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()
  ...

MAINTAINERS

@@ -9670,6 +9670,7 @@ F:	drivers/acpi/nfit/*
 F:	include/linux/nd.h
 F:	include/linux/libnvdimm.h
 F:	include/uapi/linux/ndctl.h
+F:	tools/testing/nvdimm/
 
 LICENSES and SPDX stuff
 M:	Thomas Gleixner <tglx@linutronix.de>

arch/powerpc/Kconfig

@@ -122,6 +122,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
+	select ARCH_HAS_MEMREMAP_COMPAT_ALIGN
 	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API

arch/powerpc/mm/ioremap.c

@@ -2,6 +2,7 @@
 
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/mmzone.h>
 #include <linux/vmalloc.h>
 #include <asm/io-workarounds.h>
 
@@ -97,3 +98,23 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
 
 	return NULL;
 }
+
+#ifdef CONFIG_ZONE_DEVICE
+/*
+ * Override the generic version in mm/memremap.c.
+ *
+ * With hash translation, the direct-map range is mapped with just one
+ * page size selected by htab_init_page_sizes(). Consult
+ * mmu_psize_defs[] to determine the minimum page size alignment.
+*/
+unsigned long memremap_compat_align(void)
+{
+	unsigned int shift = mmu_psize_defs[mmu_linear_psize].shift;
+
+	if (radix_enabled())
+		return SUBSECTION_SIZE;
+	return max(SUBSECTION_SIZE, 1UL << shift);
+
+}
+EXPORT_SYMBOL_GPL(memremap_compat_align);
+#endif

arch/powerpc/platforms/pseries/papr_scm.c

@@ -286,25 +286,6 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
 	return 0;
 }
 
-static inline int papr_scm_node(int node)
-{
-	int min_dist = INT_MAX, dist;
-	int nid, min_node;
-
-	if ((node == NUMA_NO_NODE) || node_online(node))
-		return node;
-
-	min_node = first_online_node;
-	for_each_online_node(nid) {
-		dist = node_distance(node, nid);
-		if (dist < min_dist) {
-			min_dist = dist;
-			min_node = nid;
-		}
-	}
-	return min_node;
-}
-
 static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 {
 	struct device *dev = &p->pdev->dev;
@@ -329,7 +310,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	}
 
 	dimm_flags = 0;
-	set_bit(NDD_ALIASING, &dimm_flags);
+	set_bit(NDD_LABELING, &dimm_flags);
 
 	p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags,
 				  PAPR_SCM_DIMM_CMD_MASK, 0, NULL);
@@ -350,7 +331,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 
 	memset(&ndr_desc, 0, sizeof(ndr_desc));
 	target_nid = dev_to_node(&p->pdev->dev);
-	online_nid = papr_scm_node(target_nid);
+	online_nid = numa_map_to_online_node(target_nid);
 	ndr_desc.numa_node = online_nid;
 	ndr_desc.target_node = target_nid;
 	ndr_desc.res = &p->res;
@@ -362,8 +343,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 
 	if (p->is_volatile)
 		p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
-	else
+	else {
+		set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags);
 		p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
+	}
 	if (!p->region) {
 		dev_err(dev, "Error registering region %pR from %pOF\n",
 				ndr_desc.res, p->dn);

arch/x86/Kconfig

@@ -1661,6 +1661,7 @@ config X86_PMEM_LEGACY
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
 	select X86_PMEM_LEGACY_DEVICE
+	select NUMA_KEEP_MEMINFO if NUMA
 	select LIBNVDIMM
 	help
 	  Treat memory marked using the non-standard e820 type of 12 as used

arch/x86/mm/numa.c

@@ -25,11 +25,8 @@ nodemask_t numa_nodes_parsed __initdata;
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
-static struct numa_meminfo numa_meminfo
-#ifndef CONFIG_MEMORY_HOTPLUG
-__initdata
-#endif
-;
+static struct numa_meminfo numa_meminfo __initdata_or_meminfo;
+static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo;
 
 static int numa_distance_cnt;
 static u8 *numa_distance;
@@ -168,6 +165,19 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
 		(mi->nr_blks - idx) * sizeof(mi->blk[0]));
 }
 
+/**
+ * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another
+ * @dst: numa_meminfo to append block to
+ * @idx: Index of memblk to remove
+ * @src: numa_meminfo to remove memblk from
+ */
+static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx,
+					 struct numa_meminfo *src)
+{
+	dst->blk[dst->nr_blks++] = src->blk[idx];
+	numa_remove_memblk_from(idx, src);
+}
+
 /**
  * numa_add_memblk - Add one numa_memblk to numa_meminfo
  * @nid: NUMA node ID of the new memblk
@@ -237,14 +247,19 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 	for (i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *bi = &mi->blk[i];
 
-		/* make sure all blocks are inside the limits */
+		/* move / save reserved memory ranges */
+		if (!memblock_overlaps_region(&memblock.memory,
+					bi->start, bi->end - bi->start)) {
+			numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi);
+			continue;
+		}
+
+		/* make sure all non-reserved blocks are inside the limits */
 		bi->start = max(bi->start, low);
 		bi->end = min(bi->end, high);
 
-		/* and there's no empty or non-exist block */
-		if (bi->start >= bi->end ||
-		    !memblock_overlaps_region(&memblock.memory,
-			bi->start, bi->end - bi->start))
+		/* and there's no empty block */
+		if (bi->start >= bi->end)
 			numa_remove_memblk_from(i--, mi);
 	}
 
@@ -881,16 +896,38 @@ EXPORT_SYMBOL(cpumask_of_node);
 
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-int memory_add_physaddr_to_nid(u64 start)
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+static int meminfo_to_nid(struct numa_meminfo *mi, u64 start)
 {
-	struct numa_meminfo *mi = &numa_meminfo;
-	int nid = mi->blk[0].nid;
 	int i;
 
 	for (i = 0; i < mi->nr_blks; i++)
 		if (mi->blk[i].start <= start && mi->blk[i].end > start)
-			nid = mi->blk[i].nid;
+			return mi->blk[i].nid;
+	return NUMA_NO_NODE;
+}
+
+int phys_to_target_node(phys_addr_t start)
+{
+	int nid = meminfo_to_nid(&numa_meminfo, start);
+
+	/*
+	 * Prefer online nodes, but if reserved memory might be
+	 * hot-added continue the search with reserved ranges.
+	 */
+	if (nid != NUMA_NO_NODE)
+		return nid;
+
+	return meminfo_to_nid(&numa_reserved_meminfo, start);
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
+
+int memory_add_physaddr_to_nid(u64 start)
+{
+	int nid = meminfo_to_nid(&numa_meminfo, start);
+
+	if (nid == NUMA_NO_NODE)
+		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);

drivers/acpi/nfit/core.c

@@ -360,7 +360,7 @@ static union acpi_object *acpi_label_info(acpi_handle handle)
 
 static u8 nfit_dsm_revid(unsigned family, unsigned func)
 {
-	static const u8 revid_table[NVDIMM_FAMILY_MAX+1][32] = {
+	static const u8 revid_table[NVDIMM_FAMILY_MAX+1][NVDIMM_CMD_MAX+1] = {
 		[NVDIMM_FAMILY_INTEL] = {
 			[NVDIMM_INTEL_GET_MODES] = 2,
 			[NVDIMM_INTEL_GET_FWINFO] = 2,
@@ -386,7 +386,7 @@ static u8 nfit_dsm_revid(unsigned family, unsigned func)
 
 	if (family > NVDIMM_FAMILY_MAX)
 		return 0;
-	if (func > 31)
+	if (func > NVDIMM_CMD_MAX)
 		return 0;
 	id = revid_table[family][func];
 	if (id == 0)
@@ -492,7 +492,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	 * Check for a valid command.  For ND_CMD_CALL, we also have to
 	 * make sure that the DSM function is supported.
 	 */
-	if (cmd == ND_CMD_CALL && !test_bit(func, &dsm_mask))
+	if (cmd == ND_CMD_CALL &&
+	    (func > NVDIMM_CMD_MAX || !test_bit(func, &dsm_mask)))
 		return -ENOTTY;
 	else if (!test_bit(cmd, &cmd_mask))
 		return -ENOTTY;
@@ -2026,8 +2027,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 			continue;
 		}
 
-		if (nfit_mem->bdw && nfit_mem->memdev_pmem)
+		if (nfit_mem->bdw && nfit_mem->memdev_pmem) {
 			set_bit(NDD_ALIASING, &flags);
+			set_bit(NDD_LABELING, &flags);
+		}
 
 		/* collate flags across all memdevs for this dimm */
 		list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
@@ -3492,7 +3495,8 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
 	if (nvdimm && cmd == ND_CMD_CALL &&
 			call_pkg->nd_family == NVDIMM_FAMILY_INTEL) {
 		func = call_pkg->nd_command;
-		if ((1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK)
+		if (func > NVDIMM_CMD_MAX ||
+		    (1 << func) & NVDIMM_INTEL_SECURITY_CMDMASK)
 			return -EOPNOTSUPP;
 	}
 

drivers/acpi/nfit/nfit.h

@@ -34,6 +34,7 @@
 		| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
 
 #define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_HYPERV
+#define NVDIMM_CMD_MAX 31
 
 #define NVDIMM_STANDARD_CMDMASK \
 (1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \
@@ -144,32 +145,32 @@ struct nfit_spa {
 	unsigned long ars_state;
 	u32 clear_err_unit;
 	u32 max_ars;
-	struct acpi_nfit_system_address spa[0];
+	struct acpi_nfit_system_address spa[];
 };
 
 struct nfit_dcr {
 	struct list_head list;
-	struct acpi_nfit_control_region dcr[0];
+	struct acpi_nfit_control_region dcr[];
 };
 
 struct nfit_bdw {
 	struct list_head list;
-	struct acpi_nfit_data_region bdw[0];
+	struct acpi_nfit_data_region bdw[];
 };
 
 struct nfit_idt {
 	struct list_head list;
-	struct acpi_nfit_interleave idt[0];
+	struct acpi_nfit_interleave idt[];
 };
 
 struct nfit_flush {
 	struct list_head list;
-	struct acpi_nfit_flush_address flush[0];
+	struct acpi_nfit_flush_address flush[];
 };
 
 struct nfit_memdev {
 	struct list_head list;
-	struct acpi_nfit_memory_map memdev[0];
+	struct acpi_nfit_memory_map memdev[];
 };
 
 enum nfit_mem_flags {

drivers/acpi/numa/srat.c

@@ -72,47 +72,6 @@ int acpi_map_pxm_to_node(int pxm)
 }
 EXPORT_SYMBOL(acpi_map_pxm_to_node);
 
-/**
- * acpi_map_pxm_to_online_node - Map proximity ID to online node
- * @pxm: ACPI proximity ID
- *
- * This is similar to acpi_map_pxm_to_node(), but always returns an online
- * node.  When the mapped node from a given proximity ID is offline, it
- * looks up the node distance table and returns the nearest online node.
- *
- * ACPI device drivers, which are called after the NUMA initialization has
- * completed in the kernel, can call this interface to obtain their device
- * NUMA topology from ACPI tables.  Such drivers do not have to deal with
- * offline nodes.  A node may be offline when a device proximity ID is
- * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
- * "numa=off" on x86.
- */
-int acpi_map_pxm_to_online_node(int pxm)
-{
-	int node, min_node;
-
-	node = acpi_map_pxm_to_node(pxm);
-
-	if (node == NUMA_NO_NODE)
-		node = 0;
-
-	min_node = node;
-	if (!node_online(node)) {
-		int min_dist = INT_MAX, dist, n;
-
-		for_each_online_node(n) {
-			dist = node_distance(node, n);
-			if (dist < min_dist) {
-				min_dist = dist;
-				min_node = n;
-			}
-		}
-	}
-
-	return min_node;
-}
-EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
-
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {

drivers/dax/bus.c

@@ -421,8 +421,10 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
 	 * device outside of mmap of the resulting character device.
 	 */
 	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
-	if (!dax_dev)
+	if (IS_ERR(dax_dev)) {
+		rc = PTR_ERR(dax_dev);
 		goto err;
+	}
 
 	/* a device_dax instance is dead while the driver is not attached */
 	kill_dax(dax_dev);

drivers/dax/super.c

@@ -344,6 +344,23 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 }
 EXPORT_SYMBOL_GPL(dax_copy_to_iter);
 
+int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+			size_t nr_pages)
+{
+	if (!dax_alive(dax_dev))
+		return -ENXIO;
+	/*
+	 * There are no callers that want to zero more than one page as of now.
+	 * Once users are there, this check can be removed after the
+	 * device mapper code has been updated to split ranges across targets.
+	 */
+	if (nr_pages != 1)
+		return -EIO;
+
+	return dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages);
+}
+EXPORT_SYMBOL_GPL(dax_zero_page_range);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
@@ -551,9 +568,16 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	dev_t devt;
 	int minor;
 
+	if (ops && !ops->zero_page_range) {
+		pr_debug("%s: error: device does not provide dax"
+			 " operation zero_page_range()\n",
+			 __host ? __host : "Unknown");
+		return ERR_PTR(-EINVAL);
+	}
+
 	host = kstrdup(__host, GFP_KERNEL);
 	if (__host && !host)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
 	if (minor < 0)
@@ -576,7 +600,7 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	ida_simple_remove(&dax_minor_ida, minor);
  err_minor:
 	kfree(host);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(alloc_dax);
 

drivers/md/dm-linear.c

@@ -201,10 +201,27 @@ static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
+				      size_t nr_pages)
+{
+	int ret;
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct dax_device *dax_dev = lc->dev->dax_dev;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+
+	dev_sector = linear_map_sector(ti, sector);
+	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
+	if (ret)
+		return ret;
+	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_copy_from_iter NULL
 #define linear_dax_copy_to_iter NULL
+#define linear_dax_zero_page_range NULL
 #endif
 
 static struct target_type linear_target = {
@@ -226,6 +243,7 @@ static struct target_type linear_target = {
 	.direct_access = linear_dax_direct_access,
 	.dax_copy_from_iter = linear_dax_copy_from_iter,
 	.dax_copy_to_iter = linear_dax_copy_to_iter,
+	.dax_zero_page_range = linear_dax_zero_page_range,
 };
 
 int __init dm_linear_init(void)

drivers/md/dm-log-writes.c

@@ -994,10 +994,26 @@ static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
 	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
 }
 
+static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
+					  size_t nr_pages)
+{
+	int ret;
+	struct log_writes_c *lc = ti->private;
+	sector_t sector = pgoff * PAGE_SECTORS;
+
+	ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT,
+			     &pgoff);
+	if (ret)
+		return ret;
+	return dax_zero_page_range(lc->dev->dax_dev, pgoff,
+				   nr_pages << PAGE_SHIFT);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_copy_from_iter NULL
 #define log_writes_dax_copy_to_iter NULL
+#define log_writes_dax_zero_page_range NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -1016,6 +1032,7 @@ static struct target_type log_writes_target = {
 	.direct_access = log_writes_dax_direct_access,
 	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
 	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
+	.dax_zero_page_range = log_writes_dax_zero_page_range,
 };
 
 static int __init dm_log_writes_init(void)

drivers/md/dm-stripe.c

@@ -360,10 +360,32 @@ static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
+				      size_t nr_pages)
+{
+	int ret;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct stripe_c *sc = ti->private;
+	struct dax_device *dax_dev;
+	struct block_device *bdev;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	dax_dev = sc->stripe[stripe].dev->dax_dev;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
+	if (ret)
+		return ret;
+	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_copy_from_iter NULL
 #define stripe_dax_copy_to_iter NULL
+#define stripe_dax_zero_page_range NULL
 #endif
 
 /*
@@ -486,6 +508,7 @@ static struct target_type stripe_target = {
 	.direct_access = stripe_dax_direct_access,
 	.dax_copy_from_iter = stripe_dax_copy_from_iter,
 	.dax_copy_to_iter = stripe_dax_copy_to_iter,
+	.dax_zero_page_range = stripe_dax_zero_page_range,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm.c

@@ -1199,6 +1199,35 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+				  size_t nr_pages)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	int ret = -EIO;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (WARN_ON(!ti->type->dax_zero_page_range)) {
+		/*
+		 * ->zero_page_range() is mandatory dax operation. If we are
+		 *  here, something is wrong.
+		 */
+		dm_put_live_table(md, srcu_idx);
+		goto out;
+	}
+	ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages);
+
+ out:
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET,
@@ -1969,7 +1998,7 @@ static struct mapped_device *alloc_dev(int minor)
 	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
 		md->dax_dev = alloc_dax(md, md->disk->disk_name,
 					&dm_dax_ops, 0);
-		if (!md->dax_dev)
+		if (IS_ERR(md->dax_dev))
 			goto bad;
 	}
 
@@ -3200,6 +3229,7 @@ static const struct dax_operations dm_dax_ops = {
 	.dax_supported = dm_dax_supported,
 	.copy_from_iter = dm_dax_copy_from_iter,
 	.copy_to_iter = dm_dax_copy_to_iter,
+	.zero_page_range = dm_dax_zero_page_range,
 };
 
 /*

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) */

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);
 

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:

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;

drivers/nvdimm/label.h

@@ -62,7 +62,7 @@ struct nd_namespace_index {
 	__le16 major;
 	__le16 minor;
 	__le64 checksum;
-	u8 free[0];
+	u8 free[];
 };
 
 /**

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;

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);

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",

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 */

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) {
 		/*

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;

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

drivers/s390/block/dcssblk.c

@@ -57,11 +57,26 @@ static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
 	return copy_to_iter(addr, bytes, i);
 }
 
+static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
+				       pgoff_t pgoff, size_t nr_pages)
+{
+	long rc;
+	void *kaddr;
+
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	if (rc < 0)
+		return rc;
+	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
+	dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT);
+	return 0;
+}
+
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
 	.dax_supported = generic_fsdax_supported,
 	.copy_from_iter = dcssblk_dax_copy_from_iter,
 	.copy_to_iter = dcssblk_dax_copy_to_iter,
+	.zero_page_range = dcssblk_dax_zero_page_range,
 };
 
 struct dcssblk_dev_info {
@@ -680,8 +695,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 
 	dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name,
 			&dcssblk_dax_ops, DAXDEV_F_SYNC);
-	if (!dev_info->dax_dev) {
-		rc = -ENOMEM;
+	if (IS_ERR(dev_info->dax_dev)) {
+		rc = PTR_ERR(dev_info->dax_dev);
+		dev_info->dax_dev = NULL;
 		goto put_dev;
 	}
 

fs/dax.c

@@ -1038,50 +1038,43 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
-static bool dax_range_is_aligned(struct block_device *bdev,
-				 unsigned int offset, unsigned int length)
+int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
+		   struct iomap *iomap)
 {
-	unsigned short sector_size = bdev_logical_block_size(bdev);
+	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
+	pgoff_t pgoff;
+	long rc, id;
+	void *kaddr;
+	bool page_aligned = false;
 
-	if (!IS_ALIGNED(offset, sector_size))
-		return false;
-	if (!IS_ALIGNED(length, sector_size))
-		return false;
 
-	return true;
-}
+	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
+	    IS_ALIGNED(size, PAGE_SIZE))
+		page_aligned = true;
 
-int __dax_zero_page_range(struct block_device *bdev,
-		struct dax_device *dax_dev, sector_t sector,
-		unsigned int offset, unsigned int size)
-{
-	if (dax_range_is_aligned(bdev, offset, size)) {
-		sector_t start_sector = sector + (offset >> 9);
+	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
+	if (rc)
+		return rc;
 
-		return blkdev_issue_zeroout(bdev, start_sector,
-				size >> 9, GFP_NOFS, 0);
-	} else {
-		pgoff_t pgoff;
-		long rc, id;
-		void *kaddr;
+	id = dax_read_lock();
 
-		rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
-		if (rc)
-			return rc;
+	if (page_aligned)
+		rc = dax_zero_page_range(iomap->dax_dev, pgoff,
+					 size >> PAGE_SHIFT);
+	else
+		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
+	if (rc < 0) {
+		dax_read_unlock(id);
+		return rc;
+	}
 
-		id = dax_read_lock();
-		rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
-		if (rc < 0) {
-			dax_read_unlock(id);
-			return rc;
-		}
+	if (!page_aligned) {
 		memset(kaddr + offset, 0, size);
-		dax_flush(dax_dev, kaddr + offset, size);
-		dax_read_unlock(id);
+		dax_flush(iomap->dax_dev, kaddr + offset, size);
 	}
+	dax_read_unlock(id);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(__dax_zero_page_range);
 
 static loff_t
 dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,

fs/iomap/buffered-io.c

@@ -975,13 +975,6 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
 }
 
-static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
-		struct iomap *iomap)
-{
-	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev,
-			iomap_sector(iomap, pos & PAGE_MASK), offset, bytes);
-}
-
 static loff_t
 iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		void *data, struct iomap *iomap, struct iomap *srcmap)
@@ -1001,7 +994,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
-			status = iomap_dax_zero(pos, offset, bytes, iomap);
+			status = dax_iomap_zero(pos, offset, bytes, iomap);
 		else
 			status = iomap_zero(inode, pos, offset, bytes, iomap,
 					srcmap);

include/linux/acpi.h

@@ -416,9 +416,30 @@ extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
 #ifdef CONFIG_ACPI_NUMA
-int acpi_map_pxm_to_online_node(int pxm);
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
+
+/**
+ * acpi_map_pxm_to_online_node - Map proximity ID to online node
+ * @pxm: ACPI proximity ID
+ *
+ * This is similar to acpi_map_pxm_to_node(), but always returns an online
+ * node.  When the mapped node from a given proximity ID is offline, it
+ * looks up the node distance table and returns the nearest online node.
+ *
+ * ACPI device drivers, which are called after the NUMA initialization has
+ * completed in the kernel, can call this interface to obtain their device
+ * NUMA topology from ACPI tables.  Such drivers do not have to deal with
+ * offline nodes.  A node may be offline when a device proximity ID is
+ * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
+ * "numa=off" on x86.
+ */
+static inline int acpi_map_pxm_to_online_node(int pxm)
+{
+	int node = acpi_map_pxm_to_node(pxm);
+
+	return numa_map_to_online_node(node);
+}
 #else
 static inline int acpi_map_pxm_to_online_node(int pxm)
 {

include/linux/dax.h

@@ -13,6 +13,7 @@
 typedef unsigned long dax_entry_t;
 
 struct iomap_ops;
+struct iomap;
 struct dax_device;
 struct dax_operations {
 	/*
@@ -34,6 +35,8 @@ struct dax_operations {
 	/* copy_to_iter: required operation for fs-dax direct-i/o */
 	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
 			struct iov_iter *);
+	/* zero_page_range: required operation. Zero page range   */
+	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 };
 
 extern struct attribute_group dax_attribute_group;
@@ -199,6 +202,8 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
+int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+			size_t nr_pages);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
@@ -210,20 +215,8 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-
-#ifdef CONFIG_FS_DAX
-int __dax_zero_page_range(struct block_device *bdev,
-		struct dax_device *dax_dev, sector_t sector,
-		unsigned int offset, unsigned int length);
-#else
-static inline int __dax_zero_page_range(struct block_device *bdev,
-		struct dax_device *dax_dev, sector_t sector,
-		unsigned int offset, unsigned int length)
-{
-	return -ENXIO;
-}
-#endif
-
+int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
+			struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);

include/linux/device-mapper.h

@@ -141,6 +141,8 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
 typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i);
+typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
+		size_t nr_pages);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
 void dm_error(const char *message);
@@ -195,6 +197,7 @@ struct target_type {
 	dm_dax_direct_access_fn direct_access;
 	dm_dax_copy_iter_fn dax_copy_from_iter;
 	dm_dax_copy_iter_fn dax_copy_to_iter;
+	dm_dax_zero_page_range_fn dax_zero_page_range;
 
 	/* For internal device-mapper use. */
 	struct list_head list;

include/linux/io.h

@@ -77,8 +77,6 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
 		size_t size, unsigned long flags);
 void devm_memunmap(struct device *dev, void *addr);
 
-void *__devm_memremap_pages(struct device *dev, struct resource *res);
-
 #ifdef CONFIG_PCI
 /*
  * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and

include/linux/libnvdimm.h

@@ -37,6 +37,8 @@ enum {
 	NDD_WORK_PENDING = 4,
 	/* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */
 	NDD_NOBLK = 5,
+	/* dimm supports namespace labels */
+	NDD_LABELING = 6,
 
 	/* need to set a limit somewhere, but yes, this is likely overkill */
 	ND_IOCTL_MAX_BUFLEN = SZ_4M,

include/linux/memremap.h

@@ -134,6 +134,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
+unsigned long memremap_compat_align(void);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
@@ -167,6 +168,12 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap,
 		unsigned long nr_pfns)
 {
 }
+
+/* when memremap_pages() is disabled all archs can remap a single page */
+static inline unsigned long memremap_compat_align(void)
+{
+	return PAGE_SIZE;
+}
 #endif /* CONFIG_ZONE_DEVICE */
 
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
@@ -174,4 +181,5 @@ static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 	if (pgmap)
 		percpu_ref_put(pgmap->ref);
 }
+
 #endif /* _LINUX_MEMREMAP_H_ */

include/linux/mmzone.h

@@ -1127,6 +1127,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 #define SUBSECTION_SHIFT 21
+#define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT)
 
 #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
 #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)

include/linux/numa.h

 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_NUMA_H
 #define _LINUX_NUMA_H
-
+#include <linux/types.h>
 
 #ifdef CONFIG_NODES_SHIFT
 #define NODES_SHIFT     CONFIG_NODES_SHIFT
@@ -13,4 +13,32 @@
 
 #define	NUMA_NO_NODE	(-1)
 
+/* optionally keep NUMA memory info available post init */
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+#define __initdata_or_meminfo
+#else
+#define __initdata_or_meminfo __initdata
+#endif
+
+#ifdef CONFIG_NUMA
+/* Generic implementation available */
+int numa_map_to_online_node(int node);
+
+/*
+ * Optional architecture specific implementation, users need a "depends
+ * on $ARCH"
+ */
+int phys_to_target_node(phys_addr_t addr);
+#else
+static inline int numa_map_to_online_node(int node)
+{
+	return NUMA_NO_NODE;
+}
+
+static inline int phys_to_target_node(phys_addr_t addr)
+{
+	return NUMA_NO_NODE;
+}
+#endif
+
 #endif /* _LINUX_NUMA_H */

lib/Kconfig

@@ -615,6 +615,9 @@ config ARCH_HAS_PMEM_API
 config MEMREGION
 	bool
 
+config ARCH_HAS_MEMREMAP_COMPAT_ALIGN
+	bool
+
 # use memcpy to implement user copies for nommu architectures
 config UACCESS_MEMCPY
 	bool

mm/Kconfig

@@ -139,6 +139,10 @@ config HAVE_FAST_GUP
 config ARCH_KEEP_MEMBLOCK
 	bool
 
+# Keep arch NUMA mapping infrastructure post-init.
+config NUMA_KEEP_MEMINFO
+	bool
+
 config MEMORY_ISOLATION
 	bool
 
@@ -154,6 +158,7 @@ config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
+	select NUMA_KEEP_MEMINFO if NUMA
 
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y

mm/mempolicy.c

@@ -127,6 +127,32 @@ static struct mempolicy default_policy = {
 
 static struct mempolicy preferred_node_policy[MAX_NUMNODES];
 
+/**
+ * numa_map_to_online_node - Find closest online node
+ * @nid: Node id to start the search
+ *
+ * Lookup the next closest node by distance if @nid is not online.
+ */
+int numa_map_to_online_node(int node)
+{
+	int min_dist = INT_MAX, dist, n, min_node;
+
+	if (node == NUMA_NO_NODE || node_online(node))
+		return node;
+
+	min_node = node;
+	for_each_online_node(n) {
+		dist = node_distance(node, n);
+		if (dist < min_dist) {
+			min_dist = dist;
+			min_node = n;
+		}
+	}
+
+	return min_node;
+}
+EXPORT_SYMBOL_GPL(numa_map_to_online_node);
+
 struct mempolicy *get_task_policy(struct task_struct *p)
 {
 	struct mempolicy *pol = p->mempolicy;

mm/memremap.c

@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/pfn_t.h>
 #include <linux/swap.h>
+#include <linux/mmzone.h>
 #include <linux/swapops.h>
 #include <linux/types.h>
 #include <linux/wait_bit.h>
@@ -14,6 +15,28 @@
 
 static DEFINE_XARRAY(pgmap_array);
 
+/*
+ * The memremap() and memremap_pages() interfaces are alternately used
+ * to map persistent memory namespaces. These interfaces place different
+ * constraints on the alignment and size of the mapping (namespace).
+ * memremap() can map individual PAGE_SIZE pages. memremap_pages() can
+ * only map subsections (2MB), and at least one architecture (PowerPC)
+ * the minimum mapping granularity of memremap_pages() is 16MB.
+ *
+ * The role of memremap_compat_align() is to communicate the minimum
+ * arch supported alignment of a namespace such that it can freely
+ * switch modes without violating the arch constraint. Namely, do not
+ * allow a namespace to be PAGE_SIZE aligned since that namespace may be
+ * reconfigured into a mode that requires SUBSECTION_SIZE alignment.
+ */
+#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN
+unsigned long memremap_compat_align(void)
+{
+	return SUBSECTION_SIZE;
+}
+EXPORT_SYMBOL_GPL(memremap_compat_align);
+#endif
+
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
 EXPORT_SYMBOL(devmap_managed_key);

tools/testing/nvdimm/Kbuild

@@ -21,8 +21,8 @@ DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm
 ACPI_SRC := $(DRIVERS)/acpi/nfit
 DAX_SRC := $(DRIVERS)/dax
-ccflags-y := -I$(src)/$(NVDIMM_SRC)/
-ccflags-y += -I$(src)/$(ACPI_SRC)/
+ccflags-y := -I$(srctree)/drivers/nvdimm/
+ccflags-y += -I$(srctree)/drivers/acpi/nfit/
 
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o

tools/testing/nvdimm/test/Kbuild

 # SPDX-License-Identifier: GPL-2.0
-ccflags-y := -I$(src)/../../../../drivers/nvdimm/
-ccflags-y += -I$(src)/../../../../drivers/acpi/nfit/
+ccflags-y := -I$(srctree)/drivers/nvdimm/
+ccflags-y += -I$(srctree)/drivers/acpi/nfit/
 
 obj-m += nfit_test.o
 obj-m += nfit_test_iomap.o

tools/testing/nvdimm/test/nfit.c

@@ -3164,7 +3164,9 @@ static __init int nfit_test_init(void)
 	mcsafe_test();
 	dax_pmem_test();
 	dax_pmem_core_test();
+#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
 	dax_pmem_compat_test();
+#endif
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);