diff options
author | Hal Finkel <hfinkel@anl.gov> | 2015-01-14 01:07:51 +0000 |
---|---|---|
committer | Hal Finkel <hfinkel@anl.gov> | 2015-01-14 01:07:51 +0000 |
commit | 934361a4b8661410b5c1d8e1f50f3f1c145e8b7e (patch) | |
tree | 15dc2d1ca8dd9d8c7d68fe98f6b3d905eae32c3b /llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp | |
parent | dcdd5ad25254e8811fdea76c39a93ecbb992d230 (diff) | |
download | bcm5719-llvm-934361a4b8661410b5c1d8e1f50f3f1c145e8b7e.tar.gz bcm5719-llvm-934361a4b8661410b5c1d8e1f50f3f1c145e8b7e.zip |
Revert "r225811 - Revert "r225808 - [PowerPC] Add StackMap/PatchPoint support""
This re-applies r225808, fixed to avoid problems with SDAG dependencies along
with the preceding fix to ScheduleDAGSDNodes::RegDefIter::InitNodeNumDefs.
These problems caused the original regression tests to assert/segfault on many
(but not all) systems.
Original commit message:
This commit does two things:
1. Refactors PPCFastISel to use more of the common infrastructure for call
lowering (this lets us take advantage of this common code for lowering some
common intrinsics, stackmap/patchpoint among them).
2. Adds support for stackmap/patchpoint lowering. For the most part, this is
very similar to the support in the AArch64 target, with the obvious differences
(different registers, NOP instructions, etc.). The test cases are adapted
from the AArch64 test cases.
One difference of note is that the patchpoint call sequence takes 24 bytes, so
you can't use less than that (on AArch64 you can go down to 16). Also, as noted
in the docs, we take the patchpoint address to be the actual code address
(assuming the call is local in the TOC-sharing sense), which should yield
higher performance than generating the full cross-DSO indirect-call sequence
and is likely just as useful for JITed code (if not, we'll change it).
StackMaps and Patchpoints are still marked as experimental, and so this support
is doubly experimental. So go ahead and experiment!
llvm-svn: 225909
Diffstat (limited to 'llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp')
-rw-r--r-- | llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp | 90 |
1 files changed, 89 insertions, 1 deletions
diff --git a/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp b/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp index 564887353dd..decc1b27f77 100644 --- a/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp +++ b/llvm/lib/Target/PowerPC/PPCAsmPrinter.cpp @@ -34,6 +34,7 @@ #include "llvm/CodeGen/MachineInstrBuilder.h" #include "llvm/CodeGen/MachineModuleInfoImpls.h" #include "llvm/CodeGen/MachineRegisterInfo.h" +#include "llvm/CodeGen/StackMaps.h" #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h" #include "llvm/IR/Constants.h" #include "llvm/IR/DebugInfo.h" @@ -69,10 +70,11 @@ namespace { MapVector<MCSymbol*, MCSymbol*> TOC; const PPCSubtarget &Subtarget; uint64_t TOCLabelID; + StackMaps SM; public: explicit PPCAsmPrinter(TargetMachine &TM, MCStreamer &Streamer) : AsmPrinter(TM, Streamer), - Subtarget(TM.getSubtarget<PPCSubtarget>()), TOCLabelID(0) {} + Subtarget(TM.getSubtarget<PPCSubtarget>()), TOCLabelID(0), SM(*this) {} const char *getPassName() const override { return "PowerPC Assembly Printer"; @@ -90,6 +92,13 @@ namespace { bool PrintAsmMemoryOperand(const MachineInstr *MI, unsigned OpNo, unsigned AsmVariant, const char *ExtraCode, raw_ostream &O) override; + + void EmitEndOfAsmFile(Module &M) override; + + void LowerSTACKMAP(MCStreamer &OutStreamer, StackMaps &SM, + const MachineInstr &MI); + void LowerPATCHPOINT(MCStreamer &OutStreamer, StackMaps &SM, + const MachineInstr &MI); }; /// PPCLinuxAsmPrinter - PowerPC assembly printer, customized for Linux @@ -316,6 +325,80 @@ MCSymbol *PPCAsmPrinter::lookUpOrCreateTOCEntry(MCSymbol *Sym) { return TOCEntry; } +void PPCAsmPrinter::EmitEndOfAsmFile(Module &M) { + SM.serializeToStackMapSection(); +} + +void PPCAsmPrinter::LowerSTACKMAP(MCStreamer &OutStreamer, StackMaps &SM, + const MachineInstr &MI) { + unsigned NumNOPBytes = MI.getOperand(1).getImm(); + + SM.recordStackMap(MI); + assert(NumNOPBytes % 4 == 0 && "Invalid number of NOP bytes requested!"); + + // Scan ahead to trim the shadow. + const MachineBasicBlock &MBB = *MI.getParent(); + MachineBasicBlock::const_iterator MII(MI); + ++MII; + while (NumNOPBytes > 0) { + if (MII == MBB.end() || MII->isCall() || + MII->getOpcode() == PPC::DBG_VALUE || + MII->getOpcode() == TargetOpcode::PATCHPOINT || + MII->getOpcode() == TargetOpcode::STACKMAP) + break; + ++MII; + NumNOPBytes -= 4; + } + + // Emit nops. + for (unsigned i = 0; i < NumNOPBytes; i += 4) + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::NOP)); +} + +// Lower a patchpoint of the form: +// [<def>], <id>, <numBytes>, <target>, <numArgs> +void PPCAsmPrinter::LowerPATCHPOINT(MCStreamer &OutStreamer, StackMaps &SM, + const MachineInstr &MI) { + SM.recordPatchPoint(MI); + PatchPointOpers Opers(&MI); + + int64_t CallTarget = Opers.getMetaOper(PatchPointOpers::TargetPos).getImm(); + unsigned EncodedBytes = 0; + if (CallTarget) { + assert((CallTarget & 0xFFFFFFFFFFFF) == CallTarget && + "High 16 bits of call target should be zero."); + unsigned ScratchReg = MI.getOperand(Opers.getNextScratchIdx()).getReg(); + EncodedBytes = 6*4; + // Materialize the jump address: + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::LI8) + .addReg(ScratchReg) + .addImm((CallTarget >> 32) & 0xFFFF)); + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::RLDIC) + .addReg(ScratchReg) + .addReg(ScratchReg) + .addImm(32).addImm(16)); + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::ORIS8) + .addReg(ScratchReg) + .addReg(ScratchReg) + .addImm((CallTarget >> 16) & 0xFFFF)); + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::ORI8) + .addReg(ScratchReg) + .addReg(ScratchReg) + .addImm(CallTarget & 0xFFFF)); + + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::MTCTR8).addReg(ScratchReg)); + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::BCTRL8)); + } + + // Emit padding. + unsigned NumBytes = Opers.getMetaOper(PatchPointOpers::NBytesPos).getImm(); + assert(NumBytes >= EncodedBytes && + "Patchpoint can't request size less than the length of a call."); + assert((NumBytes - EncodedBytes) % 4 == 0 && + "Invalid number of NOP bytes requested!"); + for (unsigned i = EncodedBytes; i < NumBytes; i += 4) + EmitToStreamer(OutStreamer, MCInstBuilder(PPC::NOP)); +} /// EmitInstruction -- Print out a single PowerPC MI in Darwin syntax to /// the current output stream. @@ -332,6 +415,11 @@ void PPCAsmPrinter::EmitInstruction(const MachineInstr *MI) { default: break; case TargetOpcode::DBG_VALUE: llvm_unreachable("Should be handled target independently"); + case TargetOpcode::STACKMAP: + return LowerSTACKMAP(OutStreamer, SM, *MI); + case TargetOpcode::PATCHPOINT: + return LowerPATCHPOINT(OutStreamer, SM, *MI); + case PPC::MoveGOTtoLR: { // Transform %LR = MoveGOTtoLR // Into this: bl _GLOBAL_OFFSET_TABLE_@local-4 |