libnvdimm: blk labels and namespace instantiation

A blk label set describes a namespace comprised of one or more
discontiguous dpa ranges on a single dimm.  They may alias with one or
more pmem interleave sets that include the given dimm.

This is the runtime/volatile configuration infrastructure for sysfs
manipulation of 'alt_name', 'uuid', 'size', and 'sector_size'.  A later
patch will make these settings persistent by writing back the label(s).

Unlike pmem namespaces, multiple blk namespaces can be created per
region.  Once a blk namespace has been created a new seed device
(unconfigured child of a parent blk region) is instantiated.  As long as
a region has 'available_size' != 0 new child namespaces may be created.

Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Neil Brown <neilb@suse.de>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/nvdimm/core.c

@@ -173,6 +173,46 @@ int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
 	return 0;
 }
 
+ssize_t nd_sector_size_show(unsigned long current_lbasize,
+		const unsigned long *supported, char *buf)
+{
+	ssize_t len = 0;
+	int i;
+
+	for (i = 0; supported[i]; i++)
+		if (current_lbasize == supported[i])
+			len += sprintf(buf + len, "[%ld] ", supported[i]);
+		else
+			len += sprintf(buf + len, "%ld ", supported[i]);
+	len += sprintf(buf + len, "\n");
+	return len;
+}
+
+ssize_t nd_sector_size_store(struct device *dev, const char *buf,
+		unsigned long *current_lbasize, const unsigned long *supported)
+{
+	unsigned long lbasize;
+	int rc, i;
+
+	if (dev->driver)
+		return -EBUSY;
+
+	rc = kstrtoul(buf, 0, &lbasize);
+	if (rc)
+		return rc;
+
+	for (i = 0; supported[i]; i++)
+		if (lbasize == supported[i])
+			break;
+
+	if (supported[i]) {
+		*current_lbasize = lbasize;
+		return 0;
+	} else {
+		return -EINVAL;
+	}
+}
+
 static ssize_t commands_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {

drivers/nvdimm/dimm_devs.c

@@ -289,6 +289,42 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
 }
 EXPORT_SYMBOL_GPL(nvdimm_create);
 
+/**
+ * nd_blk_available_dpa - account the unused dpa of BLK region
+ * @nd_mapping: container of dpa-resource-root + labels
+ *
+ * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges.
+ */
+resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping)
+{
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	resource_size_t map_end, busy = 0, available;
+	struct resource *res;
+
+	if (!ndd)
+		return 0;
+
+	map_end = nd_mapping->start + nd_mapping->size - 1;
+	for_each_dpa_resource(ndd, res)
+		if (res->start >= nd_mapping->start && res->start < map_end) {
+			resource_size_t end = min(map_end, res->end);
+
+			busy += end - res->start + 1;
+		} else if (res->end >= nd_mapping->start
+				&& res->end <= map_end) {
+			busy += res->end - nd_mapping->start;
+		} else if (nd_mapping->start > res->start
+				&& nd_mapping->start < res->end) {
+			/* total eclipse of the BLK region mapping */
+			busy += nd_mapping->size;
+		}
+
+	available = map_end - nd_mapping->start + 1;
+	if (busy < available)
+		return available - busy;
+	return 0;
+}
+
 /**
  * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa
  * @nd_mapping: container of dpa-resource-root + labels

drivers/nvdimm/nd-core.h

@@ -17,6 +17,7 @@
 #include <linux/libnvdimm.h>
 #include <linux/sizes.h>
 #include <linux/mutex.h>
+#include <linux/nd.h>
 
 extern struct list_head nvdimm_bus_list;
 extern struct mutex nvdimm_bus_list_mutex;
@@ -48,6 +49,8 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
 int __init nvdimm_bus_init(void);
 void nvdimm_bus_exit(void);
 void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
+struct nd_region;
+void nd_region_create_blk_seed(struct nd_region *nd_region);
 void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
 void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
@@ -64,8 +67,13 @@ struct nvdimm_drvdata;
 struct nd_mapping;
 resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, resource_size_t *overlap);
+resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping);
 resource_size_t nd_region_available_dpa(struct nd_region *nd_region);
 resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
 		struct nd_label_id *label_id);
+struct nd_mapping;
+struct resource *nsblk_add_resource(struct nd_region *nd_region,
+		struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk,
+		resource_size_t start);
 void get_ndd(struct nvdimm_drvdata *ndd);
 #endif /* __ND_CORE_H__ */

drivers/nvdimm/nd.h

@@ -73,6 +73,7 @@ static inline struct nd_namespace_index *to_next_namespace_index(
 
 struct nd_region {
 	struct device dev;
+	struct ida ns_ida;
 	struct device *ns_seed;
 	u16 ndr_mappings;
 	u64 ndr_size;
@@ -102,6 +103,10 @@ void nd_device_register(struct device *dev);
 void nd_device_unregister(struct device *dev, enum nd_async_mode mode);
 int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
 		size_t len);
+ssize_t nd_sector_size_show(unsigned long current_lbasize,
+		const unsigned long *supported, char *buf);
+ssize_t nd_sector_size_store(struct device *dev, const char *buf,
+		unsigned long *current_lbasize, const unsigned long *supported);
 int __init nvdimm_init(void);
 int __init nd_region_init(void);
 void nvdimm_exit(void);

drivers/nvdimm/region_devs.c

@@ -118,7 +118,12 @@ static int is_uuid_busy(struct device *dev, void *data)
 		break;
 	}
 	case ND_DEVICE_NAMESPACE_BLK: {
-		/* TODO: blk namespace support */
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		if (!nsblk->uuid)
+			break;
+		if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0)
+			return -EBUSY;
 		break;
 	}
 	default:
@@ -230,7 +235,7 @@ resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
 				goto retry;
 			}
 		} else if (is_nd_blk(&nd_region->dev)) {
-			/* TODO: BLK Namespace support */
+			available += nd_blk_available_dpa(nd_mapping);
 		}
 	}
 
@@ -360,6 +365,13 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 			nd_mapping->ndd = NULL;
 			atomic_dec(&nvdimm->busy);
 		}
+	} else if (dev->parent && is_nd_blk(dev->parent) && probe) {
+		struct nd_region *nd_region = to_nd_region(dev->parent);
+
+		nvdimm_bus_lock(dev);
+		if (nd_region->ns_seed == dev)
+			nd_region_create_blk_seed(nd_region);
+		nvdimm_bus_unlock(dev);
 	}
 }
 
@@ -533,6 +545,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	nd_region->ndr_mappings = ndr_desc->num_mappings;
 	nd_region->provider_data = ndr_desc->provider_data;
 	nd_region->nd_set = ndr_desc->nd_set;
+	ida_init(&nd_region->ns_ida);
 	dev = &nd_region->dev;
 	dev_set_name(dev, "region%d", nd_region->id);
 	dev->parent = &nvdimm_bus->dev;

include/linux/libnvdimm.h

@@ -27,6 +27,9 @@ enum {
 	ND_CMD_MAX_ENVELOPE = 16,
 	ND_CMD_ARS_STATUS_MAX = SZ_4K,
 	ND_MAX_MAPPINGS = 32,
+
+	/* mark newly adjusted resources as requiring a label update */
+	DPA_RESOURCE_ADJUSTED = 1 << 0,
 };
 
 extern struct attribute_group nvdimm_bus_attribute_group;

include/linux/nd.h

@@ -50,6 +50,26 @@ struct nd_namespace_pmem {
 	u8 *uuid;
 };
 
+/**
+ * struct nd_namespace_blk - namespace for dimm-bounded persistent memory
+ * @dev: namespace device creation by the nd region driver
+ * @alt_name: namespace name supplied in the dimm label
+ * @uuid: namespace name supplied in the dimm label
+ * @id: ida allocated id
+ * @lbasize: blk namespaces have a native sector size when btt not present
+ * @num_resources: number of dpa extents to claim
+ * @res: discontiguous dpa extents for given dimm
+ */
+struct nd_namespace_blk {
+	struct device dev;
+	char *alt_name;
+	u8 *uuid;
+	int id;
+	unsigned long lbasize;
+	int num_resources;
+	struct resource **res;
+};
+
 static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev)
 {
 	return container_of(dev, struct nd_namespace_io, dev);
@@ -62,6 +82,11 @@ static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev)
 	return container_of(nsio, struct nd_namespace_pmem, nsio);
 }
 
+static inline struct nd_namespace_blk *to_nd_namespace_blk(struct device *dev)
+{
+	return container_of(dev, struct nd_namespace_blk, dev);
+}
+
 #define MODULE_ALIAS_ND_DEVICE(type) \
 	MODULE_ALIAS("nd:t" __stringify(type) "*")
 #define ND_DEVICE_MODALIAS_FMT "nd:t%d"