Merge tag 'libnvdimm-for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm

Pull libnvdimm subsystem from Dan Williams:
 "The libnvdimm sub-system introduces, in addition to the
  libnvdimm-core, 4 drivers / enabling modules:

  NFIT:
    Instantiates an "nvdimm bus" with the core and registers memory
    devices (NVDIMMs) enumerated by the ACPI 6.0 NFIT (NVDIMM Firmware
    Interface table).

    After registering NVDIMMs the NFIT driver then registers "region"
    devices.  A libnvdimm-region defines an access mode and the
    boundaries of persistent memory media.  A region may span multiple
    NVDIMMs that are interleaved by the hardware memory controller.  In
    turn, a libnvdimm-region can be carved into a "namespace" device and
    bound to the PMEM or BLK driver which will attach a Linux block
    device (disk) interface to the memory.

  PMEM:
    Initially merged in v4.1 this driver for contiguous spans of
    persistent memory address ranges is re-worked to drive
    PMEM-namespaces emitted by the libnvdimm-core.

    In this update the PMEM driver, on x86, gains the ability to assert
    that writes to persistent memory have been flushed all the way
    through the caches and buffers in the platform to persistent media.
    See memcpy_to_pmem() and wmb_pmem().

  BLK:
    This new driver enables access to persistent memory media through
    "Block Data Windows" as defined by the NFIT.  The primary difference
    of this driver to PMEM is that only a small window of persistent
    memory is mapped into system address space at any given point in
    time.

    Per-NVDIMM windows are reprogrammed at run time, per-I/O, to access
    different portions of the media.  BLK-mode, by definition, does not
    support DAX.

  BTT:
    This is a library, optionally consumed by either PMEM or BLK, that
    converts a byte-accessible namespace into a disk with atomic sector
    update semantics (prevents sector tearing on crash or power loss).

    The sinister aspect of sector tearing is that most applications do
    not know they have a atomic sector dependency.  At least today's
    disk's rarely ever tear sectors and if they do one almost certainly
    gets a CRC error on access.  NVDIMMs will always tear and always
    silently.  Until an application is audited to be robust in the
    presence of sector-tearing the usage of BTT is recommended.

  Thanks to: Ross Zwisler, Jeff Moyer, Vishal Verma, Christoph Hellwig,
  Ingo Molnar, Neil Brown, Boaz Harrosh, Robert Elliott, Matthew Wilcox,
  Andy Rudoff, Linda Knippers, Toshi Kani, Nicholas Moulin, Rafael
  Wysocki, and Bob Moore"

* tag 'libnvdimm-for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm: (33 commits)
  arch, x86: pmem api for ensuring durability of persistent memory updates
  libnvdimm: Add sysfs numa_node to NVDIMM devices
  libnvdimm: Set numa_node to NVDIMM devices
  acpi: Add acpi_map_pxm_to_online_node()
  libnvdimm, nfit: handle unarmed dimms, mark namespaces read-only
  pmem: flag pmem block devices as non-rotational
  libnvdimm: enable iostat
  pmem: make_request cleanups
  libnvdimm, pmem: fix up max_hw_sectors
  libnvdimm, blk: add support for blk integrity
  libnvdimm, btt: add support for blk integrity
  fs/block_dev.c: skip rw_page if bdev has integrity
  libnvdimm: Non-Volatile Devices
  tools/testing/nvdimm: libnvdimm unit test infrastructure
  libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory
  nd_btt: atomic sector updates
  libnvdimm: infrastructure for btt devices
  libnvdimm: write blk label set
  libnvdimm: write pmem label set
  libnvdimm: blk labels and namespace instantiation
  ...

10 files changed, 180 insertions, 36 deletions

diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index ab21e0d58278..9d4aa18f2a82 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -158,6 +158,7 @@ static __init int is_reserve_region(efi_memory_desc_t *md)
 	case EFI_BOOT_SERVICES_CODE:
 	case EFI_BOOT_SERVICES_DATA:
 	case EFI_CONVENTIONAL_MEMORY:
+	case EFI_PERSISTENT_MEMORY:
 		return 0;
 	default:
 		break;
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index 47e962f7ed5a..caae3f4e4341 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -1222,6 +1222,10 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 				flags |= IORESOURCE_DISABLED;
 				break;
 
+			case EFI_PERSISTENT_MEMORY:
+				name = "Persistent Memory";
+				break;
+
 			case EFI_RESERVED_TYPE:
 			case EFI_RUNTIME_SERVICES_CODE:
 			case EFI_RUNTIME_SERVICES_DATA:
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4fcf0ade7e91..d05a42357ef0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,6 +27,7 @@ config X86
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
@@ -1419,6 +1420,9 @@ source "mm/Kconfig"
 
 config X86_PMEM_LEGACY
 	bool "Support non-standard NVDIMMs and ADR protected memory"
+	depends on PHYS_ADDR_T_64BIT
+	depends on BLK_DEV
+	select LIBNVDIMM
 	help
 	  Treat memory marked using the non-standard e820 type of 12 as used
 	  by the Intel Sandy Bridge-EP reference BIOS as protected memory.
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 48304b89b601..2c82bd150d43 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1224,6 +1224,10 @@ static efi_status_t setup_e820(struct boot_params *params,
 			e820_type = E820_NVS;
 			break;
 
+		case EFI_PERSISTENT_MEMORY:
+			e820_type = E820_PMEM;
+			break;
+
 		default:
 			continue;
 		}
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index b6f7457d12e4..9bf3ea14b9f0 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -4,6 +4,7 @@
 /* Caches aren't brain-dead on the intel. */
 #include <asm-generic/cacheflush.h>
 #include <asm/special_insns.h>
+#include <asm/uaccess.h>
 
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
@@ -108,4 +109,75 @@ static inline int rodata_test(void)
 }
 #endif
 
+#ifdef ARCH_HAS_NOCACHE_UACCESS
+
+/**
+ * arch_memcpy_to_pmem - copy data to persistent memory
+ * @dst: destination buffer for the copy
+ * @src: source buffer for the copy
+ * @n: length of the copy in bytes
+ *
+ * Copy data to persistent memory media via non-temporal stores so that
+ * a subsequent arch_wmb_pmem() can flush cpu and memory controller
+ * write buffers to guarantee durability.
+ */
+static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
+		size_t n)
+{
+	int unwritten;
+
+	/*
+	 * We are copying between two kernel buffers, if
+	 * __copy_from_user_inatomic_nocache() returns an error (page
+	 * fault) we would have already reported a general protection fault
+	 * before the WARN+BUG.
+	 */
+	unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
+			(void __user *) src, n);
+	if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
+				__func__, dst, src, unwritten))
+		BUG();
+}
+
+/**
+ * arch_wmb_pmem - synchronize writes to persistent memory
+ *
+ * After a series of arch_memcpy_to_pmem() operations this drains data
+ * from cpu write buffers and any platform (memory controller) buffers
+ * to ensure that written data is durable on persistent memory media.
+ */
+static inline void arch_wmb_pmem(void)
+{
+	/*
+	 * wmb() to 'sfence' all previous writes such that they are
+	 * architecturally visible to 'pcommit'.  Note, that we've
+	 * already arranged for pmem writes to avoid the cache via
+	 * arch_memcpy_to_pmem().
+	 */
+	wmb();
+	pcommit_sfence();
+}
+
+static inline bool __arch_has_wmb_pmem(void)
+{
+#ifdef CONFIG_X86_64
+	/*
+	 * We require that wmb() be an 'sfence', that is only guaranteed on
+	 * 64-bit builds
+	 */
+	return static_cpu_has(X86_FEATURE_PCOMMIT);
+#else
+	return false;
+#endif
+}
+#else /* ARCH_HAS_NOCACHE_UACCESS i.e. ARCH=um */
+extern void arch_memcpy_to_pmem(void __pmem *dst, const void *src, size_t n);
+extern void arch_wmb_pmem(void);
+
+static inline bool __arch_has_wmb_pmem(void)
+{
+	return false;
+}
+#endif
+
 #endif /* _ASM_X86_CACHEFLUSH_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 83ec9b1d77cc..cc9c61bc1abe 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -248,6 +248,12 @@ static inline void flush_write_buffers(void)
 #endif
 }
 
+static inline void __pmem *arch_memremap_pmem(resource_size_t offset,
+	unsigned long size)
+{
+	return (void __force __pmem *) ioremap_cache(offset, size);
+}
+
 #endif /* __KERNEL__ */
 
 extern void native_io_delay(void);
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index 960a8a9dc4ab..0f457e6eab18 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -32,6 +32,7 @@
 #define E820_ACPI	3
 #define E820_NVS	4
 #define E820_UNUSABLE	5
+#define E820_PMEM	7
 
 /*
  * This is a non-standardized way to represent ADR or NVDIMM regions that
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index c8dda42cb6a3..a102564d08eb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type)
 	case E820_UNUSABLE:
 		printk(KERN_CONT "unusable");
 		break;
+	case E820_PMEM:
 	case E820_PRAM:
 		printk(KERN_CONT "persistent (type %u)", type);
 		break;
@@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type)
 	case E820_ACPI:	return "ACPI Tables";
 	case E820_NVS:	return "ACPI Non-volatile Storage";
 	case E820_UNUSABLE:	return "Unusable memory";
-	case E820_PRAM: return "Persistent RAM";
+	case E820_PRAM: return "Persistent Memory (legacy)";
+	case E820_PMEM: return "Persistent Memory";
 	default:	return "reserved";
 	}
 }
 
+static bool do_mark_busy(u32 type, struct resource *res)
+{
+	/* this is the legacy bios/dos rom-shadow + mmio region */
+	if (res->start < (1ULL<<20))
+		return true;
+
+	/*
+	 * Treat persistent memory like device memory, i.e. reserve it
+	 * for exclusive use of a driver
+	 */
+	switch (type) {
+	case E820_RESERVED:
+	case E820_PRAM:
+	case E820_PMEM:
+		return false;
+	default:
+		return true;
+	}
+}
+
 /*
  * Mark e820 reserved areas as busy for the resource manager.
  */
@@ -952,9 +974,7 @@ void __init e820_reserve_resources(void)
 		 * pci device BAR resource and insert them later in
 		 * pcibios_resource_survey()
 		 */
-		if (((e820.map[i].type != E820_RESERVED) &&
-		     (e820.map[i].type != E820_PRAM)) ||
-		     res->start < (1ULL<<20)) {
+		if (do_mark_busy(e820.map[i].type, res)) {
 			res->flags |= IORESOURCE_BUSY;
 			insert_resource(&iomem_resource, res);
 		}
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 3420c874ddc5..64f90f53bb85 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -1,53 +1,82 @@
 /*
  * Copyright (c) 2015, Christoph Hellwig.
+ * Copyright (c) 2015, Intel Corporation.
  */
-#include <linux/memblock.h>
 #include <linux/platform_device.h>
-#include <linux/slab.h>
+#include <linux/libnvdimm.h>
+#include <linux/module.h>
 #include <asm/e820.h>
-#include <asm/page_types.h>
-#include <asm/setup.h>
 
-static __init void register_pmem_device(struct resource *res)
+static void e820_pmem_release(struct device *dev)
 {
-	struct platform_device *pdev;
-	int error;
+	struct nvdimm_bus *nvdimm_bus = dev->platform_data;
 
-	pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO);
-	if (!pdev)
-		return;
+	if (nvdimm_bus)
+		nvdimm_bus_unregister(nvdimm_bus);
+}
 
-	error = platform_device_add_resources(pdev, res, 1);
-	if (error)
-		goto out_put_pdev;
+static struct platform_device e820_pmem = {
+	.name = "e820_pmem",
+	.id = -1,
+	.dev = {
+		.release = e820_pmem_release,
+	},
+};
 
-	error = platform_device_add(pdev);
-	if (error)
-		goto out_put_pdev;
-	return;
+static const struct attribute_group *e820_pmem_attribute_groups[] = {
+	&nvdimm_bus_attribute_group,
+	NULL,
+};
 
-out_put_pdev:
-	dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n");
-	platform_device_put(pdev);
-}
+static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
+	&nd_region_attribute_group,
+	&nd_device_attribute_group,
+	NULL,
+};
 
-static __init int register_pmem_devices(void)
+static __init int register_e820_pmem(void)
 {
-	int i;
+	static struct nvdimm_bus_descriptor nd_desc;
+	struct device *dev = &e820_pmem.dev;
+	struct nvdimm_bus *nvdimm_bus;
+	int rc, i;
+
+	rc = platform_device_register(&e820_pmem);
+	if (rc)
+		return rc;
+
+	nd_desc.attr_groups = e820_pmem_attribute_groups;
+	nd_desc.provider_name = "e820";
+	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
+	if (!nvdimm_bus)
+		goto err;
+	dev->platform_data = nvdimm_bus;
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
+		struct resource res = {
+			.flags	= IORESOURCE_MEM,
+			.start	= ei->addr,
+			.end	= ei->addr + ei->size - 1,
+		};
+		struct nd_region_desc ndr_desc;
+
+		if (ei->type != E820_PRAM)
+			continue;
 
-		if (ei->type == E820_PRAM) {
-			struct resource res = {
-				.flags	= IORESOURCE_MEM,
-				.start	= ei->addr,
-				.end	= ei->addr + ei->size - 1,
-			};
-			register_pmem_device(&res);
-		}
+		memset(&ndr_desc, 0, sizeof(ndr_desc));
+		ndr_desc.res = &res;
+		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
+		ndr_desc.numa_node = NUMA_NO_NODE;
+		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+			goto err;
 	}
 
 	return 0;
+
+ err:
+	dev_err(dev, "failed to register legacy persistent memory ranges\n");
+	platform_device_unregister(&e820_pmem);
+	return -ENXIO;
 }
-device_initcall(register_pmem_devices);
+device_initcall(register_e820_pmem);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index c1c382c58c60..cfba30f27392 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -174,6 +174,9 @@ static void __init do_add_efi_memmap(void)
 		case EFI_UNUSABLE_MEMORY:
 			e820_type = E820_UNUSABLE;
 			break;
+		case EFI_PERSISTENT_MEMORY:
+			e820_type = E820_PMEM;
+			break;
 		default:
 			/*
 			 * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE