本篇介绍系统启动的第二个阶段,从Kernel到Init进程,分析的源码版本为Android11。
从kernel启动init进程,走到init的main函数,未传入参数的情况下,会走FirstStageMain的流程。
int main(int argc, char** argv) {
#if __has_feature(address_sanitizer)
__asan_set_error_report_callback(AsanReportCallback);
#endif
if (!strcmp(basename(argv[0]), "ueventd")) {
return ueventd_main(argc, argv);
}
if (argc > 1) {
if (!strcmp(argv[1], "subcontext")) {
android::base::InitLogging(argv, &android::base::KernelLogger);
const BuiltinFunctionMap& function_map = GetBuiltinFunctionMap();
return SubcontextMain(argc, argv, &function_map);
}
if (!strcmp(argv[1], "selinux_setup")) {
return SetupSelinux(argv);
}
if (!strcmp(argv[1], "second_stage")) {
return SecondStageMain(argc, argv);
}
}
return FirstStageMain(argc, argv);
}
1. 这个main函数的设计还挺有意思的,根据传入的不同参数来做不同的跳转。init的main只是一个入口,有可能下一步就到ueventd了,也可能去做selinux_setup了。从kernel启动进来的时候是不带其他argv的,所以前面的条件都没命中,就直接走到了FirstStageMain。
int FirstStageMain(int argc, char** argv) {
if (REBOOT_BOOTLOADER_ON_PANIC) {
InstallRebootSignalHandlers();
}
boot_clock::time_point start_time = boot_clock::now();
std::vector<std::pair<std::string, int>> errors;
//2.通过这个宏定义来执行命令并搜集错误,开始做第一阶段的初始化动作
#define CHECKCALL(x) \
if ((x) != 0) errors.emplace_back(#x " failed", errno);
// Clear the umask.
umask(0);
CHECKCALL(clearenv());
CHECKCALL(setenv("PATH", _PATH_DEFPATH, 1));
// Get the basic filesystem setup we need put together in the initramdisk
// on / and then we'll let the rc file figure out the rest.
CHECKCALL(mount("tmpfs", "/dev", "tmpfs", MS_NOSUID, "mode=0755"));
CHECKCALL(mkdir("/dev/pts", 0755));
CHECKCALL(mkdir("/dev/socket", 0755));
CHECKCALL(mount("devpts", "/dev/pts", "devpts", 0, NULL));
#define MAKE_STR(x) __STRING(x)
CHECKCALL(mount("proc", "/proc", "proc", 0, "hidepid=2,gid=" MAKE_STR(AID_READPROC)));
#undef MAKE_STR
// Don't expose the raw commandline to unprivileged processes.
CHECKCALL(chmod("/proc/cmdline", 0440));
std::string cmdline;
android::base::ReadFileToString("/proc/cmdline", &cmdline);
gid_t groups[] = {AID_READPROC};
CHECKCALL(setgroups(arraysize(groups), groups));
CHECKCALL(mount("sysfs", "/sys", "sysfs", 0, NULL));
CHECKCALL(mount("selinuxfs", "/sys/fs/selinux", "selinuxfs", 0, NULL));
CHECKCALL(mknod("/dev/kmsg", S_IFCHR | 0600, makedev(1, 11)));
if constexpr (WORLD_WRITABLE_KMSG) {
CHECKCALL(mknod("/dev/kmsg_debug", S_IFCHR | 0622, makedev(1, 11)));
}
CHECKCALL(mknod("/dev/random", S_IFCHR | 0666, makedev(1, 8)));
CHECKCALL(mknod("/dev/urandom", S_IFCHR | 0666, makedev(1, 9)));
// This is needed for log wrapper, which gets called before ueventd runs.
CHECKCALL(mknod("/dev/ptmx", S_IFCHR | 0666, makedev(5, 2)));
CHECKCALL(mknod("/dev/null", S_IFCHR | 0666, makedev(1, 3)));
// These below mounts are done in first stage init so that first stage mount can mount
// subdirectories of /mnt/{vendor,product}/. Other mounts, not required by first stage mount,
// should be done in rc files.
// Mount staging areas for devices managed by vold
// See storage config details at http://source.android.com/devices/storage/
CHECKCALL(mount("tmpfs", "/mnt", "tmpfs", MS_NOEXEC | MS_NOSUID | MS_NODEV,
"mode=0755,uid=0,gid=1000"));
// /mnt/vendor is used to mount vendor-specific partitions that can not be
// part of the vendor partition, e.g. because they are mounted read-write.
CHECKCALL(mkdir("/mnt/vendor", 0755));
// /mnt/product is used to mount product-specific partitions that can not be
// part of the product partition, e.g. because they are mounted read-write.
CHECKCALL(mkdir("/mnt/product", 0755));
// /debug_ramdisk is used to preserve additional files from the debug ramdisk
CHECKCALL(mount("tmpfs", "/debug_ramdisk", "tmpfs", MS_NOEXEC | MS_NOSUID | MS_NODEV,
"mode=0755,uid=0,gid=0"));
#undef CHECKCALL
// 重定向标准输入输出和开启kernel日志记录
SetStdioToDevNull(argv);
// Now that tmpfs is mounted on /dev and we have /dev/kmsg, we can actually
// talk to the outside world...
InitKernelLogging(argv);
if (!errors.empty()) {
for (const auto& [error_string, error_errno] : errors) {
LOG(ERROR) << error_string << " " << strerror(error_errno);
}
LOG(FATAL) << "Init encountered errors starting first stage, aborting";
}
LOG(INFO) << "init first stage started!";
auto old_root_dir = std::unique_ptr<DIR, decltype(&closedir)>{opendir("/"), closedir};
if (!old_root_dir) {
PLOG(ERROR) << "Could not opendir(\"/\"), not freeing ramdisk";
}
struct stat old_root_info;
if (stat("/", &old_root_info) != 0) {
PLOG(ERROR) << "Could not stat(\"/\"), not freeing ramdisk";
old_root_dir.reset();
}
auto want_console = ALLOW_FIRST_STAGE_CONSOLE ? FirstStageConsole(cmdline) : 0;
if (!LoadKernelModules(IsRecoveryMode() && !ForceNormalBoot(cmdline), want_console)) {
if (want_console != FirstStageConsoleParam::DISABLED) {
LOG(ERROR) << "Failed to load kernel modules, starting console";
} else {
LOG(FATAL) << "Failed to load kernel modules";
}
}
if (want_console == FirstStageConsoleParam::CONSOLE_ON_FAILURE) {
StartConsole();
}
if (ForceNormalBoot(cmdline)) {
mkdir("/first_stage_ramdisk", 0755);
// SwitchRoot() must be called with a mount point as the target, so we bind mount the
// target directory to itself here.
if (mount("/first_stage_ramdisk", "/first_stage_ramdisk", nullptr, MS_BIND, nullptr) != 0) {
LOG(FATAL) << "Could not bind mount /first_stage_ramdisk to itself";
}
SwitchRoot("/first_stage_ramdisk");
}
// If this file is present, the second-stage init will use a userdebug sepolicy
// and load adb_debug.prop to allow adb root, if the device is unlocked.
if (access("/force_debuggable", F_OK) == 0) {
std::error_code ec; // to invoke the overloaded copy_file() that won't throw.
if (!fs::copy_file("/adb_debug.prop", kDebugRamdiskProp, ec) ||
!fs::copy_file("/userdebug_plat_sepolicy.cil", kDebugRamdiskSEPolicy, ec)) {
LOG(ERROR) << "Failed to setup debug ramdisk";
} else {
// setenv for second-stage init to read above kDebugRamdisk* files.
setenv("INIT_FORCE_DEBUGGABLE", "true", 1);
}
}
if (!DoFirstStageMount()) {
LOG(FATAL) << "Failed to mount required partitions early ...";
}
struct stat new_root_info;
if (stat("/", &new_root_info) != 0) {
PLOG(ERROR) << "Could not stat(\"/\"), not freeing ramdisk";
old_root_dir.reset();
}
if (old_root_dir && old_root_info.st_dev != new_root_info.st_dev) {
FreeRamdisk(old_root_dir.get(), old_root_info.st_dev);
}
SetInitAvbVersionInRecovery();
setenv(kEnvFirstStageStartedAt, std::to_string(start_time.time_since_epoch().count()).c_str(),
1);
//3.在做完第一阶段初始化之后,会再去调用init,然后传入selinux_setup的参数
const char* path = "/system/bin/init";
const char* args[] = {path, "selinux_setup", nullptr};
auto fd = open("/dev/kmsg", O_WRONLY | O_CLOEXEC);
dup2(fd, STDOUT_FILENO);
dup2(fd, STDERR_FILENO);
close(fd);
execv(path, const_cast<char**>(args));
// execv() only returns if an error happened, in which case we
// panic and never fall through this conditional.
PLOG(FATAL) << "execv(\"" << path << "\") failed";
return 1;
}
2. 检查初始化需要使用的一些分区挂载情况,初始化printf等标准输入输出的重定向,初始化kernel log,AVB等,就会转入selinux的初始化流程。
3. 这个跳转的方式是继续调用system/bin/init,然后传入了“selinux_setup”,接着流程就会回到main函数,然后通过参数判断,走到SetupSelinux函数中。
int SetupSelinux(char** argv) {
SetStdioToDevNull(argv);
InitKernelLogging(argv);
if (REBOOT_BOOTLOADER_ON_PANIC) {
InstallRebootSignalHandlers();
}
boot_clock::time_point start_time = boot_clock::now();
MountMissingSystemPartitions();
// Set up SELinux, loading the SELinux policy.
SelinuxSetupKernelLogging();
SelinuxInitialize();
// We're in the kernel domain and want to transition to the init domain. File systems that
// store SELabels in their xattrs, such as ext4 do not need an explicit restorecon here,
// but other file systems do. In particular, this is needed for ramdisks such as the
// recovery image for A/B devices.
if (selinux_android_restorecon("/system/bin/init", 0) == -1) {
PLOG(FATAL) << "restorecon failed of /system/bin/init failed";
}
setenv(kEnvSelinuxStartedAt, std::to_string(start_time.time_since_epoch().count()).c_str(), 1);
//4.做第二阶段初始化
const char* path = "/system/bin/init";
const char* args[] = {path, "second_stage", nullptr};
execv(path, const_cast<char**>(args));
// execv() only returns if an error happened, in which case we
// panic and never return from this function.
PLOG(FATAL) << "execv(\"" << path << "\") failed";
return 1;
}
4. 在SeLinux初始化结束之后,又构建了init的second_stage参数,然后启动了/system/bin/init,进入到第二阶段的初始化流程
int SecondStageMain(int argc, char** argv) {
if (REBOOT_BOOTLOADER_ON_PANIC) {
InstallRebootSignalHandlers();
}
boot_clock::time_point start_time = boot_clock::now();
trigger_shutdown = [](const std::string& command) { shutdown_state.TriggerShutdown(command); };
SetStdioToDevNull(argv);
InitKernelLogging(argv);
LOG(INFO) << "init second stage started!";
// Init should not crash because of a dependence on any other process, therefore we ignore
// SIGPIPE and handle EPIPE at the call site directly. Note that setting a signal to SIG_IGN
// is inherited across exec, but custom signal handlers are not. Since we do not want to
// ignore SIGPIPE for child processes, we set a no-op function for the signal handler instead.
{
struct sigaction action = {.sa_flags = SA_RESTART};
action.sa_handler = [](int) {};
sigaction(SIGPIPE, &action, nullptr);
}
// Set init and its forked children's oom_adj.
if (auto result =
WriteFile("/proc/1/oom_score_adj", StringPrintf("%d", DEFAULT_OOM_SCORE_ADJUST));
!result.ok()) {
LOG(ERROR) << "Unable to write " << DEFAULT_OOM_SCORE_ADJUST
<< " to /proc/1/oom_score_adj: " << result.error();
}
// Set up a session keyring that all processes will have access to. It
// will hold things like FBE encryption keys. No process should override
// its session keyring.
keyctl_get_keyring_ID(KEY_SPEC_SESSION_KEYRING, 1);
// Indicate that booting is in progress to background fw loaders, etc.
close(open("/dev/.booting", O_WRONLY | O_CREAT | O_CLOEXEC, 0000));
// See if need to load debug props to allow adb root, when the device is unlocked.
const char* force_debuggable_env = getenv("INIT_FORCE_DEBUGGABLE");
bool load_debug_prop = false;
if (force_debuggable_env && AvbHandle::IsDeviceUnlocked()) {
load_debug_prop = "true"s == force_debuggable_env;
}
unsetenv("INIT_FORCE_DEBUGGABLE");
// Umount the debug ramdisk so property service doesn't read .prop files from there, when it
// is not meant to.
if (!load_debug_prop) {
UmountDebugRamdisk();
}
//初始化属性服务
PropertyInit();
// Umount the debug ramdisk after property service has read the .prop files when it means to.
if (load_debug_prop) {
UmountDebugRamdisk();
}
// Mount extra filesystems required during second stage init
MountExtraFilesystems();
// Now set up SELinux for second stage.
SelinuxSetupKernelLogging();
SelabelInitialize();
SelinuxRestoreContext();
Epoll epoll;
if (auto result = epoll.Open(); !result.ok()) {
PLOG(FATAL) << result.error();
}
InstallSignalFdHandler(&epoll);
InstallInitNotifier(&epoll);
StartPropertyService(&property_fd);
// 记录init阶段的启动时间
// Make the time that init stages started available for bootstat to log.
RecordStageBoottimes(start_time);
// Set libavb version for Framework-only OTA match in Treble build.
if (const char* avb_version = getenv("INIT_AVB_VERSION"); avb_version != nullptr) {
SetProperty("ro.boot.avb_version", avb_version);
}
unsetenv("INIT_AVB_VERSION");
fs_mgr_vendor_overlay_mount_all();
export_oem_lock_status();
MountHandler mount_handler(&epoll);
SetUsbController();
const BuiltinFunctionMap& function_map = GetBuiltinFunctionMap();
Action::set_function_map(&function_map);
if (!SetupMountNamespaces()) {
PLOG(FATAL) << "SetupMountNamespaces failed";
}
InitializeSubcontext();
// 5.开始加载initrc中的Action
ActionManager& am = ActionManager::GetInstance();
ServiceList& sm = ServiceList::GetInstance();
LoadBootScripts(am, sm);
// Turning this on and letting the INFO logging be discarded adds 0.2s to
// Nexus 9 boot time, so it's disabled by default.
if (false) DumpState();
// Make the GSI status available before scripts start running.
auto is_running = android::gsi::IsGsiRunning() ? "1" : "0";
SetProperty(gsi::kGsiBootedProp, is_running);
auto is_installed = android::gsi::IsGsiInstalled() ? "1" : "0";
SetProperty(gsi::kGsiInstalledProp, is_installed);
am.QueueBuiltinAction(SetupCgroupsAction, "SetupCgroups");
am.QueueBuiltinAction(SetKptrRestrictAction, "SetKptrRestrict");
am.QueueBuiltinAction(TestPerfEventSelinuxAction, "TestPerfEventSelinux");
am.QueueEventTrigger("early-init");
// Queue an action that waits for coldboot done so we know ueventd has set up all of /dev...
am.QueueBuiltinAction(wait_for_coldboot_done_action, "wait_for_coldboot_done");
// ... so that we can start queuing up actions that require stuff from /dev.
am.QueueBuiltinAction(MixHwrngIntoLinuxRngAction, "MixHwrngIntoLinuxRng");
am.QueueBuiltinAction(SetMmapRndBitsAction, "SetMmapRndBits");
Keychords keychords;
am.QueueBuiltinAction(
[&epoll, &keychords](const BuiltinArguments& args) -> Result<void> {
for (const auto& svc : ServiceList::GetInstance()) {
keychords.Register(svc->keycodes());
}
keychords.Start(&epoll, HandleKeychord);
return {};
},
"KeychordInit");
// 6.触发队列中的Action
// Trigger all the boot actions to get us started.
am.QueueEventTrigger("init");
// Repeat mix_hwrng_into_linux_rng in case /dev/hw_random or /dev/random
// wasn't ready immediately after wait_for_coldboot_done
am.QueueBuiltinAction(MixHwrngIntoLinuxRngAction, "MixHwrngIntoLinuxRng");
// Don't mount filesystems or start core system services in charger mode.
std::string bootmode = GetProperty("ro.bootmode", "");
if (bootmode == "charger") {
am.QueueEventTrigger("charger");
} else {
am.QueueEventTrigger("late-init");
}
// Run all property triggers based on current state of the properties.
am.QueueBuiltinAction(queue_property_triggers_action, "queue_property_triggers");
// 7.进入死循环等待一些指令的到来
while (true) {
// By default, sleep until something happens.
auto epoll_timeout = std::optional<std::chrono::milliseconds>{};
auto shutdown_command = shutdown_state.CheckShutdown();
if (shutdown_command) {
HandlePowerctlMessage(*shutdown_command);
}
if (!(prop_waiter_state.MightBeWaiting() || Service::is_exec_service_running())) {
am.ExecuteOneCommand();
}
if (!IsShuttingDown()) {
auto next_process_action_time = HandleProcessActions();
// If there's a process that needs restarting, wake up in time for that.
if (next_process_action_time) {
epoll_timeout = std::chrono::ceil<std::chrono::milliseconds>(
*next_process_action_time - boot_clock::now());
if (*epoll_timeout < 0ms) epoll_timeout = 0ms;
}
}
if (!(prop_waiter_state.MightBeWaiting() || Service::is_exec_service_running())) {
// If there's more work to do, wake up again immediately.
if (am.HasMoreCommands()) epoll_timeout = 0ms;
}
auto pending_functions = epoll.Wait(epoll_timeout);
if (!pending_functions.ok()) {
LOG(ERROR) << pending_functions.error();
} else if (!pending_functions->empty()) {
// We always reap children before responding to the other pending functions. This is to
// prevent a race where other daemons see that a service has exited and ask init to
// start it again via ctl.start before init has reaped it.
ReapAnyOutstandingChildren();
for (const auto& function : *pending_functions) {
(*function)();
}
}
if (!IsShuttingDown()) {
HandleControlMessages();
SetUsbController();
}
}
return 0;
}
第二个阶段的初始化主要做的事情也比较单纯:包括一些初始化动作,然后是解析initrc文件中的Action并执行,最后就进入死循环等待一些指令到来之后的处理。对应代码中的位置为
5. 加载initrc中的action、service、trigger等
6. 触发队列中的action
7. 进入死循环等待下一步指令
那么init是如何解析和执行initrc中的指令的?
initrc中的Action或者Service是通过Parser.cpp来解析,然后加入到Queue中,在这个阶段中还会加入一些内建的Action。
都添加完之后会去触发early- init,init,charger,late-init这些阶段的指令。
static void LoadBootScripts(ActionManager& action_manager, ServiceList& service_list) {
Parser parser = CreateParser(action_manager, service_list);
std::string bootscript = GetProperty("ro.boot.init_rc", "");//这个读出来是空的
if (bootscript.empty()) {
//通过ParseConfig来解析initrc文件,如果是目录会递归解析
parser.ParseConfig("/system/etc/init/hw/init.rc");
if (!parser.ParseConfig("/system/etc/init")) {
late_import_paths.emplace_back("/system/etc/init");
}
// late_import is available only in Q and earlier release. As we don't
// have system_ext in those versions, skip late_import for system_ext.
parser.ParseConfig("/system_ext/etc/init");
if (!parser.ParseConfig("/product/etc/init")) {
late_import_paths.emplace_back("/product/etc/init");
}
if (!parser.ParseConfig("/odm/etc/init")) {
late_import_paths.emplace_back("/odm/etc/init");
}
if (!parser.ParseConfig("/vendor/etc/init")) {
late_import_paths.emplace_back("/vendor/etc/init");
}
} else {
parser.ParseConfig(bootscript);
}
}