JVM系列(二)：jvm是如何加载java代码的？

　　上一篇粗略讲了下jvm的启动过程，但很多路子还没跑通。其中非常核心的，加载vm的过程。这个可以在hotspot中找到端倪。但jvm启动，又是如何载入java代码呢。

 

1. JavaMain加载流程

　　我们知道，java中入口是在main方法中，可以在命令行中指定main类，或者jar包中指定的manifest.xml中指定的main类。在java.c中，我们可以看到一个JavaMain方法，不知从何而来，但很像是直接加载java入口的方法。

// share/bin/java.c
// 加载 main 函数类
// 通过引入 JavaMain(), 接入java方法
// #define JNICALL __stdcall
int JNICALL
JavaMain(void * _args)
{
    JavaMainArgs *args = (JavaMainArgs *)_args;
    int argc = args->argc;
    char **argv = args->argv;
    int mode = args->mode;
    char *what = args->what;
    // 一些jvm的调用实例，在之前的步骤中，通过加载相应动态链接方法，保存起来的
    /** 
     * ifn->CreateJavaVM =
     *   (void *)GetProcAddress(handle, "JNI_CreateJavaVM");
     * ifn->GetDefaultJavaVMInitArgs =
     *   (void *)GetProcAddress(handle, "JNI_GetDefaultJavaVMInitArgs");
     */
    InvocationFunctions ifn = args->ifn;
    JavaVM *vm = 0;
    JNIEnv *env = 0;
    jclass mainClass = NULL;
    jclass appClass = NULL; // actual application class being launched
    jmethodID mainID;
    jobjectArray mainArgs;
    int ret = 0;
    jlong start, end;
    // collector
    RegisterThread();
    /* Initialize the virtual machine */
    start = CounterGet();
    // 初始化jvm，失败则退出
    if (!InitializeJVM(&vm, &env, &ifn)) {
        JLI_ReportErrorMessage(JVM_ERROR1);
        exit(1);
    }
    // jvm检查完毕，如果只是一些展示类请求，则展示信息后，退出jvm
    if (showSettings != NULL) {
        ShowSettings(env, showSettings);
        /**
         * 宏是神奇的操作，此处 *env 直接引用
#define CHECK_EXCEPTION_LEAVE(CEL_return_value) \
    do { \
        if ((*env)->ExceptionOccurred(env)) { \
            JLI_ReportExceptionDescription(env); \
            ret = (CEL_return_value); \
            LEAVE(); \
        } \
    } while (JNI_FALSE)
         */
        CHECK_EXCEPTION_LEAVE(1);
    }
    // 调用 LEAVE() 方法的目的在于主动销毁jvm线程
    // 且退出当前方法调用，即 LEAVE() 后方法不再被执行
/*
 * Always detach the main thread so that it appears to have ended when
 * the application's main method exits.  This will invoke the
 * uncaught exception handler machinery if main threw an
 * exception.  An uncaught exception handler cannot change the
 * launcher's return code except by calling System.exit.
 *
 * Wait for all non-daemon threads to end, then destroy the VM.
 * This will actually create a trivial new Java waiter thread
 * named "DestroyJavaVM", but this will be seen as a different
 * thread from the one that executed main, even though they are
 * the same C thread.  This allows mainThread.join() and
 * mainThread.isAlive() to work as expected.
 */
    /**
     *
     * 
#define LEAVE() \
    do { \
        if ((*vm)->DetachCurrentThread(vm) != JNI_OK) { \
            JLI_ReportErrorMessage(JVM_ERROR2); \
            ret = 1; \
        } \
        if (JNI_TRUE) { \
            (*vm)->DestroyJavaVM(vm); \
            return ret; \
        } \
    } while (JNI_FALSE)
     */
    if (printVersion || showVersion) {
        PrintJavaVersion(env, showVersion);
        CHECK_EXCEPTION_LEAVE(0);
        if (printVersion) {
            LEAVE();
        }
    }
    /* If the user specified neither a class name nor a JAR file */
    if (printXUsage || printUsage || what == 0 || mode == LM_UNKNOWN) {
        PrintUsage(env, printXUsage);
        CHECK_EXCEPTION_LEAVE(1);
        LEAVE();
    }
    // 释放内存
    FreeKnownVMs();  /* after last possible PrintUsage() */
    if (JLI_IsTraceLauncher()) {
        end = CounterGet();
        JLI_TraceLauncher("%ld micro seconds to InitializeJVM\n",
               (long)(jint)Counter2Micros(end-start));
    }
    /* At this stage, argc/argv have the application's arguments */
    if (JLI_IsTraceLauncher()){
        int i;
        printf("%s is '%s'\n", launchModeNames[mode], what);
        printf("App's argc is %d\n", argc);
        for (i=0; i < argc; i++) {
            printf("    argv[%2d] = '%s'\n", i, argv[i]);
        }
    }
    ret = 1;
    /*
     * Get the application's main class.
     *
     * See bugid 5030265.  The Main-Class name has already been parsed
     * from the manifest, but not parsed properly for UTF-8 support.
     * Hence the code here ignores the value previously extracted and
     * uses the pre-existing code to reextract the value.  This is
     * possibly an end of release cycle expedient.  However, it has
     * also been discovered that passing some character sets through
     * the environment has "strange" behavior on some variants of
     * Windows.  Hence, maybe the manifest parsing code local to the
     * launcher should never be enhanced.
     *
     * Hence, future work should either:
     *     1)   Correct the local parsing code and verify that the
     *          Main-Class attribute gets properly passed through
     *          all environments,
     *     2)   Remove the vestages of maintaining main_class through
     *          the environment (and remove these comments).
     *
     * This method also correctly handles launching existing JavaFX
     * applications that may or may not have a Main-Class manifest entry.
     */
    // 加载 main 指定的class类
    mainClass = LoadMainClass(env, mode, what);
    CHECK_EXCEPTION_NULL_LEAVE(mainClass);
    /*
     * In some cases when launching an application that needs a helper, e.g., a
     * JavaFX application with no main method, the mainClass will not be the
     * applications own main class but rather a helper class. To keep things
     * consistent in the UI we need to track and report the application main class.
     */
    appClass = GetApplicationClass(env);
    NULL_CHECK_RETURN_VALUE(appClass, -1);
    /*
     * PostJVMInit uses the class name as the application name for GUI purposes,
     * for example, on OSX this sets the application name in the menu bar for
     * both SWT and JavaFX. So we'll pass the actual application class here
     * instead of mainClass as that may be a launcher or helper class instead
     * of the application class.
     */
    // 加载main() 方法前执行初始化
    PostJVMInit(env, appClass, vm);
    CHECK_EXCEPTION_LEAVE(1);
    /*
     * The LoadMainClass not only loads the main class, it will also ensure
     * that the main method's signature is correct, therefore further checking
     * is not required. The main method is invoked here so that extraneous java
     * stacks are not in the application stack trace.
     */
    // 获取main()方法id, main(String[] args)
    mainID = (*env)->GetStaticMethodID(env, mainClass, "main",
                                       "([Ljava/lang/String;)V");
    CHECK_EXCEPTION_NULL_LEAVE(mainID);
    /* Build platform specific argument array */
    // 构建args[] 参数
    mainArgs = CreateApplicationArgs(env, argv, argc);
    CHECK_EXCEPTION_NULL_LEAVE(mainArgs);
    /* Invoke main method. */
    // 调用java实现的main()方法
    // XX:: 重要实现
    (*env)->CallStaticVoidMethod(env, mainClass, mainID, mainArgs);
    /*
     * The launcher's exit code (in the absence of calls to
     * System.exit) will be non-zero if main threw an exception.
     */
    ret = (*env)->ExceptionOccurred(env) == NULL ? 0 : 1;
    LEAVE();
}
/*
 * Loads a class and verifies that the main class is present and it is ok to
 * call it for more details refer to the java implementation.
 */
static jclass
LoadMainClass(JNIEnv *env, int mode, char *name)
{
    jmethodID mid;
    jstring str;
    jobject result;
    jlong start, end;
    jclass cls = GetLauncherHelperClass(env);
    NULL_CHECK0(cls);
    if (JLI_IsTraceLauncher()) {
        start = CounterGet();
    }
    // checkAndLoadMain(String) 方法作为中间main()调用
    NULL_CHECK0(mid = (*env)->GetStaticMethodID(env, cls,
                "checkAndLoadMain",
                "(ZILjava/lang/String;)Ljava/lang/Class;"));
    str = NewPlatformString(env, name);
    CHECK_JNI_RETURN_0(
        result = (*env)->CallStaticObjectMethod(
            env, cls, mid, USE_STDERR, mode, str));
    if (JLI_IsTraceLauncher()) {
        end   = CounterGet();
        printf("%ld micro seconds to load main class\n",
               (long)(jint)Counter2Micros(end-start));
        printf("----%s----\n", JLDEBUG_ENV_ENTRY);
    }
    return (jclass)result;
}    

// 初始化jvm, 主要是调用 CreateJavaVM() 方法，进行创建jvm操作
/*
 * Initializes the Java Virtual Machine. Also frees options array when
 * finished.
 */
static jboolean
InitializeJVM(JavaVM **pvm, JNIEnv **penv, InvocationFunctions *ifn)
{
    JavaVMInitArgs args;
    jint r;
    memset(&args, 0, sizeof(args));
    args.version  = JNI_VERSION_1_2;
    args.nOptions = numOptions;
    args.options  = options;
    args.ignoreUnrecognized = JNI_FALSE;
    if (JLI_IsTraceLauncher()) {
        int i = 0;
        printf("JavaVM args:\n    ");
        printf("version 0x%08lx, ", (long)args.version);
        printf("ignoreUnrecognized is %s, ",
               args.ignoreUnrecognized ? "JNI_TRUE" : "JNI_FALSE");
        printf("nOptions is %ld\n", (long)args.nOptions);
        for (i = 0; i < numOptions; i++)
            printf("    option[%2d] = '%s'\n",
                   i, args.options[i].optionString);
    }
    r = ifn->CreateJavaVM(pvm, (void **)penv, &args);
    JLI_MemFree(options);
    return r == JNI_OK;
}

　　略去核心加载jvm的实现，要加载main类，还是比较简单的。主要就是通过前面查找出的main_class, 然后通过在jvm的实例中获取到的各方法的函数指针，然后按照字节码的规范，调用 MainClass.main(String[]) 方法。当然了，为了兼容其他非main的场景，它还有很多附加处理逻辑。

       另外，如何翻译java代码，并执行，这是jvm的重中之重。即编译原理的拿手好戏，也是我们普通程序员越不过的坎！但至少，我们来到了门槛前面！

 

2. jvm启动框架

　　前面讲了加载main方法的过程，大致理解了c如何启动调用java的main的。那么，这又是如何调用准备的呢，在这之前都需要做哪些准备呢？

　　实际上，这是平台相关的实现。

// share/bin/java.c
/*
 * Entry point.
 */
int
JLI_Launch(int argc, char ** argv,              /* main argc, argc */
        int jargc, const char** jargv,          /* java args */
        int appclassc, const char** appclassv,  /* app classpath */
        const char* fullversion,                /* full version defined */
        const char* dotversion,                 /* dot version defined */
        const char* pname,                      /* program name */
        const char* lname,                      /* launcher name */
        jboolean javaargs,                      /* JAVA_ARGS */
        jboolean cpwildcard,                    /* classpath wildcard*/
        jboolean javaw,                         /* windows-only javaw */
        jint ergo                               /* ergonomics class policy */
)
{
    int mode = LM_UNKNOWN;
    char *what = NULL;
    char *cpath = 0;
    char *main_class = NULL;
    int ret;
    InvocationFunctions ifn;
    jlong start, end;
    char jvmpath[MAXPATHLEN];
    char jrepath[MAXPATHLEN];
    char jvmcfg[MAXPATHLEN];
    _fVersion = fullversion;
    _dVersion = dotversion;
    _launcher_name = lname;
    _program_name = pname;
    _is_java_args = javaargs;
    _wc_enabled = cpwildcard;
    _ergo_policy = ergo;
    // 初始化启动器
    InitLauncher(javaw);
    // 打印状态
    DumpState();
    // 跟踪调用启动
    if (JLI_IsTraceLauncher()) {
        int i;
        printf("Command line args:\n");
        for (i = 0; i < argc ; i++) {
            printf("argv[%d] = %s\n", i, argv[i]);
        }
        AddOption("-Dsun.java.launcher.diag=true", NULL);
    }
    /*
     * Make sure the specified version of the JRE is running.
     *
     * There are three things to note about the SelectVersion() routine:
     *  1) If the version running isn't correct, this routine doesn't
     *     return (either the correct version has been exec'd or an error
     *     was issued).
     *  2) Argc and Argv in this scope are *not* altered by this routine.
     *     It is the responsibility of subsequent code to ignore the
     *     arguments handled by this routine.
     *  3) As a side-effect, the variable "main_class" is guaranteed to
     *     be set (if it should ever be set).  This isn't exactly the
     *     poster child for structured programming, but it is a small
     *     price to pay for not processing a jar file operand twice.
     *     (Note: This side effect has been disabled.  See comment on
     *     bugid 5030265 below.)
     */
    // 解析命令行参数，选择一jre版本
    SelectVersion(argc, argv, &main_class);
    CreateExecutionEnvironment(&argc, &argv,
                               jrepath, sizeof(jrepath),
                               jvmpath, sizeof(jvmpath),
                               jvmcfg,  sizeof(jvmcfg));
    if (!IsJavaArgs()) {
        // 设置一些特殊的环境变量
        SetJvmEnvironment(argc,argv);
    }
    ifn.CreateJavaVM = 0;
    ifn.GetDefaultJavaVMInitArgs = 0;
    if (JLI_IsTraceLauncher()) {
        start = CounterGet();
    }
    // 加载VM, 重中之重
    if (!LoadJavaVM(jvmpath, &ifn)) {
        return(6);
    }
    if (JLI_IsTraceLauncher()) {
        end   = CounterGet();
    }
    JLI_TraceLauncher("%ld micro seconds to LoadJavaVM\n",
             (long)(jint)Counter2Micros(end-start));
    ++argv;
    --argc;
    // 解析更多参数信息
    if (IsJavaArgs()) {
        /* Preprocess wrapper arguments */
        TranslateApplicationArgs(jargc, jargv, &argc, &argv);
        if (!AddApplicationOptions(appclassc, appclassv)) {
            return(1);
        }
    } else {
        /* Set default CLASSPATH */
        cpath = getenv("CLASSPATH");
        if (cpath == NULL) {
            cpath = ".";
        }
        SetClassPath(cpath);
    }
    /* Parse command line options; if the return value of
     * ParseArguments is false, the program should exit.
     */
    // 解析参数
    if (!ParseArguments(&argc, &argv, &mode, &what, &ret, jrepath))
    {
        return(ret);
    }
    /* Override class path if -jar flag was specified */
    if (mode == LM_JAR) {
        SetClassPath(what);     /* Override class path */
    }
    /* set the -Dsun.java.command pseudo property */
    SetJavaCommandLineProp(what, argc, argv);
    /* Set the -Dsun.java.launcher pseudo property */
    SetJavaLauncherProp();
    /* set the -Dsun.java.launcher.* platform properties */
    SetJavaLauncherPlatformProps();
    return JVMInit(&ifn, threadStackSize, argc, argv, mode, what, ret);
}

// macos/bin/java_md_macos.c
// MacOSX we may continue in the same thread
int
JVMInit(InvocationFunctions* ifn, jlong threadStackSize,
                 int argc, char **argv,
                 int mode, char *what, int ret) {
    if (sameThread) {
        JLI_TraceLauncher("In same thread\n");
        // need to block this thread against the main thread
        // so signals get caught correctly
        __block int rslt = 0;
        NSAutoreleasePool *pool = [[NSAutoreleasePool alloc] init];
        {
            NSBlockOperation *op = [NSBlockOperation blockOperationWithBlock: ^{
                JavaMainArgs args;
                args.argc = argc;
                args.argv = argv;
                args.mode = mode;
                args.what = what;
                args.ifn  = *ifn;
                // 调用 JavaMain()
                rslt = JavaMain(&args);
            }];
            /*
             * We cannot use dispatch_sync here, because it blocks the main dispatch queue.
             * Using the main NSRunLoop allows the dispatch queue to run properly once
             * SWT (or whatever toolkit this is needed for) kicks off it's own NSRunLoop
             * and starts running.
             */
            [op performSelectorOnMainThread:@selector(start) withObject:nil waitUntilDone:YES];
        }
        [pool drain];
        return rslt;
    } else {
        return ContinueInNewThread(ifn, threadStackSize, argc, argv, mode, what, ret);
    }
}

　　以上是mac调用 javaMain的方式。在windows, 以及linux上则稍有不同。

// windows/bin/java_md.c
int
JVMInit(InvocationFunctions* ifn, jlong threadStackSize,
        int argc, char **argv,
        int mode, char *what, int ret)
{
    ShowSplashScreen();
    return ContinueInNewThread(ifn, threadStackSize, argc, argv, mode, what, ret);
}
// java.c
int
ContinueInNewThread(InvocationFunctions* ifn, jlong threadStackSize,
                    int argc, char **argv,
                    int mode, char *what, int ret)
{

    /*
     * If user doesn't specify stack size, check if VM has a preference.
     * Note that HotSpot no longer supports JNI_VERSION_1_1 but it will
     * return its default stack size through the init args structure.
     */
    if (threadStackSize == 0) {
      struct JDK1_1InitArgs args1_1;
      memset((void*)&args1_1, 0, sizeof(args1_1));
      args1_1.version = JNI_VERSION_1_1;
      ifn->GetDefaultJavaVMInitArgs(&args1_1);  /* ignore return value */
      if (args1_1.javaStackSize > 0) {
         threadStackSize = args1_1.javaStackSize;
      }
    }

    { /* Create a new thread to create JVM and invoke main method */
      JavaMainArgs args;
      int rslt;

      args.argc = argc;
      args.argv = argv;
      args.mode = mode;
      args.what = what;
      args.ifn = *ifn;
      // 传入 JavaMain() 函数参数，在新线程中运行 JavaMain
      rslt = ContinueInNewThread0(JavaMain, threadStackSize, (void*)&args);
      /* If the caller has deemed there is an error we
       * simply return that, otherwise we return the value of
       * the callee
       */
      return (ret != 0) ? ret : rslt;
    }
}
/*
 * Block current thread and continue execution in a new thread
 */
int
ContinueInNewThread0(int (JNICALL *continuation)(void *), jlong stack_size, void * args) {
    int rslt = 0;
    unsigned thread_id;
#ifndef STACK_SIZE_PARAM_IS_A_RESERVATION
#define STACK_SIZE_PARAM_IS_A_RESERVATION  (0x10000)
#endif
    /*
     * STACK_SIZE_PARAM_IS_A_RESERVATION is what we want, but it's not
     * supported on older version of Windows. Try first with the flag; and
     * if that fails try again without the flag. See MSDN document or HotSpot
     * source (os_win32.cpp) for details.
     * 调用底层内核方法，创建新线程，将JavaMain(args)作为函数调用处理。创建后立即执行
     * 如果第一次带参创建失败，则弃参重试一次
     */
    HANDLE thread_handle =
      (HANDLE)_beginthreadex(NULL,
                             (unsigned)stack_size,
                             continuation,
                             args,
                             STACK_SIZE_PARAM_IS_A_RESERVATION,
                             &thread_id);
    if (thread_handle == NULL) {
      thread_handle =
      (HANDLE)_beginthreadex(NULL,
                             (unsigned)stack_size,
                             continuation,
                             args,
                             0,
                             &thread_id);
    }
    /* AWT preloading (AFTER main thread start) */
#ifdef ENABLE_AWT_PRELOAD
    /* D3D preloading */
    if (awtPreloadD3D != 0) {
        char *envValue;
        /* D3D routines checks env.var J2D_D3D if no appropriate
         * command line params was specified
         */
        envValue = getenv("J2D_D3D");
        if (envValue != NULL && JLI_StrCaseCmp(envValue, "false") == 0) {
            awtPreloadD3D = 0;
        }
        /* Test that AWT preloading isn't disabled by J2D_D3D_PRELOAD env.var */
        envValue = getenv("J2D_D3D_PRELOAD");
        if (envValue != NULL && JLI_StrCaseCmp(envValue, "false") == 0) {
            awtPreloadD3D = 0;
        }
        if (awtPreloadD3D < 0) {
            /* If awtPreloadD3D is still undefined (-1), test
             * if it is turned on by J2D_D3D_PRELOAD env.var.
             * By default it's turned OFF.
             */
            awtPreloadD3D = 0;
            if (envValue != NULL && JLI_StrCaseCmp(envValue, "true") == 0) {
                awtPreloadD3D = 1;
            }
         }
    }
    if (awtPreloadD3D) {
        AWTPreload(D3D_PRELOAD_FUNC);
    }
#endif /* ENABLE_AWT_PRELOAD */
    if (thread_handle) {
      // 等待线程结束，并获取返回码
      WaitForSingleObject(thread_handle, INFINITE);
      GetExitCodeThread(thread_handle, &rslt);
      CloseHandle(thread_handle);
    } else {
      // 如果实在是创建线程失败，则自身直接执行该方法即可
      rslt = continuation(args);
    }
#ifdef ENABLE_AWT_PRELOAD
    if (awtPreloaded) {
        AWTPreloadStop();
    }
#endif /* ENABLE_AWT_PRELOAD */
    return rslt;
}

　　在linux中的创建线程如下:

// solaris/bin/java_md_solinux.c
/*
 * Block current thread and continue execution in a new thread
 */
int
ContinueInNewThread0(int (JNICALL *continuation)(void *), jlong stack_size, void * args) {
    int rslt;
#ifdef __linux__
    pthread_t tid;
    pthread_attr_t attr;
    pthread_attr_init(&attr);
    pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_JOINABLE);

    if (stack_size > 0) {
      pthread_attr_setstacksize(&attr, stack_size);
    }
    // 常见的 pthread_xx 方式 创建线程
    if (pthread_create(&tid, &attr, (void *(*)(void*))continuation, (void*)args) == 0) {
      void * tmp;
      pthread_join(tid, &tmp);
      rslt = (int)tmp;
    } else {
     /*
      * Continue execution in current thread if for some reason (e.g. out of
      * memory/LWP)  a new thread can't be created. This will likely fail
      * later in continuation as JNI_CreateJavaVM needs to create quite a
      * few new threads, anyway, just give it a try..
      */
      rslt = continuation(args);
    }

    pthread_attr_destroy(&attr);
#else /* ! __linux__ */
    thread_t tid;
    long flags = 0;
    if (thr_create(NULL, stack_size, (void *(*)(void *))continuation, args, flags, &tid) == 0) {
      void * tmp;
      thr_join(tid, NULL, &tmp);
      rslt = (int)tmp;
    } else {
      /* See above. Continue in current thread if thr_create() failed */
      rslt = continuation(args);
    }
#endif /* __linux__ */
    return rslt;
}

　　即相同的语义，不同平台下的各自实现而已。

 

 

　　通过C语言的函数传递，从而进行调用。通过创建一个新线程，调用JavaMain(); 由javaMain处理所有java事务。而自身则只需等待JavaMain完成即可。这也符合面向过程编程思想。

 

3. jvm初始化小结

　　我们平时是通过 java xxx.xxx  或者 java -jar xx.jar 启动jvm, 通过这两篇文章，我们也看清了其背后的原理。就是通过解析各种参数，验证各种参数，验证jre环境，然后验证jre是否可用，最后将指定的mainClass加载出来。丢到一个新的线程中去执行，将执行权力转发给java代码，最后等待该线程完成。

　　应该说事个流程没有难点，或者说一切都很理所当然。但其中的核心，都是通过加载JavaVM()去做的，也就是真正的jvm. 然后通过或者对应的几个接口方法地址，进行调用，从而完成启动任务。所以，java虽是一个启动命令，但核心并不在这里。而是在 hotspot 或其他地方。jdk 毕竟只是一个工具箱而已。jre 才是关键。