forked from OSchip/llvm-project
[WPD] Avoid noalias assumptions in unique return value optimization
Summary: Changes the type of the @__typeid_.*_unique_member imports we generate for unique return value optimization from i8 to [0 x i8]. This prevents assuming that these imports do not alias, such as when two unique return values occur in the same vtable. Fixes PR45393. Reviewers: tejohnson, pcc Reviewed By: pcc Subscribers: aganea, hiraditya, rnk, george.burgess.iv, dblaikie, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D77421
This commit is contained in:
parent
314f00a034
commit
cc5c58889e
|
@ -500,6 +500,10 @@ struct DevirtModule {
|
|||
IntegerType *Int32Ty;
|
||||
IntegerType *Int64Ty;
|
||||
IntegerType *IntPtrTy;
|
||||
/// Sizeless array type, used for imported vtables. This provides a signal
|
||||
/// to analyzers that these imports may alias, as they do for example
|
||||
/// when multiple unique return values occur in the same vtable.
|
||||
ArrayType *Int8Arr0Ty;
|
||||
|
||||
bool RemarksEnabled;
|
||||
function_ref<OptimizationRemarkEmitter &(Function *)> OREGetter;
|
||||
|
@ -529,6 +533,7 @@ struct DevirtModule {
|
|||
Int32Ty(Type::getInt32Ty(M.getContext())),
|
||||
Int64Ty(Type::getInt64Ty(M.getContext())),
|
||||
IntPtrTy(M.getDataLayout().getIntPtrType(M.getContext(), 0)),
|
||||
Int8Arr0Ty(ArrayType::get(Type::getInt8Ty(M.getContext()), 0)),
|
||||
RemarksEnabled(areRemarksEnabled()), OREGetter(OREGetter) {
|
||||
assert(!(ExportSummary && ImportSummary));
|
||||
FunctionsToSkip.init(SkipFunctionNames);
|
||||
|
@ -1415,7 +1420,8 @@ void DevirtModule::exportConstant(VTableSlot Slot, ArrayRef<uint64_t> Args,
|
|||
|
||||
Constant *DevirtModule::importGlobal(VTableSlot Slot, ArrayRef<uint64_t> Args,
|
||||
StringRef Name) {
|
||||
Constant *C = M.getOrInsertGlobal(getGlobalName(Slot, Args, Name), Int8Ty);
|
||||
Constant *C =
|
||||
M.getOrInsertGlobal(getGlobalName(Slot, Args, Name), Int8Arr0Ty);
|
||||
auto *GV = dyn_cast<GlobalVariable>(C);
|
||||
if (GV)
|
||||
GV->setVisibility(GlobalValue::HiddenVisibility);
|
||||
|
@ -1457,8 +1463,8 @@ void DevirtModule::applyUniqueRetValOpt(CallSiteInfo &CSInfo, StringRef FnName,
|
|||
for (auto &&Call : CSInfo.CallSites) {
|
||||
IRBuilder<> B(Call.CS.getInstruction());
|
||||
Value *Cmp =
|
||||
B.CreateICmp(IsOne ? ICmpInst::ICMP_EQ : ICmpInst::ICMP_NE,
|
||||
B.CreateBitCast(Call.VTable, Int8PtrTy), UniqueMemberAddr);
|
||||
B.CreateICmp(IsOne ? ICmpInst::ICMP_EQ : ICmpInst::ICMP_NE, Call.VTable,
|
||||
B.CreateBitCast(UniqueMemberAddr, Call.VTable->getType()));
|
||||
Cmp = B.CreateZExt(Cmp, Call.CS->getType());
|
||||
Call.replaceAndErase("unique-ret-val", FnName, RemarksEnabled, OREGetter,
|
||||
Cmp);
|
||||
|
|
|
@ -0,0 +1,17 @@
|
|||
---
|
||||
TypeIdMap:
|
||||
_ZTS1C:
|
||||
WPDRes:
|
||||
16:
|
||||
Kind: Indir
|
||||
ResByArg:
|
||||
'':
|
||||
Kind: UniqueRetVal
|
||||
Info: 1
|
||||
24:
|
||||
Kind: Indir
|
||||
ResByArg:
|
||||
'':
|
||||
Kind: UniqueRetVal
|
||||
Info: 1
|
||||
...
|
|
@ -11,10 +11,10 @@
|
|||
target datalayout = "e-p:64:64"
|
||||
target triple = "x86_64-unknown-linux-gnu"
|
||||
|
||||
; VCP-X86: @__typeid_typeid1_0_1_byte = external hidden global i8, !absolute_symbol !0
|
||||
; VCP-X86: @__typeid_typeid1_0_1_bit = external hidden global i8, !absolute_symbol !1
|
||||
; VCP-X86: @__typeid_typeid2_8_3_byte = external hidden global i8, !absolute_symbol !0
|
||||
; VCP-X86: @__typeid_typeid2_8_3_bit = external hidden global i8, !absolute_symbol !1
|
||||
; VCP-X86: @__typeid_typeid1_0_1_byte = external hidden global [0 x i8], !absolute_symbol !0
|
||||
; VCP-X86: @__typeid_typeid1_0_1_bit = external hidden global [0 x i8], !absolute_symbol !1
|
||||
; VCP-X86: @__typeid_typeid2_8_3_byte = external hidden global [0 x i8], !absolute_symbol !0
|
||||
; VCP-X86: @__typeid_typeid2_8_3_bit = external hidden global [0 x i8], !absolute_symbol !1
|
||||
|
||||
; Test cases where the argument values are known and we can apply virtual
|
||||
; constant propagation.
|
||||
|
@ -34,7 +34,7 @@ define i32 @call1(i8* %obj) #0 {
|
|||
; SINGLE-IMPL: call i32 bitcast (void ()* @singleimpl1 to i32 (i8*, i32)*)
|
||||
%result = call i32 %fptr_casted(i8* %obj, i32 1)
|
||||
; UNIFORM-RET-VAL: ret i32 42
|
||||
; VCP-X86: [[GEP1:%.*]] = getelementptr i8, i8* [[VT1]], i32 ptrtoint (i8* @__typeid_typeid1_0_1_byte to i32)
|
||||
; VCP-X86: [[GEP1:%.*]] = getelementptr i8, i8* [[VT1]], i32 ptrtoint ([0 x i8]* @__typeid_typeid1_0_1_byte to i32)
|
||||
; VCP-ARM: [[GEP1:%.*]] = getelementptr i8, i8* [[VT1]], i32 42
|
||||
; VCP: [[BC1:%.*]] = bitcast i8* [[GEP1]] to i32*
|
||||
; VCP: [[LOAD1:%.*]] = load i32, i32* [[BC1]]
|
||||
|
@ -85,13 +85,13 @@ define i1 @call3(i8* %obj) #0 {
|
|||
cont:
|
||||
%fptr_casted = bitcast i8* %fptr to i1 (i8*, i32)*
|
||||
%result = call i1 %fptr_casted(i8* %obj, i32 3)
|
||||
; UNIQUE-RET-VAL0: icmp ne i8* %vtablei8, @__typeid_typeid2_8_3_unique_member
|
||||
; UNIQUE-RET-VAL1: icmp eq i8* %vtablei8, @__typeid_typeid2_8_3_unique_member
|
||||
; UNIQUE-RET-VAL0: icmp ne i8* %vtablei8, getelementptr inbounds ([0 x i8], [0 x i8]* @__typeid_typeid2_8_3_unique_member, i32 0, i32 0)
|
||||
; UNIQUE-RET-VAL1: icmp eq i8* %vtablei8, getelementptr inbounds ([0 x i8], [0 x i8]* @__typeid_typeid2_8_3_unique_member, i32 0, i32 0)
|
||||
; VCP: [[VT2:%.*]] = bitcast {{.*}} to i8*
|
||||
; VCP-X86: [[GEP2:%.*]] = getelementptr i8, i8* [[VT2]], i32 ptrtoint (i8* @__typeid_typeid2_8_3_byte to i32)
|
||||
; VCP-X86: [[GEP2:%.*]] = getelementptr i8, i8* [[VT2]], i32 ptrtoint ([0 x i8]* @__typeid_typeid2_8_3_byte to i32)
|
||||
; VCP-ARM: [[GEP2:%.*]] = getelementptr i8, i8* [[VT2]], i32 43
|
||||
; VCP: [[LOAD2:%.*]] = load i8, i8* [[GEP2]]
|
||||
; VCP-X86: [[AND2:%.*]] = and i8 [[LOAD2]], ptrtoint (i8* @__typeid_typeid2_8_3_bit to i8)
|
||||
; VCP-X86: [[AND2:%.*]] = and i8 [[LOAD2]], ptrtoint ([0 x i8]* @__typeid_typeid2_8_3_bit to i8)
|
||||
; VCP-ARM: [[AND2:%.*]] = and i8 [[LOAD2]], -128
|
||||
; VCP: [[ICMP2:%.*]] = icmp ne i8 [[AND2]], 0
|
||||
; VCP: ret i1 [[ICMP2]]
|
||||
|
|
|
@ -0,0 +1,59 @@
|
|||
; Test for PR45393: Two virtual functions that return unique i1 values
|
||||
; in the same vtable. Both calls are optimized to a comparison of
|
||||
; this's vptr against the address of the vtable. When nesting these
|
||||
; checks, LLVM would previously assume the nested check always fails,
|
||||
; but that assumption does not hold if both checks refer to the same vtable.
|
||||
; This tests checks that this case is handled correctly.
|
||||
;
|
||||
; RUN: opt -S -wholeprogramdevirt -wholeprogramdevirt-summary-action=import \
|
||||
; RUN: -wholeprogramdevirt-read-summary=%p/Inputs/unique-retval-same-vtable.yaml \
|
||||
; RUN: -O2 -o - %s | FileCheck %s
|
||||
;
|
||||
; Check that C::f() contains both possible return values.
|
||||
; CHECK-LABEL: define {{.*}} @_ZNK1C1fEv
|
||||
; CHECK-NOT: }
|
||||
; CHECK: 20074028
|
||||
; CHECK-NOT: }
|
||||
; CHECK: 1008434
|
||||
|
||||
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
|
||||
target triple = "x86_64-unknown-linux-gnu"
|
||||
|
||||
%class.C = type { i32 (...)** }
|
||||
|
||||
define hidden i32 @_ZNK1C1fEv(%class.C* %this) {
|
||||
entry:
|
||||
%0 = bitcast %class.C* %this to i1 (%class.C*)***
|
||||
%vtable = load i1 (%class.C*)**, i1 (%class.C*)*** %0
|
||||
%1 = bitcast i1 (%class.C*)** %vtable to i8*
|
||||
%2 = tail call i1 @llvm.type.test(i8* %1, metadata !"_ZTS1C")
|
||||
tail call void @llvm.assume(i1 %2)
|
||||
%vfn = getelementptr inbounds i1 (%class.C*)*, i1 (%class.C*)** %vtable, i64 2
|
||||
%3 = load i1 (%class.C*)*, i1 (%class.C*)** %vfn
|
||||
%call = tail call zeroext i1 %3(%class.C* %this)
|
||||
br i1 %call, label %if.then, label %return
|
||||
|
||||
if.then:
|
||||
%vtable2 = load i1 (%class.C*)**, i1 (%class.C*)*** %0
|
||||
%4 = bitcast i1 (%class.C*)** %vtable2 to i8*
|
||||
%5 = tail call i1 @llvm.type.test(i8* %4, metadata !"_ZTS1C")
|
||||
tail call void @llvm.assume(i1 %5)
|
||||
%vfn3 = getelementptr inbounds i1 (%class.C*)*, i1 (%class.C*)** %vtable2, i64 3
|
||||
%6 = load i1 (%class.C*)*, i1 (%class.C*)** %vfn3
|
||||
; The method being called here and the method being called before
|
||||
; the branch above both return true in the same vtable and only that
|
||||
; vtable. Therefore, if this call is reached, we must select
|
||||
; 20074028. Earlier versions of LLVM mistakenly concluded that
|
||||
; this code *never* selects 200744028.
|
||||
%call4 = tail call zeroext i1 %6(%class.C* nonnull %this)
|
||||
%. = select i1 %call4, i32 20074028, i32 3007762
|
||||
br label %return
|
||||
|
||||
return:
|
||||
%retval.0 = phi i32 [ %., %if.then ], [ 1008434, %entry ]
|
||||
ret i32 %retval.0
|
||||
}
|
||||
|
||||
declare i1 @llvm.type.test(i8*, metadata)
|
||||
|
||||
declare void @llvm.assume(i1)
|
|
@ -20,15 +20,13 @@ define i1 @vf1(i8* %this) readnone {
|
|||
define i1 @call1(i8* %obj) {
|
||||
%vtableptr = bitcast i8* %obj to [1 x i8*]**
|
||||
%vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr
|
||||
; CHECK: {{.*}} = bitcast [1 x i8*]* {{.*}} to i8*
|
||||
; CHECK: [[VT1:%[^ ]*]] = bitcast [1 x i8*]* {{.*}} to i8*
|
||||
%vtablei8 = bitcast [1 x i8*]* %vtable to i8*
|
||||
%p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid1")
|
||||
call void @llvm.assume(i1 %p)
|
||||
%fptrptr = getelementptr [1 x i8*], [1 x i8*]* %vtable, i32 0, i32 0
|
||||
%fptr = load i8*, i8** %fptrptr
|
||||
%fptr_casted = bitcast i8* %fptr to i1 (i8*)*
|
||||
; CHECK: [[RES1:%[^ ]*]] = icmp eq i8* [[VT1]], bitcast ([1 x i8*]* @vt3 to i8*)
|
||||
; CHECK: [[RES1:%[^ ]*]] = icmp eq [1 x i8*]* %vtable, @vt3
|
||||
%result = call i1 %fptr_casted(i8* %obj)
|
||||
; CHECK: ret i1 [[RES1]]
|
||||
ret i1 %result
|
||||
|
@ -38,7 +36,6 @@ define i1 @call1(i8* %obj) {
|
|||
define i32 @call2(i8* %obj) {
|
||||
%vtableptr = bitcast i8* %obj to [1 x i8*]**
|
||||
%vtable = load [1 x i8*]*, [1 x i8*]** %vtableptr
|
||||
; CHECK: [[VT2:%[^ ]*]] = bitcast [1 x i8*]* {{.*}} to i8*
|
||||
%vtablei8 = bitcast [1 x i8*]* %vtable to i8*
|
||||
%p = call i1 @llvm.type.test(i8* %vtablei8, metadata !"typeid2")
|
||||
call void @llvm.assume(i1 %p)
|
||||
|
@ -46,7 +43,7 @@ define i32 @call2(i8* %obj) {
|
|||
%fptr = load i8*, i8** %fptrptr
|
||||
; Intentional type mismatch to test zero extend.
|
||||
%fptr_casted = bitcast i8* %fptr to i32 (i8*)*
|
||||
; CHECK: [[RES2:%[^ ]*]] = icmp ne i8* [[VT1]], bitcast ([1 x i8*]* @vt2 to i8*)
|
||||
; CHECK: [[RES2:%[^ ]*]] = icmp ne [1 x i8*]* %vtable, @vt2
|
||||
%result = call i32 %fptr_casted(i8* %obj)
|
||||
; CHECK: [[ZEXT2:%[^ ]*]] = zext i1 [[RES2]] to i32
|
||||
; CHECK: ret i32 [[ZEXT2:%[^ ]*]]
|
||||
|
|
Loading…
Reference in New Issue