Merge tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "This update has successfully completed a 0day-kbuild run and has
  appeared in a linux-next release.  The changes outside of the typical
  drivers/nvdimm/ and drivers/acpi/nfit.[ch] paths are related to the
  removal of IORESOURCE_CACHEABLE, the introduction of memremap(), and
  the introduction of ZONE_DEVICE + devm_memremap_pages().

  Summary:

   - Introduce ZONE_DEVICE and devm_memremap_pages() as a generic
     mechanism for adding device-driver-discovered memory regions to the
     kernel's direct map.

     This facility is used by the pmem driver to enable pfn_to_page()
     operations on the page frames returned by DAX ('direct_access' in
     'struct block_device_operations').

     For now, the 'memmap' allocation for these "device" pages comes
     from "System RAM".  Support for allocating the memmap from device
     memory will arrive in a later kernel.

   - Introduce memremap() to replace usages of ioremap_cache() and
     ioremap_wt().  memremap() drops the __iomem annotation for these
     mappings to memory that do not have i/o side effects.  The
     replacement of ioremap_cache() with memremap() is limited to the
     pmem driver to ease merging the api change in v4.3.

     Completion of the conversion is targeted for v4.4.

   - Similar to the usage of memcpy_to_pmem() + wmb_pmem() in the pmem
     driver, update the VFS DAX implementation and PMEM api to provide
     persistence guarantees for kernel operations on a DAX mapping.

   - Convert the ACPI NFIT 'BLK' driver to map the block apertures as
     cacheable to improve performance.

   - Miscellaneous updates and fixes to libnvdimm including support for
     issuing "address range scrub" commands, clarifying the optimal
     'sector size' of pmem devices, a clarification of the usage of the
     ACPI '_STA' (status) property for DIMM devices, and other minor
     fixes"

* tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (34 commits)
  libnvdimm, pmem: direct map legacy pmem by default
  libnvdimm, pmem: 'struct page' for pmem
  libnvdimm, pfn: 'struct page' provider infrastructure
  x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB
  add devm_memremap_pages
  mm: ZONE_DEVICE for "device memory"
  mm: move __phys_to_pfn and __pfn_to_phys to asm/generic/memory_model.h
  dax: drop size parameter to ->direct_access()
  nd_blk: change aperture mapping from WC to WB
  nvdimm: change to use generic kvfree()
  pmem, dax: have direct_access use __pmem annotation
  dax: update I/O path to do proper PMEM flushing
  pmem: add copy_from_iter_pmem() and clear_pmem()
  pmem, x86: clean up conditional pmem includes
  pmem: remove layer when calling arch_has_wmb_pmem()
  pmem, x86: move x86 PMEM API to new pmem.h header
  libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option
  pmem: switch to devm_ allocations
  devres: add devm_memremap
  libnvdimm, btt: write and validate parent_uuid
  ...

9 files changed, 161 insertions, 40 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a622f270f09e..708923b9b623 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1569,8 +1569,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	long (*direct_access)(struct block_device *, sector_t,
-					void **, unsigned long *pfn, long size);
+	long (*direct_access)(struct block_device *, sector_t, void __pmem **,
+			unsigned long *pfn);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1588,8 +1588,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
-extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
-						unsigned long *pfn, long size);
+extern long bdev_direct_access(struct block_device *, sector_t,
+		void __pmem **addr, unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index c27dde7215b5..e399029b68c5 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -21,7 +21,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/bug.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/page.h>
 
 /*
diff --git a/include/linux/io.h b/include/linux/io.h
index fb5a99800e77..de64c1e53612 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -20,10 +20,13 @@
 
 #include <linux/types.h>
 #include <linux/init.h>
+#include <linux/bug.h>
+#include <linux/err.h>
 #include <asm/io.h>
 #include <asm/page.h>
 
 struct device;
+struct resource;
 
 __visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
 void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
@@ -80,6 +83,27 @@ int check_signature(const volatile void __iomem *io_addr,
 			const unsigned char *signature, int length);
 void devm_ioremap_release(struct device *dev, void *res);
 
+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_ZONE_DEVICE
+void *devm_memremap_pages(struct device *dev, struct resource *res);
+#else
+static inline void *devm_memremap_pages(struct device *dev, struct resource *res)
+{
+	/*
+	 * Fail attempts to call devm_memremap_pages() without
+	 * ZONE_DEVICE support enabled, this requires callers to fall
+	 * back to plain devm_memremap() based on config
+	 */
+	WARN_ON_ONCE(1);
+	return ERR_PTR(-ENXIO);
+}
+#endif
+
 /*
  * Some systems do not have legacy ISA devices.
  * /dev/port is not a valid interface on these systems.
@@ -121,4 +145,13 @@ static inline int arch_phys_wc_index(int handle)
 #endif
 #endif
 
+enum {
+	/* See memremap() kernel-doc for usage description... */
+	MEMREMAP_WB = 1 << 0,
+	MEMREMAP_WT = 1 << 1,
+};
+
+void *memremap(resource_size_t offset, size_t size, unsigned long flags);
+void memunmap(void *addr);
+
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 75e3af01ee32..3f021dc5da8c 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -31,6 +31,9 @@ enum {
 	ND_CMD_ARS_STATUS_MAX = SZ_4K,
 	ND_MAX_MAPPINGS = 32,
 
+	/* region flag indicating to direct-map persistent memory by default */
+	ND_REGION_PAGEMAP = 0,
+
 	/* mark newly adjusted resources as requiring a label update */
 	DPA_RESOURCE_ADJUSTED = 1 << 0,
 };
@@ -91,6 +94,7 @@ struct nd_region_desc {
 	void *provider_data;
 	int num_lanes;
 	int numa_node;
+	unsigned long flags;
 };
 
 struct nvdimm_bus;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 6ffa0ac7f7d6..8f60e899b33c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -266,8 +266,9 @@ static inline void remove_memory(int nid, u64 start, u64 size) {}
 extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
 extern int add_memory(int nid, u64 start, u64 size);
-extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default);
-extern int arch_add_memory(int nid, u64 start, u64 size);
+extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
+		bool for_device);
+extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8b257c43855b..1171a292e06e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -372,7 +372,14 @@ static inline int put_page_unless_one(struct page *page)
 }
 
 extern int page_is_ram(unsigned long pfn);
-extern int region_is_ram(resource_size_t phys_addr, unsigned long size);
+
+enum {
+	REGION_INTERSECTS,
+	REGION_DISJOINT,
+	REGION_MIXED,
+};
+
+int region_intersects(resource_size_t offset, size_t size, const char *type);
 
 /* Support for virtually mapped pages */
 struct page *vmalloc_to_page(const void *addr);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ac00e2050943..d94347737292 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -319,7 +319,11 @@ enum zone_type {
 	ZONE_HIGHMEM,
 #endif
 	ZONE_MOVABLE,
+#ifdef CONFIG_ZONE_DEVICE
+	ZONE_DEVICE,
+#endif
 	__MAX_NR_ZONES
+
 };
 
 #ifndef __GENERATING_BOUNDS_H
@@ -786,6 +790,25 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat)
 	return !pgdat->node_start_pfn && !pgdat->node_spanned_pages;
 }
 
+static inline int zone_id(const struct zone *zone)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+
+	return zone - pgdat->node_zones;
+}
+
+#ifdef CONFIG_ZONE_DEVICE
+static inline bool is_dev_zone(const struct zone *zone)
+{
+	return zone_id(zone) == ZONE_DEVICE;
+}
+#else
+static inline bool is_dev_zone(const struct zone *zone)
+{
+	return false;
+}
+#endif
+
 #include <linux/memory_hotplug.h>
 
 extern struct mutex zonelists_mutex;
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 29975c73a953..366cf77953b5 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -27,9 +27,9 @@
 #include <linux/string.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
+#include <linux/io.h>
 
 #include <asm/unaligned.h>
-#include <asm/io.h>
 #include <asm/barrier.h>
 
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index d2114045a6c4..85f810b33917 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -14,28 +14,42 @@
 #define __PMEM_H__
 
 #include <linux/io.h>
+#include <linux/uio.h>
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
-#include <asm/cacheflush.h>
+#define ARCH_MEMREMAP_PMEM MEMREMAP_WB
+#include <asm/pmem.h>
 #else
+#define ARCH_MEMREMAP_PMEM MEMREMAP_WT
+/*
+ * These are simply here to enable compilation, all call sites gate
+ * calling these symbols with arch_has_pmem_api() and redirect to the
+ * implementation in asm/pmem.h.
+ */
+static inline bool __arch_has_wmb_pmem(void)
+{
+	return false;
+}
+
 static inline void arch_wmb_pmem(void)
 {
 	BUG();
 }
 
-static inline bool __arch_has_wmb_pmem(void)
+static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
+		size_t n)
 {
-	return false;
+	BUG();
 }
 
-static inline void __pmem *arch_memremap_pmem(resource_size_t offset,
-		unsigned long size)
+static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
 {
-	return NULL;
+	BUG();
+	return 0;
 }
 
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t n)
+static inline void arch_clear_pmem(void __pmem *addr, size_t size)
 {
 	BUG();
 }
@@ -43,18 +57,22 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
 
 /*
  * Architectures that define ARCH_HAS_PMEM_API must provide
- * implementations for arch_memremap_pmem(), arch_memcpy_to_pmem(),
- * arch_wmb_pmem(), and __arch_has_wmb_pmem().
+ * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(),
+ * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem().
  */
-
 static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size)
 {
 	memcpy(dst, (void __force const *) src, size);
 }
 
-static inline void memunmap_pmem(void __pmem *addr)
+static inline void memunmap_pmem(struct device *dev, void __pmem *addr)
+{
+	devm_memunmap(dev, (void __force *) addr);
+}
+
+static inline bool arch_has_pmem_api(void)
 {
-	iounmap((void __force __iomem *) addr);
+	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API);
 }
 
 /**
@@ -68,14 +86,7 @@ static inline void memunmap_pmem(void __pmem *addr)
  */
 static inline bool arch_has_wmb_pmem(void)
 {
-	if (IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API))
-		return __arch_has_wmb_pmem();
-	return false;
-}
-
-static inline bool arch_has_pmem_api(void)
-{
-	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && arch_has_wmb_pmem();
+	return arch_has_pmem_api() && __arch_has_wmb_pmem();
 }
 
 /*
@@ -85,16 +96,24 @@ static inline bool arch_has_pmem_api(void)
  * default_memremap_pmem + default_memcpy_to_pmem is sufficient for
  * making data durable relative to i/o completion.
  */
-static void default_memcpy_to_pmem(void __pmem *dst, const void *src,
+static inline void default_memcpy_to_pmem(void __pmem *dst, const void *src,
 		size_t size)
 {
 	memcpy((void __force *) dst, src, size);
 }
 
-static void __pmem *default_memremap_pmem(resource_size_t offset,
-		unsigned long size)
+static inline size_t default_copy_from_iter_pmem(void __pmem *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter_nocache((void __force *)addr, bytes, i);
+}
+
+static inline void default_clear_pmem(void __pmem *addr, size_t size)
 {
-	return (void __pmem __force *)ioremap_wt(offset, size);
+	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
+		clear_page((void __force *)addr);
+	else
+		memset((void __force *)addr, 0, size);
 }
 
 /**
@@ -109,12 +128,11 @@ static void __pmem *default_memremap_pmem(resource_size_t offset,
  * wmb_pmem() arrange for the data to be written through the
  * cache to persistent media.
  */
-static inline void __pmem *memremap_pmem(resource_size_t offset,
-		unsigned long size)
+static inline void __pmem *memremap_pmem(struct device *dev,
+		resource_size_t offset, unsigned long size)
 {
-	if (arch_has_pmem_api())
-		return arch_memremap_pmem(offset, size);
-	return default_memremap_pmem(offset, size);
+	return (void __pmem *) devm_memremap(dev, offset, size,
+			ARCH_MEMREMAP_PMEM);
 }
 
 /**
@@ -146,7 +164,42 @@ static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n)
  */
 static inline void wmb_pmem(void)
 {
-	if (arch_has_pmem_api())
+	if (arch_has_wmb_pmem())
 		arch_wmb_pmem();
+	else
+		wmb();
+}
+
+/**
+ * copy_from_iter_pmem - copy data from an iterator to PMEM
+ * @addr:	PMEM destination address
+ * @bytes:	number of bytes to copy
+ * @i:		iterator with source data
+ *
+ * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	if (arch_has_pmem_api())
+		return arch_copy_from_iter_pmem(addr, bytes, i);
+	return default_copy_from_iter_pmem(addr, bytes, i);
+}
+
+/**
+ * clear_pmem - zero a PMEM memory range
+ * @addr:	virtual start address
+ * @size:	number of bytes to zero
+ *
+ * Write zeros into the memory range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline void clear_pmem(void __pmem *addr, size_t size)
+{
+	if (arch_has_pmem_api())
+		arch_clear_pmem(addr, size);
+	else
+		default_clear_pmem(addr, size);
 }
 #endif /* __PMEM_H__ */