基于Linux與Busybox的Reboot命令流程分析

一：Busyobx層的分析

這段時(shí)間,在忙到一個(gè)項(xiàng)目時(shí),需要在busybox中用到reboot命令,開(kāi)始在busybox中的shell中輸入reboot命令,始終如下的信息,然后就停止在那里了,無(wú)法重啟...為了徹底的弄明白這個(gè)問(wèn)題,我在網(wǎng)絡(luò)上找了很久,終于有個(gè)人寫(xiě)的一個(gè)reboot流程分析,我就借花獻(xiàn)佛.在這里重新分析下busybox是如何運(yùn)行這個(gè)命令,同時(shí)又是如何調(diào)用到Linux內(nèi)核中的mach_reset中的arch_reset，當(dāng)針對(duì)不同的ARM芯片時(shí)，作為L(zhǎng)inux內(nèi)核開(kāi)發(fā)和驅(qū)動(dòng)開(kāi)發(fā)的朋友，對(duì)于這個(gè)流程還是一定要了解的。要不，出現(xiàn)問(wèn)題，又如何找出問(wèn)題呢。忘記了reboot的打印信息了，如下：

[plain]?view plain?copy

print?

The?system?is?going?down?NOW?!!??

Sending?SIGTERM?to?all?processes.??

Sending?SIGKILL?to?all?processes.??

Please?stand?by?while?rebooting?the?system.??

Restarting?system.??

.??

通過(guò)分析busybox1.20.0的代碼可以看出在init.c中有這樣一行的代碼，如下：

[cpp]?view plain?copy

print?

int?init_main(int?argc,?char?**argv)?MAIN_EXTERNALLY_VISIBLE;??

int?init_main(int?argc?UNUSED_PARAM,?char?**argv)??

{??

static?const?int?magic[]?=?{??

RB_HALT_SYSTEM,??

RB_POWER_OFF,??

RB_AUTOBOOT??

};??

static?const?smallint?signals[]?=?{?SIGUSR1,?SIGUSR2,?SIGTERM?};??

......??

/*?struct?sysinfo?is?linux-specific?*/??

#ifdef?__linux__??

/*?Make?sure?there?is?enough?memory?to?do?something?useful.?*/??

if?(ENABLE_SWAPONOFF)?{?//是否配置了swapoff命令??

struct?sysinfo?info;??

if?(sysinfo(&info)?==?0??

&&?(info.mem_unit???info.mem_unit?:?1)?*?(long?long)info.totalram?

)?{??

message(L_CONSOLE,?"Low?memory,?forcing?swapon");??

/*?swapon?-a?requires?/proc?typically?*/??

new_init_action(SYSINIT,?"mount?-t?proc?proc?/proc",?"");??

/*?Try?to?turn?on?swap?*/??

new_init_action(SYSINIT,?"swapon?-a",?"");??

run_actions(SYSINIT);???/*?wait?and?removing?*/??

}??

}??

#endif??

......??

/*?Make?the?command?line?just?say?"init"??-?thats?all,?nothing?else?*/??

strncpy(argv[0],?"init",?strlen(argv[0]));??

/*?Wipe?argv[1]-argv[N]?so?they?don't?clutter?the?ps?listing?*/??

while?(*++argv)??

memset(*argv,?0,?strlen(*argv));??

/*?Set?up?signal?handlers?*/??

/*?Set?up?signal?handlers?*/??

if?(!DEBUG_INIT)?{??

struct?sigaction?sa;??

bb_signals(0??

+?(1?<

+?(1?<

+?(1?<

,?halt_reboot_pwoff);//看到這個(gè)halt_reboot_pwoff??

signal(SIGQUIT,?restart_handler);?/*?re-exec?another?init?*/?//看到這個(gè)restart_handler函數(shù)，這是我們需要分析的??

/*?Stop?handler?must?allow?only?SIGCONT?inside?itself?*/??

memset(&sa,?0,?sizeof(sa));??

sigfillset(&sa.sa_mask);??

sigdelset(&sa.sa_mask,?SIGCONT);??

sa.sa_handler?=?stop_handler;??

/*?NB:?sa_flags?doesn't?have?SA_RESTART.?

*?It?must?be?able?to?interrupt?wait().?

*/??

sigaction_set(SIGTSTP,?&sa);?/*?pause?*/??

/*?Does?not?work?as?intended,?at?least?in?2.6.20.?

*?SIGSTOP?is?simply?ignored?by?init:?

*/??

sigaction_set(SIGSTOP,?&sa);?/*?pause?*/??

/*?SIGINT?(Ctrl-Alt-Del)?must?interrupt?wait(),?

*?setting?handler?without?SA_RESTART?flag.?

*/??

bb_signals_recursive_norestart((1?<

}??

......??

}??

單獨(dú)拿出halt_reboot_pwoff和restart_handler這個(gè)函數(shù)來(lái)看看

[cpp]?view plain?copy

print?

/*?The?SIGUSR[12]/SIGTERM?handler?*/??

static?void?halt_reboot_pwoff(int?sig)?NORETURN;??

static?void?halt_reboot_pwoff(int?sig)??

{??

const?char?*m;??

unsigned?rb;??

/*?We?may?call?run()?and?it?unmasks?signals,?

*?including?the?one?masked?inside?this?signal?handler.?

*?Testcase?which?would?start?multiple?reboot?scripts:?

*??while?true;?do?reboot;?done?

*?Preventing?it:?

*/??

reset_sighandlers_and_unblock_sigs();??

run_shutdown_and_kill_processes();??

m?=?"halt";??

rb?=?RB_HALT_SYSTEM;??

if?(sig?==?SIGTERM)?{??

m?=?"reboot";??

rb?=?RB_AUTOBOOT;??

}?else?if?(sig?==?SIGUSR2)?{??

m?=?"poweroff";??

rb?=?RB_POWER_OFF;??

}??

message(L_CONSOLE,?"Requesting?system?%s",?m);??

pause_and_low_level_reboot(rb);??

/*?not?reached?*/??

}??

restart_handler函數(shù)如下：

[cpp]?view plain?copy

print?

/*?Handler?for?QUIT?-?exec?"restart"?action,?

*?else?(no?such?action?defined)?do?nothing?*/??

static?void?restart_handler(int?sig?UNUSED_PARAM)??

{??

struct?init_action?*a;??

for?(a?=?init_action_list;?a;?a?=?a->next)?{??

if?(!(a->action_type?&?RESTART))??

continue;??

/*?Starting?from?here,?we?won't?return.?

*?Thus?don't?need?to?worry?about?preserving?errno?

*?and?such.?

*/??

reset_sighandlers_and_unblock_sigs();??

run_shutdown_and_kill_processes();??

#ifdef?RB_ENABLE_CAD??

/*?Allow?Ctrl-Alt-Del?to?reboot?the?system.?

*?This?is?how?kernel?sets?it?up?for?init,?we?follow?suit.?

*/??

reboot(RB_ENABLE_CAD);?/*?misnomer?*/??

#endif??

if?(open_stdio_to_tty(a->terminal))?{??

dbg_message(L_CONSOLE,?"Trying?to?re-exec?%s",?a->command);??

/*?Theoretically?should?be?safe.?

*?But?in?practice,?kernel?bugs?may?leave?

*?unkillable?processes,?and?wait()?may?block?forever.?

*?Oh?well.?Hoping?"new"?init?won't?be?too?surprised?

*?by?having?children?it?didn't?create.?

*/??

//while?(wait(NULL)?>?0)??

//??continue;??

init_exec(a->command);??

}??

/*?Open?or?exec?failed?*/??

pause_and_low_level_reboot(RB_HALT_SYSTEM);??

/*?not?reached?*/??

}??

}??

通過(guò)分析，我們看到他們都會(huì)有調(diào)用這兩個(gè)函數(shù)：reset_sighandlers_and_unblock_sigs();以及?run_shutdown_and_kill_processes();，我們重點(diǎn)關(guān)注如下這個(gè)函數(shù)：

[cpp]?view plain?copy

print?

static?void?run_shutdown_and_kill_processes(void)??

{??

/*?Run?everything?to?be?run?at?"shutdown".??This?is?done?_prior_?

*?to?killing?everything,?in?case?people?wish?to?use?scripts?to?

*?shut?things?down?gracefully...?*/??

run_actions(SHUTDOWN);??

message(L_CONSOLE?|?L_LOG,?"The?system?is?going?down?NOW!");??

/*?Send?signals?to?every?process?_except_?pid?1?*/??

kill(-1,?SIGTERM);??

message(L_CONSOLE?|?L_LOG,?"Sent?SIG%s?to?all?processes",?"TERM");??

sync();??

sleep(1);??

kill(-1,?SIGKILL);??

message(L_CONSOLE,?"Sent?SIG%s?to?all?processes",?"KILL");??

sync();??

/*sleep(1);?-?callers?take?care?about?making?a?pause?*/??

}??

嘿嘿，終于看到了上面的打印信息：The system is going down NOW !! 以及Sending SIGTERM to all processes. 同時(shí)在上面的halt_reboot_pwoff和restart_handler中都會(huì)調(diào)用這樣一個(gè)函數(shù)，如下：

[cpp]?view plain?copy

print?

static?void?pause_and_low_level_reboot(unsigned?magic)?NORETURN;??

static?void?pause_and_low_level_reboot(unsigned?magic)??

{??

pid_t?pid;??

/*?Allow?time?for?last?message?to?reach?serial?console,?etc?*/??

sleep(1);??

/*?We?have?to?fork?here,?since?the?kernel?calls?do_exit(EXIT_SUCCESS)?

*?in?linux/kernel/sys.c,?which?can?cause?the?machine?to?panic?when?

*?the?init?process?exits...?*/??

pid?=?vfork();??

if?(pid?==?0)?{?/*?child?*/??

reboot(magic);??

_exit(EXIT_SUCCESS);??

}??

while?(1)??

sleep(1);??

}??

看到了嗎？有一個(gè)reboot(magic)函數(shù)，對(duì)于vfork函數(shù)，請(qǐng)參考fork函數(shù)。這里不多說(shuō)了.... 我們現(xiàn)在來(lái)看看reboot.h文件，如下：

[cpp]?view plain?copy

print?

/*?

*?Definitions?related?to?the?reboot()?system?call,?

*?shared?between?init.c?and?halt.c.?

*/??

#include???

#ifndef?RB_HALT_SYSTEM??

#?if?defined(__linux__)??

#??define?RB_HALT_SYSTEM??0xcdef0123??

#??define?RB_ENABLE_CAD???0x89abcdef??

#??define?RB_DISABLE_CAD??0??

#??define?RB_POWER_OFF????0x4321fedc??

#??define?RB_AUTOBOOT?????0x01234567??

#?elif?defined(RB_HALT)??

#??define?RB_HALT_SYSTEM??RB_HALT??

#?endif??

#endif??

/*?Stop?system?and?switch?power?off?if?possible.??*/??

#ifndef?RB_POWER_OFF??

#?if?defined(RB_POWERDOWN)??

#??define?RB_POWER_OFF??RB_POWERDOWN??

#?elif?defined(__linux__)??

#??define?RB_POWER_OFF??0x4321fedc??

#?else??

#??warning?"poweroff?unsupported,?using?halt?as?fallback"??

#??define?RB_POWER_OFF??RB_HALT_SYSTEM??

#?endif??

#endif??

而在linux的內(nèi)核中的定義如下：

busybox和linux內(nèi)核中的REBOOT的定義值是一樣的。看到了沒(méi)有了。這個(gè)很重要的哦，否則busybox是無(wú)法調(diào)用linux內(nèi)核的reboot函數(shù)。

二：Linux內(nèi)核層的分析

Linux內(nèi)核是如何銜接busybox的reboot函數(shù)的呢，如下代碼：

[cpp]?view plain?copy

print?

/*?

*?Reboot?system?call:?for?obvious?reasons?only?root?may?call?it,?

*?and?even?root?needs?to?set?up?some?magic?numbers?in?the?registers?

*?so?that?some?mistake?won't?make?this?reboot?the?whole?machine.?

*?You?can?also?set?the?meaning?of?the?ctrl-alt-del-key?here.?

*?

*?reboot?doesn't?sync:?do?that?yourself?before?calling?this.?

*/??

SYSCALL_DEFINE4(reboot,?int,?magic1,?int,?magic2,?unsigned?int,?cmd,??

void?__user?*,?arg)??

{??

char?buffer[256];??

int?ret?=?0;??

/*?We?only?trust?the?superuser?with?rebooting?the?system.?*/??

if?(!capable(CAP_SYS_BOOT))??

return?-EPERM;??

/*?For?safety,?we?require?"magic"?arguments.?*/??

if?(magic1?!=?LINUX_REBOOT_MAGIC1?||??

(magic2?!=?LINUX_REBOOT_MAGIC2?&&??

magic2?!=?LINUX_REBOOT_MAGIC2A?&&??

magic2?!=?LINUX_REBOOT_MAGIC2B?&&??

magic2?!=?LINUX_REBOOT_MAGIC2C))??

return?-EINVAL;??

/*?Instead?of?trying?to?make?the?power_off?code?look?like?

*?halt?when?pm_power_off?is?not?set?do?it?the?easy?way.?

*/??

if?((cmd?==?LINUX_REBOOT_CMD_POWER_OFF)?&&?!pm_power_off)??

cmd?=?LINUX_REBOOT_CMD_HALT;??

lock_kernel();??

switch?(cmd)?{??

case?LINUX_REBOOT_CMD_RESTART:??

kernel_restart(NULL);?//這個(gè)就是重新啟動(dòng)Linx的命令??

break;??

case?LINUX_REBOOT_CMD_CAD_ON:??

C_A_D?=?1;??

break;??

case?LINUX_REBOOT_CMD_CAD_OFF:??

C_A_D?=?0;??

break;??

case?LINUX_REBOOT_CMD_HALT:??

kernel_halt();??

unlock_kernel();??

do_exit(0);??

panic("cannot?halt");??

case?LINUX_REBOOT_CMD_POWER_OFF:??

kernel_power_off();??

unlock_kernel();??

do_exit(0);??

break;??

case?LINUX_REBOOT_CMD_RESTART2:??

if?(strncpy_from_user(&buffer[0],?arg,?sizeof(buffer)?-?1)?

unlock_kernel();??

return?-EFAULT;??

}??

buffer[sizeof(buffer)?-?1]?=?'\0';??

kernel_restart(buffer);??

break;??

#ifdef?CONFIG_KEXEC??

case?LINUX_REBOOT_CMD_KEXEC:??

ret?=?kernel_kexec();??

break;??

#endif??

#ifdef?CONFIG_HIBERNATION??

case?LINUX_REBOOT_CMD_SW_SUSPEND:??

ret?=?hibernate();??

break;??

#endif??

default:??

ret?=?-EINVAL;??

break;??

}??

unlock_kernel();??

return?ret;??

}??

繼續(xù)跟蹤kernel_restart()函數(shù)，如下：

最終會(huì)調(diào)用一個(gè)machine_restart(cmd)函數(shù)，這個(gè)是跟具體的芯片有很大的關(guān)系的，我們進(jìn)一步的分析如下：

看到了嗎，最終是調(diào)用arch_reset來(lái)復(fù)位整個(gè)系統(tǒng)的。同時(shí)我們也看到了S3C2440的reset的函數(shù)如下：

在arm_pm_restart = s3c24xx_pm_restart()函數(shù)，最終也是調(diào)用arm_machine_restart(mod, cmd)來(lái)實(shí)現(xiàn)的。而在arm_machine_restart()函數(shù)中，最終也是調(diào)用arch_reset()函數(shù)來(lái)實(shí)現(xiàn)，而這個(gè)函數(shù)是在哪里呢。在S3C2440沒(méi)有看到arch_reset函數(shù)的實(shí)現(xiàn)，因此從S3C2410中找到了如下的代碼，請(qǐng)繼續(xù)看下面的代碼：

終于看到了arch_reset函數(shù)，最終是采用S3C2410或者S3C2440的WatchDog來(lái)實(shí)現(xiàn)reboot的命令的。大家可以想想，busybox的poweroff命令，是如何實(shí)現(xiàn)通過(guò)Linux系統(tǒng)關(guān)閉整個(gè)系統(tǒng)的電源呢，其實(shí)很簡(jiǎn)單，只需要實(shí)現(xiàn)下面的函數(shù)中的pm_power_off的回調(diào)函數(shù)即可。

我們可以通過(guò)一個(gè)GPIO來(lái)控制整個(gè)系統(tǒng)的電源，而通過(guò)上面的pm_power_off的回調(diào)函數(shù)來(lái)實(shí)現(xiàn)，只需要在pm_power_off函數(shù)對(duì)GPIO進(jìn)行操作就可以了。你看不是很簡(jiǎn)單嗎?

?