arm: ARMv4 assembly compatibility

There is currently a problem that U-Boot can not work on ARMv4
because assembly imlementations of memcpy() and some other functions
use "bx lr" instruction that is not available on ARMv4 ("mov pc, lr"
should be used instead).

A working preprocessor-based solution to this problem is found in
arch/arm/lib/relocate.S. Move it to the "ret" macro in
arch/arm/include/asm/assembler.h and change all "bx lr" code
to "ret lr" in functions that may run on ARMv4. Linux source code
deals with this problem in the same manner.

v1 -> v2:
Comment update. Pointed out by Andre Przywara.

Signed-off-by: Sergei Antonov <saproj@gmail.com>
CC: Samuel Holland <samuel@sholland.org>
CC: Ye Li <ye.li@nxp.com>
CC: Simon Glass <sjg@chromium.org>
CC: Andre Przywara <andre.przywara@arm.com>
CC: Marek Vasut <marex@denx.de>
CC: Sean Anderson <sean.anderson@seco.com>
CC: Tom Rini <trini@konsulko.com>

arch/arm/include/asm/assembler.h

@@ -58,16 +58,22 @@
 #endif
 
 /*
- * We only support cores that support at least Thumb-1 and thus we use
+ * Use 'bx lr' everywhere except ARMv4 (without 'T') where only 'mov pc, lr'
- * 'bx lr'
+ * works
  */
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
+
+	/* ARMv4- don't know bx lr but the assembler fails to see that */
+#ifdef __ARM_ARCH_4__
+	mov\c	pc, \reg
+#else
 	.ifeqs	"\reg", "lr"
 	bx\c	\reg
 	.else
 	mov\c	pc, \reg
 	.endif
+#endif
 	.endm
 	.endr
 

arch/arm/lib/lib1funcs.S

@@ -377,7 +377,7 @@ ENTRY(__gnu_thumb1_case_sqi)
 	lsls	r1, r1, #1
 	add	lr, lr, r1
 	pop	{r1}
-	bx	lr
+	ret	lr
 ENDPROC(__gnu_thumb1_case_sqi)
 .popsection
 
@@ -391,7 +391,7 @@ ENTRY(__gnu_thumb1_case_uqi)
 	lsls	r1, r1, #1
 	add	lr, lr, r1
 	pop	{r1}
-	bx	lr
+	ret	lr
 ENDPROC(__gnu_thumb1_case_uqi)
 .popsection
 
@@ -406,7 +406,7 @@ ENTRY(__gnu_thumb1_case_shi)
 	lsls	r1, r1, #1
 	add	lr, lr, r1
 	pop	{r0, r1}
-	bx	lr
+	ret	lr
 ENDPROC(__gnu_thumb1_case_shi)
 .popsection
 
@@ -421,7 +421,7 @@ ENTRY(__gnu_thumb1_case_uhi)
 	lsls	r1, r1, #1
 	add	lr, lr, r1
 	pop	{r0, r1}
-	bx	lr
+	ret	lr
 ENDPROC(__gnu_thumb1_case_uhi)
 .popsection
 #endif

arch/arm/lib/memcpy.S

@@ -59,7 +59,7 @@
 #endif
 ENTRY(memcpy)
 		cmp	r0, r1
-		bxeq	lr
+		reteq	lr
 
 		enter	r4, lr
 
@@ -148,7 +148,7 @@ ENTRY(memcpy)
 		str1b	r0, ip, cs, abort=21f
 
 		exit	r4, lr
-		bx	lr
+		ret	lr
 
 9:		rsb	ip, ip, #4
 		cmp	ip, #2
@@ -258,7 +258,7 @@ ENTRY(memcpy)
 
 	.macro	copy_abort_end
 	ldmfd	sp!, {r4, lr}
-	bx	lr
+	ret	lr
 	.endm
 
 ENDPROC(memcpy)

arch/arm/lib/relocate.S

@@ -61,7 +61,7 @@ ENTRY(relocate_vectors)
 	stmia	r1!, {r2-r8,r10}
 #endif
 #endif
-	bx	lr
+	ret	lr
 
 ENDPROC(relocate_vectors)
 
@@ -127,13 +127,7 @@ relocate_done:
 	mcr	p15, 0, r0, c7, c10, 4	/* drain write buffer */
 #endif
 
-	/* ARMv4- don't know bx lr but the assembler fails to see that */
+	ret	lr
-
-#ifdef __ARM_ARCH_4__
-	mov	pc, lr
-#else
-	bx	lr
-#endif
 
 ENDPROC(relocate_code)
 

arch/arm/lib/setjmp.S

@@ -17,7 +17,7 @@ ENTRY(setjmp)
 	mov  ip, sp
 	stm  a1, {v1-v8, ip, lr}
 	mov  a1, #0
-	bx   lr
+	ret  lr
 ENDPROC(setjmp)
 .popsection
 
@@ -31,6 +31,6 @@ ENTRY(longjmp)
 	bne  1f
 	mov  a1, #1
 1:
-	bx   lr
+	ret  lr
 ENDPROC(longjmp)
 .popsection