arm: make arch memset/memcpy to work with Thumb2 builds

Resynchronize memcpy/memset with kernel and build them explicitly
in Thumb2 mode (unified syntax). Those assembler files can be
built and linked in ARM mode too, however when calling them from
Thumb2 built code, the stack got corrupted and the copy did not
succeed (the exact details have not been traced back). Hoever,
the Linux kernel builds those files in Thumb2 mode. Hence U-Boot
should build them in Thumb2 mode too when CONFIG_SYS_THUMB_BUILD
is set.

Also add implicit-it=always to AFLAGS when building for Thumb2.
Furthermore add no-warn-deprecated option to AFLAGS to rid of
deprecated unified syntax:
arch/arm/lib/memcpy.S: Assembler messages:
arch/arm/lib/memcpy.S:153: Warning: conditional infixes are deprecated in unified syntax
arch/arm/lib/memcpy.S:154: Warning: conditional infixes are deprecated in unified syntax
...

1 files changed, 52 insertions, 23 deletions

diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index f655256b5d..c9424baa51 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -10,9 +10,14 @@
  *  published by the Free Software Foundation.
  */
 
+#include <linux/linkage.h>
 #include <asm/assembler.h>
 
+#ifdef CONFIG_SYS_THUMB_BUILD
+#define W(instr)	instr.w
+#else
 #define W(instr)	instr
+#endif
 
 #define LDR1W_SHIFT	0
 #define STR1W_SHIFT	0
@@ -56,13 +61,16 @@
 	.text
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
-
-.globl memcpy
-memcpy:
-
+#ifdef CONFIG_SYS_THUMB_BUILD
+	.syntax unified
+	.thumb
+	.thumb_func
+#endif
+ENTRY(memcpy)
+/*
 		cmp	r0, r1
 		moveq	pc, lr
-
+*/
 		enter	r4, lr
 
 		subs	r2, r2, #4
@@ -193,24 +201,24 @@ memcpy:
 
 12:	PLD(	pld	[r1, #124]		)
 13:		ldr4w	r1, r4, r5, r6, r7, abort=19f
-		mov	r3, lr, pull #\pull
+		mov	r3, lr, lspull #\pull
 		subs	r2, r2, #32
 		ldr4w	r1, r8, r9, ip, lr, abort=19f
-		orr	r3, r3, r4, push #\push
-		mov	r4, r4, pull #\pull
-		orr	r4, r4, r5, push #\push
-		mov	r5, r5, pull #\pull
-		orr	r5, r5, r6, push #\push
-		mov	r6, r6, pull #\pull
-		orr	r6, r6, r7, push #\push
-		mov	r7, r7, pull #\pull
-		orr	r7, r7, r8, push #\push
-		mov	r8, r8, pull #\pull
-		orr	r8, r8, r9, push #\push
-		mov	r9, r9, pull #\pull
-		orr	r9, r9, ip, push #\push
-		mov	ip, ip, pull #\pull
-		orr	ip, ip, lr, push #\push
+		orr	r3, r3, r4, lspush #\push
+		mov	r4, r4, lspull #\pull
+		orr	r4, r4, r5, lspush #\push
+		mov	r5, r5, lspull #\pull
+		orr	r5, r5, r6, lspush #\push
+		mov	r6, r6, lspull #\pull
+		orr	r6, r6, r7, lspush #\push
+		mov	r7, r7, lspull #\pull
+		orr	r7, r7, r8, lspush #\push
+		mov	r8, r8, lspull #\pull
+		orr	r8, r8, r9, lspush #\push
+		mov	r9, r9, lspull #\pull
+		orr	r9, r9, ip, lspush #\push
+		mov	ip, ip, lspull #\pull
+		orr	ip, ip, lr, lspush #\push
 		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -221,10 +229,10 @@ memcpy:
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov	r3, lr, pull #\pull
+15:		mov	r3, lr, lspull #\pull
 		ldr1w	r1, lr, abort=21f
 		subs	ip, ip, #4
-		orr	r3, r3, lr, push #\push
+		orr	r3, r3, lr, lspush #\push
 		str1w	r0, r3, abort=21f
 		bgt	15b
 	CALGN(	cmp	r2, #0			)
@@ -241,3 +249,24 @@ memcpy:
 17:		forward_copy_shift	pull=16	push=16
 
 18:		forward_copy_shift	pull=24	push=8
+
+
+/*
+ * Abort preamble and completion macros.
+ * If a fixup handler is required then those macros must surround it.
+ * It is assumed that the fixup code will handle the private part of
+ * the exit macro.
+ */
+
+	.macro	copy_abort_preamble
+19:	ldmfd	sp!, {r5 - r9}
+	b	21f
+20:	ldmfd	sp!, {r5 - r8}
+21:
+	.endm
+
+	.macro	copy_abort_end
+	ldmfd	sp!, {r4, pc}
+	.endm
+
+ENDPROC(memcpy)