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
  ...

6 files changed, 157 insertions, 136 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fe53a3a..7d7e0e8 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
deleted file mode 100644
index 0ff8fe7..0000000
--- a/arch/x86/include/asm/pmem.h
+++ /dev/null
@@ -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__ */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 733bae0..1f22bc2 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/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 */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index c5504b9..b16f6a1 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/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);
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 3b7c40a..75d3776 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/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
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index c8520b2..757b0bc 100644
--- a/arch/x86/mm/pageattr.c
+++ b/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;