linux/arch/arm/mm/proc-arm1026.S

469 lines
11 KiB
ArmAsm
Raw Normal View History

/*
* linux/arch/arm/mm/proc-arm1026.S: MMU functions for ARM1026EJ-S
*
* 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 ARM1026EJ-S.
*/
#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_arm1026_proc_init()
*/
ENTRY(cpu_arm1026_proc_init)
mov pc, lr
/*
* cpu_arm1026_proc_fin()
*/
ENTRY(cpu_arm1026_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
mov pc, lr
/*
* cpu_arm1026_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_arm1026_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
mov pc, r0
ENDPROC(cpu_arm1026_reset)
.popsection
/*
* cpu_arm1026_do_idle()
*/
.align 5
ENTRY(cpu_arm1026_do_idle)
mcr p15, 0, r0, c7, c0, 4 @ Wait for interrupt
mov pc, lr
/* ================================= CACHE ================================ */
.align 5
ARM: 6466/1: implement flush_icache_all for the rest of the CPUs Commit 81d11955bf0 ("ARM: 6405/1: Handle __flush_icache_all for CONFIG_SMP_ON_UP") added a new function to struct cpu_cache_fns: flush_icache_all(). It also implemented this for v6 and v7 but not for v5 and backwards. Without the function pointer in place, we will be calling wrong cache functions. For example with ep93xx we get following: Unable to handle kernel paging request at virtual address ee070f38 pgd = c0004000 [ee070f38] *pgd=00000000 Internal error: Oops: 80000005 [#1] PREEMPT last sysfs file: Modules linked in: CPU: 0 Not tainted (2.6.36+ #1) PC is at 0xee070f38 LR is at __dma_alloc+0x11c/0x2d0 pc : [<ee070f38>] lr : [<c0032c8c>] psr: 60000013 sp : c581bde0 ip : 00000000 fp : c0472000 r10: c0472000 r9 : 000000d0 r8 : 00020000 r7 : 0001ffff r6 : 00000000 r5 : c0472400 r4 : c5980000 r3 : c03ab7e0 r2 : 00000000 r1 : c59a0000 r0 : c5980000 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: c000717f Table: c0004000 DAC: 00000017 Process swapper (pid: 1, stack limit = 0xc581a270) [<c0032c8c>] (__dma_alloc+0x11c/0x2d0) [<c0032e5c>] (dma_alloc_writecombine+0x1c/0x24) [<c0204148>] (ep93xx_pcm_preallocate_dma_buffer+0x44/0x60) [<c02041c0>] (ep93xx_pcm_new+0x5c/0x88) [<c01ff188>] (snd_soc_instantiate_cards+0x8a8/0xbc0) [<c01ff59c>] (soc_probe+0xfc/0x134) [<c01adafc>] (platform_drv_probe+0x18/0x1c) [<c01acca4>] (driver_probe_device+0xb0/0x16c) [<c01ac284>] (bus_for_each_drv+0x48/0x84) [<c01ace90>] (device_attach+0x50/0x68) [<c01ac0f8>] (bus_probe_device+0x24/0x44) [<c01aad7c>] (device_add+0x2fc/0x44c) [<c01adfa8>] (platform_device_add+0x104/0x15c) [<c0015eb8>] (simone_init+0x60/0x94) [<c0021410>] (do_one_initcall+0xd0/0x1a4) __dma_alloc() calls (inlined) __dma_alloc_buffer() which ends up calling dmac_flush_range(). Now since the entries in the arm920_cache_fns are shifted by one, we jump into address 0xee070f38 which is actually next instruction after the arm920_cache_fns structure. So implement flush_icache_all() for the rest of the supported CPUs using a generic 'invalidate I cache' instruction. Signed-off-by: Mika Westerberg <mika.westerberg@iki.fi> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2010-10-28 10:27:40 +00:00
/*
* flush_icache_all()
*
* Unconditionally clean and invalidate the entire icache.
*/
ENTRY(arm1026_flush_icache_all)
#ifndef CONFIG_CPU_ICACHE_DISABLE
mov r0, #0
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
#endif
mov pc, lr
ENDPROC(arm1026_flush_icache_all)
/*
* flush_user_cache_all()
*
* Invalidate all cache entries in a particular address
* space.
*/
ENTRY(arm1026_flush_user_cache_all)
/* FALLTHROUGH */
/*
* flush_kern_cache_all()
*
* Clean and invalidate the entire cache.
*/
ENTRY(arm1026_flush_kern_cache_all)
mov r2, #VM_EXEC
mov ip, #0
__flush_whole_cache:
#ifndef CONFIG_CPU_DCACHE_DISABLE
1: mrc p15, 0, r15, c7, c14, 3 @ test, clean, invalidate
bne 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
mov pc, 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(arm1026_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
mov pc, 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(arm1026_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(arm1026_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
mov pc, 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(arm1026_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
mov pc, 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)
*/
arm1026_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
mov pc, lr
/*
* dma_clean_range(start, end)
*
* Clean the specified virtual address range.
*
* - start - virtual start address
* - end - virtual end address
*
* (same as v4wb)
*/
arm1026_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
mov pc, lr
/*
* dma_flush_range(start, end)
*
* Clean and invalidate the specified virtual address range.
*
* - start - virtual start address
* - end - virtual end address
*/
ENTRY(arm1026_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
mov pc, lr
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(arm1026_dma_map_area)
add r1, r1, r0
cmp r2, #DMA_TO_DEVICE
beq arm1026_dma_clean_range
bcs arm1026_dma_inv_range
b arm1026_dma_flush_range
ENDPROC(arm1026_dma_map_area)
/*
* dma_unmap_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(arm1026_dma_unmap_area)
mov pc, lr
ENDPROC(arm1026_dma_unmap_area)
ARM: mm: implement LoUIS API for cache maintenance ops ARM v7 architecture introduced the concept of cache levels and related control registers. New processors like A7 and A15 embed an L2 unified cache controller that becomes part of the cache level hierarchy. Some operations in the kernel like cpu_suspend and __cpu_disable do not require a flush of the entire cache hierarchy to DRAM but just the cache levels belonging to the Level of Unification Inner Shareable (LoUIS), which in most of ARM v7 systems correspond to L1. The current cache flushing API used in cpu_suspend and __cpu_disable, flush_cache_all(), ends up flushing the whole cache hierarchy since for v7 it cleans and invalidates all cache levels up to Level of Coherency (LoC) which cripples system performance when used in hot paths like hotplug and cpuidle. Therefore a new kernel cache maintenance API must be added to cope with latest ARM system requirements. This patch adds flush_cache_louis() to the ARM kernel cache maintenance API. This function cleans and invalidates all data cache levels up to the Level of Unification Inner Shareable (LoUIS) and invalidates the instruction cache for processors that support it (> v7). This patch also creates an alias of the cache LoUIS function to flush_kern_all for all processor versions prior to v7, so that the current cache flushing behaviour is unchanged for those processors. v7 cache maintenance code implements a cache LoUIS function that cleans and invalidates the D-cache up to LoUIS and invalidates the I-cache, according to the new API. Reviewed-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Reviewed-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Tested-by: Shawn Guo <shawn.guo@linaro.org>
2012-09-06 13:05:13 +00:00
.globl arm1026_flush_kern_cache_louis
.equ arm1026_flush_kern_cache_louis, arm1026_flush_kern_cache_all
@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
define_cache_functions arm1026
.align 5
ENTRY(cpu_arm1026_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
mov pc, lr
/* =============================== PageTable ============================== */
/*
* cpu_arm1026_switch_mm(pgd)
*
* Set the translation base pointer to be as described by pgd.
*
* pgd: new page tables
*/
.align 5
ENTRY(cpu_arm1026_switch_mm)
#ifdef CONFIG_MMU
mov r1, #0
#ifndef CONFIG_CPU_DCACHE_DISABLE
1: mrc p15, 0, r15, c7, c14, 3 @ test, clean, invalidate
bne 1b
#endif
#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
mov pc, lr
/*
* cpu_arm1026_set_pte_ext(ptep, pte, ext)
*
* Set a PTE and flush it out
*/
.align 5
ENTRY(cpu_arm1026_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 */
mov pc, lr
.type __arm1026_setup, #function
__arm1026_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
mcr p15, 0, r4, c2, c0 @ load page table pointer
#endif
#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
mov r0, #4 @ explicitly disable writeback
mcr p15, 7, r0, c15, c0, 0
#endif
adr r5, arm1026_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
mov pc, lr
.size __arm1026_setup, . - __arm1026_setup
/*
* R
* .RVI ZFRS BLDP WCAM
* .011 1001 ..11 0101
*
*/
.type arm1026_crval, #object
arm1026_crval:
crval clear=0x00007f3f, mmuset=0x00003935, ucset=0x00001934
__INITDATA
@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
define_processor_functions arm1026, dabort=v5t_early_abort, pabort=legacy_pabort
.section .rodata
string cpu_arch_name, "armv5tej"
string cpu_elf_name, "v5"
.align
string cpu_arm1026_name, "ARM1026EJ-S"
.align
.section ".proc.info.init", #alloc, #execinstr
.type __arm1026_proc_info,#object
__arm1026_proc_info:
.long 0x4106a260 @ ARM 1026EJ-S (v5TEJ)
.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 __arm1026_setup
.long cpu_arch_name
.long cpu_elf_name
.long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA
.long cpu_arm1026_name
.long arm1026_processor_functions
.long v4wbi_tlb_fns
.long v4wb_user_fns
.long arm1026_cache_fns
.size __arm1026_proc_info, . - __arm1026_proc_info