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()
  ...

8 files changed, 72 insertions, 18 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 9f70b7807d53..d661cd0ee64d 100644
--- a/include/linux/acpi.h
+++ b/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)
 {
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 328c2dbb4409..d7af5d243f24 100644
--- a/include/linux/dax.h
+++ b/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);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 475668c69dbc..af48d9da3916 100644
--- a/include/linux/device-mapper.h
+++ b/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;
diff --git a/include/linux/io.h b/include/linux/io.h
index b1c44bb4b2d7..8394c56babc2 100644
--- a/include/linux/io.h
+++ b/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
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 9df091bd30ba..18da4059be09 100644
--- a/include/linux/libnvdimm.h
+++ b/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,
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 8b37c4c9222c..5f5b2df06e61 100644
--- a/include/linux/memremap.h
+++ b/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_ */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e9892bf9eba9..1b9de7d220fb 100644
--- a/include/linux/mmzone.h
+++ b/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)
diff --git a/include/linux/numa.h b/include/linux/numa.h
index 110b0e5d0fb0..a42df804679e 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -1,7 +1,7 @@
 /* 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 */