armv7对应的CACHE操作相关文件解析

最近在使用TI的DRA726芯片。A15端需要访问图像，而图像是在外设空间的，用DMA拷贝到CACHE空间。

这样就导致了DMA的CACHE一致性的问题，需要在DMA之后清除所使用图像空间的数据CACHE。

以这个A15核心为例，解析一下ARM的CACHE操作，涉及的文件有：cacheflush.h   cache-v7.S  proc-macros.S  proc-v7.S

内存是OS中非常厉害，非常复杂的一套系统，科学严谨，每一部分都需要研究几本书才能够彻底明白。

CACHE最基本的就是加速原理，依据就是程序的局部性原理。

CACHE实际实施起来，细节就非常复杂了，比如启动的过程中，如何建立CACHE，从直接访问内存到CACHE访问等等具体问题。

这次主要就项目中的CACHE一致性问题，借机会给组员们一起分享了。

/*
 *  arch/arm/include/asm/cacheflush.h
 *
 *  Copyright (C) 1999-2002 Russell King
 *
 * 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.
 */
#ifndef _ASMARM_CACHEFLUSH_H
#define _ASMARM_CACHEFLUSH_H

#include <linux/mm.h>

#include <asm/glue-cache.h>
#include <asm/shmparam.h>
#include <asm/cachetype.h>
#include <asm/outercache.h>

#define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)

/*
 * This flag is used to indicate that the page pointed to by a pte is clean
 * and does not require cleaning before returning it to the user.
 */
#define PG_dcache_clean PG_arch_1

/*
 *	MM Cache Management
 *	===================
 *
 *	The arch/arm/mm/cache-*.S and arch/arm/mm/proc-*.S files
 *	implement these methods.
 *
 *	Start addresses are inclusive and end addresses are exclusive;
 *	start addresses should be rounded down, end addresses up.
 *
 *	See Documentation/cachetlb.txt for more information.
 *	Please note that the implementation of these, and the required
 *	effects are cache-type (VIVT/VIPT/PIPT) specific.
 *
 *	flush_icache_all()
 *
 *		Unconditionally clean and invalidate the entire icache.
 *		Currently only needed for cache-v6.S and cache-v7.S, see
 *		__flush_icache_all for the generic implementation.
 *
 *	flush_kern_all()
 *
 *		Unconditionally clean and invalidate the entire cache.
 *
 *     flush_kern_louis()
 *
 *             Flush data cache levels up to the level of unification
 *             inner shareable and invalidate the I-cache.
 *             Only needed from v7 onwards, falls back to flush_cache_all()
 *             for all other processor versions.
 *
 *	flush_user_all()
 *
 *		Clean and invalidate all user space cache entries
 *		before a change of page tables.
 *
 *	flush_user_range(start, end, flags)
 *
 *		Clean and invalidate a range of cache entries in the
 *		specified address space before a change of page tables.
 *		- start - user start address (inclusive, page aligned)
 *		- end   - user end address   (exclusive, page aligned)
 *		- flags - vma->vm_flags field
 *
 *	coherent_kern_range(start, end)
 *
 *		Ensure coherency between the Icache and the Dcache in the
 *		region described by start, end.  If you have non-snooping
 *		Harvard caches, you need to implement this function.
 *		- start  - virtual start address
 *		- end    - virtual end address
 *
 *	coherent_user_range(start, end)
 *
 *		Ensure coherency between the Icache and the Dcache in the
 *		region described by start, end.  If you have non-snooping
 *		Harvard caches, you need to implement this function.
 *		- start  - virtual start address
 *		- end    - virtual end address
 *
 *	flush_kern_dcache_area(kaddr, size)
 *
 *		Ensure that the data held in page is written back.
 *		- kaddr  - page address
 *		- size   - region size
 *
 *	DMA Cache Coherency
 *	===================
 *
 *	dma_flush_range(start, end)
 *
 *		Clean and invalidate the specified virtual address range.
 *		- start  - virtual start address
 *		- end    - virtual end address
 */

struct cpu_cache_fns {
	void (*flush_icache_all)(void);
	void (*flush_kern_all)(void);
	void (*flush_kern_louis)(void);
	void (*flush_user_all)(void);
	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);

	void (*coherent_kern_range)(unsigned long, unsigned long);
	int  (*coherent_user_range)(unsigned long, unsigned long);
	void (*flush_kern_dcache_area)(void *, size_t);

	void (*dma_map_area)(const void *, size_t, int);
	void (*dma_unmap_area)(const void *, size_t, int);

	void (*dma_flush_range)(const void *, const void *);
};

/*
 * Select the calling method
 */
#ifdef MULTI_CACHE

extern struct cpu_cache_fns cpu_cache;

#define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
#define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
#define __cpuc_flush_kern_louis		cpu_cache.flush_kern_louis
#define __cpuc_flush_user_all		cpu_cache.flush_user_all
#define __cpuc_flush_user_range		cpu_cache.flush_user_range
#define __cpuc_coherent_kern_range	cpu_cache.coherent_kern_range
#define __cpuc_coherent_user_range	cpu_cache.coherent_user_range
#define __cpuc_flush_dcache_area	cpu_cache.flush_kern_dcache_area

/*
 * These are private to the dma-mapping API.  Do not use directly.
 * Their sole purpose is to ensure that data held in the cache
 * is visible to DMA, or data written by DMA to system memory is
 * visible to the CPU.
 */
#define dmac_map_area			cpu_cache.dma_map_area
#define dmac_unmap_area			cpu_cache.dma_unmap_area
#define dmac_flush_range		cpu_cache.dma_flush_range

#else

extern void __cpuc_flush_icache_all(void);
extern void __cpuc_flush_kern_all(void);
extern void __cpuc_flush_kern_louis(void);
extern void __cpuc_flush_user_all(void);
extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
extern int  __cpuc_coherent_user_range(unsigned long, unsigned long);
extern void __cpuc_flush_dcache_area(void *, size_t);

/*
 * These are private to the dma-mapping API.  Do not use directly.
 * Their sole purpose is to ensure that data held in the cache
 * is visible to DMA, or data written by DMA to system memory is
 * visible to the CPU.
 */
extern void dmac_map_area(const void *, size_t, int);
extern void dmac_unmap_area(const void *, size_t, int);
extern void dmac_flush_range(const void *, const void *);

#endif

/*
 * Copy user data from/to a page which is mapped into a different
 * processes address space.  Really, we want to allow our "user
 * space" model to handle this.
 */
extern void copy_to_user_page(struct vm_area_struct *, struct page *,
	unsigned long, void *, const void *, unsigned long);
#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
	do {							\
		memcpy(dst, src, len);				\
	} while (0)

/*
 * Convert calls to our calling convention.
 */

/* Invalidate I-cache */
#define __flush_icache_all_generic()					\
	asm("mcr	p15, 0, %0, c7, c5, 0"				\
	    : : "r" (0));

/* Invalidate I-cache inner shareable */
#define __flush_icache_all_v7_smp()					\
	asm("mcr	p15, 0, %0, c7, c1, 0"				\
	    : : "r" (0));

/*
 * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
 * will fall through to use __flush_icache_all_generic.
 */
#if (defined(CONFIG_CPU_V7) && \
     (defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K))) || \
	defined(CONFIG_SMP_ON_UP)
#define __flush_icache_preferred	__cpuc_flush_icache_all
#elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
#define __flush_icache_preferred	__flush_icache_all_v7_smp
#elif __LINUX_ARM_ARCH__ == 6 && defined(CONFIG_ARM_ERRATA_411920)
#define __flush_icache_preferred	__cpuc_flush_icache_all
#else
#define __flush_icache_preferred	__flush_icache_all_generic
#endif

static inline void __flush_icache_all(void)
{
	__flush_icache_preferred();
	dsb();
}

/*
 * Flush caches up to Level of Unification Inner Shareable
 */
#define flush_cache_louis()		__cpuc_flush_kern_louis()

#define flush_cache_all()		__cpuc_flush_kern_all()

static inline void vivt_flush_cache_mm(struct mm_struct *mm)
{
	if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
		__cpuc_flush_user_all();
}

static inline void
vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
	struct mm_struct *mm = vma->vm_mm;

	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
					vma->vm_flags);
}

static inline void
vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
{
	struct mm_struct *mm = vma->vm_mm;

	if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
		unsigned long addr = user_addr & PAGE_MASK;
		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
	}
}

#ifndef CONFIG_CPU_CACHE_VIPT
#define flush_cache_mm(mm) \
		vivt_flush_cache_mm(mm)
#define flush_cache_range(vma,start,end) \
		vivt_flush_cache_range(vma,start,end)
#define flush_cache_page(vma,addr,pfn) \
		vivt_flush_cache_page(vma,addr,pfn)
#else
extern void flush_cache_mm(struct mm_struct *mm);
extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn);
#endif

#define flush_cache_dup_mm(mm) flush_cache_mm(mm)

/*
 * flush_cache_user_range is used when we want to ensure that the
 * Harvard caches are synchronised for the user space address range.
 * This is used for the ARM private sys_cacheflush system call.
 */
#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)

/*
 * Perform necessary cache operations to ensure that data previously
 * stored within this range of addresses can be executed by the CPU.
 */
#define flush_icache_range(s,e)		__cpuc_coherent_kern_range(s,e)

/*
 * Perform necessary cache operations to ensure that the TLB will
 * see data written in the specified area.
 */
#define clean_dcache_area(start,size)	cpu_dcache_clean_area(start, size)

/*
 * flush_dcache_page is used when the kernel has written to the page
 * cache page at virtual address page->virtual.
 *
 * If this page isn't mapped (ie, page_mapping == NULL), or it might
 * have userspace mappings, then we _must_ always clean + invalidate
 * the dcache entries associated with the kernel mapping.
 *
 * Otherwise we can defer the operation, and clean the cache when we are
 * about to change to user space.  This is the same method as used on SPARC64.
 * See update_mmu_cache for the user space part.
 */
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);

static inline void flush_kernel_vmap_range(void *addr, int size)
{
	if ((cache_is_vivt() || cache_is_vipt_aliasing()))
	  __cpuc_flush_dcache_area(addr, (size_t)size);
}
static inline void invalidate_kernel_vmap_range(void *addr, int size)
{
	if ((cache_i