上一篇中解析了init进程的启动流程,其中最后创建了zygote进程,本篇我们来详细分析zygote进程启动的部分。
1 zygote进程概述
Zygote进程又名孵化器进程,正如其名,它主要用于孵化子进程。所有的Java应用程序进程及系统服务SystemServer进程都由Zygote进程通过Linux的fork()函数孵化出来的,这也就是为什么把它称为Zygote的原因,因为他就像一个孵化器,孵化出无数子进程,而native程序则由Init程序创建启动。Zygote进程最初的名字不是“zygote”而是“app_process”,这个名字是在Android.mk文件中定义的,Zgyote是Android中的第一个art虚拟机,他通过socket的方式与其他进程进行通信。这里的“其他进程”其实主要是系统进程——SystemServer。
2 Zygote进程解析
我们接着从上一篇app_main.cpp开始分析,源码如下(源码基于7.0):
frameworks/base/cmds/app_process/app_main.cpp
int main(int argc, char* const argv[])
{
if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) < 0) {
// Older kernels don't understand PR_SET_NO_NEW_PRIVS and return
// EINVAL. Don't die on such kernels.
if (errno != EINVAL) {
LOG_ALWAYS_FATAL("PR_SET_NO_NEW_PRIVS failed: %s", strerror(errno));
return 12;
}
}
AppRuntime runtime(argv[0], computeArgBlockSize(argc, argv));
// Process command line arguments
// ignore argv[0]
argc--;
argv++;
int i;
for (i = 0; i < argc; i++) {
if (argv[i][0] != '-') {
break;
}
if (argv[i][1] == '-' && argv[i][2] == 0) {
++i; // Skip --.
break;
}
runtime.addOption(strdup(argv[i]));
}
bool zygote = false;
bool startSystemServer = false;
bool application = false;
String8 niceName;
String8 className;
++i; // Skip unused "parent dir" argument.
while (i < argc) {
const char* arg = argv[i++];
if (strcmp(arg, "--zygote") == 0) {
zygote = true;
niceName = ZYGOTE_NICE_NAME;
} else if (strcmp(arg, "--start-system-server") == 0) {
startSystemServer = true;
} else if (strcmp(arg, "--application") == 0) {
application = true;
} else if (strncmp(arg, "--nice-name=", 12) == 0) {
niceName.setTo(arg + 12);
} else if (strncmp(arg, "--", 2) != 0) {
className.setTo(arg);
break;
} else {
--i;
break;
}
}
Vector<String8> args;
if (!className.isEmpty()) {
args.add(application ? String8("application") : String8("tool"));
runtime.setClassNameAndArgs(className, argc - i, argv + i);
} else {
// We're in zygote mode.
maybeCreateDalvikCache();
if (startSystemServer) {
// 1
args.add(String8("start-system-server"));
}
char prop[PROP_VALUE_MAX];
if (property_get(ABI_LIST_PROPERTY, prop, NULL) == 0) {
LOG_ALWAYS_FATAL("app_process: Unable to determine ABI list from property %s.",
ABI_LIST_PROPERTY);
return 11;
}
String8 abiFlag("--abi-list=");
abiFlag.append(prop);
args.add(abiFlag);
// In zygote mode, pass all remaining arguments to the zygote
// main() method.
for (; i < argc; ++i) {
args.add(String8(argv[i]));
}
}
if (!niceName.isEmpty(app_main)) {
runtime.setArgv0(niceName.string());
set_process_name(niceName.string());
}
if (zygote) {
// 2
runtime.start("com.android.internal.os.ZygoteInit", args, zygote);
} else if (className) {
runtime.start("com.android.internal.os.RuntimeInit", args, zygote);
} else {
fprintf(stderr, "Error: no class name or --zygote supplied.\n");
app_usage();
LOG_ALWAYS_FATAL("app_process: no class name or --zygote supplied.");
return 10;
}
}
上面注释1处将start-system-server
作为参数放入到了args中,接着在注释2处调用了runtime.start(),也就是AppRuntime.cpp的start, 因为AppRuntime.cpp中没有此方法,AndroidRuntime.cpp是AppRuntime.cpp的父类,最终调用的是AndroidRuntime.cpp中的start方法来启动zygote。
frameworks/base/core/jni/AndroidRuntime.cpp
void AndroidRuntime::start(const char* className, const Vector<String8>& options, bool zygote)
{
ALOGD(">>>>>> START %s uid %d <<<<<<\n",
className != NULL ? className : "(unknown)", getuid());
static const String8 startSystemServer("start-system-server");
...
/* start the virtual machine */
JniInvocation jni_invocation;
jni_invocation.Init(NULL);
JNIEnv* env;
//1 启动虚拟机
if (startVm(&mJavaVM, &env, zygote) != 0) {
return;
}
onVmCreated(env);
/*
* Register android functions.
*/
//2 注册jni
if (startReg(env) < 0) {
ALOGE("Unable to register all android natives\n");
return;
}
/*
* We want to call main() with a String array with arguments in it.
* At present we have two arguments, the class name and an option string.
* Create an array to hold them.
*/
jclass stringClass;
jobjectArray strArray;
jstring classNameStr;
stringClass = env->FindClass("java/lang/String");
assert(stringClass != NULL);
strArray = env->NewObjectArray(options.size() + 1, stringClass, NULL);
assert(strArray != NULL);
//className是com.android.internal.os.ZygoteInit
classNameStr = env->NewStringUTF(className);
assert(classNameStr != NULL);
env->SetObjectArrayElement(strArray, 0, classNameStr);
for (size_t i = 0; i < options.size(); ++i) {
jstring optionsStr = env->NewStringUTF(options.itemAt(i).string());
assert(optionsStr != NULL);
env->SetObjectArrayElement(strArray, i + 1, optionsStr);
}
/*
* Start VM. This thread becomes the main thread of the VM, and will
* not return until the VM exits.
*/
char* slashClassName = toSlashClassName(className);
jclass startClass = env->FindClass(slashClassName);
if (startClass == NULL) {
ALOGE("JavaVM unable to locate class '%s'\n", slashClassName);
/* keep going */
} else {
//3 找到ZygoteInit的main函数
jmethodID startMeth = env->GetStaticMethodID(startClass, "main",
"([Ljava/lang/String;)V");
if (startMeth == NULL) {
ALOGE("JavaVM unable to find main() in '%s'\n", className);
/* keep going */
} else {
//4 通过JNI调用ZygoteInit的main函数
env->CallStaticVoidMethod(startClass, startMeth, strArray);
#if 0
if (env->ExceptionCheck())
threadExitUncaughtException(env);
#endif
}
}
free(slashClassName);
ALOGD("Shutting down VM\n");
if (mJavaVM->DetachCurrentThread() != JNI_OK)
ALOGW("Warning: unable to detach main thread\n");
if (mJavaVM->DestroyJavaVM() != 0)
ALOGW("Warning: VM did not shut down cleanly\n");
}
上面注释1处startVm方法创建虚拟机,注释2处startRg来为DVM注册JNI, 注释3处的startClass是从app_main.cpp带过来的参数为com.android.internal.os.ZygoteInit
,注释4处通过jni调用java层的ZygoteInit.java的main函数。
其中注释2处的注册JNI就是为了后面native和java层互相调用,其中部分源码如下:
frameworks/base/core/jni/android_util_Binder.cpp
int register_android_os_Binder(JNIEnv* env)
{
//1
if (int_register_android_os_Binder(env) < 0)
return -1;
if (int_register_android_os_BinderInternal(env) < 0)
return -1;
if (int_register_android_os_BinderProxy(env) < 0)
return -1;
jclass clazz = FindClassOrDie(env, "android/util/Log");
gLogOffsets.mClass = MakeGlobalRefOrDie(env, clazz);
gLogOffsets.mLogE = GetStaticMethodIDOrDie(env, clazz, "e",
"(Ljava/lang/String;Ljava/lang/String;Ljava/lang/Throwable;)I");
clazz = FindClassOrDie(env, "android/os/ParcelFileDescriptor");
gParcelFileDescriptorOffsets.mClass = MakeGlobalRefOrDie(env, clazz);
gParcelFileDescriptorOffsets.mConstructor = GetMethodIDOrDie(env, clazz, "<init>",
"(Ljava/io/FileDescriptor;)V");
clazz = FindClassOrDie(env, "android/os/StrictMode");
gStrictModeCallbackOffsets.mClass = MakeGlobalRefOrDie(env, clazz);
gStrictModeCallbackOffsets.mCallback = GetStaticMethodIDOrDie(env, clazz,
"onBinderStrictModePolicyChange", "(I)V");
return 0;
}
我们以注释1处的int_register_android_os_Binder为例,可以看到java和native一一对应的关系(其余两个BinderInternal和BinderProxy同理查看):
static const JNINativeMethod gBinderMethods[] = {
/* name, signature, funcPtr */
{ "getCallingPid", "()I", (void*)android_os_Binder_getCallingPid },
{ "getCallingUid", "()I", (void*)android_os_Binder_getCallingUid },
{ "clearCallingIdentity", "()J", (void*)android_os_Binder_clearCallingIdentity },
{ "restoreCallingIdentity", "(J)V", (void*)android_os_Binder_restoreCallingIdentity },
{ "setThreadStrictModePolicy", "(I)V", (void*)android_os_Binder_setThreadStrictModePolicy },
{ "getThreadStrictModePolicy", "()I", (void*)android_os_Binder_getThreadStrictModePolicy },
{ "flushPendingCommands", "()V", (void*)android_os_Binder_flushPendingCommands },
{ "init", "()V", (void*)android_os_Binder_init },
{ "destroy", "()V", (void*)android_os_Binder_destroy },
{ "blockUntilThreadAvailable", "()V", (void*)android_os_Binder_blockUntilThreadAvailable }
};
const char* const kBinderPathName = "android/os/Binder";
static int int_register_android_os_Binder(JNIEnv* env)
{
jclass clazz = FindClassOrDie(env, kBinderPathName);
// 方便java和native互相调用
gBinderOffsets.mClass = MakeGlobalRefOrDie(env, clazz);
gBinderOffsets.mExecTransact = GetMethodIDOrDie(env, clazz, "execTransact", "(IJJI)Z");
gBinderOffsets.mObject = GetFieldIDOrDie(env, clazz, "mObject", "J");
return RegisterMethodsOrDie(
env, kBinderPathName,
gBinderMethods, NELEM(gBinderMethods));
}
3 Zygote Java层部分
frameworks/base/core/java/com/android/internal/os/ZygoteInit
public static void main(String argv[]) {
// Mark zygote start. This ensures that thread creation will throw
// an error.
ZygoteHooks.startZygoteNoThreadCreation();
try {
Trace.traceBegin(Trace.TRACE_TAG_DALVIK, "ZygoteInit");
RuntimeInit.enableDdms();
// Start profiling the zygote initialization.
SamplingProfilerIntegration.start();
boolean startSystemServer = false;
String socketName = "zygote";
String abiList = null;
for (int i = 1; i < argv.length; i++) {
if ("start-system-server".equals(argv[i])) {
//1
startSystemServer = true;
} else if (argv[i].startsWith(ABI_LIST_ARG)) {
abiList = argv[i].substring(ABI_LIST_ARG.length());
} else if (argv[i].startsWith(SOCKET_NAME_ARG)) {
socketName = argv[i].substring(SOCKET_NAME_ARG.length());
} else {
throw new RuntimeException("Unknown command line argument: " + argv[i]);
}
}
if (abiList == null) {
throw new RuntimeException("No ABI list supplied.");
}
/**
* 2 注册zygote进程的socket
*/
registerZygoteSocket(socketName);
Trace.traceBegin(Trace.TRACE_TAG_DALVIK, "ZygotePreload");
EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_START,
SystemClock.uptimeMillis());
// 3 预加载类库和资源
preload();
EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_END,
SystemClock.uptimeMillis());
Trace.traceEnd(Trace.TRACE_TAG_DALVIK);
...
// 4 此处为true, 启动systemServer进程
if (startSystemServer) {
startSystemServer(abiList, socketName);
}
Log.i(TAG, "Accepting command socket connections");
//5 循环等待客户端的创建进程请求
runSelectLoop(abiList);
closeServerSocket();
} catch (MethodAndArgsCaller caller) {
caller.run();
} catch (Throwable ex) {
Log.e(TAG, "Zygote died with exception", ex);
closeServerSocket();
throw ex;
}
}
上面的流程如下:
- 注释1处start-system-server参数就是在上面app_main.cpp中传递的,所以这里为true
- 注释2注册zygote进程的socket,便于systemserver进程的AMS(ActivityManagerService)和zygote进程通信,用来创建新的应用程序进程。
- 注释3处preload方法会主要调用preloadClasses()和preloadResources()加载类和资源。
- 注释4处启动systemserver进程。
- 注释5处不断的while循环用来等待AMS发送创建应用程序进程的请求。
registerZygoteSocket解析
private static void registerZygoteSocket(String socketName) {
if (sServerSocket == null) {
int fileDesc;
//得到全路径
final String fullSocketName = ANDROID_SOCKET_PREFIX + socketName;
try {
String env = System.getenv(fullSocketName);
fileDesc = Integer.parseInt(env);
} catch (RuntimeException ex) {
throw new RuntimeException(fullSocketName + " unset or invalid", ex);
}
try {
FileDescriptor fd = new FileDescriptor();
fd.setInt$(fileDesc);
sServerSocket = new LocalServerSocket(fd);
} catch (IOException ex) {
throw new RuntimeException(
"Error binding to local socket '" + fileDesc + "'", ex);
}
}
}
registerZygoteSocket方法用来创建LocalServerSocket对象,针对与systemserver进程来说是服务端,等到zygote将systemserver进程启动结束后,就会在这里的socket上等待AMS发送的请求zygote进程创建新的应用程序进程的请求。
startSystemServer解析
private static boolean startSystemServer(String abiList, String socketName)
throws MethodAndArgsCaller, RuntimeException {
long capabilities = posixCapabilitiesAsBits(
OsConstants.CAP_IPC_LOCK,
OsConstants.CAP_KILL,
OsConstants.CAP_NET_ADMIN,
OsConstants.CAP_NET_BIND_SERVICE,
OsConstants.CAP_NET_BROADCAST,
OsConstants.CAP_NET_RAW,
OsConstants.CAP_SYS_MODULE,
OsConstants.CAP_SYS_NICE,
OsConstants.CAP_SYS_RESOURCE,
OsConstants.CAP_SYS_TIME,
OsConstants.CAP_SYS_TTY_CONFIG
);
/* Containers run without this capability, so avoid setting it in that case */
if (!SystemProperties.getBoolean(PROPERTY_RUNNING_IN_CONTAINER, false)) {
capabilities |= posixCapabilitiesAsBits(OsConstants.CAP_BLOCK_SUSPEND);
}
// 1
String args[] = {
"--setuid=1000",
"--setgid=1000",
"--setgroups=1001,1002,1003,1004,1005,1006,1007,1008,1009,1010,1018,1021,1032,3001,3002,3003,3006,3007,3009,3010",
"--capabilities=" + capabilities + "," + capabilities,
"--nice-name=system_server",
"--runtime-args",
"com.android.server.SystemServer",
};
ZygoteConnection.Arguments parsedArgs = null;
int pid;
try {
parsedArgs = new ZygoteConnection.Arguments(args);
ZygoteConnection.applyDebuggerSystemProperty(parsedArgs);
ZygoteConnection.applyInvokeWithSystemProperty(parsedArgs);
// 2
pid = Zygote.forkSystemServer(
parsedArgs.uid, parsedArgs.gid,
parsedArgs.gids,
parsedArgs.debugFlags,
null,
parsedArgs.permittedCapabilities,
parsedArgs.effectiveCapabilities);
} catch (IllegalArgumentException ex) {
throw new RuntimeException(ex);
}
// 3
if (pid == 0) {
if (hasSecondZygote(abiList)) {
waitForSecondaryZygote(socketName);
}
// 4
handleSystemServerProcess(parsedArgs);
}
return true;
}
在注释1处的args参数中,看到systemserver进程的uid和gid都是1000,并且进程名字为system_server
,类名为com.android.server.SystemServer
,在注释2处通过Zygote.forkSystemServer来创建子进程,返回一个pid,在注释3处根据返回的pid来执行逻辑,如果pid==0, 说明逻辑运行在子进程中,接着执行注释4处的handleSystemServerProcess来启动system_server进程。
runSelectLoop解析
private static void runSelectLoop(String abiList) throws MethodAndArgsCaller {
ArrayList<FileDescriptor> fds = new ArrayList<FileDescriptor>();
ArrayList<ZygoteConnection> peers = new ArrayList<ZygoteConnection>();
//1
fds.add(sServerSocket.getFileDescriptor());
peers.add(null);
while (true) {
StructPollfd[] pollFds = new StructPollfd[fds.size()];
for (int i = 0; i < pollFds.length; ++i) {//2
pollFds[i] = new StructPollfd();
pollFds[i].fd = fds.get(i);
pollFds[i].events = (short) POLLIN;
}
try {
Os.poll(pollFds, -1);
} catch (ErrnoException ex) {
throw new RuntimeException("poll failed", ex);
}
for (int i = pollFds.length - 1; i >= 0; --i) {//3
if ((pollFds[i].revents & POLLIN) == 0) {
continue;
}
if (i == 0) {//4
ZygoteConnection newPeer = acceptCommandPeer(abiList);
peers.add(newPeer);
fds.add(newPeer.getFileDesciptor());
} else {
boolean done = peers.get(i).runOnce();//5
if (done) {
peers.remove(i);
fds.remove(i);
}
}
}
}
}
以上代码主要逻辑如下:
- 注释1处的sServerSocket是registerZygoteSocket中创建的,调用sServerSocket.getFileDescriptor()用来获得该Socket的fd字段的值并添加到fd列表fds中,接下来while无限循环等待AMS发送请求创建新的应用程序进程。
- 注释2处将fds中存储的FileDescriptor转存到pollFds中。
- 注释3处对pollFds进行遍历。
- 注释4处i==0说明zygote进程和system_server进程的AMS建立了连接,通过acceptCommandPeer返回ZygoteConnection,然后将相关对象分别添加到peers和fds中。
- 注释5处如果i>0的话,说明ActivityManagerService向Zygote进程发送了一个创建应用进程的请求,然后调用ZygoteConnection的runOnce函数来创建一个新的应用程序进程。并在成功创建后将这个连接从Socket连接列表peers和fd列表fds中清除。
4 Zygote进程启动总结
- 通过app_main.cpp最终调用到AndroidRuntime.cpp的start方法,启动了zygote进程。
- 通过AndroidRuntime.cpp的startVm和startReg创建虚拟机和注册JNI。
- 通过JNI调用到ZygoteInit的main函数,进入到Zygote的Java框架层。
- 调用registerZygoteSocket来注册服务端的Socket。
- 调用startSystemServer用来启动system_server进程。
- 调用runSelectLoop无限循环用来接受system_server进程中ActivityManagerService发送的创建应用程序进程的请求。