diff options
Diffstat (limited to 'lib/Target/X86/X86CallFrameOptimization.cpp')
| -rw-r--r-- | lib/Target/X86/X86CallFrameOptimization.cpp | 75 |
1 files changed, 43 insertions, 32 deletions
diff --git a/lib/Target/X86/X86CallFrameOptimization.cpp b/lib/Target/X86/X86CallFrameOptimization.cpp index 78bd2add8c3b..765af67de160 100644 --- a/lib/Target/X86/X86CallFrameOptimization.cpp +++ b/lib/Target/X86/X86CallFrameOptimization.cpp @@ -17,22 +17,35 @@ // //===----------------------------------------------------------------------===// -#include <algorithm> - -#include "X86.h" +#include "MCTargetDesc/X86BaseInfo.h" +#include "X86FrameLowering.h" #include "X86InstrInfo.h" #include "X86MachineFunctionInfo.h" +#include "X86RegisterInfo.h" #include "X86Subtarget.h" -#include "llvm/ADT/Statistic.h" +#include "llvm/ADT/DenseSet.h" +#include "llvm/ADT/SmallVector.h" +#include "llvm/ADT/StringRef.h" +#include "llvm/CodeGen/MachineBasicBlock.h" +#include "llvm/CodeGen/MachineFrameInfo.h" +#include "llvm/CodeGen/MachineFunction.h" #include "llvm/CodeGen/MachineFunctionPass.h" +#include "llvm/CodeGen/MachineInstr.h" #include "llvm/CodeGen/MachineInstrBuilder.h" -#include "llvm/CodeGen/MachineModuleInfo.h" +#include "llvm/CodeGen/MachineOperand.h" #include "llvm/CodeGen/MachineRegisterInfo.h" -#include "llvm/CodeGen/Passes.h" +#include "llvm/IR/DebugLoc.h" #include "llvm/IR/Function.h" -#include "llvm/Support/Debug.h" -#include "llvm/Support/raw_ostream.h" +#include "llvm/MC/MCDwarf.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/ErrorHandling.h" +#include "llvm/Support/MathExtras.h" #include "llvm/Target/TargetInstrInfo.h" +#include "llvm/Target/TargetRegisterInfo.h" +#include <cassert> +#include <cstddef> +#include <cstdint> +#include <iterator> using namespace llvm; @@ -44,6 +57,7 @@ static cl::opt<bool> cl::init(false), cl::Hidden); namespace { + class X86CallFrameOptimization : public MachineFunctionPass { public: X86CallFrameOptimization() : MachineFunctionPass(ID) {} @@ -53,30 +67,28 @@ public: private: // Information we know about a particular call site struct CallContext { - CallContext() - : FrameSetup(nullptr), Call(nullptr), SPCopy(nullptr), ExpectedDist(0), - MovVector(4, nullptr), NoStackParams(false), UsePush(false) {} + CallContext() : FrameSetup(nullptr), MovVector(4, nullptr) {} // Iterator referring to the frame setup instruction MachineBasicBlock::iterator FrameSetup; // Actual call instruction - MachineInstr *Call; + MachineInstr *Call = nullptr; // A copy of the stack pointer - MachineInstr *SPCopy; + MachineInstr *SPCopy = nullptr; // The total displacement of all passed parameters - int64_t ExpectedDist; + int64_t ExpectedDist = 0; // The sequence of movs used to pass the parameters SmallVector<MachineInstr *, 4> MovVector; // True if this call site has no stack parameters - bool NoStackParams; + bool NoStackParams = false; // True if this call site can use push instructions - bool UsePush; + bool UsePush = false; }; typedef SmallVector<CallContext, 8> ContextVector; @@ -102,7 +114,7 @@ private: StringRef getPassName() const override { return "X86 Optimize Call Frame"; } - const TargetInstrInfo *TII; + const X86InstrInfo *TII; const X86FrameLowering *TFL; const X86Subtarget *STI; MachineRegisterInfo *MRI; @@ -112,11 +124,8 @@ private: }; char X86CallFrameOptimization::ID = 0; -} // end anonymous namespace -FunctionPass *llvm::createX86CallFrameOptimization() { - return new X86CallFrameOptimization(); -} +} // end anonymous namespace // This checks whether the transformation is legal. // Also returns false in cases where it's potentially legal, but @@ -322,7 +331,6 @@ void X86CallFrameOptimization::collectCallInfo(MachineFunction &MF, // transformation. const X86RegisterInfo &RegInfo = *static_cast<const X86RegisterInfo *>(STI->getRegisterInfo()); - unsigned FrameDestroyOpcode = TII->getCallFrameDestroyOpcode(); // We expect to enter this at the beginning of a call sequence assert(I->getOpcode() == TII->getCallFrameSetupOpcode()); @@ -331,8 +339,7 @@ void X86CallFrameOptimization::collectCallInfo(MachineFunction &MF, // How much do we adjust the stack? This puts an upper bound on // the number of parameters actually passed on it. - unsigned int MaxAdjust = - FrameSetup->getOperand(0).getImm() >> Log2SlotSize; + unsigned int MaxAdjust = TII->getFrameSize(*FrameSetup) >> Log2SlotSize; // A zero adjustment means no stack parameters if (!MaxAdjust) { @@ -425,7 +432,7 @@ void X86CallFrameOptimization::collectCallInfo(MachineFunction &MF, return; Context.Call = &*I; - if ((++I)->getOpcode() != FrameDestroyOpcode) + if ((++I)->getOpcode() != TII->getCallFrameDestroyOpcode()) return; // Now, go through the vector, and see that we don't have any gaps, @@ -455,7 +462,7 @@ void X86CallFrameOptimization::adjustCallSequence(MachineFunction &MF, // PEI will end up finalizing the handling of this. MachineBasicBlock::iterator FrameSetup = Context.FrameSetup; MachineBasicBlock &MBB = *(FrameSetup->getParent()); - FrameSetup->getOperand(1).setImm(Context.ExpectedDist); + TII->setFrameAdjustment(*FrameSetup, Context.ExpectedDist); DebugLoc DL = FrameSetup->getDebugLoc(); bool Is64Bit = STI->is64Bit(); @@ -482,11 +489,10 @@ void X86CallFrameOptimization::adjustCallSequence(MachineFunction &MF, if (isInt<8>(Val)) PushOpcode = Is64Bit ? X86::PUSH64i8 : X86::PUSH32i8; } - Push = BuildMI(MBB, Context.Call, DL, TII->get(PushOpcode)) - .addOperand(PushOp); + Push = BuildMI(MBB, Context.Call, DL, TII->get(PushOpcode)).add(PushOp); break; case X86::MOV32mr: - case X86::MOV64mr: + case X86::MOV64mr: { unsigned int Reg = PushOp.getReg(); // If storing a 32-bit vreg on 64-bit targets, extend to a 64-bit vreg @@ -496,9 +502,9 @@ void X86CallFrameOptimization::adjustCallSequence(MachineFunction &MF, Reg = MRI->createVirtualRegister(&X86::GR64RegClass); BuildMI(MBB, Context.Call, DL, TII->get(X86::IMPLICIT_DEF), UndefReg); BuildMI(MBB, Context.Call, DL, TII->get(X86::INSERT_SUBREG), Reg) - .addReg(UndefReg) - .addOperand(PushOp) - .addImm(X86::sub_32bit); + .addReg(UndefReg) + .add(PushOp) + .addImm(X86::sub_32bit); } // If PUSHrmm is not slow on this target, try to fold the source of the @@ -525,6 +531,7 @@ void X86CallFrameOptimization::adjustCallSequence(MachineFunction &MF, } break; } + } // For debugging, when using SP-based CFA, we need to adjust the CFA // offset after each push. @@ -584,3 +591,7 @@ MachineInstr *X86CallFrameOptimization::canFoldIntoRegPush( return &DefMI; } + +FunctionPass *llvm::createX86CallFrameOptimization() { + return new X86CallFrameOptimization(); +} |