基于OpenJDK 8

一直以为Java Object.hashCode()的结果就是通过对象的内存地址做相关运算得到的，但是无意在网上看到有相应的意见争论，故抽时间从源码层面验证了剖析了hashCode的默认计算方法。

先说结论：OpenJDK8 默认hashCode的计算方法是通过和当前线程有关的一个随机数+三个确定值，运用Marsaglia's xorshift scheme随机数算法得到的一个随机数。和对象内存地址无关。

下面通过查找和分析OpenJDK8源码实现来一步步分析。

1. 查找java.lang.Object.hashCode()源码

public native int hashCode();

2. 导出Object的JNI头文件

切换到Object.class文件所在目录，执行 javah -jni java.lang.Object，得到java_lang_Object.h文件，文件内容如下：

/* DO NOT EDIT THIS FILE - it is machine generated */
#include <jni.h>
/* Header for class java_lang_Object */

#ifndef _Included_java_lang_Object
#define _Included_java_lang_Object
#ifdef __cplusplus
extern "C" {
#endif
/*
 * Class:     java_lang_Object
 * Method:    registerNatives
 * Signature: ()V
 */
JNIEXPORT void JNICALL Java_java_lang_Object_registerNatives
  (JNIEnv *, jclass);

/*
 * Class:     java_lang_Object
 * Method:    getClass
 * Signature: ()Ljava/lang/Class;
 */
JNIEXPORT jclass JNICALL Java_java_lang_Object_getClass
  (JNIEnv *, jobject);

/*
 * Class:     java_lang_Object
 * Method:    hashCode
 * Signature: ()I
 */
JNIEXPORT jint JNICALL Java_java_lang_Object_hashCode
  (JNIEnv *, jobject);

/*
 * Class:     java_lang_Object
 * Method:    clone
 * Signature: ()Ljava/lang/Object;
 */
JNIEXPORT jobject JNICALL Java_java_lang_Object_clone
  (JNIEnv *, jobject);

/*
 * Class:     java_lang_Object
 * Method:    notify
 * Signature: ()V
 */
JNIEXPORT void JNICALL Java_java_lang_Object_notify
  (JNIEnv *, jobject);

/*
 * Class:     java_lang_Object
 * Method:    notifyAll
 * Signature: ()V
 */
JNIEXPORT void JNICALL Java_java_lang_Object_notifyAll
  (JNIEnv *, jobject);

/*
 * Class:     java_lang_Object
 * Method:    wait
 * Signature: (J)V
 */
JNIEXPORT void JNICALL Java_java_lang_Object_wait
  (JNIEnv *, jobject, jlong);

#ifdef __cplusplus
}
#endif
#endif

3 . 查看Object的native方法实现

OpenJDK源码链接：http://hg.openjdk.java.net/jdk8u/jdk8u/jdk/file/3462d04401ba/src/share/native/java/lang/Object.c ，查看Object.c文件，可以看到hashCode()的方法被注册成由JVM_IHashCode方法指针来处理。

static JNINativeMethod methods[] = {  
    {"hashCode",    "()I",                    (void *)&JVM_IHashCode},//hashcode的方法指针JVM_IHashCode  
    {"wait",        "(J)V",                   (void *)&JVM_MonitorWait},  
    {"notify",      "()V",                    (void *)&JVM_MonitorNotify},  
    {"notifyAll",   "()V",                    (void *)&JVM_MonitorNotifyAll},  
    {"clone",       "()Ljava/lang/Object;",   (void *)&JVM_Clone},  
};  

而JVM_IHashCode方法指针在 openjdk\hotspot\src\share\vm\prims\jvm.cpp中定义为：

JVM_ENTRY(jint, JVM_IHashCode(JNIEnv* env, jobject handle))  
  JVMWrapper("JVM_IHashCode");  
  // as implemented in the classic virtual machine; return 0 if object is NULL  
  return handle == NULL ? 0 : ObjectSynchronizer::FastHashCode (THREAD, JNIHandles::resolve_non_null(handle)) ;  
JVM_END 

从而得知，真正计算获得hashCode的值是ObjectSynchronizer::FastHashCode

4 . ObjectSynchronizer::fashHashCode方法的实现

openjdk\hotspot\src\share\vm\runtime\synchronizer.cpp 找到其实现方法。

intptr_t ObjectSynchronizer::FastHashCode (Thread * Self, oop obj) {
  if (UseBiasedLocking) {
    // NOTE: many places throughout the JVM do not expect a safepoint
    // to be taken here, in particular most operations on perm gen
    // objects. However, we only ever bias Java instances and all of
    // the call sites of identity_hash that might revoke biases have
    // been checked to make sure they can handle a safepoint. The
    // added check of the bias pattern is to avoid useless calls to
    // thread-local storage.
    if (obj->mark()->has_bias_pattern()) {
      // Box and unbox the raw reference just in case we cause a STW safepoint.
      Handle hobj (Self, obj) ;
      // Relaxing assertion for bug 6320749.
      assert (Universe::verify_in_progress() ||
              !SafepointSynchronize::is_at_safepoint(),
             "biases should not be seen by VM thread here");
      BiasedLocking::revoke_and_rebias(hobj, false, JavaThread::current());
      obj = hobj() ;
      assert(!obj->mark()->has_bias_pattern(), "biases should be revoked by now");
    }
  }

  // hashCode() is a heap mutator ...
  // Relaxing assertion for bug 6320749.
  assert (Universe::verify_in_progress() ||
          !SafepointSynchronize::is_at_safepoint(), "invariant") ;
  assert (Universe::verify_in_progress() ||
          Self->is_Java_thread() , "invariant") ;
  assert (Universe::verify_in_progress() ||
         ((JavaThread *)Self)->thread_state() != _thread_blocked, "invariant") ;

  ObjectMonitor* monitor = NULL;
  markOop temp, test;
  intptr_t hash;
  markOop mark = ReadStableMark (obj);

  // object should remain ineligible for biased locking
  assert (!mark->has_bias_pattern(), "invariant") ;

  if (mark->is_neutral()) {
    hash = mark->hash();              // this is a normal header
    if (hash) {                       // if it has hash, just return it
      return hash;
    }
    hash = get_next_hash(Self, obj);  // allocate a new hash code
    temp = mark->copy_set_hash(hash); // merge the hash code into header
    // use (machine word version) atomic operation to install the hash
    test = (markOop) Atomic::cmpxchg_ptr(temp, obj->mark_addr(), mark);
    if (test == mark) {
      return hash;
    }
    // If atomic operation failed, we must inflate the header
    // into heavy weight monitor. We could add more code here
    // for fast path, but it does not worth the complexity.
  } else if (mark->has_monitor()) {
    monitor = mark->monitor();
    temp = monitor->header();
    assert (temp->is_neutral(), "invariant") ;
    hash = temp->hash();
    if (hash) {
      return hash;
    }
    // Skip to the following code to reduce code size
  } else if (Self->is_lock_owned((address)mark->locker())) {
    temp = mark->displaced_mark_helper(); // this is a lightweight monitor owned
    assert (temp->is_neutral(), "invariant") ;
    hash = temp->hash();              // by current thread, check if the displaced
    if (hash) {                       // header contains hash code
      return hash;
    }
    // WARNING:
    //   The displaced header is strictly immutable.
    // It can NOT be changed in ANY cases. So we have
    // to inflate the header into heavyweight monitor
    // even the current thread owns the lock. The reason
    // is the BasicLock (stack slot) will be asynchronously
    // read by other threads during the inflate() function.
    // Any change to stack may not propagate to other threads
    // correctly.
  }

  // Inflate the monitor to set hash code
  monitor = ObjectSynchronizer::inflate(Self, obj);
  // Load displaced header and check it has hash code
  mark = monitor->header();
  assert (mark->is_neutral(), "invariant") ;
  hash = mark->hash();
  if (hash == 0) {
    hash = get_next_hash(Self, obj);
    temp = mark->copy_set_hash(hash); // merge hash code into header
    assert (temp->is_neutral(), "invariant") ;
    test = (markOop) Atomic::cmpxchg_ptr(temp, monitor, mark);
    if (test != mark) {
      // The only update to the header in the monitor (outside GC)
      // is install the hash code. If someone add new usage of
      // displaced header, please update this code
      hash = test->hash();
      assert (test->is_neutral(), "invariant") ;
      assert (hash != 0, "Trivial unexpected object/monitor header usage.");
    }
  }
  // We finally get the hash
  return hash;
}

该方法中

// Load displaced header and check it has hash code
  mark = monitor->header();
  assert (mark->is_neutral(), "invariant") ;
  hash = mark->hash();
  if (hash == 0) {
    hash = get_next_hash(Self, obj);
...
}

对hash值真正进行了计算，查看get_next_hash方法源码http://hg.openjdk.java.net/jdk8u/jdk8u/hotspot/file/87ee5ee27509/src/share/vm/runtime/synchronizer.cpp#l555

static inline intptr_t get_next_hash(Thread * Self, oop obj) {
  intptr_t value = 0 ;
  if (hashCode == 0) {
     // This form uses an unguarded global Park-Miller RNG,
     // so it's possible for two threads to race and generate the same RNG.
     // On MP system we'll have lots of RW access to a global, so the
     // mechanism induces lots of coherency traffic.
     value = os::random() ;
  } else
  if (hashCode == 1) {
     // This variation has the property of being stable (idempotent)
     // between STW operations.  This can be useful in some of the 1-0
     // synchronization schemes.
     intptr_t addrBits = cast_from_oop<intptr_t>(obj) >> 3 ;
     value = addrBits ^ (addrBits >> 5) ^ GVars.stwRandom ;
  } else
  if (hashCode == 2) {
     value = 1 ;            // for sensitivity testing
  } else
  if (hashCode == 3) {
     value = ++GVars.hcSequence ;
  } else
  if (hashCode == 4) {
     value = cast_from_oop<intptr_t>(obj) ;
  } else {
     // Marsaglia's xor-shift scheme with thread-specific state
     // This is probably the best overall implementation -- we'll
     // likely make this the default in future releases.
     unsigned t = Self->_hashStateX ;
     t ^= (t << 11) ;
     Self->_hashStateX = Self->_hashStateY ;
     Self->_hashStateY = Self->_hashStateZ ;
     Self->_hashStateZ = Self->_hashStateW ;
     unsigned v = Self->_hashStateW ;
     v = (v ^ (v >> 19)) ^ (t ^ (t >> 8)) ;
     Self->_hashStateW = v ;
     value = v ;
  }

  value &= markOopDesc::hash_mask;
  if (value == 0) value = 0xBAD ;
  assert (value != markOopDesc::no_hash, "invariant") ;
  TEVENT (hashCode: GENERATE) ;
  return value;
}

对于OpenJDK8版本，其默认配置http://hg.openjdk.java.net/jdk8u/jdk8u/hotspot/file/87ee5ee27509/src/share/vm/runtime/globals.hpp#l1127 为：

 product(intx, hashCode, 5,                                                \
          "(Unstable) select hashCode generation algorithm")                \

其对应的hashCode计算方案为：

    // Marsaglia's xor-shift scheme with thread-specific state
     // This is probably the best overall implementation -- we'll
     // likely make this the default in future releases.
     unsigned t = Self->_hashStateX ;
     t ^= (t << 11) ;
     Self->_hashStateX = Self->_hashStateY ;
     Self->_hashStateY = Self->_hashStateZ ;
     Self->_hashStateZ = Self->_hashStateW ;
     unsigned v = Self->_hashStateW ;
     v = (v ^ (v >> 19)) ^ (t ^ (t >> 8)) ;
     Self->_hashStateW = v ;
     value = v ;

其中Thread->_hashStateX, Thread->_hashStateY, Thread->_hashStateZ, Thread->_hashStateW在http://hg.openjdk.java.net/jdk8u/jdk8u/hotspot/file/87ee5ee27509/src/share/vm/runtime/thread.cpp#I263 有定义：

   // thread-specific hashCode stream generator state - Marsaglia shift-xor form
  _hashStateX = os::random() ;
  _hashStateY = 842502087 ;
  _hashStateZ = 0x8767 ;    // (int)(3579807591LL & 0xffff) ;
  _hashStateW = 273326509 ;

所以，JDK8 的默认hashCode的计算方法是通过和当前线程有关的一个随机数+三个确定值，运用Marsaglia's xorshift scheme随机数算法得到的一个随机数。对xorshift算法有兴趣可以参考原论文：https://www.jstatsoft.org/article/view/v008i14/xorshift.pdf 。
xorshift是由George Marsaglia发现的一类伪随机数生成器，其通过移位和与或计算，能够在计算机上以极快的速度生成伪随机数序列。其算法的基本实现如下：

unsigned long xor128(){
static unsigned long x=123456789,y=362436069,z=521288629,w=88675123;
unsigned long t;
t=(xˆ(x<<11));x=y;y=z;z=w; return( w=(wˆ(w>>19))ˆ(tˆ(t>>8)) );

这就和上面计算hashCode的OpenJDK代码对应了起来。

5 . 其他几类hashCode计算方案：

• hashCode == 0
  此类方案返回一个Park-Miller伪随机数生成器生成的随机数
  OpenJdk 6 &7的默认实现。http://hg.openjdk.java.net/jdk7u/jdk7u/hotspot/file/5b9a416a5632/src/share/vm/runtime/globals.hpp#l1100
  http://hg.openjdk.java.net/jdk6/jdk6/hotspot/file/5cec449cc409/src/share/vm/runtime/globals.hpp#l1128

if (hashCode == 0) {
     // This form uses an unguarded global Park-Miller RNG,
     // so it's possible for two threads to race and generate the same RNG.
     // On MP system we'll have lots of RW access to a global, so the
     // mechanism induces lots of coherency traffic.
     value = os::random() ;
  }

• hashCode == 1
  此类方案将对象的内存地址，做移位运算后与一个随机数进行异或得到结果

if (hashCode == 1) {
     // This variation has the property of being stable (idempotent)
     // between STW operations.  This can be useful in some of the 1-0
     // synchronization schemes.
     intptr_t addrBits = cast_from_oop<intptr_t>(obj) >> 3 ;
     value = addrBits ^ (addrBits >> 5) ^ GVars.stwRandom ;
  }

• hashCode == 2
  此类方案返回固定的1

if (hashCode == 2) {
     value = 1 ;            // for sensitivity testing
  } 

• hashCode == 3
  此类方案返回一个自增序列的当前值

if (hashCode == 3) {
     value = ++GVars.hcSequence ;
  } 

• hashCode == 4
  此类方案返回当前对象的内存地址

if (hashCode == 4) {
     value = cast_from_oop<intptr_t>(obj) ;
  }

可以通过在JVM启动参数中添加-XX:hashCode=4，改变默认的hashCode计算方式。

参考资料：
https://srvaroa.github.io/jvm/java/openjdk/biased-locking/2017/01/30/hashCode.html
https://en.wikipedia.org/wiki/Xorshift
http://www.cnblogs.com/mengyou0304/p/4763220.html
http://stackoverflow.com/questions/2427631/how-is-hashcode-calculated-in-java
http://hllvm.group.iteye.com/group/topic/39183