Merge tag 'libnvdimm-for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm

Pull libnvdimm subsystem from Dan Williams:
 "The libnvdimm sub-system introduces, in addition to the
  libnvdimm-core, 4 drivers / enabling modules:

  NFIT:
    Instantiates an "nvdimm bus" with the core and registers memory
    devices (NVDIMMs) enumerated by the ACPI 6.0 NFIT (NVDIMM Firmware
    Interface table).

    After registering NVDIMMs the NFIT driver then registers "region"
    devices.  A libnvdimm-region defines an access mode and the
    boundaries of persistent memory media.  A region may span multiple
    NVDIMMs that are interleaved by the hardware memory controller.  In
    turn, a libnvdimm-region can be carved into a "namespace" device and
    bound to the PMEM or BLK driver which will attach a Linux block
    device (disk) interface to the memory.

  PMEM:
    Initially merged in v4.1 this driver for contiguous spans of
    persistent memory address ranges is re-worked to drive
    PMEM-namespaces emitted by the libnvdimm-core.

    In this update the PMEM driver, on x86, gains the ability to assert
    that writes to persistent memory have been flushed all the way
    through the caches and buffers in the platform to persistent media.
    See memcpy_to_pmem() and wmb_pmem().

  BLK:
    This new driver enables access to persistent memory media through
    "Block Data Windows" as defined by the NFIT.  The primary difference
    of this driver to PMEM is that only a small window of persistent
    memory is mapped into system address space at any given point in
    time.

    Per-NVDIMM windows are reprogrammed at run time, per-I/O, to access
    different portions of the media.  BLK-mode, by definition, does not
    support DAX.

  BTT:
    This is a library, optionally consumed by either PMEM or BLK, that
    converts a byte-accessible namespace into a disk with atomic sector
    update semantics (prevents sector tearing on crash or power loss).

    The sinister aspect of sector tearing is that most applications do
    not know they have a atomic sector dependency.  At least today's
    disk's rarely ever tear sectors and if they do one almost certainly
    gets a CRC error on access.  NVDIMMs will always tear and always
    silently.  Until an application is audited to be robust in the
    presence of sector-tearing the usage of BTT is recommended.

  Thanks to: Ross Zwisler, Jeff Moyer, Vishal Verma, Christoph Hellwig,
  Ingo Molnar, Neil Brown, Boaz Harrosh, Robert Elliott, Matthew Wilcox,
  Andy Rudoff, Linda Knippers, Toshi Kani, Nicholas Moulin, Rafael
  Wysocki, and Bob Moore"

* tag 'libnvdimm-for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm: (33 commits)
  arch, x86: pmem api for ensuring durability of persistent memory updates
  libnvdimm: Add sysfs numa_node to NVDIMM devices
  libnvdimm: Set numa_node to NVDIMM devices
  acpi: Add acpi_map_pxm_to_online_node()
  libnvdimm, nfit: handle unarmed dimms, mark namespaces read-only
  pmem: flag pmem block devices as non-rotational
  libnvdimm: enable iostat
  pmem: make_request cleanups
  libnvdimm, pmem: fix up max_hw_sectors
  libnvdimm, blk: add support for blk integrity
  libnvdimm, btt: add support for blk integrity
  fs/block_dev.c: skip rw_page if bdev has integrity
  libnvdimm: Non-Volatile Devices
  tools/testing/nvdimm: libnvdimm unit test infrastructure
  libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory
  nd_btt: atomic sector updates
  libnvdimm: infrastructure for btt devices
  libnvdimm: write blk label set
  libnvdimm: write pmem label set
  libnvdimm: blk labels and namespace instantiation
  ...

1 files changed, 1870 insertions, 0 deletions

diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
new file mode 100644
index 000000000000..fef0dd80d4ad
--- /dev/null
+++ b/drivers/nvdimm/namespace_devs.c
@@ -0,0 +1,1870 @@
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/nd.h>
+#include "nd-core.h"
+#include "nd.h"
+
+static void namespace_io_release(struct device *dev)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
+
+	kfree(nsio);
+}
+
+static void namespace_pmem_release(struct device *dev)
+{
+	struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+	kfree(nspm->alt_name);
+	kfree(nspm->uuid);
+	kfree(nspm);
+}
+
+static void namespace_blk_release(struct device *dev)
+{
+	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+
+	if (nsblk->id >= 0)
+		ida_simple_remove(&nd_region->ns_ida, nsblk->id);
+	kfree(nsblk->alt_name);
+	kfree(nsblk->uuid);
+	kfree(nsblk->res);
+	kfree(nsblk);
+}
+
+static struct device_type namespace_io_device_type = {
+	.name = "nd_namespace_io",
+	.release = namespace_io_release,
+};
+
+static struct device_type namespace_pmem_device_type = {
+	.name = "nd_namespace_pmem",
+	.release = namespace_pmem_release,
+};
+
+static struct device_type namespace_blk_device_type = {
+	.name = "nd_namespace_blk",
+	.release = namespace_blk_release,
+};
+
+static bool is_namespace_pmem(struct device *dev)
+{
+	return dev ? dev->type == &namespace_pmem_device_type : false;
+}
+
+static bool is_namespace_blk(struct device *dev)
+{
+	return dev ? dev->type == &namespace_blk_device_type : false;
+}
+
+static bool is_namespace_io(struct device *dev)
+{
+	return dev ? dev->type == &namespace_io_device_type : false;
+}
+
+const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
+		char *name)
+{
+	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
+	const char *suffix = "";
+
+	if (ndns->claim && is_nd_btt(ndns->claim))
+		suffix = "s";
+
+	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev))
+		sprintf(name, "pmem%d%s", nd_region->id, suffix);
+	else if (is_namespace_blk(&ndns->dev)) {
+		struct nd_namespace_blk *nsblk;
+
+		nsblk = to_nd_namespace_blk(&ndns->dev);
+		sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id, suffix);
+	} else {
+		return NULL;
+	}
+
+	return name;
+}
+EXPORT_SYMBOL(nvdimm_namespace_disk_name);
+
+static ssize_t nstype_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+
+	return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region));
+}
+static DEVICE_ATTR_RO(nstype);
+
+static ssize_t __alt_name_store(struct device *dev, const char *buf,
+		const size_t len)
+{
+	char *input, *pos, *alt_name, **ns_altname;
+	ssize_t rc;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		ns_altname = &nspm->alt_name;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		ns_altname = &nsblk->alt_name;
+	} else
+		return -ENXIO;
+
+	if (dev->driver || to_ndns(dev)->claim)
+		return -EBUSY;
+
+	input = kmemdup(buf, len + 1, GFP_KERNEL);
+	if (!input)
+		return -ENOMEM;
+
+	input[len] = '\0';
+	pos = strim(input);
+	if (strlen(pos) + 1 > NSLABEL_NAME_LEN) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	alt_name = kzalloc(NSLABEL_NAME_LEN, GFP_KERNEL);
+	if (!alt_name) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	kfree(*ns_altname);
+	*ns_altname = alt_name;
+	sprintf(*ns_altname, "%s", pos);
+	rc = len;
+
+out:
+	kfree(input);
+	return rc;
+}
+
+static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk)
+{
+	struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
+	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	struct nd_label_id label_id;
+	resource_size_t size = 0;
+	struct resource *res;
+
+	if (!nsblk->uuid)
+		return 0;
+	nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
+	for_each_dpa_resource(ndd, res)
+		if (strcmp(res->name, label_id.id) == 0)
+			size += resource_size(res);
+	return size;
+}
+
+static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
+{
+	struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
+	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	struct nd_label_id label_id;
+	struct resource *res;
+	int count, i;
+
+	if (!nsblk->uuid || !nsblk->lbasize || !ndd)
+		return false;
+
+	count = 0;
+	nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
+	for_each_dpa_resource(ndd, res) {
+		if (strcmp(res->name, label_id.id) != 0)
+			continue;
+		/*
+		 * Resources with unacknoweldged adjustments indicate a
+		 * failure to update labels
+		 */
+		if (res->flags & DPA_RESOURCE_ADJUSTED)
+			return false;
+		count++;
+	}
+
+	/* These values match after a successful label update */
+	if (count != nsblk->num_resources)
+		return false;
+
+	for (i = 0; i < nsblk->num_resources; i++) {
+		struct resource *found = NULL;
+
+		for_each_dpa_resource(ndd, res)
+			if (res == nsblk->res[i]) {
+				found = res;
+				break;
+			}
+		/* stale resource */
+		if (!found)
+			return false;
+	}
+
+	return true;
+}
+
+resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
+{
+	resource_size_t size;
+
+	nvdimm_bus_lock(&nsblk->common.dev);
+	size = __nd_namespace_blk_validate(nsblk);
+	nvdimm_bus_unlock(&nsblk->common.dev);
+
+	return size;
+}
+EXPORT_SYMBOL(nd_namespace_blk_validate);
+
+
+static int nd_namespace_label_update(struct nd_region *nd_region,
+		struct device *dev)
+{
+	dev_WARN_ONCE(dev, dev->driver || to_ndns(dev)->claim,
+			"namespace must be idle during label update\n");
+	if (dev->driver || to_ndns(dev)->claim)
+		return 0;
+
+	/*
+	 * Only allow label writes that will result in a valid namespace
+	 * or deletion of an existing namespace.
+	 */
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+		resource_size_t size = resource_size(&nspm->nsio.res);
+
+		if (size == 0 && nspm->uuid)
+			/* delete allocation */;
+		else if (!nspm->uuid)
+			return 0;
+
+		return nd_pmem_namespace_label_update(nd_region, nspm, size);
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+		resource_size_t size = nd_namespace_blk_size(nsblk);
+
+		if (size == 0 && nsblk->uuid)
+			/* delete allocation */;
+		else if (!nsblk->uuid || !nsblk->lbasize)
+			return 0;
+
+		return nd_blk_namespace_label_update(nd_region, nsblk, size);
+	} else
+		return -ENXIO;
+}
+
+static ssize_t alt_name_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	ssize_t rc;
+
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	rc = __alt_name_store(dev, buf, len);
+	if (rc >= 0)
+		rc = nd_namespace_label_update(nd_region, dev);
+	dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc);
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return rc < 0 ? rc : len;
+}
+
+static ssize_t alt_name_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	char *ns_altname;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		ns_altname = nspm->alt_name;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		ns_altname = nsblk->alt_name;
+	} else
+		return -ENXIO;
+
+	return sprintf(buf, "%s\n", ns_altname ? ns_altname : "");
+}
+static DEVICE_ATTR_RW(alt_name);
+
+static int scan_free(struct nd_region *nd_region,
+		struct nd_mapping *nd_mapping, struct nd_label_id *label_id,
+		resource_size_t n)
+{
+	bool is_blk = strncmp(label_id->id, "blk", 3) == 0;
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	int rc = 0;
+
+	while (n) {
+		struct resource *res, *last;
+		resource_size_t new_start;
+
+		last = NULL;
+		for_each_dpa_resource(ndd, res)
+			if (strcmp(res->name, label_id->id) == 0)
+				last = res;
+		res = last;
+		if (!res)
+			return 0;
+
+		if (n >= resource_size(res)) {
+			n -= resource_size(res);
+			nd_dbg_dpa(nd_region, ndd, res, "delete %d\n", rc);
+			nvdimm_free_dpa(ndd, res);
+			/* retry with last resource deleted */
+			continue;
+		}
+
+		/*
+		 * Keep BLK allocations relegated to high DPA as much as
+		 * possible
+		 */
+		if (is_blk)
+			new_start = res->start + n;
+		else
+			new_start = res->start;
+
+		rc = adjust_resource(res, new_start, resource_size(res) - n);
+		if (rc == 0)
+			res->flags |= DPA_RESOURCE_ADJUSTED;
+		nd_dbg_dpa(nd_region, ndd, res, "shrink %d\n", rc);
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * shrink_dpa_allocation - for each dimm in region free n bytes for label_id
+ * @nd_region: the set of dimms to reclaim @n bytes from
+ * @label_id: unique identifier for the namespace consuming this dpa range
+ * @n: number of bytes per-dimm to release
+ *
+ * Assumes resources are ordered.  Starting from the end try to
+ * adjust_resource() the allocation to @n, but if @n is larger than the
+ * allocation delete it and find the 'new' last allocation in the label
+ * set.
+ */
+static int shrink_dpa_allocation(struct nd_region *nd_region,
+		struct nd_label_id *label_id, resource_size_t n)
+{
+	int i;
+
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		int rc;
+
+		rc = scan_free(nd_region, nd_mapping, label_id, n);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static resource_size_t init_dpa_allocation(struct nd_label_id *label_id,
+		struct nd_region *nd_region, struct nd_mapping *nd_mapping,
+		resource_size_t n)
+{
+	bool is_blk = strncmp(label_id->id, "blk", 3) == 0;
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	resource_size_t first_dpa;
+	struct resource *res;
+	int rc = 0;
+
+	/* allocate blk from highest dpa first */
+	if (is_blk)
+		first_dpa = nd_mapping->start + nd_mapping->size - n;
+	else
+		first_dpa = nd_mapping->start;
+
+	/* first resource allocation for this label-id or dimm */
+	res = nvdimm_allocate_dpa(ndd, label_id, first_dpa, n);
+	if (!res)
+		rc = -EBUSY;
+
+	nd_dbg_dpa(nd_region, ndd, res, "init %d\n", rc);
+	return rc ? n : 0;
+}
+
+static bool space_valid(bool is_pmem, bool is_reserve,
+		struct nd_label_id *label_id, struct resource *res)
+{
+	/*
+	 * For BLK-space any space is valid, for PMEM-space, it must be
+	 * contiguous with an existing allocation unless we are
+	 * reserving pmem.
+	 */
+	if (is_reserve || !is_pmem)
+		return true;
+	if (!res || strcmp(res->name, label_id->id) == 0)
+		return true;
+	return false;
+}
+
+enum alloc_loc {
+	ALLOC_ERR = 0, ALLOC_BEFORE, ALLOC_MID, ALLOC_AFTER,
+};
+
+static resource_size_t scan_allocate(struct nd_region *nd_region,
+		struct nd_mapping *nd_mapping, struct nd_label_id *label_id,
+		resource_size_t n)
+{
+	resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1;
+	bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
+	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	const resource_size_t to_allocate = n;
+	struct resource *res;
+	int first;
+
+ retry:
+	first = 0;
+	for_each_dpa_resource(ndd, res) {
+		resource_size_t allocate, available = 0, free_start, free_end;
+		struct resource *next = res->sibling, *new_res = NULL;
+		enum alloc_loc loc = ALLOC_ERR;
+		const char *action;
+		int rc = 0;
+
+		/* ignore resources outside this nd_mapping */
+		if (res->start > mapping_end)
+			continue;
+		if (res->end < nd_mapping->start)
+			continue;
+
+		/* space at the beginning of the mapping */
+		if (!first++ && res->start > nd_mapping->start) {
+			free_start = nd_mapping->start;
+			available = res->start - free_start;
+			if (space_valid(is_pmem, is_reserve, label_id, NULL))
+				loc = ALLOC_BEFORE;
+		}
+
+		/* space between allocations */
+		if (!loc && next) {
+			free_start = res->start + resource_size(res);
+			free_end = min(mapping_end, next->start - 1);
+			if (space_valid(is_pmem, is_reserve, label_id, res)
+					&& free_start < free_end) {
+				available = free_end + 1 - free_start;
+				loc = ALLOC_MID;
+			}
+		}
+
+		/* space at the end of the mapping */
+		if (!loc && !next) {
+			free_start = res->start + resource_size(res);
+			free_end = mapping_end;
+			if (space_valid(is_pmem, is_reserve, label_id, res)
+					&& free_start < free_end) {
+				available = free_end + 1 - free_start;
+				loc = ALLOC_AFTER;
+			}
+		}
+
+		if (!loc || !available)
+			continue;
+		allocate = min(available, n);
+		switch (loc) {
+		case ALLOC_BEFORE:
+			if (strcmp(res->name, label_id->id) == 0) {
+				/* adjust current resource up */
+				if (is_pmem && !is_reserve)
+					return n;
+				rc = adjust_resource(res, res->start - allocate,
+						resource_size(res) + allocate);
+				action = "cur grow up";
+			} else
+				action = "allocate";
+			break;
+		case ALLOC_MID:
+			if (strcmp(next->name, label_id->id) == 0) {
+				/* adjust next resource up */
+				if (is_pmem && !is_reserve)
+					return n;
+				rc = adjust_resource(next, next->start
+						- allocate, resource_size(next)
+						+ allocate);
+				new_res = next;
+				action = "next grow up";
+			} else if (strcmp(res->name, label_id->id) == 0) {
+				action = "grow down";
+			} else
+				action = "allocate";
+			break;
+		case ALLOC_AFTER:
+			if (strcmp(res->name, label_id->id) == 0)
+				action = "grow down";
+			else
+				action = "allocate";
+			break;
+		default:
+			return n;
+		}
+
+		if (strcmp(action, "allocate") == 0) {
+			/* BLK allocate bottom up */
+			if (!is_pmem)
+				free_start += available - allocate;
+			else if (!is_reserve && free_start != nd_mapping->start)
+				return n;
+
+			new_res = nvdimm_allocate_dpa(ndd, label_id,
+					free_start, allocate);
+			if (!new_res)
+				rc = -EBUSY;
+		} else if (strcmp(action, "grow down") == 0) {
+			/* adjust current resource down */
+			rc = adjust_resource(res, res->start, resource_size(res)
+					+ allocate);
+			if (rc == 0)
+				res->flags |= DPA_RESOURCE_ADJUSTED;
+		}
+
+		if (!new_res)
+			new_res = res;
+
+		nd_dbg_dpa(nd_region, ndd, new_res, "%s(%d) %d\n",
+				action, loc, rc);
+
+		if (rc)
+			return n;
+
+		n -= allocate;
+		if (n) {
+			/*
+			 * Retry scan with newly inserted resources.
+			 * For example, if we did an ALLOC_BEFORE
+			 * insertion there may also have been space
+			 * available for an ALLOC_AFTER insertion, so we
+			 * need to check this same resource again
+			 */
+			goto retry;
+		} else
+			return 0;
+	}
+
+	/*
+	 * If we allocated nothing in the BLK case it may be because we are in
+	 * an initial "pmem-reserve pass".  Only do an initial BLK allocation
+	 * when none of the DPA space is reserved.
+	 */
+	if ((is_pmem || !ndd->dpa.child) && n == to_allocate)
+		return init_dpa_allocation(label_id, nd_region, nd_mapping, n);
+	return n;
+}
+
+static int merge_dpa(struct nd_region *nd_region,
+		struct nd_mapping *nd_mapping, struct nd_label_id *label_id)
+{
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	struct resource *res;
+
+	if (strncmp("pmem", label_id->id, 4) == 0)
+		return 0;
+ retry:
+	for_each_dpa_resource(ndd, res) {
+		int rc;
+		struct resource *next = res->sibling;
+		resource_size_t end = res->start + resource_size(res);
+
+		if (!next || strcmp(res->name, label_id->id) != 0
+				|| strcmp(next->name, label_id->id) != 0
+				|| end != next->start)
+			continue;
+		end += resource_size(next);
+		nvdimm_free_dpa(ndd, next);
+		rc = adjust_resource(res, res->start, end - res->start);
+		nd_dbg_dpa(nd_region, ndd, res, "merge %d\n", rc);
+		if (rc)
+			return rc;
+		res->flags |= DPA_RESOURCE_ADJUSTED;
+		goto retry;
+	}
+
+	return 0;
+}
+
+static int __reserve_free_pmem(struct device *dev, void *data)
+{
+	struct nvdimm *nvdimm = data;
+	struct nd_region *nd_region;
+	struct nd_label_id label_id;
+	int i;
+
+	if (!is_nd_pmem(dev))
+		return 0;
+
+	nd_region = to_nd_region(dev);
+	if (nd_region->ndr_mappings == 0)
+		return 0;
+
+	memset(&label_id, 0, sizeof(label_id));
+	strcat(label_id.id, "pmem-reserve");
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		resource_size_t n, rem = 0;
+
+		if (nd_mapping->nvdimm != nvdimm)
+			continue;
+
+		n = nd_pmem_available_dpa(nd_region, nd_mapping, &rem);
+		if (n == 0)
+			return 0;
+		rem = scan_allocate(nd_region, nd_mapping, &label_id, n);
+		dev_WARN_ONCE(&nd_region->dev, rem,
+				"pmem reserve underrun: %#llx of %#llx bytes\n",
+				(unsigned long long) n - rem,
+				(unsigned long long) n);
+		return rem ? -ENXIO : 0;
+	}
+
+	return 0;
+}
+
+static void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
+		struct nd_mapping *nd_mapping)
+{
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	struct resource *res, *_res;
+
+	for_each_dpa_resource_safe(ndd, res, _res)
+		if (strcmp(res->name, "pmem-reserve") == 0)
+			nvdimm_free_dpa(ndd, res);
+}
+
+static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus,
+		struct nd_mapping *nd_mapping)
+{
+	struct nvdimm *nvdimm = nd_mapping->nvdimm;
+	int rc;
+
+	rc = device_for_each_child(&nvdimm_bus->dev, nvdimm,
+			__reserve_free_pmem);
+	if (rc)
+		release_free_pmem(nvdimm_bus, nd_mapping);
+	return rc;
+}
+
+/**
+ * grow_dpa_allocation - for each dimm allocate n bytes for @label_id
+ * @nd_region: the set of dimms to allocate @n more bytes from
+ * @label_id: unique identifier for the namespace consuming this dpa range
+ * @n: number of bytes per-dimm to add to the existing allocation
+ *
+ * Assumes resources are ordered.  For BLK regions, first consume
+ * BLK-only available DPA free space, then consume PMEM-aliased DPA
+ * space starting at the highest DPA.  For PMEM regions start
+ * allocations from the start of an interleave set and end at the first
+ * BLK allocation or the end of the interleave set, whichever comes
+ * first.
+ */
+static int grow_dpa_allocation(struct nd_region *nd_region,
+		struct nd_label_id *label_id, resource_size_t n)
+{
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
+	int i;
+
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		resource_size_t rem = n;
+		int rc, j;
+
+		/*
+		 * In the BLK case try once with all unallocated PMEM
+		 * reserved, and once without
+		 */
+		for (j = is_pmem; j < 2; j++) {
+			bool blk_only = j == 0;
+
+			if (blk_only) {
+				rc = reserve_free_pmem(nvdimm_bus, nd_mapping);
+				if (rc)
+					return rc;
+			}
+			rem = scan_allocate(nd_region, nd_mapping,
+					label_id, rem);
+			if (blk_only)
+				release_free_pmem(nvdimm_bus, nd_mapping);
+
+			/* try again and allow encroachments into PMEM */
+			if (rem == 0)
+				break;
+		}
+
+		dev_WARN_ONCE(&nd_region->dev, rem,
+				"allocation underrun: %#llx of %#llx bytes\n",
+				(unsigned long long) n - rem,
+				(unsigned long long) n);
+		if (rem)
+			return -ENXIO;
+
+		rc = merge_dpa(nd_region, nd_mapping, label_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static void nd_namespace_pmem_set_size(struct nd_region *nd_region,
+		struct nd_namespace_pmem *nspm, resource_size_t size)
+{
+	struct resource *res = &nspm->nsio.res;
+
+	res->start = nd_region->ndr_start;
+	res->end = nd_region->ndr_start + size - 1;
+}
+
+static ssize_t __size_store(struct device *dev, unsigned long long val)
+{
+	resource_size_t allocated = 0, available = 0;
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_mapping *nd_mapping;
+	struct nvdimm_drvdata *ndd;
+	struct nd_label_id label_id;
+	u32 flags = 0, remainder;
+	u8 *uuid = NULL;
+	int rc, i;
+
+	if (dev->driver || to_ndns(dev)->claim)
+		return -EBUSY;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		uuid = nspm->uuid;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		uuid = nsblk->uuid;
+		flags = NSLABEL_FLAG_LOCAL;
+	}
+
+	/*
+	 * We need a uuid for the allocation-label and dimm(s) on which
+	 * to store the label.
+	 */
+	if (!uuid || nd_region->ndr_mappings == 0)
+		return -ENXIO;
+
+	div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder);
+	if (remainder) {
+		dev_dbg(dev, "%llu is not %dK aligned\n", val,
+				(SZ_4K * nd_region->ndr_mappings) / SZ_1K);
+		return -EINVAL;
+	}
+
+	nd_label_gen_id(&label_id, uuid, flags);
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		nd_mapping = &nd_region->mapping[i];
+		ndd = to_ndd(nd_mapping);
+
+		/*
+		 * All dimms in an interleave set, or the base dimm for a blk
+		 * region, need to be enabled for the size to be changed.
+		 */
+		if (!ndd)
+			return -ENXIO;
+
+		allocated += nvdimm_allocated_dpa(ndd, &label_id);
+	}
+	available = nd_region_available_dpa(nd_region);
+
+	if (val > available + allocated)
+		return -ENOSPC;
+
+	if (val == allocated)
+		return 0;
+
+	val = div_u64(val, nd_region->ndr_mappings);
+	allocated = div_u64(allocated, nd_region->ndr_mappings);
+	if (val < allocated)
+		rc = shrink_dpa_allocation(nd_region, &label_id,
+				allocated - val);
+	else
+		rc = grow_dpa_allocation(nd_region, &label_id, val - allocated);
+
+	if (rc)
+		return rc;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		nd_namespace_pmem_set_size(nd_region, nspm,
+				val * nd_region->ndr_mappings);
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		/*
+		 * Try to delete the namespace if we deleted all of its
+		 * allocation, this is not the seed device for the
+		 * region, and it is not actively claimed by a btt
+		 * instance.
+		 */
+		if (val == 0 && nd_region->ns_seed != dev
+				&& !nsblk->common.claim)
+			nd_device_unregister(dev, ND_ASYNC);
+	}
+
+	return rc;
+}
+
+static ssize_t size_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	unsigned long long val;
+	u8 **uuid = NULL;
+	int rc;
+
+	rc = kstrtoull(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	rc = __size_store(dev, val);
+	if (rc >= 0)
+		rc = nd_namespace_label_update(nd_region, dev);
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		uuid = &nspm->uuid;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		uuid = &nsblk->uuid;
+	}
+
+	if (rc == 0 && val == 0 && uuid) {
+		/* setting size zero == 'delete namespace' */
+		kfree(*uuid);
+		*uuid = NULL;
+	}
+
+	dev_dbg(dev, "%s: %llx %s (%d)\n", __func__, val, rc < 0
+			? "fail" : "success", rc);
+
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return rc < 0 ? rc : len;
+}
+
+resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
+{
+	struct device *dev = &ndns->dev;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		return resource_size(&nspm->nsio.res);
+	} else if (is_namespace_blk(dev)) {
+		return nd_namespace_blk_size(to_nd_namespace_blk(dev));
+	} else if (is_namespace_io(dev)) {
+		struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
+
+		return resource_size(&nsio->res);
+	} else
+		WARN_ONCE(1, "unknown namespace type\n");
+	return 0;
+}
+
+resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
+{
+	resource_size_t size;
+
+	nvdimm_bus_lock(&ndns->dev);
+	size = __nvdimm_namespace_capacity(ndns);
+	nvdimm_bus_unlock(&ndns->dev);
+
+	return size;
+}
+EXPORT_SYMBOL(nvdimm_namespace_capacity);
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%llu\n", (unsigned long long)
+			nvdimm_namespace_capacity(to_ndns(dev)));
+}
+static DEVICE_ATTR(size, S_IRUGO, size_show, size_store);
+
+static ssize_t uuid_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	u8 *uuid;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		uuid = nspm->uuid;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		uuid = nsblk->uuid;
+	} else
+		return -ENXIO;
+
+	if (uuid)
+		return sprintf(buf, "%pUb\n", uuid);
+	return sprintf(buf, "\n");
+}
+
+/**
+ * namespace_update_uuid - check for a unique uuid and whether we're "renaming"
+ * @nd_region: parent region so we can updates all dimms in the set
+ * @dev: namespace type for generating label_id
+ * @new_uuid: incoming uuid
+ * @old_uuid: reference to the uuid storage location in the namespace object
+ */
+static int namespace_update_uuid(struct nd_region *nd_region,
+		struct device *dev, u8 *new_uuid, u8 **old_uuid)
+{
+	u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0;
+	struct nd_label_id old_label_id;
+	struct nd_label_id new_label_id;
+	int i;
+
+	if (!nd_is_uuid_unique(dev, new_uuid))
+		return -EINVAL;
+
+	if (*old_uuid == NULL)
+		goto out;
+
+	/*
+	 * If we've already written a label with this uuid, then it's
+	 * too late to rename because we can't reliably update the uuid
+	 * without losing the old namespace.  Userspace must delete this
+	 * namespace to abandon the old uuid.
+	 */
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+
+		/*
+		 * This check by itself is sufficient because old_uuid
+		 * would be NULL above if this uuid did not exist in the
+		 * currently written set.
+		 *
+		 * FIXME: can we delete uuid with zero dpa allocated?
+		 */
+		if (nd_mapping->labels)
+			return -EBUSY;
+	}
+
+	nd_label_gen_id(&old_label_id, *old_uuid, flags);
+	nd_label_gen_id(&new_label_id, new_uuid, flags);
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+		struct resource *res;
+
+		for_each_dpa_resource(ndd, res)
+			if (strcmp(res->name, old_label_id.id) == 0)
+				sprintf((void *) res->name, "%s",
+						new_label_id.id);
+	}
+	kfree(*old_uuid);
+ out:
+	*old_uuid = new_uuid;
+	return 0;
+}
+
+static ssize_t uuid_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_region *nd_region = to_nd_region(dev->parent);
+	u8 *uuid = NULL;
+	ssize_t rc = 0;
+	u8 **ns_uuid;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		ns_uuid = &nspm->uuid;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		ns_uuid = &nsblk->uuid;
+	} else
+		return -ENXIO;
+
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	if (to_ndns(dev)->claim)
+		rc = -EBUSY;
+	if (rc >= 0)
+		rc = nd_uuid_store(dev, &uuid, buf, len);
+	if (rc >= 0)
+		rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid);
+	if (rc >= 0)
+		rc = nd_namespace_label_update(nd_region, dev);
+	else
+		kfree(uuid);
+	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
+			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return rc < 0 ? rc : len;
+}
+static DEVICE_ATTR_RW(uuid);
+
+static ssize_t resource_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct resource *res;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		res = &nspm->nsio.res;
+	} else if (is_namespace_io(dev)) {
+		struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
+
+		res = &nsio->res;
+	} else
+		return -ENXIO;
+
+	/* no address to convey if the namespace has no allocation */
+	if (resource_size(res) == 0)
+		return -ENXIO;
+	return sprintf(buf, "%#llx\n", (unsigned l