Merge tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm and dax updates from Dan Williams:
 "There were multiple touches outside of drivers/nvdimm/ this round to
  add cross arch compatibility to the devm_memremap_pages() interface,
  enhance numa information for persistent memory ranges, and add a
  zero_page_range() dax operation.

  This cycle I switched from the patchwork api to Konstantin's b4 script
  for collecting tags (from x86, PowerPC, filesystem, and device-mapper
  folks), and everything looks to have gone ok there. This has all
  appeared in -next with no reported issues.

  Summary:

   - Add support for region alignment configuration and enforcement to
     fix compatibility across architectures and PowerPC page size
     configurations.

   - Introduce 'zero_page_range' as a dax operation. This facilitates
     filesystem-dax operation without a block-device.

   - Introduce phys_to_target_node() to facilitate drivers that want to
     know resulting numa node if a given reserved address range was
     onlined.

   - Advertise a persistence-domain for of_pmem and papr_scm. The
     persistence domain indicates where cpu-store cycles need to reach
     in the platform-memory subsystem before the platform will consider
     them power-fail protected.

   - Promote numa_map_to_online_node() to a cross-kernel generic
     facility.

   - Save x86 numa information to allow for node-id lookups for reserved
     memory ranges, deploy that capability for the e820-pmem driver.

   - Pick up some miscellaneous minor fixes, that missed v5.6-final,
     including a some smatch reports in the ioctl path and some unit
     test compilation fixups.

   - Fixup some flexible-array declarations"

* tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (29 commits)
  dax: Move mandatory ->zero_page_range() check in alloc_dax()
  dax,iomap: Add helper dax_iomap_zero() to zero a range
  dax: Use new dax zero page method for zeroing a page
  dm,dax: Add dax zero_page_range operation
  s390,dcssblk,dax: Add dax zero_page_range operation to dcssblk driver
  dax, pmem: Add a dax operation zero_page_range
  pmem: Add functions for reading/writing page to/from pmem
  libnvdimm: Update persistence domain value for of_pmem and papr_scm device
  tools/test/nvdimm: Fix out of tree build
  libnvdimm/region: Fix build error
  libnvdimm/region: Replace zero-length array with flexible-array member
  libnvdimm/label: Replace zero-length array with flexible-array member
  ACPI: NFIT: Replace zero-length array with flexible-array member
  libnvdimm/region: Introduce an 'align' attribute
  libnvdimm/region: Introduce NDD_LABELING
  libnvdimm/namespace: Enforce memremap_compat_align()
  libnvdimm/pfn: Prevent raw mode fallback if pfn-infoblock valid
  libnvdimm: Out of bounds read in __nd_ioctl()
  acpi/nfit: improve bounds checking for 'func'
  mm/memremap_pages: Introduce memremap_compat_align()
  ...

12 files changed, 342 insertions, 103 deletions

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index a8b515968569..09087c38fabd 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -1042,8 +1042,10 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 			return -EFAULT;
 	}
 
-	if (!desc || (desc->out_num + desc->in_num == 0) ||
-			!test_bit(cmd, &cmd_mask))
+	if (!desc ||
+	    (desc->out_num + desc->in_num == 0) ||
+	    cmd > ND_CMD_CALL ||
+	    !test_bit(cmd, &cmd_mask))
 		return -ENOTTY;
 
 	/* fail write commands (when read-only) */
diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c
index 64776ed15bb3..7d4ddc4d9322 100644
--- a/drivers/nvdimm/dimm.c
+++ b/drivers/nvdimm/dimm.c
@@ -99,7 +99,7 @@ static int nvdimm_probe(struct device *dev)
 	if (ndd->ns_current >= 0) {
 		rc = nd_label_reserve_dpa(ndd);
 		if (rc == 0)
-			nvdimm_set_aliasing(dev);
+			nvdimm_set_labeling(dev);
 	}
 	nvdimm_bus_unlock(dev);
 
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index 94ea6dba6b4f..b7b77e8d9027 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -32,7 +32,7 @@ int nvdimm_check_config_data(struct device *dev)
 
 	if (!nvdimm->cmd_mask ||
 	    !test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask)) {
-		if (test_bit(NDD_ALIASING, &nvdimm->flags))
+		if (test_bit(NDD_LABELING, &nvdimm->flags))
 			return -ENXIO;
 		else
 			return -ENOTTY;
@@ -173,11 +173,11 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 	return rc;
 }
 
-void nvdimm_set_aliasing(struct device *dev)
+void nvdimm_set_labeling(struct device *dev)
 {
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 
-	set_bit(NDD_ALIASING, &nvdimm->flags);
+	set_bit(NDD_LABELING, &nvdimm->flags);
 }
 
 void nvdimm_set_locked(struct device *dev)
@@ -312,8 +312,9 @@ static ssize_t flags_show(struct device *dev,
 {
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 
-	return sprintf(buf, "%s%s\n",
+	return sprintf(buf, "%s%s%s\n",
 			test_bit(NDD_ALIASING, &nvdimm->flags) ? "alias " : "",
+			test_bit(NDD_LABELING, &nvdimm->flags) ? "label " : "",
 			test_bit(NDD_LOCKED, &nvdimm->flags) ? "lock " : "");
 }
 static DEVICE_ATTR_RO(flags);
@@ -562,6 +563,21 @@ int nvdimm_security_freeze(struct nvdimm *nvdimm)
 	return rc;
 }
 
+static unsigned long dpa_align(struct nd_region *nd_region)
+{
+	struct device *dev = &nd_region->dev;
+
+	if (dev_WARN_ONCE(dev, !is_nvdimm_bus_locked(dev),
+				"bus lock required for capacity provision\n"))
+		return 0;
+	if (dev_WARN_ONCE(dev, !nd_region->ndr_mappings || nd_region->align
+				% nd_region->ndr_mappings,
+				"invalid region align %#lx mappings: %d\n",
+				nd_region->align, nd_region->ndr_mappings))
+		return 0;
+	return nd_region->align / nd_region->ndr_mappings;
+}
+
 int alias_dpa_busy(struct device *dev, void *data)
 {
 	resource_size_t map_end, blk_start, new;
@@ -570,6 +586,7 @@ int alias_dpa_busy(struct device *dev, void *data)
 	struct nd_region *nd_region;
 	struct nvdimm_drvdata *ndd;
 	struct resource *res;
+	unsigned long align;
 	int i;
 
 	if (!is_memory(dev))
@@ -607,13 +624,21 @@ int alias_dpa_busy(struct device *dev, void *data)
 	 * Find the free dpa from the end of the last pmem allocation to
 	 * the end of the interleave-set mapping.
 	 */
+	align = dpa_align(nd_region);
+	if (!align)
+		return 0;
+
 	for_each_dpa_resource(ndd, res) {
+		resource_size_t start, end;
+
 		if (strncmp(res->name, "pmem", 4) != 0)
 			continue;
-		if ((res->start >= blk_start && res->start < map_end)
-				|| (res->end >= blk_start
-					&& res->end <= map_end)) {
-			new = max(blk_start, min(map_end + 1, res->end + 1));
+
+		start = ALIGN_DOWN(res->start, align);
+		end = ALIGN(res->end + 1, align) - 1;
+		if ((start >= blk_start && start < map_end)
+				|| (end >= blk_start && end <= map_end)) {
+			new = max(blk_start, min(map_end, end) + 1);
 			if (new != blk_start) {
 				blk_start = new;
 				goto retry;
@@ -653,6 +678,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 		.res = NULL,
 	};
 	struct resource *res;
+	unsigned long align;
 
 	if (!ndd)
 		return 0;
@@ -660,10 +686,20 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 	device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy);
 
 	/* now account for busy blk allocations in unaliased dpa */
+	align = dpa_align(nd_region);
+	if (!align)
+		return 0;
 	for_each_dpa_resource(ndd, res) {
+		resource_size_t start, end, size;
+
 		if (strncmp(res->name, "blk", 3) != 0)
 			continue;
-		info.available -= resource_size(res);
+		start = ALIGN_DOWN(res->start, align);
+		end = ALIGN(res->end + 1, align) - 1;
+		size = end - start + 1;
+		if (size >= info.available)
+			return 0;
+		info.available -= size;
 	}
 
 	return info.available;
@@ -682,19 +718,31 @@ resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
 	struct nvdimm_bus *nvdimm_bus;
 	resource_size_t max = 0;
 	struct resource *res;
+	unsigned long align;
 
 	/* if a dimm is disabled the available capacity is zero */
 	if (!ndd)
 		return 0;
 
+	align = dpa_align(nd_region);
+	if (!align)
+		return 0;
+
 	nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
 	if (__reserve_free_pmem(&nd_region->dev, nd_mapping->nvdimm))
 		return 0;
 	for_each_dpa_resource(ndd, res) {
+		resource_size_t start, end;
+
 		if (strcmp(res->name, "pmem-reserve") != 0)
 			continue;
-		if (resource_size(res) > max)
-			max = resource_size(res);
+		/* trim free space relative to current alignment setting */
+		start = ALIGN(res->start, align);
+		end = ALIGN_DOWN(res->end + 1, align) - 1;
+		if (end < start)
+			continue;
+		if (end - start + 1 > max)
+			max = end - start + 1;
 	}
 	release_free_pmem(nvdimm_bus, nd_mapping);
 	return max;
@@ -722,24 +770,33 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
 	struct resource *res;
 	const char *reason;
+	unsigned long align;
 
 	if (!ndd)
 		return 0;
 
+	align = dpa_align(nd_region);
+	if (!align)
+		return 0;
+
 	map_start = nd_mapping->start;
 	map_end = map_start + nd_mapping->size - 1;
 	blk_start = max(map_start, map_end + 1 - *overlap);
 	for_each_dpa_resource(ndd, res) {
-		if (res->start >= map_start && res->start < map_end) {
+		resource_size_t start, end;
+
+		start = ALIGN_DOWN(res->start, align);
+		end = ALIGN(res->end + 1, align) - 1;
+		if (start >= map_start && start < map_end) {
 			if (strncmp(res->name, "blk", 3) == 0)
 				blk_start = min(blk_start,
-						max(map_start, res->start));
-			else if (res->end > map_end) {
+						max(map_start, start));
+			else if (end > map_end) {
 				reason = "misaligned to iset";
 				goto err;
 			} else
-				busy += resource_size(res);
-		} else if (res->end >= map_start && res->end <= map_end) {
+				busy += end - start + 1;
+		} else if (end >= map_start && end <= map_end) {
 			if (strncmp(res->name, "blk", 3) == 0) {
 				/*
 				 * If a BLK allocation overlaps the start of
@@ -748,8 +805,8 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 				 */
 				blk_start = map_start;
 			} else
-				busy += resource_size(res);
-		} else if (map_start > res->start && map_start < res->end) {
+				busy += end - start + 1;
+		} else if (map_start > start && map_start < end) {
 			/* total eclipse of the mapping */
 			busy += nd_mapping->size;
 			blk_start = map_start;
@@ -759,7 +816,7 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 	*overlap = map_end + 1 - blk_start;
 	available = blk_start - map_start;
 	if (busy < available)
-		return available - busy;
+		return ALIGN_DOWN(available - busy, align);
 	return 0;
 
  err:
diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
index e02f60ad6c99..4cd18be9d0e9 100644
--- a/drivers/nvdimm/e820.c
+++ b/drivers/nvdimm/e820.c
@@ -7,6 +7,7 @@
 #include <linux/memory_hotplug.h>
 #include <linux/libnvdimm.h>
 #include <linux/module.h>
+#include <linux/numa.h>
 
 static int e820_pmem_remove(struct platform_device *pdev)
 {
@@ -16,27 +17,16 @@ static int e820_pmem_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int e820_range_to_nid(resource_size_t addr)
-{
-	return memory_add_physaddr_to_nid(addr);
-}
-#else
-static int e820_range_to_nid(resource_size_t addr)
-{
-	return NUMA_NO_NODE;
-}
-#endif
-
 static int e820_register_one(struct resource *res, void *data)
 {
 	struct nd_region_desc ndr_desc;
 	struct nvdimm_bus *nvdimm_bus = data;
+	int nid = phys_to_target_node(res->start);
 
 	memset(&ndr_desc, 0, sizeof(ndr_desc));
 	ndr_desc.res = res;
-	ndr_desc.numa_node = e820_range_to_nid(res->start);
-	ndr_desc.target_node = ndr_desc.numa_node;
+	ndr_desc.numa_node = numa_map_to_online_node(nid);
+	ndr_desc.target_node = nid;
 	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
 	if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
 		return -ENXIO;
diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h
index 4c7b775c2811..956b6d1bd8cc 100644
--- a/drivers/nvdimm/label.h
+++ b/drivers/nvdimm/label.h
@@ -62,7 +62,7 @@ struct nd_namespace_index {
 	__le16 major;
 	__le16 minor;
 	__le64 checksum;
-	u8 free[0];
+	u8 free[];
 };
 
 /**
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 032dc61725ff..ae155e860fdc 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -10,6 +10,7 @@
 #include <linux/nd.h>
 #include "nd-core.h"
 #include "pmem.h"
+#include "pfn.h"
 #include "nd.h"
 
 static void namespace_io_release(struct device *dev)
@@ -541,6 +542,11 @@ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd,
 {
 	bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
 	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
+	unsigned long align;
+
+	align = nd_region->align / nd_region->ndr_mappings;
+	valid->start = ALIGN(valid->start, align);
+	valid->end = ALIGN_DOWN(valid->end + 1, align) - 1;
 
 	if (valid->start >= valid->end)
 		goto invalid;
@@ -980,10 +986,10 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 		return -ENXIO;
 	}
 
-	div_u64_rem(val, PAGE_SIZE * nd_region->ndr_mappings, &remainder);
+	div_u64_rem(val, nd_region->align, &remainder);
 	if (remainder) {
 		dev_dbg(dev, "%llu is not %ldK aligned\n", val,
-				(PAGE_SIZE * nd_region->ndr_mappings) / SZ_1K);
+				nd_region->align / SZ_1K);
 		return -EINVAL;
 	}
 
@@ -1739,6 +1745,22 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 		return ERR_PTR(-ENODEV);
 	}
 
+	/*
+	 * Note, alignment validation for fsdax and devdax mode
+	 * namespaces happens in nd_pfn_validate() where infoblock
+	 * padding parameters can be applied.
+	 */
+	if (pmem_should_map_pages(dev)) {
+		struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+		struct resource *res = &nsio->res;
+
+		if (!IS_ALIGNED(res->start | (res->end + 1),
+					memremap_compat_align())) {
+			dev_err(&ndns->dev, "%pr misaligned, unable to map\n", res);
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+	}
+
 	if (is_namespace_pmem(&ndns->dev)) {
 		struct nd_namespace_pmem *nspm;
 
@@ -2521,7 +2543,7 @@ static int init_active_labels(struct nd_region *nd_region)
 		if (!ndd) {
 			if (test_bit(NDD_LOCKED, &nvdimm->flags))
 				/* fail, label data may be unreadable */;
-			else if (test_bit(NDD_ALIASING, &nvdimm->flags))
+			else if (test_bit(NDD_LABELING, &nvdimm->flags))
 				/* fail, labels needed to disambiguate dpa */;
 			else
 				return 0;
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index c9f6a5b5253a..85dbb2a322b9 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -39,7 +39,7 @@ struct nd_region_data {
 	int ns_count;
 	int ns_active;
 	unsigned int hints_shift;
-	void __iomem *flush_wpq[0];
+	void __iomem *flush_wpq[];
 };
 
 static inline void __iomem *ndrd_get_flush_wpq(struct nd_region_data *ndrd,
@@ -146,6 +146,7 @@ struct nd_region {
 	struct device *btt_seed;
 	struct device *pfn_seed;
 	struct device *dax_seed;
+	unsigned long align;
 	u16 ndr_mappings;
 	u64 ndr_size;
 	u64 ndr_start;
@@ -156,7 +157,7 @@ struct nd_region {
 	struct nd_interleave_set *nd_set;
 	struct nd_percpu_lane __percpu *lane;
 	int (*flush)(struct nd_region *nd_region, struct bio *bio);
-	struct nd_mapping mapping[0];
+	struct nd_mapping mapping[];
 };
 
 struct nd_blk_region {
@@ -252,7 +253,7 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
 		void *buf, size_t len);
 long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 		unsigned int len);
-void nvdimm_set_aliasing(struct device *dev);
+void nvdimm_set_labeling(struct device *dev);
 void nvdimm_set_locked(struct device *dev);
 void nvdimm_clear_locked(struct device *dev);
 int nvdimm_security_setup_events(struct device *dev);
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 8224d1431ea9..6826a274a1f1 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -62,8 +62,10 @@ static int of_pmem_region_probe(struct platform_device *pdev)
 
 		if (is_volatile)
 			region = nvdimm_volatile_region_create(bus, &ndr_desc);
-		else
+		else {
+			set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags);
 			region = nvdimm_pmem_region_create(bus, &ndr_desc);
+		}
 
 		if (!region)
 			dev_warn(&pdev->dev, "Unable to register region %pR from %pOF\n",
diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index acb19517f678..37cb1b8a2a39 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -24,6 +24,18 @@ struct nd_pfn_sb {
 	__le64 npfns;
 	__le32 mode;
 	/* minor-version-1 additions for section alignment */
+	/**
+	 * @start_pad: Deprecated attribute to pad start-misaligned namespaces
+	 *
+	 * start_pad is deprecated because the original definition did
+	 * not comprehend that dataoff is relative to the base address
+	 * of the namespace not the start_pad adjusted base. The result
+	 * is that the dax path is broken, but the block-I/O path is
+	 * not. The kernel will no longer create namespaces using start
+	 * padding, but it still supports block-I/O for legacy
+	 * configurations mainly to allow a backup, reconfigure the
+	 * namespace, and restore flow to repair dax operation.
+	 */
 	__le32 start_pad;
 	__le32 end_trunc;
 	/* minor-version-2 record the base alignment of the mapping */
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index b94f7a7e94b8..34db557dbad1 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -446,6 +446,7 @@ static bool nd_supported_alignment(unsigned long align)
 int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	u64 checksum, offset;
+	struct resource *res;
 	enum nd_pfn_mode mode;
 	struct nd_namespace_io *nsio;
 	unsigned long align, start_pad;
@@ -561,14 +562,14 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 			dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
 					nd_pfn->align, align, nd_pfn->mode,
 					mode);
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		}
 	}
 
 	if (align > nvdimm_namespace_capacity(ndns)) {
 		dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
 				align, nvdimm_namespace_capacity(ndns));
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	/*
@@ -578,18 +579,31 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 	 * established.
 	 */
 	nsio = to_nd_namespace_io(&ndns->dev);
-	if (offset >= resource_size(&nsio->res)) {
+	res = &nsio->res;
+	if (offset >= resource_size(res)) {
 		dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
 				dev_name(&ndns->dev));
-		return -EBUSY;
+		return -EOPNOTSUPP;
 	}
 
-	if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align))
+	if ((align && !IS_ALIGNED(res->start + offset + start_pad, align))
 			|| !IS_ALIGNED(offset, PAGE_SIZE)) {
 		dev_err(&nd_pfn->dev,
 				"bad offset: %#llx dax disabled align: %#lx\n",
 				offset, align);
-		return -ENXIO;
+		return -EOPNOTSUPP;
+	}
+
+	if (!IS_ALIGNED(res->start + le32_to_cpu(pfn_sb->start_pad),
+				memremap_compat_align())) {
+		dev_err(&nd_pfn->dev, "resource start misaligned\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (!IS_ALIGNED(res->end + 1 - le32_to_cpu(pfn_sb->end_trunc),
+				memremap_compat_align())) {
+		dev_err(&nd_pfn->dev, "resource end misaligned\n");
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -750,7 +764,19 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	start = nsio->res.start;
 	size = resource_size(&nsio->res);
 	npfns = PHYS_PFN(size - SZ_8K);
-	align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT));
+	align = max(nd_pfn->align, memremap_compat_align());
+
+	/*
+	 * When @start is misaligned fail namespace creation. See
+	 * the 'struct nd_pfn_sb' commentary on why ->start_pad is not
+	 * an option.
+	 */
+	if (!IS_ALIGNED(start, memremap_compat_align())) {
+		dev_err(&nd_pfn->dev, "%s: start %pa misaligned to %#lx\n",
+				dev_name(&ndns->dev), &start,
+				memremap_compat_align());
+		return -EINVAL;
+	}
 	end_trunc = start + size - ALIGN_DOWN(start + size, align);
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
 		/*
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4ffc6f7ca131..2df6994acf83 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -136,9 +136,25 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 	return BLK_STS_OK;
 }
 
-static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, unsigned int op,
-			sector_t sector)
+static blk_status_t pmem_do_read(struct pmem_device *pmem,
+			struct page *page, unsigned int page_off,
+			sector_t sector, unsigned int len)
+{
+	blk_status_t rc;
+	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
+	void *pmem_addr = pmem->virt_addr + pmem_off;
+
+	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
+		return BLK_STS_IOERR;
+
+	rc = read_pmem(page, page_off, pmem_addr, len);
+	flush_dcache_page(page);
+	return rc;
+}
+
+static blk_status_t pmem_do_write(struct pmem_device *pmem,
+			struct page *page, unsigned int page_off,
+			sector_t sector, unsigned int len)
 {
 	blk_status_t rc = BLK_STS_OK;
 	bool bad_pmem = false;
@@ -148,34 +164,25 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!op_is_write(op)) {
-		if (unlikely(bad_pmem))
-			rc = BLK_STS_IOERR;
-		else {
-			rc = read_pmem(page, off, pmem_addr, len);
-			flush_dcache_page(page);
-		}
-	} else {
-		/*
-		 * Note that we write the data both before and after
-		 * clearing poison.  The write before clear poison
-		 * handles situations where the latest written data is
-		 * preserved and the clear poison operation simply marks
-		 * the address range as valid without changing the data.
-		 * In this case application software can assume that an
-		 * interrupted write will either return the new good
-		 * data or an error.
-		 *
-		 * However, if pmem_clear_poison() leaves the data in an
-		 * indeterminate state we need to perform the write
-		 * after clear poison.
-		 */
-		flush_dcache_page(page);
-		write_pmem(pmem_addr, page, off, len);
-		if (unlikely(bad_pmem)) {
-			rc = pmem_clear_poison(pmem, pmem_off, len);
-			write_pmem(pmem_addr, page, off, len);
-		}
+	/*
+	 * Note that we write the data both before and after
+	 * clearing poison.  The write before clear poison
+	 * handles situations where the latest written data is
+	 * preserved and the clear poison operation simply marks
+	 * the address range as valid without changing the data.
+	 * In this case application software can assume that an
+	 * interrupted write will either return the new good
+	 * data or an error.
+	 *
+	 * However, if pmem_clear_poison() leaves the data in an
+	 * indeterminate state we need to perform the write
+	 * after clear poison.
+	 */
+	flush_dcache_page(page);
+	write_pmem(pmem_addr, page, page_off, len);
+	if (unlikely(bad_pmem)) {
+		rc = pmem_clear_poison(pmem, pmem_off, len);
+		write_pmem(pmem_addr, page, page_off, len);
 	}
 
 	return rc;
@@ -197,8 +204,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
-		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, bio_op(bio), iter.bi_sector);
+		if (op_is_write(bio_op(bio)))
+			rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset,
+				iter.bi_sector, bvec.bv_len);
+		else
+			rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset,
+				iter.bi_sector, bvec.bv_len);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -223,9 +234,12 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
-	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, op, sector);
-
+	if (op_is_write(op))
+		rc = pmem_do_write(pmem, page, 0, sector,
+				   hpage_nr_pages(page) * PAGE_SIZE);
+	else
+		rc = pmem_do_read(pmem, page, 0, sector,
+				   hpage_nr_pages(page) * PAGE_SIZE);
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
 	 * retries on any error, so we can only invoke page_endio() in
@@ -268,6 +282,16 @@ static const struct block_device_operations pmem_fops = {
 	.revalidate_disk =	nvdimm_revalidate_disk,
 };
 
+static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+				    size_t nr_pages)
+{
+	struct pmem_device *pmem = dax_get_private(dax_dev);
+
+	return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0,
+				   PFN_PHYS(pgoff) >> SECTOR_SHIFT,
+				   PAGE_SIZE));
+}
+
 static long pmem_dax_direct_access(struct dax_device *dax_dev,
 		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
 {
@@ -299,6 +323,7 @@ static const struct dax_operations pmem_dax_ops = {
 	.dax_supported = generic_fsdax_supported,
 	.copy_from_iter = pmem_copy_from_iter,
 	.copy_to_iter = pmem_copy_to_iter,
+	.zero_page_range = pmem_dax_zero_page_range,
 };
 
 static const struct attribute_group *pmem_attribute_groups[] = {
@@ -461,9 +486,9 @@ static int pmem_attach_disk(struct device *dev,
 	if (is_nvdimm_sync(nd_region))
 		flags = DAXDEV_F_SYNC;
 	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags);
-	if (!dax_dev) {
+	if (IS_ERR(dax_dev)) {
 		put_disk(disk);
-		return -ENOMEM;
+		return PTR_ERR(dax_dev);
 	}
 	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index a19e535830d9..ccbb5b43b8b2 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -195,16 +195,16 @@ EXPORT_SYMBOL_GPL(nd_blk_region_set_provider_data);
 int nd_region_to_nstype(struct nd_region *nd_region)
 {
 	if (is_memory(&nd_region->dev)) {
-		u16 i, alias;
+		u16 i, label;
 
-		for (i = 0, alias = 0; i < nd_region->ndr_mappings; i++) {
+		for (i = 0, label = 0; i < nd_region->ndr_mappings; i++) {
 			struct nd_mapping *nd_mapping = &nd_region->mapping[i];
 			struct nvdimm *nvdimm = nd_mapping->nvdimm;
 
-			if (test_bit(NDD_ALIASING, &nvdimm->flags))
-				alias++;
+			if (test_bit(NDD_LABELING, &nvdimm->flags))
+				label++;
 		}
-		if (alias)
+		if (label)
 			return ND_DEVICE_NAMESPACE_PMEM;
 		else
 			return ND_DEVICE_NAMESPACE_IO;
@@ -216,21 +216,25 @@ int nd_region_to_nstype(struct nd_region *nd_region)
 }
 EXPORT_SYMBOL(nd_region_to_nstype);
 
-static ssize_t size_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static unsigned long long region_size(struct nd_region *nd_region)
 {
-	struct nd_region *nd_region = to_nd_region(dev);
-	unsigned long long size = 0;
-
-	if (is_memory(dev)) {
-		size = nd_region->ndr_size;
+	if (is_memory(&nd_region->dev)) {
+		return nd_region->ndr_size;
 	} else if (nd_region->ndr_mappings == 1) {
 		struct nd_mapping *nd_mapping = &nd_region->mapping[0];
 
-		size = nd_mapping->size;
+		return nd_mapping->size;
 	}
 
-	return sprintf(buf, "%llu\n", size);
+	return 0;
+}
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%llu\n", region_size(nd_region));
 }
 static DEVICE_ATTR_RO(size);
 
@@ -529,6 +533,54 @@ static ssize_t read_only_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(read_only);
 
+static ssize_t align_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+
+	return sprintf(buf, "%#lx\n", nd_region->align);
+}
+
+static ssize_t align_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	unsigned long val, dpa;
+	u32 remainder;
+	int rc;
+
+	rc = kstrtoul(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	if (!nd_region->ndr_mappings)
+		return -ENXIO;
+
+	/*
+	 * Ensure space-align is evenly divisible by the region
+	 * interleave-width because the kernel typically has no facility
+	 * to determine which DIMM(s), dimm-physical-addresses, would
+	 * contribute to the tail capacity in system-physical-address
+	 * space for the namespace.
+	 */
+	dpa = div_u64_rem(val, nd_region->ndr_mappings, &remainder);
+	if (!is_power_of_2(dpa) || dpa < PAGE_SIZE
+			|| val > region_size(nd_region) || remainder)
+		return -EINVAL;
+
+	/*
+	 * Given that space allocation consults this value multiple
+	 * times ensure it does not change for the duration of the
+	 * allocation.
+	 */
+	nvdimm_bus_lock(dev);
+	nd_region->align = val;
+	nvdimm_bus_unlock(dev);
+
+	return len;
+}
+static DEVICE_ATTR_RW(align);
+
 static ssize_t region_badblocks_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -571,6 +623,7 @@ static DEVICE_ATTR_RO(persistence_domain);
 
 static struct attribute *nd_region_attributes[] = {
 	&dev_attr_size.attr,
+	&dev_attr_align.attr,
 	&dev_attr_nstype.attr,
 	&dev_attr_mappings.attr,
 	&dev_attr_btt_seed.attr,
@@ -626,6 +679,19 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
 		return a->mode;
 	}
 
+	if (a == &dev_attr_align.attr) {
+		int i;
+
+		for (i = 0; i < nd_region->ndr_mappings; i++) {
+			struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+			struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+			if (test_bit(NDD_LABELING, &nvdimm->flags))
+				return a->mode;
+		}
+		return 0;
+	}
+
 	if (a != &dev_attr_set_cookie.attr
 			&& a != &dev_attr_available_size.attr)
 		return a->mode;
@@ -935,6 +1001,41 @@ void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane)
 }
 EXPORT_SYMBOL(nd_region_release_lane);
 
+/*
+ * PowerPC requires this alignment for memremap_pages(). All other archs
+ * should be ok with SUBSECTION_SIZE (see memremap_compat_align()).
+ */
+#define MEMREMAP_COMPAT_ALIGN_MAX SZ_16M
+
+static unsigned long default_align(struct nd_region *nd_region)
+{
+	unsigned long align;
+	int i, mappings;
+	u32 remainder;
+
+	if (is_nd_blk(&nd_region->dev))
+		align = PAGE_SIZE;
+	else
+		align = MEMREMAP_COMPAT_ALIGN_MAX;
+
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+
+		if (test_bit(NDD_ALIASING, &nvdimm->flags)) {
+			align = MEMREMAP_COMPAT_ALIGN_MAX;
+			break;
+		}
+	}
+
+	mappings = max_t(u16, 1, nd_region->ndr_mappings);
+	div_u64_rem(align, mappings, &remainder);
+	if (remainder)
+		align *= mappings;
+
+	return align;
+}
+
 static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 		struct nd_region_desc *ndr_desc,
 		const struct device_type *dev_type, const char *caller)
@@ -1039,6 +1140,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	dev->of_node = ndr_desc->of_node;
 	nd_region->ndr_size = resource_size(ndr_desc->res);
 	nd_region->ndr_start = ndr_desc->res->start;
+	nd_region->align = default_align(nd_region);
 	if (ndr_desc->flush)
 		nd_region->flush = ndr_desc->flush;
 	else