mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 01:26:44 +07:00
2ffe2da3e7
ARMv6 and ARMv7 CPUs can perform speculative prefetching, which makes DMA cache coherency handling slightly more interesting. Rather than being able to rely upon the CPU not accessing the DMA buffer until DMA has completed, we now must expect that the cache could be loaded with possibly stale data from the DMA buffer. Where DMA involves data being transferred to the device, we clean the cache before handing it over for DMA, otherwise we invalidate the buffer to get rid of potential writebacks. On DMA Completion, if data was transferred from the device, we invalidate the buffer to get rid of any stale speculative prefetches. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Tested-By: Santosh Shilimkar <santosh.shilimkar@ti.com>
306 lines
7.1 KiB
ArmAsm
306 lines
7.1 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/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
|
|
|
|
#ifdef CONFIG_ARM_ERRATA_411920
|
|
/*
|
|
* Invalidate the entire I cache (this code is a workaround for the 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_icache_inval_all)
|
|
mov r0, #0
|
|
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
|
|
mov pc, lr
|
|
#endif
|
|
|
|
/*
|
|
* 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_icache_inval_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
|
|
2:
|
|
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_icache_inval_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, just try the next page.
|
|
*/
|
|
9001:
|
|
mov r0, r0, lsr #12
|
|
mov r0, r0, lsl #12
|
|
add r0, r0, #4096
|
|
b 2b
|
|
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
|
|
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:
|
|
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
|
|
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
|
|
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 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)
|
|
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
|
|
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
|
|
b v6_dma_clean_range
|
|
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)
|
|
add r1, r1, r0
|
|
teq r2, #DMA_TO_DEVICE
|
|
bne v6_dma_inv_range
|
|
mov pc, lr
|
|
ENDPROC(v6_dma_unmap_area)
|
|
|
|
__INITDATA
|
|
|
|
.type v6_cache_fns, #object
|
|
ENTRY(v6_cache_fns)
|
|
.long v6_flush_kern_cache_all
|
|
.long v6_flush_user_cache_all
|
|
.long v6_flush_user_cache_range
|
|
.long v6_coherent_kern_range
|
|
.long v6_coherent_user_range
|
|
.long v6_flush_kern_dcache_area
|
|
.long v6_dma_map_area
|
|
.long v6_dma_unmap_area
|
|
.long v6_dma_flush_range
|
|
.size v6_cache_fns, . - v6_cache_fns
|