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
  6aa734a2f38e ("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
  ...

8 files changed, 103 insertions, 144 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 5ec1f6c47716..8f39db7439c3 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -16,8 +16,15 @@ struct dax_operations {
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
 			void **, pfn_t *);
+	/* copy_from_iter: required operation for fs-dax direct-i/o */
+	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
+			struct iov_iter *);
+	/* flush: optional driver-specific cache management after writes */
+	void (*flush)(struct dax_device *, pgoff_t, void *, size_t);
 };
 
+extern struct attribute_group dax_attribute_group;
+
 #if IS_ENABLED(CONFIG_DAX)
 struct dax_device *dax_get_by_host(const char *host);
 void put_dax(struct dax_device *dax_dev);
@@ -75,6 +82,11 @@ void kill_dax(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		void **kaddr, pfn_t *pfn);
+size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i);
+void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t size);
+void dax_write_cache(struct dax_device *dax_dev, bool wc);
 
 /*
  * We use lowest available bit in exceptional entry for locking, one bit for
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 0c1b50ad23b0..1473455d0341 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -132,6 +132,10 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
+typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i);
+typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr,
+		size_t size);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
 void dm_error(const char *message);
@@ -181,6 +185,8 @@ struct target_type {
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
+	dm_dax_copy_from_iter_fn dax_copy_from_iter;
+	dm_dax_flush_fn dax_flush;
 
 	/* For internal device-mapper use. */
 	struct list_head list;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 6c807017128d..f3d3e6af8838 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/sizes.h>
 #include <linux/types.h>
+#include <linux/uuid.h>
 
 enum {
 	/* when a dimm supports both PMEM and BLK access a label is required */
@@ -54,6 +55,7 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
 
 struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
+	unsigned long bus_dsm_mask;
 	unsigned long cmd_mask;
 	struct module *module;
 	char *provider_name;
@@ -71,9 +73,14 @@ struct nd_cmd_desc {
 };
 
 struct nd_interleave_set {
-	u64 cookie;
+	/* v1.1 definition of the interleave-set-cookie algorithm */
+	u64 cookie1;
+	/* v1.2 definition of the interleave-set-cookie algorithm */
+	u64 cookie2;
 	/* compatibility with initial buggy Linux implementation */
 	u64 altcookie;
+
+	guid_t type_guid;
 };
 
 struct nd_mapping_desc {
@@ -159,9 +166,11 @@ void *nd_region_provider_data(struct nd_region *nd_region);
 void *nd_blk_region_provider_data(struct nd_blk_region *ndbr);
 void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data);
 struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr);
+unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr);
 unsigned int nd_region_acquire_lane(struct nd_region *nd_region);
 void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane);
 u64 nd_fletcher64(void *addr, size_t len, bool le);
 void nvdimm_flush(struct nd_region *nd_region);
 int nvdimm_has_flush(struct nd_region *nd_region);
+int nvdimm_has_cache(struct nd_region *nd_region);
 #endif /* __LIBNVDIMM_H__ */
diff --git a/include/linux/nd.h b/include/linux/nd.h
index 194b8e002ea7..5dc6b695437d 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -21,6 +21,15 @@ enum nvdimm_event {
 	NVDIMM_REVALIDATE_POISON,
 };
 
+enum nvdimm_claim_class {
+	NVDIMM_CCLASS_NONE,
+	NVDIMM_CCLASS_BTT,
+	NVDIMM_CCLASS_BTT2,
+	NVDIMM_CCLASS_PFN,
+	NVDIMM_CCLASS_DAX,
+	NVDIMM_CCLASS_UNKNOWN,
+};
+
 struct nd_device_driver {
 	struct device_driver drv;
 	unsigned long type;
@@ -41,12 +50,14 @@ static inline struct nd_device_driver *to_nd_device_driver(
  * @force_raw: ignore other personalities for the namespace (e.g. btt)
  * @dev: device model node
  * @claim: when set a another personality has taken ownership of the namespace
+ * @claim_class: restrict claim type to a given class
  * @rw_bytes: access the raw namespace capacity with byte-aligned transfers
  */
 struct nd_namespace_common {
 	int force_raw;
 	struct device dev;
 	struct device *claim;
+	enum nvdimm_claim_class claim_class;
 	int (*rw_bytes)(struct nd_namespace_common *, resource_size_t offset,
 			void *buf, size_t size, int rw, unsigned long flags);
 };
@@ -75,12 +86,14 @@ struct nd_namespace_io {
 /**
  * struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory
  * @nsio: device and system physical address range to drive
+ * @lbasize: logical sector size for the namespace in block-device-mode
  * @alt_name: namespace name supplied in the dimm label
  * @uuid: namespace name supplied in the dimm label
  * @id: ida allocated id
  */
 struct nd_namespace_pmem {
 	struct nd_namespace_io nsio;
+	unsigned long lbasize;
 	char *alt_name;
 	u8 *uuid;
 	int id;
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
deleted file mode 100644
index 71ecf3d46aac..000000000000
--- a/include/linux/pmem.h
+++ /dev/null
@@ -1,142 +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 __PMEM_H__
-#define __PMEM_H__
-
-#include <linux/io.h>
-#include <linux/uio.h>
-
-#ifdef CONFIG_ARCH_HAS_PMEM_API
-#define ARCH_MEMREMAP_PMEM MEMREMAP_WB
-#include <asm/pmem.h>
-#else
-#define ARCH_MEMREMAP_PMEM MEMREMAP_WT
-/*
- * These are simply here to enable compilation, all call sites gate
- * calling these symbols with arch_has_pmem_api() and redirect to the
- * implementation in asm/pmem.h.
- */
-static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
-{
-	BUG();
-}
-
-static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
-		struct iov_iter *i)
-{
-	BUG();
-	return 0;
-}
-
-static inline void arch_clear_pmem(void *addr, size_t size)
-{
-	BUG();
-}
-
-static inline void arch_wb_cache_pmem(void *addr, size_t size)
-{
-	BUG();
-}
-
-static inline void arch_invalidate_pmem(void *addr, size_t size)
-{
-	BUG();
-}
-#endif
-
-static inline bool arch_has_pmem_api(void)
-{
-	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API);
-}
-
-/**
- * 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
- *
- * Perform a memory copy that results in the destination of the copy
- * being effectively evicted from, or never written to, the processor
- * cache hierarchy after the copy completes.  After memcpy_to_pmem()
- * data may still reside in cpu or platform buffers, so this operation
- * must be followed by a blkdev_issue_flush() on the pmem block device.
- */
-static inline void memcpy_to_pmem(void *dst, const void *src, size_t n)
-{
-	if (arch_has_pmem_api())
-		arch_memcpy_to_pmem(dst, src, n);
-	else
-		memcpy(dst, src, n);
-}
-
-/**
- * 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'.
- * See blkdev_issue_flush() note for memcpy_to_pmem().
- */
-static inline size_t copy_from_iter_pmem(void *addr, size_t bytes,
-		struct iov_iter *i)
-{
-	if (arch_has_pmem_api())
-		return arch_copy_from_iter_pmem(addr, bytes, i);
-	return copy_from_iter_nocache(addr, bytes, i);
-}
-
-/**
- * clear_pmem - zero a PMEM memory range
- * @addr:	virtual start address
- * @size:	number of bytes to zero
- *
- * Write zeros into the memory range starting at 'addr' for 'size' bytes.
- * See blkdev_issue_flush() note for memcpy_to_pmem().
- */
-static inline void clear_pmem(void *addr, size_t size)
-{
-	if (arch_has_pmem_api())
-		arch_clear_pmem(addr, size);
-	else
-		memset(addr, 0, size);
-}
-
-/**
- * invalidate_pmem - flush a pmem range from the cache hierarchy
- * @addr:	virtual start address
- * @size:	bytes to invalidate (internally aligned to cache line size)
- *
- * For platforms that support clearing poison this flushes any poisoned
- * ranges out of the cache
- */
-static inline void invalidate_pmem(void *addr, size_t size)
-{
-	if (arch_has_pmem_api())
-		arch_invalidate_pmem(addr, size);
-}
-
-/**
- * wb_cache_pmem - write back processor cache for PMEM memory range
- * @addr:	virtual start address
- * @size:	number of bytes to write back
- *
- * Write back the processor cache range starting at 'addr' for 'size' bytes.
- * See blkdev_issue_flush() note for memcpy_to_pmem().
- */
-static inline void wb_cache_pmem(void *addr, size_t size)
-{
-	if (arch_has_pmem_api())
-		arch_wb_cache_pmem(addr, size);
-}
-#endif /* __PMEM_H__ */
diff --git a/include/linux/string.h b/include/linux/string.h
index 537918f8a98e..7439d83eaa33 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -122,6 +122,12 @@ static inline __must_check int memcpy_mcsafe(void *dst, const void *src,
 	return 0;
 }
 #endif
+#ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE
+static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+{
+	memcpy(dst, src, cnt);
+}
+#endif
 void *memchr_inv(const void *s, int c, size_t n);
 char *strreplace(char *s, char old, char new);
 
diff --git a/include/linux/uio.h b/include/linux/uio.h
index f2d36a3d3005..55cd54a0e941 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -95,6 +95,21 @@ size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
 bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i);
 size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/*
+ * Note, users like pmem that depend on the stricter semantics of
+ * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for
+ * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the
+ * destination is flushed from the cache on return.
+ */
+size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
+#else
+static inline size_t copy_from_iter_flushcache(void *addr, size_t bytes,
+				       struct iov_iter *i)
+{
+	return copy_from_iter_nocache(addr, bytes, i);
+}
+#endif
 bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i);
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index 7ad3863cb88b..6d3c54264d8e 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -105,7 +105,8 @@ struct nd_cmd_ars_cap {
 	__u32 status;
 	__u32 max_ars_out;
 	__u32 clear_err_unit;
-	__u32 reserved;
+	__u16 flags;
+	__u16 reserved;
 } __packed;
 
 struct nd_cmd_ars_start {
@@ -144,6 +145,43 @@ struct nd_cmd_clear_error {
 	__u64 cleared;
 } __packed;
 
+struct nd_cmd_trans_spa {
+	__u64 spa;
+	__u32 status;
+	__u8  flags;
+	__u8  _reserved[3];
+	__u64 trans_length;
+	__u32 num_nvdimms;
+	struct nd_nvdimm_device {
+		__u32 nfit_device_handle;
+		__u32 _reserved;
+		__u64 dpa;
+	} __packed devices[0];
+
+} __packed;
+
+struct nd_cmd_ars_err_inj {
+	__u64 err_inj_spa_range_base;
+	__u64 err_inj_spa_range_length;
+	__u8  err_inj_options;
+	__u32 status;
+} __packed;
+
+struct nd_cmd_ars_err_inj_clr {
+	__u64 err_inj_clr_spa_range_base;
+	__u64 err_inj_clr_spa_range_length;
+	__u32 status;
+} __packed;
+
+struct nd_cmd_ars_err_inj_stat {
+	__u32 status;
+	__u32 inj_err_rec_count;
+	struct nd_error_stat_query_record {
+		__u64 err_inj_stat_spa_range_base;
+		__u64 err_inj_stat_spa_range_length;
+	} __packed record[0];
+} __packed;
+
 enum {
 	ND_CMD_IMPLEMENTED = 0,
 
@@ -169,6 +207,7 @@ enum {
 enum {
 	ND_ARS_VOLATILE = 1,
 	ND_ARS_PERSISTENT = 2,
+	ND_ARS_RETURN_PREV_DATA = 1 << 1,
 	ND_CONFIG_LOCKED = 1,
 };
 
@@ -179,6 +218,7 @@ static inline const char *nvdimm_bus_cmd_name(unsigned cmd)
 		[ND_CMD_ARS_START] = "ars_start",
 		[ND_CMD_ARS_STATUS] = "ars_status",
 		[ND_CMD_CLEAR_ERROR] = "clear_error",
+		[ND_CMD_CALL] = "cmd_call",
 	};
 
 	if (cmd < ARRAY_SIZE(names) && names[cmd])