u-boot/arch/mips/cpu/start.S
Paul Burton 9f8ac82452 MIPS: Use unchecked immediate addition/subtraction
In MIPS assembly there have historically been 2 variants of immediate
addition - the standard "addi" which traps if an overflow occurs, and
the unchecked "addiu" which does not trap on overflow. In release 6 of
the MIPS architecture the trapping variants of immediate addition &
subtraction have been removed. In preparation for supporting MIPSr6,
stop using the trapping instructions from assembly & switch to their
unchecked variants.

Signed-off-by: Paul Burton <paul.burton@imgtec.com>
2016-05-21 01:36:39 +02:00

320 lines
6.6 KiB
ArmAsm

/*
* Startup Code for MIPS32 CPU-core
*
* Copyright (c) 2003 Wolfgang Denk <wd@denx.de>
*
* SPDX-License-Identifier: GPL-2.0+
*/
#include <asm-offsets.h>
#include <config.h>
#include <asm/asm.h>
#include <asm/regdef.h>
#include <asm/mipsregs.h>
#ifndef CONFIG_SYS_MIPS_CACHE_MODE
#define CONFIG_SYS_MIPS_CACHE_MODE CONF_CM_CACHABLE_NONCOHERENT
#endif
#ifndef CONFIG_SYS_INIT_SP_ADDR
#define CONFIG_SYS_INIT_SP_ADDR (CONFIG_SYS_SDRAM_BASE + \
CONFIG_SYS_INIT_SP_OFFSET)
#endif
#ifdef CONFIG_32BIT
# define MIPS_RELOC 3
# define STATUS_SET 0
#endif
#ifdef CONFIG_64BIT
# ifdef CONFIG_SYS_LITTLE_ENDIAN
# define MIPS64_R_INFO(ssym, r_type3, r_type2, r_type) \
(((r_type) << 24) | ((r_type2) << 16) | ((r_type3) << 8) | (ssym))
# else
# define MIPS64_R_INFO(ssym, r_type3, r_type2, r_type) \
((r_type) | ((r_type2) << 8) | ((r_type3) << 16) | (ssym) << 24)
# endif
# define MIPS_RELOC MIPS64_R_INFO(0x00, 0x00, 0x12, 0x03)
# define STATUS_SET ST0_KX
#endif
/*
* For the moment disable interrupts, mark the kernel mode and
* set ST0_KX so that the CPU does not spit fire when using
* 64-bit addresses.
*/
.macro setup_c0_status set clr
.set push
mfc0 t0, CP0_STATUS
or t0, ST0_CU0 | \set | 0x1f | \clr
xor t0, 0x1f | \clr
mtc0 t0, CP0_STATUS
.set noreorder
sll zero, 3 # ehb
.set pop
.endm
.set noreorder
ENTRY(_start)
/* U-Boot entry point */
b reset
nop
.org 0x10
#if defined(CONFIG_SYS_XWAY_EBU_BOOTCFG)
/*
* Almost all Lantiq XWAY SoC devices have an external bus unit (EBU) to
* access external NOR flashes. If the board boots from NOR flash the
* internal BootROM does a blind read at address 0xB0000010 to read the
* initial configuration for that EBU in order to access the flash
* device with correct parameters. This config option is board-specific.
*/
.word CONFIG_SYS_XWAY_EBU_BOOTCFG
.word 0x0
#elif defined(CONFIG_MALTA)
/*
* Linux expects the Board ID here.
*/
.word 0x00000420 # 0x420 (Malta Board with CoreLV)
.word 0x00000000
#endif
.org 0x200
/* TLB refill, 32 bit task */
1: b 1b
nop
.org 0x280
/* XTLB refill, 64 bit task */
1: b 1b
nop
.org 0x300
/* Cache error exception */
1: b 1b
nop
.org 0x380
/* General exception */
1: b 1b
nop
.org 0x400
/* Catch interrupt exceptions */
1: b 1b
nop
.org 0x480
/* EJTAG debug exception */
1: b 1b
nop
.align 4
reset:
/* Clear watch registers */
MTC0 zero, CP0_WATCHLO
mtc0 zero, CP0_WATCHHI
/* WP(Watch Pending), SW0/1 should be cleared */
mtc0 zero, CP0_CAUSE
setup_c0_status STATUS_SET 0
/* Init Timer */
mtc0 zero, CP0_COUNT
mtc0 zero, CP0_COMPARE
#ifndef CONFIG_SKIP_LOWLEVEL_INIT
/* CONFIG0 register */
li t0, CONF_CM_UNCACHED
mtc0 t0, CP0_CONFIG
#endif
/*
* Initialize $gp, force pointer sized alignment of bal instruction to
* forbid the compiler to put nop's between bal and _gp. This is
* required to keep _gp and ra aligned to 8 byte.
*/
.align PTRLOG
bal 1f
nop
PTR _gp
1:
PTR_L gp, 0(ra)
#ifndef CONFIG_SKIP_LOWLEVEL_INIT
/* Initialize any external memory */
PTR_LA t9, lowlevel_init
jalr t9
nop
/* Initialize caches... */
PTR_LA t9, mips_cache_reset
jalr t9
nop
/* ... and enable them */
li t0, CONFIG_SYS_MIPS_CACHE_MODE
mtc0 t0, CP0_CONFIG
#endif
/* Set up temporary stack */
li t0, -16
PTR_LI t1, CONFIG_SYS_INIT_SP_ADDR
and sp, t1, t0 # force 16 byte alignment
PTR_SUBU \
sp, sp, GD_SIZE # reserve space for gd
and sp, sp, t0 # force 16 byte alignment
move k0, sp # save gd pointer
#ifdef CONFIG_SYS_MALLOC_F_LEN
li t2, CONFIG_SYS_MALLOC_F_LEN
PTR_SUBU \
sp, sp, t2 # reserve space for early malloc
and sp, sp, t0 # force 16 byte alignment
#endif
move fp, sp
/* Clear gd */
move t0, k0
1:
PTR_S zero, 0(t0)
blt t0, t1, 1b
PTR_ADDIU t0, PTRSIZE
#ifdef CONFIG_SYS_MALLOC_F_LEN
PTR_S sp, GD_MALLOC_BASE(k0) # gd->malloc_base offset
#endif
move a0, zero # a0 <-- boot_flags = 0
PTR_LA t9, board_init_f
jr t9
move ra, zero
END(_start)
/*
* void relocate_code (addr_sp, gd, addr_moni)
*
* This "function" does not return, instead it continues in RAM
* after relocating the monitor code.
*
* a0 = addr_sp
* a1 = gd
* a2 = destination address
*/
ENTRY(relocate_code)
move sp, a0 # set new stack pointer
move fp, sp
move s0, a1 # save gd in s0
move s2, a2 # save destination address in s2
PTR_LI t0, CONFIG_SYS_MONITOR_BASE
PTR_SUB s1, s2, t0 # s1 <-- relocation offset
PTR_LA t3, in_ram
PTR_L t2, -(3 * PTRSIZE)(t3) # t2 <-- __image_copy_end
move t1, a2
PTR_ADD gp, s1 # adjust gp
/*
* t0 = source address
* t1 = target address
* t2 = source end address
*/
1:
PTR_L t3, 0(t0)
PTR_S t3, 0(t1)
PTR_ADDU t0, PTRSIZE
blt t0, t2, 1b
PTR_ADDU t1, PTRSIZE
/* If caches were enabled, we would have to flush them here. */
PTR_SUB a1, t1, s2 # a1 <-- size
PTR_LA t9, flush_cache
jalr t9
move a0, s2 # a0 <-- destination address
/* Jump to where we've relocated ourselves */
PTR_ADDIU t0, s2, in_ram - _start
jr t0
nop
PTR __rel_dyn_end
PTR __rel_dyn_start
PTR __image_copy_end
PTR _GLOBAL_OFFSET_TABLE_
PTR num_got_entries
in_ram:
/*
* Now we want to update GOT.
*
* GOT[0] is reserved. GOT[1] is also reserved for the dynamic object
* generated by GNU ld. Skip these reserved entries from relocation.
*/
PTR_L t3, -(1 * PTRSIZE)(t0) # t3 <-- num_got_entries
PTR_L t8, -(2 * PTRSIZE)(t0) # t8 <-- _GLOBAL_OFFSET_TABLE_
PTR_ADD t8, s1 # t8 now holds relocated _G_O_T_
PTR_ADDIU t8, t8, 2 * PTRSIZE # skipping first two entries
PTR_LI t2, 2
1:
PTR_L t1, 0(t8)
beqz t1, 2f
PTR_ADD t1, s1
PTR_S t1, 0(t8)
2:
PTR_ADDIU t2, 1
blt t2, t3, 1b
PTR_ADDIU t8, PTRSIZE
/* Update dynamic relocations */
PTR_L t1, -(4 * PTRSIZE)(t0) # t1 <-- __rel_dyn_start
PTR_L t2, -(5 * PTRSIZE)(t0) # t2 <-- __rel_dyn_end
b 2f # skip first reserved entry
PTR_ADDIU t1, 2 * PTRSIZE
1:
lw t8, -4(t1) # t8 <-- relocation info
PTR_LI t3, MIPS_RELOC
bne t8, t3, 2f # skip non-MIPS_RELOC entries
nop
PTR_L t3, -(2 * PTRSIZE)(t1) # t3 <-- location to fix up in FLASH
PTR_L t8, 0(t3) # t8 <-- original pointer
PTR_ADD t8, s1 # t8 <-- adjusted pointer
PTR_ADD t3, s1 # t3 <-- location to fix up in RAM
PTR_S t8, 0(t3)
2:
blt t1, t2, 1b
PTR_ADDIU t1, 2 * PTRSIZE # each rel.dyn entry is 2*PTRSIZE bytes
/*
* Clear BSS
*
* GOT is now relocated. Thus __bss_start and __bss_end can be
* accessed directly via $gp.
*/
PTR_LA t1, __bss_start # t1 <-- __bss_start
PTR_LA t2, __bss_end # t2 <-- __bss_end
1:
PTR_S zero, 0(t1)
blt t1, t2, 1b
PTR_ADDIU t1, PTRSIZE
move a0, s0 # a0 <-- gd
move a1, s2
PTR_LA t9, board_init_r
jr t9
move ra, zero
END(relocate_code)