3 files changed, 50 insertions, 21 deletions

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index db4e5aa0858b..b2f1822084ae 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -16,6 +16,30 @@
 #include <asm/smap.h>
 #include <asm/export.h>
 
+.macro ALIGN_DESTINATION
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE_UA(100b, 103b)
+	_ASM_EXTABLE_UA(101b, 103b)
+	.endm
+
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
  * This version is for CPUs like P4 that don't have efficient micro
@@ -194,6 +218,30 @@ ENDPROC(copy_user_enhanced_fast_string)
 EXPORT_SYMBOL(copy_user_enhanced_fast_string)
 
 /*
+ * Try to copy last bytes and clear the rest if needed.
+ * Since protection fault in copy_from/to_user is not a normal situation,
+ * it is not necessary to optimize tail handling.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ALIGN;
+copy_user_handle_tail:
+	movl %edx,%ecx
+1:	rep movsb
+2:	mov %ecx,%eax
+	ASM_CLAC
+	ret
+
+	_ASM_EXTABLE_UA(1b, 2b)
+ENDPROC(copy_user_handle_tail)
+
+/*
  * copy_user_nocache - Uncached memory copy with exception handling
  * This will force destination out of cache for more performance.
  *
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 3b24dc05251c..9d05572370ed 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe)
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorl %eax, %eax
+.L_done:
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
@@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 	addl	%edx, %ecx
 .E_trailing_bytes:
 	mov	%ecx, %eax
-	ret
+	jmp	.L_done
 
 	/*
 	 * For write fault handling, given the destination is unaligned,
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index ee42bb0cbeb3..9952a01cad24 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -55,26 +55,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 EXPORT_SYMBOL(clear_user);
 
 /*
- * Try to copy last bytes and clear the rest if needed.
- * Since protection fault in copy_from/to_user is not a normal situation,
- * it is not necessary to optimize tail handling.
- */
-__visible unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++) {
-		char c;
-
-		if (__get_user_nocheck(c, from++, sizeof(char)))
-			break;
-		if (__put_user_nocheck(c, to, sizeof(char)))
-			break;
-	}
-	clac();
-	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().