Zygote进程启动过程

Zygpte 进程的启动脚本

Zygote 进程是在 init 进程启动时创建的，Zygote 的启动脚本在 system/core/rootdir 目录下，这里不详细说 init 进程启动过程了，它可以简单描述为解析 init.rc ，启动相应的脚本

init.zygote32.rc 代码

#zygote配置文件相关init.rc
service zygote /system/bin/app_process -Xzygote /system/bin --zygote --start-system-server
    class main
    priority -20
    user root
    group root readproc
    socket zygote stream 660 root system
    onrestart write /sys/android_power/request_state wake
    onrestart write /sys/power/state on
    onrestart restart audioserver
    onrestart restart cameraserver
    onrestart restart media
    onrestart restart netd
    onrestart restart wificond
    writepid /dev/cpuset/foreground/tasks

init 进程会调用 app_main.cpp 的 main 函数，frameworks\base\cmds\app_process\app_main.cpp

int main(int argc, char* const argv[])
{
    //...
    AppRuntime runtime(argv[0], computeArgBlockSize(argc, argv));

    // Parse runtime arguments.  Stop at first unrecognized option.
    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++];
        //判断参数 arg 是否包含了 --zygote
        if (strcmp(arg, "--zygote") == 0) {
            //如果当前运行在 Zygote 进程中，则将 zygote设置为true
            zygote = true;
            niceName = ZYGOTE_NICE_NAME;
        } else if (strcmp(arg, "--start-system-server") == 0) {
            //如果包含 --start-system-server 则将 startSystemServer 设置为true
            startSystemServer = true;
        //...
            --i;
            break;
        }
    }
    //...
    if (zygote) {
        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.");
    }
}

这段代码很简单，先对参数进行判断，之后由参数调用相对应的函数，这里 zygote 为 true，调到 runtime#start 方法

frameworks/base/core/jni/AndroidRuntime.cpp

void AndroidRuntime::start(const char* className, const Vector<String8>& options, bool zygote)
{
//...
    /* start the virtual machine */
    JniInvocation jni_invocation;
    jni_invocation.Init(NULL);
    JNIEnv* env;
    //创建 Java 虚拟机
    if (startVm(&mJavaVM, &env, zygote) != 0) {
        return;
    }
    onVmCreated(env);

    /*
     * Register android functions.
     */
     //为 Java 虚拟机注册 JNI 方法
    if (startReg(env) < 0) {
        ALOGE("Unable to register all android natives\n");
        return;
    }
//...
    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 为 com.android.internal.os.ZygoteInit
    classNameStr = env->NewStringUTF(className);
    assert(classNameStr != NULL);
    env->SetObjectArrayElement(strArray, 0, classNameStr);
     //将 className 的 “.” 替换为 “/”  com/android/internal/os/ZygoteInit
    char* slashClassName = toSlashClassName(className != NULL ? className : "");
    //找到这个类
    jclass startClass = env->FindClass(slashClassName);
    if (startClass == NULL) {
        ALOGE("JavaVM unable to locate class '%s'\n", slashClassName);
        /* keep going */
    } else {
        //找到 main 方法
        jmethodID startMeth = env->GetStaticMethodID(startClass, "main",
            "([Ljava/lang/String;)V");
        if (startMeth == NULL) {
          
        } else {
            env->CallStaticVoidMethod(startClass, startMeth, strArray);

#if 0
            if (env->ExceptionCheck())
                threadExitUncaughtException(env);
#endif
        }
    }

AndroidRuntime#start 函数调用 ZygoteInit 中 main 方法。这里 CallStaticVoidMethod 方法是通过 JNI 调用 Java 中的方法。

frameworks/base/core/java/com/android/internal/os/ZygoteInit.java 

    public static void main(String argv[]) {
        //创建 ZygoteServer
        ZygoteServer zygoteServer = new ZygoteServer();
//...

        final Runnable caller;
        try {
//...
            boolean startSystemServer = false;
            String socketName = "zygote";
            String abiList = null;
            boolean enableLazyPreload = false;
//...
            //创建一个 Server 端的 Socket，socketName 的值为 "zygote"
            zygoteServer.registerServerSocket(socketName);
            // In some configurations, we avoid preloading resources and classes eagerly.
            // In such cases, we will preload things prior to our first fork.
            if (!enableLazyPreload) {
                bootTimingsTraceLog.traceBegin("ZygotePreload");
                EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_START,
                    SystemClock.uptimeMillis());
                //预加载资源和类
                preload(bootTimingsTraceLog);
                EventLog.writeEvent(LOG_BOOT_PROGRESS_PRELOAD_END,
                    SystemClock.uptimeMillis());
                bootTimingsTraceLog.traceEnd(); // ZygotePreload
            } else {
                Zygote.resetNicePriority();
            }

//...
            if (startSystemServer) {
                //fork SystenService进程
                Runnable r = forkSystemServer(abiList, socketName, zygoteServer);

                // {@code r == null} in the parent (zygote) process, and {@code r != null} in the
                // child (system_server) process.
                if (r != null) {
                    //启动 SystemService 进程
                    r.run();
                    return;
                }
            }
            //等待 AMS 请求
            caller = zygoteServer.runSelectLoop(abiList);
        } catch (Throwable ex) {
            Log.e(TAG, "System zygote died with exception", ex);
            throw ex;
        } finally {
            zygoteServer.closeServerSocket();
        }

        if (caller != null) {
            caller.run();
        }
    }

ZygoteInit#main 函数主要做了4件事情：创建一个 Server 端的 Socket，预加载类和资源，启动 SystemServer进程，等待 AMS 请求创建新的应用程序。

registerServerSocket

    void registerServerSocket(String socketName) {
        if (mServerSocket == null) {
            int fileDesc;
            //拼接 Socket 的名称
            final String fullSocketName = ANDROID_SOCKET_PREFIX + socketName;
            try {
                //得到 Socket 的环境变量
                String env = System.getenv(fullSocketName);
                //将 Socket 环境变量的值转换为文件描述符的参数
                fileDesc = Integer.parseInt(env);
            } catch (RuntimeException ex) {
                throw new RuntimeException(fullSocketName + " unset or invalid", ex);
            }

            try {
                //创建文件描述符
                FileDescriptor fd = new FileDescriptor();
                fd.setInt$(fileDesc);
                //创建 Socket 服务端
                mServerSocket = new LocalServerSocket(fd);
            } catch (IOException ex) {
                throw new RuntimeException(
                        "Error binding to local socket '" + fileDesc + "'", ex);
            }
        }
    }

创建 LocalServerSocket，LocalServerSocket 的构造函数中创建 LocalSocketImpl 实现类，调用 create 方法

    public void create(int sockType) throws IOException {
//...
        try {
            fd = Os.socket(OsConstants.AF_UNIX, osType, 0);
            mFdCreatedInternally = true;
        } catch (ErrnoException e) {
            e.rethrowAsIOException();
        }
    }

这里用到了 linux 中 socket 编程。

preload

    static void preload(TimingsTraceLog bootTimingsTraceLog) {
        bootTimingsTraceLog.traceBegin("PreloadClasses");
        //预加载 Class
        preloadClasses();
        //预加载资源
        preloadResources();
        //OpenGL
        preloadOpenGL();
        //三方库
        preloadSharedLibraries();
        //文本资源
        preloadTextResources();

        sPreloadComplete = true;
    }

由名字可以看出预加载的资源有大概情况。

forkSystemServer

    private static Runnable forkSystemServer(String abiList, String socketName,
            ZygoteServer zygoteServer) {
//...
        /* 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);
        }
        //创建 aargs 数组，保存启动参数
        String args[] = {
            "--setuid=1000",
            "--setgid=1000",
            "--setgroups=1001,1002,1003,1004,1005,1006,1007,1008,1009,1010,1018,1021,1023,1032,3001,3002,3003,3006,3007,3009,3010",
            "--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);

            pid = Zygote.forkSystemServer(
                    parsedArgs.uid, parsedArgs.gid,
                    parsedArgs.gids,
                    parsedArgs.debugFlags,
                    null,
                    parsedArgs.permittedCapabilities,
                    parsedArgs.effectiveCapabilities);
        } catch (IllegalArgumentException ex) {
            throw new RuntimeException(ex);
        }

        if (pid == 0) {
            if (hasSecondZygote(abiList)) {
                waitForSecondaryZygote(socketName);
            }

            zygoteServer.closeServerSocket();
            return handleSystemServerProcess(parsedArgs);
        }

        return null;
    }

先准备启动参数 args 数组，之后将 args 封装成 ZygoteConnection.Arguments 对象，最后调用 Zygote#forkSystemServer 创建子进程。

    public static int forkSystemServer(int uid, int gid, int[] gids, int debugFlags,
            int[][] rlimits, long permittedCapabilities, long effectiveCapabilities) {
        VM_HOOKS.preFork();
        // Resets nice priority for zygote process.
        resetNicePriority();
        int pid = nativeForkSystemServer(
                uid, gid, gids, debugFlags, rlimits, permittedCapabilities, effectiveCapabilities);
        // Enable tracing as soon as we enter the system_server.
        if (pid == 0) {
            Trace.setTracingEnabled(true, debugFlags);
        }
        VM_HOOKS.postForkCommon();
        return pid;
    }

    native private static int nativeForkSystemServer(int uid, int gid, int[] gids, int debugFlags,
            int[][] rlimits, long permittedCapabilities, long effectiveCapabilities);

这里直接调用 native 层的 nativeForkSystemServer 创建，底层也是调用了 fork() 函数。

关于 fork()

fork() 函数通过系统调用创建一个与原来进程几乎完全相同的进程，也就是两个进程可以做完全相同的事，但如果初始参数或者传入的变量不同，两个进程也可以做不同的事。
    一个进程调用 fork() 函数后，系统先给新的进程分配资源，例如存储数据和代码的空间。然后把原来的进程的所有值都复制到新的新进程中，只有少数值与原来的进程的值不同。相当于克隆了一个自己。

fork被调用一次，却能够返回两次，它可能有三种不同的返回值：

在父进程中，fork返回新创建子进程的进程ID；在子进程中，fork返回0；如果出现错误，fork返回一个负值；

runSelectLoop

Runnable runSelectLoop(String abiList) {
        ArrayList<FileDescriptor> fds = new ArrayList<FileDescriptor>();
        ArrayList<ZygoteConnection> peers = new ArrayList<ZygoteConnection>();
        //添加到 fds 列表中
        fds.add(mServerSocket.getFileDescriptor());
        peers.add(null);
        //死循环
        while (true) {
            StructPollfd[] pollFds = new StructPollfd[fds.size()];
            //遍历 fds 将 fds 中信息转移到 pollFds 中
            for (int i = 0; i < pollFds.length; ++i) {
                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);
            }
            //遍历 pollFds
            for (int i = pollFds.length - 1; i >= 0; --i) {
                if ((pollFds[i].revents & POLLIN) == 0) {
                    continue;
                }

                if (i == 0) {
                    //通过 acceptCommandPeer 方法得到 ZygoteConnection，并添加到 peers 连接列表中
                    ZygoteConnection newPeer = acceptCommandPeer(abiList);
                    peers.add(newPeer);
                    fds.add(newPeer.getFileDesciptor());
                } else {
//...
                }
            }
        }
    }

首先调用 registerServerSocket 函数创建的服务端 Socket 获取 此Socket 设置的 fd 字段，接着无限循环遍历，注意这里 i == 0 ，说明服务器端 Socket 与客户端连接上了，也就是 Zygote 进程与 AMS 建立了连接。

Zygote的启动流程就此结束。