Merge tag 'libnvdimm-for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "libnvdimm updates for the latest ACPI and UEFI specifications. This
  pull request also includes new 'struct dax_operations' enabling to
  undo the abuse of copy_user_nocache() for copy operations to pmem.

  The dax work originally missed 4.12 to address concerns raised by Al.

  Summary:

   - Introduce the _flushcache() family of memory copy helpers and use
     them for persistent memory write operations on x86. The
     _flushcache() semantic indicates that the cache is either bypassed
     for the copy operation (movnt) or any lines dirtied by the copy
     operation are written back (clwb, clflushopt, or clflush).

   - Extend dax_operations with ->copy_from_iter() and ->flush()
     operations. These operations and other infrastructure updates allow
     all persistent memory specific dax functionality to be pushed into
     libnvdimm and the pmem driver directly. It also allows dax-specific
     sysfs attributes to be linked to a host device, for example:
     /sys/block/pmem0/dax/write_cache

   - Add support for the new NVDIMM platform/firmware mechanisms
     introduced in ACPI 6.2 and UEFI 2.7. This support includes the v1.2
     namespace label format, extensions to the address-range-scrub
     command set, new error injection commands, and a new BTT
     (block-translation-table) layout. These updates support inter-OS
     and pre-OS compatibility.

   - Fix a longstanding memory corruption bug in nfit_test.

   - Make the pmem and nvdimm-region 'badblocks' sysfs files poll(2)
     capable.

   - Miscellaneous fixes and small updates across libnvdimm and the nfit
     driver.

  Acknowledgements that came after the branch was pushed: commit
  6aa734a2f3 ("libnvdimm, region, pmem: fix 'badblocks'
  sysfs_get_dirent() reference lifetime") was reviewed by Toshi Kani
  <toshi.kani@hpe.com>"

* tag 'libnvdimm-for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (42 commits)
  libnvdimm, namespace: record 'lbasize' for pmem namespaces
  acpi/nfit: Issue Start ARS to retrieve existing records
  libnvdimm: New ACPI 6.2 DSM functions
  acpi, nfit: Show bus_dsm_mask in sysfs
  libnvdimm, acpi, nfit: Add bus level dsm mask for pass thru.
  acpi, nfit: Enable DSM pass thru for root functions.
  libnvdimm: passthru functions clear to send
  libnvdimm, btt: convert some info messages to warn/err
  libnvdimm, region, pmem: fix 'badblocks' sysfs_get_dirent() reference lifetime
  libnvdimm: fix the clear-error check in nsio_rw_bytes
  libnvdimm, btt: fix btt_rw_page not returning errors
  acpi, nfit: quiet invalid block-aperture-region warnings
  libnvdimm, btt: BTT updates for UEFI 2.7 format
  acpi, nfit: constify *_attribute_group
  libnvdimm, pmem: disable dax flushing when pmem is fronting a volatile region
  libnvdimm, pmem, dax: export a cache control attribute
  dax: convert to bitmask for flags
  dax: remove default copy_from_iter fallback
  libnvdimm, nfit: enable support for volatile ranges
  libnvdimm, pmem: fix persistence warning
  ...

MAINTAINERS

@@ -7680,9 +7680,7 @@ M:	Ross Zwisler <ross.zwisler@linux.intel.com>
 L:	linux-nvdimm@lists.01.org
 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
+F:	drivers/nvdimm/pmem*
 
 LIGHTNVM PLATFORM SUPPORT
 M:	Matias Bjorling <mb@lightnvm.io>

arch/powerpc/sysdev/axonram.c

@@ -45,6 +45,7 @@
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
 #include <linux/pfn_t.h>
+#include <linux/uio.h>
 
 #include <asm/page.h>
 #include <asm/prom.h>
@@ -163,8 +164,15 @@ axon_ram_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pa
 	return __axon_ram_direct_access(bank, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t axon_ram_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter(addr, bytes, i);
+}
+
 static const struct dax_operations axon_ram_dax_ops = {
 	.direct_access = axon_ram_dax_direct_access,
+	.copy_from_iter = axon_ram_copy_from_iter,
 };
 
 /**

arch/x86/Kconfig

@@ -54,6 +54,7 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MMIO_FLUSH
 	select ARCH_HAS_PMEM_API		if X86_64
+	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX

arch/x86/include/asm/pmem.h

@@ -1,136 +0,0 @@
-/*
- * 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 pmem driver flush operation will drain posted write queues.
- */
-static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
-{
-	int rem;
-
-	/*
-	 * 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.
-	 */
-	rem = __copy_from_user_inatomic_nocache(dst, (void __user *) src, n);
-	if (WARN(rem, "%s: fault copying %p <- %p unwritten: %d\n",
-				__func__, dst, src, rem))
-		BUG();
-}
-
-/**
- * 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. Note that @size is internally rounded up to be cache
- * line size aligned.
- */
-static inline void arch_wb_cache_pmem(void *addr, size_t size)
-{
-	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
-	unsigned long clflush_mask = x86_clflush_size - 1;
-	void *vend = addr + size;
-	void *p;
-
-	for (p = (void *)((unsigned long)addr & ~clflush_mask);
-	     p < vend; p += x86_clflush_size)
-		clwb(p);
-}
-
-/**
- * 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'.
- */
-static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
-		struct iov_iter *i)
-{
-	size_t len;
-
-	/* TODO: skip the write-back by always using non-temporal stores */
-	len = copy_from_iter_nocache(addr, bytes, i);
-
-	/*
-	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
-	 * non-temporal stores for the bulk of the transfer, but we need
-	 * to manually flush if the transfer is unaligned. A cached
-	 * memory copy is used when destination or size is not naturally
-	 * aligned. That is:
-	 *   - Require 8-byte alignment when size is 8 bytes or larger.
-	 *   - Require 4-byte alignment when size is 4 bytes.
-	 *
-	 * In the non-iovec case the entire destination needs to be
-	 * flushed.
-	 */
-	if (iter_is_iovec(i)) {
-		unsigned long flushed, dest = (unsigned long) addr;
-
-		if (bytes < 8) {
-			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
-				arch_wb_cache_pmem(addr, bytes);
-		} else {
-			if (!IS_ALIGNED(dest, 8)) {
-				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
-				arch_wb_cache_pmem(addr, 1);
-			}
-
-			flushed = dest - (unsigned long) addr;
-			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
-				arch_wb_cache_pmem(addr + bytes - 1, 1);
-		}
-	} else
-		arch_wb_cache_pmem(addr, 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.
- */
-static inline void arch_clear_pmem(void *addr, size_t size)
-{
-	memset(addr, 0, size);
-	arch_wb_cache_pmem(addr, size);
-}
-
-static inline void arch_invalidate_pmem(void *addr, size_t size)
-{
-	clflush_cache_range(addr, size);
-}
-#endif /* CONFIG_ARCH_HAS_PMEM_API */
-#endif /* __ASM_X86_PMEM_H__ */

arch/x86/include/asm/string_64.h

@@ -109,6 +109,11 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt)
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+#define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
+void memcpy_flushcache(void *dst, const void *src, size_t cnt);
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_STRING_64_H */

arch/x86/include/asm/uaccess_64.h

@@ -171,6 +171,10 @@ unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigne
 extern long __copy_user_nocache(void *dst, const void __user *src,
 				unsigned size, int zerorest);
 
+extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
+extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
+			   size_t len);
+
 static inline int
 __copy_from_user_inatomic_nocache(void *dst, const void __user *src,
 				  unsigned size)
@@ -179,6 +183,13 @@ __copy_from_user_inatomic_nocache(void *dst, const void __user *src,
 	return __copy_user_nocache(dst, src, size, 0);
 }
 
+static inline int
+__copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
+{
+	kasan_check_write(dst, size);
+	return __copy_user_flushcache(dst, src, size);
+}
+
 unsigned long
 copy_user_handle_tail(char *to, char *from, unsigned len);
 

arch/x86/lib/usercopy_64.c

@@ -7,6 +7,7 @@
  */
 #include <linux/export.h>
 #include <linux/uaccess.h>
+#include <linux/highmem.h>
 
 /*
  * Zero Userspace
@@ -73,3 +74,136 @@ copy_user_handle_tail(char *to, char *from, unsigned len)
 	clac();
 	return len;
 }
+
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * clean_cache_range - 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. Note that @size is internally rounded up to be cache
+ * line size aligned.
+ */
+static void clean_cache_range(void *addr, size_t size)
+{
+	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+	unsigned long clflush_mask = x86_clflush_size - 1;
+	void *vend = addr + size;
+	void *p;
+
+	for (p = (void *)((unsigned long)addr & ~clflush_mask);
+	     p < vend; p += x86_clflush_size)
+		clwb(p);
+}
+
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	clean_cache_range(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
+{
+	unsigned long flushed, dest = (unsigned long) dst;
+	long rc = __copy_user_nocache(dst, src, size, 0);
+
+	/*
+	 * __copy_user_nocache() uses non-temporal stores for the bulk
+	 * of the transfer, but we need to manually flush if the
+	 * transfer is unaligned. A cached memory copy is used when
+	 * destination or size is not naturally aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 */
+	if (size < 8) {
+		if (!IS_ALIGNED(dest, 4) || size != 4)
+			clean_cache_range(dst, 1);
+	} else {
+		if (!IS_ALIGNED(dest, 8)) {
+			dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+			clean_cache_range(dst, 1);
+		}
+
+		flushed = dest - (unsigned long) dst;
+		if (size > flushed && !IS_ALIGNED(size - flushed, 8))
+			clean_cache_range(dst + size - 1, 1);
+	}
+
+	return rc;
+}
+
+void memcpy_flushcache(void *_dst, const void *_src, size_t size)
+{
+	unsigned long dest = (unsigned long) _dst;
+	unsigned long source = (unsigned long) _src;
+
+	/* cache copy and flush to align dest */
+	if (!IS_ALIGNED(dest, 8)) {
+		unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest);
+
+		memcpy((void *) dest, (void *) source, len);
+		clean_cache_range((void *) dest, len);
+		dest += len;
+		source += len;
+		size -= len;
+		if (!size)
+			return;
+	}
+
+	/* 4x8 movnti loop */
+	while (size >= 32) {
+		asm("movq    (%0), %%r8\n"
+		    "movq   8(%0), %%r9\n"
+		    "movq  16(%0), %%r10\n"
+		    "movq  24(%0), %%r11\n"
+		    "movnti  %%r8,   (%1)\n"
+		    "movnti  %%r9,  8(%1)\n"
+		    "movnti %%r10, 16(%1)\n"
+		    "movnti %%r11, 24(%1)\n"
+		    :: "r" (source), "r" (dest)
+		    : "memory", "r8", "r9", "r10", "r11");
+		dest += 32;
+		source += 32;
+		size -= 32;
+	}
+
+	/* 1x8 movnti loop */
+	while (size >= 8) {
+		asm("movq    (%0), %%r8\n"
+		    "movnti  %%r8,   (%1)\n"
+		    :: "r" (source), "r" (dest)
+		    : "memory", "r8");
+		dest += 8;
+		source += 8;
+		size -= 8;
+	}
+
+	/* 1x4 movnti loop */
+	while (size >= 4) {
+		asm("movl    (%0), %%r8d\n"
+		    "movnti  %%r8d,   (%1)\n"
+		    :: "r" (source), "r" (dest)
+		    : "memory", "r8");
+		dest += 4;
+		source += 4;
+		size -= 4;
+	}
+
+	/* cache copy for remaining bytes */
+	if (size) {
+		memcpy((void *) dest, (void *) source, size);
+		clean_cache_range((void *) dest, size);
+	}
+}
+EXPORT_SYMBOL_GPL(memcpy_flushcache);
+
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
+		size_t len)
+{
+	char *from = kmap_atomic(page);
+
+	memcpy_flushcache(to, from + offset, len);
+	kunmap_atomic(from);
+}
+#endif

arch/x86/mm/pageattr.c

@@ -150,6 +150,12 @@ void clflush_cache_range(void *vaddr, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(clflush_cache_range);
 
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	clflush_cache_range(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+
 static void __cpa_flush_all(void *arg)
 {
 	unsigned long cache = (unsigned long)arg;

drivers/acpi/nfit/core.c

@@ -20,7 +20,6 @@
 #include <linux/list.h>
 #include <linux/acpi.h>
 #include <linux/sort.h>
-#include <linux/pmem.h>
 #include <linux/io.h>
 #include <linux/nd.h>
 #include <asm/cacheflush.h>
@@ -253,6 +252,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		cmd_name = nvdimm_bus_cmd_name(cmd);
 		cmd_mask = nd_desc->cmd_mask;
 		dsm_mask = cmd_mask;
+		if (cmd == ND_CMD_CALL)
+			dsm_mask = nd_desc->bus_dsm_mask;
 		desc = nd_cmd_bus_desc(cmd);
 		guid = to_nfit_uuid(NFIT_DEV_BUS);
 		handle = adev->handle;
@@ -927,6 +928,17 @@ static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc)
 	return 0;
 }
 
+static ssize_t bus_dsm_mask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+
+	return sprintf(buf, "%#lx\n", nd_desc->bus_dsm_mask);
+}
+static struct device_attribute dev_attr_bus_dsm_mask =
+		__ATTR(dsm_mask, 0444, bus_dsm_mask_show, NULL);
+
 static ssize_t revision_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -1031,7 +1043,7 @@ static ssize_t scrub_store(struct device *dev,
 	if (nd_desc) {
 		struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-		rc = acpi_nfit_ars_rescan(acpi_desc);
+		rc = acpi_nfit_ars_rescan(acpi_desc, 0);
 	}
 	device_unlock(dev);
 	if (rc)
@@ -1063,10 +1075,11 @@ static struct attribute *acpi_nfit_attributes[] = {
 	&dev_attr_revision.attr,
 	&dev_attr_scrub.attr,
 	&dev_attr_hw_error_scrub.attr,
+	&dev_attr_bus_dsm_mask.attr,
 	NULL,
 };
 
-static struct attribute_group acpi_nfit_attribute_group = {
+static const struct attribute_group acpi_nfit_attribute_group = {
 	.name = "nfit",
 	.attrs = acpi_nfit_attributes,
 	.is_visible = nfit_visible,
@@ -1346,7 +1359,7 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-static struct attribute_group acpi_nfit_dimm_attribute_group = {
+static const struct attribute_group acpi_nfit_dimm_attribute_group = {
 	.name = "nfit",
 	.attrs = acpi_nfit_dimm_attributes,
 	.is_visible = acpi_nfit_dimm_attr_visible,
@@ -1608,11 +1621,23 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 			acpi_desc);
 }
 
+/*
+ * These constants are private because there are no kernel consumers of
+ * these commands.
+ */
+enum nfit_aux_cmds {
+        NFIT_CMD_TRANSLATE_SPA = 5,
+        NFIT_CMD_ARS_INJECT_SET = 7,
+        NFIT_CMD_ARS_INJECT_CLEAR = 8,
+        NFIT_CMD_ARS_INJECT_GET = 9,
+};
+
 static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 {
 	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
 	const guid_t *guid = to_nfit_uuid(NFIT_DEV_BUS);
 	struct acpi_device *adev;
+	unsigned long dsm_mask;
 	int i;
 
 	nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en;
@@ -1623,6 +1648,20 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	for (i = ND_CMD_ARS_CAP; i <= ND_CMD_CLEAR_ERROR; i++)
 		if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i))
 			set_bit(i, &nd_desc->cmd_mask);
+	set_bit(ND_CMD_CALL, &nd_desc->cmd_mask);
+
+	dsm_mask =
+		(1 << ND_CMD_ARS_CAP) |
+		(1 << ND_CMD_ARS_START) |
+		(1 << ND_CMD_ARS_STATUS) |
+		(1 << ND_CMD_CLEAR_ERROR) |
+		(1 << NFIT_CMD_TRANSLATE_SPA) |
+		(1 << NFIT_CMD_ARS_INJECT_SET) |
+		(1 << NFIT_CMD_ARS_INJECT_CLEAR) |
+		(1 << NFIT_CMD_ARS_INJECT_GET);
+	for_each_set_bit(i, &dsm_mask, BITS_PER_LONG)
+		if (acpi_check_dsm(adev->handle, guid, 1, 1ULL << i))
+			set_bit(i, &nd_desc->bus_dsm_mask);
 }
 
 static ssize_t range_index_show(struct device *dev,
@@ -1640,7 +1679,7 @@ static struct attribute *acpi_nfit_region_attributes[] = {
 	NULL,
 };
 
-static struct attribute_group acpi_nfit_region_attribute_group = {
+static const struct attribute_group acpi_nfit_region_attribute_group = {
 	.name = "nfit",
 	.attrs = acpi_nfit_region_attributes,
 };
@@ -1663,12 +1702,29 @@ struct nfit_set_info {
 	} mapping[0];
 };
 
+struct nfit_set_info2 {
+	struct nfit_set_info_map2 {
+		u64 region_offset;
+		u32 serial_number;
+		u16 vendor_id;
+		u16 manufacturing_date;
+		u8  manufacturing_location;
+		u8  reserved[31];
+	} mapping[0];
+};
+
 static size_t sizeof_nfit_set_info(int num_mappings)
 {
 	return sizeof(struct nfit_set_info)
 		+ num_mappings * sizeof(struct nfit_set_info_map);
 }
 
+static size_t sizeof_nfit_set_info2(int num_mappings)
+{
+	return sizeof(struct nfit_set_info2)
+		+ num_mappings * sizeof(struct nfit_set_info_map2);
+}
+
 static int cmp_map_compat(const void *m0, const void *m1)
 {
 	const struct nfit_set_info_map *map0 = m0;
@@ -1690,6 +1746,18 @@ static int cmp_map(const void *m0, const void *m1)
 	return 0;
 }
 
+static int cmp_map2(const void *m0, const void *m1)
+{
+	const struct nfit_set_info_map2 *map0 = m0;
+	const struct nfit_set_info_map2 *map1 = m1;
+
+	if (map0->region_offset < map1->region_offset)
+		return -1;
+	else if (map0->region_offset > map1->region_offset)
+		return 1;
+	return 0;
+}
+
 /* Retrieve the nth entry referencing this spa */
 static struct acpi_nfit_memory_map *memdev_from_spa(
 		struct acpi_nfit_desc *acpi_desc, u16 range_index, int n)
@@ -1707,27 +1775,31 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 		struct nd_region_desc *ndr_desc,
 		struct acpi_nfit_system_address *spa)
 {
-	int i, spa_type = nfit_spa_type(spa);
 	struct device *dev = acpi_desc->dev;
 	struct nd_interleave_set *nd_set;
 	u16 nr = ndr_desc->num_mappings;
+	struct nfit_set_info2 *info2;
 	struct nfit_set_info *info;
-
-	if (spa_type == NFIT_SPA_PM || spa_type == NFIT_SPA_VOLATILE)
-		/* pass */;
-	else
-		return 0;
+	int i;
 
 	nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL);
 	if (!nd_set)
 		return -ENOMEM;
+	ndr_desc->nd_set = nd_set;
+	guid_copy(&nd_set->type_guid, (guid_t *) spa->range_guid);
 
 	info = devm_kzalloc(dev, sizeof_nfit_set_info(nr), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
+
+	info2 = devm_kzalloc(dev, sizeof_nfit_set_info2(nr), GFP_KERNEL);
+	if (!info2)
+		return -ENOMEM;
+
 	for (i = 0; i < nr; i++) {
 		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
 		struct nfit_set_info_map *map = &info->mapping[i];
+		struct nfit_set_info_map2 *map2 = &info2->mapping[i];
 		struct nvdimm *nvdimm = mapping->nvdimm;
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 		struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc,
@@ -1740,19 +1812,32 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 
 		map->region_offset = memdev->region_offset;
 		map->serial_number = nfit_mem->dcr->serial_number;
+
+		map2->region_offset = memdev->region_offset;
+		map2->serial_number = nfit_mem->dcr->serial_number;
+		map2->vendor_id = nfit_mem->dcr->vendor_id;
+		map2->manufacturing_date = nfit_mem->dcr->manufacturing_date;
+		map2->manufacturing_location = nfit_mem->dcr->manufacturing_location;
 	}
 
+	/* v1.1 namespaces */
 	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
 			cmp_map, NULL);
-	nd_set->cookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
+	nd_set->cookie1 = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
 
-	/* support namespaces created with the wrong sort order */
+	/* v1.2 namespaces */
+	sort(&info2->mapping[0], nr, sizeof(struct nfit_set_info_map2),
+			cmp_map2, NULL);
+	nd_set->cookie2 = nd_fletcher64(info2, sizeof_nfit_set_info2(nr), 0);
+
+	/* support v1.1 namespaces created with the wrong sort order */
 	sort(&info->mapping[0], nr, sizeof(struct nfit_set_info_map),
 			cmp_map_compat, NULL);
 	nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
 
 	ndr_desc->nd_set = nd_set;
 	devm_kfree(dev, info);
+	devm_kfree(dev, info2);
 
 	return 0;
 }
@@ -1842,8 +1927,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 		}
 
 		if (rw)
-			memcpy_to_pmem(mmio->addr.aperture + offset,
-					iobuf + copied, c);
+			memcpy_flushcache(mmio->addr.aperture + offset, iobuf + copied, c);
 		else {
 			if (nfit_blk->dimm_flags & NFIT_BLK_READ_FLUSH)
 				mmio_flush_range((void __force *)
@@ -1957,7 +2041,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
 	mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address,
-                        nfit_mem->spa_bdw->length, ARCH_MEMREMAP_PMEM);
+                        nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
 	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
@@ -2051,6 +2135,7 @@ static int ars_start(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa
 	memset(&ars_start, 0, sizeof(ars_start));
 	ars_start.address = spa->address;
 	ars_start.length = spa->length;
+	ars_start.flags = acpi_desc->ars_start_flags;
 	if (nfit_spa_type(spa) == NFIT_SPA_PM)
 		ars_start.type = ND_ARS_PERSISTENT;
 	else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE)
@@ -2077,6 +2162,7 @@ static int ars_continue(struct acpi_nfit_desc *acpi_desc)
 	ars_start.address = ars_status->restart_address;
 	ars_start.length = ars_status->restart_length;
 	ars_start.type = ars_status->type;
+	ars_start.flags = acpi_desc->ars_start_flags;
 	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, &ars_start,
 			sizeof(ars_start), &cmd_rc);
 	if (rc < 0)
@@ -2179,7 +2265,7 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 	struct acpi_nfit_system_address *spa = nfit_spa->spa;
 	struct nd_blk_region_desc *ndbr_desc;
 	struct nfit_mem *nfit_mem;
-	int blk_valid = 0;
+	int blk_valid = 0, rc;
 
 	if (!nvdimm) {
 		dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n",
@@ -2211,6 +2297,9 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		ndbr_desc = to_blk_region_desc(ndr_desc);
 		ndbr_desc->enable = acpi_nfit_blk_region_enable;
 		ndbr_desc->do_io = acpi_desc->blk_do_io;
+		rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa);
+		if (rc)
+			return rc;
 		nfit_spa->nd_region = nvdimm_blk_region_create(acpi_desc->nvdimm_bus,
 				ndr_desc);
 		if (!nfit_spa->nd_region)
@@ -2229,6 +2318,13 @@ static bool nfit_spa_is_virtual(struct acpi_nfit_system_address *spa)
 		nfit_spa_type(spa) == NFIT_SPA_PCD);
 }
 
+static bool nfit_spa_is_volatile(struct acpi_nfit_system_address *spa)
+{
+	return (nfit_spa_type(spa) == NFIT_SPA_VDISK ||
+		nfit_spa_type(spa) == NFIT_SPA_VCD   ||
+		nfit_spa_type(spa) == NFIT_SPA_VOLATILE);
+}
+
 static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_spa *nfit_spa)
 {
@@ -2303,7 +2399,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 				ndr_desc);
 		if (!nfit_spa->nd_region)
 			rc = -ENOMEM;
-	} else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) {
+	} else if (nfit_spa_is_volatile(spa)) {
 		nfit_spa->nd_region = nvdimm_volatile_region_create(nvdimm_bus,
 				ndr_desc);
 		if (!nfit_spa->nd_region)
@@ -2595,6 +2691,7 @@ static void acpi_nfit_scrub(struct work_struct *work)
 	list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
 		acpi_nfit_async_scrub(acpi_desc, nfit_spa);
 	acpi_desc->scrub_count++;
+	acpi_desc->ars_start_flags = 0;
 	if (acpi_desc->scrub_count_state)
 		sysfs_notify_dirent(acpi_desc->scrub_count_state);
 	mutex_unlock(&acpi_desc->init_mutex);
@@ -2613,6 +2710,7 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
 				return rc;
 		}
 
+	acpi_desc->ars_start_flags = 0;
 	if (!acpi_desc->cancel)
 		queue_work(nfit_wq, &acpi_desc->work);
 	return 0;
@@ -2817,7 +2915,7 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
 	return 0;
 }
 
-int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
+int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, u8 flags)
 {
 	struct device *dev = acpi_desc->dev;
 	struct nfit_spa *nfit_spa;
@@ -2839,6 +2937,7 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
 
 		nfit_spa->ars_required = 1;
 	}
+	acpi_desc->ars_start_flags = flags;
 	queue_work(nfit_wq, &acpi_desc->work);
 	dev_dbg(dev, "%s: ars_scan triggered\n", __func__);
 	mutex_unlock(&acpi_desc->init_mutex);
@@ -2967,7 +3066,7 @@ static int acpi_nfit_remove(struct acpi_device *adev)
 	return 0;
 }
 
-void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event)
+static void acpi_nfit_update_notify(struct device *dev, acpi_handle handle)
 {
 	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(dev);
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -2975,11 +3074,6 @@ void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event)
 	acpi_status status;
 	int ret;
 
-	dev_dbg(dev, "%s: event: %d\n", __func__, event);
-
-	if (event != NFIT_NOTIFY_UPDATE)
-		return;
-
 	if (!dev->driver) {
 		/* dev->driver may be null if we're being removed */
 		dev_dbg(dev, "%s: no driver found for dev\n", __func__);
@@ -3016,6 +3110,29 @@ void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event)
 		dev_err(dev, "Invalid _FIT\n");
 	kfree(buf.pointer);
 }
+
+static void acpi_nfit_uc_error_notify(struct device *dev, acpi_handle handle)
+{
+	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(dev);
+	u8 flags = (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) ?
+			0 : ND_ARS_RETURN_PREV_DATA;
+
+	acpi_nfit_ars_rescan(acpi_desc, flags);
+}
+
+void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event)
+{
+	dev_dbg(dev, "%s: event: 0x%x\n", __func__, event);
+
+	switch (event) {
+	case NFIT_NOTIFY_UPDATE:
+		return acpi_nfit_update_notify(dev, handle);
+	case NFIT_NOTIFY_UC_MEMORY_ERROR:
+		return acpi_nfit_uc_error_notify(dev, handle);
+	default:
+		return;
+	}
+}
 EXPORT_SYMBOL_GPL(__acpi_nfit_notify);
 
 static void acpi_nfit_notify(struct acpi_device *adev, u32 event)

drivers/acpi/nfit/mce.c

@@ -79,7 +79,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 			 * already in progress, just let that be the last
 			 * authoritative one
 			 */
-			acpi_nfit_ars_rescan(acpi_desc);
+			acpi_nfit_ars_rescan(acpi_desc, 0);
 		}
 		break;
 	}

drivers/acpi/nfit/nfit.h

@@ -79,6 +79,7 @@ enum {
 
 enum nfit_root_notifiers {
 	NFIT_NOTIFY_UPDATE = 0x80,
+	NFIT_NOTIFY_UC_MEMORY_ERROR = 0x81,
 };
 
 enum nfit_dimm_notifiers {
@@ -154,6 +155,7 @@ struct acpi_nfit_desc {
 	struct list_head idts;
 	struct nvdimm_bus *nvdimm_bus;
 	struct device *dev;
+	u8 ars_start_flags;
 	struct nd_cmd_ars_status *ars_status;
 	size_t ars_status_size;
 	struct work_struct work;
@@ -206,7 +208,7 @@ struct nfit_blk {
 
 extern struct list_head acpi_descs;
 extern struct mutex acpi_desc_lock;
-int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc);
+int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, u8 flags);
 
 #ifdef CONFIG_X86_MCE
 void nfit_mce_register(void);

drivers/block/brd.c

@@ -22,6 +22,7 @@
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 #include <linux/pfn_t.h>
 #include <linux/dax.h>
+#include <linux/uio.h>
 #endif
 
 #include <linux/uaccess.h>
@@ -354,8 +355,15 @@ static long brd_dax_direct_access(struct dax_device *dax_dev,
 	return __brd_direct_access(brd, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t brd_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter(addr, bytes, i);
+}
+
 static const struct dax_operations brd_dax_ops = {
 	.direct_access = brd_dax_direct_access,
+	.copy_from_iter = brd_dax_copy_from_iter,
 };
 #endif
 

drivers/dax/super.c

@@ -18,6 +18,7 @@
 #include <linux/cdev.h>
 #include <linux/hash.h>
 #include <linux/slab.h>
+#include <linux/uio.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
 
@@ -115,13 +116,20 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 EXPORT_SYMBOL_GPL(__bdev_dax_supported);
 #endif
 
+enum dax_device_flags {
+	/* !alive + rcu grace period == no new operations / mappings */
+	DAXDEV_ALIVE,
+	/* gate whether dax_flush() calls the low level flush routine */
+	DAXDEV_WRITE_CACHE,
+};
+
 /**
  * struct dax_device - anchor object for dax services
  * @inode: core vfs
  * @cdev: optional character interface for "device dax"
  * @host: optional name for lookups where the device path is not available
  * @private: dax driver private data
- * @alive: !alive + rcu grace period == no new operations / mappings
+ * @flags: state and boolean properties
  */
 struct dax_device {
 	struct hlist_node list;
@@ -129,10 +137,75 @@ struct dax_device {
 	struct cdev cdev;
 	const char *host;
 	void *private;
-	bool alive;
+	unsigned long flags;
 	const struct dax_operations *ops;
 };
 
+static ssize_t write_cache_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+	ssize_t rc;
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return -ENXIO;
+
+	rc = sprintf(buf, "%d\n", !!test_bit(DAXDEV_WRITE_CACHE,
+				&dax_dev->flags));
+	put_dax(dax_dev);
+	return rc;
+}
+
+static ssize_t write_cache_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	bool write_cache;
+	int rc = strtobool(buf, &write_cache);
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return -ENXIO;
+
+	if (rc)
+		len = rc;
+	else if (write_cache)
+		set_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+	else
+		clear_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+
+	put_dax(dax_dev);
+	return len;
+}
+static DEVICE_ATTR_RW(write_cache);
+
+static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return 0;
+
+	if (a == &dev_attr_write_cache.attr && !dax_dev->ops->flush)
+		return 0;
+	return a->mode;
+}
+
+static struct attribute *dax_attributes[] = {
+	&dev_attr_write_cache.attr,
+	NULL,
+};
+
+struct attribute_group dax_attribute_group = {
+	.name = "dax",
+	.attrs = dax_attributes,
+	.is_visible = dax_visible,
+};
+EXPORT_SYMBOL_GPL(dax_attribute_group);
+
 /**
  * dax_direct_access() - translate a device pgoff to an absolute pfn
  * @dax_dev: a dax_device instance representing the logical memory range
@@ -172,10 +245,43 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 }
 EXPORT_SYMBOL_GPL(dax_direct_access);
 
+size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	if (!dax_alive(dax_dev))
+		return 0;
+
+	return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_from_iter);
+
+void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	if (!dax_alive(dax_dev))
+		return;
+
+	if (!test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags))
+		return;
+
+	if (dax_dev->ops->flush)
+		dax_dev->ops->flush(dax_dev, pgoff, addr, size);
+}
+EXPORT_SYMBOL_GPL(dax_flush);
+
+void dax_write_cache(struct dax_device *dax_dev, bool wc)
+{
+	if (wc)
+		set_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+	else
+		clear_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(dax_write_cache);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);
-	return dax_dev->alive;
+	return test_bit(DAXDEV_ALIVE, &dax_dev->flags);
 }
 EXPORT_SYMBOL_GPL(dax_alive);
 
@@ -195,7 +301,7 @@ void kill_dax(struct dax_device *dax_dev)
 	if (!dax_dev)
 		return;
 
-	dax_dev->alive = false;
+	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
 
 	synchronize_srcu(&dax_srcu);
 
@@ -239,7 +345,7 @@ static void dax_destroy_inode(struct inode *inode)
 {
 	struct dax_device *dax_dev = to_dax_dev(inode);
 
-	WARN_ONCE(dax_dev->alive,
+	WARN_ONCE(test_bit(DAXDEV_ALIVE, &dax_dev->flags),
 			"kill_dax() must be called before final iput()\n");
 	call_rcu(&inode->i_rcu, dax_i_callback);
 }
@@ -291,7 +397,7 @@ static struct dax_device *dax_dev_get(dev_t devt)
 
 	dax_dev = to_dax_dev(inode);
 	if (inode->i_state & I_NEW) {
-		dax_dev->alive = true;
+		set_bit(DAXDEV_ALIVE, &dax_dev->flags);
 		inode->i_cdev = &dax_dev->cdev;
 		inode->i_mode = S_IFCHR;
 		inode->i_flags = S_DAX;

drivers/md/dm-linear.c

@@ -170,6 +170,34 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct dax_device *dax_dev = lc->dev->dax_dev;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+
+	dev_sector = linear_map_sector(ti, sector);
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
+static void linear_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct dax_device *dax_dev = lc->dev->dax_dev;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+
+	dev_sector = linear_map_sector(ti, sector);
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff))
+		return;
+	dax_flush(dax_dev, pgoff, addr, size);
+}
+
 static struct target_type linear_target = {
 	.name   = "linear",
 	.version = {1, 4, 0},
@@ -183,6 +211,8 @@ static struct target_type linear_target = {
 	.prepare_ioctl = linear_prepare_ioctl,
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
+	.dax_copy_from_iter = linear_dax_copy_from_iter,
+	.dax_flush = linear_dax_flush,
 };
 
 int __init dm_linear_init(void)

drivers/md/dm-stripe.c

@@ -332,6 +332,44 @@ static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct stripe_c *sc = ti->private;
+	struct dax_device *dax_dev;
+	struct block_device *bdev;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	dax_dev = sc->stripe[stripe].dev->dax_dev;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
+static void stripe_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct stripe_c *sc = ti->private;
+	struct dax_device *dax_dev;
+	struct block_device *bdev;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	dax_dev = sc->stripe[stripe].dev->dax_dev;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff))
+		return;
+	dax_flush(dax_dev, pgoff, addr, size);
+}
+
 /*
  * Stripe status:
  *
@@ -452,6 +490,8 @@ static struct target_type stripe_target = {
 	.iterate_devices = stripe_iterate_devices,
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
+	.dax_copy_from_iter = stripe_dax_copy_from_iter,
+	.dax_flush = stripe_dax_flush,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm.c

@@ -19,6 +19,7 @@
 #include <linux/dax.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/uio.h>
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
@@ -972,6 +973,48 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	long ret = 0;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (!ti->type->dax_copy_from_iter) {
+		ret = copy_from_iter(addr, bytes, i);
+		goto out;
+	}
+	ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i);
+ out:
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
+static void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (ti->type->dax_flush)
+		ti->type->dax_flush(ti, pgoff, addr, size);
+ out:
+	dm_put_live_table(md, srcu_idx);
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH.
@@ -2958,6 +3001,8 @@ static const struct block_device_operations dm_blk_dops = {
 
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
+	.copy_from_iter = dm_dax_copy_from_iter,
+	.flush = dm_dax_flush,
 };
 
 /*

drivers/nvdimm/btt.c

@@ -37,8 +37,8 @@ static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
 	struct nd_btt *nd_btt = arena->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
-	/* arena offsets are 4K from the base of the device */
-	offset += SZ_4K;
+	/* arena offsets may be shifted from the base of the device */
+	offset += arena->nd_btt->initial_offset;
 	return nvdimm_read_bytes(ndns, offset, buf, n, flags);
 }
 
@@ -48,8 +48,8 @@ static int arena_write_bytes(struct arena_info *arena, resource_size_t offset,
 	struct nd_btt *nd_btt = arena->nd_btt;
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
-	/* arena offsets are 4K from the base of the device */
-	offset += SZ_4K;
+	/* arena offsets may be shifted from the base of the device */
+	offset += arena->nd_btt->initial_offset;
 	return nvdimm_write_bytes(ndns, offset, buf, n, flags);
 }
 
@@ -323,7 +323,7 @@ static int btt_log_read(struct arena_info *arena, u32 lane,
 
 	old_ent = btt_log_get_old(log);
 	if (old_ent < 0 || old_ent > 1) {
-		dev_info(to_dev(arena),
+		dev_err(to_dev(arena),
 				"log corruption (%d): lane %d seq [%d, %d]\n",
 			old_ent, lane, log[0].seq, log[1].seq);
 		/* TODO set error state? */
@@ -576,8 +576,8 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size,
 	arena->internal_lbasize = roundup(arena->external_lbasize,
 					INT_LBASIZE_ALIGNMENT);
 	arena->nfree = BTT_DEFAULT_NFREE;
-	arena->version_major = 1;
-	arena->version_minor = 1;
+	arena->version_major = btt->nd_btt->version_major;
+	arena->version_minor = btt->nd_btt->version_minor;
 
 	if (available % BTT_PG_SIZE)
 		available -= (available % BTT_PG_SIZE);
@@ -684,7 +684,7 @@ static int discover_arenas(struct btt *btt)
 				dev_info(to_dev(arena), "No existing arenas\n");
 				goto out;
 			} else {
-				dev_info(to_dev(arena),
+				dev_err(to_dev(arena),
 						"Found corrupted metadata!\n");
 				ret = -ENODEV;
 				goto out;
@@ -1227,7 +1227,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
 				  op_is_write(bio_op(bio)), iter.bi_sector);
 		if (err) {
-			dev_info(&btt->nd_btt->dev,
+			dev_err(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
 					(op_is_write(bio_op(bio))) ? "WRITE" :
 					"READ",
@@ -1248,10 +1248,13 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector,
 		struct page *page, bool is_write)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
+	int rc;
 
-	btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, 0);
-	return 0;
+	rc = btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector);
+	if (rc == 0)
+		page_endio(page, is_write, 0);
+
+	return rc;
 }
 
 
@@ -1369,7 +1372,7 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 	}
 
 	if (btt->init_state != INIT_READY && nd_region->ro) {
-		dev_info(dev, "%s is read-only, unable to init btt metadata\n",
+		dev_warn(dev, "%s is read-only, unable to init btt metadata\n",
 				dev_name(&nd_region->dev));
 		return NULL;
 	} else if (btt->init_state != INIT_READY) {
@@ -1424,6 +1427,7 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 {
 	struct nd_btt *nd_btt = to_nd_btt(ndns->claim);
 	struct nd_region *nd_region;
+	struct btt_sb *btt_sb;
 	struct btt *btt;
 	size_t rawsize;
 
@@ -1432,10 +1436,21 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 		return -ENODEV;
 	}
 
-	rawsize = nvdimm_namespace_capacity(ndns) - SZ_4K;
+	btt_sb = devm_kzalloc(&nd_btt->dev, sizeof(*btt_sb), GFP_KERNEL);
+
+	/*
+	 * If this returns < 0, that is ok as it just means there wasn't
+	 * an existing BTT, and we're creating a new one. We still need to
+	 * call this as we need the version dependent fields in nd_btt to be
+	 * set correctly based on the holder class
+	 */
+	nd_btt_version(nd_btt, ndns, btt_sb);
+
+	rawsize = nvdimm_namespace_capacity(ndns) - nd_btt->initial_offset;
 	if (rawsize < ARENA_MIN_SIZE) {
 		dev_dbg(&nd_btt->dev, "%s must be at least %ld bytes\n",
-				dev_name(&ndns->dev), ARENA_MIN_SIZE + SZ_4K);
+				dev_name(&ndns->dev),
+				ARENA_MIN_SIZE + nd_btt->initial_offset);
 		return -ENXIO;
 	}
 	nd_region = to_nd_region(nd_btt->dev.parent);

drivers/nvdimm/btt.h

@@ -184,5 +184,7 @@ struct btt {
 };
 
 bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super);
+int nd_btt_version(struct nd_btt *nd_btt, struct nd_namespace_common *ndns,
+		struct btt_sb *btt_sb);
 
 #endif

drivers/nvdimm/btt_devs.c

@@ -260,20 +260,55 @@ bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
 }
 EXPORT_SYMBOL(nd_btt_arena_is_valid);
 
+int nd_btt_version(struct nd_btt *nd_btt, struct nd_namespace_common *ndns,
+		struct btt_sb *btt_sb)
+{
+	if (ndns->claim_class == NVDIMM_CCLASS_BTT2) {
+		/* Probe/setup for BTT v2.0 */
+		nd_btt->initial_offset = 0;
+		nd_btt->version_major = 2;
+		nd_btt->version_minor = 0;
+		if (nvdimm_read_bytes(ndns, 0, btt_sb, sizeof(*btt_sb), 0))
+			return -ENXIO;
+		if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
+			return -ENODEV;
+		if ((le16_to_cpu(btt_sb->version_major) != 2) ||
+				(le16_to_cpu(btt_sb->version_minor) != 0))
+			return -ENODEV;
+	} else {
+		/*
+		 * Probe/setup for BTT v1.1 (NVDIMM_CCLASS_NONE or
+		 * NVDIMM_CCLASS_BTT)
+		 */
+		nd_btt->initial_offset = SZ_4K;
+		nd_btt->version_major = 1;
+		nd_btt->version_minor = 1;
+		if (nvdimm_read_bytes(ndns, SZ_4K, btt_sb, sizeof(*btt_sb), 0))
+			return -ENXIO;
+		if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
+			return -ENODEV;
+		if ((le16_to_cpu(btt_sb->version_major) != 1) ||
+				(le16_to_cpu(btt_sb->version_minor) != 1))
+			return -ENODEV;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(nd_btt_version);
+
 static int __nd_btt_probe(struct nd_btt *nd_btt,
 		struct nd_namespace_common *ndns, struct btt_sb *btt_sb)
 {
+	int rc;
+
 	if (!btt_sb || !ndns || !nd_btt)
 		return -ENODEV;
 
-	if (nvdimm_read_bytes(ndns, SZ_4K, btt_sb, sizeof(*btt_sb), 0))
-		return -ENXIO;
-
 	if (nvdimm_namespace_capacity(ndns) < SZ_16M)
 		return -ENXIO;
 
-	if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
-		return -ENODEV;
+	rc = nd_btt_version(nd_btt, ndns, btt_sb);
+	if (rc < 0)
+		return rc;
 
 	nd_btt->lbasize = le32_to_cpu(btt_sb->external_lbasize);
 	nd_btt->uuid = kmemdup(btt_sb->uuid, 16, GFP_KERNEL);
@@ -295,6 +330,15 @@ int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns)
 	if (ndns->force_raw)
 		return -ENODEV;
 
+	switch (ndns->claim_class) {
+	case NVDIMM_CCLASS_NONE:
+	case NVDIMM_CCLASS_BTT:
+	case NVDIMM_CCLASS_BTT2:
+		break;
+	default:
+		return -ENODEV;
+	}
+
 	nvdimm_bus_lock(&ndns->dev);
 	btt_dev = __nd_btt_create(nd_region, 0, NULL, ndns);
 	nvdimm_bus_unlock(&ndns->dev);

drivers/nvdimm/bus.c

@@ -38,13 +38,13 @@ static int to_nd_device_type(struct device *dev)
 {
 	if (is_nvdimm(dev))
 		return ND_DEVICE_DIMM;
-	else if (is_nd_pmem(dev))
+	else if (is_memory(dev))
 		return ND_DEVICE_REGION_PMEM;
 	else if (is_nd_blk(dev))
 		return ND_DEVICE_REGION_BLK;
 	else if (is_nd_dax(dev))
 		return ND_DEVICE_DAX_PMEM;
-	else if (is_nd_pmem(dev->parent) || is_nd_blk(dev->parent))
+	else if (is_nd_region(dev->parent))
 		return nd_region_to_nstype(to_nd_region(dev->parent));
 
 	return 0;
@@ -56,7 +56,7 @@ static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 	 * Ensure that region devices always have their numa node set as
 	 * early as possible.
 	 */
-	if (is_nd_pmem(dev) || is_nd_blk(dev))
+	if (is_nd_region(dev))
 		set_dev_node(dev, to_nd_region(dev)->numa_node);
 	return add_uevent_var(env, "MODALIAS=" ND_DEVICE_MODALIAS_FMT,
 			to_nd_device_type(dev));
@@ -65,7 +65,7 @@ static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 static struct module *to_bus_provider(struct device *dev)
 {
 	/* pin bus providers while regions are enabled */
-	if (is_nd_pmem(dev) || is_nd_blk(dev)) {
+	if (is_nd_region(dev)) {
 		struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
 
 		return nvdimm_bus->nd_desc->module;
@@ -198,6 +198,9 @@ static int nvdimm_clear_badblocks_region(struct device *dev, void *data)
 	sector = (ctx->phys - nd_region->ndr_start) / 512;
 	badblocks_clear(&nd_region->bb, sector, ctx->cleared / 512);
 
+	if (nd_region->bb_state)
+		sysfs_notify_dirent(nd_region->bb_state);
+
 	return 0;
 }
 
@@ -907,6 +910,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	static char in_env[ND_CMD_MAX_ENVELOPE];
 	const struct nd_cmd_desc *desc = NULL;
 	unsigned int cmd = _IOC_NR(ioctl_cmd);
+	unsigned int func = cmd;
 	void __user *p = (void __user *) arg;
 	struct device *dev = &nvdimm_bus->dev;
 	struct nd_cmd_pkg pkg;
@@ -972,6 +976,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	}
 
 	if (cmd == ND_CMD_CALL) {
+		func = pkg.nd_command;
 		dev_dbg(dev, "%s:%s, idx: %llu, in: %zu, out: %zu, len %zu\n",
 				__func__, dimm_name, pkg.nd_command,
 				in_len, out_len, buf_len);
@@ -1020,7 +1025,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 	}
 
 	nvdimm_bus_lock(&nvdimm_bus->dev);
-	rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, cmd, buf);
+	rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, func, buf);
 	if (rc)
 		goto out_unlock;