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, 176 insertions, 156 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 117e2f373e50..cc0d73eac047 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -27,7 +27,8 @@ 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_PMEM_API		if X86_64
+	select ARCH_HAS_MMIO_FLUSH
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
@@ -1450,10 +1451,14 @@ config ILLEGAL_POINTER_VALUE
 
 source "mm/Kconfig"
 
+config X86_PMEM_LEGACY_DEVICE
+	bool
+
 config X86_PMEM_LEGACY
-	bool "Support non-standard NVDIMMs and ADR protected memory"
+	tristate "Support non-standard NVDIMMs and ADR protected memory"
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
+	select X86_PMEM_LEGACY_DEVICE
 	select LIBNVDIMM
 	help
 	  Treat memory marked using the non-standard e820 type of 12 as used
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 9bf3ea14b9f0..e63aa38e85fb 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -89,6 +89,8 @@ int set_pages_rw(struct page *page, int numpages);
 
 void clflush_cache_range(void *addr, unsigned int size);
 
+#define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
+
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
@@ -109,75 +111,4 @@ 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 7cfc085b6879..de25aad07853 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -250,12 +250,6 @@ 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/asm/pmem.h b/arch/x86/include/asm/pmem.h
new file mode 100644
index 000000000000..d8ce3ec816ab
--- /dev/null
+++ b/arch/x86/include/asm/pmem.h
@@ -0,0 +1,153 @@
+/*
+ * Copyright(c) 2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef __ASM_X86_PMEM_H__
+#define __ASM_X86_PMEM_H__
+
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/special_insns.h>
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+/**
+ * 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();
+}
+
+/**
+ * __arch_wb_cache_pmem - write back a cache range with CLWB
+ * @vaddr:	virtual start address
+ * @size:	number of bytes to write back
+ *
+ * Write back a cache range using the CLWB (cache line write back)
+ * instruction.  This function requires explicit ordering with an
+ * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ */
+static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
+{
+	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+	unsigned long clflush_mask = x86_clflush_size - 1;
+	void *vend = vaddr + size;
+	void *p;
+
+	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	     p < vend; p += x86_clflush_size)
+		clwb(p);
+}
+
+/*
+ * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
+ * iterators, so for other types (bvec & kvec) we must do a cache write-back.
+ */
+static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
+{
+	return iter_is_iovec(i) == false;
+}
+
+/**
+ * arch_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 an arch_wmb_pmem() call.
+ */
+static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	void *vaddr = (void __force *)addr;
+	size_t len;
+
+	/* TODO: skip the write-back by always using non-temporal stores */
+	len = copy_from_iter_nocache(vaddr, bytes, i);
+
+	if (__iter_needs_pmem_wb(i))
+		__arch_wb_cache_pmem(vaddr, bytes);
+
+	return len;
+}
+
+/**
+ * arch_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 an arch_wmb_pmem() call.
+ */
+static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+{
+	void *vaddr = (void __force *)addr;
+
+	/* TODO: implement the zeroing via non-temporal writes */
+	if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0)
+		clear_page(vaddr);
+	else
+		memset(vaddr, 0, size);
+
+	__arch_wb_cache_pmem(vaddr, size);
+}
+
+static inline bool __arch_has_wmb_pmem(void)
+{
+	/*
+	 * We require that wmb() be an 'sfence', that is only guaranteed on
+	 * 64-bit builds
+	 */
+	return static_cpu_has(X86_FEATURE_PCOMMIT);
+}
+#endif /* CONFIG_ARCH_HAS_PMEM_API */
+#endif /* __ASM_X86_PMEM_H__ */
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index 0f457e6eab18..9dafe59cf6e2 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -37,7 +37,7 @@
 /*
  * This is a non-standardized way to represent ADR or NVDIMM regions that
  * persist over a reboot.  The kernel will ignore their special capabilities
- * unless the CONFIG_X86_PMEM_LEGACY=y option is set.
+ * unless the CONFIG_X86_PMEM_LEGACY option is set.
  *
  * ( Note that older platforms also used 6 for the same type of memory,
  *   but newer versions switched to 12 as 6 was assigned differently.  Some
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3c3622176340..9ffdf25e5b86 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -94,7 +94,7 @@ obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
-obj-$(CONFIG_X86_PMEM_LEGACY)	+= pmem.o
+obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 64f90f53bb85..4f00b63d7ff3 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -3,80 +3,17 @@
  * Copyright (c) 2015, Intel Corporation.
  */
 #include <linux/platform_device.h>
-#include <linux/libnvdimm.h>
 #include <linux/module.h>
-#include <asm/e820.h>
-
-static void e820_pmem_release(struct device *dev)
-{
-	struct nvdimm_bus *nvdimm_bus = dev->platform_data;
-
-	if (nvdimm_bus)
-		nvdimm_bus_unregister(nvdimm_bus);
-}
-
-static struct platform_device e820_pmem = {
-	.name = "e820_pmem",
-	.id = -1,
-	.dev = {
-		.release = e820_pmem_release,
-	},
-};
-
-static const struct attribute_group *e820_pmem_attribute_groups[] = {
-	&nvdimm_bus_attribute_group,
-	NULL,
-};
-
-static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
-	&nd_region_attribute_group,
-	&nd_device_attribute_group,
-	NULL,
-};
 
 static __init int register_e820_pmem(void)
 {
-	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;
-
-		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;
+	struct platform_device *pdev;
+
+	/*
+	 * See drivers/nvdimm/e820.c for the implementation, this is
+	 * simply here to trigger the module to load on demand.
+	 */
+	pdev = platform_device_alloc("e820_pmem", -1);
+	return platform_device_add(pdev);
 }
 device_initcall(register_e820_pmem);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 68aec42545c2..7562f42914b4 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -823,11 +823,11 @@ void __init 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)
 {
 	struct pglist_data *pgdata = NODE_DATA(nid);
 	struct zone *zone = pgdata->node_zones +
-		zone_for_memory(nid, start, size, ZONE_HIGHMEM);
+		zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3fba623e3ba5..30564e2752d3 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -687,11 +687,11 @@ static void  update_end_of_memory_vars(u64 start, u64 size)
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
-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 *pgdat = NODE_DATA(nid);
 	struct zone *zone = pgdat->node_zones +
-		zone_for_memory(nid, start, size, ZONE_NORMAL);
+		zone_for_memory(nid, start, size, ZONE_NORMAL, for_device);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;