JVM系列(五)：gc实现概要01

　　java的一大核心特性，即是自动内存回收。这让一些人从繁琐的内存管理中解脱出来，但对大部分人来说，貌似这太理所当然了。因为现在市场上的语言，几乎都已经没有了还需要自己去管理内存这事。大家似乎都以为，语言不就应该干这事吗。

　　其实在我们现在的编程语言中，从某种角度上，大致可以分为多进程并发模型和多线程并发模型。进程的资源可以操作系统直接管理，而线程则依附于进程而存在。所以，从这个角度来说，也许多进程并发模型的内存回收，也许会简单些。因为，多进程运行，可能带来的就是进程的快速创建与消亡。而进程消亡后，就可以由操作系统进行管理内存了。这种编程语言多见于各种脚本语言。但实际上，并没有那么简单。虽说多线程并发模型中，必然伴随着进程的长期运行，线程的反复创建与销毁，所以内存资源需要语言自行实现。但，多进程并发模型，难道就不可以长时间运行了吗？难道就不会使用超过最大内存限制的空间了吗？难道就没有需要删除的空间了吗？其实它同样都会面临这些问题，所以，它们都会有内存回收的需求。只是各自实现的精细度不一样，也是合理的。

　　网上有许多的资料，讲解java gc的工作过程，参数控制，最佳实践等等。但多半只算得黑盒测试，但也足够我们从容应对工作了。业有余力之时，我们可以来看看，具体的gc如何用代码敲出来，亦是快事。

1. 垃圾回收算法及收集器简述

　　前面说了，有太多的文章讲解这类工作。我们只提只言片语。

　　如何判定一个对象是否可以回收，主要算法有： 引用计数器算法（简单加减引用）、可达性分析算法（图论分析）。

　　而具体的内存回收，则可以分几大算法进行描述：标记-清除算法，复制算法，标记-整理算法，混合之。具体处理过程，可以望文生义，也可以查详细资料理解。

　　具体的java垃圾回收器：Serial/Serial Old收集器；ParNew收集器；Parallel Scavenge收集器；Parallel Old收集器；CMS（Concurrent Mark Sweep）收集器；G1收集器；ZGC收集器；具体解释请参考其他资料。

2. hotspot垃圾回收器入口1

　　我们知道，垃圾回收器实际是在时刻都在工作的，比如minor空间不足时，触发一次MinorGC，当老年代空间不足时，触发MajorGC。但要说我们主动触发GC,则可以直接调用  System.gc(); 即可完成一次gc工作。

// jdk/src/share/native/java/lang/Runtime.c
JNIEXPORT void JNICALL
Java_java_lang_Runtime_gc(JNIEnv *env, jobject this)
{
    JVM_GC();
}
// jdk,hosport, share/vm/prims/jvm.h
JNIEXPORT void JNICALL
JVM_GC(void);
// hotspot/src/share/vm/prims/jvm.cpp
JVM_ENTRY_NO_ENV(void, JVM_GC(void))
  JVMWrapper("JVM_GC");
  if (!DisableExplicitGC) {
      // 调用对应的gc实现，collect 回收内存
    Universe::heap()->collect(GCCause::_java_lang_system_gc);
  }
JVM_END

　　其中，heap() 和 collect() 都是有许多实现版本的，即根据选择的垃圾回收器的不同，而执行不同的逻辑。

　　具体的heap()选择，需要依赖于外部设置。我们看两个具体的 heap 由来。一个是默认的，一个PS的，一个G1的。

  // share/memory/universe.cpp
  // The particular choice of collected heap.
  static CollectedHeap* heap() { return _collectedHeap; }

// share/vm/gc_implemention/parallelScavenge/parallelScavengeHeap.cpp
ParallelScavengeHeap* ParallelScavengeHeap::heap() {
  assert(_psh != NULL, "Uninitialized access to ParallelScavengeHeap::heap()");
  assert(_psh->kind() == CollectedHeap::ParallelScavengeHeap, "not a parallel scavenge heap");
  return _psh;
}

// share/vm/gc_implemention/g1/g1CollectionHeap.cpp
G1CollectedHeap* G1CollectedHeap::heap() {
  assert(_sh->kind() == CollectedHeap::G1CollectedHeap,
         "not a garbage-first heap");
  return _g1h;
}

　　具体内存回收由 collect完成，而每个垃圾回收器有各自的实现。我们就看3个实现，1.默认新生代回收；2.多线程新生代回收；3.G1新生代回收；只需看个入口框架，细节留待后续完成。

// 1. defNew 回收
// share/memory/defNewGeneration.cpp
void DefNewGeneration::collect(bool   full,
                               bool   clear_all_soft_refs,
                               size_t size,
                               bool   is_tlab) {
  assert(full || size > 0, "otherwise we don't want to collect");

  GenCollectedHeap* gch = GenCollectedHeap::heap();

  _gc_timer->register_gc_start();
  DefNewTracer gc_tracer;
  gc_tracer.report_gc_start(gch->gc_cause(), _gc_timer->gc_start());

  _next_gen = gch->next_gen(this);

  // If the next generation is too full to accommodate promotion
  // from this generation, pass on collection; let the next generation
  // do it.
  if (!collection_attempt_is_safe()) {
    if (Verbose && PrintGCDetails) {
      gclog_or_tty->print(" :: Collection attempt not safe :: ");
    }
    gch->set_incremental_collection_failed(); // Slight lie: we did not even attempt one
    return;
  }
  assert(to()->is_empty(), "Else not collection_attempt_is_safe");

  init_assuming_no_promotion_failure();

  GCTraceTime t1(GCCauseString("GC", gch->gc_cause()), PrintGC && !PrintGCDetails, true, NULL);
  // Capture heap used before collection (for printing).
  size_t gch_prev_used = gch->used();

  gch->trace_heap_before_gc(&gc_tracer);

  SpecializationStats::clear();

  // These can be shared for all code paths
  IsAliveClosure is_alive(this);
  ScanWeakRefClosure scan_weak_ref(this);

  age_table()->clear();
  to()->clear(SpaceDecorator::Mangle);

  gch->rem_set()->prepare_for_younger_refs_iterate(false);

  assert(gch->no_allocs_since_save_marks(0),
         "save marks have not been newly set.");

  // Not very pretty.
  CollectorPolicy* cp = gch->collector_policy();

  FastScanClosure fsc_with_no_gc_barrier(this, false);
  FastScanClosure fsc_with_gc_barrier(this, true);

  KlassScanClosure klass_scan_closure(&fsc_with_no_gc_barrier,
                                      gch->rem_set()->klass_rem_set());

  set_promo_failure_scan_stack_closure(&fsc_with_no_gc_barrier);
  FastEvacuateFollowersClosure evacuate_followers(gch, _level, this,
                                                  &fsc_with_no_gc_barrier,
                                                  &fsc_with_gc_barrier);

  assert(gch->no_allocs_since_save_marks(0),
         "save marks have not been newly set.");

  int so = SharedHeap::SO_AllClasses | SharedHeap::SO_Strings | SharedHeap::SO_CodeCache;

  gch->gen_process_strong_roots(_level,
                                true,  // Process younger gens, if any,
                                       // as strong roots.
                                true,  // activate StrongRootsScope
                                true,  // is scavenging
                                SharedHeap::ScanningOption(so),
                                &fsc_with_no_gc_barrier,
                                true,   // walk *all* scavengable nmethods
                                &fsc_with_gc_barrier,
                                &klass_scan_closure);

  // "evacuate followers".
  evacuate_followers.do_void();

  FastKeepAliveClosure keep_alive(this, &scan_weak_ref);
  ReferenceProcessor* rp = ref_processor();
  rp->setup_policy(clear_all_soft_refs);
  const ReferenceProcessorStats& stats =
  rp->process_discovered_references(&is_alive, &keep_alive, &evacuate_followers,
                                    NULL, _gc_timer);
  gc_tracer.report_gc_reference_stats(stats);

  if (!_promotion_failed) {
    // Swap the survivor spaces.
    eden()->clear(SpaceDecorator::Mangle);
    from()->clear(SpaceDecorator::Mangle);
    if (ZapUnusedHeapArea) {
      // This is now done here because of the piece-meal mangling which
      // can check for valid mangling at intermediate points in the
      // collection(s).  When a minor collection fails to collect
      // sufficient space resizing of the young generation can occur
      // an redistribute the spaces in the young generation.  Mangle
      // here so that unzapped regions don't get distributed to
      // other spaces.
      to()->mangle_unused_area();
    }
    swap_spaces();

    assert(to()->is_empty(), "to space should be empty now");

    adjust_desired_tenuring_threshold();

    // A successful scavenge should restart the GC time limit count which is
    // for full GC's.
    AdaptiveSizePolicy* size_policy = gch->gen_policy()->size_policy();
    size_policy->reset_gc_overhead_limit_count();
    if (PrintGC && !PrintGCDetails) {
      gch->print_heap_change(gch_prev_used);
    }
    assert(!gch->incremental_collection_failed(), "Should be clear");
  } else {
    assert(_promo_failure_scan_stack.is_empty(), "post condition");
    _promo_failure_scan_stack.clear(true); // Clear cached segments.

    remove_forwarding_pointers();
    if (PrintGCDetails) {
      gclog_or_tty->print(" (promotion failed) ");
    }
    // Add to-space to the list of space to compact
    // when a promotion failure has occurred.  In that
    // case there can be live objects in to-space
    // as a result of a partial evacuation of eden
    // and from-space.
    swap_spaces();   // For uniformity wrt ParNewGeneration.
    from()->set_next_compaction_space(to());
    gch->set_incremental_collection_failed();

    // Inform the next generation that a promotion failure occurred.
    _next_gen->promotion_failure_occurred();
    gc_tracer.report_promotion_failed(_promotion_failed_info);

    // Reset the PromotionFailureALot counters.
    NOT_PRODUCT(Universe::heap()->reset_promotion_should_fail();)
  }
  // set new iteration safe limit for the survivor spaces
  from()->set_concurrent_iteration_safe_limit(from()->top());
  to()->set_concurrent_iteration_safe_limit(to()->top());
  SpecializationStats::print();

  // We need to use a monotonically non-decreasing time in ms
  // or we will see time-warp warnings and os::javaTimeMillis()
  // does not guarantee monotonicity.
  jlong now = os::javaTimeNanos() / NANOSECS_PER_MILLISEC;
  update_time_of_last_gc(now);

  gch->trace_heap_after_gc(&gc_tracer);
  gc_tracer.report_tenuring_threshold(tenuring_threshold());

  _gc_timer->register_gc_end();

  gc_tracer.report_gc_end(_gc_timer->gc_end(), _gc_timer->time_partitions());
}

// 2. parNew 回收
// share/vm/gc_implemention/parNew/parNewGeneration.cpp
void ParNewGeneration::collect(bool   full,
                               bool   clear_all_soft_refs,
                               size_t size,
                               bool   is_tlab) {
  assert(full || size > 0, "otherwise we don't want to collect");
  // 获得堆空间的指针
  GenCollectedHeap* gch = GenCollectedHeap::heap();

  _gc_timer->register_gc_start();

  assert(gch->kind() == CollectedHeap::GenCollectedHeap,
    "not a CMS generational heap");
  AdaptiveSizePolicy* size_policy = gch->gen_policy()->size_policy();
  FlexibleWorkGang* workers = gch->workers();
  assert(workers != NULL, "Need workgang for parallel work");
  int active_workers =
      AdaptiveSizePolicy::calc_active_workers(workers->total_workers(),
                                   workers->active_workers(),
                                   Threads::number_of_non_daemon_threads());
  workers->set_active_workers(active_workers);
  assert(gch->n_gens() == 2,
         "Par collection currently only works with single older gen.");
  _next_gen = gch->next_gen(this);
  // Do we have to avoid promotion_undo?
  if (gch->collector_policy()->is_concurrent_mark_sweep_policy()) {
    set_avoid_promotion_undo(true);
  }

  // If the next generation is too full to accommodate worst-case promotion
  // from this generation, pass on collection; let the next generation
  // do it.
  if (!collection_attempt_is_safe()) {
    gch->set_incremental_collection_failed();  // slight lie, in that we did not even attempt one
    return;
  }
  assert(to()->is_empty(), "Else not collection_attempt_is_safe");

  ParNewTracer gc_tracer;
  gc_tracer.report_gc_start(gch->gc_cause(), _gc_timer->gc_start());
  gch->trace_heap_before_gc(&gc_tracer);

  init_assuming_no_promotion_failure();

  if (UseAdaptiveSizePolicy) {
    set_survivor_overflow(false);
    size_policy->minor_collection_begin();
  }

  GCTraceTime t1(GCCauseString("GC", gch->gc_cause()), PrintGC && !PrintGCDetails, true, NULL);
  // Capture heap used before collection (for printing).
  size_t gch_prev_used = gch->used();

  SpecializationStats::clear();

  age_table()->clear();
  to()->clear(SpaceDecorator::Mangle);

  gch->save_marks();
  assert(workers != NULL, "Need parallel worker threads.");
  int n_workers = active_workers;

  // Set the correct parallelism (number of queues) in the reference processor
  ref_processor()->set_active_mt_degree(n_workers);

  // Always set the terminator for the active number of workers
  // because only those workers go through the termination protocol.
  ParallelTaskTerminator _term(n_workers, task_queues());
  ParScanThreadStateSet thread_state_set(workers->active_workers(),
                                         *to(), *this, *_next_gen, *task_queues(),
                                         _overflow_stacks, desired_plab_sz(), _term);

  ParNewGenTask tsk(this, _next_gen, reserved().end(), &thread_state_set);
  gch->set_par_threads(n_workers);
  gch->rem_set()->prepare_for_younger_refs_iterate(true);
  // It turns out that even when we're using 1 thread, doing the work in a
  // separate thread causes wide variance in run times.  We can't help this
  // in the multi-threaded case, but we special-case n=1 here to get
  // repeatable measurements of the 1-thread overhead of the parallel code.
  if (n_workers > 1) {
      // 使用GcRoots 可达性分析法
    GenCollectedHeap::StrongRootsScope srs(gch);
    workers->run_task(&tsk);
  } else {
    GenCollectedHeap::StrongRootsScope srs(gch);
    tsk.work(0);
  }
  thread_state_set.reset(0 /* Bad value in debug if not reset */,
                         promotion_failed());

  // Process (weak) reference objects found during scavenge.
  ReferenceProcessor* rp = ref_processor();
  IsAliveClosure is_alive(this);
  ScanWeakRefClosure scan_weak_ref(this);
  KeepAliveClosure keep_alive(&scan_weak_ref);
  ScanClosure               scan_without_gc_barrier(this, false);
  ScanClosureWithParBarrier scan_with_gc_barrier(this, true);
  set_promo_failure_scan_stack_closure(&scan_without_gc_barrier);
  EvacuateFollowersClosureGeneral evacuate_followers(gch, _level,
    &scan_without_gc_barrier, &scan_with_gc_barrier);
  rp->setup_policy(clear_all_soft_refs);
  // Can  the mt_degree be set later (at run_task() time would be best)?
  rp->set_active_mt_degree(active_workers);
  ReferenceProcessorStats stats;
  if (rp->processing_is_mt()) {
    ParNewRefProcTaskExecutor task_executor(*this, thread_state_set);
    stats = rp->process_discovered_references(&is_alive, &keep_alive,
                                              &evacuate_followers, &task_executor,
                                              _gc_timer);
  } else {
    thread_state_set.flush();
    gch->set_par_threads(0);  // 0 ==> non-parallel.
    gch->save_marks();
    stats = rp->process_discovered_references(&is_alive, &keep_alive,
                                              &evacuate_followers, NULL,
                                              _gc_timer);
  }
  gc_tracer.report_gc_reference_stats(stats);
  if (!promotion_failed()) {
    // Swap the survivor spaces.
    eden()->clear(SpaceDecorator::Mangle);
    from()->clear(SpaceDecorator::Mangle);
    if (ZapUnusedHeapArea) {
      // This is now done here because of the piece-meal mangling which
      // can check for valid mangling at intermediate points in the
      // collection(s).  When a minor collection fails to collect
      // sufficient space resizing of the young generation can occur
      // an redistribute the spaces in the young generation.  Mangle
      // here so that unzapped regions don't get distributed to
      // other spaces.
      to()->mangle_unused_area();
    }
    swap_spaces();

    // A successful scavenge should restart the GC time limit count which is
    // for full GC's.
    size_policy->reset_gc_overhead_limit_count();

    assert(to()->is_empty(), "to space should be empty now");

    adjust_desired_tenuring_threshold();
  } else {
    handle_promotion_failed(gch, thread_state_set, gc_tracer);
  }
  // set new iteration safe limit for the survivor spaces
  from()->set_concurrent_iteration_safe_limit(from()->top());
  to()->set_concurrent_iteration_safe_limit(to()->top());

  if (ResizePLAB) {
    plab_stats()->adjust_desired_plab_sz(n_workers);
  }
  // 输出gc日志
  if (PrintGC && !PrintGCDetails) {
    gch->print_heap_change(gch_prev_used);
  }

  if (PrintGCDetails && ParallelGCVerbose) {
    TASKQUEUE_STATS_ONLY(thread_state_set.print_termination_stats());
    TASKQUEUE_STATS_ONLY(thread_state_set.print_taskqueue_stats());
  }

  if (UseAdaptiveSizePolicy) {
    size_policy->minor_collection_end(gch->gc_cause());
    size_policy->avg_survived()->sample(from()->used());
  }

  // We need to use a monotonically non-deccreasing time in ms
  // or we will see time-warp warnings and os::javaTimeMillis()
  // does not guarantee monotonicity.
  jlong now = os::javaTimeNanos() / NANOSECS_PER_MILLISEC;
  update_time_of_last_gc(now);

  SpecializationStats::print();

  rp->set_enqueuing_is_done(true);
  if (rp->processing_is_mt()) {
    ParNewRefProcTaskExecutor task_executor(*this, thread_state_set);
    rp->enqueue_discovered_references(&task_executor);
  } else {
    rp->enqueue_discovered_references(NULL);
  }
  rp->verify_no_references_recorded();

  gch->trace_heap_after_gc(&gc_tracer);
  gc_tracer.report_tenuring_threshold(tenuring_threshold());

  _gc_timer->register_gc_end();

  gc_tracer.report_gc_end(_gc_timer->gc_end(), _gc_timer->time_partitions());
}

// 3. 分代收集回收
// share/vm/memory/genCollectedHeap.cpp
void GenCollectedHeap::collect(GCCause::Cause cause) {
  // 判断是否需要进行FGC, 依据是 cms 收集器且 cause==_gc_locker
  if (should_do_concurrent_full_gc(cause)) {
#if INCLUDE_ALL_GCS
    // mostly concurrent full collection
    collect_mostly_concurrent(cause);
#else  // INCLUDE_ALL_GCS
    ShouldNotReachHere();
#endif // INCLUDE_ALL_GCS
  } else {
#ifdef ASSERT
    if (cause == GCCause::_scavenge_alot) {
      // minor collection only
      // 新生代gc
      collect(cause, 0);
    } else {
      // Stop-the-world full collection
      collect(cause, n_gens() - 1);
    }
#else
    // Stop-the-world full collection
    collect(cause, n_gens() - 1);
#endif
  }
}

void GenCollectedHeap::collect(GCCause::Cause cause, int max_level) {
  // The caller doesn't have the Heap_lock
  assert(!Heap_lock->owned_by_self(), "this thread should not own the Heap_lock");
  MutexLocker ml(Heap_lock);
  // 上锁收集内存
  collect_locked(cause, max_level);
}

// this is the private collection interface
// The Heap_lock is expected to be held on entry.

void GenCollectedHeap::collect_locked(GCCause::Cause cause, int max_level) {
  // Read the GC count while holding the Heap_lock
  unsigned int gc_count_before      = total_collections();
  unsigned int full_gc_count_before = total_full_collections();
  {
    MutexUnlocker mu(Heap_lock);  // give up heap lock, execute gets it back
    // 整个gc过程就由 VM_GenCollectFull 去实现了，而其中最重要的则是 doIt() 方法的实现
    VM_GenCollectFull op(gc_count_before, full_gc_count_before,
                         cause, max_level);
    // 交给虚拟机线程完成该工作
    VMThread::execute(&op);
  }
}

// 4. G1回收
// share/vm/gc_implemention/g1/g1CollectedHeap.cpp
void G1CollectedHeap::collect(GCCause::Cause cause) {
  assert_heap_not_locked();

  unsigned int gc_count_before;
  unsigned int old_marking_count_before;
  bool retry_gc;

  do {
    retry_gc = false;

    {
      MutexLocker ml(Heap_lock);

      // Read the GC count while holding the Heap_lock
      gc_count_before = total_collections();
      old_marking_count_before = _old_marking_cycles_started;
    }
    // FullGc 判定
    if (should_do_concurrent_full_gc(cause)) {
      // Schedule an initial-mark evacuation pause that will start a
      // concurrent cycle. We're setting word_size to 0 which means that
      // we are not requesting a post-GC allocation.
         // 整个 FGC 过程由 VM_G1IncCollectionPause 完成
      VM_G1IncCollectionPause op(gc_count_before,
                                 0,     /* word_size */
                                 true,  /* should_initiate_conc_mark */
                                 g1_policy()->max_pause_time_ms(),
                                 cause);

      VMThread::execute(&op);
      if (!op.pause_succeeded()) {
        if (old_marking_count_before == _old_marking_cycles_started) {
          retry_gc = op.should_retry_gc();
        } else {
          // A Full GC happened while we were trying to schedule the
          // initial-mark GC. No point in starting a new cycle given
          // that the whole heap was collected anyway.
        }

        if (retry_gc) {
          if (GC_locker::is_active_and_needs_gc()) {
            GC_locker::stall_until_clear();
          }
        }
      }
    } else {
      if (cause == GCCause::_gc_locker
          DEBUG_ONLY(|| cause == GCCause::_scavenge_alot)) {

        // Schedule a standard evacuation pause. We're setting word_size
        // to 0 which means that we are not requesting a post-GC allocation.
        VM_G1IncCollectionPause op(gc_count_before,
                                   0,     /* word_size */
                                   false, /* should_initiate_conc_mark */
                                   g1_policy()->max_pause_time_ms(),
                                   cause);
        VMThread::execute(&op);
      } else {
        // Schedule a Full GC.
        VM_G1CollectFull op(gc_count_before, old_marking_count_before, cause);
        VMThread::execute(&op);
      }
    }
  } while (retry_gc);
}

　　以上是几个收集的实现入门框架，从中我们可以窥得一些实现方式。尤其是对于 单线程类的收集器，基本思路已经形成。只是具体如何，还得看官们自花心思。

　　除了要了解gc从何处开始执行，我们应该还需要知道如何选择收集器，以及他们是如何初始化的。这自然是在jvm启动时完成的。

// universe初始化
// share/vm/runtime/init.cpp
jint init_globals() {
  HandleMark hm;
  management_init();
  bytecodes_init();
  classLoader_init();
  codeCache_init();
  VM_Version_init();
  os_init_globals();
  stubRoutines_init1();
  // gc 初始化入口
  jint status = universe_init();  // dependent on codeCache_init and
                                  // stubRoutines_init1 and metaspace_init.
  if (status != JNI_OK)
    return status;

  interpreter_init();  // before any methods loaded
  invocationCounter_init();  // before any methods loaded
  marksweep_init();
  accessFlags_init();
  templateTable_init();
  InterfaceSupport_init();
  SharedRuntime::generate_stubs();
  universe2_init();  // dependent on codeCache_init and stubRoutines_init1
  referenceProcessor_init();
  jni_handles_init();
#if INCLUDE_VM_STRUCTS
  vmStructs_init();
#endif // INCLUDE_VM_STRUCTS

  vtableStubs_init();
  InlineCacheBuffer_init();
  compilerOracle_init();
  compilationPolicy_init();
  compileBroker_init();
  VMRegImpl::set_regName();

  if (!universe_post_init()) {
    return JNI_ERR;
  }
  javaClasses_init();   // must happen after vtable initialization
  stubRoutines_init2(); // note: StubRoutines need 2-phase init

  // All the flags that get adjusted by VM_Version_init and os::init_2
  // have been set so dump the flags now.
  if (PrintFlagsFinal) {
    CommandLineFlags::printFlags(tty, false);
  }

  return JNI_OK;
}

// memory/universe.cpp
jint universe_init() {
  assert(!Universe::_fully_initialized, "called after initialize_vtables");
  guarantee(1 << LogHeapWordSize == sizeof(HeapWord),
         "LogHeapWordSize is incorrect.");
  guarantee(sizeof(oop) >= sizeof(HeapWord), "HeapWord larger than oop?");
  guarantee(sizeof(oop) % sizeof(HeapWord) == 0,
            "oop size is not not a multiple of HeapWord size");
  TraceTime timer("Genesis", TraceStartupTime);
  GC_locker::lock();  // do not allow gc during bootstrapping
  JavaClasses::compute_hard_coded_offsets();

  jint status = Universe::initialize_heap();
  if (status != JNI_OK) {
    return status;
  }

  Metaspace::global_initialize();

  // Create memory for metadata.  Must be after initializing heap for
  // DumpSharedSpaces.
  ClassLoaderData::init_null_class_loader_data();

  // We have a heap so create the Method* caches before
  // Metaspace::initialize_shared_spaces() tries to populate them.
  Universe::_finalizer_register_cache = new LatestMethodCache();
  Universe::_loader_addClass_cache    = new LatestMethodCache();
  Universe::_pd_implies_cache         = new LatestMethodCache();

  if (UseSharedSpaces) {
    // Read the data structures supporting the shared spaces (shared
    // system dictionary, symbol table, etc.).  After that, access to
    // the file (other than the mapped regions) is no longer needed, and
    // the file is closed. Closing the file does not affect the
    // currently mapped regions.
    MetaspaceShared::initialize_shared_spaces();
    StringTable::create_table();
  } else {
    SymbolTable::create_table();
    StringTable::create_table();
    ClassLoader::create_package_info_table();
  }

  return JNI_OK;
}

// hotspot/src/share/vm/memory/universe.cpp：
jint Universe::initialize_heap() {

  if (UseParallelGC) {
#if INCLUDE_ALL_GCS
    Universe::_collectedHeap = new ParallelScavengeHeap();
#else  // INCLUDE_ALL_GCS
    fatal("UseParallelGC not supported in this VM.");
#endif // INCLUDE_ALL_GCS

  } else if (UseG1GC) {
#if INCLUDE_ALL_GCS
    G1CollectorPolicy* g1p = new G1CollectorPolicy();
    g1p->initialize_all();
    G1CollectedHeap* g1h = new G1CollectedHeap(g1p);
    Universe::_collectedHeap = g1h;
#else  // INCLUDE_ALL_GCS
    fatal("UseG1GC not supported in java kernel vm.");
#endif // INCLUDE_ALL_GCS

  } else {
    GenCollectorPolicy *gc_policy;

    if (UseSerialGC) {
      gc_policy = new MarkSweepPolicy();
    } else if (UseConcMarkSweepGC) {
#if INCLUDE_ALL_GCS
      if (UseAdaptiveSizePolicy) {
        gc_policy = new ASConcurrentMarkSweepPolicy();
      } else {
        gc_policy = new ConcurrentMarkSweepPolicy();
      }
#else  // INCLUDE_ALL_GCS
    fatal("UseConcMarkSweepGC not supported in this VM.");
#endif // INCLUDE_ALL_GCS
    } else { // default old generation
      gc_policy = new MarkSweepPolicy();
    }
    gc_policy->initialize_all();

    Universe::_collectedHeap = new GenCollectedHeap(gc_policy);
  }

  jint status = Universe::heap()->initialize();
  if (status != JNI_OK) {
    return status;
  }

#ifdef _LP64
  if (UseCompressedOops) {
    // Subtract a page because something can get allocated at heap base.
    // This also makes implicit null checking work, because the
    // memory+1 page below heap_base needs to cause a signal.
    // See needs_explicit_null_check.
    // Only set the heap base for compressed oops because it indicates
    // compressed oops for pstack code.
    bool verbose = PrintCompressedOopsMode || (PrintMiscellaneous && Verbose);
    if (verbose) {
      tty->cr();
      tty->print("heap address: " PTR_FORMAT ", size: " SIZE_FORMAT " MB",
                 Universe::heap()->base(), Universe::heap()->reserved_region().byte_size()/M);
    }
    if (((uint64_t)Universe::heap()->reserved_region().end() > OopEncodingHeapMax)) {
      // Can't reserve heap below 32Gb.
      // keep the Universe::narrow_oop_base() set in Universe::reserve_heap()
      Universe::set_narrow_oop_shift(LogMinObjAlignmentInBytes);
      if (verbose) {
        tty->print(", %s: "PTR_FORMAT,
            narrow_oop_mode_to_string(HeapBasedNarrowOop),
            Universe::narrow_oop_base());
      }
    } else {
      Universe::set_narrow_oop_base(0);
      if (verbose) {
        tty->print(", %s", narrow_oop_mode_to_string(ZeroBasedNarrowOop));
      }
#ifdef _WIN64
      if (!Universe::narrow_oop_use_implicit_null_checks()) {
        // Don't need guard page for implicit checks in indexed addressing
        // mode with zero based Compressed Oops.
        Universe::set_narrow_oop_use_implicit_null_checks(true);
      }
#endif //  _WIN64
      if((uint64_t)Universe::heap()->reserved_region().end() > UnscaledOopHeapMax) {
        // Can't reserve heap below 4Gb.
        Universe::set_narrow_oop_shift(LogMinObjAlignmentInBytes);
      } else {
        Universe::set_narrow_oop_shift(0);
        if (verbose) {
          tty->print(", %s", narrow_oop_mode_to_string(UnscaledNarrowOop));
        }
      }
    }

    if (verbose) {
      tty->cr();
      tty->cr();
    }
    Universe::set_narrow_ptrs_base(Universe::narrow_oop_base());
  }
  // Universe::narrow_oop_base() is one page below the heap.
  assert((intptr_t)Universe::narrow_oop_base() <= (intptr_t)(Universe::heap()->base() -
         os::vm_page_size()) ||
         Universe::narrow_oop_base() == NULL, "invalid value");
  assert(Universe::narrow_oop_shift() == LogMinObjAlignmentInBytes ||
         Universe::narrow_oop_shift() == 0, "invalid value");
#endif

  // We will never reach the CATCH below since Exceptions::_throw will cause
  // the VM to exit if an exception is thrown during initialization

  if (UseTLAB) {
    assert(Universe::heap()->supports_tlab_allocation(),
           "Should support thread-local allocation buffers");
    ThreadLocalAllocBuffer::startup_initialization();
  }
  return JNI_OK;
}

3. 一个内存回收器的工作示例

　　该部分我们以一某个垃圾收集器的实现过程，来了解gc是如何完成的。这自然算不得真正的了解gc原理，但是有其一定的作用。

　　首先，一般的gc动作都会有独立的vm线程，也就是我们通过jstack查看时看到的gc线程。当然了，在代码中我们看到的是 VMThread. vm线程运行垃圾回收：

// share/vm/runtime/vmThread.cpp
void VMThread::execute(VM_Operation* op) {
  Thread* t = Thread::current();

  if (!t->is_VM_thread()) {
    SkipGCALot sgcalot(t);    // avoid re-entrant attempts to gc-a-lot
    // JavaThread or WatcherThread
    bool concurrent = op->evaluate_concurrently();
    // only blocking VM operations need to verify the caller's safepoint state:
    if (!concurrent) {
      t->check_for_valid_safepoint_state(true);
    }

    // New request from Java thread, evaluate prologue
    if (!op->doit_prologue()) {
      return;   // op was cancelled
    }

    // Setup VM_operations for execution
    op->set_calling_thread(t, Thread::get_priority(t));

    // It does not make sense to execute the epilogue, if the VM operation object is getting
    // deallocated by the VM thread.
    bool execute_epilog = !op->is_cheap_allocated();
    assert(!concurrent || op->is_cheap_allocated(), "concurrent => cheap_allocated");

    // Get ticket number for non-concurrent VM operations
    int ticket = 0;
    if (!concurrent) {
      ticket = t->vm_operation_ticket();
    }

    // Add VM operation to list of waiting threads. We are guaranteed not to block while holding the
    // VMOperationQueue_lock, so we can block without a safepoint check. This allows vm operation requests
    // to be queued up during a safepoint synchronization.
    {
      VMOperationQueue_lock->lock_without_safepoint_check();
      bool ok = _vm_queue->add(op);
    op->set_timestamp(os::javaTimeMillis());
      VMOperationQueue_lock->notify();
      VMOperationQueue_lock->unlock();
      // VM_Operation got skipped
      if (!ok) {
        assert(concurrent, "can only skip concurrent tasks");
        if (op->is_cheap_allocated()) delete op;
        return;
      }
    }

    if (!concurrent) {
      // Wait for completion of request (non-concurrent)
      // Note: only a JavaThread triggers the safepoint check when locking
      MutexLocker mu(VMOperationRequest_lock);
      while(t->vm_operation_completed_count() < ticket) {
        VMOperationRequest_lock->wait(!t->is_Java_thread());
      }
    }

    if (execute_epilog) {
      op->doit_epilogue();
    }
  } else {
    // invoked by VM thread; usually nested VM operation
    assert(t->is_VM_thread(), "must be a VM thread");
    VM_Operation* prev_vm_operation = vm_operation();
    if (prev_vm_operation != NULL) {
      // Check the VM operation allows nested VM operation. This normally not the case, e.g., the compiler
      // does not allow nested scavenges or compiles.
      if (!prev_vm_operation->allow_nested_vm_operations()) {
        fatal(err_msg("Nested VM operation %s requested by operation %s",
                      op->name(), vm_operation()->name()));
      }
      op->set_calling_thread(prev_vm_operation->calling_thread(), prev_vm_operation->priority());
    }

    EventMark em("Executing %s VM operation: %s", prev_vm_operation ? "nested" : "", op->name());

    // Release all internal handles after operation is evaluated
    HandleMark hm(t);
    _cur_vm_operation = op;

    if (op->evaluate_at_safepoint() && !SafepointSynchronize::is_at_safepoint()) {
      SafepointSynchronize::begin();
      op->evaluate();
      SafepointSynchronize::end();
    } else {
      op->evaluate();
    }

    // Free memory if needed
    if (op->is_cheap_allocated()) delete op;

    _cur_vm_operation = prev_vm_operation;
  }
}

　　我们看前面的 GenCollectedHeap 的垃圾回收方法，其最终向 vmThread 提交了一个 VM_GenCollectFull 的op任务，而其核心实现是在 doit() 方法中。 分代垃圾回收，由vm线程执行。

// vm/gc_implemention/shared/vmGCOperations.cpp
void VM_GenCollectFull::doit() {
  SvcGCMarker sgcm(SvcGCMarker::FULL);

  GenCollectedHeap* gch = GenCollectedHeap::heap();
  GCCauseSetter gccs(gch, _gc_cause);
  // 清理软引用，再做回收
  gch->do_full_collection(gch->must_clear_all_soft_refs(), _max_level);
}
// memory/genCollectedHeap.cpp
void GenCollectedHeap::do_full_collection(bool clear_all_soft_refs,
                                          int max_level) {
  int local_max_level;
  if (!incremental_collection_will_fail(false /* don't consult_young */) &&
      gc_cause() == GCCause::_gc_locker) {
    local_max_level = 0;
  } else {
    local_max_level = max_level;
  }
  // 具体回收动作
  do_collection(true                 /* full */,
                clear_all_soft_refs  /* clear_all_soft_refs */,
                0                    /* size */,
                false                /* is_tlab */,
                local_max_level      /* max_level */);
  // Hack XXX FIX ME !!!
  // A scavenge may not have been attempted, or may have
  // been attempted and failed, because the old gen was too full
  // 触发一次 FGC
  if (local_max_level == 0 && gc_cause() == GCCause::_gc_locker &&
      incremental_collection_will_fail(false /* don't consult_young */)) {
    if (PrintGCDetails) {
      gclog_or_tty->print_cr("GC locker: Trying a full collection "
                             "because scavenge failed");
    }
    // This time allow the old gen to be collected as well
    do_collection(true                 /* full */,
                  clear_all_soft_refs  /* clear_all_soft_refs */,
                  0                    /* size */,
                  false                /* is_tlab */,
                  n_gens() - 1         /* max_level */);
  }
}

// memory/genCollectedHeap.cpp
void GenCollectedHeap::do_collection(bool  full,
                                     bool   clear_all_soft_refs,
                                     size_t size,
                                     bool   is_tlab,
                                     int    max_level) {
  bool prepared_for_verification = false;
  ResourceMark rm;
  DEBUG_ONLY(Thread* my_thread = Thread::current();)

  assert(SafepointSynchronize::is_at_safepoint(), "should be at safepoint");
  assert(my_thread->is_VM_thread() ||
         my_thread->is_ConcurrentGC_thread(),
         "incorrect thread type capability");
  assert(Heap_lock->is_locked(),
         "the requesting thread should have the Heap_lock");
  guarantee(!is_gc_active(), "collection is not reentrant");
  assert(max_level < n_gens(), "sanity check");

  if (GC_locker::check_active_before_gc()) {
    return; // GC is disabled (e.g. JNI GetXXXCritical operation)
  }

  const bool do_clear_all_soft_refs = clear_all_soft_refs ||
                          collector_policy()->should_clear_all_soft_refs();

  ClearedAllSoftRefs casr(do_clear_all_soft_refs, collector_policy());

  const size_t metadata_prev_used = MetaspaceAux::allocated_used_bytes();

  print_heap_before_gc();

  {
    FlagSetting fl(_is_gc_active, true);

    bool complete = full && (max_level == (n_gens()-1));
    const char* gc_cause_prefix = complete ? "Full GC" : "GC";
    gclog_or_tty->date_stamp(PrintGC && PrintGCDateStamps);
    TraceCPUTime tcpu(PrintGCDetails, true, gclog_or_tty);
    GCTraceTime t(GCCauseString(gc_cause_prefix, gc_cause()), PrintGCDetails, false, NULL);

    gc_prologue(complete);
    increment_total_collections(complete);

    size_t gch_prev_used = used();

    int starting_level = 0;
    if (full) {
      // Search for the oldest generation which will collect all younger
      // generations, and start collection loop there.
      for (int i = max_level; i >= 0; i--) {
        if (_gens[i]->full_collects_younger_generations()) {
          starting_level = i;
          break;
        }
      }
    }

    bool must_restore_marks_for_biased_locking = false;

    int max_level_collected = starting_level;
    for (int i = starting_level; i <= max_level; i++) {
      if (_gens[i]->should_collect(full, size, is_tlab)) {
          // 升级FGC
        if (i == n_gens() - 1) {  // a major collection is to happen
          if (!complete) {
            // The full_collections increment was missed above.
            increment_total_full_collections();
          }
          pre_full_gc_dump(NULL);    // do any pre full gc dumps
        }
        // Timer for individual generations. Last argument is false: no CR
        // FIXME: We should try to start the timing earlier to cover more of the GC pause
        GCTraceTime t1(_gens[i]->short_name(), PrintGCDetails, false, NULL);
        TraceCollectorStats tcs(_gens[i]->counters());
        TraceMemoryManagerStats tmms(_gens[i]->kind(),gc_cause());

        size_t prev_used = _gens[i]->used();
        _gens[i]->stat_record()->invocations++;
        _gens[i]->stat_record()->accumulated_time.start();

        // Must be done anew before each collection because
        // a previous collection will do mangling and will
        // change top of some spaces.
        record_gen_tops_before_GC();

        if (PrintGC && Verbose) {
          gclog_or_tty->print("level=%d invoke=%d size=" SIZE_FORMAT,
                     i,
                     _gens[i]->stat_record()->invocations,
                     size*HeapWordSize);
        }

        if (VerifyBeforeGC && i >= VerifyGCLevel &&
            total_collections() >= VerifyGCStartAt) {
          HandleMark hm;  // Discard invalid handles created during verification
          if (!prepared_for_verification) {
            prepare_for_verify();
            prepared_for_verification = true;
          }
          Universe::verify(" VerifyBeforeGC:");
        }
        COMPILER2_PRESENT(DerivedPointerTable::clear());

        if (!must_restore_marks_for_biased_locking &&
            _gens[i]->performs_in_place_marking()) {
          // We perform this mark word preservation work lazily
          // because it's only at this point that we know whether we
          // absolutely have to do it; we want to avoid doing it for
          // scavenge-only collections where it's unnecessary
          must_restore_marks_for_biased_locking = true;
          BiasedLocking::preserve_marks();
        }

        // Do collection work
        {
          // Note on ref discovery: For what appear to be historical reasons,
          // GCH enables and disabled (by enqueing) refs discovery.
          // In the future this should be moved into the generation's
          // collect method so that ref discovery and enqueueing concerns
          // are local to a generation. The collect method could return
          // an appropriate indication in the case that notification on
          // the ref lock was needed. This will make the treatment of
          // weak refs more uniform (and indeed remove such concerns
          // from GCH). XXX

          HandleMark hm;  // Discard invalid handles created during gc
          save_marks();   // save marks for all gens
          // We want to discover references, but not process them yet.
          // This mode is disabled in process_discovered_references if the
          // generation does some collection work, or in
          // enqueue_discovered_references if the generation returns
          // without doing any work.
          ReferenceProcessor* rp = _gens[i]->ref_processor();
          // If the discovery of ("weak") refs in this generation is
          // atomic wrt other collectors in this configuration, we
          // are guaranteed to have empty discovered ref lists.
          if (rp->discovery_is_atomic()) {
            rp->enable_discovery(true /*verify_disabled*/, true /*verify_no_refs*/);
            rp->setup_policy(do_clear_all_soft_refs);
          } else {
            // collect() below will enable discovery as appropriate
          }
          // 每个年代的对象各自回收
          _gens[i]->collect(full, do_clear_all_soft_refs, size, is_tlab);
          if (!rp->enqueuing_is_done()) {
            rp->enqueue_discovered_references();
          } else {
            rp->set_enqueuing_is_done(false);
          }
          rp->verify_no_references_recorded();
        }
        max_level_collected = i;

        // Determine if allocation request was met.
        if (size > 0) {
          if (!is_tlab || _gens[i]->supports_tlab_allocation()) {
            if (size*HeapWordSize <= _gens[i]->unsafe_max_alloc_nogc()) {
              size = 0;
            }
          }
        }

        COMPILER2_PRESENT(DerivedPointerTable::update_pointers());

        _gens[i]->stat_record()->accumulated_time.stop();

        update_gc_stats(i, full);

        if (VerifyAfterGC && i >= VerifyGCLevel &&
            total_collections() >= VerifyGCStartAt) {
          HandleMark hm;  // Discard invalid handles created during verification
          Universe::verify(" VerifyAfterGC:");
        }

        if (PrintGCDetails) {
          gclog_or_tty->print(":");
          _gens[i]->print_heap_change(prev_used);
        }
      }
    }

    // Update "complete" boolean wrt what actually transpired --
    // for instance, a promotion failure could have led to
    // a whole heap collection.
    complete = complete || (max_level_collected == n_gens() - 1);

    if (complete) { // We did a "major" collection
      // FIXME: See comment at pre_full_gc_dump call
      post_full_gc_dump(NULL);   // do any post full gc dumps
    }

    if (PrintGCDetails) {
      print_heap_change(gch_prev_used);

      // Print metaspace info for full GC with PrintGCDetails flag.
      if (complete) {
        MetaspaceAux::print_metaspace_change(metadata_prev_used);
      }
    }

    for (int j = max_level_collected; j >= 0; j -= 1) {
      // Adjust generation sizes.
      _gens[j]->compute_new_size();
    }

    if (complete) {
      // Delete metaspaces for unloaded class loaders and clean up loader_data graph
      ClassLoaderDataGraph::purge();
      MetaspaceAux::verify_metrics();
      // Resize the metaspace capacity after full collections
      MetaspaceGC::compute_new_size();
      update_full_collections_completed();
    }

    // Track memory usage and detect low memory after GC finishes
    MemoryService::track_memory_usage();

    gc_epilogue(complete);

    if (must_restore_marks_for_biased_locking) {
      BiasedLocking::restore_marks();
    }
  }

  AdaptiveSizePolicy* sp = gen_policy()->size_policy();
  AdaptiveSizePolicyOutput(sp, total_collections());

  print_heap_after_gc();

#ifdef TRACESPINNING
  ParallelTaskTerminator::print_termination_counts();
#endif
}
// memory/generation.cpp
void OneContigSpaceCardGeneration::collect(bool   full,
                                           bool   clear_all_soft_refs,
                                           size_t size,
                                           bool   is_tlab) {
  GenCollectedHeap* gch = GenCollectedHeap::heap();

  SpecializationStats::clear();
  // Temporarily expand the span of our ref processor, so
  // refs discovery is over the entire heap, not just this generation
  ReferenceProcessorSpanMutator
    x(ref_processor(), gch->reserved_region());

  STWGCTimer* gc_timer = GenMarkSweep::gc_timer();
  gc_timer->register_gc_start();

  SerialOldTracer* gc_tracer = GenMarkSweep::gc_tracer();
  gc_tracer->report_gc_start(gch->gc_cause(), gc_timer->gc_start());
  // 标记清除算法调用
  GenMarkSweep::invoke_at_safepoint(_level, ref_processor(), clear_all_soft_refs);

  gc_timer->register_gc_end();

  gc_tracer->report_gc_end(gc_timer->gc_end(), gc_timer->time_partitions());

  SpecializationStats::print();
}

// memory/genMarkSweep.cpp
void GenMarkSweep::invoke_at_safepoint(int level, ReferenceProcessor* rp, bool clear_all_softrefs) {
  guarantee(level == 1, "We always collect both old and young.");
  assert(SafepointSynchronize::is_at_safepoint(), "must be at a safepoint");

  GenCollectedHeap* gch = GenCollectedHeap::heap();
#ifdef ASSERT
  if (gch->collector_policy()->should_clear_all_soft_refs()) {
    assert(clear_all_softrefs, "Policy should have been checked earlier");
  }
#endif

  // hook up weak ref data so it can be used during Mark-Sweep
  assert(ref_processor() == NULL, "no stomping");
  assert(rp != NULL, "should be non-NULL");
  _ref_processor = rp;
  rp->setup_policy(clear_all_softrefs);

  GCTraceTime t1(GCCauseString("Full GC", gch->gc_cause()), PrintGC && !PrintGCDetails, true, NULL);

  gch->trace_heap_before_gc(_gc_tracer);

  // When collecting the permanent generation Method*s may be moving,
  // so we either have to flush all bcp data or convert it into bci.
  CodeCache::gc_prologue();
  Threads::gc_prologue();

  // Increment the invocation count
  _total_invocations++;

  // Capture heap size before collection for printing.
  size_t gch_prev_used = gch->used();

  // Capture used regions for each generation that will be
  // subject to collection, so that card table adjustments can
  // be made intelligently (see clear / invalidate further below).
  gch->save_used_regions(level);

  allocate_stacks();
  // 阶段1~4
  // 1. Mark live objects
  // 2. Calculate new addresses
  // 3. Update pointers
  // 4. Move objects to new positions
  mark_sweep_phase1(level, clear_all_softrefs);

  mark_sweep_phase2();

  // Don't add any more derived pointers during phase3
  COMPILER2_PRESENT(assert(DerivedPointerTable::is_active(), "Sanity"));
  COMPILER2_PRESENT(DerivedPointerTable::set_active(false));

  mark_sweep_phase3(level);

  mark_sweep_phase4();

  restore_marks();

  // Set saved marks for allocation profiler (and other things? -- dld)
  // (Should this be in general part?)
  gch->save_marks();

  deallocate_stacks();

  // If compaction completely evacuated all generations younger than this
  // one, then we can clear the card table.  Otherwise, we must invalidate
  // it (consider all cards dirty).  In the future, we might consider doing
  // compaction within generations only, and doing card-table sliding.
  bool all_empty = true;
  for (int i = 0; all_empty && i < level; i++) {
    Generation* g = gch->get_gen(i);
    all_empty = all_empty && gch->get_gen(i)->used() == 0;
  }
  GenRemSet* rs = gch->rem_set();
  Generation* old_gen = gch->get_gen(level);
  // Clear/invalidate below make use of the "prev_used_regions" saved earlier.
  if (all_empty) {
    // We've evacuated all generations below us.
    rs->clear_into_younger(old_gen);
  } else {
    // Invalidate the cards corresponding to the currently used
    // region and clear those corresponding to the evacuated region.
    rs->invalidate_or_clear(old_gen);
  }

  Threads::gc_epilogue();
  CodeCache::gc_epilogue();
  JvmtiExport::gc_epilogue();

  if (PrintGC && !PrintGCDetails) {
    gch->print_heap_change(gch_prev_used);
  }

  // refs processing: clean slate
  _ref_processor = NULL;

  // Update heap occupancy information which is used as
  // input to soft ref clearing policy at the next gc.
  Universe::update_heap_info_at_gc();

  // Update time of last gc for all generations we collected
  // (which curently is all the generations in the heap).
  // We need to use a monotonically non-deccreasing time in ms
  // or we will see time-warp warnings and os::javaTimeMillis()
  // does not guarantee monotonicity.
  jlong now = os::javaTimeNanos() / NANOSECS_PER_MILLISEC;
  gch->update_time_of_last_gc(now);

  gch->trace_heap_after_gc(_gc_tracer);
}

　　害，太复杂，有空慢慢拆解吧。反正大致就是标记-清除算法步骤，在必要地方记录gc信息并打印，更新上下文信息。其中，最重要的是几个 phase, 可展开阅读。此处就当抛砖引玉了。

// genMarkSweep.cpp
void GenMarkSweep::mark_sweep_phase1(int level,
                                  bool clear_all_softrefs) {
  // Recursively traverse all live objects and mark them
  GCTraceTime tm("phase 1", PrintGC && Verbose, true, _gc_timer);
  trace(" 1");

  GenCollectedHeap* gch = GenCollectedHeap::heap();

  // Because follow_root_closure is created statically, cannot
  // use OopsInGenClosure constructor which takes a generation,
  // as the Universe has not been created when the static constructors
  // are run.
  follow_root_closure.set_orig_generation(gch->get_gen(level));

  // Need new claim bits before marking starts.
  ClassLoaderDataGraph::clear_claimed_marks();

  gch->gen_process_strong_roots(level,
                                false, // Younger gens are not roots.
                                true,  // activate StrongRootsScope
                                false, // not scavenging
                                SharedHeap::SO_SystemClasses,
                                &follow_root_closure,
                                true,   // walk code active on stacks
                                &follow_root_closure,
                                &follow_klass_closure);

  // Process reference objects found during marking
  {
    ref_processor()->setup_policy(clear_all_softrefs);
    const ReferenceProcessorStats& stats =
      ref_processor()->process_discovered_references(
        &is_alive, &keep_alive, &follow_stack_closure, NULL, _gc_timer);
    gc_tracer()->report_gc_reference_stats(stats);
  }

  // This is the point where the entire marking should have completed.
  assert(_marking_stack.is_empty(), "Marking should have completed");

  // Unload classes and purge the SystemDictionary.
  bool purged_class = SystemDictionary::do_unloading(&is_alive);

  // Unload nmethods.
  CodeCache::do_unloading(&is_alive, purged_class);

  // Prune dead klasses from subklass/sibling/implementor lists.
  Klass::clean_weak_klass_links(&is_alive);

  // Delete entries for dead interned strings.
  StringTable::unlink(&is_alive);

  // Clean up unreferenced symbols in symbol table.
  SymbolTable::unlink();

  gc_tracer()->report_object_count_after_gc(&is_alive);
}

void GenMarkSweep::mark_sweep_phase2() {
  // Now all live objects are marked, compute the new object addresses.

  // It is imperative that we traverse perm_gen LAST. If dead space is
  // allowed a range of dead object may get overwritten by a dead int
  // array. If perm_gen is not traversed last a Klass* may get
  // overwritten. This is fine since it is dead, but if the class has dead
  // instances we have to skip them, and in order to find their size we
  // need the Klass*!
  //
  // It is not required that we traverse spaces in the same order in
  // phase2, phase3 and phase4, but the ValidateMarkSweep live oops
  // tracking expects us to do so. See comment under phase4.

  GenCollectedHeap* gch = GenCollectedHeap::heap();

  GCTraceTime tm("phase 2", PrintGC && Verbose, true, _gc_timer);
  trace("2");

  gch->prepare_for_compaction();
}

void GenMarkSweep::mark_sweep_phase3(int level) {
  GenCollectedHeap* gch = GenCollectedHeap::heap();

  // Adjust the pointers to reflect the new locations
  GCTraceTime tm("phase 3", PrintGC && Verbose, true, _gc_timer);
  trace("3");

  // Need new claim bits for the pointer adjustment tracing.
  ClassLoaderDataGraph::clear_claimed_marks();

  // Because the closure below is created statically, we cannot
  // use OopsInGenClosure constructor which takes a generation,
  // as the Universe has not been created when the static constructors
  // are run.
  adjust_pointer_closure.set_orig_generation(gch->get_gen(level));

  gch->gen_process_strong_roots(level,
                                false, // Younger gens are not roots.
                                true,  // activate StrongRootsScope
                                false, // not scavenging
                                SharedHeap::SO_AllClasses,
                                &adjust_pointer_closure,
                                false, // do not walk code
                                &adjust_pointer_closure,
                                &adjust_klass_closure);

  // Now adjust pointers in remaining weak roots.  (All of which should
  // have been cleared if they pointed to non-surviving objects.)
  CodeBlobToOopClosure adjust_code_pointer_closure(&adjust_pointer_closure,
                                                   /*do_marking=*/ false);
  gch->gen_process_weak_roots(&adjust_pointer_closure,
                              &adjust_code_pointer_closure);

  adjust_marks();
  GenAdjustPointersClosure blk;
  gch->generation_iterate(&blk, true);
}

void GenMarkSweep::mark_sweep_phase4() {
  // All pointers are now adjusted, move objects accordingly

  // It is imperative that we traverse perm_gen first in phase4. All
  // classes must be allocated earlier than their instances, and traversing
  // perm_gen first makes sure that all Klass*s have moved to their new
  // location before any instance does a dispatch through it's klass!

  // The ValidateMarkSweep live oops tracking expects us to traverse spaces
  // in the same order in phase2, phase3 and phase4. We don't quite do that
  // here (perm_gen first rather than last), so we tell the validate code
  // to use a higher index (saved from phase2) when verifying perm_gen.
  GenCollectedHeap* gch = GenCollectedHeap::heap();

  GCTraceTime tm("phase 4", PrintGC && Verbose, true, _gc_timer);
  trace("4");

  GenCompactClosure blk;
  gch->generation_iterate(&blk, true);
}