mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-13 20:32:21 +00:00
43c3e8b176
------------------------------------------------------------------------ r221703 | wschmidt | 2014-11-11 20:44:09 +0000 (Tue, 11 Nov 2014) | 48 lines [PowerPC] Replace foul hackery with real calls to __tls_get_addr My original support for the general dynamic and local dynamic TLS models contained some fairly obtuse hacks to generate calls to __tls_get_addr when lowering a TargetGlobalAddress. Rather than generating real calls, special GET_TLS_ADDR nodes were used to wrap the calls and only reveal them at assembly time. I attempted to provide correct parameter and return values by chaining CopyToReg and CopyFromReg nodes onto the GET_TLS_ADDR nodes, but this was also not fully correct. Problems were seen with two back-to-back stores to TLS variables, where the call sequences ended up overlapping with unhappy results. Additionally, since these weren't real calls, the proper register side effects of a call were not recorded, so clobbered values were kept live across the calls. The proper thing to do is to lower these into calls in the first place. This is relatively straightforward; see the changes to PPCTargetLowering::LowerGlobalTLSAddress() in PPCISelLowering.cpp. The changes here are standard call lowering, except that we need to track the fact that these calls will require a relocation. This is done by adding a machine operand flag of MO_TLSLD or MO_TLSGD to the TargetGlobalAddress operand that appears earlier in the sequence. The calls to LowerCallTo() eventually find their way to LowerCall_64SVR4() or LowerCall_32SVR4(), which call FinishCall(), which calls PrepareCall(). In PrepareCall(), we detect the calls to __tls_get_addr and immediately snag the TargetGlobalTLSAddress with the annotated relocation information. This becomes an extra operand on the call following the callee, which is expected for nodes of type tlscall. We change the call opcode to CALL_TLS for this case. Back in FinishCall(), we change it again to CALL_NOP_TLS for 64-bit only, since we require a TOC-restore nop following the call for the 64-bit ABIs. During selection, patterns in PPCInstrInfo.td and PPCInstr64Bit.td convert the CALL_TLS nodes into BL_TLS nodes, and convert the CALL_NOP_TLS nodes into BL8_NOP_TLS nodes. This replaces the code removed from PPCAsmPrinter.cpp, as the BL_TLS or BL8_NOP_TLS nodes can now be emitted normally using their patterns and the associated printTLSCall print method. Finally, as a result of these changes, all references to get-tls-addr in its various guises are no longer used, so they have been removed. There are existing TLS tests to verify the changes haven't messed anything up). I've added one new test that verifies that the problem with the original code has been fixed. ------------------------------------------------------------------------ git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_35@223742 91177308-0d34-0410-b5e6-96231b3b80d8
111 lines
3.6 KiB
C++
111 lines
3.6 KiB
C++
//===-- PPC.h - Top-level interface for PowerPC Target ----------*- C++ -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file contains the entry points for global functions defined in the LLVM
|
|
// PowerPC back-end.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_TARGET_POWERPC_H
|
|
#define LLVM_TARGET_POWERPC_H
|
|
|
|
#include "MCTargetDesc/PPCMCTargetDesc.h"
|
|
#include <string>
|
|
|
|
// GCC #defines PPC on Linux but we use it as our namespace name
|
|
#undef PPC
|
|
|
|
namespace llvm {
|
|
class PPCTargetMachine;
|
|
class PassRegistry;
|
|
class FunctionPass;
|
|
class ImmutablePass;
|
|
class JITCodeEmitter;
|
|
class MachineInstr;
|
|
class AsmPrinter;
|
|
class MCInst;
|
|
|
|
FunctionPass *createPPCCTRLoops(PPCTargetMachine &TM);
|
|
#ifndef NDEBUG
|
|
FunctionPass *createPPCCTRLoopsVerify();
|
|
#endif
|
|
FunctionPass *createPPCEarlyReturnPass();
|
|
FunctionPass *createPPCVSXCopyPass();
|
|
FunctionPass *createPPCVSXCopyCleanupPass();
|
|
FunctionPass *createPPCVSXFMAMutatePass();
|
|
FunctionPass *createPPCBranchSelectionPass();
|
|
FunctionPass *createPPCISelDag(PPCTargetMachine &TM);
|
|
FunctionPass *createPPCJITCodeEmitterPass(PPCTargetMachine &TM,
|
|
JITCodeEmitter &MCE);
|
|
void LowerPPCMachineInstrToMCInst(const MachineInstr *MI, MCInst &OutMI,
|
|
AsmPrinter &AP, bool isDarwin);
|
|
|
|
/// \brief Creates an PPC-specific Target Transformation Info pass.
|
|
ImmutablePass *createPPCTargetTransformInfoPass(const PPCTargetMachine *TM);
|
|
|
|
void initializePPCVSXFMAMutatePass(PassRegistry&);
|
|
extern char &PPCVSXFMAMutateID;
|
|
|
|
namespace PPCII {
|
|
|
|
/// Target Operand Flag enum.
|
|
enum TOF {
|
|
//===------------------------------------------------------------------===//
|
|
// PPC Specific MachineOperand flags.
|
|
MO_NO_FLAG,
|
|
|
|
/// MO_PLT_OR_STUB - On a symbol operand "FOO", this indicates that the
|
|
/// reference is actually to the "FOO$stub" or "FOO@plt" symbol. This is
|
|
/// used for calls and jumps to external functions on Tiger and earlier, and
|
|
/// for PIC calls on Linux and ELF systems.
|
|
MO_PLT_OR_STUB = 1,
|
|
|
|
/// MO_PIC_FLAG - If this bit is set, the symbol reference is relative to
|
|
/// the function's picbase, e.g. lo16(symbol-picbase).
|
|
MO_PIC_FLAG = 2,
|
|
|
|
/// MO_NLP_FLAG - If this bit is set, the symbol reference is actually to
|
|
/// the non_lazy_ptr for the global, e.g. lo16(symbol$non_lazy_ptr-picbase).
|
|
MO_NLP_FLAG = 4,
|
|
|
|
/// MO_NLP_HIDDEN_FLAG - If this bit is set, the symbol reference is to a
|
|
/// symbol with hidden visibility. This causes a different kind of
|
|
/// non-lazy-pointer to be generated.
|
|
MO_NLP_HIDDEN_FLAG = 8,
|
|
|
|
/// The next are not flags but distinct values.
|
|
MO_ACCESS_MASK = 0xf0,
|
|
|
|
/// MO_LO, MO_HA - lo16(symbol) and ha16(symbol)
|
|
MO_LO = 1 << 4,
|
|
MO_HA = 2 << 4,
|
|
|
|
MO_TPREL_LO = 4 << 4,
|
|
MO_TPREL_HA = 3 << 4,
|
|
|
|
/// These values identify relocations on immediates folded
|
|
/// into memory operations.
|
|
MO_DTPREL_LO = 5 << 4,
|
|
MO_TLSLD_LO = 6 << 4,
|
|
MO_TOC_LO = 7 << 4,
|
|
|
|
// Symbol for VK_PPC_TLS fixup attached to an ADD instruction
|
|
MO_TLS = 8 << 4,
|
|
|
|
// Symbols for VK_PPC_TLSGD and VK_PPC_TLSLD in __tls_get_addr
|
|
// call sequences.
|
|
MO_TLSLD = 9 << 4,
|
|
MO_TLSGD = 10 << 4
|
|
};
|
|
} // end namespace PPCII
|
|
|
|
} // end namespace llvm;
|
|
|
|
#endif
|