概述
以下内容源于朱有鹏嵌入式课程的学习,如有侵权,请告知删除。
前言
1、内容总结
汇编阶段,或者说内核引导阶段,主要是arch/arm/kernel/head.S文件,主要完成以下内容:
(1)校验启动合法性(CPU ID,机器码,uboot给内核的传参格式等)。
(2)建立段式映射的页表,并开启MMU以方便使用内存。
(3)构建C运行环境,跳入C阶段。
2、head.S文件代码
/* * linux/arch/arm/kernel/head.S * * Copyright (C) 1994-2002 Russell King * Copyright (c) 2003 ARM Limited * All Rights Reserved * * 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. * * Kernel startup code for all 32-bit CPUs */ #include <linux/linkage.h> #include <linux/init.h> #include <asm/assembler.h> #include <asm/domain.h> #include <asm/ptrace.h> #include <asm/asm-offsets.h> #include <asm/memory.h> #include <asm/thread_info.h> #include <asm/system.h> #if (PHYS_OFFSET & 0x001fffff) #error "PHYS_OFFSET must be at an even 2MiB boundary!" #endif #define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET) #define KERNEL_RAM_PADDR (PHYS_OFFSET + TEXT_OFFSET) /* * swapper_pg_dir is the virtual address of the initial page table. * We place the page tables 16K below KERNEL_RAM_VADDR. Therefore, we must * make sure that KERNEL_RAM_VADDR is correctly set. Currently, we expect * the least significant 16 bits to be 0x8000, but we could probably * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000. */ #if (KERNEL_RAM_VADDR & 0xffff) != 0x8000 #error KERNEL_RAM_VADDR must start at 0xXXXX8000 #endif .globl swapper_pg_dir .equ swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000 .macro pgtbl, rd ldr rd, =(KERNEL_RAM_PADDR - 0x4000) .endm #ifdef CONFIG_XIP_KERNEL #define KERNEL_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR) #define KERNEL_END _edata_loc #else #define KERNEL_START KERNEL_RAM_VADDR #define KERNEL_END _end #endif /* * Kernel startup entry point. * --------------------------- * * This is normally called from the decompressor code. The requirements * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0, * r1 = machine nr, r2 = atags pointer. * * This code is mostly position independent, so if you link the kernel at * 0xc0008000, you call this at __pa(0xc0008000). * * See linux/arch/arm/tools/mach-types for the complete list of machine * numbers for r1. * * We're trying to keep crap to a minimum; DO NOT add any machine specific * crap here - that's what the boot loader (or in extreme, well justified * circumstances, zImage) is for. */ __HEAD ENTRY(stext) setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode @ and irqs disabled mrc p15, 0, r9, c0, c0 @ get processor id bl __lookup_processor_type @ r5=procinfo r9=cpuid movs r10, r5 @ invalid processor (r5=0)? beq __error_p @ yes, error 'p' bl __lookup_machine_type @ r5=machinfo movs r8, r5 @ invalid machine (r5=0)? beq __error_a @ yes, error 'a' bl __vet_atags bl __create_page_tables /* * The following calls CPU specific code in a position independent * manner. See arch/arm/mm/proc-*.S for details. r10 = base of * xxx_proc_info structure selected by __lookup_machine_type * above. On return, the CPU will be ready for the MMU to be * turned on, and r0 will hold the CPU control register value. */ ldr r13, __switch_data @ address to jump to after @ mmu has been enabled adr lr, BSYM(__enable_mmu) @ return (PIC) address ARM( add pc, r10, #PROCINFO_INITFUNC ) THUMB( add r12, r10, #PROCINFO_INITFUNC ) THUMB( mov pc, r12 ) ENDPROC(stext) #if defined(CONFIG_SMP) ENTRY(secondary_startup) /* * Common entry point for secondary CPUs. * * Ensure that we're in SVC mode, and IRQs are disabled. Lookup * the processor type - there is no need to check the machine type * as it has already been validated by the primary processor. */ setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 mrc p15, 0, r9, c0, c0 @ get processor id bl __lookup_processor_type movs r10, r5 @ invalid processor? moveq r0, #'p' @ yes, error 'p' beq __error /* * Use the page tables supplied from __cpu_up. */ adr r4, __secondary_data ldmia r4, {r5, r7, r12} @ address to jump to after sub r4, r4, r5 @ mmu has been enabled ldr r4, [r7, r4] @ get secondary_data.pgdir adr lr, BSYM(__enable_mmu) @ return address mov r13, r12 @ __secondary_switched address ARM( add pc, r10, #PROCINFO_INITFUNC ) @ initialise processor @ (return control reg) THUMB( add r12, r10, #PROCINFO_INITFUNC ) THUMB( mov pc, r12 ) ENDPROC(secondary_startup) /* * r6 = &secondary_data */ ENTRY(__secondary_switched) ldr sp, [r7, #4] @ get secondary_data.stack mov fp, #0 b secondary_start_kernel ENDPROC(__secondary_switched) .type __secondary_data, %object __secondary_data: .long . .long secondary_data .long __secondary_switched #endif /* defined(CONFIG_SMP) */ /* * Setup common bits before finally enabling the MMU. Essentially * this is just loading the page table pointer and domain access * registers. */ __enable_mmu: #ifdef CONFIG_ALIGNMENT_TRAP orr r0, r0, #CR_A #else bic r0, r0, #CR_A #endif #ifdef CONFIG_CPU_DCACHE_DISABLE bic r0, r0, #CR_C #endif #ifdef CONFIG_CPU_BPREDICT_DISABLE bic r0, r0, #CR_Z #endif #ifdef CONFIG_CPU_ICACHE_DISABLE bic r0, r0, #CR_I #endif mov r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | domain_val(DOMAIN_IO, DOMAIN_CLIENT)) mcr p15, 0, r5, c3, c0, 0 @ load domain access register mcr p15, 0, r4, c2, c0, 0 @ load page table pointer b __turn_mmu_on ENDPROC(__enable_mmu) /* * Enable the MMU. This completely changes the structure of the visible * memory space. You will not be able to trace execution through this. * If you have an enquiry about this, *please* check the linux-arm-kernel * mailing list archives BEFORE sending another post to the list. * * r0 = cp#15 control register * r13 = *virtual* address to jump to upon completion * * other registers depend on the function called upon completion */ .align 5 __turn_mmu_on: mov r0, r0 mcr p15, 0, r0, c1, c0, 0 @ write control reg mrc p15, 0, r3, c0, c0, 0 @ read id reg mov r3, r3 mov r3, r13 mov pc, r3 ENDPROC(__turn_mmu_on) /* * Setup the initial page tables. We only setup the barest * amount which are required to get the kernel running, which * generally means mapping in the kernel code. * * r8 = machinfo * r9 = cpuid * r10 = procinfo * * Returns: * r0, r3, r6, r7 corrupted * r4 = physical page table address */ __create_page_tables: pgtbl r4 @ page table address /* * Clear the 16K level 1 swapper page table */ mov r0, r4 mov r3, #0 add r6, r0, #0x4000 1: str r3, [r0], #4 str r3, [r0], #4 str r3, [r0], #4 str r3, [r0], #4 teq r0, r6 bne 1b ldr r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags /* * Create identity mapping for first MB of kernel to * cater for the MMU enable. This identity mapping * will be removed by paging_init(). We use our current program * counter to determine corresponding section base address. */ mov r6, pc mov r6, r6, lsr #20 @ start of kernel section orr r3, r7, r6, lsl #20 @ flags + kernel base str r3, [r4, r6, lsl #2] @ identity mapping /* * Now setup the pagetables for our kernel direct * mapped region. */ add r0, r4, #(KERNEL_START & 0xff000000) >> 18 str r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]! ldr r6, =(KERNEL_END - 1) add r0, r0, #4 add r6, r4, r6, lsr #18 1: cmp r0, r6 add r3, r3, #1 << 20 strls r3, [r0], #4 bls 1b #ifdef CONFIG_XIP_KERNEL /* * Map some ram to cover our .data and .bss areas. */ orr r3, r7, #(KERNEL_RAM_PADDR & 0xff000000) .if (KERNEL_RAM_PADDR & 0x00f00000) orr r3, r3, #(KERNEL_RAM_PADDR & 0x00f00000) .endif add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> 18 str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]! ldr r6, =(_end - 1) add r0, r0, #4 add r6, r4, r6, lsr #18 1: cmp r0, r6 add r3, r3, #1 << 20 strls r3, [r0], #4 bls 1b #endif /* * Then map first 1MB of ram in case it contains our boot params. */ add r0, r4, #PAGE_OFFSET >> 18 orr r6, r7, #(PHYS_OFFSET & 0xff000000) .if (PHYS_OFFSET & 0x00f00000) orr r6, r6, #(PHYS_OFFSET & 0x00f00000) .endif str r6, [r0] #ifdef CONFIG_DEBUG_LL ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags /* * Map in IO space for serial debugging. * This allows debug messages to be output * via a serial console before paging_init. */ ldr r3, [r8, #MACHINFO_PGOFFIO] add r0, r4, r3 rsb r3, r3, #0x4000 @ PTRS_PER_PGD*sizeof(long) cmp r3, #0x0800 @ limit to 512MB movhi r3, #0x0800 add r6, r0, r3 ldr r3, [r8, #MACHINFO_PHYSIO] orr r3, r3, r7 1: str r3, [r0], #4 add r3, r3, #1 << 20 teq r0, r6 bne 1b #if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS) /* * If we're using the NetWinder or CATS, we also need to map * in the 16550-type serial port for the debug messages */ add r0, r4, #0xff000000 >> 18 orr r3, r7, #0x7c000000 str r3, [r0] #endif #ifdef CONFIG_ARCH_RPC /* * Map in screen at 0x02000000 & SCREEN2_BASE * Similar reasons here - for debug. This is * only for Acorn RiscPC architectures. */ add r0, r4, #0x02000000 >> 18 orr r3, r7, #0x02000000 str r3, [r0] add r0, r4, #0xd8000000 >> 18 str r3, [r0] #endif #endif mov pc, lr ENDPROC(__create_page_tables) .ltorg #include "head-common.S"
一、分析kernel的链接脚本
由内核配置与编译——内核的链接脚本可知,kernel的入口地址在arch/arm/kernel/head.S文件的ENTRY(stext)处。
二、分析head.S文件
1、内核运行的物理地址与虚拟地址
(1)KERNEL_RAM_VADDR(VADDR就是virtual address),这个宏定义了内核运行时的虚拟地址,值为0xC0008000。
(2)KERNEL_RAM_PADDR(PADDR就是physical address),这个宏定义内核运行时的物理地址,值为0x30008000。
(3)因此,内核运行的物理地址是0x30008000,对应的虚拟地址是0xC0008000。
2、内核的真正入口
(1)__HEAD定义了段名为.head.text的段。在/include/linux/init.h文件中,有如下代码:
/* For assembly routines */ #define __HEAD .section ".head.text","ax" //定义了段名为.head.text的段 #define __INIT .section ".init.text","ax" #define __FINIT .previous
(2)“ENTRY(stext)”表明内核的真正入口。
(3)uboot启动内核后,实际调用zImage前面的那段未经压缩的解压代码,解压代码运行时先将zImage后面的部分解压开,然后再去调用运行真正的内核入口(即这里)。
(4)内核启动需要一定先决条件,这个条件由启动内核的bootloader(比如uboot)来构建保证。
(5)ARM体系中,函数调用时实际是通过寄存器传参的。
- 函数调用时传参有两种设计:一种是寄存器传参,另一种是栈内存传参。
- uboot中最后theKernel (0, machid, bd->bi_boot_params);执行内核时,实际把0放入r0中,machid放入到了r1中,bd->bi_boot_params放入到了r2中。
- ARM的这种处理技巧刚好满足了kernel启动的条件和要求。
(6)此时MMU是关闭的,因此硬件上需要的是物理地址。但是内核是一个整体(zImage)只能被链接到一个地址(不能分散加载),这个链接地址肯定是虚拟地址。因此head.S文件中尚未开启MMU之前的代码必须是位置无关码,而且其中涉及到操作硬件寄存器等时必须使用物理地址。
3、检验CPU_ID与机器码的合法性
分别通过__lookup_processor_type与__lookup_machine_type,校验CPU_ID与机器码的合法性。这两个函数都在arch/arm/kernel/head-common.S文件中。
__lookup_processor_type函数内容如下:
__lookup_machine_type函数内容如下:
(1)cp15协处理器的c0寄存器中读取出硬件的CPU ID号,然后调用__lookup_processor_type来进行合法性检验。如果合法则继续启动,如果不合法则停止启动,转向__error_p启动失败。
(2)__lookup_processor_type检验cpu id合法性的方法。内核会维护一个本内核支持的CPU ID号码的数组,然后该函数将从硬件中读取到的cpu id号码和数组中存储的各个id号码依次对比,如果没有一个相等则不合法,如果有一个相等的则合法。
(3)内核启动时设计这个校验,也是为了内核启动的安全性着想。
(4)__lookup_machine_type函数的设计理念和思路和上面校验cpu id的函数一样的,不同之处是本函数校验的是机器码。
4、校验uboot给内核传参的格式
利用__vet_atags函数,对uboot通过tag给内核传参的格式进行校验。
这函数在arch/arm/kernel/head-common.S文件中。
(1)该函数的设计思路和上面2个一样,用来对uboot通过tag给内核传参的格式进行校验。参数包括板子的内存分布memtag、uboot的bootargs等等。
(2)如果uboot给内核传参的格式不对,内核将启动不起来。比如uboot的bootargs设置不正确,则内核可能就会不启动。
5、建立段式页表
利用__create_page_tables函数建立段式页表。
这函数在arch/arm/kernel/head.S文件中。
(1)linux内核本身被链接在虚拟地址处,因此kernel希望尽快建立页表并且启动MMU进入虚拟地址工作状态。
(2)kernel建立页表分为2步。
- 第一步,先建立一个段式页表(1MB为单位的段页表)。段式页表建立过程简单(段式页表1MB一个映射,4GB空间需要4096个页表项,每个页表项4字节,因此一共需要16KB内存来做页表),但不能精细管理内存。上面的函数就是用来建立段式页表的。
- 第二步,然后建立一个细页表(4kb为单位的细页表),然后启用新的细页表,并废除第一步建立的段式映射页表。
(3)内核启动的早期建立段式页表,并在内核启动早期使用;内核启动的后期再次建立细页表并启用。等内核工作起来后,就只有细页表了。
6、构建C语言运行环境
(1)建立段式页表后进入__switch_data部分,它是一个函数指针数组。
(2)分析得知下一步要执行__mmap_switched函数。
- 复制数据段、清除bss段(目的是构建C语言运行环境)。
- 保存起来cpu id号、机器码、tag传参的首地址。
- b start_kernel跳转到C语言运行阶段。
最后
以上就是老迟到野狼为你收集整理的内核源码——汇编阶段的head.S文件前言一、分析kernel的链接脚本二、分析head.S文件的全部内容,希望文章能够帮你解决内核源码——汇编阶段的head.S文件前言一、分析kernel的链接脚本二、分析head.S文件所遇到的程序开发问题。
如果觉得靠谱客网站的内容还不错,欢迎将靠谱客网站推荐给程序员好友。
发表评论 取消回复