6ebbf2ce43
ARMv6 and greater introduced a new instruction ("bx") which can be used
to return from function calls. Recent CPUs perform better when the
"bx lr" instruction is used rather than the "mov pc, lr" instruction,
and this sequence is strongly recommended to be used by the ARM
architecture manual (section A.4.1.1).
We provide a new macro "ret" with all its variants for the condition
code which will resolve to the appropriate instruction.
Rather than doing this piecemeal, and miss some instances, change all
the "mov pc" instances to use the new macro, with the exception of
the "movs" instruction and the kprobes code. This allows us to detect
the "mov pc, lr" case and fix it up - and also gives us the possibility
of deploying this for other registers depending on the CPU selection.
Reported-by: Will Deacon <will.deacon@arm.com>
Tested-by: Stephen Warren <swarren@nvidia.com> # Tegra Jetson TK1
Tested-by: Robert Jarzmik <robert.jarzmik@free.fr> # mioa701_bootresume.S
Tested-by: Andrew Lunn <andrew@lunn.ch> # Kirkwood
Tested-by: Shawn Guo <shawn.guo@freescale.com>
Tested-by: Tony Lindgren <tony@atomide.com> # OMAPs
Tested-by: Gregory CLEMENT <gregory.clement@free-electrons.com> # Armada XP, 375, 385
Acked-by: Sekhar Nori <nsekhar@ti.com> # DaVinci
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> # kvm/hyp
Acked-by: Haojian Zhuang <haojian.zhuang@gmail.com> # PXA3xx
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> # Xen
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> # ARMv7M
Tested-by: Simon Horman <horms+renesas@verge.net.au> # Shmobile
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
152 lines
3.9 KiB
ArmAsm
152 lines
3.9 KiB
ArmAsm
/*
|
|
* linux/arch/arm/mm/arm740.S: utility functions for ARM740
|
|
*
|
|
* Copyright (C) 2004-2006 Hyok S. Choi (hyok.choi@samsung.com)
|
|
*
|
|
* 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.
|
|
*
|
|
*/
|
|
#include <linux/linkage.h>
|
|
#include <linux/init.h>
|
|
#include <asm/assembler.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/hwcap.h>
|
|
#include <asm/pgtable-hwdef.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/ptrace.h>
|
|
|
|
#include "proc-macros.S"
|
|
|
|
.text
|
|
/*
|
|
* cpu_arm740_proc_init()
|
|
* cpu_arm740_do_idle()
|
|
* cpu_arm740_dcache_clean_area()
|
|
* cpu_arm740_switch_mm()
|
|
*
|
|
* These are not required.
|
|
*/
|
|
ENTRY(cpu_arm740_proc_init)
|
|
ENTRY(cpu_arm740_do_idle)
|
|
ENTRY(cpu_arm740_dcache_clean_area)
|
|
ENTRY(cpu_arm740_switch_mm)
|
|
ret lr
|
|
|
|
/*
|
|
* cpu_arm740_proc_fin()
|
|
*/
|
|
ENTRY(cpu_arm740_proc_fin)
|
|
mrc p15, 0, r0, c1, c0, 0
|
|
bic r0, r0, #0x3f000000 @ bank/f/lock/s
|
|
bic r0, r0, #0x0000000c @ w-buffer/cache
|
|
mcr p15, 0, r0, c1, c0, 0 @ disable caches
|
|
ret lr
|
|
|
|
/*
|
|
* cpu_arm740_reset(loc)
|
|
* Params : r0 = address to jump to
|
|
* Notes : This sets up everything for a reset
|
|
*/
|
|
.pushsection .idmap.text, "ax"
|
|
ENTRY(cpu_arm740_reset)
|
|
mov ip, #0
|
|
mcr p15, 0, ip, c7, c0, 0 @ invalidate cache
|
|
mrc p15, 0, ip, c1, c0, 0 @ get ctrl register
|
|
bic ip, ip, #0x0000000c @ ............wc..
|
|
mcr p15, 0, ip, c1, c0, 0 @ ctrl register
|
|
ret r0
|
|
ENDPROC(cpu_arm740_reset)
|
|
.popsection
|
|
|
|
.type __arm740_setup, #function
|
|
__arm740_setup:
|
|
mov r0, #0
|
|
mcr p15, 0, r0, c7, c0, 0 @ invalidate caches
|
|
|
|
mcr p15, 0, r0, c6, c3 @ disable area 3~7
|
|
mcr p15, 0, r0, c6, c4
|
|
mcr p15, 0, r0, c6, c5
|
|
mcr p15, 0, r0, c6, c6
|
|
mcr p15, 0, r0, c6, c7
|
|
|
|
mov r0, #0x0000003F @ base = 0, size = 4GB
|
|
mcr p15, 0, r0, c6, c0 @ set area 0, default
|
|
|
|
ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
|
|
ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB)
|
|
mov r4, #10 @ 11 is the minimum (4KB)
|
|
1: add r4, r4, #1 @ area size *= 2
|
|
movs r3, r3, lsr #1
|
|
bne 1b @ count not zero r-shift
|
|
orr r0, r0, r4, lsl #1 @ the area register value
|
|
orr r0, r0, #1 @ set enable bit
|
|
mcr p15, 0, r0, c6, c1 @ set area 1, RAM
|
|
|
|
ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
|
|
ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB)
|
|
cmp r3, #0
|
|
moveq r0, #0
|
|
beq 2f
|
|
mov r4, #10 @ 11 is the minimum (4KB)
|
|
1: add r4, r4, #1 @ area size *= 2
|
|
movs r3, r3, lsr #1
|
|
bne 1b @ count not zero r-shift
|
|
orr r0, r0, r4, lsl #1 @ the area register value
|
|
orr r0, r0, #1 @ set enable bit
|
|
2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH
|
|
|
|
mov r0, #0x06
|
|
mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable
|
|
#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
|
|
mov r0, #0x00 @ disable whole write buffer
|
|
#else
|
|
mov r0, #0x02 @ Region 1 write bufferred
|
|
#endif
|
|
mcr p15, 0, r0, c3, c0
|
|
|
|
mov r0, #0x10000
|
|
sub r0, r0, #1 @ r0 = 0xffff
|
|
mcr p15, 0, r0, c5, c0 @ all read/write access
|
|
|
|
mrc p15, 0, r0, c1, c0 @ get control register
|
|
bic r0, r0, #0x3F000000 @ set to standard caching mode
|
|
@ need some benchmark
|
|
orr r0, r0, #0x0000000d @ MPU/Cache/WB
|
|
|
|
ret lr
|
|
|
|
.size __arm740_setup, . - __arm740_setup
|
|
|
|
__INITDATA
|
|
|
|
@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
|
|
define_processor_functions arm740, dabort=v4t_late_abort, pabort=legacy_pabort, nommu=1
|
|
|
|
.section ".rodata"
|
|
|
|
string cpu_arch_name, "armv4"
|
|
string cpu_elf_name, "v4"
|
|
string cpu_arm740_name, "ARM740T"
|
|
|
|
.align
|
|
|
|
.section ".proc.info.init", #alloc, #execinstr
|
|
.type __arm740_proc_info,#object
|
|
__arm740_proc_info:
|
|
.long 0x41807400
|
|
.long 0xfffffff0
|
|
.long 0
|
|
.long 0
|
|
b __arm740_setup
|
|
.long cpu_arch_name
|
|
.long cpu_elf_name
|
|
.long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
|
|
.long cpu_arm740_name
|
|
.long arm740_processor_functions
|
|
.long 0
|
|
.long 0
|
|
.long v4_cache_fns @ cache model
|
|
.size __arm740_proc_info, . - __arm740_proc_info
|