//@arch/arm/kernel/setup.c
void __init setup_arch(char **cmdline_p)
+-- setup_processor(void)
+-- struct proc_info_list *list; //struct proc_info_lsit ...
//locate processor in the list of supported processor types. The linker builds this
//table for us from the entries in arch/arm/mm/proc-*.S
+-- list = lookup_processor_type(read_cpuid_id()); //lookup_processor_type()@
+-- cpu_name = list->cpu_name;
+-- __cpu_architecture = __get_cpu_architecture();
+-- processor = *list->proc;
+-- cpu_tlb = *list->tlb; //所有tlb相关的函数集都从这里得到.
+-- cpu_user = *list->user;
+-- cpu_cache = *list->cache; //cpu_cache是从list中拿到的,而list通过汇编函数lookup_processor_type获得
+-- elf_hwcap = list->elf_hwcap;
+-- feat_v6_fixup();
+-- cacheid_init();
+-- cpu_init();
//struct proc_info_lsit的定义如下:
//@arch/arm/include/asm/procinfo.h
##########################################
//Note! struct processor is always defined if we're using MULTI_CPU, otherwise this entry
//is unused, but still exists.
//NOTE! The following structure is defined by assembly language, NOT C code. For more information,
//check: arch/arm/mm/proc-*.S and arch/arm/kernel/head.S
struct proc_info_list {
unsigned int cpu_val;
unsigned int cpu_mask;
unsigned long __cpu_mm_mmu_flags; /* used by head.S */
unsigned long __cpu_io_mmu_flags; /* used by head.S */
unsigned long __cpu_flush; /* used by head.S */
const char *arch_name;
const char *elf_name;
unsigned int elf_hwcap;
const char *cpu_name;
struct processor *proc;
struct cpu_tlb_fns *tlb;
struct cpu_user_fns *user;
struct cpu_cache_fns *cache;
};
@arch/arm/kernel/head-common.S
/*
* This provides a C-API version of __lookup_processor_type
*/
ENTRY(lookup_processor_type)
stmfd sp!, {r4 - r6, r9, lr}
mov r9, r0
bl __lookup_processor_type
mov r0, r5
ldmfd sp!, {r4 - r6, r9, pc}
ENDPROC(lookup_processor_type)
/*
* Read processor ID register (CP#15, CR0), and look up in the linker-built
* supported processor list. Note that we can't use the absolute addresses
* for the __proc_info lists since we aren't running with the MMU on
* (and therefore, we are not in the correct address space). We have to
* calculate the offset.
*
* r9 = cpuid
* Returns:
* r3, r4, r6 corrupted
* r5 = proc_info pointer in physical address space
* r9 = cpuid (preserved)
*/
__CPUINIT
__lookup_processor_type:
adr r3, __lookup_processor_type_data
ldmia r3, {r4 - r6}
sub r3, r3, r4 @ get offset between virt&phys
add r5, r5, r3 @ convert virt addresses to
add r6, r6, r3 @ physical address space
1: ldmia r5, {r3, r4} @ value, mask
and r4, r4, r9 @ mask wanted bits
teq r3, r4
beq 2f
add r5, r5, #PROC_INFO_SZ @ sizeof(proc_info_list)
cmp r5, r6
blo 1b
mov r5, #0 @ unknown processor
2: mov pc, lr
ENDPROC(__lookup_processor_type)
/*
* Look in <asm/procinfo.h> for information about the __proc_info structure.
*/
.align 2
.type __lookup_processor_type_data, %object
__lookup_processor_type_data:
.long .
.long __proc_info_begin @r4
.long __proc_info_end @r5
.size __lookup_processor_type_data, . - __lookup_processor_type_data @r6
@arch/arm/kernel/vmlinux.lds.S
....
#define PROC_INFO \
. = ALIGN(4); \
VMLINUX_SYMBOL(__proc_info_begin) = .; \
*(.proc.info.init) \
VMLINUX_SYMBOL(__proc_info_end) = .;
....
.text : {
....
*(.got) /* Global offset table */
ARM_CPU_KEEP(PROC_INFO)
....
_etext = .; /* End of text and rodata section */
....
.init.proc.info : {
ARM_CPU_DISCARD(PROC_INFO)
}
.init.arch.info : {
__arch_info_begin = .;
*(.arch.info.init)
__arch_info_end = .;
}
.init.tagtable : {
__tagtable_begin = .;
*(.taglist.init)
__tagtable_end = .;
}
....
}
ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
//proc_info_list结构的定义如下
@arch/arm/include/asm/procinfo.h
struct proc_info_list {
unsigned int cpu_val;
unsigned int cpu_mask;
unsigned long __cpu_mm_mmu_flags; /* used by head.S */
unsigned long __cpu_io_mmu_flags; /* used by head.S */
unsigned long __cpu_flush; /* used by head.S */
const char *arch_name;
const char *elf_name;
unsigned int elf_hwcap;
const char *cpu_name;
struct processor *proc;
struct cpu_tlb_fns *tlb;
struct cpu_user_fns *user;
struct cpu_cache_fns *cache; //cpu cache的操作函数集.
};
//cpu_cache_fns结构的定义如下:
@arch/arm/include/asm/cacheflush.h
/*
* 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_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_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 *);
};
@arch/arm/include/asm/cacheflush.h
#ifdef MULTI_CPU
struct processor processor __read_mostly;
#endif
#ifdef MULTI_TLB
struct cpu_tlb_fns cpu_tlb __read_mostly;
#endif
#ifdef MULTI_USER
struct cpu_user_fns cpu_user __read_mostly;
#endif
#ifdef MULTI_CACHE
=>ruct cpu_cache_fns cpu_cache __read_mostly;
#endif
#ifdef CONFIG_OUTER_CACHE
struct outer_cache_fns outer_cache __read_mostly;
EXPORT_SYMBOL(outer_cache);
#endif
##########################################################
@arch/arm/include/asm/cacheflush.h
#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_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_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 void __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
//@arch/arm/mm/proc-arm920.S
...
.align
.section ".proc.info.init", #alloc, #execinstr //__arm920_proc_info就被分配在这个段.
.type __arm920_proc_info,#object
__arm920_proc_info:
.long 0x41009200
.long 0xff00fff0
.long PMD_TYPE_SECT | \
PMD_SECT_BUFFERABLE | \
PMD_SECT_CACHEABLE | \
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 __arm920_setup
.long cpu_arch_name
.long cpu_elf_name
.long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
.long cpu_arm920_name
.long arm920_processor_functions
.long v4wbi_tlb_fns
.long v4wb_user_fns
#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
.long arm920_cache_fns
#else
.long v4wt_cache_fns
#endif
.size __arm920_proc_info, . - __arm920_proc_info
//再找v4wt_cache_fns的定义,这个变量直接grep是找不到的,因此可以推断是用预处理器宏定义的
//结合struct cpu_cache_fns 的注释可以发现v4wt对应的函数集貌似在cache-v4wt.S文件中定义了
[zrlean@e4]$grep ENTRY cache-v4wt.S
ENTRY(v4wt_flush_icache_all)
ENTRY(v4wt_flush_user_cache_all)
ENTRY(v4wt_flush_kern_cache_all)
ENTRY(v4wt_flush_user_cache_range)
ENTRY(v4wt_coherent_kern_range)
ENTRY(v4wt_coherent_user_range)
ENTRY(v4wt_flush_kern_dcache_area)
ENTRY(v4wt_dma_unmap_area)
ENTRY(v4wt_dma_map_area)
//而在arch/arm/mm/cache-v4wt.S文件的最后有如下定义
__INITDATA
@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
define_cache_functions v4wt
//这里的define_cache_functions是一个汇编定义的宏
@arch/arm/mm/proc-macro.S
...
.macro define_cache_functions name:req
.align 2
.type \name\()_cache_fns, #object
ENTRY(\name\()_cache_fns)
.long \name\()_flush_icache_all
.long \name\()_flush_kern_cache_all
.long \name\()_flush_user_cache_all
.long \name\()_flush_user_cache_range
.long \name\()_coherent_kern_range
.long \name\()_coherent_user_range
.long \name\()_flush_kern_dcache_area
.long \name\()_dma_map_area
.long \name\()_dma_unmap_area
.long \name\()_dma_flush_range
.size \name\()_cache_fns, . - \name\()_cache_fns
.endm
//因此 define_cache_functions v4wt 实际就是
.align 2
.type v4wt_cache_fns, #object
ENTRY(v4wt_cache_fns)
.long v4wt_flush_icache_all
.long v4wt_flush_kern_cache_all
.long v4wt_flush_user_cache_all
.long v4wt_flush_user_cache_range
.long v4wt_coherent_kern_range
.long v4wt_coherent_user_range
.long v4wt_flush_kern_dcache_area
.long v4wt_dma_map_area
.long v4wt_dma_unmap_area
.long v4wt_dma_flush_range
.size v4wt_cache_fns, . - v4wt_cache_fns
//而v4wt_cache_fns,刚好就是__arm920_proc_info.cache被初始化成的那个struct proc_info_list指针.
//这样,所有这写操作cache的函数就都找到了