#include "llvm/ADT/Statistic.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/IR/Function.h"
// Information we know about a particular call site
struct CallContext {
CallContext()
- : Call(nullptr), SPCopy(nullptr), ExpectedDist(0),
- MovVector(4, nullptr), NoStackParams(false), UsePush(false){};
+ : FrameSetup(nullptr), Call(nullptr), SPCopy(nullptr), ExpectedDist(0),
+ MovVector(4, nullptr), NoStackParams(false), UsePush(false){}
- // Actuall call instruction
+ // Iterator referring to the frame setup instruction
+ MachineBasicBlock::iterator FrameSetup;
+
+ // Actual call instruction
MachineInstr *Call;
// A copy of the stack pointer
bool UsePush;
};
- typedef DenseMap<MachineInstr *, CallContext> ContextMap;
+ typedef SmallVector<CallContext, 8> ContextVector;
bool isLegal(MachineFunction &MF);
- bool isProfitable(MachineFunction &MF, ContextMap &CallSeqMap);
+ bool isProfitable(MachineFunction &MF, ContextVector &CallSeqMap);
void collectCallInfo(MachineFunction &MF, MachineBasicBlock &MBB,
MachineBasicBlock::iterator I, CallContext &Context);
- bool adjustCallSequence(MachineFunction &MF, MachineBasicBlock::iterator I,
- const CallContext &Context);
+ bool adjustCallSequence(MachineFunction &MF, const CallContext &Context);
MachineInstr *canFoldIntoRegPush(MachineBasicBlock::iterator FrameSetup,
unsigned Reg);
const char *getPassName() const override { return "X86 Optimize Call Frame"; }
const TargetInstrInfo *TII;
- const TargetFrameLowering *TFL;
+ const X86FrameLowering *TFL;
+ const X86Subtarget *STI;
const MachineRegisterInfo *MRI;
static char ID;
};
// No point in running this in 64-bit mode, since some arguments are
// passed in-register in all common calling conventions, so the pattern
// we're looking for will never match.
- const X86Subtarget &STI = MF.getSubtarget<X86Subtarget>();
- if (STI.is64Bit())
+ if (STI->is64Bit())
+ return false;
+
+ // We can't encode multiple DW_CFA_GNU_args_size or DW_CFA_def_cfa_offset
+ // in the compact unwind encoding that Darwin uses. So, bail if there
+ // is a danger of that being generated.
+ if (STI->isTargetDarwin() &&
+ (!MF.getMMI().getLandingPads().empty() ||
+ (MF.getFunction()->needsUnwindTableEntry() && !TFL->hasFP(MF))))
return false;
// You would expect straight-line code between call-frame setup and
// Check whether this trasnformation is profitable for a particular
// function - in terms of code size.
bool X86CallFrameOptimization::isProfitable(MachineFunction &MF,
- ContextMap &CallSeqMap) {
+ ContextVector &CallSeqVector) {
// This transformation is always a win when we do not expect to have
// a reserved call frame. Under other circumstances, it may be either
// a win or a loss, and requires a heuristic.
return true;
// Don't do this when not optimizing for size.
- bool OptForSize =
- MF.getFunction()->hasFnAttribute(Attribute::OptimizeForSize) ||
- MF.getFunction()->hasFnAttribute(Attribute::MinSize);
-
- if (!OptForSize)
+ if (!MF.getFunction()->optForSize())
return false;
unsigned StackAlign = TFL->getStackAlignment();
int64_t Advantage = 0;
- for (auto CC : CallSeqMap) {
+ for (auto CC : CallSeqVector) {
// Call sites where no parameters are passed on the stack
// do not affect the cost, since there needs to be no
// stack adjustment.
- if (CC.second.NoStackParams)
+ if (CC.NoStackParams)
continue;
- if (!CC.second.UsePush) {
+ if (!CC.UsePush) {
// If we don't use pushes for a particular call site,
// we pay for not having a reserved call frame with an
// additional sub/add esp pair. The cost is ~3 bytes per instruction,
// We'll need a add after the call.
Advantage -= 3;
// If we have to realign the stack, we'll also need and sub before
- if (CC.second.ExpectedDist % StackAlign)
+ if (CC.ExpectedDist % StackAlign)
Advantage -= 3;
// Now, for each push, we save ~3 bytes. For small constants, we actually,
// save more (up to 5 bytes), but 3 should be a good approximation.
- Advantage += (CC.second.ExpectedDist / 4) * 3;
+ Advantage += (CC.ExpectedDist / 4) * 3;
}
}
}
bool X86CallFrameOptimization::runOnMachineFunction(MachineFunction &MF) {
- TII = MF.getSubtarget().getInstrInfo();
- TFL = MF.getSubtarget().getFrameLowering();
+ STI = &MF.getSubtarget<X86Subtarget>();
+ TII = STI->getInstrInfo();
+ TFL = STI->getFrameLowering();
MRI = &MF.getRegInfo();
if (!isLegal(MF))
bool Changed = false;
- ContextMap CallSeqMap;
+ ContextVector CallSeqVector;
for (MachineFunction::iterator BB = MF.begin(), E = MF.end(); BB != E; ++BB)
for (MachineBasicBlock::iterator I = BB->begin(); I != BB->end(); ++I)
if (I->getOpcode() == FrameSetupOpcode) {
- CallContext &Context = CallSeqMap[I];
+ CallContext Context;
collectCallInfo(MF, *BB, I, Context);
+ CallSeqVector.push_back(Context);
}
- if (!isProfitable(MF, CallSeqMap))
+ if (!isProfitable(MF, CallSeqVector))
return false;
- for (auto CC : CallSeqMap)
- if (CC.second.UsePush)
- Changed |= adjustCallSequence(MF, CC.first, CC.second);
+ for (auto CC : CallSeqVector)
+ if (CC.UsePush)
+ Changed |= adjustCallSequence(MF, CC);
return Changed;
}
// Check that this particular call sequence is amenable to the
// transformation.
const X86RegisterInfo &RegInfo = *static_cast<const X86RegisterInfo *>(
- MF.getSubtarget().getRegisterInfo());
- unsigned StackPtr = RegInfo.getStackRegister();
+ STI->getRegisterInfo());
unsigned FrameDestroyOpcode = TII->getCallFrameDestroyOpcode();
// We expect to enter this at the beginning of a call sequence
assert(I->getOpcode() == TII->getCallFrameSetupOpcode());
MachineBasicBlock::iterator FrameSetup = I++;
+ Context.FrameSetup = FrameSetup;
// How much do we adjust the stack? This puts an upper bound on
// the number of parameters actually passed on it.
if (!I->isCopy() || !I->getOperand(0).isReg())
return;
Context.SPCopy = I++;
- StackPtr = Context.SPCopy->getOperand(0).getReg();
+
+ unsigned StackPtr = Context.SPCopy->getOperand(0).getReg();
// Scan the call setup sequence for the pattern we're looking for.
// We only handle a simple case - a sequence of MOV32mi or MOV32mr
}
bool X86CallFrameOptimization::adjustCallSequence(MachineFunction &MF,
- MachineBasicBlock::iterator I,
const CallContext &Context) {
// Ok, we can in fact do the transformation for this call.
// Do not remove the FrameSetup instruction, but adjust the parameters.
// PEI will end up finalizing the handling of this.
- MachineBasicBlock::iterator FrameSetup = I;
- MachineBasicBlock &MBB = *(I->getParent());
+ MachineBasicBlock::iterator FrameSetup = Context.FrameSetup;
+ MachineBasicBlock &MBB = *(FrameSetup->getParent());
FrameSetup->getOperand(1).setImm(Context.ExpectedDist);
- DebugLoc DL = I->getDebugLoc();
+ DebugLoc DL = FrameSetup->getDebugLoc();
// Now, iterate through the vector in reverse order, and replace the movs
// with pushes. MOVmi/MOVmr doesn't have any defs, so no need to
// replace uses.
for (int Idx = (Context.ExpectedDist / 4) - 1; Idx >= 0; --Idx) {
MachineBasicBlock::iterator MOV = *Context.MovVector[Idx];
MachineOperand PushOp = MOV->getOperand(X86::AddrNumOperands);
+ MachineBasicBlock::iterator Push = nullptr;
if (MOV->getOpcode() == X86::MOV32mi) {
unsigned PushOpcode = X86::PUSHi32;
// If the operand is a small (8-bit) immediate, we can use a
if (isInt<8>(Val))
PushOpcode = X86::PUSH32i8;
}
- BuildMI(MBB, Context.Call, DL, TII->get(PushOpcode)).addOperand(PushOp);
+ Push = BuildMI(MBB, Context.Call, DL, TII->get(PushOpcode))
+ .addOperand(PushOp);
} else {
unsigned int Reg = PushOp.getReg();
// If PUSHrmm is not slow on this target, try to fold the source of the
// push into the instruction.
- const X86Subtarget &ST = MF.getSubtarget<X86Subtarget>();
- bool SlowPUSHrmm = ST.isAtom() || ST.isSLM();
+ bool SlowPUSHrmm = STI->isAtom() || STI->isSLM();
// Check that this is legal to fold. Right now, we're extremely
// conservative about that.
MachineInstr *DefMov = nullptr;
if (!SlowPUSHrmm && (DefMov = canFoldIntoRegPush(FrameSetup, Reg))) {
- MachineInstr *Push =
- BuildMI(MBB, Context.Call, DL, TII->get(X86::PUSH32rmm));
+ Push = BuildMI(MBB, Context.Call, DL, TII->get(X86::PUSH32rmm));
unsigned NumOps = DefMov->getDesc().getNumOperands();
for (unsigned i = NumOps - X86::AddrNumOperands; i != NumOps; ++i)
DefMov->eraseFromParent();
} else {
- BuildMI(MBB, Context.Call, DL, TII->get(X86::PUSH32r))
+ Push = BuildMI(MBB, Context.Call, DL, TII->get(X86::PUSH32r))
.addReg(Reg)
.getInstr();
}
}
+ // For debugging, when using SP-based CFA, we need to adjust the CFA
+ // offset after each push.
+ // TODO: This is needed only if we require precise CFA.
+ if (!TFL->hasFP(MF))
+ TFL->BuildCFI(MBB, std::next(Push), DL,
+ MCCFIInstruction::createAdjustCfaOffset(nullptr, 4));
+
MBB.erase(MOV);
}
DefMI->getParent() != FrameSetup->getParent())
return nullptr;
- // Now, make sure everything else up until the ADJCALLSTACK is a sequence
- // of MOVs. To be less conservative would require duplicating a lot of the
- // logic from PeepholeOptimizer.
- // FIXME: A possibly better approach would be to teach the PeepholeOptimizer
- // to be smarter about folding into pushes.
+ // Make sure we don't have any instructions between DefMI and the
+ // push that make folding the load illegal.
for (auto I = DefMI; I != FrameSetup; ++I)
- if (I->getOpcode() != X86::MOV32rm)
+ if (I->isLoadFoldBarrier())
return nullptr;
return DefMI;
projects / oota-llvm.git / blobdiff