// Alias Analysis" by Zhang Q, Lyu M R, Yuan H, and Su Z. -- to summarize the
// papers, we build a graph of the uses of a variable, where each node is a
// memory location, and each edge is an action that happened on that memory
-// location. The "actions" can be one of Dereference, Reference, Assign, or
-// Assign.
+// location. The "actions" can be one of Dereference, Reference, or Assign.
//
// Two variables are considered as aliasing iff you can reach one value's node
// from the other value's node and the language formed by concatenating all of
//===----------------------------------------------------------------------===//
#include "StratifiedSets.h"
-#include "llvm/Analysis/Passes.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/Optional.h"
#include "llvm/ADT/None.h"
+#include "llvm/ADT/Optional.h"
#include "llvm/Analysis/AliasAnalysis.h"
+#include "llvm/Analysis/Passes.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Function.h"
-#include "llvm/IR/Instructions.h"
#include "llvm/IR/InstVisitor.h"
+#include "llvm/IR/Instructions.h"
#include "llvm/IR/ValueHandle.h"
#include "llvm/Pass.h"
#include "llvm/Support/Allocator.h"
+#include "llvm/Support/Compiler.h"
+#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cassert>
#include <forward_list>
+#include <memory>
#include <tuple>
using namespace llvm;
+#define DEBUG_TYPE "cfl-aa"
+
// Try to go from a Value* to a Function*. Never returns nullptr.
static Optional<Function *> parentFunctionOfValue(Value *);
// This notes that we should ignore those.
static bool hasUsefulEdges(Instruction *);
+const StratifiedIndex StratifiedLink::SetSentinel =
+ std::numeric_limits<StratifiedIndex>::max();
+
namespace {
// StratifiedInfo Attribute things.
typedef unsigned StratifiedAttr;
-constexpr unsigned MaxStratifiedAttrIndex = NumStratifiedAttrs;
-constexpr unsigned AttrAllIndex = 0;
-constexpr unsigned AttrGlobalIndex = 1;
-constexpr unsigned AttrFirstArgIndex = 2;
-constexpr unsigned AttrLastArgIndex = MaxStratifiedAttrIndex;
-constexpr unsigned AttrMaxNumArgs = AttrLastArgIndex - AttrFirstArgIndex;
-
-constexpr StratifiedAttr AttrNone = 0;
-constexpr StratifiedAttr AttrAll = ~AttrNone;
+LLVM_CONSTEXPR unsigned MaxStratifiedAttrIndex = NumStratifiedAttrs;
+LLVM_CONSTEXPR unsigned AttrAllIndex = 0;
+LLVM_CONSTEXPR unsigned AttrGlobalIndex = 1;
+LLVM_CONSTEXPR unsigned AttrUnknownIndex = 2;
+LLVM_CONSTEXPR unsigned AttrFirstArgIndex = 3;
+LLVM_CONSTEXPR unsigned AttrLastArgIndex = MaxStratifiedAttrIndex;
+LLVM_CONSTEXPR unsigned AttrMaxNumArgs = AttrLastArgIndex - AttrFirstArgIndex;
+
+LLVM_CONSTEXPR StratifiedAttr AttrNone = 0;
+LLVM_CONSTEXPR StratifiedAttr AttrUnknown = 1 << AttrUnknownIndex;
+LLVM_CONSTEXPR StratifiedAttr AttrAll = ~AttrNone;
// \brief StratifiedSets call for knowledge of "direction", so this is how we
// represent that locally.
StratifiedSets<Value *> Sets;
// Lots of functions have < 4 returns. Adjust as necessary.
SmallVector<Value *, 4> ReturnedValues;
+
+ FunctionInfo(StratifiedSets<Value *> &&S, SmallVector<Value *, 4> &&RV)
+ : Sets(std::move(S)), ReturnedValues(std::move(RV)) {}
};
struct CFLAliasAnalysis;
-struct FunctionHandle : public CallbackVH {
+struct FunctionHandle final : public CallbackVH {
FunctionHandle(Function *Fn, CFLAliasAnalysis *CFLAA)
: CallbackVH(Fn), CFLAA(CFLAA) {
assert(Fn != nullptr);
assert(CFLAA != nullptr);
}
- virtual ~FunctionHandle() {}
-
- virtual void deleted() override { removeSelfFromCache(); }
- virtual void allUsesReplacedWith(Value *) override { removeSelfFromCache(); }
+ void deleted() override { removeSelfFromCache(); }
+ void allUsesReplacedWith(Value *) override { removeSelfFromCache(); }
private:
CFLAliasAnalysis *CFLAA;
initializeCFLAliasAnalysisPass(*PassRegistry::getPassRegistry());
}
- virtual ~CFLAliasAnalysis() {}
+ ~CFLAliasAnalysis() override {}
- void getAnalysisUsage(AnalysisUsage &AU) const {
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
AliasAnalysis::getAnalysisUsage(AU);
}
return Iter->second;
}
- AliasResult query(const Location &LocA, const Location &LocB);
+ AliasResult query(const MemoryLocation &LocA, const MemoryLocation &LocB);
- AliasResult alias(const Location &LocA, const Location &LocB) override {
+ AliasResult alias(const MemoryLocation &LocA,
+ const MemoryLocation &LocB) override {
if (LocA.Ptr == LocB.Ptr) {
if (LocA.Size == LocB.Size) {
return MustAlias;
// Comparisons between global variables and other constants should be
// handled by BasicAA.
+ // TODO: ConstantExpr handling -- CFLAA may report NoAlias when comparing
+ // a GlobalValue and ConstantExpr, but every query needs to have at least
+ // one Value tied to a Function, and neither GlobalValues nor ConstantExprs
+ // are.
if (isa<Constant>(LocA.Ptr) && isa<Constant>(LocB.Ptr)) {
- return MayAlias;
+ return AliasAnalysis::alias(LocA, LocB);
}
- return query(LocA, LocB);
+ AliasResult QueryResult = query(LocA, LocB);
+ if (QueryResult == MayAlias)
+ return AliasAnalysis::alias(LocA, LocB);
+
+ return QueryResult;
}
- void initializePass() override { InitializeAliasAnalysis(this); }
+ bool doInitialization(Module &M) override;
};
void FunctionHandle::removeSelfFromCache() {
llvm_unreachable("Unsupported instruction encountered");
}
+ void visitPtrToIntInst(PtrToIntInst &Inst) {
+ auto *Ptr = Inst.getOperand(0);
+ Output.push_back(Edge(Ptr, Ptr, EdgeType::Assign, AttrUnknown));
+ }
+
+ void visitIntToPtrInst(IntToPtrInst &Inst) {
+ auto *Ptr = &Inst;
+ Output.push_back(Edge(Ptr, Ptr, EdgeType::Assign, AttrUnknown));
+ }
+
void visitCastInst(CastInst &Inst) {
- Output.push_back({&Inst, Inst.getOperand(0), EdgeType::Assign, AttrNone});
+ Output.push_back(
+ Edge(&Inst, Inst.getOperand(0), EdgeType::Assign, AttrNone));
}
void visitBinaryOperator(BinaryOperator &Inst) {
auto *Op1 = Inst.getOperand(0);
auto *Op2 = Inst.getOperand(1);
- Output.push_back({&Inst, Op1, EdgeType::Assign, AttrNone});
- Output.push_back({&Inst, Op2, EdgeType::Assign, AttrNone});
+ Output.push_back(Edge(&Inst, Op1, EdgeType::Assign, AttrNone));
+ Output.push_back(Edge(&Inst, Op2, EdgeType::Assign, AttrNone));
}
void visitAtomicCmpXchgInst(AtomicCmpXchgInst &Inst) {
auto *Ptr = Inst.getPointerOperand();
auto *Val = Inst.getNewValOperand();
- Output.push_back({Ptr, Val, EdgeType::Dereference, AttrNone});
+ Output.push_back(Edge(Ptr, Val, EdgeType::Dereference, AttrNone));
}
void visitAtomicRMWInst(AtomicRMWInst &Inst) {
auto *Ptr = Inst.getPointerOperand();
auto *Val = Inst.getValOperand();
- Output.push_back({Ptr, Val, EdgeType::Dereference, AttrNone});
+ Output.push_back(Edge(Ptr, Val, EdgeType::Dereference, AttrNone));
}
void visitPHINode(PHINode &Inst) {
- for (unsigned I = 0, E = Inst.getNumIncomingValues(); I != E; ++I) {
- Value *Val = Inst.getIncomingValue(I);
- Output.push_back({&Inst, Val, EdgeType::Assign, AttrNone});
+ for (Value *Val : Inst.incoming_values()) {
+ Output.push_back(Edge(&Inst, Val, EdgeType::Assign, AttrNone));
}
}
void visitGetElementPtrInst(GetElementPtrInst &Inst) {
auto *Op = Inst.getPointerOperand();
- Output.push_back({&Inst, Op, EdgeType::Assign, AttrNone});
+ Output.push_back(Edge(&Inst, Op, EdgeType::Assign, AttrNone));
for (auto I = Inst.idx_begin(), E = Inst.idx_end(); I != E; ++I)
- Output.push_back({&Inst, *I, EdgeType::Assign, AttrNone});
+ Output.push_back(Edge(&Inst, *I, EdgeType::Assign, AttrNone));
}
void visitSelectInst(SelectInst &Inst) {
- auto *Condition = Inst.getCondition();
- Output.push_back({&Inst, Condition, EdgeType::Assign, AttrNone});
+ // Condition is not processed here (The actual statement producing
+ // the condition result is processed elsewhere). For select, the
+ // condition is evaluated, but not loaded, stored, or assigned
+ // simply as a result of being the condition of a select.
+
auto *TrueVal = Inst.getTrueValue();
- Output.push_back({&Inst, TrueVal, EdgeType::Assign, AttrNone});
+ Output.push_back(Edge(&Inst, TrueVal, EdgeType::Assign, AttrNone));
auto *FalseVal = Inst.getFalseValue();
- Output.push_back({&Inst, FalseVal, EdgeType::Assign, AttrNone});
+ Output.push_back(Edge(&Inst, FalseVal, EdgeType::Assign, AttrNone));
}
void visitAllocaInst(AllocaInst &) {}
void visitLoadInst(LoadInst &Inst) {
auto *Ptr = Inst.getPointerOperand();
auto *Val = &Inst;
- Output.push_back({Val, Ptr, EdgeType::Reference, AttrNone});
+ Output.push_back(Edge(Val, Ptr, EdgeType::Reference, AttrNone));
}
void visitStoreInst(StoreInst &Inst) {
auto *Ptr = Inst.getPointerOperand();
auto *Val = Inst.getValueOperand();
- Output.push_back({Ptr, Val, EdgeType::Dereference, AttrNone});
+ Output.push_back(Edge(Ptr, Val, EdgeType::Dereference, AttrNone));
+ }
+
+ void visitVAArgInst(VAArgInst &Inst) {
+ // We can't fully model va_arg here. For *Ptr = Inst.getOperand(0), it does
+ // two things:
+ // 1. Loads a value from *((T*)*Ptr).
+ // 2. Increments (stores to) *Ptr by some target-specific amount.
+ // For now, we'll handle this like a landingpad instruction (by placing the
+ // result in its own group, and having that group alias externals).
+ auto *Val = &Inst;
+ Output.push_back(Edge(Val, Val, EdgeType::Assign, AttrAll));
}
static bool isFunctionExternal(Function *Fn) {
tryInterproceduralAnalysis(const SmallVectorImpl<Function *> &Fns,
Value *FuncValue,
const iterator_range<User::op_iterator> &Args) {
- constexpr unsigned ExpectedMaxArgs = 8;
- constexpr unsigned MaxSupportedArgs = 50;
+ const unsigned ExpectedMaxArgs = 8;
+ const unsigned MaxSupportedArgs = 50;
assert(Fns.size() > 0);
// I put this here to give us an upper bound on time taken by IPA. Is it
// really (realistically) needed? Keep in mind that we do have an n^2 algo.
- if (std::distance(Args.begin(), Args.end()) > MaxSupportedArgs)
+ if (std::distance(Args.begin(), Args.end()) > (int)MaxSupportedArgs)
return false;
// Exit early if we'll fail anyway
}
}
if (AddEdge)
- Output.push_back({FuncValue, ArgVal, EdgeType::Assign,
- StratifiedAttrs().flip()});
+ Output.push_back(Edge(FuncValue, ArgVal, EdgeType::Assign,
+ StratifiedAttrs().flip()));
}
if (Parameters.size() != Arguments.size())
continue;
auto NewAttrs = SubAttrs | MainAttrs;
- Output.push_back({MainVal, SubVal, EdgeType::Assign, NewAttrs});
+ Output.push_back(Edge(MainVal, SubVal, EdgeType::Assign, NewAttrs));
}
}
}
}
for (Value *V : Inst.arg_operands())
- Output.push_back({&Inst, V, EdgeType::Assign, AttrAll});
+ Output.push_back(Edge(&Inst, V, EdgeType::Assign, AttrAll));
}
void visitCallInst(CallInst &Inst) { visitCallLikeInst(Inst); }
void visitExtractElementInst(ExtractElementInst &Inst) {
auto *Ptr = Inst.getVectorOperand();
auto *Val = &Inst;
- Output.push_back({Val, Ptr, EdgeType::Reference, AttrNone});
+ Output.push_back(Edge(Val, Ptr, EdgeType::Reference, AttrNone));
}
void visitInsertElementInst(InsertElementInst &Inst) {
auto *Vec = Inst.getOperand(0);
auto *Val = Inst.getOperand(1);
- Output.push_back({&Inst, Vec, EdgeType::Assign, AttrNone});
- Output.push_back({&Inst, Val, EdgeType::Dereference, AttrNone});
+ Output.push_back(Edge(&Inst, Vec, EdgeType::Assign, AttrNone));
+ Output.push_back(Edge(&Inst, Val, EdgeType::Dereference, AttrNone));
}
void visitLandingPadInst(LandingPadInst &Inst) {
// Exceptions come from "nowhere", from our analysis' perspective.
// So we place the instruction its own group, noting that said group may
// alias externals
- Output.push_back({&Inst, &Inst, EdgeType::Assign, AttrAll});
+ Output.push_back(Edge(&Inst, &Inst, EdgeType::Assign, AttrAll));
}
void visitInsertValueInst(InsertValueInst &Inst) {
auto *Agg = Inst.getOperand(0);
auto *Val = Inst.getOperand(1);
- Output.push_back({&Inst, Agg, EdgeType::Assign, AttrNone});
- Output.push_back({&Inst, Val, EdgeType::Dereference, AttrNone});
+ Output.push_back(Edge(&Inst, Agg, EdgeType::Assign, AttrNone));
+ Output.push_back(Edge(&Inst, Val, EdgeType::Dereference, AttrNone));
}
void visitExtractValueInst(ExtractValueInst &Inst) {
auto *Ptr = Inst.getAggregateOperand();
- Output.push_back({&Inst, Ptr, EdgeType::Reference, AttrNone});
+ Output.push_back(Edge(&Inst, Ptr, EdgeType::Reference, AttrNone));
}
void visitShuffleVectorInst(ShuffleVectorInst &Inst) {
auto *From1 = Inst.getOperand(0);
auto *From2 = Inst.getOperand(1);
- Output.push_back({&Inst, From1, EdgeType::Assign, AttrNone});
- Output.push_back({&Inst, From2, EdgeType::Assign, AttrNone});
+ Output.push_back(Edge(&Inst, From1, EdgeType::Assign, AttrNone));
+ Output.push_back(Edge(&Inst, From2, EdgeType::Assign, AttrNone));
+ }
+
+ void visitConstantExpr(ConstantExpr *CE) {
+ switch (CE->getOpcode()) {
+ default:
+ llvm_unreachable("Unknown instruction type encountered!");
+// Build the switch statement using the Instruction.def file.
+#define HANDLE_INST(NUM, OPCODE, CLASS) \
+ case Instruction::OPCODE: \
+ visit##OPCODE(*(CLASS *)CE); \
+ break;
+#include "llvm/IR/Instruction.def"
+ }
}
};
typedef std::size_t Node;
private:
- constexpr static Node StartNode = Node(0);
+ const static Node StartNode = Node(0);
struct Edge {
EdgeTypeT Weight;
Node Other;
+ Edge(const EdgeTypeT &W, const Node &N) : Weight(W), Other(N) {}
+
bool operator==(const Edge &E) const {
return Weight == E.Weight && Other == E.Other;
}
// ----- Various Edge iterators for the graph ----- //
// \brief Iterator for edges. Because this graph is bidirected, we don't
- // allow modificaiton of the edges using this iterator. Additionally, the
+ // allow modification of the edges using this iterator. Additionally, the
// iterator becomes invalid if you add edges to or from the node you're
// getting the edges of.
struct EdgeIterator : public std::iterator<std::forward_iterator_tag,
// ----- Actual graph-related things ----- //
- WeightedBidirectionalGraph() = default;
+ WeightedBidirectionalGraph() {}
WeightedBidirectionalGraph(WeightedBidirectionalGraph<EdgeTypeT> &&Other)
: NodeImpls(std::move(Other.NodeImpls)) {}
assert(inbounds(To));
auto &FromNode = getNode(From);
auto &ToNode = getNode(To);
- FromNode.Edges.push_back(Edge{Weight, To});
- ToNode.Edges.push_back(Edge{ReverseWeight, From});
+ FromNode.Edges.push_back(Edge(Weight, To));
+ ToNode.Edges.push_back(Edge(ReverseWeight, From));
}
EdgeIterable edgesFor(const Node &N) const {
static void argsToEdges(CFLAliasAnalysis &, Instruction *,
SmallVectorImpl<Edge> &);
+// Gets edges of the given ConstantExpr*, writing them to the SmallVector*.
+static void argsToEdges(CFLAliasAnalysis &, ConstantExpr *,
+ SmallVectorImpl<Edge> &);
+
// Gets the "Level" that one should travel in StratifiedSets
// given an EdgeType.
static Level directionOfEdgeType(EdgeType);
static void buildGraphFrom(CFLAliasAnalysis &, Function *,
SmallVectorImpl<Value *> &, NodeMapT &, GraphT &);
+// Gets the edges of a ConstantExpr as if it was an Instruction. This
+// function also acts on any nested ConstantExprs, adding the edges
+// of those to the given SmallVector as well.
+static void constexprToEdges(CFLAliasAnalysis &, ConstantExpr &,
+ SmallVectorImpl<Edge> &);
+
+// Given an Instruction, this will add it to the graph, along with any
+// Instructions that are potentially only available from said Instruction
+// For example, given the following line:
+// %0 = load i16* getelementptr ([1 x i16]* @a, 0, 0), align 2
+// addInstructionToGraph would add both the `load` and `getelementptr`
+// instructions to the graph appropriately.
+static void addInstructionToGraph(CFLAliasAnalysis &, Instruction &,
+ SmallVectorImpl<Value *> &, NodeMapT &,
+ GraphT &);
+
+// Notes whether it would be pointless to add the given Value to our sets.
+static bool canSkipAddingToSets(Value *Val);
+
// Builds the graph + StratifiedSets for a function.
static FunctionInfo buildSetsFrom(CFLAliasAnalysis &, Function *);
return !isa<CmpInst>(Inst) && !isa<FenceInst>(Inst) && !IsNonInvokeTerminator;
}
+static bool hasUsefulEdges(ConstantExpr *CE) {
+ // ConstantExpr doesn't have terminators, invokes, or fences, so only needs
+ // to check for compares.
+ return CE->getOpcode() != Instruction::ICmp &&
+ CE->getOpcode() != Instruction::FCmp;
+}
+
static Optional<StratifiedAttr> valueToAttrIndex(Value *Val) {
if (isa<GlobalValue>(Val))
return AttrGlobalIndex;
if (auto *Arg = dyn_cast<Argument>(Val))
- if (!Arg->hasNoAliasAttr())
+ // Only pointer arguments should have the argument attribute,
+ // because things can't escape through scalars without us seeing a
+ // cast, and thus, interaction with them doesn't matter.
+ if (!Arg->hasNoAliasAttr() && Arg->getType()->isPointerTy())
return argNumberToAttrIndex(Arg->getArgNo());
return NoneType();
}
static StratifiedAttr argNumberToAttrIndex(unsigned ArgNum) {
- if (ArgNum > AttrMaxNumArgs)
+ if (ArgNum >= AttrMaxNumArgs)
return AttrAllIndex;
return ArgNum + AttrFirstArgIndex;
}
static void argsToEdges(CFLAliasAnalysis &Analysis, Instruction *Inst,
SmallVectorImpl<Edge> &Output) {
+ assert(hasUsefulEdges(Inst) &&
+ "Expected instructions to have 'useful' edges");
GetEdgesVisitor v(Analysis, Output);
v.visit(Inst);
}
+static void argsToEdges(CFLAliasAnalysis &Analysis, ConstantExpr *CE,
+ SmallVectorImpl<Edge> &Output) {
+ assert(hasUsefulEdges(CE) && "Expected constant expr to have 'useful' edges");
+ GetEdgesVisitor v(Analysis, Output);
+ v.visitConstantExpr(CE);
+}
+
static Level directionOfEdgeType(EdgeType Weight) {
switch (Weight) {
case EdgeType::Reference:
llvm_unreachable("Incomplete switch coverage");
}
-// Aside: We may remove graph construction entirely, because it doesn't really
-// buy us much that we don't already have. I'd like to add interprocedural
-// analysis prior to this however, in case that somehow requires the graph
-// produced by this for efficient execution
-static void buildGraphFrom(CFLAliasAnalysis &Analysis, Function *Fn,
- SmallVectorImpl<Value *> &ReturnedValues,
- NodeMapT &Map, GraphT &Graph) {
+static void constexprToEdges(CFLAliasAnalysis &Analysis,
+ ConstantExpr &CExprToCollapse,
+ SmallVectorImpl<Edge> &Results) {
+ SmallVector<ConstantExpr *, 4> Worklist;
+ Worklist.push_back(&CExprToCollapse);
+
+ SmallVector<Edge, 8> ConstexprEdges;
+ SmallPtrSet<ConstantExpr *, 4> Visited;
+ while (!Worklist.empty()) {
+ auto *CExpr = Worklist.pop_back_val();
+
+ if (!hasUsefulEdges(CExpr))
+ continue;
+
+ ConstexprEdges.clear();
+ argsToEdges(Analysis, CExpr, ConstexprEdges);
+ for (auto &Edge : ConstexprEdges) {
+ if (auto *Nested = dyn_cast<ConstantExpr>(Edge.From))
+ if (Visited.insert(Nested).second)
+ Worklist.push_back(Nested);
+
+ if (auto *Nested = dyn_cast<ConstantExpr>(Edge.To))
+ if (Visited.insert(Nested).second)
+ Worklist.push_back(Nested);
+ }
+
+ Results.append(ConstexprEdges.begin(), ConstexprEdges.end());
+ }
+}
+
+static void addInstructionToGraph(CFLAliasAnalysis &Analysis, Instruction &Inst,
+ SmallVectorImpl<Value *> &ReturnedValues,
+ NodeMapT &Map, GraphT &Graph) {
const auto findOrInsertNode = [&Map, &Graph](Value *Val) {
auto Pair = Map.insert(std::make_pair(Val, GraphT::Node()));
auto &Iter = Pair.first;
return Iter->second;
};
+ // We don't want the edges of most "return" instructions, but we *do* want
+ // to know what can be returned.
+ if (isa<ReturnInst>(&Inst))
+ ReturnedValues.push_back(&Inst);
+
+ if (!hasUsefulEdges(&Inst))
+ return;
+
SmallVector<Edge, 8> Edges;
- for (auto &Bb : Fn->getBasicBlockList()) {
- for (auto &Inst : Bb.getInstList()) {
- // We don't want the edges of most "return" instructions, but we *do* want
- // to know what can be returned.
- if (auto *Ret = dyn_cast<ReturnInst>(&Inst))
- ReturnedValues.push_back(Ret);
-
- if (!hasUsefulEdges(&Inst))
- continue;
+ argsToEdges(Analysis, &Inst, Edges);
+
+ // In the case of an unused alloca (or similar), edges may be empty. Note
+ // that it exists so we can potentially answer NoAlias.
+ if (Edges.empty()) {
+ auto MaybeVal = getTargetValue(&Inst);
+ assert(MaybeVal.hasValue());
+ auto *Target = *MaybeVal;
+ findOrInsertNode(Target);
+ return;
+ }
- Edges.clear();
- argsToEdges(Analysis, &Inst, Edges);
+ const auto addEdgeToGraph = [&Graph, &findOrInsertNode](const Edge &E) {
+ auto To = findOrInsertNode(E.To);
+ auto From = findOrInsertNode(E.From);
+ auto FlippedWeight = flipWeight(E.Weight);
+ auto Attrs = E.AdditionalAttrs;
+ Graph.addEdge(From, To, std::make_pair(E.Weight, Attrs),
+ std::make_pair(FlippedWeight, Attrs));
+ };
- // In the case of an unused alloca (or similar), edges may be empty. Note
- // that it exists so we can potentially answer NoAlias.
- if (Edges.empty()) {
- auto MaybeVal = getTargetValue(&Inst);
- assert(MaybeVal.hasValue());
- auto *Target = *MaybeVal;
- findOrInsertNode(Target);
- continue;
- }
+ SmallVector<ConstantExpr *, 4> ConstantExprs;
+ for (const Edge &E : Edges) {
+ addEdgeToGraph(E);
+ if (auto *Constexpr = dyn_cast<ConstantExpr>(E.To))
+ ConstantExprs.push_back(Constexpr);
+ if (auto *Constexpr = dyn_cast<ConstantExpr>(E.From))
+ ConstantExprs.push_back(Constexpr);
+ }
- for (const Edge &E : Edges) {
- auto To = findOrInsertNode(E.To);
- auto From = findOrInsertNode(E.From);
- auto FlippedWeight = flipWeight(E.Weight);
- auto Attrs = E.AdditionalAttrs;
- Graph.addEdge(From, To, {E.Weight, Attrs}, {FlippedWeight, Attrs});
- }
- }
+ for (ConstantExpr *CE : ConstantExprs) {
+ Edges.clear();
+ constexprToEdges(Analysis, *CE, Edges);
+ std::for_each(Edges.begin(), Edges.end(), addEdgeToGraph);
}
}
+// Aside: We may remove graph construction entirely, because it doesn't really
+// buy us much that we don't already have. I'd like to add interprocedural
+// analysis prior to this however, in case that somehow requires the graph
+// produced by this for efficient execution
+static void buildGraphFrom(CFLAliasAnalysis &Analysis, Function *Fn,
+ SmallVectorImpl<Value *> &ReturnedValues,
+ NodeMapT &Map, GraphT &Graph) {
+ for (auto &Bb : Fn->getBasicBlockList())
+ for (auto &Inst : Bb.getInstList())
+ addInstructionToGraph(Analysis, Inst, ReturnedValues, Map, Graph);
+}
+
+static bool canSkipAddingToSets(Value *Val) {
+ // Constants can share instances, which may falsely unify multiple
+ // sets, e.g. in
+ // store i32* null, i32** %ptr1
+ // store i32* null, i32** %ptr2
+ // clearly ptr1 and ptr2 should not be unified into the same set, so
+ // we should filter out the (potentially shared) instance to
+ // i32* null.
+ if (isa<Constant>(Val)) {
+ bool Container = isa<ConstantVector>(Val) || isa<ConstantArray>(Val) ||
+ isa<ConstantStruct>(Val);
+ // TODO: Because all of these things are constant, we can determine whether
+ // the data is *actually* mutable at graph building time. This will probably
+ // come for free/cheap with offset awareness.
+ bool CanStoreMutableData =
+ isa<GlobalValue>(Val) || isa<ConstantExpr>(Val) || Container;
+ return !CanStoreMutableData;
+ }
+
+ return false;
+}
+
static FunctionInfo buildSetsFrom(CFLAliasAnalysis &Analysis, Function *Fn) {
NodeMapT Map;
GraphT Graph;
DenseMap<GraphT::Node, Value *> NodeValueMap;
NodeValueMap.resize(Map.size());
for (const auto &Pair : Map)
- NodeValueMap.insert({Pair.second, Pair.first});
+ NodeValueMap.insert(std::make_pair(Pair.second, Pair.first));
const auto findValueOrDie = [&NodeValueMap](GraphT::Node Node) {
auto ValIter = NodeValueMap.find(Node);
while (!Worklist.empty()) {
auto Node = Worklist.pop_back_val();
auto *CurValue = findValueOrDie(Node);
- if (isa<Constant>(CurValue) && !isa<GlobalValue>(CurValue))
+ if (canSkipAddingToSets(CurValue))
continue;
for (const auto &EdgeTuple : Graph.edgesFor(Node)) {
auto &OtherNode = std::get<1>(EdgeTuple);
auto *OtherValue = findValueOrDie(OtherNode);
- if (isa<Constant>(OtherValue) && !isa<GlobalValue>(OtherValue))
+ if (canSkipAddingToSets(OtherValue))
continue;
bool Added;
break;
}
- if (Added) {
- auto Aliasing = Weight.second;
- if (auto MaybeCurIndex = valueToAttrIndex(CurValue))
- Aliasing.set(*MaybeCurIndex);
- if (auto MaybeOtherIndex = valueToAttrIndex(OtherValue))
- Aliasing.set(*MaybeOtherIndex);
- Builder.noteAttributes(CurValue, Aliasing);
- Builder.noteAttributes(OtherValue, Aliasing);
+ auto Aliasing = Weight.second;
+ if (auto MaybeCurIndex = valueToAttrIndex(CurValue))
+ Aliasing.set(*MaybeCurIndex);
+ if (auto MaybeOtherIndex = valueToAttrIndex(OtherValue))
+ Aliasing.set(*MaybeOtherIndex);
+ Builder.noteAttributes(CurValue, Aliasing);
+ Builder.noteAttributes(OtherValue, Aliasing);
+
+ if (Added)
Worklist.push_back(OtherNode);
- }
}
}
}
// things that were present during construction being present in the graph.
// So, we add all present arguments here.
for (auto &Arg : Fn->args()) {
- Builder.add(&Arg);
+ if (!Builder.add(&Arg))
+ continue;
+
+ auto Attrs = valueToAttrIndex(&Arg);
+ if (Attrs.hasValue())
+ Builder.noteAttributes(&Arg, *Attrs);
}
- return {Builder.build(), std::move(ReturnedValues)};
+ return FunctionInfo(Builder.build(), std::move(ReturnedValues));
}
void CFLAliasAnalysis::scan(Function *Fn) {
- auto InsertPair = Cache.insert({Fn, Optional<FunctionInfo>()});
+ auto InsertPair = Cache.insert(std::make_pair(Fn, Optional<FunctionInfo>()));
(void)InsertPair;
assert(InsertPair.second &&
"Trying to scan a function that has already been cached");
Handles.push_front(FunctionHandle(Fn, this));
}
-AliasAnalysis::AliasResult
-CFLAliasAnalysis::query(const AliasAnalysis::Location &LocA,
- const AliasAnalysis::Location &LocB) {
+AliasResult CFLAliasAnalysis::query(const MemoryLocation &LocA,
+ const MemoryLocation &LocB) {
auto *ValA = const_cast<Value *>(LocA.Ptr);
auto *ValB = const_cast<Value *>(LocB.Ptr);
auto MaybeFnA = parentFunctionOfValue(ValA);
auto MaybeFnB = parentFunctionOfValue(ValB);
if (!MaybeFnA.hasValue() && !MaybeFnB.hasValue()) {
- llvm_unreachable("Don't know how to extract the parent function "
- "from values A or B");
+ // The only times this is known to happen are when globals + InlineAsm
+ // are involved
+ DEBUG(dbgs() << "CFLAA: could not extract parent function information.\n");
+ return MayAlias;
}
if (MaybeFnA.hasValue()) {
auto &Sets = MaybeInfo->Sets;
auto MaybeA = Sets.find(ValA);
if (!MaybeA.hasValue())
- return AliasAnalysis::MayAlias;
+ return MayAlias;
auto MaybeB = Sets.find(ValB);
if (!MaybeB.hasValue())
- return AliasAnalysis::MayAlias;
+ return MayAlias;
auto SetA = *MaybeA;
auto SetB = *MaybeB;
+ auto AttrsA = Sets.getLink(SetA.Index).Attrs;
+ auto AttrsB = Sets.getLink(SetB.Index).Attrs;
+
+ // Stratified set attributes are used as markets to signify whether a member
+ // of a StratifiedSet (or a member of a set above the current set) has
+ // interacted with either arguments or globals. "Interacted with" meaning
+ // its value may be different depending on the value of an argument or
+ // global. The thought behind this is that, because arguments and globals
+ // may alias each other, if AttrsA and AttrsB have touched args/globals,
+ // we must conservatively say that they alias. However, if at least one of
+ // the sets has no values that could legally be altered by changing the value
+ // of an argument or global, then we don't have to be as conservative.
+ if (AttrsA.any() && AttrsB.any())
+ return MayAlias;
+
+ // We currently unify things even if the accesses to them may not be in
+ // bounds, so we can't return partial alias here because we don't
+ // know whether the pointer is really within the object or not.
+ // IE Given an out of bounds GEP and an alloca'd pointer, we may
+ // unify the two. We can't return partial alias for this case.
+ // Since we do not currently track enough information to
+ // differentiate
if (SetA.Index == SetB.Index)
- return AliasAnalysis::PartialAlias;
+ return MayAlias;
- auto AttrsA = Sets.getLink(SetA.Index).Attrs;
- auto AttrsB = Sets.getLink(SetB.Index).Attrs;
- auto CombinedAttrs = AttrsA | AttrsB;
- if (CombinedAttrs.any())
- return AliasAnalysis::PartialAlias;
+ return NoAlias;
+}
- return AliasAnalysis::NoAlias;
+bool CFLAliasAnalysis::doInitialization(Module &M) {
+ InitializeAliasAnalysis(this, &M.getDataLayout());
+ return true;
}