Linux4.1初始化流程详细注释——第一阶段head.S与head-common.S

Linux4.1初始化流程详细注释——第一阶段head.S与head-common.S

    • 1)head.S/头文件、宏定义等
    • 2)head.S/stext
    • 2.1)编译后的汇编:head.S/stext
    • 3)head.S/__create_page_tables
    • 3.1)编译后的汇编:head.S/__create_page_tables
    • 4)暂未注解:head.S/...
    • -)暂未注解: head-common.S
    • #)初始化第一阶段流程

  • 本文直接展示head.S与head-common.S的源码、编译后的汇编码,并在此基础上增加行注释
  • 由于汇编源码中使用的行注释是@,所以此文增加的行注释使用 //
  • 内核版本4.1

1)head.S/头文件、宏定义等

/*
 *  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 
#include 

#include 
#include 
#include 
#include 
#include 
#include 
#include 
#include 

#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
#include CONFIG_DEBUG_LL_INCLUDE
#endif

/*
 * 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.
 */
#define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
							// PAGE_OFFSET = 0xC0000000
							// TEXT_OFFSET = 0x00008000
							// KERNEL_RAM_VADDR = 0xC0008000
#if (KERNEL_RAM_VADDR & 0xffff) != 0x8000
#error KERNEL_RAM_VADDR must start at 0xXXXX8000
#endif

#ifdef CONFIG_ARM_LPAE			// 未定义,所以PG_DIR_SIZE = 0x4000,PMD_ORDER = 2
								// PG_DIR_SIZE代表一级也表的大小,2^12个entry,每个entry是4字节,即需要16K(0x4000)空间
								// PMD_ORDER代表每个entry是4字节(2^2=4)
	/* LPAE requires an additional page for the PGD */
#define PG_DIR_SIZE	0x5000
#define PMD_ORDER	3
#else
#define PG_DIR_SIZE	0x4000
#define PMD_ORDER	2
#endif

	.globl	swapper_pg_dir
	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
									// swapper_pg_dir = 0x50004000
	.macro	pgtbl, rd, phys
	add	\rd, \phys, #TEXT_OFFSET	// rd = phys + 0x8000
	sub	\rd, \rd, #PG_DIR_SIZE		// rd = rd - 0x4000
	.endm

2)head.S/stext

/*
 * 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 or dtb 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.
 */
	.arm

	__HEAD
ENTRY(stext)
	ARM_BE8(setend	be)				@ ensure we are in BE8 mode

	THUMB( adr	r9, BSYM(1f) )		@ Kernel is always entered in ARM.
	THUMB( bx	r9			 )		@ If this is a Thumb-2 kernel,
	THUMB( .thumb			 )		@ switch to Thumb now.
	THUMB( 1:				 )

#ifdef CONFIG_ARM_VIRT_EXT
	bl	__hyp_stub_install
#endif
	@ ensure svc mode and all interrupts masked
	safe_svcmode_maskall r9

	mrc	p15, 0, r9, c0, c0			@ get processor id
									// 获取处理器id,我的是r9 = 0x410fb766
	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
									// r5 = 0x50619e38
	movs	r10, r5					@ invalid processor (r5=0)?
									// r10 = 0x50619e38
 THUMB( it	eq )					@ force fixup-able long branch encoding
	beq	__error_p					@ yes, error 'p'

#ifdef CONFIG_ARM_LPAE				// 未定义,跳过
	mrc	p15, 0, r3, c0, c1, 4		@ read ID_MMFR0
	and	r3, r3, #0xf				@ extract VMSA support
	cmp	r3, #5						@ long-descriptor translation table format?
 THUMB( it	lo )					@ force fixup-able long branch encoding
	blo	__error_lpae				@ only classic page table format
#endif

#ifndef CONFIG_XIP_KERNEL			// 未定义,不跳过
	adr	r3, 2f						// r3 = 0xc000807c
	ldmia	r3, {r4, r8}			// r4 = 0xc000807c, r8 = 0xc0000000
	sub	r4, r3, r4					@ (PHYS_OFFSET - PAGE_OFFSET)
									// PHYS_OFFSET = 0x50000000
									// PAGE_OFFSET = 0xC0000000
									// r4 = 0x90000000
	add	r8, r8, r4					@ PHYS_OFFSET
									// r8 = 0x50000000
#else								// 跳过
	ldr	r8, =PLAT_PHYS_OFFSET		@ always constant in this case
#endif

	/*
	 * r1 = machine no, r2 = atags or dtb,
	 * r8 = phys_offset, r9 = cpuid, r10 = procinfo
	 */
	bl	__vet_atags
#ifdef CONFIG_SMP_ON_UP				// 未定义,跳过
	bl	__fixup_smp
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
	bl	__fixup_pv_table
#endif
	bl	__create_page_tables		// 简单初始化MMU页表项,后面还会继续初始化

	/*
	 * 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_processor_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, =__mmap_switched		@ address to jump to after
									@ mmu has been enabled
	adr	lr, BSYM(1f)				@ return (PIC) address
	mov	r8, r4						@ set TTBR1 to swapper_pg_dir
	ldr	r12, [r10, #PROCINFO_INITFUNC]
	add	r12, r12, r10
	ret	r12
1:	b	__enable_mmu
ENDPROC(stext)
	.ltorg
#ifndef CONFIG_XIP_KERNEL
2:	.long	.
	.long	PAGE_OFFSET
#endif

2.1)编译后的汇编:head.S/stext

包含指令地址,用于与上文对比

c0008000 <stext>:
c0008000:	e10f9000 	mrs	r9, CPSR
c0008004:	e229901a 	eor	r9, r9, #26
c0008008:	e319001f 	tst	r9, #31
c000800c:	e3c9901f 	bic	r9, r9, #31
c0008010:	e38990d3 	orr	r9, r9, #211	; 0xd3
c0008014:	1a000004 	bne	c000802c <stext+0x2c>
c0008018:	e3899c01 	orr	r9, r9, #256	; 0x100
c000801c:	e28fe00c 	add	lr, pc, #12
c0008020:	e16ff009 	msr	SPSR_fsxc, r9
c0008024:	e12ef30e 	.word	0xe12ef30e
c0008028:	e160006e 	.word	0xe160006e
c000802c:	e121f009 	msr	CPSR_c, r9
c0008030:	ee109f10 	mrc	15, 0, r9, cr0, cr0, {0}
c0008034:	eb00051b 	bl	c00094a8 <__lookup_processor_type>
c0008038:	e1b0a005 	movs	sl, r5
c000803c:	0a00053e 	beq	c000953c <__error_p>
c0008040:	e28f3034 	add	r3, pc, #52	; 0x34
c0008044:	e8930110 	ldm	r3, {r4, r8}
c0008048:	e0434004 	sub	r4, r3, r4
c000804c:	e0888004 	add	r8, r8, r4
c0008050:	eb00005f 	bl	c00081d4 <__vet_atags>
c0008054:	eb000049 	bl	c0008180 <__fixup_pv_table>
c0008058:	eb000009 	bl	c0008084 <__create_page_tables>
c000805c:	e59fd014 	ldr	sp, [pc, #20]	; c0008078 <stext+0x78>
c0008060:	e28fe00c 	add	lr, pc, #12
c0008064:	e1a08004 	mov	r8, r4
c0008068:	e59ac010 	ldr	ip, [sl, #16]
c000806c:	e08cc00a 	add	ip, ip, sl
c0008070:	e1a0f00c 	mov	pc, ip
c0008074:	ea00003c 	b	c000816c <__enable_mmu>
c0008078:	c058a2e0 	.word	0xc058a2e0
c000807c:	c000807c 	.word	0xc000807c
c0008080:	c0000000 	.word	0xc0000000

3)head.S/__create_page_tables

/*
 * 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 = phys_offset, r9 = cpuid, r10 = procinfo
 *
 * Returns:
 *  r0, r3, r5-r7 corrupted
 *  r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
 */
__create_page_tables:
	pgtbl	r4, r8					@ page table address
									// pgtbl是汇编宏,定义在第一节
									// r4 = 0x50004000
	/*
	 * Clear the swapper page table
	 * 0x50004000~0x50007fff物理地址中的数据清零
	 */
	mov	r0, r4						// r0 = 0x50004000
	mov	r3, #0						// r3 = 0
	add	r6, r0, #PG_DIR_SIZE		// r6 = 0x50008000
1:	str	r3, [r0], #4				// *(0x50004000) = 0;*(0x50004010) = 0;...
	str	r3, [r0], #4				// *(0x50004004) = 0;*(0x50004014) = 0;...
	str	r3, [r0], #4				// *(0x50004008) = 0;*(0x50004018) = 0;...
	str	r3, [r0], #4				// *(0x5000400c) = 0;*(0x5000401c) = 0;...
	teq	r0, r6						// if r0 != r6
	bne	1b							// goto 1b

#ifdef CONFIG_ARM_LPAE				// 未定义,跳过一大段
	/*
	 * Build the PGD table (first level) to point to the PMD table. A PGD
	 * entry is 64-bit wide.
	 */
	mov	r0, r4
	add	r3, r4, #0x1000				@ first PMD table address
	orr	r3, r3, #3					@ PGD block type
	mov	r6, #4						@ PTRS_PER_PGD
	mov	r7, #1 << (55 - 32)			@ L_PGD_SWAPPER
1:
#ifdef CONFIG_CPU_ENDIAN_BE8
	str	r7, [r0], #4				@ set top PGD entry bits
	str	r3, [r0], #4				@ set bottom PGD entry bits
#else
	str	r3, [r0], #4				@ set bottom PGD entry bits
	str	r7, [r0], #4				@ set top PGD entry bits
#endif
	add	r3, r3, #0x1000				@ next PMD table
	subs	r6, r6, #1
	bne	1b

	add	r4, r4, #0x1000				@ point to the PMD tables
#ifdef CONFIG_CPU_ENDIAN_BE8
	add	r4, r4, #4					@ we only write the bottom word
#endif
#endif

	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags	// r7 = 0xc0e(mmu低12位标志符)

	/*
	 * Create identity mapping to cater for __enable_mmu.
	 * This identity mapping will be removed by paging_init().
	 */
	adr	r0, __turn_mmu_on_loc			// r0 = 0x50008160
	ldmia	r0, {r3, r5, r6}			// r3 = 0xc0008160
										// r5 = 0xc0008220
										// r6 = 0xc0008240
	sub	r0, r0, r3						@ virt->phys offset
										// r0 = 0x90000000
	add	r5, r5, r0						@ phys __turn_mmu_on
										// r5 = 0x50008220
	add	r6, r6, r0						@ phys __turn_mmu_on_end
										// r6 = 0x50008240
	mov	r5, r5, lsr #SECTION_SHIFT		// SECTION_SHIFT = 20
										// r5 = 0x500
	mov	r6, r6, lsr #SECTION_SHIFT		// r6 = 0x500

1:	orr	r3, r7, r5, lsl #SECTION_SHIFT	@ flags + kernel base
										// r3 = 0x50000c0e
	str	r3, [r4, r5, lsl #PMD_ORDER]	@ identity mapping
										// *(0x50004000 + 0x1400) = 0x50000c0e
	cmp	r5, r6							// if r5 < r6
										// cmp指令是不保存结果只设置状态寄存器的sub指令
										// 此时r5 == r6,下面的addlo(addcc)与blo(bcc)只有r5小于r6时才会执行
	addlo	r5, r5, #1					@ next section
										// r5 = 0x500
	blo	1b								// 不跳转

	/*
	 * Map our RAM from the start to the end of the kernel .bss section.
	 * 将0xc000000到.end之间的虚拟内存地址映射到0x50007000到0x50007xxx;我这里是0x5000701a
	 * (gdb) x/32x 0x50007000
	 * 0x50007000:     0x50000c0e      0x50100c0e      0x50200c0e      0x50300c0e
	 * 0x50007010:     0x50400c0e      0x50500c0e      0x50600c0e      0x00000000
	 * 0x50007020:     0x00000000      0x00000000      0x00000000      0x00000000
	 */
	add	r0, r4, #PAGE_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
										// r0 = 0x50004000 + (0xc0000000 >> 18) = 0x50007000
	ldr	r6, =(_end - 1)					// vmlinux.lds.S中,BSS_SECTION后,_end = .;
										// 我这里是r6 = 0xc06b15d7
	orr	r3, r8, r7						// r3 = 0x50000000 | 0xc0e = 0x50000c0e
	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
										// r6 = 0x50007xxx;我这里是0x5000701a
1:	str	r3, [r0], #1 << PMD_ORDER		// *(0x50007000) = 0x50000c0e
										// r0++
	add	r3, r3, #1 << SECTION_SHIFT		// r3 = 0x50100c0e
	cmp	r0, r6							// if r0 < r6;这个cmp与前一段的套路完全一样
	bls	1b								// goto 1b

#ifdef CONFIG_XIP_KERNEL				// 未定义,跳过
	/*
	 * Map the kernel image separately as it is not located in RAM.
	 */
#define XIP_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR)
	mov	r3, pc
	mov	r3, r3, lsr #SECTION_SHIFT
	orr	r3, r7, r3, lsl #SECTION_SHIFT
	add	r0, r4,  #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
	str	r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]!
	ldr	r6, =(_edata_loc - 1)
	add	r0, r0, #1 << PMD_ORDER
	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
1:	cmp	r0, r6
	add	r3, r3, #1 << SECTION_SHIFT
	strls	r3, [r0], #1 << PMD_ORDER
	bls	1b
#endif

	/*
	 * Then map boot params address in r2 if specified.
	 * We map 2 sections in case the ATAGs/DTB crosses a section boundary.
	 * 这一段没看懂,最后设置了页表项0x50007000于0x50007004,不过该页表项前面已经设置过了,内容也没有任何改变
	 */
	mov	r0, r2, lsr #SECTION_SHIFT							// r2 = 0x50000100, r0 = 0x500
	movs	r0, r0, lsl #SECTION_SHIFT						// r0 = 0x50000000
	subne	r3, r0, r8										// r3 = 0
	addne	r3, r3, #PAGE_OFFSET							// r3 = 0xc0000000
	addne	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)	// r3 = 0x50007000
	orrne	r6, r7, r0										// r6 = 0x50000c0e
	strne	r6, [r3], #1 << PMD_ORDER						// *(0x50007000) = 0x50000c0e
	addne	r6, r6, #1 << SECTION_SHIFT						// r6 = 0x50100c0e
	strne	r6, [r3]										// *(0x50007004) = 0x50100c0e

#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8) 			// CONFIG_ARM_LPAE未定义,跳过
	sub	r4, r4, #4					@ Fixup page table pointer
									@ for 64-bit descriptors
#endif

#ifdef CONFIG_DEBUG_LL													// 不跳过
#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING) // 不跳过
	/*
	 * Map in IO space for serial debugging.
	 * This allows debug messages to be output
	 * via a serial console before paging_init.
	 * 设置串口控制器物理地址对应的虚拟地址页表项
	 * (gdb) x/4x 0x50007dc0
	 * 0x50007dc0:     0x7f000c12      0x00000000      0x00000000      0x00000000
	 */
	addruart r7, r3, r0										// r7 = 0x7f005000, r3 = 0xf7005000
															// addruart是宏定义:
															//   将串口控制器的物理地址赋值给r7,该地址由平台体系决定,
															//   翻看arm11的datasheet可知地址固定为0x7f005000
															//   将串口控制器的虚拟地址赋值给r3,该地址由内核开发者决定

	mov	r3, r3, lsr #SECTION_SHIFT							// r3 = 0xf70
	mov	r3, r3, lsl #PMD_ORDER								// r3 = 0x3dc0

	add	r0, r4, r3											// 0x50007dc0
	mov	r3, r7, lsr #SECTION_SHIFT							// r3 = 0xf70
	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags		// r7 = 0xc12
	orr	r3, r7, r3, lsl #SECTION_SHIFT						// r3 = 0x7f000c12
#ifdef CONFIG_ARM_LPAE										// 未定义,跳过
	mov	r7, #1 << (54 - 32)			@ XN
#ifdef CONFIG_CPU_ENDIAN_BE8
	str	r7, [r0], #4
	str	r3, [r0], #4
#else
	str	r3, [r0], #4
	str	r7, [r0], #4
#endif
#else														// 不跳过
	orr	r3, r3, #PMD_SECT_XN								// r3 = 0x7f000c12
	str	r3, [r0], #4										// *(0x50007dc0) = 0x7f000c12
#endif

#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */	// 跳过
	/* we don't need any serial debugging mappings */
	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
#endif

#if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)	// 未定义,跳过
	/*
	 * 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 >> (SECTION_SHIFT - PMD_ORDER)
	orr	r3, r7, #0x7c000000
	str	r3, [r0]
#endif
#ifdef CONFIG_ARCH_RPC										// 未定义,跳过
	/*
	 * Map in screen at 0x02000000 & SCREEN2_BASE
	 * Similar reasons here - for debug.  This is
	 * only for Acorn RiscPC architectures.
	 */
	add	r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER)
	orr	r3, r7, #0x02000000
	str	r3, [r0]
	add	r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER)
	str	r3, [r0]
#endif
#endif
#ifdef CONFIG_ARM_LPAE										// 未定义,跳过
	sub	r4, r4, #0x1000				@ point to the PGD table
	mov	r4, r4, lsr #ARCH_PGD_SHIFT
#endif
	ret	lr													// return
ENDPROC(__create_page_tables)
	.ltorg
	.align
__turn_mmu_on_loc:
	.long	.
	.long	__turn_mmu_on
	.long	__turn_mmu_on_end

3.1)编译后的汇编:head.S/__create_page_tables

包含指令地址,用于与上文对比

c0008084 <__create_page_tables>:
c0008084:	e2884902 	add	r4, r8, #32768	; 0x8000
c0008088:	e2444901 	sub	r4, r4, #16384	; 0x4000
c000808c:	e1a00004 	mov	r0, r4
c0008090:	e3a03000 	mov	r3, #0
c0008094:	e2806901 	add	r6, r0, #16384	; 0x4000
c0008098:	e4803004 	str	r3, [r0], #4
c000809c:	e4803004 	str	r3, [r0], #4
c00080a0:	e4803004 	str	r3, [r0], #4
c00080a4:	e4803004 	str	r3, [r0], #4
c00080a8:	e1300006 	teq	r0, r6
c00080ac:	1afffff9 	bne	c0008098 <__create_page_tables+0x14>
c00080b0:	e59a7008 	ldr	r7, [sl, #8]
c00080b4:	e28f00a4 	add	r0, pc, #164	; 0xa4
c00080b8:	e8900068 	ldm	r0, {r3, r5, r6}
c00080bc:	e0400003 	sub	r0, r0, r3
c00080c0:	e0855000 	add	r5, r5, r0
c00080c4:	e0866000 	add	r6, r6, r0
c00080c8:	e1a05a25 	lsr	r5, r5, #20
c00080cc:	e1a06a26 	lsr	r6, r6, #20
c00080d0:	e1873a05 	orr	r3, r7, r5, lsl #20
c00080d4:	e7843105 	str	r3, [r4, r5, lsl #2]
c00080d8:	e1550006 	cmp	r5, r6
c00080dc:	32855001 	addcc	r5, r5, #1
c00080e0:	3afffffa 	bcc	c00080d0 <__create_page_tables+0x4c>
c00080e4:	e2840a03 	add	r0, r4, #12288	; 0x3000
c00080e8:	e59f6064 	ldr	r6, [pc, #100]	; c0008154 <__create_page_tables+0xd0>
c00080ec:	e1883007 	orr	r3, r8, r7
c00080f0:	e0846926 	add	r6, r4, r6, lsr #18
c00080f4:	e4803004 	str	r3, [r0], #4
c00080f8:	e2833601 	add	r3, r3, #1048576	; 0x100000
c00080fc:	e1500006 	cmp	r0, r6
c0008100:	9afffffb 	bls	c00080f4 <__create_page_tables+0x70>
c0008104:	e1a00a22 	lsr	r0, r2, #20
c0008108:	e1b00a00 	lsls	r0, r0, #20
c000810c:	10403008 	subne	r3, r0, r8
c0008110:	12833103 	addne	r3, r3, #-1073741824	; 0xc0000000
c0008114:	10843923 	addne	r3, r4, r3, lsr #18
c0008118:	11876000 	orrne	r6, r7, r0
c000811c:	14836004 	strne	r6, [r3], #4
c0008120:	12866601 	addne	r6, r6, #1048576	; 0x100000
c0008124:	15836000 	strne	r6, [r3]
c0008128:	e59f7028 	ldr	r7, [pc, #40]	; c0008158 <__create_page_tables+0xd4>
c000812c:	e59f3028 	ldr	r3, [pc, #40]	; c000815c <__create_page_tables+0xd8>
c0008130:	e1a03a23 	lsr	r3, r3, #20
c0008134:	e1a03103 	lsl	r3, r3, #2
c0008138:	e0840003 	add	r0, r4, r3
c000813c:	e1a03a27 	lsr	r3, r7, #20
c0008140:	e59a700c 	ldr	r7, [sl, #12]
c0008144:	e1873a03 	orr	r3, r7, r3, lsl #20
c0008148:	e3833010 	orr	r3, r3, #16
c000814c:	e4803004 	str	r3, [r0], #4
c0008150:	e12fff1e 	bx	lr
c0008154:	c06354d7 	.word	0xc06354d7
c0008158:	7f005000 	.word	0x7f005000
c000815c:	f7005000 	.word	0xf7005000

c0008160 <__turn_mmu_on_loc>:
c0008160:	c0008160 	.word	0xc0008160
c0008164:	c0008220 	.word	0xc0008220
c0008168:	c0008240 	.word	0xc0008240

4)暂未注解:head.S/…

#if defined(CONFIG_SMP)				// 未定义,跳过;直接跳到__enable_mmu
	.text
ENTRY(secondary_startup_arm)
	.arm
 THUMB(	adr	r9, BSYM(1f)	)		@ Kernel is entered in ARM.
 THUMB(	bx	r9				)		@ If this is a Thumb-2 kernel,
 THUMB(	.thumb				)		@ switch to Thumb now.
 THUMB(1:					)
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.
	 */

 ARM_BE8(setend	be)					@ ensure we are in BE8 mode

#ifdef CONFIG_ARM_VIRT_EXT
	bl	__hyp_stub_install_secondary
#endif
	safe_svcmode_maskall 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'
 THUMB( it	eq )					@ force fixup-able long branch encoding
	beq	__error_p

	/*
	 * Use the page tables supplied from  __cpu_up.
	 */
	adr	r4, __secondary_data
	ldmia	r4, {r5, r7, r12}		@ address to jump to after
	sub	lr, r4, r5					@ mmu has been enabled
	ldr	r4, [r7, lr]				@ get secondary_data.pgdir
	add	r7, r7, #4
	ldr	r8, [r7, lr]				@ get secondary_data.swapper_pg_dir
	adr	lr, BSYM(__enable_mmu)		@ return address
	mov	r13, r12					@ __secondary_switched address
	ldr	r12, [r10, #PROCINFO_INITFUNC]
	add	r12, r12, r10				@ initialise processor
									@ (return control reg)
	ret	r12
ENDPROC(secondary_startup)
ENDPROC(secondary_startup_arm)

	/*
	 * r6  = &secondary_data
	 */
ENTRY(__secondary_switched)
	ldr	sp, [r7, #4]				@ get secondary_data.stack
	mov	fp, #0
	b	secondary_start_kernel
ENDPROC(__secondary_switched)

	.align

	.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.
 *
 *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
 *  r4  = page table (see ARCH_PGD_SHIFT in asm/memory.h)
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 */
__enable_mmu:
#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
	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
#ifndef CONFIG_ARM_LPAE
	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
#endif
	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
 *  r1  = machine ID
 *  r2  = atags or dtb pointer
 *  r9  = processor ID
 *  r13 = *virtual* address to jump to upon completion
 *
 * other registers depend on the function called upon completion
 */
	.align	5
	.pushsection	.idmap.text, "ax"
ENTRY(__turn_mmu_on)
	mov	r0, r0
	instr_sync
	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
	instr_sync
	mov	r3, r3
	mov	r3, r13
	ret	r3
__turn_mmu_on_end:
ENDPROC(__turn_mmu_on)
	.popsection


#ifdef CONFIG_SMP_ON_UP
	__HEAD
__fixup_smp:
	and	r3, r9, #0x000f0000			@ architecture version
	teq	r3, #0x000f0000				@ CPU ID supported?
	bne	__fixup_smp_on_up			@ no, assume UP

	bic	r3, r9, #0x00ff0000
	bic	r3, r3, #0x0000000f			@ mask 0xff00fff0
	mov	r4, #0x41000000
	orr	r4, r4, #0x0000b000
	orr	r4, r4, #0x00000020			@ val 0x4100b020
	teq	r3, r4						@ ARM 11MPCore?
	reteq	lr						@ yes, assume SMP

	mrc	p15, 0, r0, c0, c0, 5		@ read MPIDR
	and	r0, r0, #0xc0000000			@ multiprocessing extensions and
	teq	r0, #0x80000000				@ not part of a uniprocessor system?
	bne    __fixup_smp_on_up		@ no, assume UP

	@ Core indicates it is SMP. Check for Aegis SOC where a single
	@ Cortex-A9 CPU is present but SMP operations fault.
	mov	r4, #0x41000000
	orr	r4, r4, #0x0000c000
	orr	r4, r4, #0x00000090
	teq	r3, r4						@ Check for ARM Cortex-A9
	retne	lr						@ Not ARM Cortex-A9,

	@ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the
	@ below address check will need to be #ifdef'd or equivalent
	@ for the Aegis platform.
	mrc	p15, 4, r0, c15, c0	@ get SCU base address
	teq	r0, #0x0					@ '0' on actual UP A9 hardware
	beq	__fixup_smp_on_up			@ So its an A9 UP
	ldr	r0, [r0, #4]				@ read SCU Config
ARM_BE8(rev	r0, r0)					@ byteswap if big endian
	and	r0, r0, #0x3				@ number of CPUs
	teq	r0, #0x0					@ is 1?
	retne	lr

__fixup_smp_on_up:
	adr	r0, 1f
	ldmia	r0, {r3 - r5}
	sub	r3, r0, r3
	add	r4, r4, r3
	add	r5, r5, r3
	b	__do_fixup_smp_on_up
ENDPROC(__fixup_smp)

	.align
1:	.word	.
	.word	__smpalt_begin
	.word	__smpalt_end

	.pushsection .data
	.globl	smp_on_up
smp_on_up:
	ALT_SMP(.long	1)
	ALT_UP(.long	0)
	.popsection
#endif

	.text
__do_fixup_smp_on_up:
	cmp	r4, r5
	reths	lr
	ldmia	r4!, {r0, r6}
 ARM(	str	r6, [r0, r3]	)
 THUMB(	add	r0, r0, r3	)
#ifdef __ARMEB__
 THUMB(	mov	r6, r6, ror #16		)	@ Convert word order for big-endian.
#endif
 THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
 THUMB(	mov	r6, r6, lsr #16		)	@ to be robust against misaligned r3.
 THUMB(	strh	r6, [r0]		)
	b	__do_fixup_smp_on_up
ENDPROC(__do_fixup_smp_on_up)

ENTRY(fixup_smp)
	stmfd	sp!, {r4 - r6, lr}
	mov	r4, r0
	add	r5, r0, r1
	mov	r3, #0
	bl	__do_fixup_smp_on_up
	ldmfd	sp!, {r4 - r6, pc}
ENDPROC(fixup_smp)

#ifdef __ARMEB__
#define LOW_OFFSET	0x4
#define HIGH_OFFSET	0x0
#else
#define LOW_OFFSET	0x0
#define HIGH_OFFSET	0x4
#endif

#ifdef CONFIG_ARM_PATCH_PHYS_VIRT

/* __fixup_pv_table - patch the stub instructions with the delta between
 * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and
 * can be expressed by an immediate shifter operand. The stub instruction
 * has a form of '(add|sub) rd, rn, #imm'.
 */
	__HEAD
__fixup_pv_table:
	adr	r0, 1f
	ldmia	r0, {r3-r7}
	mvn	ip, #0
	subs	r3, r0, r3				@ PHYS_OFFSET - PAGE_OFFSET
	add	r4, r4, r3					@ adjust table start address
	add	r5, r5, r3					@ adjust table end address
	add	r6, r6, r3					@ adjust __pv_phys_pfn_offset address
	add	r7, r7, r3					@ adjust __pv_offset address
	mov	r0, r8, lsr #PAGE_SHIFT		@ convert to PFN
	str	r0, [r6]					@ save computed PHYS_OFFSET to __pv_phys_pfn_offset
	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
	mov	r6, r3, lsr #24				@ constant for add/sub instructions
	teq	r3, r6, lsl #24			 	@ must be 16MiB aligned
THUMB(	it	ne						@ cross section branch )
	bne	__error
	str	r3, [r7, #LOW_OFFSET]		@ save to __pv_offset low bits
	b	__fixup_a_pv_table
ENDPROC(__fixup_pv_table)

	.align
1:	.long	.
	.long	__pv_table_begin
	.long	__pv_table_end
2:	.long	__pv_phys_pfn_offset
	.long	__pv_offset

	.text
__fixup_a_pv_table:
	adr	r0, 3f
	ldr	r6, [r0]
	add	r6, r6, r3
	ldr	r0, [r6, #HIGH_OFFSET]		@ pv_offset high word
	ldr	r6, [r6, #LOW_OFFSET]		@ pv_offset low word
	mov	r6, r6, lsr #24
	cmn	r0, #1
#ifdef CONFIG_THUMB2_KERNEL
	moveq	r0, #0x200000			@ set bit 21, mov to mvn instruction
	lsls	r6, #24
	beq	2f
	clz	r7, r6
	lsr	r6, #24
	lsl	r6, r7
	bic	r6, #0x0080
	lsrs	r7, #1
	orrcs	r6, #0x0080
	orr	r6, r6, r7, lsl #12
	orr	r6, #0x4000
	b	2f
1:	add     r7, r3
	ldrh	ip, [r7, #2]
ARM_BE8(rev16	ip, ip)
	tst	ip, #0x4000
	and	ip, #0x8f00
	orrne	ip, r6					@ mask in offset bits 31-24
	orreq	ip, r0					@ mask in offset bits 7-0
ARM_BE8(rev16	ip, ip)
	strh	ip, [r7, #2]
	bne	2f
	ldrh	ip, [r7]
ARM_BE8(rev16	ip, ip)
	bic	ip, #0x20
	orr	ip, ip, r0, lsr #16
ARM_BE8(rev16	ip, ip)
	strh	ip, [r7]
2:	cmp	r4, r5
	ldrcc	r7, [r4], #4			@ use branch for delay slot
	bcc	1b
	bx	lr
#else
#ifdef CONFIG_CPU_ENDIAN_BE8
	moveq	r0, #0x00004000			@ set bit 22, mov to mvn instruction
#else
	moveq	r0, #0x400000			@ set bit 22, mov to mvn instruction
#endif
	b	2f
1:	ldr	ip, [r7, r3]
#ifdef CONFIG_CPU_ENDIAN_BE8
	@ in BE8, we load data in BE, but instructions still in LE
	bic	ip, ip, #0xff000000
	tst	ip, #0x000f0000				@ check the rotation field
	orrne	ip, ip, r6, lsl #24 	@ mask in offset bits 31-24
	biceq	ip, ip, #0x00004000 	@ clear bit 22
	orreq	ip, ip, r0      		@ mask in offset bits 7-0
#else
	bic	ip, ip, #0x000000ff
	tst	ip, #0xf00					@ check the rotation field
	orrne	ip, ip, r6				@ mask in offset bits 31-24
	biceq	ip, ip, #0x400000		@ clear bit 22
	orreq	ip, ip, r0				@ mask in offset bits 7-0
#endif
	str	ip, [r7, r3]
2:	cmp	r4, r5
	ldrcc	r7, [r4], #4			@ use branch for delay slot
	bcc	1b
	ret	lr
#endif
ENDPROC(__fixup_a_pv_table)

	.align
3:	.long __pv_offset

ENTRY(fixup_pv_table)
	stmfd	sp!, {r4 - r7, lr}
	mov	r3, #0			@ no offset
	mov	r4, r0			@ r0 = table start
	add	r5, r0, r1		@ r1 = table size
	bl	__fixup_a_pv_table
	ldmfd	sp!, {r4 - r7, pc}
ENDPROC(fixup_pv_table)

	.data
	.globl	__pv_phys_pfn_offset
	.type	__pv_phys_pfn_offset, %object
__pv_phys_pfn_offset:
	.word	0
	.size	__pv_phys_pfn_offset, . -__pv_phys_pfn_offset

	.globl	__pv_offset
	.type	__pv_offset, %object
__pv_offset:
	.quad	0
	.size	__pv_offset, . -__pv_offset
#endif

#include "head-common.S"

-)暂未注解: head-common.S

/*
 *  linux/arch/arm/kernel/head-common.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.
 *
 */
#include 

#define ATAG_CORE 0x54410001
#define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
#define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2)

#ifdef CONFIG_CPU_BIG_ENDIAN
#define OF_DT_MAGIC 0xd00dfeed
#else
#define OF_DT_MAGIC 0xedfe0dd0 /* 0xd00dfeed in big-endian */
#endif

/*
 * Exception handling.  Something went wrong and we can't proceed.  We
 * ought to tell the user, but since we don't have any guarantee that
 * we're even running on the right architecture, we do virtually nothing.
 *
 * If CONFIG_DEBUG_LL is set we try to print out something about the error
 * and hope for the best (useful if bootloader fails to pass a proper
 * machine ID for example).
 */
	__HEAD

/* Determine validity of the r2 atags pointer.  The heuristic requires
 * that the pointer be aligned, in the first 16k of physical RAM and
 * that the ATAG_CORE marker is first and present.  If CONFIG_OF_FLATTREE
 * is selected, then it will also accept a dtb pointer.  Future revisions
 * of this function may be more lenient with the physical address and
 * may also be able to move the ATAGS block if necessary.
 *
 * Returns:
 *  r2 either valid atags pointer, valid dtb pointer, or zero
 *  r5, r6 corrupted
 */
__vet_atags:
	tst	r2, #0x3					@ aligned?
	bne	1f

	ldr	r5, [r2, #0]
#ifdef CONFIG_OF_FLATTREE
	ldr	r6, =OF_DT_MAGIC			@ is it a DTB?
	cmp	r5, r6
	beq	2f
#endif
	cmp	r5, #ATAG_CORE_SIZE			@ is first tag ATAG_CORE?
	cmpne	r5, #ATAG_CORE_SIZE_EMPTY
	bne	1f
	ldr	r5, [r2, #4]
	ldr	r6, =ATAG_CORE
	cmp	r5, r6
	bne	1f

2:	ret	lr							@ atag/dtb pointer is ok

1:	mov	r2, #0
	ret	lr
ENDPROC(__vet_atags)

/*
 * The following fragment of code is executed with the MMU on in MMU mode,
 * and uses absolute addresses; this is not position independent.
 *
 *  r0  = cp#15 control register
 *  r1  = machine ID
 *  r2  = atags/dtb pointer
 *  r9  = processor ID
 */
	__INIT
__mmap_switched:
	adr	r3, __mmap_switched_data

	ldmia	r3!, {r4, r5, r6, r7}
	cmp	r4, r5						@ Copy data segment if needed
1:	cmpne	r5, r6
	ldrne	fp, [r4], #4
	strne	fp, [r5], #4
	bne	1b

	mov	fp, #0						@ Clear BSS (and zero fp)
1:	cmp	r6, r7
	strcc	fp, [r6],#4
	bcc	1b

 ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
 THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
 THUMB(	ldr	sp, [r3, #16]				)
	str	r9, [r4]					@ Save processor ID
	str	r1, [r5]					@ Save machine type
	str	r2, [r6]					@ Save atags pointer
	cmp	r7, #0
	strne	r0, [r7]				@ Save control register values
	b	start_kernel
ENDPROC(__mmap_switched)

	.align	2
	.type	__mmap_switched_data, %object
__mmap_switched_data:
	.long	__data_loc				@ r4
	.long	_sdata					@ r5
	.long	__bss_start				@ r6
	.long	_end					@ r7
	.long	processor_id			@ r4
	.long	__machine_arch_type		@ r5
	.long	__atags_pointer			@ r6
#ifdef CONFIG_CPU_CP15
	.long	cr_alignment			@ r7
#else
	.long	0						@ r7
#endif
	.long	init_thread_union + THREAD_START_SP @ sp
	.size	__mmap_switched_data, . - __mmap_switched_data

/*
 * 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)

	__FINIT
	.text

/*
 * 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)
 */
__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:	ret	lr
ENDPROC(__lookup_processor_type)

/*
 * Look in  for information about the __proc_info structure.
 */
	.align	2
	.type	__lookup_processor_type_data, %object
__lookup_processor_type_data:
	.long	.
	.long	__proc_info_begin
	.long	__proc_info_end
	.size	__lookup_processor_type_data, . - __lookup_processor_type_data

__error_lpae:
#ifdef CONFIG_DEBUG_LL
	adr	r0, str_lpae
	bl 	printascii
	b	__error
str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
#else
	b	__error
#endif
	.align
ENDPROC(__error_lpae)

__error_p:
#ifdef CONFIG_DEBUG_LL
	adr	r0, str_p1
	bl	printascii
	mov	r0, r9
	bl	printhex8
	adr	r0, str_p2
	bl	printascii
	b	__error
str_p1:	.asciz	"\nError: unrecognized/unsupported processor variant (0x"
str_p2:	.asciz	").\n"
	.align
#endif
ENDPROC(__error_p)

__error:
#ifdef CONFIG_ARCH_RPC
/*
 * Turn the screen red on a error - RiscPC only.
 */
	mov	r0, #0x02000000
	mov	r3, #0x11
	orr	r3, r3, r3, lsl #8
	orr	r3, r3, r3, lsl #16
	str	r3, [r0], #4
	str	r3, [r0], #4
	str	r3, [r0], #4
	str	r3, [r0], #4
#endif
1:	mov	r0, r0
	b	1b
ENDPROC(__error)

#)初始化第一阶段流程

  1. arch/arm/kernel/head.S/stext

  2. arch/arm/kernel/head.S/__enable_mmu

  3. arch/arm/kernel/head.S/__trun_mmu_on

  4. arch/arm/kernel/head-common.S/__mmap_switched

  5. init/main.c/start_kernel

你可能感兴趣的:(arm,linux,linux,arm开发)