Merge branch 'x86-dax-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 dax updates from Ingo Molnar:
 "This contains x86 memcpy_mcsafe() fault handling improvements the
  nvdimm tree would like to make more use of"

* 'x86-dax-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()
  x86/asm/memcpy_mcsafe: Add write-protection-fault handling
  x86/asm/memcpy_mcsafe: Return bytes remaining
  x86/asm/memcpy_mcsafe: Add labels for __memcpy_mcsafe() write fault handling
  x86/asm/memcpy_mcsafe: Remove loop unrolling

5 files changed, 86 insertions, 62 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f2ee6a8ffe65..1fe24b624d44 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -62,6 +62,7 @@ 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
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 533f74c300c2..d33f92b9fa22 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/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);
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 62546b3a398e..62acb613114b 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -47,6 +47,17 @@ copy_user_generic(void *to, const void *from, unsigned len)
 }
 
 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)
 {
 	int ret = 0;
@@ -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 */
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 9a53a06e5a3e..c3b527a9f95d 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -184,11 +184,11 @@ ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
 /*
- * 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 +204,29 @@ ENTRY(memcpy_mcsafe_unrolled)
 	subl $8, %ecx
 	negl %ecx
 	subl %ecx, %edx
-.L_copy_leading_bytes:
+.L_read_leading_bytes:
 	movb (%rsi), %al
+.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
+.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 +235,53 @@ ENTRY(memcpy_mcsafe_unrolled)
 
 	/* Copy trailing bytes */
 	movl %edx, %ecx
-.L_copy_trailing_bytes:
+.L_read_trailing_bytes:
 	movb (%rsi), %al
+.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
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index a624dcc4de10..9c5606d88f61 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -74,6 +74,27 @@ 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