u-boot/arch/arm/include/asm/assembler.h
Albert ARIBAUD 6b4e942683 armv5te: make 'ret lr' produce iinterworking 'bx lr'
Current ARM assembler helper for the 'return to caller' pseudo-instruction
turns 'ret lr' into 'mov pc, lr' for ARMv5TE. This causes the core to remain
in its current ARM state even when the routine doing the 'ret' was called
from Thumb-1 state, triggering an undefined instruction exception.

This causes early run-time failures in all boards compiled using the Thumb-1
instruction set (for instance the Open-RD family).

ARMv5TE supports 'bx lr' which properly implements interworking and thus
correctly returns to Thumb-1 state from ARM state.

This change makes 'ret lr' turn into 'bx lr' for ARMv5TE.

Signed-off-by: Albert ARIBAUD <albert.u.boot@aribaud.net>
2017-03-01 21:28:31 -05:00

84 lines
2 KiB
C

/*
* arch/arm/include/asm/assembler.h
*
* Copyright (C) 1996-2000 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This file contains arm architecture specific defines
* for the different processors.
*
* Do not include any C declarations in this file - it is included by
* assembler source.
*/
#include <config.h>
#include <asm/unified.h>
/*
* Endian independent macros for shifting bytes within registers.
*/
#ifndef __ARMEB__
#define lspull lsr
#define lspush lsl
#define get_byte_0 lsl #0
#define get_byte_1 lsr #8
#define get_byte_2 lsr #16
#define get_byte_3 lsr #24
#define put_byte_0 lsl #0
#define put_byte_1 lsl #8
#define put_byte_2 lsl #16
#define put_byte_3 lsl #24
#else
#define lspull lsl
#define lspush lsr
#define get_byte_0 lsr #24
#define get_byte_1 lsr #16
#define get_byte_2 lsr #8
#define get_byte_3 lsl #0
#define put_byte_0 lsl #24
#define put_byte_1 lsl #16
#define put_byte_2 lsl #8
#define put_byte_3 lsl #0
#endif
/*
* Data preload for architectures that support it
*/
#if defined(__ARM_ARCH_5E__) || defined(__ARM_ARCH_5TE__) || \
defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || \
defined(__ARM_ARCH_6T2__) || defined(__ARM_ARCH_6Z__) || \
defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_7A__) || \
defined(__ARM_ARCH_7R__)
#define PLD(code...) code
#else
#define PLD(code...)
#endif
.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
.macro ret\c, reg
#if defined(__ARM_ARCH_5E__)
mov\c pc, \reg
#else
.ifeqs "\reg", "lr"
bx\c \reg
.else
mov\c pc, \reg
.endif
#endif
.endm
.endr
/*
* Cache aligned, used for optimized memcpy/memset
* In the kernel this is only enabled for Feroceon CPU's...
* We disable it especially for Thumb builds since those instructions
* are not made in a Thumb ready way...
*/
#ifdef CONFIG_SYS_THUMB_BUILD
#define CALGN(code...)
#else
#define CALGN(code...) code
#endif