kernel_optimize_test/arch/arm/mm/cache-v6.S
Lorenzo Pieralisi 031bd879f7 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>
2012-09-25 11:20:25 +01:00

336 lines
7.9 KiB
ArmAsm

/*
* linux/arch/arm/mm/cache-v6.S
*
* Copyright (C) 2001 Deep Blue Solutions Ltd.
*
* 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 is the "shell" of the ARMv6 processor support.
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <asm/assembler.h>
#include <asm/errno.h>
#include <asm/unwind.h>
#include "proc-macros.S"
#define HARVARD_CACHE
#define CACHE_LINE_SIZE 32
#define D_CACHE_LINE_SIZE 32
#define BTB_FLUSH_SIZE 8
/*
* v6_flush_icache_all()
*
* Flush the whole I-cache.
*
* ARM1136 erratum 411920 - Invalidate Instruction Cache operation can fail.
* This erratum is present in 1136, 1156 and 1176. It does not affect the
* MPCore.
*
* Registers:
* r0 - set to 0
* r1 - corrupted
*/
ENTRY(v6_flush_icache_all)
mov r0, #0
#ifdef CONFIG_ARM_ERRATA_411920
mrs r1, cpsr
cpsid ifa @ disable interrupts
mcr p15, 0, r0, c7, c5, 0 @ invalidate entire I-cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate entire I-cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate entire I-cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate entire I-cache
msr cpsr_cx, r1 @ restore interrupts
.rept 11 @ ARM Ltd recommends at least
nop @ 11 NOPs
.endr
#else
mcr p15, 0, r0, c7, c5, 0 @ invalidate I-cache
#endif
mov pc, lr
ENDPROC(v6_flush_icache_all)
/*
* v6_flush_cache_all()
*
* Flush the entire cache.
*
* It is assumed that:
*/
ENTRY(v6_flush_kern_cache_all)
mov r0, #0
#ifdef HARVARD_CACHE
mcr p15, 0, r0, c7, c14, 0 @ D cache clean+invalidate
#ifndef CONFIG_ARM_ERRATA_411920
mcr p15, 0, r0, c7, c5, 0 @ I+BTB cache invalidate
#else
b v6_flush_icache_all
#endif
#else
mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate
#endif
mov pc, lr
/*
* v6_flush_cache_all()
*
* Flush all TLB entries in a particular address space
*
* - mm - mm_struct describing address space
*/
ENTRY(v6_flush_user_cache_all)
/*FALLTHROUGH*/
/*
* v6_flush_cache_range(start, end, flags)
*
* Flush a range of TLB entries in the specified address space.
*
* - start - start address (may not be aligned)
* - end - end address (exclusive, may not be aligned)
* - flags - vm_area_struct flags describing address space
*
* It is assumed that:
* - we have a VIPT cache.
*/
ENTRY(v6_flush_user_cache_range)
mov pc, lr
/*
* v6_coherent_kern_range(start,end)
*
* Ensure that the I and D caches are coherent within specified
* region. This is typically used when code has been written to
* a memory region, and will be executed.
*
* - start - virtual start address of region
* - end - virtual end address of region
*
* It is assumed that:
* - the Icache does not read data from the write buffer
*/
ENTRY(v6_coherent_kern_range)
/* FALLTHROUGH */
/*
* v6_coherent_user_range(start,end)
*
* Ensure that the I and D caches are coherent within specified
* region. This is typically used when code has been written to
* a memory region, and will be executed.
*
* - start - virtual start address of region
* - end - virtual end address of region
*
* It is assumed that:
* - the Icache does not read data from the write buffer
*/
ENTRY(v6_coherent_user_range)
UNWIND(.fnstart )
#ifdef HARVARD_CACHE
bic r0, r0, #CACHE_LINE_SIZE - 1
1:
USER( mcr p15, 0, r0, c7, c10, 1 ) @ clean D line
add r0, r0, #CACHE_LINE_SIZE
cmp r0, r1
blo 1b
#endif
mov r0, #0
#ifdef HARVARD_CACHE
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
#ifndef CONFIG_ARM_ERRATA_411920
mcr p15, 0, r0, c7, c5, 0 @ I+BTB cache invalidate
#else
b v6_flush_icache_all
#endif
#else
mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB
#endif
mov pc, lr
/*
* Fault handling for the cache operation above. If the virtual address in r0
* isn't mapped, fail with -EFAULT.
*/
9001:
mov r0, #-EFAULT
mov pc, lr
UNWIND(.fnend )
ENDPROC(v6_coherent_user_range)
ENDPROC(v6_coherent_kern_range)
/*
* v6_flush_kern_dcache_area(void *addr, size_t size)
*
* Ensure that the data held in the page kaddr is written back
* to the page in question.
*
* - addr - kernel address
* - size - region size
*/
ENTRY(v6_flush_kern_dcache_area)
add r1, r0, r1
bic r0, r0, #D_CACHE_LINE_SIZE - 1
1:
#ifdef HARVARD_CACHE
mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line
#else
mcr p15, 0, r0, c7, c15, 1 @ clean & invalidate unified line
#endif
add r0, r0, #D_CACHE_LINE_SIZE
cmp r0, r1
blo 1b
#ifdef HARVARD_CACHE
mov r0, #0
mcr p15, 0, r0, c7, c10, 4
#endif
mov pc, lr
/*
* v6_dma_inv_range(start,end)
*
* Invalidate the data cache within the specified region; we will
* be performing a DMA operation in this region and we want to
* purge old data in the cache.
*
* - start - virtual start address of region
* - end - virtual end address of region
*/
v6_dma_inv_range:
#ifdef CONFIG_DMA_CACHE_RWFO
ldrb r2, [r0] @ read for ownership
strb r2, [r0] @ write for ownership
#endif
tst r0, #D_CACHE_LINE_SIZE - 1
bic r0, r0, #D_CACHE_LINE_SIZE - 1
#ifdef HARVARD_CACHE
mcrne p15, 0, r0, c7, c10, 1 @ clean D line
#else
mcrne p15, 0, r0, c7, c11, 1 @ clean unified line
#endif
tst r1, #D_CACHE_LINE_SIZE - 1
#ifdef CONFIG_DMA_CACHE_RWFO
ldrneb r2, [r1, #-1] @ read for ownership
strneb r2, [r1, #-1] @ write for ownership
#endif
bic r1, r1, #D_CACHE_LINE_SIZE - 1
#ifdef HARVARD_CACHE
mcrne p15, 0, r1, c7, c14, 1 @ clean & invalidate D line
#else
mcrne p15, 0, r1, c7, c15, 1 @ clean & invalidate unified line
#endif
1:
#ifdef HARVARD_CACHE
mcr p15, 0, r0, c7, c6, 1 @ invalidate D line
#else
mcr p15, 0, r0, c7, c7, 1 @ invalidate unified line
#endif
add r0, r0, #D_CACHE_LINE_SIZE
cmp r0, r1
#ifdef CONFIG_DMA_CACHE_RWFO
ldrlo r2, [r0] @ read for ownership
strlo r2, [r0] @ write for ownership
#endif
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mov pc, lr
/*
* v6_dma_clean_range(start,end)
* - start - virtual start address of region
* - end - virtual end address of region
*/
v6_dma_clean_range:
bic r0, r0, #D_CACHE_LINE_SIZE - 1
1:
#ifdef CONFIG_DMA_CACHE_RWFO
ldr r2, [r0] @ read for ownership
#endif
#ifdef HARVARD_CACHE
mcr p15, 0, r0, c7, c10, 1 @ clean D line
#else
mcr p15, 0, r0, c7, c11, 1 @ clean unified line
#endif
add r0, r0, #D_CACHE_LINE_SIZE
cmp r0, r1
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mov pc, lr
/*
* v6_dma_flush_range(start,end)
* - start - virtual start address of region
* - end - virtual end address of region
*/
ENTRY(v6_dma_flush_range)
#ifdef CONFIG_DMA_CACHE_RWFO
ldrb r2, [r0] @ read for ownership
strb r2, [r0] @ write for ownership
#endif
bic r0, r0, #D_CACHE_LINE_SIZE - 1
1:
#ifdef HARVARD_CACHE
mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line
#else
mcr p15, 0, r0, c7, c15, 1 @ clean & invalidate line
#endif
add r0, r0, #D_CACHE_LINE_SIZE
cmp r0, r1
#ifdef CONFIG_DMA_CACHE_RWFO
ldrlob r2, [r0] @ read for ownership
strlob r2, [r0] @ write for ownership
#endif
blo 1b
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
mov pc, lr
/*
* dma_map_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(v6_dma_map_area)
add r1, r1, r0
teq r2, #DMA_FROM_DEVICE
beq v6_dma_inv_range
#ifndef CONFIG_DMA_CACHE_RWFO
b v6_dma_clean_range
#else
teq r2, #DMA_TO_DEVICE
beq v6_dma_clean_range
b v6_dma_flush_range
#endif
ENDPROC(v6_dma_map_area)
/*
* dma_unmap_area(start, size, dir)
* - start - kernel virtual start address
* - size - size of region
* - dir - DMA direction
*/
ENTRY(v6_dma_unmap_area)
#ifndef CONFIG_DMA_CACHE_RWFO
add r1, r1, r0
teq r2, #DMA_TO_DEVICE
bne v6_dma_inv_range
#endif
mov pc, lr
ENDPROC(v6_dma_unmap_area)
.globl v6_flush_kern_cache_louis
.equ v6_flush_kern_cache_louis, v6_flush_kern_cache_all
__INITDATA
@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
define_cache_functions v6