/*

 * Copyright (c) 1997, 2011, Oracle and/or its affiliates. All rights reserved.

 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

 *

 * This code is free software; you can redistribute it and/or modify it

 * under the terms of the GNU General Public License version 2 only, as

 * published by the Free Software Foundation.

 *

 * This code is distributed in the hope that it will be useful, but WITHOUT

 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

 * version 2 for more details (a copy is included in the LICENSE file that

 * accompanied this code).

 *

 * You should have received a copy of the GNU General Public License version

 * 2 along with this work; if not, write to the Free Software Foundation,

 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

 *

 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

 * or visit www.oracle.com if you need additional information or have any

 * questions.

 *

 */

#include "precompiled.hpp"

#include "classfile/systemDictionary.hpp"

#include "code/codeCache.hpp"

#include "code/icBuffer.hpp"

#include "code/nmethod.hpp"

#include "code/pcDesc.hpp"

#include "code/scopeDesc.hpp"

#include "gc_interface/collectedHeap.hpp"

#include "interpreter/interpreter.hpp"

#include "memory/resourceArea.hpp"

#include "memory/universe.inline.hpp"

#include "oops/oop.inline.hpp"

#include "oops/symbol.hpp"

#include "runtime/compilationPolicy.hpp"

#include "runtime/deoptimization.hpp"

#include "runtime/frame.inline.hpp"

#include "runtime/interfaceSupport.hpp"

#include "runtime/mutexLocker.hpp"

#include "runtime/osThread.hpp"

#include "runtime/safepoint.hpp"

#include "runtime/signature.hpp"

#include "runtime/stubCodeGenerator.hpp"

#include "runtime/stubRoutines.hpp"

#include "runtime/sweeper.hpp"

#include "runtime/synchronizer.hpp"

#include "services/runtimeService.hpp"

#include "utilities/events.hpp"

#ifdef TARGET_ARCH_x86

# include "nativeInst_x86.hpp"

# include "vmreg_x86.inline.hpp"

#endif

#ifdef TARGET_ARCH_sparc

# include "nativeInst_sparc.hpp"

# include "vmreg_sparc.inline.hpp"

#endif

#ifdef TARGET_ARCH_zero

# include "nativeInst_zero.hpp"

# include "vmreg_zero.inline.hpp"

#endif

#ifdef TARGET_ARCH_arm

# include "nativeInst_arm.hpp"

# include "vmreg_arm.inline.hpp"

#endif

#ifdef TARGET_ARCH_ppc

# include "nativeInst_ppc.hpp"

# include "vmreg_ppc.inline.hpp"

#endif

#ifdef TARGET_OS_FAMILY_linux

# include "thread_linux.inline.hpp"

#endif

#ifdef TARGET_OS_FAMILY_solaris

# include "thread_solaris.inline.hpp"

#endif

#ifdef TARGET_OS_FAMILY_windows

# include "thread_windows.inline.hpp"

#endif

#ifndef SERIALGC

#include "gc_implementation/concurrentMarkSweep/concurrentMarkSweepThread.hpp"

#include "gc_implementation/shared/concurrentGCThread.hpp"

#endif

#ifdef COMPILER1

#include "c1/c1_globals.hpp"

#endif

// --------------------------------------------------------------------------------------------------

// Implementation of Safepoint begin/end

SafepointSynchronize::SynchronizeState volatile SafepointSynchronize::_state = SafepointSynchronize::_not_synchronized;

volatile int  SafepointSynchronize::_waiting_to_block = 0;

volatile int SafepointSynchronize::_safepoint_counter = 0;

long  SafepointSynchronize::_end_of_last_safepoint = 0;

static volatile int PageArmed = 0 ;        // safepoint polling page is RO|RW vs PROT_NONE

static volatile int TryingToBlock = 0 ;    // proximate value -- for advisory use only

static bool timeout_error_printed = false;

// Roll all threads forward to a safepoint and suspend them all

void SafepointSynchronize::begin() {

  Thread* myThread = Thread::current();

  assert(myThread->is_VM_thread(), "Only VM thread may execute a safepoint");

  if (PrintSafepointStatistics || PrintSafepointStatisticsTimeout > 0) {

    _safepoint_begin_time = os::javaTimeNanos();

    _ts_of_current_safepoint = tty->time_stamp().seconds();

  }

#ifndef SERIALGC

  if (UseConcMarkSweepGC) {

    // In the future we should investigate whether CMS can use the

    // more-general mechanism below.  DLD (01/05).

    ConcurrentMarkSweepThread::synchronize(false);

  } else if (UseG1GC) {

    ConcurrentGCThread::safepoint_synchronize();

  }

#endif // SERIALGC

  // By getting the Threads_lock, we assure that no threads are about to start or

  // exit. It is released again in SafepointSynchronize::end().

  Threads_lock->lock();

  assert( _state == _not_synchronized, "trying to safepoint synchronize with wrong state");

  int nof_threads = Threads::number_of_threads();

  if (TraceSafepoint) {

    tty->print_cr("Safepoint synchronization initiated. (%d)", nof_threads);

  }

  RuntimeService::record_safepoint_begin();

  {

  MutexLocker mu(Safepoint_lock);

  // Set number of threads to wait for, before we initiate the callbacks

  _waiting_to_block = nof_threads;

  TryingToBlock     = 0 ;

  int still_running = nof_threads;

  // Save the starting time, so that it can be compared to see if this has taken

  // too long to complete.

  jlong safepoint_limit_time;

  timeout_error_printed = false;

  // PrintSafepointStatisticsTimeout can be specified separately. When

  // specified, PrintSafepointStatistics will be set to true in

  // deferred_initialize_stat method. The initialization has to be done

  // early enough to avoid any races. See bug 6880029 for details.

  if (PrintSafepointStatistics || PrintSafepointStatisticsTimeout > 0) {

    deferred_initialize_stat();

  }

  // Begin the process of bringing the system to a safepoint.

  // Java threads can be in several different states and are

  // stopped by different mechanisms:

  //

  //  1. Running interpreted

  //     The interpeter dispatch table is changed to force it to

  //     check for a safepoint condition between bytecodes.

  //  2. Running in native code

  //     When returning from the native code, a Java thread must check

  //     the safepoint _state to see if we must block.  If the

  //     VM thread sees a Java thread in native, it does

  //     not wait for this thread to block.  The order of the memory

  //     writes and reads of both the safepoint state and the Java

  //     threads state is critical.  In order to guarantee that the

  //     memory writes are serialized with respect to each other,

  //     the VM thread issues a memory barrier instruction

  //     (on MP systems).  In order to avoid the overhead of issuing

  //     a memory barrier for each Java thread making native calls, each Java

  //     thread performs a write to a single memory page after changing

  //     the thread state.  The VM thread performs a sequence of

  //     mprotect OS calls which forces all previous writes from all

  //     Java threads to be serialized.  This is done in the

  //     os::serialize_thread_states() call.  This has proven to be

  //     much more efficient than executing a membar instruction

  //     on every call to native code.

  //  3. Running compiled Code

  //     Compiled code reads a global (Safepoint Polling) page that

  //     is set to fault if we are trying to get to a safepoint.

  //  4. Blocked

  //     A thread which is blocked will not be allowed to return from the

  //     block condition until the safepoint operation is complete.

  //  5. In VM or Transitioning between states

  //     If a Java thread is currently running in the VM or transitioning

  //     between states, the safepointing code will wait for the thread to

  //     block itself when it attempts transitions to a new state.

  //

  _state            = _synchronizing;

  OrderAccess::fence();

  // Flush all thread states to memory

  if (!UseMembar) {

    os::serialize_thread_states();

  }

  // Make interpreter safepoint aware

  Interpreter::notice_safepoints();

  if (UseCompilerSafepoints && DeferPollingPageLoopCount < 0) {

    // Make polling safepoint aware

    guarantee (PageArmed == 0, "invariant") ;

    PageArmed = 1 ;

    os::make_polling_page_unreadable();

  }

  // Consider using active_processor_count() ... but that call is expensive.

  int ncpus = os::processor_count() ;

#ifdef ASSERT

  for (JavaThread *cur = Threads::first(); cur != NULL; cur = cur->next()) {

    assert(cur->safepoint_state()->is_running(), "Illegal initial state");

  }

#endif // ASSERT

  if (SafepointTimeout)

    safepoint_limit_time = os::javaTimeNanos() + (jlong)SafepointTimeoutDelay * MICROUNITS;

  // Iterate through all threads until it have been determined how to stop them all at a safepoint

  unsigned int iterations = 0;

  int steps = 0 ;

  while(still_running > 0) {

    for (JavaThread *cur = Threads::first(); cur != NULL; cur = cur->next()) {

      assert(!cur->is_ConcurrentGC_thread(), "A concurrent GC thread is unexpectly being suspended");

      ThreadSafepointState *cur_state = cur->safepoint_state();

      if (cur_state->is_running()) {

        cur_state->examine_state_of_thread();

        if (!cur_state->is_running()) {

           still_running--;

           // consider adjusting steps downward:

           //   steps = 0

           //   steps -= NNN

           //   steps >>= 1

           //   steps = MIN(steps, 2000-100)

           //   if (iterations != 0) steps -= NNN

        }

        if (TraceSafepoint && Verbose) cur_state->print();

      }

    }

    if (PrintSafepointStatistics && iterations == 0) {

      begin_statistics(nof_threads, still_running);

    }

    if (still_running > 0) {

      // Check for if it takes to long

      if (SafepointTimeout && safepoint_limit_time < os::javaTimeNanos()) {

        print_safepoint_timeout(_spinning_timeout);

      }

      // Spin to avoid context switching.

      // There's a tension between allowing the mutators to run (and rendezvous)

      // vs spinning.  As the VM thread spins, wasting cycles, it consumes CPU that

      // a mutator might otherwise use profitably to reach a safepoint.  Excessive

      // spinning by the VM thread on a saturated system can increase rendezvous latency.

      // Blocking or yielding incur their own penalties in the form of context switching

      // and the resultant loss of $ residency.

      //

      // Further complicating matters is that yield() does not work as naively expected

      // on many platforms -- yield() does not guarantee that any other ready threads

      // will run.   As such we revert yield_all() after some number of iterations.

      // Yield_all() is implemented as a short unconditional sleep on some platforms.

      // Typical operating systems round a "short" sleep period up to 10 msecs, so sleeping

      // can actually increase the time it takes the VM thread to detect that a system-wide

      // stop-the-world safepoint has been reached.  In a pathological scenario such as that

      // described in CR6415670 the VMthread may sleep just before the mutator(s) become safe.

      // In that case the mutators will be stalled waiting for the safepoint to complete and the

      // the VMthread will be sleeping, waiting for the mutators to rendezvous.  The VMthread

      // will eventually wake up and detect that all mutators are safe, at which point

      // we'll again make progress.

      //

      // Beware too that that the VMThread typically runs at elevated priority.

      // Its default priority is higher than the default mutator priority.

      // Obviously, this complicates spinning.

      //

      // Note too that on Windows XP SwitchThreadTo() has quite different behavior than Sleep(0).

      // Sleep(0) will _not yield to lower priority threads, while SwitchThreadTo() will.

      //

      // See the comments in synchronizer.cpp for additional remarks on spinning.

      //

      // In the future we might:

      // 1. Modify the safepoint scheme to avoid potentally unbounded spinning.

      //    This is tricky as the path used by a thread exiting the JVM (say on

      //    on JNI call-out) simply stores into its state field.  The burden

      //    is placed on the VM thread, which must poll (spin).

      // 2. Find something useful to do while spinning.  If the safepoint is GC-related

      //    we might aggressively scan the stacks of threads that are already safe.

      // 3. Use Solaris schedctl to examine the state of the still-running mutators.

      //    If all the mutators are ONPROC there's no reason to sleep or yield.

      // 4. YieldTo() any still-running mutators that are ready but OFFPROC.

      // 5. Check system saturation.  If the system is not fully saturated then

      //    simply spin and avoid sleep/yield.

      // 6. As still-running mutators rendezvous they could unpark the sleeping

      //    VMthread.  This works well for still-running mutators that become

      //    safe.  The VMthread must still poll for mutators that call-out.

      // 7. Drive the policy on time-since-begin instead of iterations.

      // 8. Consider making the spin duration a function of the # of CPUs:

      //    Spin = (((ncpus-1) * M) + K) + F(still_running)

      //    Alternately, instead of counting iterations of the outer loop

      //    we could count the # of threads visited in the inner loop, above.

      // 9. On windows consider using the return value from SwitchThreadTo()

      //    to drive subsequent spin/SwitchThreadTo()/Sleep(N) decisions.

      if (UseCompilerSafepoints && int(iterations) == DeferPollingPageLoopCount) {

         guarantee (PageArmed == 0, "invariant") ;

         PageArmed = 1 ;

         os::make_polling_page_unreadable();

      }

      // Instead of (ncpus > 1) consider either (still_running < (ncpus + EPSILON)) or

      // ((still_running + _waiting_to_block - TryingToBlock)) < ncpus)

      ++steps ;

      if (ncpus > 1 && steps < SafepointSpinBeforeYield) {

        SpinPause() ;     // MP-Polite spin

      } else

      if (steps < DeferThrSuspendLoopCount) {

        os::NakedYield() ;

      } else {

        os::yield_all(steps) ;

        // Alternately, the VM thread could transiently depress its scheduling priority or

        // transiently increase the priority of the tardy mutator(s).

      }

      iterations ++ ;

    }

    assert(iterations < (uint)max_jint, "We have been iterating in the safepoint loop too long");

  }

  assert(still_running == 0, "sanity check");

  if (PrintSafepointStatistics) {

    update_statistics_on_spin_end();

  }

  // wait until all threads are stopped

  while (_waiting_to_block > 0) {

    if (TraceSafepoint) tty->print_cr("Waiting for %d thread(s) to block", _waiting_to_block);

    if (!SafepointTimeout || timeout_error_printed) {

      Safepoint_lock->wait(true);  // true, means with no safepoint checks

    } else {

      // Compute remaining time

      jlong remaining_time = safepoint_limit_time - os::javaTimeNanos();

      // If there is no remaining time, then there is an error

      if (remaining_time < 0 || Safepoint_lock->wait(true, remaining_time / MICROUNITS)) {

        print_safepoint_timeout(_blocking_timeout);

      }

    }

  }

  assert(_waiting_to_block == 0, "sanity check");

#ifndef PRODUCT

  if (SafepointTimeout) {

    jlong current_time = os::javaTimeNanos();

    if (safepoint_limit_time < current_time) {

      tty->print_cr("# SafepointSynchronize: Finished after "

                    INT64_FORMAT_W(6) " ms",

                    ((current_time - safepoint_limit_time) / MICROUNITS +

                     SafepointTimeoutDelay));

    }

  }

#endif

  assert((_safepoint_counter & 0x1) == 0, "must be even");

  assert(Threads_lock->owned_by_self(), "must hold Threads_lock");

  _safepoint_counter ++;

  // Record state

  _state = _synchronized;

  OrderAccess::fence();

  if (TraceSafepoint) {

    VM_Operation *op = VMThread::vm_operation();

    tty->print_cr("Entering safepoint region: %s", (op != NULL) ? op->name() : "no vm operation");

  }

  RuntimeService::record_safepoint_synchronized();

  if (PrintSafepointStatistics) {

    update_statistics_on_sync_end(os::javaTimeNanos());

  }

  // Call stuff that needs to be run when a safepoint is just about to be completed

  do_cleanup_tasks();

  if (PrintSafepointStatistics) {

    // Record how much time spend on the above cleanup tasks

    update_statistics_on_cleanup_end(os::javaTimeNanos());

  }

  }

}

// Wake up all threads, so they are ready to resume execution after the safepoint

// operation has been carried out

void SafepointSynchronize::end() {

  assert(Threads_lock->owned_by_self(), "must hold Threads_lock");

  assert((_safepoint_counter & 0x1) == 1, "must be odd");

  _safepoint_counter ++;

  // memory fence isn't required here since an odd _safepoint_counter

  // value can do no harm and a fence is issued below anyway.

  DEBUG_ONLY(Thread* myThread = Thread::current();)

  assert(myThread->is_VM_thread(), "Only VM thread can execute a safepoint");

  if (PrintSafepointStatistics) {

    end_statistics(os::javaTimeNanos());

  }

#ifdef ASSERT

  // A pending_exception cannot be installed during a safepoint.  The threads

  // may install an async exception after they come back from a safepoint into

  // pending_exception after they unblock.  But that should happen later.

  for(JavaThread *cur = Threads::first(); cur; cur = cur->next()) {

    assert (!(cur->has_pending_exception() &&

              cur->safepoint_state()->is_at_poll_safepoint()),

            "safepoint installed a pending exception");

  }

#endif // ASSERT

  if (PageArmed) {

    // Make polling safepoint aware

    os::make_polling_page_readable();

    PageArmed = 0 ;

  }

  // Remove safepoint check from interpreter

  Interpreter::ignore_safepoints();

  {

    MutexLocker mu(Safepoint_lock);

    assert(_state == _synchronized, "must be synchronized before ending safepoint synchronization");

    // Set to not synchronized, so the threads will not go into the signal_thread_blocked method

    // when they get restarted.

    _state = _not_synchronized;

    OrderAccess::fence();

    if (TraceSafepoint) {

       tty->print_cr("Leaving safepoint region");

    }

    // Start suspended threads

    for(JavaThread *current = Threads::first(); current; current = current->next()) {

      // A problem occurring on Solaris is when attempting to restart threads

      // the first #cpus - 1 go well, but then the VMThread is preempted when we get

      // to the next one (since it has been running the longest).  We then have

      // to wait for a cpu to become available before we can continue restarting

      // threads.

      // FIXME: This causes the performance of the VM to degrade when active and with

      // large numbers of threads.  Apparently this is due to the synchronous nature

      // of suspending threads.

      //

      // TODO-FIXME: the comments above are vestigial and no longer apply.

      // Furthermore, using solaris' schedctl in this particular context confers no benefit

      if (VMThreadHintNoPreempt) {

        os::hint_no_preempt();

      }

      ThreadSafepointState* cur_state = current->safepoint_state();

      assert(cur_state->type() != ThreadSafepointState::_running, "Thread not suspended at safepoint");

      cur_state->restart();

      assert(cur_state->is_running(), "safepoint state has not been reset");

    }

    RuntimeService::record_safepoint_end();

    // Release threads lock, so threads can be created/destroyed again. It will also starts all threads

    // blocked in signal_thread_blocked

    Threads_lock->unlock();

  }

#ifndef SERIALGC

  // If there are any concurrent GC threads resume them.

  if (UseConcMarkSweepGC) {

    ConcurrentMarkSweepThread::desynchronize(false);

  } else if (UseG1GC) {

    ConcurrentGCThread::safepoint_desynchronize();

  }

#endif // SERIALGC

  // record this time so VMThread can keep track how much time has elasped

  // since last safepoint.

  _end_of_last_safepoint = os::javaTimeMillis();

}

bool SafepointSynchronize::is_cleanup_needed() {

  // Need a safepoint if some inline cache buffers is non-empty

  if (!InlineCacheBuffer::is_empty()) return true;

  return false;

}

// Various cleaning tasks that should be done periodically at safepoints

void SafepointSynchronize::do_cleanup_tasks() {

  {

    TraceTime t1("deflating idle monitors", TraceSafepointCleanupTime);

    ObjectSynchronizer::deflate_idle_monitors();

  }

  {

    TraceTime t2("updating inline caches", TraceSafepointCleanupTime);

    InlineCacheBuffer::update_inline_caches();

  }

  {

    TraceTime t3("compilation policy safepoint handler", TraceSafepointCleanupTime);

    CompilationPolicy::policy()->do_safepoint_work();

  }

  TraceTime t4("sweeping nmethods", TraceSafepointCleanupTime);

  NMethodSweeper::scan_stacks();

  // rotate log files?