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

• 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 <linux/linkage.h>
#include <linux/init.h>

#include <asm/assembler.h>
#include <asm/cp15.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/pgtable.h>

#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