6791168: Fix invalid code in bytecodeInterpreter that can cause gcc ICE

Summary: Fix compilation errors from latest gcc in CC_INTERP including offending missing void* cast.
Reviewed-by: xlu

src/cpu/x86/vm/assembler_x86.cpp

@@ -6943,29 +6943,32 @@ void MacroAssembler::trigfunc(char trig, int num_fpu_regs_in_use) {
 
   Label slow_case, done;
 
-  // x ?<= pi/4
-  fld_d(ExternalAddress((address)&pi_4));
-  fld_s(1);                // Stack:  X  PI/4  X
-  fabs();                  // Stack: |X| PI/4  X
-  fcmp(tmp);
-  jcc(Assembler::above, slow_case);
+  ExternalAddress pi4_adr = (address)&pi_4;
+  if (reachable(pi4_adr)) {
+    // x ?<= pi/4
+    fld_d(pi4_adr);
+    fld_s(1);                // Stack:  X  PI/4  X
+    fabs();                  // Stack: |X| PI/4  X
+    fcmp(tmp);
+    jcc(Assembler::above, slow_case);
 
-  // fastest case: -pi/4 <= x <= pi/4
-  switch(trig) {
-  case 's':
-    fsin();
-    break;
-  case 'c':
-    fcos();
-    break;
-  case 't':
-    ftan();
-    break;
-  default:
-    assert(false, "bad intrinsic");
-    break;
+    // fastest case: -pi/4 <= x <= pi/4
+    switch(trig) {
+    case 's':
+      fsin();
+      break;
+    case 'c':
+      fcos();
+      break;
+    case 't':
+      ftan();
+      break;
+    default:
+      assert(false, "bad intrinsic");
+      break;
+    }
+    jmp(done);
   }
-  jmp(done);
 
   // slow case: runtime call
   bind(slow_case);

src/cpu/x86/vm/bytecodeInterpreter_x86.inline.hpp

@@ -213,7 +213,7 @@ inline jint BytecodeInterpreter::VMintAnd(jint op1, jint op2) {
 
 inline jint BytecodeInterpreter::VMintDiv(jint op1, jint op2) {
   /* it's possible we could catch this special case implicitly */
-  if (op1 == 0x80000000 && op2 == -1) return op1;
+  if ((juint)op1 == 0x80000000 && op2 == -1) return op1;
   else return op1 / op2;
 }
 
@@ -231,7 +231,7 @@ inline jint BytecodeInterpreter::VMintOr(jint op1, jint op2) {
 
 inline jint BytecodeInterpreter::VMintRem(jint op1, jint op2) {
   /* it's possible we could catch this special case implicitly */
-  if (op1 == 0x80000000 && op2 == -1) return 0;
+  if ((juint)op1 == 0x80000000 && op2 == -1) return 0;
   else return op1 % op2;
 }
 

src/cpu/x86/vm/cppInterpreter_x86.cpp

@@ -594,7 +594,7 @@ void InterpreterGenerator::generate_counter_overflow(Label* do_continue) {
   __ call_VM(noreg, CAST_FROM_FN_PTR(address, InterpreterRuntime::frequency_counter_overflow), rax);
 
   // for c++ interpreter can rsi really be munged?
-  __ lea(state, Address(rbp, -sizeof(BytecodeInterpreter)));                               // restore state
+  __ lea(state, Address(rbp, -(int)sizeof(BytecodeInterpreter)));                               // restore state
   __ movptr(rbx, Address(state, byte_offset_of(BytecodeInterpreter, _method)));            // restore method
   __ movptr(rdi, Address(state, byte_offset_of(BytecodeInterpreter, _locals)));            // get locals pointer
 
@@ -658,7 +658,7 @@ void InterpreterGenerator::generate_stack_overflow_check(void) {
     const Address size_of_stack    (rbx, methodOopDesc::max_stack_offset());
     // Always give one monitor to allow us to start interp if sync method.
     // Any additional monitors need a check when moving the expression stack
-    const one_monitor = frame::interpreter_frame_monitor_size() * wordSize;
+    const int one_monitor = frame::interpreter_frame_monitor_size() * wordSize;
   __ load_unsigned_word(rax, size_of_stack);                            // get size of expression stack in words
   __ lea(rax, Address(noreg, rax, Interpreter::stackElementScale(), one_monitor));
   __ lea(rax, Address(rax, rdx, Interpreter::stackElementScale(), overhead_size));
@@ -1829,7 +1829,7 @@ address InterpreterGenerator::generate_normal_entry(bool synchronized) {
   Label unwind_and_forward;
 
   // restore state pointer.
-  __ lea(state, Address(rbp,  -sizeof(BytecodeInterpreter)));
+  __ lea(state, Address(rbp,  -(int)sizeof(BytecodeInterpreter)));
 
   __ movptr(rbx, STATE(_method));                       // get method
 #ifdef _LP64
@@ -1877,14 +1877,14 @@ address InterpreterGenerator::generate_normal_entry(bool synchronized) {
 
   // The FPU stack is clean if UseSSE >= 2 but must be cleaned in other cases
   if (UseSSE < 2) {
-    __ lea(state, Address(rbp,  -sizeof(BytecodeInterpreter)));
+    __ lea(state, Address(rbp,  -(int)sizeof(BytecodeInterpreter)));
     __ movptr(rbx, STATE(_result._to_call._callee));                   // get method just executed
     __ movl(rcx, Address(rbx, methodOopDesc::result_index_offset()));
     __ cmpl(rcx, AbstractInterpreter::BasicType_as_index(T_FLOAT));    // Result stub address array index
     __ jcc(Assembler::equal, do_float);
     __ cmpl(rcx, AbstractInterpreter::BasicType_as_index(T_DOUBLE));    // Result stub address array index
     __ jcc(Assembler::equal, do_double);
-#ifdef COMPILER2
+#if !defined(_LP64) || defined(COMPILER1) || !defined(COMPILER2)
     __ empty_FPU_stack();
 #endif // COMPILER2
     __ jmp(done_conv);
@@ -1928,7 +1928,7 @@ address InterpreterGenerator::generate_normal_entry(bool synchronized) {
 
   // Restore rsi/r13 as compiled code may not preserve it
 
-  __ lea(state, Address(rbp,  -sizeof(BytecodeInterpreter)));
+  __ lea(state, Address(rbp,  -(int)sizeof(BytecodeInterpreter)));
 
   // restore stack to what we had when we left (in case i2c extended it)
 
@@ -1942,7 +1942,7 @@ address InterpreterGenerator::generate_normal_entry(bool synchronized) {
 #else
   __ movptr(rcx, STATE(_thread));                       // get thread
   __ cmpptr(Address(rcx, Thread::pending_exception_offset()), (int32_t)NULL_WORD);
-#endif / __LP64
+#endif // _LP64
   __ jcc(Assembler::notZero, return_with_exception);
 
   // get method just executed

src/cpu/x86/vm/frame_x86.inline.hpp

@@ -139,7 +139,7 @@ inline address* frame::native_param_addr(int idx) const { return (address*) addr
 #ifdef CC_INTERP
 
 inline interpreterState frame::get_interpreterState() const {
-  return ((interpreterState)addr_at( -sizeof(BytecodeInterpreter)/wordSize ));
+  return ((interpreterState)addr_at( -((int)sizeof(BytecodeInterpreter))/wordSize ));
 }
 
 inline intptr_t*    frame::sender_sp()        const {

src/cpu/x86/vm/interp_masm_x86_64.cpp

@@ -30,7 +30,7 @@
 
 #ifdef CC_INTERP
 void InterpreterMacroAssembler::get_method(Register reg) {
-  movptr(reg, Address(rbp, -(sizeof(BytecodeInterpreter) + 2 * wordSize)));
+  movptr(reg, Address(rbp, -((int)sizeof(BytecodeInterpreter) + 2 * wordSize)));
   movptr(reg, Address(reg, byte_offset_of(BytecodeInterpreter, _method)));
 }
 #endif // CC_INTERP

src/cpu/x86/vm/sharedRuntime_x86_64.cpp

@@ -2954,10 +2954,16 @@ void SharedRuntime::generate_uncommon_trap_blob() {
   __ pushptr(Address(rcx, 0));     // Save return address
   __ enter();                      // Save old & set new rbp
   __ subptr(rsp, rbx);             // Prolog
+#ifdef CC_INTERP
+  __ movptr(Address(rbp,
+                  -(sizeof(BytecodeInterpreter)) + in_bytes(byte_offset_of(BytecodeInterpreter, _sender_sp))),
+            sender_sp); // Make it walkable
+#else // CC_INTERP
   __ movptr(Address(rbp, frame::interpreter_frame_sender_sp_offset * wordSize),
             sender_sp);            // Make it walkable
   // This value is corrected by layout_activation_impl
   __ movptr(Address(rbp, frame::interpreter_frame_last_sp_offset * wordSize), (int32_t)NULL_WORD );
+#endif // CC_INTERP
   __ mov(sender_sp, rsp);          // Pass sender_sp to next frame
   __ addptr(rsi, wordSize);        // Bump array pointer (sizes)
   __ addptr(rcx, wordSize);        // Bump array pointer (pcs)

src/share/vm/interpreter/bytecodeInterpreter.cpp

@@ -163,7 +163,7 @@
 #ifdef USELABELS
 // Have to do this dispatch this way in C++ because otherwise gcc complains about crossing an
 // initialization (which is is the initialization of the table pointer...)
-#define DISPATCH(opcode) goto *dispatch_table[opcode]
+#define DISPATCH(opcode) goto *(void*)dispatch_table[opcode]
 #define CONTINUE {                              \
         opcode = *pc;                           \
         DO_UPDATE_INSTRUCTION_COUNT(opcode);    \
@@ -341,7 +341,7 @@
  */
 #undef CHECK_NULL
 #define CHECK_NULL(obj_)                                                 \
-    if ((obj_) == 0) {                                                   \
+    if ((obj_) == NULL) {                                                \
         VM_JAVA_ERROR(vmSymbols::java_lang_NullPointerException(), "");  \
     }
 
@@ -1362,7 +1362,7 @@ run:
 
 #define NULL_COMPARISON_NOT_OP(name)                                         \
       CASE(_if##name): {                                                     \
-          int skip = (!(STACK_OBJECT(-1) == 0))                              \
+          int skip = (!(STACK_OBJECT(-1) == NULL))                           \
                       ? (int16_t)Bytes::get_Java_u2(pc + 1) : 3;             \
           address branch_pc = pc;                                            \
           UPDATE_PC_AND_TOS(skip, -1);                                       \
@@ -1372,7 +1372,7 @@ run:
 
 #define NULL_COMPARISON_OP(name)                                             \
       CASE(_if##name): {                                                     \
-          int skip = ((STACK_OBJECT(-1) == 0))                               \
+          int skip = ((STACK_OBJECT(-1) == NULL))                            \
                       ? (int16_t)Bytes::get_Java_u2(pc + 1) : 3;             \
           address branch_pc = pc;                                            \
           UPDATE_PC_AND_TOS(skip, -1);                                       \

src/share/vm/interpreter/bytecodeInterpreter.hpp

@@ -66,7 +66,6 @@ friend class CppInterpreterGenerator;
 friend class InterpreterGenerator;
 friend class InterpreterMacroAssembler;
 friend class frame;
-friend class SharedRuntime;
 friend class VMStructs;
 
 public: