-//===-- SelectionDAGBuilder.h - Selection-DAG building --------------------===//
+//===-- SelectionDAGBuilder.h - Selection-DAG building --------*- C++ -*---===//
//
// The LLVM Compiler Infrastructure
//
#ifndef SELECTIONDAGBUILDER_H
#define SELECTIONDAGBUILDER_H
-#include "llvm/Constants.h"
-#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/DenseMap.h"
+#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/SelectionDAGNodes.h"
#include "llvm/CodeGen/ValueTypes.h"
+#include "llvm/IR/Constants.h"
#include "llvm/Support/CallSite.h"
#include "llvm/Support/ErrorHandling.h"
#include <vector>
class SIToFPInst;
class StoreInst;
class SwitchInst;
-class TargetData;
+class DataLayout;
+class TargetLibraryInfo;
class TargetLowering;
class TruncInst;
class UIToFPInst;
class UnreachableInst;
-class UnwindInst;
class VAArgInst;
class ZExtInst;
/// implementation that is parameterized by a TargetLowering object.
///
class SelectionDAGBuilder {
- /// CurDebugLoc - current file + line number. Changes as we build the DAG.
- DebugLoc CurDebugLoc;
+ /// CurInst - The current instruction being visited
+ const Instruction *CurInst;
DenseMap<const Value*, SDValue> NodeMap;
/// Case - A struct to record the Value for a switch case, and the
/// case's target basic block.
struct Case {
- Constant* Low;
- Constant* High;
+ const Constant *Low;
+ const Constant *High;
MachineBasicBlock* BB;
+ uint32_t ExtraWeight;
+
+ Case() : Low(0), High(0), BB(0), ExtraWeight(0) { }
+ Case(const Constant *low, const Constant *high, MachineBasicBlock *bb,
+ uint32_t extraweight) : Low(low), High(high), BB(bb),
+ ExtraWeight(extraweight) { }
- Case() : Low(0), High(0), BB(0) { }
- Case(Constant* low, Constant* high, MachineBasicBlock* bb) :
- Low(low), High(high), BB(bb) { }
APInt size() const {
const APInt &rHigh = cast<ConstantInt>(High)->getValue();
const APInt &rLow = cast<ConstantInt>(Low)->getValue();
uint64_t Mask;
MachineBasicBlock* BB;
unsigned Bits;
+ uint32_t ExtraWeight;
- CaseBits(uint64_t mask, MachineBasicBlock* bb, unsigned bits):
- Mask(mask), BB(bb), Bits(bits) { }
+ CaseBits(uint64_t mask, MachineBasicBlock* bb, unsigned bits,
+ uint32_t Weight):
+ Mask(mask), BB(bb), Bits(bits), ExtraWeight(Weight) { }
};
typedef std::vector<Case> CaseVector;
CaseBlock(ISD::CondCode cc, const Value *cmplhs, const Value *cmprhs,
const Value *cmpmiddle,
MachineBasicBlock *truebb, MachineBasicBlock *falsebb,
- MachineBasicBlock *me)
+ MachineBasicBlock *me,
+ uint32_t trueweight = 0, uint32_t falseweight = 0)
: CC(cc), CmpLHS(cmplhs), CmpMHS(cmpmiddle), CmpRHS(cmprhs),
- TrueBB(truebb), FalseBB(falsebb), ThisBB(me) {}
+ TrueBB(truebb), FalseBB(falsebb), ThisBB(me),
+ TrueWeight(trueweight), FalseWeight(falseweight) { }
+
// CC - the condition code to use for the case block's setcc node
ISD::CondCode CC;
+
// CmpLHS/CmpRHS/CmpMHS - The LHS/MHS/RHS of the comparison to emit.
// Emit by default LHS op RHS. MHS is used for range comparisons:
// If MHS is not null: (LHS <= MHS) and (MHS <= RHS).
const Value *CmpLHS, *CmpMHS, *CmpRHS;
+
// TrueBB/FalseBB - the block to branch to if the setcc is true/false.
MachineBasicBlock *TrueBB, *FalseBB;
+
// ThisBB - the block into which to emit the code for the setcc and branches
MachineBasicBlock *ThisBB;
+
+ // TrueWeight/FalseWeight - branch weights.
+ uint32_t TrueWeight, FalseWeight;
};
+
struct JumpTable {
JumpTable(unsigned R, unsigned J, MachineBasicBlock *M,
MachineBasicBlock *D): Reg(R), JTI(J), MBB(M), Default(D) {}
typedef std::pair<JumpTableHeader, JumpTable> JumpTableBlock;
struct BitTestCase {
- BitTestCase(uint64_t M, MachineBasicBlock* T, MachineBasicBlock* Tr):
- Mask(M), ThisBB(T), TargetBB(Tr) { }
+ BitTestCase(uint64_t M, MachineBasicBlock* T, MachineBasicBlock* Tr,
+ uint32_t Weight):
+ Mask(M), ThisBB(T), TargetBB(Tr), ExtraWeight(Weight) { }
uint64_t Mask;
MachineBasicBlock *ThisBB;
MachineBasicBlock *TargetBB;
+ uint32_t ExtraWeight;
};
typedef SmallVector<BitTestCase, 3> BitTestInfo;
struct BitTestBlock {
BitTestBlock(APInt F, APInt R, const Value* SV,
- unsigned Rg, EVT RgVT, bool E,
+ unsigned Rg, MVT RgVT, bool E,
MachineBasicBlock* P, MachineBasicBlock* D,
const BitTestInfo& C):
First(F), Range(R), SValue(SV), Reg(Rg), RegVT(RgVT), Emitted(E),
APInt Range;
const Value *SValue;
unsigned Reg;
- EVT RegVT;
+ MVT RegVT;
bool Emitted;
MachineBasicBlock *Parent;
MachineBasicBlock *Default;
BitTestInfo Cases;
};
-public:
- // TLI - This is information that describes the available target features we
- // need for lowering. This indicates when operations are unavailable,
- // implemented with a libcall, etc.
+ /// A class which encapsulates all of the information needed to generate a
+ /// stack protector check and signals to isel via its state being initialized
+ /// that a stack protector needs to be generated.
+ ///
+ /// *NOTE* The following is a high level documentation of SelectionDAG Stack
+ /// Protector Generation. The reason that it is placed here is for a lack of
+ /// other good places to stick it.
+ ///
+ /// High Level Overview of SelectionDAG Stack Protector Generation:
+ ///
+ /// Previously, generation of stack protectors was done exclusively in the
+ /// pre-SelectionDAG Codegen LLVM IR Pass "Stack Protector". This necessitated
+ /// splitting basic blocks at the IR level to create the success/failure basic
+ /// blocks in the tail of the basic block in question. As a result of this,
+ /// calls that would have qualified for the sibling call optimization were no
+ /// longer eligible for optimization since said calls were no longer right in
+ /// the "tail position" (i.e. the immediate predecessor of a ReturnInst
+ /// instruction).
+ ///
+ /// Then it was noticed that since the sibling call optimization causes the
+ /// callee to reuse the caller's stack, if we could delay the generation of
+ /// the stack protector check until later in CodeGen after the sibling call
+ /// decision was made, we get both the tail call optimization and the stack
+ /// protector check!
+ ///
+ /// A few goals in solving this problem were:
+ ///
+ /// 1. Preserve the architecture independence of stack protector generation.
+ ///
+ /// 2. Preserve the normal IR level stack protector check for platforms like
+ /// OpenBSD for which we support platform specific stack protector
+ /// generation.
+ ///
+ /// The main problem that guided the present solution is that one can not
+ /// solve this problem in an architecture independent manner at the IR level
+ /// only. This is because:
+ ///
+ /// 1. The decision on whether or not to perform a sibling call on certain
+ /// platforms (for instance i386) requires lower level information
+ /// related to available registers that can not be known at the IR level.
+ ///
+ /// 2. Even if the previous point were not true, the decision on whether to
+ /// perform a tail call is done in LowerCallTo in SelectionDAG which
+ /// occurs after the Stack Protector Pass. As a result, one would need to
+ /// put the relevant callinst into the stack protector check success
+ /// basic block (where the return inst is placed) and then move it back
+ /// later at SelectionDAG/MI time before the stack protector check if the
+ /// tail call optimization failed. The MI level option was nixed
+ /// immediately since it would require platform specific pattern
+ /// matching. The SelectionDAG level option was nixed because
+ /// SelectionDAG only processes one IR level basic block at a time
+ /// implying one could not create a DAG Combine to move the callinst.
+ ///
+ /// To get around this problem a few things were realized:
+ ///
+ /// 1. While one can not handle multiple IR level basic blocks at the
+ /// SelectionDAG Level, one can generate multiple machine basic blocks
+ /// for one IR level basic block. This is how we handle bit tests and
+ /// switches.
+ ///
+ /// 2. At the MI level, tail calls are represented via a special return
+ /// MIInst called "tcreturn". Thus if we know the basic block in which we
+ /// wish to insert the stack protector check, we get the correct behavior
+ /// by always inserting the stack protector check right before the return
+ /// statement. This is a "magical transformation" since no matter where
+ /// the stack protector check intrinsic is, we always insert the stack
+ /// protector check code at the end of the BB.
+ ///
+ /// Given the aforementioned constraints, the following solution was devised:
+ ///
+ /// 1. On platforms that do not support SelectionDAG stack protector check
+ /// generation, allow for the normal IR level stack protector check
+ /// generation to continue.
+ ///
+ /// 2. On platforms that do support SelectionDAG stack protector check
+ /// generation:
+ ///
+ /// a. Use the IR level stack protector pass to decide if a stack
+ /// protector is required/which BB we insert the stack protector check
+ /// in by reusing the logic already therein. If we wish to generate a
+ /// stack protector check in a basic block, we place a special IR
+ /// intrinsic called llvm.stackprotectorcheck right before the BB's
+ /// returninst or if there is a callinst that could potentially be
+ /// sibling call optimized, before the call inst.
+ ///
+ /// b. Then when a BB with said intrinsic is processed, we codegen the BB
+ /// normally via SelectBasicBlock. In said process, when we visit the
+ /// stack protector check, we do not actually emit anything into the
+ /// BB. Instead, we just initialize the stack protector descriptor
+ /// class (which involves stashing information/creating the success
+ /// mbbb and the failure mbb if we have not created one for this
+ /// function yet) and export the guard variable that we are going to
+ /// compare.
+ ///
+ /// c. After we finish selecting the basic block, in FinishBasicBlock if
+ /// the StackProtectorDescriptor attached to the SelectionDAGBuilder is
+ /// initialized, we first find a splice point in the parent basic block
+ /// before the terminator and then splice the terminator of said basic
+ /// block into the success basic block. Then we code-gen a new tail for
+ /// the parent basic block consisting of the two loads, the comparison,
+ /// and finally two branches to the success/failure basic blocks. We
+ /// conclude by code-gening the failure basic block if we have not
+ /// code-gened it already (all stack protector checks we generate in
+ /// the same function, use the same failure basic block).
+ class StackProtectorDescriptor {
+ public:
+ StackProtectorDescriptor() : ParentMBB(0), SuccessMBB(0), FailureMBB(0),
+ Guard(0) { }
+ ~StackProtectorDescriptor() { }
+
+ /// Returns true if all fields of the stack protector descriptor are
+ /// initialized implying that we should/are ready to emit a stack protector.
+ bool shouldEmitStackProtector() const {
+ return ParentMBB && SuccessMBB && FailureMBB && Guard;
+ }
+
+ /// Initialize the stack protector descriptor structure for a new basic
+ /// block.
+ void initialize(const BasicBlock *BB,
+ MachineBasicBlock *MBB,
+ const CallInst &StackProtCheckCall) {
+ // Make sure we are not initialized yet.
+ assert(!shouldEmitStackProtector() && "Stack Protector Descriptor is "
+ "already initialized!");
+ ParentMBB = MBB;
+ SuccessMBB = AddSuccessorMBB(BB, MBB);
+ FailureMBB = AddSuccessorMBB(BB, MBB, FailureMBB);
+ if (!Guard)
+ Guard = StackProtCheckCall.getArgOperand(0);
+ }
+
+ /// Reset state that changes when we handle different basic blocks.
+ ///
+ /// This currently includes:
+ ///
+ /// 1. The specific basic block we are generating a
+ /// stack protector for (ParentMBB).
+ ///
+ /// 2. The successor machine basic block that will contain the tail of
+ /// parent mbb after we create the stack protector check (SuccessMBB). This
+ /// BB is visited only on stack protector check success.
+ void resetPerBBState() {
+ ParentMBB = 0;
+ SuccessMBB = 0;
+ }
+
+ /// Reset state that only changes when we switch functions.
+ ///
+ /// This currently includes:
+ ///
+ /// 1. FailureMBB since we reuse the failure code path for all stack
+ /// protector checks created in an individual function.
+ ///
+ /// 2.The guard variable since the guard variable we are checking against is
+ /// always the same.
+ void resetPerFunctionState() {
+ FailureMBB = 0;
+ Guard = 0;
+ }
+
+ MachineBasicBlock *getParentMBB() { return ParentMBB; }
+ MachineBasicBlock *getSuccessMBB() { return SuccessMBB; }
+ MachineBasicBlock *getFailureMBB() { return FailureMBB; }
+ const Value *getGuard() { return Guard; }
+
+ private:
+ /// The basic block for which we are generating the stack protector.
+ ///
+ /// As a result of stack protector generation, we will splice the
+ /// terminators of this basic block into the successor mbb SuccessMBB and
+ /// replace it with a compare/branch to the successor mbbs
+ /// SuccessMBB/FailureMBB depending on whether or not the stack protector
+ /// was violated.
+ MachineBasicBlock *ParentMBB;
+
+ /// A basic block visited on stack protector check success that contains the
+ /// terminators of ParentMBB.
+ MachineBasicBlock *SuccessMBB;
+
+ /// This basic block visited on stack protector check failure that will
+ /// contain a call to __stack_chk_fail().
+ MachineBasicBlock *FailureMBB;
+
+ /// The guard variable which we will compare against the stored value in the
+ /// stack protector stack slot.
+ const Value *Guard;
+
+ /// Add a successor machine basic block to ParentMBB. If the successor mbb
+ /// has not been created yet (i.e. if SuccMBB = 0), then the machine basic
+ /// block will be created.
+ MachineBasicBlock *AddSuccessorMBB(const BasicBlock *BB,
+ MachineBasicBlock *ParentMBB,
+ MachineBasicBlock *SuccMBB = 0);
+ };
+
+private:
const TargetMachine &TM;
- const TargetLowering &TLI;
+public:
SelectionDAG &DAG;
- const TargetData *TD;
+ const DataLayout *TD;
AliasAnalysis *AA;
+ const TargetLibraryInfo *LibInfo;
/// SwitchCases - Vector of CaseBlock structures used to communicate
/// SwitchInst code generation information.
/// BitTestCases - Vector of BitTestBlock structures used to communicate
/// SwitchInst code generation information.
std::vector<BitTestBlock> BitTestCases;
+ /// A StackProtectorDescriptor structure used to communicate stack protector
+ /// information in between SelectBasicBlock and FinishBasicBlock.
+ StackProtectorDescriptor SPDescriptor;
// Emit PHI-node-operand constants only once even if used by multiple
// PHI nodes.
/// GFI - Garbage collection metadata for the function.
GCFunctionInfo *GFI;
+ /// LPadToCallSiteMap - Map a landing pad to the call site indexes.
+ DenseMap<MachineBasicBlock*, SmallVector<unsigned, 4> > LPadToCallSiteMap;
+
/// HasTailCall - This is set to true if a call in the current
/// block has been translated as a tail call. In this case,
/// no subsequent DAG nodes should be created.
SelectionDAGBuilder(SelectionDAG &dag, FunctionLoweringInfo &funcinfo,
CodeGenOpt::Level ol)
- : SDNodeOrder(0), TM(dag.getTarget()), TLI(dag.getTargetLoweringInfo()),
+ : CurInst(NULL), SDNodeOrder(0), TM(dag.getTarget()),
DAG(dag), FuncInfo(funcinfo), OptLevel(ol),
- HasTailCall(false), Context(dag.getContext()) {
+ HasTailCall(false) {
}
- void init(GCFunctionInfo *gfi, AliasAnalysis &aa);
+ void init(GCFunctionInfo *gfi, AliasAnalysis &aa,
+ const TargetLibraryInfo *li);
/// clear - Clear out the current SelectionDAG and the associated
/// state and prepare this SelectionDAGBuilder object to be used
void clear();
/// clearDanglingDebugInfo - Clear the dangling debug information
- /// map. This function is seperated from the clear so that debug
+ /// map. This function is separated from the clear so that debug
/// information that is dangling in a basic block can be properly
/// resolved in a different basic block. This allows the
/// SelectionDAG to resolve dangling debug information attached
///
SDValue getControlRoot();
- DebugLoc getCurDebugLoc() const { return CurDebugLoc; }
+ SDLoc getCurSDLoc() const {
+ return SDLoc(CurInst, SDNodeOrder);
+ }
+
+ DebugLoc getCurDebugLoc() const {
+ return CurInst ? CurInst->getDebugLoc() : DebugLoc();
+ }
unsigned getSDNodeOrder() const { return SDNodeOrder; }
void CopyValueToVirtualRegister(const Value *V, unsigned Reg);
- /// AssignOrderingToNode - Assign an ordering to the node. The order is gotten
- /// from how the code appeared in the source. The ordering is used by the
- /// scheduler to effectively turn off scheduling.
- void AssignOrderingToNode(const SDNode *Node);
-
void visit(const Instruction &I);
void visit(unsigned Opcode, const User &I);
MachineBasicBlock* Default,
MachineBasicBlock *SwitchBB);
- uint32_t getEdgeWeight(MachineBasicBlock *Src, MachineBasicBlock *Dst);
- void addSuccessorWithWeight(MachineBasicBlock *Src, MachineBasicBlock *Dst);
+ uint32_t getEdgeWeight(const MachineBasicBlock *Src,
+ const MachineBasicBlock *Dst) const;
+ void addSuccessorWithWeight(MachineBasicBlock *Src, MachineBasicBlock *Dst,
+ uint32_t Weight = 0);
public:
void visitSwitchCase(CaseBlock &CB,
MachineBasicBlock *SwitchBB);
+ void visitSPDescriptorParent(StackProtectorDescriptor &SPD,
+ MachineBasicBlock *ParentBB);
+ void visitSPDescriptorFailure(StackProtectorDescriptor &SPD);
void visitBitTestHeader(BitTestBlock &B, MachineBasicBlock *SwitchBB);
void visitBitTestCase(BitTestBlock &BB,
MachineBasicBlock* NextMBB,
+ uint32_t BranchWeightToNext,
unsigned Reg,
BitTestCase &B,
MachineBasicBlock *SwitchBB);
// These all get lowered before this pass.
void visitInvoke(const InvokeInst &I);
void visitResume(const ResumeInst &I);
- void visitUnwind(const UnwindInst &I);
void visitBinary(const User &I, unsigned OpCode);
void visitShift(const User &I, unsigned Opcode);
void visitAlloca(const AllocaInst &I);
void visitLoad(const LoadInst &I);
void visitStore(const StoreInst &I);
+ void visitAtomicCmpXchg(const AtomicCmpXchgInst &I);
+ void visitAtomicRMW(const AtomicRMWInst &I);
void visitFence(const FenceInst &I);
void visitPHI(const PHINode &I);
void visitCall(const CallInst &I);
bool visitMemCmpCall(const CallInst &I);
-
+ bool visitMemChrCall(const CallInst &I);
+ bool visitStrCpyCall(const CallInst &I, bool isStpcpy);
+ bool visitStrCmpCall(const CallInst &I);
+ bool visitStrLenCall(const CallInst &I);
+ bool visitStrNLenCall(const CallInst &I);
+ bool visitUnaryFloatCall(const CallInst &I, unsigned Opcode);
+ void visitAtomicLoad(const LoadInst &I);
+ void visitAtomicStore(const StoreInst &I);
+
void visitInlineAsm(ImmutableCallSite CS);
const char *visitIntrinsicCall(const CallInst &I, unsigned Intrinsic);
void visitTargetIntrinsic(const CallInst &I, unsigned Intrinsic);
- void visitPow(const CallInst &I);
- void visitExp2(const CallInst &I);
- void visitExp(const CallInst &I);
- void visitLog(const CallInst &I);
- void visitLog2(const CallInst &I);
- void visitLog10(const CallInst &I);
-
void visitVAStart(const CallInst &I);
void visitVAArg(const VAArgInst &I);
void visitVAEnd(const CallInst &I);
void visitUserOp2(const Instruction &I) {
llvm_unreachable("UserOp2 should not exist at instruction selection time!");
}
-
- const char *implVisitBinaryAtomic(const CallInst& I, ISD::NodeType Op);
- const char *implVisitAluOverflow(const CallInst &I, ISD::NodeType Op);
+
+ void processIntegerCallValue(const Instruction &I,
+ SDValue Value, bool IsSigned);
void HandlePHINodesInSuccessorBlocks(const BasicBlock *LLVMBB);