Shenandoah: Merging gc state tests for two dependent loads

Shenandoah will merge two gc state tests (from two LRBs) if they satisfy certain control flow constraint (in ShenandoahBarrierC2Support::merge_back_to_back_tests). I think there could be an issue if the two loads the two LRBs guard are dependent.

To reproduce, I ran java -XX:-UseCompressedOops -XX:+UseShenandoahGC -XX:CompileCommand=print,*ThreadLocal.set -jar SPECjvm2008.jar -coe -ict -ikv -i 2 -bt 8 derby

The C2 outcome for ThreadLocal.set has:

..
  0: mov 0x268(%r15),%rsi ; Thread t = Thread.currentThread(); // get oop handle
  1: mov (%rsi),%r12 ; Thread t = Thread.currentThread(); // get oop out of oop handle
  2: mov 0x58(%r12),%rbx ; ThreadLocalMap map = getMap(t);
  3: nopl 0x0(%rax)
  4: testb $0x1,0x20(%r15) ; gc state test is too late here
  5: jne 0x00007f0a3508f6e7
..

There is no barrier between line 1 and line 2. There was a barrier, but it was merged with the barrier for line 2, (the gc state tests are merged) and the merged test is placed at line 4. The problem is line 2 could visit from-space object and get outdated data.

If I comment out the call to ShenandoahBarrierC2Support::merge_back_to_back_tests, the outcome is more like what I expected:

..
  0: mov 0x268(%r15),%rsi
  1: mov (%rsi),%r12
  2: nopw 0x0(%rax,%rax,1)
  3: testb $0x1,0x20(%r15) ; first gc state test
  4: jne 0x00007ff55d077207
  5: mov 0x58(%r12),%rbx
  6: testb $0x1,0x20(%r15) ; second gc state test
  7: jne 0x00007ff55d077235
..

I think the merging didn't consider that the second load could use the result from the first load (in this case, r12). Can anyone confirm if this is an issue?