diff options
author | Philip Reames <listmail@philipreames.com> | 2014-12-01 22:52:56 +0000 |
---|---|---|
committer | Philip Reames <listmail@philipreames.com> | 2014-12-01 22:52:56 +0000 |
commit | 78cc6fcb01a7306a380aeb65f411c89d6aa5532d (patch) | |
tree | 19515a69d384d25199f8bc26b13ab1d2b14e9cc0 /lib/Target/X86 | |
parent | 204e21b51a87e9e0738865cfea2025199a694e96 (diff) |
[Statepoints 2/4] Statepoint infrastructure for garbage collection: MI & x86-64 Backend
This is the second patch in a small series. This patch contains the MachineInstruction and x86-64 backend pieces required to lower Statepoints. It does not include the code to actually generate the STATEPOINT machine instruction and as a result, the entire patch is currently dead code. I will be submitting the SelectionDAG parts within the next 24-48 hours. Since those pieces are by far the most complicated, I wanted to minimize the size of that patch. That patch will include the tests which exercise the functionality in this patch. The entire series can be seen as one combined whole in http://reviews.llvm.org/D5683.
The STATEPOINT psuedo node is generated after all gc values are explicitly spilled to stack slots. The purpose of this node is to wrap an actual call instruction while recording the spill locations of the meta arguments used for garbage collection and other purposes. The STATEPOINT is modeled as modifing all of those locations to prevent backend optimizations from forwarding the value from before the STATEPOINT to after the STATEPOINT. (Doing so would break relocation semantics for collectors which wish to relocate roots.)
The implementation of STATEPOINT is closely modeled on PATCHPOINT. Eventually, much of the code in this patch will be removed. The long term plan is to merge the functionality provided by statepoints and patchpoints. Merging their implementations in the backend is likely to be a good starting point.
Reviewed by: atrick, ributzka
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223085 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/X86')
-rw-r--r-- | lib/Target/X86/X86FrameLowering.cpp | 73 | ||||
-rw-r--r-- | lib/Target/X86/X86FrameLowering.h | 4 | ||||
-rw-r--r-- | lib/Target/X86/X86ISelLowering.cpp | 5 | ||||
-rw-r--r-- | lib/Target/X86/X86MCInstLower.cpp | 64 |
4 files changed, 145 insertions, 1 deletions
diff --git a/lib/Target/X86/X86FrameLowering.cpp b/lib/Target/X86/X86FrameLowering.cpp index b9920b1b84c..278e4f910d4 100644 --- a/lib/Target/X86/X86FrameLowering.cpp +++ b/lib/Target/X86/X86FrameLowering.cpp @@ -1135,6 +1135,79 @@ int X86FrameLowering::getFrameIndexReference(const MachineFunction &MF, int FI, return getFrameIndexOffset(MF, FI); } +// Simplified from getFrameIndexOffset keeping only StackPointer cases +int X86FrameLowering::getFrameIndexOffsetFromSP(const MachineFunction &MF, int FI) const { + const X86RegisterInfo *RegInfo = + static_cast<const X86RegisterInfo*>(MF.getSubtarget().getRegisterInfo()); + const MachineFrameInfo *MFI = MF.getFrameInfo(); + const uint64_t StackSize = MFI->getStackSize(); //not including dynamic realign + + { +#ifndef NDEBUG + // Note: LLVM arranges the stack as: + // Args > Saved RetPC (<--FP) > CSRs > dynamic alignment (<--BP) + // > "Stack Slots" (<--SP) + // We can always address StackSlots from RSP. We can usually (unless + // needsStackRealignment) address CSRs from RSP, but sometimes need to + // address them from RBP. FixedObjects can be placed anywhere in the stack + // frame depending on their specific requirements (i.e. we can actually + // refer to arguments to the function which are stored in the *callers* + // frame). As a result, THE RESULT OF THIS CALL IS MEANINGLESS FOR CSRs + // AND FixedObjects IFF needsStackRealignment or hasVarSizedObject. + + assert(!RegInfo->hasBasePointer(MF) && "we don't handle this case"); + + // We don't handle tail calls, and shouldn't be seeing them + // either. + int TailCallReturnAddrDelta = + MF.getInfo<X86MachineFunctionInfo>()->getTCReturnAddrDelta(); + assert(!(TailCallReturnAddrDelta < 0) && "we don't handle this case!"); +#endif + } + + // This is how the math works out: + // + // %rsp grows (i.e. gets lower) left to right. Each box below is + // one word (eight bytes). Obj0 is the stack slot we're trying to + // get to. + // + // ---------------------------------- + // | BP | Obj0 | Obj1 | ... | ObjN | + // ---------------------------------- + // ^ ^ ^ ^ + // A B C E + // + // A is the incoming stack pointer. + // (B - A) is the local area offset (-8 for x86-64) [1] + // (C - A) is the Offset returned by MFI->getObjectOffset for Obj0 [2] + // + // |(E - B)| is the StackSize (absolute value, positive). For a + // stack that grown down, this works out to be (B - E). [3] + // + // E is also the value of %rsp after stack has been set up, and we + // want (C - E) -- the value we can add to %rsp to get to Obj0. Now + // (C - E) == (C - A) - (B - A) + (B - E) + // { Using [1], [2] and [3] above } + // == getObjectOffset - LocalAreaOffset + StackSize + // + + // Get the Offset from the StackPointer + int Offset = MFI->getObjectOffset(FI) - getOffsetOfLocalArea(); + + return Offset + StackSize; +} +// Simplified from getFrameIndexReference keeping only StackPointer cases +int X86FrameLowering::getFrameIndexReferenceFromSP(const MachineFunction &MF, int FI, + unsigned &FrameReg) const { + const X86RegisterInfo *RegInfo = + static_cast<const X86RegisterInfo*>(MF.getSubtarget().getRegisterInfo()); + + assert(!RegInfo->hasBasePointer(MF) && "we don't handle this case"); + + FrameReg = RegInfo->getStackRegister(); + return getFrameIndexOffsetFromSP(MF, FI); +} + bool X86FrameLowering::assignCalleeSavedSpillSlots( MachineFunction &MF, const TargetRegisterInfo *TRI, std::vector<CalleeSavedInfo> &CSI) const { diff --git a/lib/Target/X86/X86FrameLowering.h b/lib/Target/X86/X86FrameLowering.h index 7740c3ad6f3..2ee71159c19 100644 --- a/lib/Target/X86/X86FrameLowering.h +++ b/lib/Target/X86/X86FrameLowering.h @@ -69,6 +69,10 @@ public: int getFrameIndexReference(const MachineFunction &MF, int FI, unsigned &FrameReg) const override; + int getFrameIndexOffsetFromSP(const MachineFunction &MF, int FI) const; + int getFrameIndexReferenceFromSP(const MachineFunction &MF, int FI, + unsigned &FrameReg) const override; + void eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB, MachineBasicBlock::iterator MI) const override; diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp index b67bbcb39c3..7faa58cf377 100644 --- a/lib/Target/X86/X86ISelLowering.cpp +++ b/lib/Target/X86/X86ISelLowering.cpp @@ -21346,6 +21346,11 @@ X86TargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI, case X86::EH_SjLj_LongJmp64: return emitEHSjLjLongJmp(MI, BB); + case TargetOpcode::STATEPOINT: + // As an implementation detail, STATEPOINT shares the STACKMAP format at + // this point in the process. We diverge later. + return emitPatchPoint(MI, BB); + case TargetOpcode::STACKMAP: case TargetOpcode::PATCHPOINT: return emitPatchPoint(MI, BB); diff --git a/lib/Target/X86/X86MCInstLower.cpp b/lib/Target/X86/X86MCInstLower.cpp index 4e0d594238c..6a10916aa60 100644 --- a/lib/Target/X86/X86MCInstLower.cpp +++ b/lib/Target/X86/X86MCInstLower.cpp @@ -808,6 +808,66 @@ static void EmitNops(MCStreamer &OS, unsigned NumBytes, bool Is64Bit, const MCSu } // while (NumBytes) } +static void LowerSTATEPOINT(MCStreamer &OS, StackMaps &SM, + const MachineInstr &MI, bool Is64Bit, + const TargetMachine& TM, + const MCSubtargetInfo& STI, + X86MCInstLower &MCInstLowering) { + assert(Is64Bit && "Statepoint currently only supports X86-64"); + + // We need to record the frame size for stack walking + const MachineFunction* MF = MI.getParent()->getParent(); + assert(MF && "can't find machine function?"); + + // + // Emit call instruction + // + + // Lower call target and choose correct opcode + const MachineOperand &call_target = StatepointOpers(&MI).getCallTarget(); + MCOperand call_target_mcop; + unsigned call_opcode; + switch (call_target.getType()) { + case MachineOperand::MO_GlobalAddress: + case MachineOperand::MO_ExternalSymbol: + call_target_mcop = MCInstLowering.LowerSymbolOperand( + call_target, + MCInstLowering.GetSymbolFromOperand(call_target)); + call_opcode = X86::CALL64pcrel32; + // Currently, we only support relative addressing with statepoints. + // Otherwise, we'll need a scratch register to hold the target + // address. You'll fail asserts during load & relocation if this + // symbol is to far away. (TODO: support non-relative addressing) + break; + case MachineOperand::MO_Immediate: + call_target_mcop = MCOperand::CreateImm(call_target.getImm()); + call_opcode = X86::CALL64pcrel32; + // Currently, we only support relative addressing with statepoints. + // Otherwise, we'll need a scratch register to hold the target + // immediate. You'll fail asserts during load & relocation if this + // address is to far away. (TODO: support non-relative addressing) + break; + case MachineOperand::MO_Register: + call_target_mcop = MCOperand::CreateReg(call_target.getReg()); + call_opcode = X86::CALL64r; + break; + default: + llvm_unreachable("Unsupported operand type in statepoint call target"); + break; + } + + // Emit call + MCInst call_inst; + call_inst.setOpcode(call_opcode); + call_inst.addOperand(call_target_mcop); + OS.EmitInstruction(call_inst, STI); + + // Record our statepoint node in the same section used by STACKMAP + // and PATCHPOINT + SM.recordStatepoint(MI); +} + + // Lower a stackmap of the form: // <id>, <shadowBytes>, ... void X86AsmPrinter::LowerSTACKMAP(const MachineInstr &MI) { @@ -1030,7 +1090,9 @@ void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) { .addExpr(DotExpr)); return; } - + case TargetOpcode::STATEPOINT: + return LowerSTATEPOINT(OutStreamer, SM, *MI, Subtarget->is64Bit(), TM, + getSubtargetInfo(), MCInstLowering); case TargetOpcode::STACKMAP: return LowerSTACKMAP(*MI); |