[AArch64] Stack probing for dynamic allocas in SelectionDAG #66525
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-clang-codegen @llvm/pr-subscribers-backend-aarch64 ChangesAdd support for probing for dynamic allocas (variable-size objects and outgoing stack arguments). (This is stacked on top of #66524 and will be rebased as needed)Patch is 128.98 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/66525.diff 13 Files Affected:
diff --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index 68e68449d4073b2..701fea37ef825e2 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -301,6 +301,7 @@ static bool produceCompactUnwindFrame(MachineFunction &MF);
static bool needsWinCFI(const MachineFunction &MF);
static StackOffset getSVEStackSize(const MachineFunction &MF);
static bool needsShadowCallStackPrologueEpilogue(MachineFunction &MF);
+static unsigned findScratchNonCalleeSaveRegister(MachineBasicBlock *MBB);
/// Returns true if a homogeneous prolog or epilog code can be emitted
/// for the size optimization. If possible, a frame helper call is injected.
@@ -470,6 +471,9 @@ MachineBasicBlock::iterator AArch64FrameLowering::eliminateCallFramePseudoInstr(
MachineBasicBlock::iterator I) const {
const AArch64InstrInfo *TII =
static_cast<const AArch64InstrInfo *>(MF.getSubtarget().getInstrInfo());
+ const AArch64TargetLowering *TLI =
+ MF.getSubtarget<AArch64Subtarget>().getTargetLowering();
+ MachineFrameInfo &MFI = MF.getFrameInfo();
DebugLoc DL = I->getDebugLoc();
unsigned Opc = I->getOpcode();
bool IsDestroy = Opc == TII->getCallFrameDestroyOpcode();
@@ -496,8 +500,24 @@ MachineBasicBlock::iterator AArch64FrameLowering::eliminateCallFramePseudoInstr(
// Most call frames will be allocated at the start of a function so
// this is OK, but it is a limitation that needs dealing with.
assert(Amount > -0xffffff && Amount < 0xffffff && "call frame too large");
- emitFrameOffset(MBB, I, DL, AArch64::SP, AArch64::SP,
- StackOffset::getFixed(Amount), TII);
+
+ if (TLI->hasInlineStackProbe(MF) &&
+ -Amount >= AArch64::StackProbeMaxUnprobedStack) {
+ // When stack probing is enabled, the decrement of SP may need to be
+ // probed. We only need to do this if the call site needs 1024 bytes of
+ // space or more, because a region smaller than that is allowed to be
+ // unprobed at an ABI boundary. We rely on the fact that SP has been
+ // probed exactly at this point, either by the prologue or most recent
+ // dynamic allocation.
+ assert(MFI.hasVarSizedObjects() &&
+ "non-reserved call frame without var sized objects?");
+ Register ScratchReg =
+ MF.getRegInfo().createVirtualRegister(&AArch64::GPR64RegClass);
+ inlineStackProbeFixed(I, ScratchReg, -Amount, StackOffset::get(0, 0));
+ } else {
+ emitFrameOffset(MBB, I, DL, AArch64::SP, AArch64::SP,
+ StackOffset::getFixed(Amount), TII);
+ }
}
} else if (CalleePopAmount != 0) {
// If the calling convention demands that the callee pops arguments from the
@@ -672,6 +692,74 @@ void AArch64FrameLowering::emitCalleeSavedSVERestores(
emitCalleeSavedRestores(MBB, MBBI, true);
}
+void AArch64FrameLowering::allocateSVEStackSpace(
+ MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
+ StackOffset AllocSize, StackOffset InitialOffset, bool EmitCFI) const {
+ DebugLoc DL;
+ MachineFunction &MF = *MBB.getParent();
+ const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
+ const AArch64RegisterInfo &RegInfo = *Subtarget.getRegisterInfo();
+ const AArch64TargetLowering &TLI = *Subtarget.getTargetLowering();
+ const TargetInstrInfo &TII = *Subtarget.getInstrInfo();
+
+ // If not probing the stack or the (uknown) allocation size is less than the
+ // probe size decrement the stack pointer right away. This avoids having to
+ // emit a probing loop when allocating space for up to 16 SVE registers when
+ // using 4k probes.
+
+ // The bit-length of SVE registers is architecturally limited.
+ const int64_t MAX_BYTES_PER_SCALABLE_BYTE = 16;
+ int64_t ProbeSize = TLI.getStackProbeSize(MF);
+ if (!TLI.hasInlineStackProbe(MF) ||
+ AllocSize.getScalable() * MAX_BYTES_PER_SCALABLE_BYTE +
+ AllocSize.getFixed() <=
+ ProbeSize) {
+ emitFrameOffset(MBB, MBBI, DL, AArch64::SP, AArch64::SP, -AllocSize, &TII,
+ MachineInstr::FrameSetup, false, false, nullptr, EmitCFI,
+ InitialOffset);
+ if (TLI.hasInlineStackProbe(MF)) {
+ // Issue a probe at the top of the stack to prepare for subsequent
+ // allocations.
+ // STR XZR, [TargetReg]
+ BuildMI(MBB, MBBI, DL, TII.get(AArch64::STRXui))
+ .addReg(AArch64::XZR)
+ .addReg(AArch64::SP)
+ .addImm(0)
+ .setMIFlags(MachineInstr::FrameSetup);
+ }
+ return;
+ }
+
+ // If we can't be sure the allocation size if less than the probe size, we
+ // have to emit a stack probing loop.
+ Register ScratchReg = findScratchNonCalleeSaveRegister(&MBB);
+ assert(ScratchReg != AArch64::NoRegister);
+ // Get the new top of the stack into a scratch register.
+ emitFrameOffset(MBB, MBBI, DL, ScratchReg, AArch64::SP, -AllocSize, &TII,
+ MachineInstr::FrameSetup, false, false, nullptr, EmitCFI,
+ InitialOffset);
+ // Arrange to emit a probing loop by decrementing SP until it reaches that
+ // new top of the stack.
+ BuildMI(MBB, MBBI, DL, TII.get(AArch64::PROBED_STACKALLOC_VAR), AArch64::SP)
+ .addReg(ScratchReg);
+ // Set SP to its new value.
+ // MOV SP, Xs
+ BuildMI(MBB, MBBI, DL, TII.get(AArch64::ADDXri), AArch64::SP)
+ .addReg(ScratchReg)
+ .addImm(0)
+ .addImm(AArch64_AM::getShifterImm(AArch64_AM::LSL, 0))
+ .setMIFlags(MachineInstr::FrameSetup);
+ if (EmitCFI) {
+ // Set the CFA register back to SP.
+ unsigned Reg = RegInfo.getDwarfRegNum(AArch64::SP, true);
+ unsigned CFIIndex =
+ MF.addFrameInst(MCCFIInstruction::createDefCfaRegister(nullptr, Reg));
+ BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::CFI_INSTRUCTION))
+ .addCFIIndex(CFIIndex)
+ .setMIFlags(MachineInstr::FrameSetup);
+ }
+}
+
static MCRegister getRegisterOrZero(MCRegister Reg, bool HasSVE) {
switch (Reg.id()) {
default:
@@ -855,9 +943,11 @@ bool AArch64FrameLowering::canUseAsPrologue(
MachineBasicBlock *TmpMBB = const_cast<MachineBasicBlock *>(&MBB);
const AArch64Subtarget &Subtarget = MF->getSubtarget<AArch64Subtarget>();
const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();
+ const AArch64TargetLowering *TLI = Subtarget.getTargetLowering();
- // Don't need a scratch register if we're not going to re-align the stack.
- if (!RegInfo->hasStackRealignment(*MF))
+ // Don't need a scratch register if we're not going to re-align the stack or
+ // emit stack probes.
+ if (!RegInfo->hasStackRealignment(*MF) && TLI->hasInlineStackProbe(*MF))
return true;
// Otherwise, we can use any block as long as it has a scratch register
// available.
@@ -1429,6 +1519,7 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
const Function &F = MF.getFunction();
const AArch64Subtarget &Subtarget = MF.getSubtarget<AArch64Subtarget>();
const AArch64RegisterInfo *RegInfo = Subtarget.getRegisterInfo();
+ const AArch64TargetLowering &TLI = *Subtarget.getTargetLowering();
const TargetInstrInfo *TII = Subtarget.getInstrInfo();
MachineModuleInfo &MMI = MF.getMMI();
AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
@@ -1784,12 +1875,14 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
}
}
- StackOffset AllocateBefore = SVEStackSize, AllocateAfter = {};
+ StackOffset SVECalleeSavedSize = {}, SVELocalsSize = SVEStackSize;
MachineBasicBlock::iterator CalleeSavesBegin = MBBI, CalleeSavesEnd = MBBI;
// Process the SVE callee-saves to determine what space needs to be
// allocated.
if (int64_t CalleeSavedSize = AFI->getSVECalleeSavedStackSize()) {
+ LLVM_DEBUG(dbgs() << "SVECalleeSavedStackSize = " << CalleeSavedSize
+ << "\n");
// Find callee save instructions in frame.
CalleeSavesBegin = MBBI;
assert(IsSVECalleeSave(CalleeSavesBegin) && "Unexpected instruction");
@@ -1797,33 +1890,40 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
++MBBI;
CalleeSavesEnd = MBBI;
- AllocateBefore = StackOffset::getScalable(CalleeSavedSize);
- AllocateAfter = SVEStackSize - AllocateBefore;
+ SVECalleeSavedSize = StackOffset::getScalable(CalleeSavedSize);
+ SVELocalsSize = SVEStackSize - SVECalleeSavedSize;
+
+ // Allocate space for the SVE callee saves.
+ if (SVECalleeSavedSize) {
+ allocateSVEStackSpace(
+ MBB, CalleeSavesBegin, SVECalleeSavedSize,
+ StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes),
+ EmitAsyncCFI && !HasFP);
+ if (EmitAsyncCFI)
+ emitCalleeSavedSVELocations(MBB, CalleeSavesEnd);
+ }
}
- // Allocate space for the callee saves (if any).
- emitFrameOffset(
- MBB, CalleeSavesBegin, DL, AArch64::SP, AArch64::SP, -AllocateBefore, TII,
- MachineInstr::FrameSetup, false, false, nullptr,
- EmitAsyncCFI && !HasFP && AllocateBefore,
- StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes));
-
- if (EmitAsyncCFI)
- emitCalleeSavedSVELocations(MBB, CalleeSavesEnd);
-
- // Finally allocate remaining SVE stack space.
- emitFrameOffset(MBB, CalleeSavesEnd, DL, AArch64::SP, AArch64::SP,
- -AllocateAfter, TII, MachineInstr::FrameSetup, false, false,
- nullptr, EmitAsyncCFI && !HasFP && AllocateAfter,
- AllocateBefore + StackOffset::getFixed(
- (int64_t)MFI.getStackSize() - NumBytes));
+ // Allocate stack space for the local SVE objects.
+ if (SVELocalsSize)
+ allocateSVEStackSpace(
+ MBB, CalleeSavesEnd, SVELocalsSize,
+ SVECalleeSavedSize +
+ StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes),
+ EmitAsyncCFI && !HasFP);
// Allocate space for the rest of the frame.
if (NumBytes) {
unsigned scratchSPReg = AArch64::SP;
+ bool NeedsStackProbe = TLI.hasInlineStackProbe(MF) &&
+ (NumBytes > AArch64::StackProbeMaxUnprobedStack ||
+ MFI.hasVarSizedObjects());
if (NeedsRealignment) {
scratchSPReg = findScratchNonCalleeSaveRegister(&MBB);
+ NeedsStackProbe |= TLI.hasInlineStackProbe(MF) &&
+ (NumBytes + MFI.getMaxAlign().value()) >
+ AArch64::StackProbeMaxUnprobedStack;
assert(scratchSPReg != AArch64::NoRegister);
}
@@ -1832,12 +1932,36 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
// FIXME: in the case of dynamic re-alignment, NumBytes doesn't have
// the correct value here, as NumBytes also includes padding bytes,
// which shouldn't be counted here.
- emitFrameOffset(
- MBB, MBBI, DL, scratchSPReg, AArch64::SP,
- StackOffset::getFixed(-NumBytes), TII, MachineInstr::FrameSetup,
- false, NeedsWinCFI, &HasWinCFI, EmitAsyncCFI && !HasFP,
+ StackOffset CFAOffset =
SVEStackSize +
- StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes));
+ StackOffset::getFixed((int64_t)MFI.getStackSize() - NumBytes);
+ if (NeedsStackProbe && !NeedsRealignment) {
+ // If we don't need to re-align the stack, we can use a more efficient
+ // sequence for stack probing.
+ Register ScratchReg = findScratchNonCalleeSaveRegister(&MBB);
+ assert(ScratchReg != AArch64::NoRegister);
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::PROBED_STACKALLOC))
+ .addDef(ScratchReg)
+ .addImm(NumBytes)
+ .addImm(CFAOffset.getFixed())
+ .addImm(CFAOffset.getScalable());
+ // The fixed allocation may leave unprobed bytes at the top of the
+ // stack. If we have variable-sized objects, we need to issue an extra
+ // probe, so their allocations starts in a known state.
+ if (MFI.hasVarSizedObjects()) {
+ // STR XZR, [SP]
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::STRXui))
+ .addReg(AArch64::XZR)
+ .addReg(AArch64::SP)
+ .addImm(0)
+ .setMIFlags(MachineInstr::FrameSetup);
+ }
+ } else {
+ emitFrameOffset(MBB, MBBI, DL, scratchSPReg, AArch64::SP,
+ StackOffset::getFixed(-NumBytes), TII,
+ MachineInstr::FrameSetup, false, NeedsWinCFI,
+ &HasWinCFI, EmitAsyncCFI && !HasFP, CFAOffset);
+ }
}
if (NeedsRealignment) {
assert(MFI.getMaxAlign() > Align(1));
@@ -1846,12 +1970,48 @@ void AArch64FrameLowering::emitPrologue(MachineFunction &MF,
// SUB X9, SP, NumBytes
// -- X9 is temporary register, so shouldn't contain any live data here,
// -- free to use. This is already produced by emitFrameOffset above.
- // AND SP, X9, 0b11111...0000
- uint64_t AndMask = ~(MFI.getMaxAlign().value() - 1);
- BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)
- .addReg(scratchSPReg, RegState::Kill)
- .addImm(AArch64_AM::encodeLogicalImmediate(AndMask, 64));
+ const uint64_t MaxAlign = MFI.getMaxAlign().value();
+ const uint64_t AndMask = ~(MaxAlign - 1);
+
+ if (NeedsStackProbe) {
+ // If allocation size is known to not exceed the probe size, don't emit
+ // a probing loop.
+ if (NumBytes + MaxAlign - 1 <= TLI.getStackProbeSize(MF)) {
+ // AND SP, X9, 0b11111...0000
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)
+ .addReg(scratchSPReg, RegState::Kill)
+ .addImm(AArch64_AM::encodeLogicalImmediate(AndMask, 64))
+ .setMIFlags(MachineInstr::FrameSetup);
+ // STR XZR, [SP]
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::STRXui))
+ .addReg(AArch64::XZR)
+ .addReg(AArch64::SP)
+ .addImm(0)
+ .setMIFlags(MachineInstr::FrameSetup);
+ } else {
+ // AND X9, X9, 0b11111...0000
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), scratchSPReg)
+ .addReg(scratchSPReg, RegState::Kill)
+ .addImm(AArch64_AM::encodeLogicalImmediate(AndMask, 64))
+ .setMIFlags(MachineInstr::FrameSetup);
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::PROBED_STACKALLOC_VAR),
+ AArch64::SP)
+ .addReg(scratchSPReg);
+ // MOV SP, X9
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::ADDXri), AArch64::SP)
+ .addReg(scratchSPReg)
+ .addImm(0)
+ .addImm(AArch64_AM::getShifterImm(AArch64_AM::LSL, 0))
+ .setMIFlags(MachineInstr::FrameSetup);
+ }
+ } else {
+ // AND SP, X9, 0b11111...0000
+ BuildMI(MBB, MBBI, DL, TII->get(AArch64::ANDXri), AArch64::SP)
+ .addReg(scratchSPReg, RegState::Kill)
+ .addImm(AArch64_AM::encodeLogicalImmediate(AndMask, 64))
+ .setMIFlags(MachineInstr::FrameSetup);
+ }
AFI->setStackRealigned(true);
// No need for SEH instructions here; if we're realigning the stack,
@@ -4057,3 +4217,192 @@ void AArch64FrameLowering::orderFrameObjects(
dbgs() << "\n";
});
}
+
+/// Emit a loop to decrement SP until it is equal to TargetReg, with probes at
+/// least every ProbeSize bytes. Returns an iterator of the first instruction
+/// after the loop. The difference between SP and TargetReg must be an exact
+/// multiple of ProbeSize.
+MachineBasicBlock::iterator
+AArch64FrameLowering::inlineStackProbeLoopExactMultiple(
+ MachineBasicBlock::iterator MBBI, int64_t ProbeSize,
+ Register TargetReg) const {
+ MachineBasicBlock &MBB = *MBBI->getParent();
+ MachineFunction &MF = *MBB.getParent();
+ const AArch64InstrInfo *TII =
+ MF.getSubtarget<AArch64Subtarget>().getInstrInfo();
+ DebugLoc DL = MBB.findDebugLoc(MBBI);
+
+ MachineFunction::iterator MBBInsertPoint = std::next(MBB.getIterator());
+ MachineBasicBlock *LoopMBB = MF.CreateMachineBasicBlock(MBB.getBasicBlock());
+ MF.insert(MBBInsertPoint, LoopMBB);
+ MachineBasicBlock *ExitMBB = MF.CreateMachineBasicBlock(MBB.getBasicBlock());
+ MF.insert(MBBInsertPoint, ExitMBB);
+
+ // SUB SP, SP, #ProbeSize (or equivalent if ProbeSize is not encodable
+ // in SUB).
+ emitFrameOffset(*LoopMBB, LoopMBB->end(), DL, AArch64::SP, AArch64::SP,
+ StackOffset::getFixed(-ProbeSize), TII,
+ MachineInstr::FrameSetup);
+ // STR XZR, [SP]
+ BuildMI(*LoopMBB, LoopMBB->end(), DL, TII->get(AArch64::STRXui))
+ .addReg(AArch64::XZR)
+ .addReg(AArch64::SP)
+ .addImm(0)
+ .setMIFlags(MachineInstr::FrameSetup);
+ // CMP SP, TargetReg
+ BuildMI(*LoopMBB, LoopMBB->end(), DL, TII->get(AArch64::SUBSXrx64),
+ AArch64::XZR)
+ .addReg(AArch64::SP)
+ .addReg(TargetReg)
+ .addImm(AArch64_AM::getArithExtendImm(AArch64_AM::UXTX, 0))
+ .setMIFlags(MachineInstr::FrameSetup);
+ // B.CC Loop
+ BuildMI(*LoopMBB, LoopMBB->end(), DL, TII->get(AArch64::Bcc))
+ .addImm(AArch64CC::NE)
+ .addMBB(LoopMBB)
+ .setMIFlags(MachineInstr::FrameSetup);
+
+ LoopMBB->addSuccessor(ExitMBB);
+ LoopMBB->addSuccessor(LoopMBB);
+ // Synthesize the exit MBB.
+ ExitMBB->splice(ExitMBB->end(), &MBB, MBBI, MBB.end());
+ ExitMBB->transferSuccessorsAndUpdatePHIs(&MBB);
+ MBB.addSuccessor(LoopMBB);
+ // Update liveins.
+ recomputeLiveIns(*LoopMBB);
+ recomputeLiveIns(*ExitMBB);
+
+ return ExitMBB->begin();
+}
+
+MachineBasicBlock::iterator AArch64FrameLowering::inlineStackProbeFixed(
+ MachineBasicBlock::iterator MBBI, Register ScratchReg, int64_t FrameSize,
+ StackOffset CFAOffset) const {
+ MachineBasicBlock *MBB = MBBI->getParent();
+ MachineFunction &MF = *MBB->getParent();
+ const AArch64TargetLowering *TLI =
+ MF.getSubtarget<AArch64Subtarget>().getTargetLowering();
+ const AArch64InstrInfo *TII =
+ MF.getSubtarget<AArch64Subtarget>().getInstrInfo();
+ AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
+ bool EmitAsyncCFI = AFI->needsAsyncDwarfUnwindInfo(MF);
+ bool HasFP = hasFP(MF);
+
+ DebugLoc DL;
+ int64_t ProbeSize = TLI->getStackProbeSize(MF);
+ int64_t NumBlocks = FrameSize / ProbeSize;
+ int64_t ResidualSize = FrameSize % ProbeSize;
+
+ LLVM_DEBUG(dbgs() << "Stack probing: total " << FrameSize << " bytes, "
+ << NumBlocks << " blocks of " << ProbeSize
+ << " bytes, plus " << ResidualSize << " bytes\n");
+
+ // Decrement SP by NumBlock * ProbeSize bytes, with either unrolled or
+ // ordinary loop.
+ if (NumBlocks <= AArch64::StackProbeMaxLoopUnroll) {
+ for (int i = 0; i < NumBlocks; ++i) {
+ // SUB SP, SP, #FrameSize (or equivalent if FrameSize is not
+ // encodable in a SUB).
+ emitFrameOffset(*MBB, MBBI, DL, AArch64::SP, AArch64::SP,
+ StackOffset::getFixed(-ProbeSize), TII,
+ MachineInstr::FrameSetup, false, false, nullptr,
+ EmitAsyncCFI && !HasFP, CFAOffset);
+ CFAOffset += StackOffset::getFixed(ProbeSize);
+ // STR XZR, [SP]
+ BuildMI(*MBB, MBBI, DL, TII->get(AArch64::STRXui))
+ .addReg(AArch64::XZR)
+ .addReg(AArch64::SP)
+ .addImm(0)
+ .setMIFlags(MachineInstr::FrameSetup);
+ }
+ } else if (NumBlocks != 0) {
+ // SUB ScratchReg, SP, #FrameSize (or equivalent if FrameSize is not
+ // encodable in ADD). ScrathReg may temporarily become the CFA register.
+ emitFrameOffset(*MBB, MBBI, DL, ScratchReg, AArch64::SP,
+ StackOffset::getFixed(-ProbeSize * NumBlocks), TII,
+ MachineInstr::FrameSetup, false, false, nullptr,
+ EmitAsyncCFI && !HasFP, CFAOffset);
+ CFAOffset += StackOffset::getFixed(ProbeSize * NumBlocks);
+ MBBI = inlineStackProbeLoopExactMultiple(MBBI, ProbeSize, ScratchReg);
+ MBB = MBBI->getParent();
+ if (EmitAsyncCFI && !HasFP) {
+ // Set the CFA register back to SP.
+ const AArch64RegisterInfo &RegInfo =
+ *MF.getSubtarget<AArch64Subtarget>().getRegisterInfo();
+ unsigned Reg = RegInfo.getDwarfRegNum(AArch64::SP, true);
+...
[truncated]
|
momchil-velikov
requested review from
aemerson,
zatrazz,
serge-sans-paille,
SamTebbs33,
bzEq,
hassnaaHamdi,
davemgreen,
CarolineConcatto,
JonPsson and
efriedma-quic
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
0a0691b
to
86e003f
Compare
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
00ea8af
to
de1ba97
Compare
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
de1ba97
to
e32ff3b
Compare
llvmbot
added
clang
|
✅ With the latest revision this PR passed the C/C++ code formatter. |
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
e32ff3b
to
d89e026
Compare
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
d89e026
to
227b5e0
Compare
|
Ping? |
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
3 times, most recently
from
1994b30
to
ef887bd
Compare
SamTebbs33
approved these changes
Nov 14, 2023
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
2 times, most recently
from
de974b2
to
ce36a30
Compare
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
ce36a30
to
769e1e8
Compare
|
Do the call frame changes here affect Windows? (I guess that would indicate a latent bug in our Windows ABI support...) |
TBH, I have not tested on Windows. However, by construction, I've hopefully made sure the Windows and non-Windows are isolated and separate - either with checks whether target is or isn't Windows or with check about a particular kind of stack probing (e.g. attribute "probe-stack"="inline" means not Windows). |
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
2 times, most recently
from
1e0eb05
to
9a4d280
Compare
|
Oh, I see, the new code is effectively guarded by an You might want to put a note in AArch64FrameLowering::hasReservedCallFrame mentioning that you're making assumptions about the implementation elsewhere. (We could conceivably mess with the way that works in the future.) |
I'm missing something here. Which assumptions? |
|
The |
Change-Id: I1ef19ce40702a789d220c4bbfd5560220fa329f5 Co-authored-by: Oliver Stannard <[email protected]>
…ctor Change-Id: I1f9645b7ca786259bb7276806a9cfa17ba543a5a
momchil-velikov
force-pushed
the
stack-clash-protection-dynalloc-dag
branch
from
9a4d280
to
fecf2a2
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add support for probing for dynamic allocas (variable-size objects and outgoing stack arguments).
(This is stacked on top of #66524 and will be rebased as needed)