Linux 启动流程之自解压（三）
4 打开cache
/*
* Set up a page table only if it won't overwrite ourself.
* That means r4 < pc || r4 - 16k page directory > &_end.
* Given that r4 > &_end is most unfrequent, we add a rough
* additional 1MB of room for a possible appended DTB.
*/
//只有在页表不会覆盖我们自己的情况下才设置页表。
//这意味着r4 < pc || r4 - 16k页表> 当前地址。
//考虑到r4 >和_end是最不常见的，我们为可能附加的
//DTB增加了大约1MB的空间。
mov r0, pc
cmp r0, r4
ldrcc r0, LC0+32
addcc r0, r0, pc
cmpcc r4, r0
orrcc r4, r4, #1 @ remember we skipped cache_on
blcs cache_on
/*
* Turn on the cache. We need to setup some page tables so that we
* can have both the I and D caches on.
*
* We place the page tables 16k down from the kernel execution address,
* and we hope that nothing else is using it. If we're using it, we
* will go pop!
*
* On entry,
* r4 = kernel execution address
* r7 = architecture number
* r8 = atags pointer
* On exit,
* r0, r1, r2, r3, r9, r10, r12 corrupted
* This routine must preserve:
* r4, r7, r8
*/
//打开缓存。我们需要设置一些页表，这样我们就可以同时拥有I和D缓存。
//我们将页表放在离内核执行地址16k以下的位置，希望没有其他东西在使用它。
//如果我们用它，我们就会爆掉!
//在入口处,
//r4 =内核执行地址
//r7 =体系结构编号
//r8 = atags指针
//在退出时,r0 r1 r2 r3 r9 r10 r12损坏
//这个程序必须保留:r4、r7 r8
.align 5
cache_on: mov r3, #8 @ cache_on function
b call_cache_fn
call_cache_fn: adr r12, proc_types
#ifdef CONFIG_CPU_CP15
mrc p15, 0, r9, c0, c0 @ get processor ID，获取cpu_id
#elif defined(CONFIG_CPU_V7M)
/*
* On v7-M the processor id is located in the V7M_SCB_CPUID
* register, but as cache handling is IMPLEMENTATION DEFINED on
* v7-M (if existant at all) we just return early here.
* If V7M_SCB_CPUID were used the cpu ID functions (i.e.
* __armv7_mmu_cache_{on,off,flush}) would be selected which
* use cp15 registers that are not implemented on v7-M.
*/
bx lr
#else
ldr r9, =CONFIG_PROCESSOR_ID
#endif
1: ldr r1, [r12, #0] @ get value
ldr r2, [r12, #4] @ get mask
eor r1, r1, r9 @ (real ^ match)
tst r1, r2 @ & mask
ARM( addeq pc, r12, r3 ) @ call cache function，调用具体的cache函数
THUMB( addeq r12, r3 )
THUMB( moveq pc, r12 ) @ call cache function
add r12, r12, #PROC_ENTRY_SIZE
b 1b
/*
* Table for cache operations. This is basically:
* - CPU ID match
* - CPU ID mask
* - 'cache on' method instruction
* - 'cache off' method instruction
* - 'cache flush' method instruction
*
* We match an entry using: ((real_id ^ match) & mask) == 0
*
* Writethrough caches generally only need 'on' and 'off'
* methods. Writeback caches _must_ have the flush method
* defined.
*/
//用于缓存操作的表。这基本上是:
//- CPU ID匹配
//- CPU ID掩码
//- 'cache on'方法指令
//- 'cache off'方法指令
//-'cache flush'方法指令
//write - through缓存通常只需要“on”和“off”方法。
//Writeback缓存_must_定义了刷新方法。
.align 2
.type proc_types,#object
proc_types:
.word 0x41000000 @ old ARM ID
.word 0xff00f000
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
.word 0x41007000 @ ARM7/710
.word 0xfff8fe00
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
.word 0x41807200 @ ARM720T (writethrough)
.word 0xffffff00
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
mov pc, lr
THUMB( nop )
.word 0x41007400 @ ARM74x
.word 0xff00ff00
W(b) __armv3_mpu_cache_on
W(b) __armv3_mpu_cache_off
W(b) __armv3_mpu_cache_flush
.word 0x41009400 @ ARM94x
.word 0xff00ff00
W(b) __armv4_mpu_cache_on
W(b) __armv4_mpu_cache_off
W(b) __armv4_mpu_cache_flush
.word 0x41069260 @ ARM926EJ-S (v5TEJ)
.word 0xff0ffff0
W(b) __arm926ejs_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv5tej_mmu_cache_flush
.word 0x00007000 @ ARM7 IDs
.word 0x0000f000
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
@ Everything from here on will be the new ID system.
.word 0x4401a100 @ sa110 / sa1100
.word 0xffffffe0
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv4_mmu_cache_flush
.word 0x6901b110 @ sa1110
.word 0xfffffff0
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv4_mmu_cache_flush
.word 0x56056900
.word 0xffffff00 @ PXA9xx
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv4_mmu_cache_flush
.word 0x56158000 @ PXA168
.word 0xfffff000
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv5tej_mmu_cache_flush
.word 0x56050000 @ Feroceon
.word 0xff0f0000
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv5tej_mmu_cache_flush
#ifdef CONFIG_CPU_FEROCEON_OLD_ID
/* this conflicts with the standard ARMv5TE entry */
.long 0x41009260 @ Old Feroceon
.long 0xff00fff0
b __armv4_mmu_cache_on
b __armv4_mmu_cache_off
b __armv5tej_mmu_cache_flush
#endif
.word 0x66015261 @ FA526
.word 0xff01fff1
W(b) __fa526_cache_on
W(b) __armv4_mmu_cache_off
W(b) __fa526_cache_flush
@ These match on the architecture ID
.word 0x00020000 @ ARMv4T
.word 0x000f0000
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv4_mmu_cache_flush
.word 0x00050000 @ ARMv5TE
.word 0x000f0000
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv4_mmu_cache_flush
.word 0x00060000 @ ARMv5TEJ
.word 0x000f0000
W(b) __armv4_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv5tej_mmu_cache_flush
.word 0x0007b000 @ ARMv6
.word 0x000ff000
W(b) __armv6_mmu_cache_on
W(b) __armv4_mmu_cache_off
W(b) __armv6_mmu_cache_flush
.word 0x000f0000 @ new CPU Id
.word 0x000f0000
W(b) __armv7_mmu_cache_on
W(b) __armv7_mmu_cache_off
W(b) __armv7_mmu_cache_flush
.word 0 @ unrecognised type,最后一个条目，无法识别的id
.word 0
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
mov pc, lr
THUMB( nop )
.size proc_types, . - proc_types
/*
* If you get a "non-constant expression in ".if" statement"
* error from the assembler on this line, check that you have
* not accidentally written a "b" instruction where you should
* have written W(b).
*/
.if (. - proc_types) % PROC_ENTRY_SIZE != 0
.error "The size of one or more proc_types entries is wrong."
.endif
Armv7打开cache：
__armv7_mmu_cache_on:
mov r12, lr
#ifdef CONFIG_MMU
mrc p15, 0, r11, c0, c1, 4 @ read ID_MMFR0
tst r11, #0xf @ VMSA
movne r6, #CB_BITS | 0x02 @ !XN
blne __setup_mmu
mov r0, #0
mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
tst r11, #0xf @ VMSA
mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
#endif
mrc p15, 0, r0, c1, c0, 0 @ read control reg
bic r0, r0, #1 << 28 @ clear SCTLR.TRE
orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement
orr r0, r0, #0x003c @ write buffer
bic r0, r0, #2 @ A (no unaligned access fault)
orr r0, r0, #1 << 22 @ U (v6 unaligned access model)
@ (needed for ARM1176)
#ifdef CONFIG_MMU
ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables
mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg
orrne r0, r0, #1 @ MMU enabled
movne r1, #0xfffffffd @ domain 0 = client
bic r6, r6, #1 << 31 @ 32-bit translation system
bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0
mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
mcrne p15, 0, r6, c2, c0, 2 @ load ttb control
#endif
mcr p15, 0, r0, c7, c5, 4 @ ISB
mcr p15, 0, r0, c1, c0, 0 @ load control register
mrc p15, 0, r0, c1, c0, 0 @ and read it back
mov r0, #0
mcr p15, 0, r0, c7, c5, 4 @ ISB
mov pc, r12
建立页表：
__setup_mmu: sub r3, r4, #16384 @ Page directory size
bic r3, r3, #0xff @ Align the pointer
bic r3, r3, #0x3f00
/*
* Initialise the page tables, turning on the cacheable and bufferable
* bits for the RAM area only.
*/
mov r0, r3
mov r9, r0, lsr #18
mov r9, r9, lsl #18 @ start of RAM
add r10, r9, #0x10000000 @ a reasonable RAM size
mov r1, #0x12 @ XN|U + section mapping
orr r1, r1, #3 << 10 @ AP=11
add r2, r3, #16384
1: cmp r1, r9 @ if virt > start of RAM
cmphs r10, r1 @ && end of RAM > virt
bic r1, r1, #0x1c @ clear XN|U + C + B
orrlo r1, r1, #0x10 @ Set XN|U for non-RAM
orrhs r1, r1, r6 @ set RAM section settings
str r1, [r0], #4 @ 1:1 mapping
add r1, r1, #1048576
teq r0, r2
bne 1b
/*
* If ever we are running from Flash, then we surely want the cache
* to be enabled also for our execution instance... We map 2MB of it
* so there is no map overlap problem for up to 1 MB compressed kernel.
* If the execution is in RAM then we would only be duplicating the above.
*/
orr r1, r6, #0x04 @ ensure B is set for this
orr r1, r1, #3 << 10
mov r2, pc
mov r2, r2, lsr #20
orr r1, r1, r2, lsl #20
add r0, r3, r2, lsl #2
str r1, [r0], #4
add r1, r1, #1048576
str r1, [r0]
mov pc, lr
ENDPROC(__setup_mmu)
页表存放地址空间：
我们知道r4存内核解压后的基址，那么这句就是把页表放在解压后的内核地址的前面16K空间如下图所示：
