arm: build arch memset/memcpy in Thumb2 mode

Resynchronize memcpy/memset with kernel 3.17 and build them 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). However, 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.

To build the files without warning, some assembler instructions
had to be replaced with their UAL compliant variant (thanks
Jeroen for this input).

To build the file in Thumb2 mode the implicit-it=always option need
to be set to generate Thumb2 compliant IT instructions where needed.
We add this option to the general AFLAGS when building for Thumb2.

Reviewed-by: Simon Glass <sjg@chromium.org>
Tested-by: Simon Glass <sjg@chromium.org>
Signed-off-by: Stefan Agner <stefan@agner.ch>
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 0cdf895..7208f20 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -9,32 +9,25 @@
  *
  *  ASM optimised string functions
  */
+#include <linux/linkage.h>
 #include <asm/assembler.h>
 
 	.text
 	.align	5
-	.word	0
 
-1:	subs	r2, r2, #4		@ 1 do we have enough
-	blt	5f			@ 1 bytes to align with?
-	cmp	r3, #2			@ 1
-	strltb	r1, [r0], #1		@ 1
-	strleb	r1, [r0], #1		@ 1
-	strb	r1, [r0], #1		@ 1
-	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
-/*
- * The pointer is now aligned and the length is adjusted.  Try doing the
- * memset again.
- */
-
-.globl memset
-memset:
+	.syntax unified
+#ifdef CONFIG_SYS_THUMB_BUILD
+	.thumb
+	.thumb_func
+#endif
+ENTRY(memset)
 	ands	r3, r0, #3		@ 1 unaligned?
-	bne	1b			@ 1
+	mov	ip, r0			@ preserve r0 as return value
+	bne	6f			@ 1
 /*
- * we know that the pointer in r0 is aligned to a word boundary.
+ * we know that the pointer in ip is aligned to a word boundary.
  */
-	orr	r1, r1, r1, lsl #8
+1:	orr	r1, r1, r1, lsl #8
 	orr	r1, r1, r1, lsl #16
 	mov	r3, r1
 	cmp	r2, #16
@@ -43,29 +36,28 @@
 #if ! CALGN(1)+0
 
 /*
- * We need an extra register for this loop - save the return address and
- * use the LR
+ * We need 2 extra registers for this loop - use r8 and the LR
  */
-	str	lr, [sp, #-4]!
-	mov	ip, r1
+	stmfd	sp!, {r8, lr}
+	mov	r8, r1
 	mov	lr, r1
 
 2:	subs	r2, r2, #64
-	stmgeia	r0!, {r1, r3, ip, lr}	@ 64 bytes at a time.
-	stmgeia	r0!, {r1, r3, ip, lr}
-	stmgeia	r0!, {r1, r3, ip, lr}
-	stmgeia	r0!, {r1, r3, ip, lr}
+	stmiage	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
+	stmiage	ip!, {r1, r3, r8, lr}
 	bgt	2b
-	ldmeqfd	sp!, {pc}		@ Now <64 bytes to go.
+	ldmfdeq	sp!, {r8, pc}		@ Now <64 bytes to go.
 /*
  * No need to correct the count; we're only testing bits from now on
  */
 	tst	r2, #32
-	stmneia	r0!, {r1, r3, ip, lr}
-	stmneia	r0!, {r1, r3, ip, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
+	stmiane	ip!, {r1, r3, r8, lr}
 	tst	r2, #16
-	stmneia	r0!, {r1, r3, ip, lr}
-	ldr	lr, [sp], #4
+	stmiane	ip!, {r1, r3, r8, lr}
+	ldmfd	sp!, {r8, lr}
 
 #else
 
@@ -74,53 +66,63 @@
  * whole cache lines at once.
  */
 
-	stmfd	sp!, {r4-r7, lr}
+	stmfd	sp!, {r4-r8, lr}
 	mov	r4, r1
 	mov	r5, r1
 	mov	r6, r1
 	mov	r7, r1
-	mov	ip, r1
+	mov	r8, r1
 	mov	lr, r1
 
 	cmp	r2, #96
-	tstgt	r0, #31
+	tstgt	ip, #31
 	ble	3f
 
-	and	ip, r0, #31
-	rsb	ip, ip, #32
-	sub	r2, r2, ip
-	movs	ip, ip, lsl #(32 - 4)
-	stmcsia	r0!, {r4, r5, r6, r7}
-	stmmiia	r0!, {r4, r5}
-	tst	ip, #(1 << 30)
-	mov	ip, r1
-	strne	r1, [r0], #4
+	and	r8, ip, #31
+	rsb	r8, r8, #32
+	sub	r2, r2, r8
+	movs	r8, r8, lsl #(32 - 4)
+	stmiacs	ip!, {r4, r5, r6, r7}
+	stmiami	ip!, {r4, r5}
+	tst	r8, #(1 << 30)
+	mov	r8, r1
+	strne	r1, [ip], #4
 
 3:	subs	r2, r2, #64
-	stmgeia	r0!, {r1, r3-r7, ip, lr}
-	stmgeia	r0!, {r1, r3-r7, ip, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
+	stmiage	ip!, {r1, r3-r8, lr}
 	bgt	3b
-	ldmeqfd	sp!, {r4-r7, pc}
+	ldmfdeq	sp!, {r4-r8, pc}
 
 	tst	r2, #32
-	stmneia	r0!, {r1, r3-r7, ip, lr}
+	stmiane	ip!, {r1, r3-r8, lr}
 	tst	r2, #16
-	stmneia	r0!, {r4-r7}
-	ldmfd	sp!, {r4-r7, lr}
+	stmiane	ip!, {r4-r7}
+	ldmfd	sp!, {r4-r8, lr}
 
 #endif
 
 4:	tst	r2, #8
-	stmneia	r0!, {r1, r3}
+	stmiane	ip!, {r1, r3}
 	tst	r2, #4
-	strne	r1, [r0], #4
+	strne	r1, [ip], #4
 /*
  * When we get here, we've got less than 4 bytes to zero.  We
  * may have an unaligned pointer as well.
  */
 5:	tst	r2, #2
-	strneb	r1, [r0], #1
-	strneb	r1, [r0], #1
+	strbne	r1, [ip], #1
+	strbne	r1, [ip], #1
 	tst	r2, #1
-	strneb	r1, [r0], #1
-	mov	pc, lr
+	strbne	r1, [ip], #1
+	ret	lr
+
+6:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5b			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strblt	r1, [ip], #1		@ 1
+	strble	r1, [ip], #1		@ 1
+	strb	r1, [ip], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+	b	1b
+ENDPROC(memset)