[IR] Add token types

This introduces the basic functionality to support "token types".
The motivation stems from the need to perform operations on a Value
whose provenance cannot be obscured.

There are several applications for such a type but my immediate
motivation stems from WinEH.  Our personality routine enforces a
single-entry - single-exit regime for cleanups.  After several rounds of
optimizations, we may be left with a terminator whose "cleanup-entry
block" is not entirely clear because control flow has merged two
cleanups together.  We have experimented with using labels as operands
inside of instructions which are not terminators to indicate where we
came from but found that LLVM does not expect such exotic uses of
BasicBlocks.

Instead, we can use this new type to clearly associate the "entry point"
and "exit point" of our cleanup.  This is done by having the cleanuppad
yield a Token and consuming it at the cleanupret.
The token type makes it impossible to obscure or otherwise hide the
Value, making it trivial to track the relationship between the two
points.

What is the burden to the optimizer?  Well, it turns out we have already
paid down this cost by accepting that there are certain calls that we
are not permitted to duplicate, optimizations have to watch out for
such instructions anyway.  There are additional places in the optimizer
that we will probably have to update but early examination has given me
the impression that this will not be heroic.

Differential Revision: http://reviews.llvm.org/D11861

llvm-svn: 245029
This commit is contained in:
David Majnemer 2015-08-14 05:09:07 +00:00
parent b20d3957b6
commit 10f2d9234b
29 changed files with 160 additions and 25 deletions

View File

@ -2168,6 +2168,26 @@ The label type represents code labels.
label
.. _t_token:
Token Type
^^^^^^^^^^
:Overview:
The token type is used when a value is associated with an instruction
but all uses of the value must not attempt to introspect or obscure it.
As such, it is not appropriate to have a :ref:`phi <i_phi>` or
:ref:`select <i_select>` of type token.
:Syntax:
::
token
.. _t_metadata:
Metadata Type

View File

@ -274,7 +274,8 @@ typedef enum {
LLVMPointerTypeKind, /**< Pointers */
LLVMVectorTypeKind, /**< SIMD 'packed' format, or other vector type */
LLVMMetadataTypeKind, /**< Metadata */
LLVMX86_MMXTypeKind /**< X86 MMX */
LLVMX86_MMXTypeKind, /**< X86 MMX */
LLVMTokenTypeKind /**< Tokens */
} LLVMTypeKind;
typedef enum {

View File

@ -121,7 +121,9 @@ namespace bitc {
TYPE_CODE_STRUCT_NAME = 19, // STRUCT_NAME: [strchr x N]
TYPE_CODE_STRUCT_NAMED = 20,// STRUCT_NAMED: [ispacked, eltty x N]
TYPE_CODE_FUNCTION = 21 // FUNCTION: [vararg, retty, paramty x N]
TYPE_CODE_FUNCTION = 21, // FUNCTION: [vararg, retty, paramty x N]
TYPE_CODE_TOKEN = 22 // TOKEN
};
// The type symbol table only has one code (TST_ENTRY_CODE).

View File

@ -63,15 +63,16 @@ public:
LabelTyID, ///< 7: Labels
MetadataTyID, ///< 8: Metadata
X86_MMXTyID, ///< 9: MMX vectors (64 bits, X86 specific)
TokenTyID, ///< 10: Tokens
// Derived types... see DerivedTypes.h file.
// Make sure FirstDerivedTyID stays up to date!
IntegerTyID, ///< 10: Arbitrary bit width integers
FunctionTyID, ///< 11: Functions
StructTyID, ///< 12: Structures
ArrayTyID, ///< 13: Arrays
PointerTyID, ///< 14: Pointers
VectorTyID ///< 15: SIMD 'packed' format, or other vector type
IntegerTyID, ///< 11: Arbitrary bit width integers
FunctionTyID, ///< 12: Functions
StructTyID, ///< 13: Structures
ArrayTyID, ///< 14: Arrays
PointerTyID, ///< 15: Pointers
VectorTyID ///< 16: SIMD 'packed' format, or other vector type
};
private:
@ -178,6 +179,9 @@ public:
/// isMetadataTy - Return true if this is 'metadata'.
bool isMetadataTy() const { return getTypeID() == MetadataTyID; }
/// isTokenTy - Return true if this is 'token'.
bool isTokenTy() const { return getTypeID() == TokenTyID; }
/// isIntegerTy - True if this is an instance of IntegerType.
///
bool isIntegerTy() const { return getTypeID() == IntegerTyID; }
@ -378,6 +382,7 @@ public:
static Type *getFP128Ty(LLVMContext &C);
static Type *getPPC_FP128Ty(LLVMContext &C);
static Type *getX86_MMXTy(LLVMContext &C);
static Type *getTokenTy(LLVMContext &C);
static IntegerType *getIntNTy(LLVMContext &C, unsigned N);
static IntegerType *getInt1Ty(LLVMContext &C);
static IntegerType *getInt8Ty(LLVMContext &C);

View File

@ -155,6 +155,9 @@ void CodeMetrics::analyzeBasicBlock(const BasicBlock *BB,
if (isa<ExtractElementInst>(II) || II->getType()->isVectorTy())
++NumVectorInsts;
if (II->getType()->isTokenTy() && II->isUsedOutsideOfBlock(BB))
notDuplicatable = true;
if (const CallInst *CI = dyn_cast<CallInst>(II))
if (CI->cannotDuplicate())
notDuplicatable = true;

View File

@ -220,6 +220,8 @@ bool Loop::isSafeToClone() const {
if (CI->cannotDuplicate())
return false;
}
if (BI->getType()->isTokenTy() && BI->isUsedOutsideOfBlock(*I))
return false;
}
}
return true;

View File

@ -691,6 +691,7 @@ lltok::Kind LLLexer::LexIdentifier() {
TYPEKEYWORD("label", Type::getLabelTy(Context));
TYPEKEYWORD("metadata", Type::getMetadataTy(Context));
TYPEKEYWORD("x86_mmx", Type::getX86_MMXTy(Context));
TYPEKEYWORD("token", Type::getTokenTy(Context));
#undef TYPEKEYWORD
// Keywords for instructions.

View File

@ -1360,6 +1360,9 @@ std::error_code BitcodeReader::parseTypeTableBody() {
case bitc::TYPE_CODE_X86_MMX: // X86_MMX
ResultTy = Type::getX86_MMXTy(Context);
break;
case bitc::TYPE_CODE_TOKEN: // TOKEN
ResultTy = Type::getTokenTy(Context);
break;
case bitc::TYPE_CODE_INTEGER: { // INTEGER: [width]
if (Record.size() < 1)
return error("Invalid record");

View File

@ -405,6 +405,7 @@ static void WriteTypeTable(const ValueEnumerator &VE, BitstreamWriter &Stream) {
case Type::LabelTyID: Code = bitc::TYPE_CODE_LABEL; break;
case Type::MetadataTyID: Code = bitc::TYPE_CODE_METADATA; break;
case Type::X86_MMXTyID: Code = bitc::TYPE_CODE_X86_MMX; break;
case Type::TokenTyID: Code = bitc::TYPE_CODE_TOKEN; break;
case Type::IntegerTyID:
// INTEGER: [width]
Code = bitc::TYPE_CODE_INTEGER;

View File

@ -467,6 +467,7 @@ void TypePrinting::print(Type *Ty, raw_ostream &OS) {
case Type::LabelTyID: OS << "label"; return;
case Type::MetadataTyID: OS << "metadata"; return;
case Type::X86_MMXTyID: OS << "x86_mmx"; return;
case Type::TokenTyID: OS << "token"; return;
case Type::IntegerTyID:
OS << 'i' << cast<IntegerType>(Ty)->getBitWidth();
return;

View File

@ -262,6 +262,8 @@ LLVMTypeKind LLVMGetTypeKind(LLVMTypeRef Ty) {
return LLVMVectorTypeKind;
case Type::X86_MMXTyID:
return LLVMX86_MMXTypeKind;
case Type::TokenTyID:
return LLVMTokenTypeKind;
}
llvm_unreachable("Unhandled TypeID.");
}
@ -366,6 +368,9 @@ LLVMTypeRef LLVMPPCFP128TypeInContext(LLVMContextRef C) {
LLVMTypeRef LLVMX86MMXTypeInContext(LLVMContextRef C) {
return (LLVMTypeRef) Type::getX86_MMXTy(*unwrap(C));
}
LLVMTypeRef LLVMTokenTypeInContext(LLVMContextRef C) {
return (LLVMTypeRef) Type::getTokenTy(*unwrap(C));
}
LLVMTypeRef LLVMHalfType(void) {
return LLVMHalfTypeInContext(LLVMGetGlobalContext());

View File

@ -62,7 +62,10 @@ UnaryInstruction::~UnaryInstruction() {
const char *SelectInst::areInvalidOperands(Value *Op0, Value *Op1, Value *Op2) {
if (Op1->getType() != Op2->getType())
return "both values to select must have same type";
if (Op1->getType()->isTokenTy())
return "select values cannot have token type";
if (VectorType *VT = dyn_cast<VectorType>(Op0->getType())) {
// Vector select.
if (VT->getElementType() != Type::getInt1Ty(Op0->getContext()))

View File

@ -27,6 +27,7 @@ LLVMContextImpl::LLVMContextImpl(LLVMContext &C)
FloatTy(C, Type::FloatTyID),
DoubleTy(C, Type::DoubleTyID),
MetadataTy(C, Type::MetadataTyID),
TokenTy(C, Type::TokenTyID),
X86_FP80Ty(C, Type::X86_FP80TyID),
FP128Ty(C, Type::FP128TyID),
PPC_FP128Ty(C, Type::PPC_FP128TyID),

View File

@ -928,7 +928,7 @@ public:
ConstantInt *TheFalseVal;
// Basic type instances.
Type VoidTy, LabelTy, HalfTy, FloatTy, DoubleTy, MetadataTy;
Type VoidTy, LabelTy, HalfTy, FloatTy, DoubleTy, MetadataTy, TokenTy;
Type X86_FP80Ty, FP128Ty, PPC_FP128Ty, X86_MMXTy;
IntegerType Int1Ty, Int8Ty, Int16Ty, Int32Ty, Int64Ty, Int128Ty;

View File

@ -35,6 +35,7 @@ Type *Type::getPrimitiveType(LLVMContext &C, TypeID IDNumber) {
case LabelTyID : return getLabelTy(C);
case MetadataTyID : return getMetadataTy(C);
case X86_MMXTyID : return getX86_MMXTy(C);
case TokenTyID : return getTokenTy(C);
default:
return nullptr;
}
@ -220,6 +221,7 @@ Type *Type::getHalfTy(LLVMContext &C) { return &C.pImpl->HalfTy; }
Type *Type::getFloatTy(LLVMContext &C) { return &C.pImpl->FloatTy; }
Type *Type::getDoubleTy(LLVMContext &C) { return &C.pImpl->DoubleTy; }
Type *Type::getMetadataTy(LLVMContext &C) { return &C.pImpl->MetadataTy; }
Type *Type::getTokenTy(LLVMContext &C) { return &C.pImpl->TokenTy; }
Type *Type::getX86_FP80Ty(LLVMContext &C) { return &C.pImpl->X86_FP80Ty; }
Type *Type::getFP128Ty(LLVMContext &C) { return &C.pImpl->FP128Ty; }
Type *Type::getPPC_FP128Ty(LLVMContext &C) { return &C.pImpl->PPC_FP128Ty; }
@ -595,7 +597,8 @@ void StructType::setBody(Type *type, ...) {
bool StructType::isValidElementType(Type *ElemTy) {
return !ElemTy->isVoidTy() && !ElemTy->isLabelTy() &&
!ElemTy->isMetadataTy() && !ElemTy->isFunctionTy();
!ElemTy->isMetadataTy() && !ElemTy->isFunctionTy() &&
!ElemTy->isTokenTy();
}
/// isLayoutIdentical - Return true if this is layout identical to the
@ -690,7 +693,8 @@ ArrayType *ArrayType::get(Type *ElementType, uint64_t NumElements) {
bool ArrayType::isValidElementType(Type *ElemTy) {
return !ElemTy->isVoidTy() && !ElemTy->isLabelTy() &&
!ElemTy->isMetadataTy() && !ElemTy->isFunctionTy();
!ElemTy->isMetadataTy() && !ElemTy->isFunctionTy() &&
!ElemTy->isTokenTy();
}
//===----------------------------------------------------------------------===//
@ -758,7 +762,7 @@ PointerType *Type::getPointerTo(unsigned addrs) const {
bool PointerType::isValidElementType(Type *ElemTy) {
return !ElemTy->isVoidTy() && !ElemTy->isLabelTy() &&
!ElemTy->isMetadataTy();
!ElemTy->isMetadataTy() && !ElemTy->isTokenTy();
}
bool PointerType::isLoadableOrStorableType(Type *ElemTy) {

View File

@ -1739,11 +1739,18 @@ void Verifier::visitFunction(const Function &F) {
FT->getParamType(i));
Assert(I->getType()->isFirstClassType(),
"Function arguments must have first-class types!", I);
if (!isLLVMdotName)
if (!isLLVMdotName) {
Assert(!I->getType()->isMetadataTy(),
"Function takes metadata but isn't an intrinsic", I, &F);
Assert(!I->getType()->isTokenTy(),
"Function takes token but isn't an intrinsic", I, &F);
}
}
if (!isLLVMdotName)
Assert(!F.getReturnType()->isTokenTy(),
"Functions returns a token but isn't an intrinsic", &F);
// Get the function metadata attachments.
SmallVector<std::pair<unsigned, MDNode *>, 4> MDs;
F.getAllMetadata(MDs);
@ -2190,6 +2197,9 @@ void Verifier::visitPHINode(PHINode &PN) {
isa<PHINode>(--BasicBlock::iterator(&PN)),
"PHI nodes not grouped at top of basic block!", &PN, PN.getParent());
// Check that a PHI doesn't yield a Token.
Assert(!PN.getType()->isTokenTy(), "PHI nodes cannot have token type!");
// Check that all of the values of the PHI node have the same type as the
// result, and that the incoming blocks are really basic blocks.
for (Value *IncValue : PN.incoming_values()) {
@ -2292,12 +2302,19 @@ void Verifier::VerifyCallSite(CallSite CS) {
// Verify that there's no metadata unless it's a direct call to an intrinsic.
if (CS.getCalledFunction() == nullptr ||
!CS.getCalledFunction()->getName().startswith("llvm.")) {
for (FunctionType::param_iterator PI = FTy->param_begin(),
PE = FTy->param_end(); PI != PE; ++PI)
Assert(!(*PI)->isMetadataTy(),
for (Type *ParamTy : FTy->params()) {
Assert(!ParamTy->isMetadataTy(),
"Function has metadata parameter but isn't an intrinsic", I);
Assert(!ParamTy->isTokenTy(),
"Function has token parameter but isn't an intrinsic", I);
}
}
// Verify that indirect calls don't return tokens.
if (CS.getCalledFunction() == nullptr)
Assert(!FTy->getReturnType()->isTokenTy(),
"Return type cannot be token for indirect call!");
if (Function *F = CS.getCalledFunction())
if (Intrinsic::ID ID = (Intrinsic::ID)F->getIntrinsicID())
visitIntrinsicCallSite(ID, CS);

View File

@ -551,7 +551,8 @@ void CppWriter::printAttributes(const AttributeSet &PAL,
void CppWriter::printType(Type* Ty) {
// We don't print definitions for primitive types
if (Ty->isFloatingPointTy() || Ty->isX86_MMXTy() || Ty->isIntegerTy() ||
Ty->isLabelTy() || Ty->isMetadataTy() || Ty->isVoidTy())
Ty->isLabelTy() || Ty->isMetadataTy() || Ty->isVoidTy() ||
Ty->isTokenTy())
return;
// If we already defined this type, we don't need to define it again.

View File

@ -654,6 +654,7 @@ int FunctionComparator::cmpTypes(Type *TyL, Type *TyR) const {
case Type::PPC_FP128TyID:
case Type::LabelTyID:
case Type::MetadataTyID:
case Type::TokenTyID:
return 0;
case Type::PointerTyID: {

View File

@ -260,6 +260,11 @@ static unsigned getJumpThreadDuplicationCost(const BasicBlock *BB,
if (isa<BitCastInst>(I) && I->getType()->isPointerTy())
continue;
// Bail out if this instruction gives back a token type, it is not possible
// to duplicate it if it used outside this BB.
if (I->getType()->isTokenTy() && I->isUsedOutsideOfBlock(BB))
return ~0U;
// All other instructions count for at least one unit.
++Size;

View File

@ -337,14 +337,8 @@ static void HandleInlinedEHPad(InvokeInst *II, BasicBlock *FirstNewBlock,
TPI->eraseFromParent();
UpdatePHINodes(BB);
}
} else if (auto *CPI = dyn_cast<CleanupPadInst>(I)) {
if (CPI->getNumOperands() == 0) {
CleanupPadInst::Create(CPI->getType(), {UnwindDest}, CPI->getName(),
CPI);
CPI->eraseFromParent();
}
} else {
assert(isa<CatchPadInst>(I));
assert(isa<CatchPadInst>(I) || isa<CleanupPadInst>(I));
}
}

6
test/Assembler/token.ll Normal file
View File

@ -0,0 +1,6 @@
; RUN: llvm-as < %s | llvm-dis | FileCheck %s
; RUN: verify-uselistorder %s
; Basic smoke test for token type.
; CHECK: declare void @llvm.token.foobar(token)
declare void @llvm.token.foobar(token)

View File

@ -1212,6 +1212,9 @@ define void @misc.metadata() {
ret void
}
declare void @llvm.tokenfoo(token)
; CHECK: declare void @llvm.tokenfoo(token)
; CHECK: attributes #0 = { alignstack=4 }
; CHECK: attributes #1 = { alignstack=8 }
; CHECK: attributes #2 = { alwaysinline }

11
test/Verifier/token1.ll Normal file
View File

@ -0,0 +1,11 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
define void @f(token %A, token %B) {
entry:
br label %bb
bb:
%phi = phi token [ %A, %bb ], [ %B, %entry]
; CHECK: PHI nodes cannot have token type!
br label %bb
}

11
test/Verifier/token2.ll Normal file
View File

@ -0,0 +1,11 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
define void @f(token %A, token %B) {
entry:
br label %bb
bb:
%sel = select i1 undef, token %A, token %B
; CHECK: select values cannot have token type
br label %bb
}

8
test/Verifier/token3.ll Normal file
View File

@ -0,0 +1,8 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
define void @f(token %A, token %B) {
entry:
alloca token
; CHECK: invalid type for alloca
ret void
}

4
test/Verifier/token4.ll Normal file
View File

@ -0,0 +1,4 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
@GV = external global token
; CHECK: invalid type for global variable

7
test/Verifier/token5.ll Normal file
View File

@ -0,0 +1,7 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
define void @f(token %A) {
entry:
ret void
}
; CHECK: Function takes token but isn't an intrinsic

7
test/Verifier/token6.ll Normal file
View File

@ -0,0 +1,7 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
define token @f() {
entry:
ret token undef
}
; CHECK: Functions returns a token but isn't an intrinsic

8
test/Verifier/token7.ll Normal file
View File

@ -0,0 +1,8 @@
; RUN: not llvm-as %s -o /dev/null 2>&1 | FileCheck %s
define void @f() {
entry:
call token () undef ()
ret void
}
; CHECK: Return type cannot be token for indirect call!