[X86] Support EGPR (R16-R31) for APX (#67702)

1. Map R16-R31 to DWARF registers 130-145.
2. Make R16-R31 caller-saved registers.
3. Make R16-31 allocatable only when feature EGPR is supported
4. Make R16-31 availabe for instructions in legacy maps 0/1 and EVEX
space, except XSAVE*/XRSTOR

RFC:
https://discourse.llvm.org/t/rfc-design-for-apx-feature-egpr-and-ndd-support/73031/4

Explanations for some seemingly unrelated changes:

inline-asm-registers.mir, statepoint-invoke-ra-enter-at-end.mir:
The immediate (TargetInstrInfo.cpp:1612) used for the regdef/reguse is
the encoding for the register
  class in the enum generated by tablegen. This encoding will change
  any time a new register class is added. Since the number is part
  of the input, this means it can become stale.

seh-directive-errors.s:
   R16-R31 makes ".seh_pushreg 17" legal

musttail-varargs.ll:
It seems some LLVM passes use the number of registers rather the number
of allocatable registers as heuristic.

Author: KanRobert

llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h

@@ -1208,6 +1208,43 @@ namespace X86II {
     return false;
   }
 
+  inline bool canUseApxExtendedReg(const MCInstrDesc &Desc) {
+    uint64_t TSFlags = Desc.TSFlags;
+    uint64_t Encoding = TSFlags & EncodingMask;
+    // EVEX can always use egpr.
+    if (Encoding == X86II::EVEX)
+      return true;
+
+    // To be conservative, egpr is not used for all pseudo instructions
+    // because we are not sure what instruction it will become.
+    // FIXME: Could we improve it in X86ExpandPseudo?
+    if (isPseudo(TSFlags))
+      return false;
+
+    // MAP OB/TB in legacy encoding space can always use egpr except
+    // XSAVE*/XRSTOR*.
+    unsigned Opcode = Desc.Opcode;
+    switch (Opcode) {
+    default:
+      break;
+    case X86::XSAVE:
+    case X86::XSAVE64:
+    case X86::XSAVEOPT:
+    case X86::XSAVEOPT64:
+    case X86::XSAVEC:
+    case X86::XSAVEC64:
+    case X86::XSAVES:
+    case X86::XSAVES64:
+    case X86::XRSTOR:
+    case X86::XRSTOR64:
+    case X86::XRSTORS:
+    case X86::XRSTORS64:
+      return false;
+    }
+    uint64_t OpMap = TSFlags & X86II::OpMapMask;
+    return !Encoding && (OpMap == X86II::OB || OpMap == X86II::TB);
+  }
+
   /// \returns true if the MemoryOperand is a 32 extended (zmm16 or higher)
   /// registers, e.g. zmm21, etc.
   static inline bool is32ExtendedReg(unsigned RegNo) {

llvm/lib/Target/X86/X86.td

@@ -331,6 +331,8 @@ def FeatureMOVDIRI  : SubtargetFeature<"movdiri", "HasMOVDIRI", "true",
                                        "Support movdiri instruction (direct store integer)">;
 def FeatureMOVDIR64B : SubtargetFeature<"movdir64b", "HasMOVDIR64B", "true",
                                         "Support movdir64b instruction (direct store 64 bytes)">;
+def FeatureEGPR : SubtargetFeature<"egpr", "HasEGPR", "true",
+                                   "Support extended general purpose register">;
 
 // Ivy Bridge and newer processors have enhanced REP MOVSB and STOSB (aka
 // "string operations"). See "REP String Enhancement" in the Intel Software

llvm/lib/Target/X86/X86InstrInfo.cpp

@@ -92,6 +92,37 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
       Subtarget(STI), RI(STI.getTargetTriple()) {
 }
 
+const TargetRegisterClass *
+X86InstrInfo::getRegClass(const MCInstrDesc &MCID, unsigned OpNum,
+                          const TargetRegisterInfo *TRI,
+                          const MachineFunction &MF) const {
+  auto *RC = TargetInstrInfo::getRegClass(MCID, OpNum, TRI, MF);
+  // If the target does not have egpr, then r16-r31 will be resereved for all
+  // instructions.
+  if (!RC || !Subtarget.hasEGPR())
+    return RC;
+
+  if (X86II::canUseApxExtendedReg(MCID))
+    return RC;
+
+  switch (RC->getID()) {
+  default:
+    return RC;
+  case X86::GR8RegClassID:
+    return &X86::GR8_NOREX2RegClass;
+  case X86::GR16RegClassID:
+    return &X86::GR16_NOREX2RegClass;
+  case X86::GR32RegClassID:
+    return &X86::GR32_NOREX2RegClass;
+  case X86::GR64RegClassID:
+    return &X86::GR64_NOREX2RegClass;
+  case X86::GR32_NOSPRegClassID:
+    return &X86::GR32_NOREX2_NOSPRegClass;
+  case X86::GR64_NOSPRegClassID:
+    return &X86::GR64_NOREX2_NOSPRegClass;
+  }
+}
+
 bool
 X86InstrInfo::isCoalescableExtInstr(const MachineInstr &MI,
                                     Register &SrcReg, Register &DstReg,

llvm/lib/Target/X86/X86InstrInfo.h

@@ -150,6 +150,17 @@ class X86InstrInfo final : public X86GenInstrInfo {
 public:
   explicit X86InstrInfo(X86Subtarget &STI);
 
+  /// Given a machine instruction descriptor, returns the register
+  /// class constraint for OpNum, or NULL. Returned register class
+  /// may be different from the definition in the TD file, e.g.
+  /// GR*RegClass (definition in TD file)
+  /// ->
+  /// GR*_NOREX2RegClass (Returned register class)
+  const TargetRegisterClass *
+  getRegClass(const MCInstrDesc &MCID, unsigned OpNum,
+              const TargetRegisterInfo *TRI,
+              const MachineFunction &MF) const override;
+
   /// getRegisterInfo - TargetInstrInfo is a superset of MRegister info.  As
   /// such, whenever a client has an instance of instruction info, it should
   /// always be able to get register info as well (through this method).

llvm/lib/Target/X86/X86RegisterInfo.cpp

@@ -158,6 +158,10 @@ X86RegisterInfo::getLargestLegalSuperClass(const TargetRegisterClass *RC,
     case X86::GR16RegClassID:
     case X86::GR32RegClassID:
     case X86::GR64RegClassID:
+    case X86::GR8_NOREX2RegClassID:
+    case X86::GR16_NOREX2RegClassID:
+    case X86::GR32_NOREX2RegClassID:
+    case X86::GR64_NOREX2RegClassID:
     case X86::RFP32RegClassID:
     case X86::RFP64RegClassID:
     case X86::RFP80RegClassID:
@@ -610,6 +614,14 @@ BitVector X86RegisterInfo::getReservedRegs(const MachineFunction &MF) const {
     }
   }
 
+  // Reserve the extended general purpose registers.
+  if (!Is64Bit || !MF.getSubtarget<X86Subtarget>().hasEGPR()) {
+    for (unsigned n = 0; n != 16; ++n) {
+      for (MCRegAliasIterator AI(X86::R16 + n, this, true); AI.isValid(); ++AI)
+        Reserved.set(*AI);
+    }
+  }
+
   assert(checkAllSuperRegsMarked(Reserved,
                                  {X86::SIL, X86::DIL, X86::BPL, X86::SPL,
                                   X86::SIH, X86::DIH, X86::BPH, X86::SPH}));