Index: lib/Transforms/Coroutines/CoroEarly.cpp =================================================================== --- lib/Transforms/Coroutines/CoroEarly.cpp +++ lib/Transforms/Coroutines/CoroEarly.cpp @@ -12,12 +12,69 @@ //===----------------------------------------------------------------------===// #include "CoroInternal.h" +#include "llvm/IR/CallSite.h" +#include "llvm/IR/InstIterator.h" +#include "llvm/IR/Module.h" #include "llvm/Pass.h" using namespace llvm; #define DEBUG_TYPE "coro-early" +namespace { +// Created on demand if CoroEarly pass has work to do. +class Lowerer : public coro::LowererBase { + void lowerResumeOrDestroy(CallSite CS, CoroSubFnInst::ResumeKind); + +public: + Lowerer(Module &M) : LowererBase(M) {} + static std::unique_ptr createIfNeeded(Module &M); + bool lowerEarlyIntrinsics(Function &F); +}; +} + +// Replace a direct call to coro.resume or coro.destroy with an indirect call to +// an address returned by coro.subfn.addr intrinsic. This is done so that +// CGPassManager recognizes devirtualization when CoroElide pass replaces a call +// to coro.subfn.addr with an appropriate function address. +void Lowerer::lowerResumeOrDestroy(CallSite CS, + CoroSubFnInst::ResumeKind Index) { + Value *ResumeAddr = + makeSubFnCall(CS.getArgOperand(0), Index, CS.getInstruction()); + CS.setCalledFunction(ResumeAddr); + CS.setCallingConv(CallingConv::Fast); +} + +bool Lowerer::lowerEarlyIntrinsics(Function &F) { + bool Changed = false; + for (auto IB = inst_begin(F), IE = inst_end(F); IB != IE;) { + Instruction &I = *IB++; + if (auto *II = dyn_cast(&I)) { + switch (II->getIntrinsicID()) { + default: + continue; + case Intrinsic::coro_resume: + lowerResumeOrDestroy(II, CoroSubFnInst::ResumeIndex); + break; + case Intrinsic::coro_destroy: + lowerResumeOrDestroy(II, CoroSubFnInst::DestroyIndex); + break; + } + Changed = true; + } + } + return Changed; +} + +// This pass has work to do only if we find intrinsics we are going to lower in +// the module. +std::unique_ptr Lowerer::createIfNeeded(Module &M) { + if (M.getNamedValue(CORO_RESUME_STR) || M.getNamedValue(CORO_DESTROY_STR)) + return llvm::make_unique(M); + + return {}; +} + //===----------------------------------------------------------------------===// // Top Level Driver //===----------------------------------------------------------------------===// @@ -25,12 +82,25 @@ namespace { struct CoroEarly : public FunctionPass { - static char ID; // Pass identification, replacement for typeid + static char ID; // Pass identification, replacement for typeid. CoroEarly() : FunctionPass(ID) {} - bool runOnFunction(Function &F) override { return false; } + std::unique_ptr L; + + bool doInitialization(Module &M) override { + L = Lowerer::createIfNeeded(M); + return false; + } + + bool runOnFunction(Function &F) override { + if (!L) + return false; + + return L->lowerEarlyIntrinsics(F); + } + void getAnalysisUsage(AnalysisUsage &AU) const override { - AU.setPreservesAll(); + AU.setPreservesCFG(); } }; Index: lib/Transforms/Coroutines/CoroInstr.h =================================================================== --- /dev/null +++ lib/Transforms/Coroutines/CoroInstr.h @@ -0,0 +1,67 @@ +//===-- CoroInstr.h - Coroutine Intrinsics Instruction Wrappers -*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// This file defines classes that make it really easy to deal with intrinsic +// functions with the isa/dyncast family of functions. In particular, this +// allows you to do things like: +// +// if (auto *SF = dyn_cast(Inst)) +// ... SF->getFrame() ... SF->getAlloc() ... +// +// All intrinsic function calls are instances of the call instruction, so these +// are all subclasses of the CallInst class. Note that none of these classes +// has state or virtual methods, which is an important part of this gross/neat +// hack working. +// +// The helpful comment above is borrowed from llvm/IntrinsicInst.h, we keep +// coroutine intrinsic wrappers here since they are only used by the passes in +// the Coroutine library. +//===----------------------------------------------------------------------===// + +#include "llvm/IR/GlobalVariable.h" +#include "llvm/IR/IntrinsicInst.h" + +namespace llvm { + +#define CORO_DESTROY_STR "llvm.coro.destroy" +#define CORO_RESUME_STR "llvm.coro.resume" + +/// This class represents the llvm.coro.subfn.addr instruction. +class LLVM_LIBRARY_VISIBILITY CoroSubFnInst : public IntrinsicInst { + enum { FrameArg, IndexArg }; + +public: + enum ResumeKind { + ResumeIndex, + DestroyIndex, + IndexLast, + IndexFirst = ResumeIndex + }; + + Value *getFrame() const { return getArgOperand(FrameArg); } + ResumeKind getIndex() const { + int64_t Index = getRawIndex()->getValue().getSExtValue(); + assert(Index >= IndexFirst && Index < IndexLast && + "unexpected CoroSubFnInst index argument"); + return static_cast(Index); + } + + ConstantInt *getRawIndex() const { + return cast(getArgOperand(IndexArg)); + } + + // Methods to support type inquiry through isa, cast, and dyn_cast: + static inline bool classof(const IntrinsicInst *I) { + return I->getIntrinsicID() == Intrinsic::coro_subfn_addr; + } + static inline bool classof(const Value *V) { + return isa(V) && classof(cast(V)); + } +}; + +} // End namespace llvm. Index: lib/Transforms/Coroutines/CoroInternal.h =================================================================== --- lib/Transforms/Coroutines/CoroInternal.h +++ lib/Transforms/Coroutines/CoroInternal.h @@ -12,10 +12,14 @@ #ifndef LLVM_LIB_TRANSFORMS_COROUTINES_COROINTERNAL_H #define LLVM_LIB_TRANSFORMS_COROUTINES_COROINTERNAL_H +#include "CoroInstr.h" #include "llvm/Transforms/Coroutines.h" namespace llvm { +class FunctionType; +class LLVMContext; +class Module; class PassRegistry; void initializeCoroEarlyPass(PassRegistry &); @@ -23,6 +27,19 @@ void initializeCoroElidePass(PassRegistry &); void initializeCoroCleanupPass(PassRegistry &); -} +namespace coro { + +// Keeps data and helper functions for lowering coroutine intrinsics. +struct LowererBase { + Module &TheModule; + LLVMContext &Context; + FunctionType *const ResumeFnType; + + LowererBase(Module &M); + Value *makeSubFnCall(Value *Arg, int Index, Instruction *InsertPt); +}; + +} // End namespace coro. +} // End namespace llvm #endif Index: lib/Transforms/Coroutines/Coroutines.cpp =================================================================== --- lib/Transforms/Coroutines/Coroutines.cpp +++ lib/Transforms/Coroutines/Coroutines.cpp @@ -66,3 +66,31 @@ Builder.addExtension(PassManagerBuilder::EP_OptimizerLast, addCoroutineOptimizerLastPasses); } + +// Construct the lowerer base class and initialize its members. +coro::LowererBase::LowererBase(Module &M) + : TheModule(M), Context(M.getContext()), + ResumeFnType(FunctionType::get(Type::getVoidTy(Context), + Type::getInt8PtrTy(Context), + /*isVarArg=*/false)) {} + +// Creates a sequence of instructions to obtain a resume function address using +// llvm.coro.subfn.addr. It generates the following sequence: +// +// call i8* @llvm.coro.subfn.addr(i8* %Arg, i8 %index) +// bitcast i8* %2 to void(i8*)* + +Value *coro::LowererBase::makeSubFnCall(Value *Arg, int Index, + Instruction *InsertPt) { + auto *IndexVal = ConstantInt::get(Type::getInt8Ty(Context), Index); + auto *Fn = Intrinsic::getDeclaration(&TheModule, Intrinsic::coro_subfn_addr); + + assert(Index >= CoroSubFnInst::IndexFirst && + Index < CoroSubFnInst::IndexLast && + "makeSubFnCall: Index value out of range"); + auto *Call = CallInst::Create(Fn, {Arg, IndexVal}, "", InsertPt); + + auto *Bitcast = + new BitCastInst(Call, ResumeFnType->getPointerTo(), "", InsertPt); + return Bitcast; +} Index: test/Transforms/Coroutines/coro-early.ll =================================================================== --- /dev/null +++ test/Transforms/Coroutines/coro-early.ll @@ -0,0 +1,24 @@ +; Tests that CoroEarly pass correctly lowers coro.resume and coro.destroy +; intrinsics. +; RUN: opt < %s -S -coro-early | FileCheck %s + +; CHECK-LABEL: @callResume +define void @callResume(i8* %hdl) { +; CHECK-NEXT: entry +entry: +; CHECK-NEXT: %0 = call i8* @llvm.coro.subfn.addr(i8* %hdl, i8 0) +; CHECK-NEXT: %1 = bitcast i8* %0 to void (i8*)* +; CHECK-NEXT: call fastcc void %1(i8* %hdl) + call void @llvm.coro.resume(i8* %hdl) + +; CHECK-NEXT: %2 = call i8* @llvm.coro.subfn.addr(i8* %hdl, i8 1) +; CHECK-NEXT: %3 = bitcast i8* %2 to void (i8*)* +; CHECK-NEXT: call fastcc void %3(i8* %hdl) + call void @llvm.coro.destroy(i8* %hdl) + + ret void +; CHECK-NEXT: ret void +} + +declare void @llvm.coro.resume(i8*) +declare void @llvm.coro.destroy(i8*)