Merge branch 'for-4.18/mcsafe' into libnvdimm-for-next

arch/x86/Kconfig

@@ -60,6 +60,7 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
+	select ARCH_HAS_UACCESS_MCSAFE		if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX

arch/x86/Kconfig.debug

@@ -72,6 +72,9 @@ config EARLY_PRINTK_USB_XDBC
 	  You should normally say N here, unless you want to debug early
 	  crashes or need a very simple printk logging facility.
 
+config MCSAFE_TEST
+	def_bool n
+
 config X86_PTDUMP_CORE
 	def_bool n
 

arch/x86/include/asm/mcsafe_test.h

@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MCSAFE_TEST_H_
+#define _MCSAFE_TEST_H_
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_MCSAFE_TEST
+extern unsigned long mcsafe_test_src;
+extern unsigned long mcsafe_test_dst;
+
+static inline void mcsafe_inject_src(void *addr)
+{
+	if (addr)
+		mcsafe_test_src = (unsigned long) addr;
+	else
+		mcsafe_test_src = ~0UL;
+}
+
+static inline void mcsafe_inject_dst(void *addr)
+{
+	if (addr)
+		mcsafe_test_dst = (unsigned long) addr;
+	else
+		mcsafe_test_dst = ~0UL;
+}
+#else /* CONFIG_MCSAFE_TEST */
+static inline void mcsafe_inject_src(void *addr)
+{
+}
+
+static inline void mcsafe_inject_dst(void *addr)
+{
+}
+#endif /* CONFIG_MCSAFE_TEST */
+
+#else /* __ASSEMBLY__ */
+#include <asm/export.h>
+
+#ifdef CONFIG_MCSAFE_TEST
+.macro MCSAFE_TEST_CTL
+	.pushsection .data
+	.align 8
+	.globl mcsafe_test_src
+	mcsafe_test_src:
+		.quad 0
+	EXPORT_SYMBOL_GPL(mcsafe_test_src)
+	.globl mcsafe_test_dst
+	mcsafe_test_dst:
+		.quad 0
+	EXPORT_SYMBOL_GPL(mcsafe_test_dst)
+	.popsection
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+	leaq \count(\reg), %r9
+	cmp mcsafe_test_src, %r9
+	ja \target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+	leaq \count(\reg), %r9
+	cmp mcsafe_test_dst, %r9
+	ja \target
+.endm
+#else
+.macro MCSAFE_TEST_CTL
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+.endm
+#endif /* CONFIG_MCSAFE_TEST */
+#endif /* __ASSEMBLY__ */
+#endif /* _MCSAFE_TEST_H_ */

arch/x86/include/asm/string_64.h

@@ -116,7 +116,8 @@ int strcmp(const char *cs, const char *ct);
 #endif
 
 #define __HAVE_ARCH_MEMCPY_MCSAFE 1
-__must_check int memcpy_mcsafe_unrolled(void *dst, const void *src, size_t cnt);
+__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src,
+		size_t cnt);
 DECLARE_STATIC_KEY_FALSE(mcsafe_key);
 
 /**
@@ -131,14 +132,15 @@ DECLARE_STATIC_KEY_FALSE(mcsafe_key);
  * actually do machine check recovery. Everyone else can just
  * use memcpy().
  *
- * Return 0 for success, -EFAULT for fail
+ * Return 0 for success, or number of bytes not copied if there was an
+ * exception.
  */
-static __always_inline __must_check int
+static __always_inline __must_check unsigned long
 memcpy_mcsafe(void *dst, const void *src, size_t cnt)
 {
 #ifdef CONFIG_X86_MCE
 	if (static_branch_unlikely(&mcsafe_key))
-		return memcpy_mcsafe_unrolled(dst, src, cnt);
+		return __memcpy_mcsafe(dst, src, cnt);
 	else
 #endif
 		memcpy(dst, src, cnt);

arch/x86/include/asm/uaccess_64.h

@@ -46,6 +46,17 @@ copy_user_generic(void *to, const void *from, unsigned len)
 	return ret;
 }
 
+static __always_inline __must_check unsigned long
+copy_to_user_mcsafe(void *to, const void *from, unsigned len)
+{
+	unsigned long ret;
+
+	__uaccess_begin();
+	ret = memcpy_mcsafe(to, from, len);
+	__uaccess_end();
+	return ret;
+}
+
 static __always_inline __must_check unsigned long
 raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 {
@@ -194,4 +205,7 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 unsigned long
 copy_user_handle_tail(char *to, char *from, unsigned len);
 
+unsigned long
+mcsafe_handle_tail(char *to, char *from, unsigned len);
+
 #endif /* _ASM_X86_UACCESS_64_H */

arch/x86/lib/memcpy_64.S

@@ -3,6 +3,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
+#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -183,12 +184,15 @@ ENTRY(memcpy_orig)
 ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
+
+MCSAFE_TEST_CTL
+
 /*
- * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
+ * __memcpy_mcsafe - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(memcpy_mcsafe_unrolled)
+ENTRY(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled)
 	subl $8, %ecx
 	negl %ecx
 	subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_leading_bytes
+	jnz .L_read_leading_bytes
 
 .L_8byte_aligned:
-	/* Figure out how many whole cache lines (64-bytes) to copy */
-	movl %edx, %ecx
-	andl $63, %edx
-	shrl $6, %ecx
-	jz .L_no_whole_cache_lines
-
-	/* Loop copying whole cache lines */
-.L_cache_w0: movq (%rsi), %r8
-.L_cache_w1: movq 1*8(%rsi), %r9
-.L_cache_w2: movq 2*8(%rsi), %r10
-.L_cache_w3: movq 3*8(%rsi), %r11
-	movq %r8, (%rdi)
-	movq %r9, 1*8(%rdi)
-	movq %r10, 2*8(%rdi)
-	movq %r11, 3*8(%rdi)
-.L_cache_w4: movq 4*8(%rsi), %r8
-.L_cache_w5: movq 5*8(%rsi), %r9
-.L_cache_w6: movq 6*8(%rsi), %r10
-.L_cache_w7: movq 7*8(%rsi), %r11
-	movq %r8, 4*8(%rdi)
-	movq %r9, 5*8(%rdi)
-	movq %r10, 6*8(%rdi)
-	movq %r11, 7*8(%rdi)
-	leaq 64(%rsi), %rsi
-	leaq 64(%rdi), %rdi
-	decl %ecx
-	jnz .L_cache_w0
-
-	/* Are there any trailing 8-byte words? */
-.L_no_whole_cache_lines:
 	movl %edx, %ecx
 	andl $7, %edx
 	shrl $3, %ecx
 	jz .L_no_whole_words
 
-	/* Copy trailing words */
-.L_copy_trailing_words:
+.L_read_words:
 	movq (%rsi), %r8
-	mov %r8, (%rdi)
-	leaq 8(%rsi), %rsi
-	leaq 8(%rdi), %rdi
+	MCSAFE_TEST_SRC %rsi 8 .E_read_words
+	MCSAFE_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
 	decl %ecx
-	jnz .L_copy_trailing_words
+	jnz .L_read_words
 
 	/* Any trailing bytes? */
 .L_no_whole_words:
@@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled)
 
 	/* Copy trailing bytes */
 	movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz .L_copy_trailing_bytes
+	jnz .L_read_trailing_bytes
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorq %rax, %rax
 	ret
-ENDPROC(memcpy_mcsafe_unrolled)
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
+ENDPROC(__memcpy_mcsafe)
+EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
-	/* Return -EFAULT for any failure */
-.L_memcpy_mcsafe_fail:
-	mov	$-EFAULT, %rax
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
 	ret
 
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp mcsafe_handle_tail
+
 	.previous
 
-	_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail)
-	_ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail)
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
 #endif

arch/x86/lib/usercopy_64.c

@@ -75,6 +75,27 @@ copy_user_handle_tail(char *to, char *from, unsigned len)
 	return len;
 }
 
+/*
+ * Similar to copy_user_handle_tail, probe for the write fault point,
+ * but reuse __memcpy_mcsafe in case a new read error is encountered.
+ * clac() is handled in _copy_to_iter_mcsafe().
+ */
+__visible unsigned long
+mcsafe_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++) {
+		/*
+		 * Call the assembly routine back directly since
+		 * memcpy_mcsafe() may silently fallback to memcpy.
+		 */
+		unsigned long rem = __memcpy_mcsafe(to, from, 1);
+
+		if (rem)
+			break;
+	}
+	return len;
+}
+
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB

drivers/dax/super.c

@@ -287,6 +287,16 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 }
 EXPORT_SYMBOL_GPL(dax_copy_from_iter);
 
+size_t dax_copy_to_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_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_to_iter);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)

drivers/md/dm-linear.c

@@ -185,9 +185,24 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static size_t linear_dax_copy_to_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_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_copy_from_iter NULL
+#define linear_dax_copy_to_iter NULL
 #endif
 
 static struct target_type linear_target = {
@@ -204,6 +219,7 @@ static struct target_type linear_target = {
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
 	.dax_copy_from_iter = linear_dax_copy_from_iter,
+	.dax_copy_to_iter = linear_dax_copy_to_iter,
 };
 
 int __init dm_linear_init(void)

drivers/md/dm-log-writes.c

@@ -962,9 +962,23 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
 dax_copy:
 	return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
 }
+
+static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
+					  pgoff_t pgoff, void *addr, size_t bytes,
+					  struct iov_iter *i)
+{
+	struct log_writes_c *lc = ti->private;
+	sector_t sector = pgoff * PAGE_SECTORS;
+
+	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_copy_from_iter NULL
+#define log_writes_dax_copy_to_iter NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -982,6 +996,7 @@ static struct target_type log_writes_target = {
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
 	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
+	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
 };
 
 static int __init dm_log_writes_init(void)

drivers/md/dm-stripe.c

@@ -354,9 +354,29 @@ static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static size_t stripe_dax_copy_to_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_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_copy_from_iter NULL
+#define stripe_dax_copy_to_iter NULL
 #endif
 
 /*
@@ -478,6 +498,7 @@ static struct target_type stripe_target = {
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
 	.dax_copy_from_iter = stripe_dax_copy_from_iter,
+	.dax_copy_to_iter = stripe_dax_copy_to_iter,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm.c

@@ -1089,6 +1089,30 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static size_t dm_dax_copy_to_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_to_iter) {
+		ret = copy_to_iter(addr, bytes, i);
+		goto out;
+	}
+	ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i);
+ out:
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
@@ -3134,6 +3158,7 @@ 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,
+	.copy_to_iter = dm_dax_copy_to_iter,
 };
 
 /*

drivers/nvdimm/claim.c

@@ -276,7 +276,8 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	if (rw == READ) {
 		if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
 			return -EIO;
-		return memcpy_mcsafe(buf, nsio->addr + offset, size);
+		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
+			return -EIO;
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {

drivers/nvdimm/pmem.c

@@ -101,15 +101,15 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 		void *pmem_addr, unsigned int len)
 {
 	unsigned int chunk;
-	int rc;
+	unsigned long rem;
 	void *mem;
 
 	while (len) {
 		mem = kmap_atomic(page);
 		chunk = min_t(unsigned int, len, PAGE_SIZE);
-		rc = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+		rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
 		kunmap_atomic(mem);
-		if (rc)
+		if (rem)
 			return BLK_STS_IOERR;
 		len -= chunk;
 		off = 0;
@@ -259,9 +259,16 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return copy_from_iter_flushcache(addr, bytes, i);
 }
 
+static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter_mcsafe(addr, bytes, i);
+}
+
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
 	.copy_from_iter = pmem_copy_from_iter,
+	.copy_to_iter = pmem_copy_to_iter,
 };
 
 static const struct attribute_group *pmem_attribute_groups[] = {

drivers/s390/block/dcssblk.c

@@ -51,9 +51,16 @@ static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev,
 	return copy_from_iter(addr, bytes, i);
 }
 
+static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
 	.copy_from_iter = dcssblk_dax_copy_from_iter,
+	.copy_to_iter = dcssblk_dax_copy_to_iter,
 };
 
 struct dcssblk_dev_info {

fs/dax.c

@@ -1082,6 +1082,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	struct iov_iter *iter = data;
 	loff_t end = pos + length, done = 0;
 	ssize_t ret = 0;
+	size_t xfer;
 	int id;
 
 	if (iov_iter_rw(iter) == READ) {
@@ -1145,18 +1146,20 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		 * vfs_write(), depending on which operation we are doing.
 		 */
 		if (iov_iter_rw(iter) == WRITE)
-			map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
+			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
-			map_len = copy_to_iter(kaddr, map_len, iter);
-		if (map_len <= 0) {
-			ret = map_len ? map_len : -EFAULT;
-			break;
-		}
+			xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
+					map_len, iter);
 
-		pos += map_len;
-		length -= map_len;
-		done += map_len;
+		pos += xfer;
+		length -= xfer;
+		done += xfer;
+
+		if (xfer == 0)
+			ret = -EFAULT;
+		if (xfer < map_len)
+			break;
 	}
 	dax_read_unlock(id);
 

include/linux/dax.h

@@ -20,6 +20,9 @@ struct dax_operations {
 	/* 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 *);
+	/* copy_to_iter: required operation for fs-dax direct-i/o */
+	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
+			struct iov_iter *);
 };
 
 extern struct attribute_group dax_attribute_group;
@@ -125,6 +128,8 @@ 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);
+size_t dax_copy_to_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, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,

include/linux/device-mapper.h

@@ -133,7 +133,7 @@ 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,
+typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
@@ -184,7 +184,8 @@ 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_copy_iter_fn dax_copy_from_iter;
+	dm_dax_copy_iter_fn dax_copy_to_iter;
 
 	/* For internal device-mapper use. */
 	struct list_head list;

include/linux/string.h

@@ -147,8 +147,8 @@ extern int memcmp(const void *,const void *,__kernel_size_t);
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif
 #ifndef __HAVE_ARCH_MEMCPY_MCSAFE
-static inline __must_check int memcpy_mcsafe(void *dst, const void *src,
-		size_t cnt)
+static inline __must_check unsigned long memcpy_mcsafe(void *dst,
+		const void *src, size_t cnt)
 {
 	memcpy(dst, src, cnt);
 	return 0;

include/linux/uio.h

@@ -154,6 +154,12 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 #define _copy_from_iter_flushcache _copy_from_iter_nocache
 #endif
 
+#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
+size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i);
+#else
+#define _copy_to_iter_mcsafe _copy_to_iter
+#endif
+
 static __always_inline __must_check
 size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
@@ -163,6 +169,15 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 		return _copy_from_iter_flushcache(addr, bytes, i);
 }
 
+static __always_inline __must_check
+size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (unlikely(!check_copy_size(addr, bytes, false)))
+		return 0;
+	else
+		return _copy_to_iter_mcsafe(addr, bytes, i);
+}
+
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i);

lib/Kconfig

@@ -586,6 +586,9 @@ config ARCH_HAS_PMEM_API
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
+config ARCH_HAS_UACCESS_MCSAFE
+	bool
+
 config STACKDEPOT
 	bool
 	select STACKTRACE

lib/iov_iter.c

@@ -573,6 +573,67 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(_copy_to_iter);
 
+#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
+static int copyout_mcsafe(void __user *to, const void *from, size_t n)
+{
+	if (access_ok(VERIFY_WRITE, to, n)) {
+		kasan_check_read(from, n);
+		n = copy_to_user_mcsafe((__force void *) to, from, n);
+	}
+	return n;
+}
+
+static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
+		const char *from, size_t len)
+{
+	unsigned long ret;
+	char *to;
+
+	to = kmap_atomic(page);
+	ret = memcpy_mcsafe(to + offset, from, len);
+	kunmap_atomic(to);
+
+	return ret;
+}
+
+size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
+{
+	const char *from = addr;
+	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
+
+	if (unlikely(i->type & ITER_PIPE)) {
+		WARN_ON(1);
+		return 0;
+	}
+	if (iter_is_iovec(i))
+		might_fault();
+	iterate_and_advance(i, bytes, v,
+		copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		({
+		rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
+                               (from += v.bv_len) - v.bv_len, v.bv_len);
+		if (rem) {
+			curr_addr = (unsigned long) from;
+			bytes = curr_addr - s_addr - rem;
+			return bytes;
+		}
+		}),
+		({
+		rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
+				v.iov_len);
+		if (rem) {
+			curr_addr = (unsigned long) from;
+			bytes = curr_addr - s_addr - rem;
+			return bytes;
+		}
+		})
+	)
+
+	return bytes;
+}
+EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
+#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */
+
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;

tools/testing/nvdimm/test/nfit.c

@@ -29,6 +29,8 @@
 #include "nfit_test.h"
 #include "../watermark.h"
 
+#include <asm/mcsafe_test.h>
+
 /*
  * Generate an NFIT table to describe the following topology:
  *
@@ -2681,6 +2683,107 @@ static struct platform_driver nfit_test_driver = {
 	.id_table = nfit_test_id,
 };
 
+static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+
+enum INJECT {
+	INJECT_NONE,
+	INJECT_SRC,
+	INJECT_DST,
+};
+
+static void mcsafe_test_init(char *dst, char *src, size_t size)
+{
+	size_t i;
+
+	memset(dst, 0xff, size);
+	for (i = 0; i < size; i++)
+		src[i] = (char) i;
+}
+
+static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
+		size_t size, unsigned long rem)
+{
+	size_t i;
+
+	for (i = 0; i < size - rem; i++)
+		if (dst[i] != (unsigned char) i) {
+			pr_info_once("%s:%d: offset: %zd got: %#x expect: %#x\n",
+					__func__, __LINE__, i, dst[i],
+					(unsigned char) i);
+			return false;
+		}
+	for (i = size - rem; i < size; i++)
+		if (dst[i] != 0xffU) {
+			pr_info_once("%s:%d: offset: %zd got: %#x expect: 0xff\n",
+					__func__, __LINE__, i, dst[i]);
+			return false;
+		}
+	return true;
+}
+
+void mcsafe_test(void)
+{
+	char *inject_desc[] = { "none", "source", "destination" };
+	enum INJECT inj;
+
+	if (IS_ENABLED(CONFIG_MCSAFE_TEST)) {
+		pr_info("%s: run...\n", __func__);
+	} else {
+		pr_info("%s: disabled, skip.\n", __func__);
+		return;
+	}
+
+	for (inj = INJECT_NONE; inj <= INJECT_DST; inj++) {
+		int i;
+
+		pr_info("%s: inject: %s\n", __func__, inject_desc[inj]);
+		for (i = 0; i < 512; i++) {
+			unsigned long expect, rem;
+			void *src, *dst;
+			bool valid;
+
+			switch (inj) {
+			case INJECT_NONE:
+				mcsafe_inject_src(NULL);
+				mcsafe_inject_dst(NULL);
+				dst = &mcsafe_buf[2048];
+				src = &mcsafe_buf[1024 - i];
+				expect = 0;
+				break;
+			case INJECT_SRC:
+				mcsafe_inject_src(&mcsafe_buf[1024]);
+				mcsafe_inject_dst(NULL);
+				dst = &mcsafe_buf[2048];
+				src = &mcsafe_buf[1024 - i];
+				expect = 512 - i;
+				break;
+			case INJECT_DST:
+				mcsafe_inject_src(NULL);
+				mcsafe_inject_dst(&mcsafe_buf[2048]);
+				dst = &mcsafe_buf[2048 - i];
+				src = &mcsafe_buf[1024];
+				expect = 512 - i;
+				break;
+			}
+
+			mcsafe_test_init(dst, src, 512);
+			rem = __memcpy_mcsafe(dst, src, 512);
+			valid = mcsafe_test_validate(dst, src, 512, expect);
+			if (rem == expect && valid)
+				continue;
+			pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
+					__func__,
+					((unsigned long) dst) & ~PAGE_MASK,
+					((unsigned long ) src) & ~PAGE_MASK,
+					512, i, rem, valid ? "valid" : "bad",
+					expect);
+		}
+	}
+
+	mcsafe_inject_src(NULL);
+	mcsafe_inject_dst(NULL);
+}
+
 static __init int nfit_test_init(void)
 {
 	int rc, i;
@@ -2689,6 +2792,7 @@ static __init int nfit_test_init(void)
 	libnvdimm_test();
 	acpi_nfit_test();
 	device_dax_test();
+	mcsafe_test();
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);