[AArch64] Implement INIT/ADJUST_TRAMPOLINE

Add support for llvm.init.trampoline and llvm.adjust.trampoline intrinsics for
AArch64.

Fixes #65573
Updates #27174
Updates #66157

Author: ceseo

compiler-rt/lib/builtins/README.txt

@@ -272,6 +272,11 @@ switch32
 switch8
 switchu8
 
+// This function generates a custom trampoline function with the specific
+// realFunc and localsPtr values.
+void __trampoline_setup(uint32_t* trampOnStack, int trampSizeAllocated,
+                        const void* realFunc, void* localsPtr);
+
 // There is no C interface to the *_vfp_d8_d15_regs functions.  There are
 // called in the prolog and epilog of Thumb1 functions.  When the C++ ABI use
 // SJLJ for exceptions, each function with a catch clause or destructors needs

compiler-rt/lib/builtins/trampoline_setup.c

@@ -41,3 +41,30 @@ COMPILER_RT_ABI void __trampoline_setup(uint32_t *trampOnStack,
   __clear_cache(trampOnStack, &trampOnStack[10]);
 }
 #endif // __powerpc__ && !defined(__powerpc64__)
+
+// The AArch64 compiler generates calls to __trampoline_setup() when creating
+// trampoline functions on the stack for use with nested functions.
+// This function creates a custom 20-byte trampoline function on the stack
+// which loads x18 with a pointer to the outer function's locals
+// and then jumps to the target nested function.
+
+#if __aarch64__
+COMPILER_RT_ABI void __trampoline_setup(uint32_t *trampOnStack,
+                                        int trampSizeAllocated,
+                                        const void *realFunc, void *localsPtr) {
+  // should never happen, but if compiler did not allocate
+  // enough space on stack for the trampoline, abort
+  if (trampSizeAllocated < 20)
+    compilerrt_abort();
+
+  // create trampoline
+  trampOnStack[0] = 0x580000b1; // ldr x17, realFunc
+  trampOnStack[1] = 0x580000d2; // ldr x18, localsPtr
+  trampOnStack[2] = 0xd61f0220; // br x17
+  trampOnStack[3] = (uint32_t)realFunc;
+  trampOnStack[4] = (uint32_t)localsPtr;
+
+  // clear instruction cache
+  __clear_cache(trampOnStack, &trampOnStack[10]);
+}
+#endif // __aarch64__

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -5946,6 +5946,56 @@ static SDValue LowerFLDEXP(SDValue Op, SelectionDAG &DAG) {
   return Final;
 }
 
+SDValue AArch64TargetLowering::LowerADJUST_TRAMPOLINE(SDValue Op,
+                                                      SelectionDAG &DAG) const {
+  // Note: x18 cannot be used for the Nest parameter on Windows and macOS.
+  if (Subtarget->isTargetDarwin() || Subtarget->isTargetWindows())
+    report_fatal_error(
+        "ADJUST_TRAMPOLINE operation is only supported on Linux.");
+
+  return Op.getOperand(0);
+}
+
+SDValue AArch64TargetLowering::LowerINIT_TRAMPOLINE(SDValue Op,
+                                                    SelectionDAG &DAG) const {
+
+  // Note: x18 cannot be used for the Nest parameter on Windows and macOS.
+  if (Subtarget->isTargetDarwin() || Subtarget->isTargetWindows())
+    report_fatal_error("INIT_TRAMPOLINE operation is only supported on Linux.");
+
+  SDValue Chain = Op.getOperand(0);
+  SDValue Trmp = Op.getOperand(1); // trampoline
+  SDValue FPtr = Op.getOperand(2); // nested function
+  SDValue Nest = Op.getOperand(3); // 'nest' parameter value
+  SDLoc dl(Op);
+
+  EVT PtrVT = getPointerTy(DAG.getDataLayout());
+  Type *IntPtrTy = DAG.getDataLayout().getIntPtrType(*DAG.getContext());
+
+  TargetLowering::ArgListTy Args;
+  TargetLowering::ArgListEntry Entry;
+
+  Entry.Ty = IntPtrTy;
+  Entry.Node = Trmp;
+  Args.push_back(Entry);
+  Entry.Node = DAG.getConstant(20, dl, MVT::i64);
+  Args.push_back(Entry);
+
+  Entry.Node = FPtr;
+  Args.push_back(Entry);
+  Entry.Node = Nest;
+  Args.push_back(Entry);
+
+  // Lower to a call to __trampoline_setup(Trmp, TrampSize, FPtr, ctx_reg)
+  TargetLowering::CallLoweringInfo CLI(DAG);
+  CLI.setDebugLoc(dl).setChain(Chain).setLibCallee(
+      CallingConv::C, Type::getVoidTy(*DAG.getContext()),
+      DAG.getExternalSymbol("__trampoline_setup", PtrVT), std::move(Args));
+
+  std::pair<SDValue, SDValue> CallResult = LowerCallTo(CLI);
+  return CallResult.second;
+}
+
 SDValue AArch64TargetLowering::LowerOperation(SDValue Op,
                                               SelectionDAG &DAG) const {
   LLVM_DEBUG(dbgs() << "Custom lowering: ");
@@ -5961,6 +6011,10 @@ SDValue AArch64TargetLowering::LowerOperation(SDValue Op,
     return LowerGlobalAddress(Op, DAG);
   case ISD::GlobalTLSAddress:
     return LowerGlobalTLSAddress(Op, DAG);
+  case ISD::ADJUST_TRAMPOLINE:
+    return LowerADJUST_TRAMPOLINE(Op, DAG);
+  case ISD::INIT_TRAMPOLINE:
+    return LowerINIT_TRAMPOLINE(Op, DAG);
   case ISD::SETCC:
   case ISD::STRICT_FSETCC:
   case ISD::STRICT_FSETCCS:

llvm/lib/Target/AArch64/AArch64ISelLowering.h

@@ -1045,6 +1045,8 @@ class AArch64TargetLowering : public TargetLowering {
   SDValue LowerSELECT_CC(ISD::CondCode CC, SDValue LHS, SDValue RHS,
                          SDValue TVal, SDValue FVal, const SDLoc &dl,
                          SelectionDAG &DAG) const;
+  SDValue LowerINIT_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
+  SDValue LowerADJUST_TRAMPOLINE(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerJumpTable(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerBR_JT(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerConstantPool(SDValue Op, SelectionDAG &DAG) const;