# HG changeset patch
# User Jin
# Date 1462298232 14400
# Node ID 76df293e57aad419e9c6fd290b537ebcbffbf120
# Parent  52672a450193dd8ab6185b5a4e9a691a9249a577
[3A2000-B/4way] ParallelOldGC: add SYNC in BlockData

When running on 3A2000B-4way, compiler crashes in Full GC.

In BlockData, multiple threads writes to the same
memory location without explict synchronization,

Sync is required for access correctness.

Ref:  http://10.2.5.21:8000/projects/java/wiki/Jgj-log-2016-5-4_

[List.java]

public class List extends Thread {
    public List sub[];
    public List next;

    public List() {
        this.next = null;
    }

    public void insert(int n) {
        List p = new List();
        p.next = this.next;
        this.next = p;

        p.sub = new List[404];
        for (int i = 0; i < 404; i++)
           p.sub[i] = new List();
    }

    public void run()
    {
        int i = 0;
        while(true)
            insert(i++);
    }

    public static void main(String[] args) throws Exception {
        int N = 16;
        Thread[] threads = new Thread[N];

        for (int i = 0; i < N; i++)
        {
          List th = new List();
          threads[i] = th;
          th.start();
        }
        System.err.println(N + " threads Created.");

        for (int i = 0; i < N; i++)
        {
          threads[i].join();
        }
        System.err.println("Done.");
    }
}

[1.sh]

i=1

while true; do

echo === $i ===
date

#/opt/j2sdk-image-test/bin/java \
time \
numactl --cpunodebind=0 --membind=0 \
/mnt/j2sdk-image/bin/java \
  -Xmx62M -Xms62M \
  -XX:+PrintGC \
  -XX:-UseCompressedOops \
  -XX:+UnlockDiagnosticVMOptions \
  -XX:ParallelGCThreads=2 \
  -XX:+ScavengeBeforeFullGC \
  -XX:+VerifyAfterGC \
  List &
  #-XX:+UseNUMA \

sleep 10

killall -9 java

i=$(($i+1))
done

Effect:
* Before: crashed in VerifyAfterGC
* After: 50 times OK
* compiler(-bt 16): OK, 97.86 ops/m%

diff -r 52672a450193 -r 76df293e57aa src/share/vm/gc_implementation/parallelScavenge/psParallelCompact.cpp
--- a/src/share/vm/gc_implementation/parallelScavenge/psParallelCompact.cpp	Fri Apr 29 12:46:05 2016 -0400
+++ b/src/share/vm/gc_implementation/parallelScavenge/psParallelCompact.cpp	Tue May 03 13:57:12 2016 -0400
@@ -3233,6 +3233,13 @@
     if (new_block != cur_block) {
       cur_block = new_block;
       sd.block(cur_block)->set_offset(bitmap->bits_to_words(live_bits));
+
+#ifdef MIPS64
+      /* 2016/5/4 Jin: On 3A2000-B, when multiple threads write to
+         the same memory location without explict synchronization,
+         sync is required for access correctness. */
+      OrderAccess::fence();
+#endif
     }
 
     const size_t end_bit = bitmap->find_obj_end(beg_bit, range_end);