is_visible	= nvme_ns_id_attrs_are_visible,
+static const struct attribute_group nvme_ns_attr_group = {
+	.attrs		= nvme_ns_attrs,
+	.is_visible	= nvme_ns_attrs_are_visible,
 };
 
-const struct attribute_group *nvme_ns_id_attr_groups[] = {
-	&nvme_ns_id_attr_group,
+const struct attribute_group *nvme_ns_attr_groups[] = {
+	&nvme_ns_attr_group,
 	NULL,
 };
 

drivers/nvme/host/zns.c

@@ -11,7 +11,7 @@ int nvme_revalidate_zones(struct nvme_ns *ns)
 {
 	struct request_queue *q = ns->queue;
 
-	blk_queue_chunk_sectors(q, ns->zsze);
+	blk_queue_chunk_sectors(q, ns->head->zsze);
 	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
 
 	return blk_revalidate_disk_zones(ns->disk, NULL);
@@ -99,11 +99,12 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
-	if (!is_power_of_2(ns->zsze)) {
+	ns->head->zsze =
+		nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
+	if (!is_power_of_2(ns->head->zsze)) {
 		dev_warn(ns->ctrl->device,
 			"invalid zone size:%llu for namespace:%u\n",
-			ns->zsze, ns->head->ns_id);
+			ns->head->zsze, ns->head->ns_id);
 		status = -ENODEV;
 		goto free_data;
 	}
@@ -128,7 +129,7 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 				   sizeof(struct nvme_zone_descriptor);
 
 	nr_zones = min_t(unsigned int, nr_zones,
-			 get_capacity(ns->disk) >> ilog2(ns->zsze));
+			 get_capacity(ns->disk) >> ilog2(ns->head->zsze));
 
 	bufsize = sizeof(struct nvme_zone_report) +
 		nr_zones * sizeof(struct nvme_zone_descriptor);
@@ -147,7 +148,8 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	return NULL;
 }
 
-static int nvme_zone_parse_entry(struct nvme_ns *ns,
+static int nvme_zone_parse_entry(struct nvme_ctrl *ctrl,
+				 struct nvme_ns_head *head,
 				 struct nvme_zone_descriptor *entry,
 				 unsigned int idx, report_zones_cb cb,
 				 void *data)
@@ -155,20 +157,20 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	struct blk_zone zone = { };
 
 	if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
-		dev_err(ns->ctrl->device, "invalid zone type %#x\n",
+		dev_err(ctrl->device, "invalid zone type %#x\n",
 				entry->zt);
 		return -EINVAL;
 	}
 
 	zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
 	zone.cond = entry->zs >> 4;
-	zone.len = ns->zsze;
-	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
-	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
+	zone.len = head->zsze;
+	zone.capacity = nvme_lba_to_sect(head, le64_to_cpu(entry->zcap));
+	zone.start = nvme_lba_to_sect(head, le64_to_cpu(entry->zslba));
 	if (zone.cond == BLK_ZONE_COND_FULL)
 		zone.wp = zone.start + zone.len;
 	else
-		zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+		zone.wp = nvme_lba_to_sect(head, le64_to_cpu(entry->wp));
 
 	return cb(&zone, idx, data);
 }
@@ -196,11 +198,11 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
 	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
 
-	sector &= ~(ns->zsze - 1);
+	sector &= ~(ns->head->zsze - 1);
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);
 
-		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, sector));
 		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
 		if (ret) {
 			if (ret > 0)
@@ -213,14 +215,15 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 			break;
 
 		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
-			ret = nvme_zone_parse_entry(ns, &report->entries[i],
+			ret = nvme_zone_parse_entry(ns->ctrl, ns->head,
+						    &report->entries[i],
 						    zone_idx, cb, data);
 			if (ret)
 				goto out_free;
 			zone_idx++;
 		}
 
-		sector += ns->zsze * nz;
+		sector += ns->head->zsze * nz;
 	}
 
 	if (zone_idx > 0)
@@ -239,7 +242,7 @@ blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 
 	c->zms.opcode = nvme_cmd_zone_mgmt_send;
 	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
-	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
 	c->zms.zsa = action;
 
 	if (req_op(req) == REQ_OP_ZONE_RESET_ALL)

drivers/nvme/target/configfs.c

@@ -1274,7 +1274,7 @@ static ssize_t nvmet_subsys_attr_cntlid_min_store(struct config_item *item,
 		return -EINVAL;
 
 	down_write(&nvmet_config_sem);
-	if (cntlid_min >= to_subsys(item)->cntlid_max)
+	if (cntlid_min > to_subsys(item)->cntlid_max)
 		goto out_unlock;
 	to_subsys(item)->cntlid_min = cntlid_min;
 	up_write(&nvmet_config_sem);
@@ -1304,7 +1304,7 @@ static ssize_t nvmet_subsys_attr_cntlid_max_store(struct config_item *item,
 		return -EINVAL;
 
 	down_write(&nvmet_config_sem);
-	if (cntlid_max <= to_subsys(item)->cntlid_min)
+	if (cntlid_max < to_subsys(item)->cntlid_min)
 		goto out_unlock;
 	to_subsys(item)->cntlid_max = cntlid_max;
 	up_write(&nvmet_config_sem);

drivers/nvme/target/core.c

@@ -1425,9 +1425,6 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	if (!ctrl->sqs)
 		goto out_free_changed_ns_list;
 
-	if (subsys->cntlid_min > subsys->cntlid_max)
-		goto out_free_sqs;
-
 	ret = ida_alloc_range(&cntlid_ida,
 			     subsys->cntlid_min, subsys->cntlid_max,
 			     GFP_KERNEL);

drivers/nvme/target/passthru.c

@@ -602,7 +602,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 		goto out_put_file;
 	}
 
-	old = xa_cmpxchg(&passthru_subsystems, ctrl->cntlid, NULL,
+	old = xa_cmpxchg(&passthru_subsystems, ctrl->instance, NULL,
 			 subsys, GFP_KERNEL);
 	if (xa_is_err(old)) {
 		ret = xa_err(old);
@@ -635,7 +635,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys)
 {
 	if (subsys->passthru_ctrl) {
-		xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid);
+		xa_erase(&passthru_subsystems, subsys->passthru_ctrl->instance);
 		module_put(subsys->passthru_ctrl->ops->module);
 		nvme_put_ctrl(subsys->passthru_ctrl);
 	}