MIPS: microMIPS: Optimise 'strncpy' core library function.

Optimise 'strncpy' to use microMIPS instructions and/or optimisations
for binary size reduction. When the microMIPS ISA is not being used,
the library function compiles to the original binary code.

Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com>
diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S
index bad5394..92870b6 100644
--- a/arch/mips/lib/strncpy_user.S
+++ b/arch/mips/lib/strncpy_user.S
@@ -3,7 +3,8 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (c) 1996, 1999 by Ralf Baechle
+ * Copyright (C) 1996, 1999 by Ralf Baechle
+ * Copyright (C) 2011 MIPS Technologies, Inc.
  */
 #include <linux/errno.h>
 #include <asm/asm.h>
@@ -33,26 +34,27 @@
 	bnez		v0, .Lfault
 
 FEXPORT(__strncpy_from_user_nocheck_asm)
-	move		v0, zero
-	move		v1, a1
 	.set		noreorder
-1:	EX(lbu, t0, (v1), .Lfault)
+	move		t0, zero
+	move		v1, a1
+1:	EX(lbu, v0, (v1), .Lfault)
 	PTR_ADDIU	v1, 1
 	R10KCBARRIER(0(ra))
-	beqz		t0, 2f
-	 sb		t0, (a0)
-	PTR_ADDIU	v0, 1
-	.set		reorder
-	PTR_ADDIU	a0, 1
-	bne		v0, a2, 1b
-2:	PTR_ADDU	t0, a1, v0
-	xor		t0, a1
-	bltz		t0, .Lfault
+	beqz		v0, 2f
+	 sb		v0, (a0)
+	PTR_ADDIU	t0, 1
+	bne		t0, a2, 1b
+	 PTR_ADDIU	a0, 1
+2:	PTR_ADDU	v0, a1, t0
+	xor		v0, a1
+	bltz		v0, .Lfault
+	 nop
 	jr		ra			# return n
+	 move		v0, t0
 	END(__strncpy_from_user_asm)
 
-.Lfault:	li		v0, -EFAULT
-	jr		ra
+.Lfault: jr		ra
+	  li		v0, -EFAULT
 
 	.section	__ex_table,"a"
 	PTR		1b, .Lfault