src/hotspot/cpu/x86/sharedRuntime_x86_32.cpp

*** 2005,2020 ****
      __ orptr(swap_reg, Address(obj_reg, oopDesc::mark_offset_in_bytes()));
  
      // Save (object->mark() | 1) into BasicLock's displaced header
      __ movptr(Address(lock_reg, mark_word_offset), swap_reg);
  
-     if (os::is_MP()) {
-       __ lock();
-     }
- 
      // src -> dest iff dest == rax, else rax, <- dest
      // *obj_reg = lock_reg iff *obj_reg == rax, else rax, = *(obj_reg)
      __ cmpxchgptr(lock_reg, Address(obj_reg, oopDesc::mark_offset_in_bytes()));
      __ jcc(Assembler::equal, lock_done);
  
      // Test if the oopMark is an obvious stack pointer, i.e.,
      //  1) (mark & 3) == 0, and
--- 2005,2017 ----
      __ orptr(swap_reg, Address(obj_reg, oopDesc::mark_offset_in_bytes()));
  
      // Save (object->mark() | 1) into BasicLock's displaced header
      __ movptr(Address(lock_reg, mark_word_offset), swap_reg);
  
      // src -> dest iff dest == rax, else rax, <- dest
      // *obj_reg = lock_reg iff *obj_reg == rax, else rax, = *(obj_reg)
+     __ lock();
      __ cmpxchgptr(lock_reg, Address(obj_reg, oopDesc::mark_offset_in_bytes()));
      __ jcc(Assembler::equal, lock_done);
  
      // Test if the oopMark is an obvious stack pointer, i.e.,
      //  1) (mark & 3) == 0, and
*** 2089,2099 ****
    //     VM thread changes sync state to synchronizing and suspends threads for GC.
    //     Thread A is resumed to finish this native method, but doesn't block here since it
    //     didn't see any synchronization is progress, and escapes.
    __ movl(Address(thread, JavaThread::thread_state_offset()), _thread_in_native_trans);
  
-   if(os::is_MP()) {
      if (UseMembar) {
        // Force this write out before the read below
        __ membar(Assembler::Membar_mask_bits(
             Assembler::LoadLoad | Assembler::LoadStore |
             Assembler::StoreLoad | Assembler::StoreStore));
--- 2086,2095 ----
*** 2102,2112 ****
        // We use the current thread pointer to calculate a thread specific
        // offset to write to within the page. This minimizes bus traffic
        // due to cache line collision.
        __ serialize_memory(thread, rcx);
      }
-   }
  
    if (AlwaysRestoreFPU) {
      // Make sure the control word is correct.
      __ fldcw(ExternalAddress(StubRoutines::addr_fpu_cntrl_wrd_std()));
    }
--- 2098,2107 ----
*** 2197,2212 ****
  
      // get address of the stack lock
      __ lea(rax, Address(rbp, lock_slot_rbp_offset));
  
      // Atomic swap old header if oop still contains the stack lock
-     if (os::is_MP()) {
-     __ lock();
-     }
- 
      // src -> dest iff dest == rax, else rax, <- dest
      // *obj_reg = rbx, iff *obj_reg == rax, else rax, = *(obj_reg)
      __ cmpxchgptr(rbx, Address(obj_reg, oopDesc::mark_offset_in_bytes()));
      __ jcc(Assembler::notEqual, slow_path_unlock);
  
      // slow path re-enters here
      __ bind(unlock_done);
--- 2192,2204 ----
  
      // get address of the stack lock
      __ lea(rax, Address(rbp, lock_slot_rbp_offset));
  
      // Atomic swap old header if oop still contains the stack lock
      // src -> dest iff dest == rax, else rax, <- dest
      // *obj_reg = rbx, iff *obj_reg == rax, else rax, = *(obj_reg)
+     __ lock();
      __ cmpxchgptr(rbx, Address(obj_reg, oopDesc::mark_offset_in_bytes()));
      __ jcc(Assembler::notEqual, slow_path_unlock);
  
      // slow path re-enters here
      __ bind(unlock_done);