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
  ...

92 files changed, 2142 insertions, 745 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 6a34a0f4d37c..06d443450f21 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -397,7 +397,8 @@ prototypes:
 	int (*release) (struct gendisk *, fmode_t);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
+	int (*direct_access) (struct block_device *, sector_t, void __pmem **,
+				unsigned long *);
 	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
diff --git a/MAINTAINERS b/MAINTAINERS
index 6dfc2242715d..82778382bef6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6229,6 +6229,7 @@ Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
 F:	drivers/nvdimm/pmem.c
 F:	include/linux/pmem.h
+F:	arch/*/include/asm/pmem.h
 
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index b7f6fb462ea0..98d58bb04ac5 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -119,12 +119,6 @@
 #endif
 
 /*
- * Convert a physical address to a Page Frame Number and back
- */
-#define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
-#define	__pfn_to_phys(pfn)	((phys_addr_t)(pfn) << PAGE_SHIFT)
-
-/*
  * Convert a page to/from a physical address
  */
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
diff --git a/arch/arm/mach-clps711x/board-cdb89712.c b/arch/arm/mach-clps711x/board-cdb89712.c
index 1ec378c334e5..972abdb10028 100644
--- a/arch/arm/mach-clps711x/board-cdb89712.c
+++ b/arch/arm/mach-clps711x/board-cdb89712.c
@@ -95,7 +95,7 @@ static struct physmap_flash_data cdb89712_bootrom_pdata __initdata = {
 
 static struct resource cdb89712_bootrom_resources[] __initdata = {
 	DEFINE_RES_NAMED(CS7_PHYS_BASE, SZ_128, "BOOTROM", IORESOURCE_MEM |
-			 IORESOURCE_CACHEABLE | IORESOURCE_READONLY),
+			 IORESOURCE_READONLY),
 };
 
 static struct platform_device cdb89712_bootrom_pdev __initdata = {
diff --git a/arch/arm/mach-shmobile/pm-rcar.c b/arch/arm/mach-shmobile/pm-rcar.c
index 4092ad16e0a4..0af05d288b09 100644
--- a/arch/arm/mach-shmobile/pm-rcar.c
+++ b/arch/arm/mach-shmobile/pm-rcar.c
@@ -12,7 +12,7 @@
 #include <linux/err.h>
 #include <linux/mm.h>
 #include <linux/spinlock.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include "pm-rcar.h"
 
 /* SYSC Common */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 44a59c20e773..6b4c3ad75a2a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -81,12 +81,6 @@
 #define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET + PAGE_OFFSET))
 
 /*
- * Convert a physical address to a Page Frame Number and back
- */
-#define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
-#define	__pfn_to_phys(pfn)	((phys_addr_t)(pfn) << PAGE_SHIFT)
-
-/*
  * Convert a page to/from a physical address
  */
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 80a7e34be009..9041bbe2b7b4 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -435,6 +435,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 {
 	return ioremap(phys_addr, size);
 }
+#define ioremap_cache ioremap_cache
 
 
 /*
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 4826ff957a3d..5fa3848ba224 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -4,7 +4,7 @@
 #include <linux/errno.h>
 #include <linux/timex.h>
 #include <linux/clocksource.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 /* IBM Summit (EXA) Cyclone counter code*/
 #define CYCLONE_CBAR_ADDR 0xFEB00CD0
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 97e48b0eefc7..1841ef69183d 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -645,7 +645,7 @@ mem_init (void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	pg_data_t *pgdat;
 	struct zone *zone;
@@ -656,7 +656,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	pgdat = NODE_DATA(nid);
 
 	zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL);
+		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
 	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 
 	if (ret)
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index c8c62c7fc31c..2e710c15893f 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -102,7 +102,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 			res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
 		} else if (i == dev->rom_base_reg) {
 			res = &dev->resource[PCI_ROM_RESOURCE];
-			flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE;
+			flags |= IORESOURCE_READONLY;
 		} else {
 			printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
 			continue;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index e1fe333da946..22d94c3e6fc4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -113,7 +113,7 @@ int memory_add_physaddr_to_nid(u64 start)
 }
 #endif
 
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata;
 	struct zone *zone;
@@ -128,7 +128,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	/* this should work for most non-highmem platforms */
 	zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, 0);
+		zone_for_memory(nid, start, size, 0, for_device);
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index f86250c48b53..d2b79bc336c1 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -141,13 +141,14 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  */
 static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void **kaddr, unsigned long *pfn, long size)
+		       void __pmem **kaddr, unsigned long *pfn)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
 	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
+	void *addr = (void *)(bank->ph_addr + offset);
 
-	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+	*kaddr = (void __pmem *)addr;
+	*pfn = virt_to_phys(addr) >> PAGE_SHIFT;
 
 	return bank->size - offset;
 }
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 2963b563621c..c3c07d3505ba 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -169,7 +169,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
 	unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS);
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 93ec9066dbef..3280a6bfa503 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -342,6 +342,7 @@ ioremap_cache(phys_addr_t offset, unsigned long size)
 {
 	return __ioremap_mode(offset, size, PAGE_KERNEL);
 }
+#define ioremap_cache ioremap_cache
 
 #ifdef CONFIG_HAVE_IOREMAP_PROT
 static inline void __iomem *
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 17f486233db0..75491862d900 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -485,7 +485,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
 {
 	pg_data_t *pgdat;
 	unsigned long start_pfn = PFN_DOWN(start);
@@ -496,7 +496,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	/* We only have ZONE_NORMAL, so this is easy.. */
 	ret = __add_pages(nid, pgdat->node_zones +
-			zone_for_memory(nid, start, size, ZONE_NORMAL),
+			zone_for_memory(nid, start, size, ZONE_NORMAL,
+			for_device),
 			start_pfn, nr_pages);
 	if (unlikely(ret))
 		printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 3a14a35592fe..b91d7f146175 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -231,8 +231,7 @@ static void pci_parse_of_addrs(struct platform_device *op,
 			res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
 		} else if (i == dev->rom_base_reg) {
 			res = &dev->resource[PCI_ROM_RESOURCE];
-			flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE
-			      | IORESOURCE_SIZEALIGN;
+			flags |= IORESOURCE_READONLY | IORESOURCE_SIZEALIGN;
 		} else {
 			printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
 			continue;
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index 5bd252e3fdc5..d4e1fc41d06d 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -863,7 +863,7 @@ void __init mem_init(void)
  * memory to the highmem for now.
  */
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-int arch_add_memory(u64 start, u64 size)
+int arch_add_memory(u64 start, u64 size, bool for_device)
 {
 	struct pglist_data *pgdata = &contig_page_data;
 	struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1;
diff --git a/arch/unicore32/include/asm/memory.h b/arch/unicore32/include/asm/memory.h
index debafc40200a..3bb0a29fd2d7 100644
--- a/arch/unicore32/include/asm/memory.h
+++ b/arch/unicore32/include/asm/memory.h
@@ -61,12 +61,6 @@
 #endif
 
 /*
- * Convert a physical address to a Page Frame Number and back
- */
-#define	__phys_to_pfn(paddr)	((paddr) >> PAGE_SHIFT)
-#define	__pfn_to_phys(pfn)	((pfn) << PAGE_SHIFT)
-
-/*
  * Convert a page to/from a physical address
  */
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 117e2f373