今天下载了最新版本的4.2.0的内核进行阅读。
这是我理解的流程图
首先开始解压zImage内核镜像文件。代码在linux4.2.0/arch/arm/boot/compress/head.S中
首先我们找到程序的入口
start:
.type start,#function
.rept 7
__nop
.endr
#ifndef CONFIG_THUMB2_KERNEL
mov r0, r0
#else
AR_CLASS( sub pc, pc, #3 ) @ A/R: switch to Thumb2 mode
M_CLASS( nop.w ) @ M: already in Thumb2 mode
.thumb
#endif
W(b) 1f
.word _magic_sig @ Magic numbers to help the loader
.word _magic_start @ absolute load/run zImage address
.word _magic_end @ zImage end address
.word 0x04030201 @ endianness flag
.word 0x45454545 @ another magic number to indicate
.word _magic_table @ additional data table
__EFI_HEADER
1:
ARM_BE8( setend be ) @ go BE8 if compiled for BE8
AR_CLASS( mrs r9, cpsr )
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install @ get into SVC mode, reversibly
#endif
mov r7, r1 @ save architecture ID
mov r8, r2 @ save atags pointer
#ifndef CONFIG_CPU_V7M
/*
* Booting from Angel - need to enter SVC mode and disable
* FIQs/IRQs (numeric definitions from angel arm.h source).
* We only do this if we were in user mode on entry.
*/
mrs r2, cpsr @ get current mode
tst r2, #3 @ not user?
bne not_angel
mov r0, #0x17 @ angel_SWIreason_EnterSVC
ARM( swi 0x123456 ) @ angel_SWI_ARM
THUMB( svc 0xab ) @ angel_SWI_THUMB
not_angel:
safe_svcmode_maskall r0
msr spsr_cxsf, r9 @ Save the CPU boot mode in
@ SPSR
#endif
在该文件夹下的makefile中去寻找我们的define,找到的定义如下:
ifeq ($(CONFIG_ARM_VIRT_EXT),y)
OBJS += hyp-stub.o
endif
开始将机器码ID存入R7中,将参数数据存入R8中。因为没有定义CONFIG_CPU_V7M所以进入SVC模式。
SVC的进入接口safe+svcmode_maskall在linux4.2.0/arch/arm/include/asm/assembler.h
.macro safe_svcmode_maskall reg:req
#if __LINUX_ARM_ARCH__ >= 6 && !defined(CONFIG_CPU_V7M)
mrs \reg , cpsr
eor \reg, \reg, #HYP_MODE
tst \reg, #MODE_MASK
bic \reg , \reg , #MODE_MASK
orr \reg , \reg , #PSR_I_BIT | PSR_F_BIT | SVC_MODE
THUMB( orr \reg , \reg , #PSR_T_BIT )
bne 1f
orr \reg, \reg, #PSR_A_BIT
badr lr, 2f
msr spsr_cxsf, \reg
__MSR_ELR_HYP(14)
__ERET
1: msr cpsr_c, \reg
2:
#else
/*
* workaround for possibly broken pre-v6 hardware
* (akita, Sharp Zaurus C-1000, PXA270-based)
*/
setmode PSR_F_BIT | PSR_I_BIT | SVC_MODE, \reg
#endif
.endm
在进入SVC模式时会关闭FIQ/IRQ。
接下来我们继续顺序执行程序
.text
#ifdef CONFIG_AUTO_ZRELADDR
/*
* Find the start of physical memory. As we are executing
* without the MMU on, we are in the physical address space.
* We just need to get rid of any offset by aligning the
* address.
*
* This alignment is a balance between the requirements of
* different platforms - we have chosen 128MB to allow
* platforms which align the start of their physical memory
* to 128MB to use this feature, while allowing the zImage
* to be placed within the first 128MB of memory on other
* platforms. Increasing the alignment means we place
* stricter alignment requirements on the start of physical
* memory, but relaxing it means that we break people who
* are already placing their zImage in (eg) the top 64MB
* of this range.
*/
mov r4, pc
and r4, r4, #0xf8000000
/* Determine final kernel image address. */
add r4, r4, #TEXT_OFFSET
#else
ldr r4, =zreladdr
#endif
在该文件夹下的makefile并没有发现定义了CONFIG_AUTO_ZERLADDR。所以直接将镜像文件的地址设置为zreladdr
然后继续执行代码
/*
* 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.
*/
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
restart: adr r0, LC0
ldmia r0, {r1, r2, r3, r6, r10, r11, r12}
ldr sp, [r0, #28]
/*
* We might be running at a different address. We need
* to fix up various pointers.
*/
sub r0, r0, r1 @ calculate the delta offset
add r6, r6, r0 @ _edata
add r10, r10, r0 @ inflated kernel size location
/*
* The kernel build system appends the size of the
* decompressed kernel at the end of the compressed data
* in little-endian form.
*/
ldrb r9, [r10, #0]
ldrb lr, [r10, #1]
orr r9, r9, lr, lsl #8
ldrb lr, [r10, #2]
ldrb r10, [r10, #3]
orr r9, r9, lr, lsl #16
orr r9, r9, r10, lsl #24
#ifndef CONFIG_ZBOOT_ROM
/* malloc space is above the relocated stack (64k max) */
add sp, sp, r0
add r10, sp, #0x10000
#else
/*
* With ZBOOT_ROM the bss/stack is non relocatable,
* but someone could still run this code from RAM,
* in which case our reference is _edata.
*/
mov r10, r6
#endif
mov r5, #0 @ init dtb size to 0
#ifdef CONFIG_ARM_APPENDED_DTB
/*
* r0 = delta
* r2 = BSS start
* r3 = BSS end
* r4 = final kernel address (possibly with LSB set)
* r5 = appended dtb size (still unknown)
* r6 = _edata
* r7 = architecture ID
* r8 = atags/device tree pointer
* r9 = size of decompressed image
* r10 = end of this image, including bss/stack/malloc space if non XIP
* r11 = GOT start
* r12 = GOT end
* sp = stack pointer
*
* if there are device trees (dtb) appended to zImage, advance r10 so that the
* dtb data will get relocated along with the kernel if necessary.
*/
判断内核解压地址是否在镜像文件的地址,是则pc指针地址直接赋值给r0,如果不是则创建一个页表。之后初始化缓存,计算镜像文件地址。
然后继续向下
mov r8, r6 @ use the appended device tree
/*
* Make sure that the DTB doesn't end up in the final
* kernel's .bss area. To do so, we adjust the decompressed
* kernel size to compensate if that .bss size is larger
* than the relocated code.
*/
ldr r5, =_kernel_bss_size
adr r1, wont_overwrite
sub r1, r6, r1
subs r1, r5, r1
addhi r9, r9, r1
/* Get the current DTB size */
ldr r5, [r6, #4]
#ifndef __ARMEB__
/* convert r5 (dtb size) to little endian */
eor r1, r5, r5, ror #16
bic r1, r1, #0x00ff0000
mov r5, r5, ror #8
eor r5, r5, r1, lsr #8
#endif
/* preserve 64-bit alignment */
add r5, r5, #7
bic r5, r5, #7
/* relocate some pointers past the appended dtb */
add r6, r6, r5
add r10, r10, r5
add sp, sp, r5
这里重新调整设备树
/*
* Check to see if we will overwrite ourselves.
* r4 = final kernel address (possibly with LSB set)
* r9 = size of decompressed image
* r10 = end of this image, including bss/stack/malloc space if non XIP
* We basically want:
* r4 - 16k page directory >= r10 -> OK
* r4 + image length <= address of wont_overwrite -> OK
* Note: the possible LSB in r4 is harmless here.
*/
add r10, r10, #16384
cmp r4, r10
bhs wont_overwrite
add r10, r4, r9
adr r9, wont_overwrite
cmp r10, r9
bls wont_overwrite
这部分代码用来分析当前代码是否会和最后的解压部分重叠,如果有重叠则需要执行代码搬移,判断r4,r9,r10是否需要代码搬运,需要则进行代码搬运。
/*
* Relocate ourselves past the end of the decompressed kernel.
* r6 = _edata
* r10 = end of the decompressed kernel
* Because we always copy ahead, we need to do it from the end and go
* backward in case the source and destination overlap.
*/
/*
* Bump to the next 256-byte boundary with the size of
* the relocation code added. This avoids overwriting
* ourself when the offset is small.
*/
add r10, r10, #((reloc_code_end - restart + 256) & ~255)
bic r10, r10, #255
/* Get start of code we want to copy and align it down. */
adr r5, restart
bic r5, r5, #31
/* Relocate the hyp vector base if necessary */
然后进行代码搬移地址的扩展
sub r9, r6, r5 @ size to copy
add r9, r9, #31 @ rounded up to a multiple
bic r9, r9, #31 @ ... of 32 bytes
add r6, r9, r5
add r9, r9, r10
bl cache_clean_flush
badr r0, restart
add r0, r0, r6
mov pc, r0
这里首先计算出需要搬运的大小保存到r9中,搬运的原结束地址到r6中,搬运的目的结束地址到r9中。注意这里只搬运代码段和数据段,并不包含bss、栈和堆空间。cache_clean_flush清除缓存然后正式开始搬运
然后继续运行程序
wont_overwrite:
/*
* If delta is zero, we are running at the address we were linked at.
* r0 = delta
* r2 = BSS start
* r3 = BSS end
* r4 = kernel execution address (possibly with LSB set)
* r5 = appended dtb size (0 if not present)
* r7 = architecture ID
* r8 = atags pointer
* r11 = GOT start
* r12 = GOT end
* sp = stack pointer
*/
orrs r1, r0, r5
beq not_relocated
add r11, r11, r0
add r12, r12, r0
如果r0为0则说明当前运行的地址就是链接地址,无需进行重定位,跳转到not_relocated执行,但是这里运行的地址已经被移动到内核解压地址之后跳转到not_relocated
not_relocated: mov r0, #0
1: str r0, [r2], #4 @ clear bss
str r0, [r2], #4
str r0, [r2], #4
str r0, [r2], #4
cmp r2, r3
blo 1b
/*
* Did we skip the cache setup earlier?
* That is indicated by the LSB in r4.
* Do it now if so.
*/
tst r4, #1
bic r4, r4, #1
blne cache_on
/*
* The C runtime environment should now be setup sufficiently.
* Set up some pointers, and start decompressing.
* r4 = kernel execution address
* r7 = architecture ID
* r8 = atags pointer
*/
mov r0, r4
mov r1, sp @ malloc space above stack
add r2, sp, #0x10000 @ 64k max
mov r3, r7
bl decompress_kernel
bl cache_clean_flush
bl cache_off
#ifdef CONFIG_ARM_VIRT_EXT
mrs r0, spsr @ Get saved CPU boot mode
and r0, r0, #MODE_MASK
cmp r0, #HYP_MODE @ if not booted in HYP mode...
bne __enter_kernel @ boot kernel directly
adr r12, .L__hyp_reentry_vectors_offset
ldr r0, [r12]
add r0, r0, r12
bl __hyp_set_vectors
__HVC(0) @ otherwise bounce to hyp mode
b . @ should never be reached
.align 2
.L__hyp_reentry_vectors_offset: .long __hyp_reentry_vectors - .
#else
b __enter_kernel
#endif
__enter_kernel:
mov r0, #0 @ must be 0
mov r1, r7 @ restore architecture number
mov r2, r8 @ restore atags pointer
ARM( mov pc, r4 ) @ call kernel
M_CLASS( add r4, r4, #1 ) @ enter in Thumb mode for M class
THUMB( bx r4 ) @ entry point is always ARM for A/R classes
然后解压镜像文件,刷新缓存,关闭缓存,然后进入内核入口。之后我们就转到内核中去。在文件linux-4.20/arch/arm/kernel/head.S中。
其实我还是很多地方不懂,等学到一定程度再回来复习吧。我是参考ARM Linux启动流程分析——内核自解压阶段
这是进入内核的启动流程
__HEAD
ENTRY(stext)
ARM_BE8(setend be ) @ ensure we are in BE8 mode
THUMB( badr r9, 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
一进入内核我们就先进入SVC模式和关闭中断。
mrc p15, 0, r9, c0, c0 @ get processor id
bl __lookup_processor_type @ r5=procinfo r9=cpuid
movs r10, r5 @ invalid processor (r5=0)?
THUMB( it eq ) @ force fixup-able long branch encoding
beq __error_p @ yes, error 'p'
然后进行处理器类型检测,成功再进行下一步
#ifndef CONFIG_XIP_KERNEL
adr r3, 2f
ldmia r3, {r4, r8}
sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET)
add r8, r8, r4 @ PHYS_OFFSET
#else
ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case
#endif
网络初始化
/*
* r1 = machine no, r2 = atags or dtb,
* r8 = phys_offset, r9 = cpuid, r10 = procinfo
*/
bl __vet_atags
#ifdef CONFIG_SMP_ON_UP
bl __fixup_smp
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
bl __fixup_pv_table
#endif
bl __create_page_tables
创建核心页
ldr r13, =__mmap_switched @ address to jump to after
@ mmu has been enabled
badr lr, 1f @ return (PIC) address
#ifdef CONFIG_ARM_LPAE
mov r5, #0 @ high TTBR0
mov r8, r4, lsr #12 @ TTBR1 is swapper_pg_dir pfn
#else
mov r8, r4 @ set TTBR1 to swapper_pg_dir
#endif
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
/*
* Setup common bits before finally enabling the MMU. Essentially
* this is just loading the page table pointer and domain access
* registers. All these registers need to be preserved by the
* processor setup function (or set in the case of r0)
*
* r0 = cp#15 control register
* r1 = machine ID
* r2 = atags or dtb pointer
* r4 = TTBR pointer (low word)
* r5 = TTBR pointer (high word if LPAE)
* 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
#ifdef CONFIG_ARM_LPAE
mcrr p15, 0, r4, r5, c2 @ load TTBR0
#else
mov r5, #DACR_INIT
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)
这里进行mmu的使能,然后返回R13的地址,让我们来看看r13到底是什么,我们一点点网上找
mov r13, r12 @ __secondary_switched address
adr r4, __secondary_data
ldmia r4, {r5, r7, r12} @ address to jump to after
就是_secondary_data的地址,然后我们继续代码的运行
__secondary_data:
.long .
.long secondary_data
.long __secondary_switched
ENTRY(__secondary_switched)
ldr sp, [r7, #12] @ get secondary_data.stack
mov fp, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
这样我们就运行到代码的内核启动了,开始代码在init/main.c下面,因为已经初始化栈和指针所以这部分是c语言写的
asmlinkage __visible void __init start_kernel(void)
{
char *command_line;
char *after_dashes;
set_task_stack_end_magic(&init_task);
smp_setup_processor_id();
debug_objects_early_init();
cgroup_init_early();
local_irq_disable();
early_boot_irqs_disabled = true;
/*
* Interrupts are still disabled. Do necessary setups, then
* enable them.
*/
boot_cpu_init();
page_address_init();
pr_notice("%s", linux_banner);
setup_arch(&command_line);
/*
* Set up the the initial canary and entropy after arch
* and after adding latent and command line entropy.
*/
add_latent_entropy();
add_device_randomness(command_line, strlen(command_line));
boot_init_stack_canary();
mm_init_cpumask(&init_mm);
setup_command_line(command_line);
setup_nr_cpu_ids();
setup_per_cpu_areas();
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
boot_cpu_hotplug_init();
build_all_zonelists(NULL);
page_alloc_init();
pr_notice("Kernel command line: %s\n", boot_command_line);
parse_early_param();
after_dashes = parse_args("Booting kernel",
static_command_line, __start___param,
__stop___param - __start___param,
-1, -1, NULL, &unknown_bootoption);
if (!IS_ERR_OR_NULL(after_dashes))
parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
NULL, set_init_arg);
jump_label_init();
/*
* These use large bootmem allocations and must precede
* kmem_cache_init()
*/
setup_log_buf(0);
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_init();
ftrace_init();
/* trace_printk can be enabled here */
early_trace_init();
/*
* Set up the scheduler prior starting any interrupts (such as the
* timer interrupt). Full topology setup happens at smp_init()
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
/*
* Disable preemption - early bootup scheduling is extremely
* fragile until we cpu_idle() for the first time.
*/
preempt_disable();
if (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
radix_tree_init();
/*
* Set up housekeeping before setting up workqueues to allow the unbound
* workqueue to take non-housekeeping into account.
*/
housekeeping_init();
/*
* Allow workqueue creation and work item queueing/cancelling
* early. Work item execution depends on kthreads and starts after
* workqueue_init().
*/
workqueue_init_early();
rcu_init();
/* Trace events are available after this */
trace_init();
if (initcall_debug)
initcall_debug_enable();
context_tracking_init();
/* init some links before init_ISA_irqs() */
early_irq_init();
init_IRQ();
tick_init();
rcu_init_nohz();
init_timers();
hrtimers_init();
softirq_init();
timekeeping_init();
time_init();
printk_safe_init();
perf_event_init();
profile_init();
call_function_init();
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
early_boot_irqs_disabled = false;
local_irq_enable();
kmem_cache_init_late();
/*
* HACK ALERT! This is early. We're enabling the console before
* we've done PCI setups etc, and console_init() must be aware of
* this. But we do want output early, in case something goes wrong.
*/
console_init();
if (panic_later)
panic("Too many boot %s vars at `%s'", panic_later,
panic_param);
lockdep_init();
/*
* Need to run this when irqs are enabled, because it wants
* to self-test [hard/soft]-irqs on/off lock inversion bugs
* too:
*/
locking_selftest();
/*
* This needs to be called before any devices perform DMA
* operations that might use the SWIOTLB bounce buffers. It will
* mark the bounce buffers as decrypted so that their usage will
* not cause "plain-text" data to be decrypted when accessed.
*/
mem_encrypt_init();
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
pr_crit("initrd overwritten (0x%08lx < 0x%08lx) - disabling it.\n",
page_to_pfn(virt_to_page((void *)initrd_start)),
min_low_pfn);
initrd_start = 0;
}
#endif
page_ext_init();
kmemleak_init();
debug_objects_mem_init();
setup_per_cpu_pageset();
numa_policy_init();
acpi_early_init();
if (late_time_init)
late_time_init();
sched_clock_init();
calibrate_delay();
pid_idr_init();
anon_vma_init();
#ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
thread_stack_cache_init();
cred_init();
fork_init();
proc_caches_init();
uts_ns_init();
buffer_init();
key_init();
security_init();
dbg_late_init();
vfs_caches_init();
pagecache_init();
signals_init();
seq_file_init();
proc_root_init();
nsfs_init();
cpuset_init();
cgroup_init();
taskstats_init_early();
delayacct_init();
check_bugs();
acpi_subsystem_init();
arch_post_acpi_subsys_init();
sfi_init_late();
if (efi_enabled(EFI_RUNTIME_SERVICES)) {
efi_free_boot_services();
}
/* Do the rest non-__init'ed, we're now alive */
arch_call_rest_init();
}
先将各种资源初始化好后最后调用进程初始化。arch_call_rest_init()里面是这样的
void __init __weak arch_call_rest_init(void)
{
rest_init();
}
noinline void __ref rest_init(void)
{
struct task_struct *tsk;
int pid;
rcu_scheduler_starting();
/*
* We need to spawn init first so that it obtains pid 1, however
* the init task will end up wanting to create kthreads, which, if
* we schedule it before we create kthreadd, will OOPS.
*/
pid = kernel_thread(kernel_init, NULL, CLONE_FS);
/*
* Pin init on the boot CPU. Task migration is not properly working
* until sched_init_smp() has been run. It will set the allowed
* CPUs for init to the non isolated CPUs.
*/
rcu_read_lock();
tsk = find_task_by_pid_ns(pid, &init_pid_ns);
set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
rcu_read_unlock();
numa_default_policy();
pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
rcu_read_lock();
kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
rcu_read_unlock();
/*
* Enable might_sleep() and smp_processor_id() checks.
* They cannot be enabled earlier because with CONFIG_PREEMPT=y
* kernel_thread() would trigger might_sleep() splats. With
* CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
* already, but it's stuck on the kthreadd_done completion.
*/
system_state = SYSTEM_SCHEDULING;
complete(&kthreadd_done);
/*
* The boot idle thread must execute schedule()
* at least once to get things moving:
*/
schedule_preempt_disabled();
/* Call into cpu_idle with preempt disabled */
cpu_startup_entry(CPUHP_ONLINE);
}
内核启动
static int __ref kernel_init(void *unused)
{
int ret;
kernel_init_freeable();
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
ftrace_free_init_mem();
free_initmem();
mark_readonly();
/*
* Kernel mappings are now finalized - update the userspace page-table
* to finalize PTI.
*/
pti_finalize();
system_state = SYSTEM_RUNNING;
numa_default_policy();
rcu_end_inkernel_boot();
if (ramdisk_execute_command) {
ret = run_init_process(ramdisk_execute_command);
if (!ret)
return 0;
pr_err("Failed to execute %s (error %d)\n",
ramdisk_execute_command, ret);
}
/*
* We try each of these until one succeeds.
*
* The Bourne shell can be used instead of init if we are
* trying to recover a really broken machine.
*/
if (execute_command) {
ret = run_init_process(execute_command);
if (!ret)
return 0;
panic("Requested init %s failed (error %d).",
execute_command, ret);
}
if (!try_to_run_init_process("/sbin/init") ||
!try_to_run_init_process("/etc/init") ||
!try_to_run_init_process("/bin/init") ||
!try_to_run_init_process("/bin/sh"))
return 0;
panic("No working init found. Try passing init= option to kernel. "
"See Linux Documentation/admin-guide/init.rst for guidance.");
}
static noinline void __init kernel_init_freeable(void)
{
/*
* Wait until kthreadd is all set-up.
*/
wait_for_completion(&kthreadd_done);
/* Now the scheduler is fully set up and can do blocking allocations */
gfp_allowed_mask = __GFP_BITS_MASK;
/*
* init can allocate pages on any node
*/
set_mems_allowed(node_states[N_MEMORY]);
cad_pid = task_pid(current);
smp_prepare_cpus(setup_max_cpus);
workqueue_init();
init_mm_internals();
do_pre_smp_initcalls();
lockup_detector_init();
smp_init();
sched_init_smp();
page_alloc_init_late();
do_basic_setup();
/* Open the /dev/console on the rootfs, this should never fail */
if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
pr_err("Warning: unable to open an initial console.\n");
(void) ksys_dup(0);
(void) ksys_dup(0);
/*
* check if there is an early userspace init. If yes, let it do all
* the work
*/
if (!ramdisk_execute_command)
ramdisk_execute_command = "/init";
if (ksys_access((const char __user *)
ramdisk_execute_command, 0) != 0) {
ramdisk_execute_command = NULL;
prepare_namespace();
}
/*
* Ok, we have completed the initial bootup, and
* we're essentially up and running. Get rid of the
* initmem segments and start the user-mode stuff..
*
* rootfs is available now, try loading the public keys
* and default modules
*/
integrity_load_keys();
load_default_modules();
}
其中prepare_namespace()是根文件系统的挂载,代码在linux-4.20/init/do_mounts.c中
/*
* Prepare the namespace - decide what/where to mount, load ramdisks, etc.
*/
void __init prepare_namespace(void)
{
int is_floppy;
if (root_delay) {
printk(KERN_INFO "Waiting %d sec before mounting root device...\n",
root_delay);
ssleep(root_delay);
}
/*
* wait for the known devices to complete their probing
*
* Note: this is a potential source of long boot delays.
* For example, it is not atypical to wait 5 seconds here
* for the touchpad of a laptop to initialize.
*/
wait_for_device_probe();
md_run_setup();
if (saved_root_name[0]) {
root_device_name = saved_root_name;
if (!strncmp(root_device_name, "mtd", 3) ||
!strncmp(root_device_name, "ubi", 3)) {
mount_block_root(root_device_name, root_mountflags);
goto out;
}
ROOT_DEV = name_to_dev_t(root_device_name);
if (strncmp(root_device_name, "/dev/", 5) == 0)
root_device_name += 5;
}
if (initrd_load())
goto out;
/* wait for any asynchronous scanning to complete */
if ((ROOT_DEV == 0) && root_wait) {
printk(KERN_INFO "Waiting for root device %s...\n",
saved_root_name);
while (driver_probe_done() != 0 ||
(ROOT_DEV = name_to_dev_t(saved_root_name)) == 0)
msleep(5);
async_synchronize_full();
}
is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
if (is_floppy && rd_doload && rd_load_disk(0))
ROOT_DEV = Root_RAM0;
mount_root();
out:
devtmpfs_mount("dev");
ksys_mount(".", "/", NULL, MS_MOVE, NULL);
ksys_chroot(".");
}
加载完成,最后交出权限,运行用户代码(linux首先启动/sbin/init)。总结下精简的流程如下