Index: llvm/lib/Analysis/InlineCost.cpp =================================================================== --- llvm/lib/Analysis/InlineCost.cpp +++ llvm/lib/Analysis/InlineCost.cpp @@ -135,7 +135,7 @@ bool ContainsNoDuplicateCall; bool HasReturn; bool HasIndirectBr; - bool HasFrameEscape; + bool HasUninlineableIntrinsic; bool UsesVarArgs; /// Number of bytes allocated statically by the callee. @@ -281,12 +281,13 @@ IsCallerRecursive(false), IsRecursiveCall(false), ExposesReturnsTwice(false), HasDynamicAlloca(false), ContainsNoDuplicateCall(false), HasReturn(false), HasIndirectBr(false), - HasFrameEscape(false), UsesVarArgs(false), AllocatedSize(0), NumInstructions(0), - NumVectorInstructions(0), VectorBonus(0), SingleBBBonus(0), - EnableLoadElimination(true), LoadEliminationCost(0), NumConstantArgs(0), - NumConstantOffsetPtrArgs(0), NumAllocaArgs(0), NumConstantPtrCmps(0), - NumConstantPtrDiffs(0), NumInstructionsSimplified(0), - SROACostSavings(0), SROACostSavingsLost(0) {} + HasUninlineableIntrinsic(false), UsesVarArgs(false), AllocatedSize(0), + NumInstructions(0), NumVectorInstructions(0), VectorBonus(0), + SingleBBBonus(0), EnableLoadElimination(true), LoadEliminationCost(0), + NumConstantArgs(0), NumConstantOffsetPtrArgs(0), NumAllocaArgs(0), + NumConstantPtrCmps(0), NumConstantPtrDiffs(0), + NumInstructionsSimplified(0), SROACostSavings(0), + SROACostSavingsLost(0) {} bool analyzeCall(CallSite CS); @@ -1231,8 +1232,9 @@ disableLoadElimination(); // SROA can usually chew through these intrinsics, but they aren't free. return false; + case Intrinsic::icall_branch_funnel: case Intrinsic::localescape: - HasFrameEscape = true; + HasUninlineableIntrinsic = true; return false; case Intrinsic::vastart: case Intrinsic::vaend: @@ -1572,7 +1574,7 @@ using namespace ore; // If the visit this instruction detected an uninlinable pattern, abort. if (IsRecursiveCall || ExposesReturnsTwice || HasDynamicAlloca || - HasIndirectBr || HasFrameEscape || UsesVarArgs) { + HasIndirectBr || HasUninlineableIntrinsic || UsesVarArgs) { if (ORE) ORE->emit([&]() { return OptimizationRemarkMissed(DEBUG_TYPE, "NeverInline", @@ -2044,6 +2046,9 @@ switch (CS.getCalledFunction()->getIntrinsicID()) { default: break; + // Disallow inlining of @llvm.icall.branch.funnel because current + // backend can't separate call targets from call arguments. + case llvm::Intrinsic::icall_branch_funnel: // Disallow inlining functions that call @llvm.localescape. Doing this // correctly would require major changes to the inliner. case llvm::Intrinsic::localescape: Index: llvm/test/Transforms/Inline/inline-brunch-funnel.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/Inline/inline-brunch-funnel.ll @@ -0,0 +1,35 @@ +; Test that inliner skips @llvm.icall.branch.funnel +; RUN: opt < %s -inline -S | FileCheck %s + +target datalayout = "e-p:64:64" +target triple = "x86_64-unknown-linux-gnu" + +declare void @llvm.icall.branch.funnel(...) + +; CHECK-LABEL: define void @fn_musttail( +define void @fn_musttail() { + call void (...) @bf_musttail() + ; CHECK: call void (...) @bf_musttail( + ret void +} + +; CHECK-LABEL: define internal void @bf_musttail( +define internal void @bf_musttail(...) { + musttail call void (...) @llvm.icall.branch.funnel(...) + ; CHECK: musttail call void (...) @llvm.icall.branch.funnel( + ret void +} + +; CHECK-LABEL: define void @fn_musttail_always( +define void @fn_musttail_always() { + call void (...) @bf_musttail_always() + ; CHECK: call void (...) @bf_musttail_always( + ret void +} + +; CHECK-LABEL: define internal void @bf_musttail_always( +define internal void @bf_musttail_always(...) alwaysinline { + musttail call void (...) @llvm.icall.branch.funnel(...) + ; CHECK: musttail call void (...) @llvm.icall.branch.funnel( + ret void +} Index: llvm/test/Transforms/WholeProgramDevirt/branch-funnel.ll =================================================================== --- llvm/test/Transforms/WholeProgramDevirt/branch-funnel.ll +++ llvm/test/Transforms/WholeProgramDevirt/branch-funnel.ll @@ -1,6 +1,10 @@ ; RUN: opt -S -wholeprogramdevirt %s | FileCheck --check-prefixes=CHECK,RETP %s ; RUN: sed -e 's,+retpoline,-retpoline,g' %s | opt -S -wholeprogramdevirt | FileCheck --check-prefixes=CHECK,NORETP %s + ; RUN: opt -wholeprogramdevirt -wholeprogramdevirt-summary-action=export -wholeprogramdevirt-read-summary=%S/Inputs/export.yaml -wholeprogramdevirt-write-summary=%t -S -o - %s | FileCheck --check-prefixes=CHECK,RETP %s + +; RUN: opt -wholeprogramdevirt -wholeprogramdevirt-summary-action=export -wholeprogramdevirt-read-summary=%S/Inputs/export.yaml -wholeprogramdevirt-write-summary=%t -O3 -S -o - %s | FileCheck --check-prefixes=CHECK %s + ; RUN: FileCheck --check-prefix=SUMMARY %s < %t ; SUMMARY: TypeIdMap: @@ -89,7 +93,10 @@ declare i32 @vf4_1(i8* %this, i32 %arg) declare i32 @vf4_2(i8* %this, i32 %arg) -; CHECK: define i32 @fn1 + + +; CHECK-LABEL: define i32 @fn1 +; CHECK-NOT: call void (...) @llvm.icall.branch.funnel define i32 @fn1(i8* %obj) #0 { %vtableptr = bitcast i8* %obj to [1 x i8*]** %vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr @@ -107,7 +114,8 @@ ret i32 %result } -; CHECK: define i32 @fn2 +; CHECK-LABEL: define i32 @fn2 +; CHECK-NOT: call void (...) @llvm.icall.branch.funnel define i32 @fn2(i8* %obj) #0 { %vtableptr = bitcast i8* %obj to [1 x i8*]** %vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr @@ -122,7 +130,8 @@ ret i32 %result } -; CHECK: define i32 @fn3 +; CHECK-LABEL: define i32 @fn3 +; CHECK-NOT: call void (...) @llvm.icall.branch.funnel define i32 @fn3(i8* %obj) #0 { %vtableptr = bitcast i8* %obj to [1 x i8*]** %vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr @@ -138,10 +147,9 @@ ret i32 %result } -; CHECK: define internal void @branch_funnel(i8* nest, ...) - +; CHECK-LABEL: define internal void @branch_funnel(i8* ; CHECK: define hidden void @__typeid_typeid1_0_branch_funnel(i8* nest, ...) -; CHECK-NEXT: call void (...) @llvm.icall.branch.funnel(i8* %0, i8* bitcast ([1 x i8*]* @vt1_1 to i8*), i32 (i8*, i32)* @vf1_1, i8* bitcast ([1 x i8*]* @vt1_2 to i8*), i32 (i8*, i32)* @vf1_2, ...) +; CHECK-NEXT: musttail call void (...) @llvm.icall.branch.funnel(i8* %0, i8* bitcast ([1 x i8*]* {{(nonnull )?}}@vt1_1 to i8*), i32 (i8*, i32)* {{(nonnull )?}}@vf1_1, i8* bitcast ([1 x i8*]* {{(nonnull )?}}@vt1_2 to i8*), i32 (i8*, i32)* {{(nonnull )?}}@vf1_2, ...) declare i1 @llvm.type.test(i8*, metadata) declare void @llvm.assume(i1)