linux/arch/arm/mm/proc-arm1022.S
Russell King 6ebbf2ce43 ARM: convert all "mov.* pc, reg" to "bx reg" for ARMv6+
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>
2014-07-18 12:29:04 +01:00

475 lines
11 KiB
ArmAsm

/*
* linux/arch/arm/mm/proc-arm1022.S: MMU functions for ARM1022E
*
* Copyright (C) 2000 ARM Limited
* Copyright (C) 2000 Deep Blue Solutions Ltd.
* hacked for non-paged-MM by Hyok S. Choi, 2003.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
*
* These are the low level assembler for performing cache and TLB
* functions on the ARM1022E.
*/
#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"
/*
* This is the maximum size of an area which will be invalidated
* using the single invalidate entry instructions. Anything larger
* than this, and we go for the whole cache.
*
* This value should be chosen such that we choose the cheapest
* alternative.
*/
#define MAX_AREA_SIZE 32768
/*
* The size of one data cache line.
*/
#define CACHE_DLINESIZE 32
/*
* The number of data cache segments.
*/
#define CACHE_DSEGMENTS 16
/*
* The number of lines in a cache segment.
*/
#define CACHE_DENTRIES 64
/*
* This is the size at which it becomes more efficient to
* clean the whole cache, rather than using the individual
* cache line maintenance instructions.
*/
#define CACHE_DLIMIT 32768
.text
/*
* cpu_arm1022_proc_init()
*/
ENTRY(cpu_arm1022_proc_init)
ret lr
/*
* cpu_arm1022_proc_fin()
*/
ENTRY(cpu_arm1022_proc_fin)
mrc p15, 0, r0, c1, c0, 0 @ ctrl register
bic r0, r0, #0x1000 @ ...i............
bic r0, r0, #0x000e @ ............wca.
mcr p15, 0, r0, c1, c0, 0 @ disable caches
ret lr
/*
* cpu_arm1022_reset(loc)
*
* Perform a soft reset of the system. Put the CPU into the
* same state as it would be if it had been reset, and branch
* to what would be the reset vector.
*
* loc: location to jump to for soft reset
*/
.align 5
.pushsection .idmap.text, "ax"
ENTRY(cpu_arm1022_reset)
mov ip, #0
mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches
mcr p15, 0, ip, c7, c10, 4 @ drain WB
#ifdef CONFIG_MMU
mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs
#endif
mrc p15, 0, ip, c1, c0, 0 @ ctrl register
bic ip, ip, #0x000f @ ............wcam
bic ip, ip, #0x1100 @ ...i...s........
mcr p15, 0, ip, c1, c0, 0 @ ctrl register
ret r0
ENDPROC(cpu_arm1022_reset)
.popsection
/*
* cpu_arm1022_do_idle()
*/
.align 5
ENTRY(cpu_arm1022_do_idle)
mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt
ret lr
/* ================================= CACHE ================================ */
.align 5
/*
* flush_icache_all()
*
* Unconditionally clean and invalidate the entire icache.
*/
ENTRY(arm1022_flush_icache_all)
#ifndef CONFIG_CPU_ICACHE_DISABLE
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
#endif
ret lr
ENDPROC(arm1022_flush_icache_all)
/*
* flush_user_cache_all()
*
* Invalidate all cache entries in a particular address
* space.
*/
ENTRY(arm1022_flush_user_cache_all)
/* FALLTHROUGH */
/*
* flush_kern_cache_all()
*
* Clean and invalidate the entire cache.
*/
ENTRY(arm1022_flush_kern_cache_all)
mov r2, #VM_EXEC
mov ip, #0
__flush_whole_cache:
#ifndef CONFIG_CPU_DCACHE_DISABLE
mov r1, #(CACHE_DSEGMENTS - 1) << 5 @ 16 segments
1: orr r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
2: mcr p15, 0, r3, c7, c14, 2 @ clean+invalidate D index
subs r3, r3, #1 << 26
bcs 2b @ entries 63 to 0
subs r1, r1, #1 << 5
bcs 1b @ segments 15 to 0
#endif
tst r2, #VM_EXEC
#ifndef CONFIG_CPU_ICACHE_DISABLE
mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache
#endif
mcrne p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
/*
* flush_user_cache_range(start, end, flags)
*
* Invalidate a range of cache entries in the specified
* address space.
*
* - start - start address (inclusive)
* - end - end address (exclusive)
* - flags - vm_flags for this space
*/
ENTRY(arm1022_flush_user_cache_range)
mov ip, #0
sub r3, r1, r0 @ calculate total size
cmp r3, #CACHE_DLIMIT
bhs __flush_whole_cache
#ifndef CONFIG_CPU_DCACHE_DISABLE
1: mcr p15, 0, r0, c7, c14, 1 @ clean+invalidate D entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
#endif
tst r2, #VM_EXEC
#ifndef CONFIG_CPU_ICACHE_DISABLE
mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache
#endif
mcrne p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
/*
* coherent_kern_range(start, end)
*
* Ensure coherency between the Icache and the Dcache in the
* region described by start. If you have non-snooping
* Harvard caches, you need to implement this function.
*
* - start - virtual start address
* - end - virtual end address
*/
ENTRY(arm1022_coherent_kern_range)
/* FALLTHROUGH */
/*
* coherent_user_range(start, end)
*
* Ensure coherency between the Icache and the Dcache in the
* region described by start. If you have non-snooping
* Harvard caches, you need to implement this function.
*
* - start - virtual start address
* - end - virtual end address
*/
ENTRY(arm1022_coherent_user_range)
mov ip, #0
bic r0, r0, #CACHE_DLINESIZE - 1
1:
#ifndef CONFIG_CPU_DCACHE_DISABLE
mcr p15, 0, r0, c7, c10, 1 @ clean D entry
#endif
#ifndef CONFIG_CPU_ICACHE_DISABLE
mcr p15, 0, r0, c7, c5, 1 @ invalidate I entry
#endif
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
mcr p15, 0, ip, c7, c10, 4 @ drain WB
mov r0, #0
ret lr
/*
* flush_kern_dcache_area(void *addr, size_t size)
*
* Ensure no D cache aliasing occurs, either with itself or
* the I cache
*
* - addr - kernel address
* - size - region size
*/
ENTRY(arm1022_flush_kern_dcache_area)
mov ip, #0
#ifndef CONFIG_CPU_DCACHE_DISABLE
add r1, r0, r1
1: mcr p15, 0, r0, c7, c14, 1 @ clean+invalidate D entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
#endif
mcr p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
/*
* dma_inv_range(start, end)
*
* Invalidate (discard) the specified virtual address range.
* May not write back any entries. If 'start' or 'end'
* are not cache line aligned, those lines must be written
* back.
*
* - start - virtual start address
* - end - virtual end address
*
* (same as v4wb)
*/
arm1022_dma_inv_range:
mov ip, #0
#ifndef CONFIG_CPU_DCACHE_DISABLE
tst r0, #CACHE_DLINESIZE - 1
bic r0, r0, #CACHE_DLINESIZE - 1
mcrne p15, 0, r0, c7, c10, 1 @ clean D entry
tst r1, #CACHE_DLINESIZE - 1
mcrne p15, 0, r1, c7, c10, 1 @ clean D entry
1: mcr p15, 0, r0, c7, c6, 1 @ invalidate D entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
#endif
mcr p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
/*
* dma_clean_range(start, end)
*
* Clean the specified virtual address range.
*
* - start - virtual start address
* - end - virtual end address
*
* (same as v4wb)
*/
arm1022_dma_clean_range:
mov ip, #0
#ifndef CONFIG_CPU_DCACHE_DISABLE
bic r0, r0, #CACHE_DLINESIZE - 1
1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
#endif
mcr p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
/*
* dma_flush_range(start, end)
*
* Clean and invalidate the specified virtual address range.
*
* - start - virtual start address
* - end - virtual end address
*/
ENTRY(arm1022_dma_flush_range)
mov ip, #0
#ifndef CONFIG_CPU_DCACHE_DISABLE
bic r0, r0, #CACHE_DLINESIZE - 1
1: mcr p15, 0, r0, c7, c14, 1 @ clean+invalidate D entry
add r0, r0, #CACHE_DLINESIZE
cmp r0, r1
blo 1b
#endif
mcr p15, 0, ip, c7, c10, 4 @ drain WB
ret lr
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(arm1022_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm1022_dma_clean_range
bcs arm1022_dma_inv_range
b arm1022_dma_flush_range
ENDPROC(arm1022_dma_map_area)
/*
* dma_unmap_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(arm1022_dma_unmap_area)
ret lr
ENDPROC(arm1022_dma_unmap_area)
.globl arm1022_flush_kern_cache_louis
.equ arm1022_flush_kern_cache_louis, arm1022_flush_kern_cache_all
@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
define_cache_functions arm1022
.align 5
ENTRY(cpu_arm1022_dcache_clean_area)
#ifndef CONFIG_CPU_DCACHE_DISABLE
mov ip, #0
1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
add r0, r0, #CACHE_DLINESIZE
subs r1, r1, #CACHE_DLINESIZE
bhi 1b
#endif
ret lr
/* =============================== PageTable ============================== */
/*
* cpu_arm1022_switch_mm(pgd)
*
* Set the translation base pointer to be as described by pgd.
*
* pgd: new page tables
*/
.align 5
ENTRY(cpu_arm1022_switch_mm)
#ifdef CONFIG_MMU
#ifndef CONFIG_CPU_DCACHE_DISABLE
mov r1, #(CACHE_DSEGMENTS - 1) << 5 @ 16 segments
1: orr r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
2: mcr p15, 0, r3, c7, c14, 2 @ clean+invalidate D index
subs r3, r3, #1 << 26
bcs 2b @ entries 63 to 0
subs r1, r1, #1 << 5
bcs 1b @ segments 15 to 0
#endif
mov r1, #0
#ifndef CONFIG_CPU_ICACHE_DISABLE
mcr p15, 0, r1, c7, c5, 0 @ invalidate I cache
#endif
mcr p15, 0, r1, c7, c10, 4 @ drain WB
mcr p15, 0, r0, c2, c0, 0 @ load page table pointer
mcr p15, 0, r1, c8, c7, 0 @ invalidate I & D TLBs
#endif
ret lr
/*
* cpu_arm1022_set_pte_ext(ptep, pte, ext)
*
* Set a PTE and flush it out
*/
.align 5
ENTRY(cpu_arm1022_set_pte_ext)
#ifdef CONFIG_MMU
armv3_set_pte_ext
mov r0, r0
#ifndef CONFIG_CPU_DCACHE_DISABLE
mcr p15, 0, r0, c7, c10, 1 @ clean D entry
#endif
#endif /* CONFIG_MMU */
ret lr
.type __arm1022_setup, #function
__arm1022_setup:
mov r0, #0
mcr p15, 0, r0, c7, c7 @ invalidate I,D caches on v4
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer on v4
#ifdef CONFIG_MMU
mcr p15, 0, r0, c8, c7 @ invalidate I,D TLBs on v4
#endif
adr r5, arm1022_crval
ldmia r5, {r5, r6}
mrc p15, 0, r0, c1, c0 @ get control register v4
bic r0, r0, r5
orr r0, r0, r6
#ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
orr r0, r0, #0x4000 @ .R..............
#endif
ret lr
.size __arm1022_setup, . - __arm1022_setup
/*
* R
* .RVI ZFRS BLDP WCAM
* .011 1001 ..11 0101
*
*/
.type arm1022_crval, #object
arm1022_crval:
crval clear=0x00007f3f, mmuset=0x00003935, ucset=0x00001930
__INITDATA
@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
define_processor_functions arm1022, dabort=v4t_early_abort, pabort=legacy_pabort
.section ".rodata"
string cpu_arch_name, "armv5te"
string cpu_elf_name, "v5"
string cpu_arm1022_name, "ARM1022"
.align
.section ".proc.info.init", #alloc, #execinstr
.type __arm1022_proc_info,#object
__arm1022_proc_info:
.long 0x4105a220 @ ARM 1022E (v5TE)
.long 0xff0ffff0
.long PMD_TYPE_SECT | \
PMD_BIT4 | \
PMD_SECT_AP_WRITE | \
PMD_SECT_AP_READ
.long PMD_TYPE_SECT | \
PMD_BIT4 | \
PMD_SECT_AP_WRITE | \
PMD_SECT_AP_READ
b __arm1022_setup
.long cpu_arch_name
.long cpu_elf_name
.long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_EDSP
.long cpu_arm1022_name
.long arm1022_processor_functions
.long v4wbi_tlb_fns
.long v4wb_user_fns
.long arm1022_cache_fns
.size __arm1022_proc_info, . - __arm1022_proc_info