[PowerPC] ELFv2 MC support for .localentry directive

A second binutils feature needed to support ELFv2 is the .localentry
directive.  In the ELFv2 ABI, functions may have two entry points:
one for calling the routine locally via "bl", and one for calling the
function via function pointer (either at the source level, or implicitly
via a PLT stub for global calls).  The two entry points share a single
ELF symbol, where the ELF symbol address identifies the global entry
point address, while the local entry point is found by adding a delta
offset to the symbol address.  That offset is encoded into three
platform-specific bits of the ELF symbol st_other field.

The .localentry directive instructs the assembler to set those fields
to encode a particular offset.  This is typically used by a function
prologue sequence like this:

func:
        addis r2, r12, (.TOC.-func)@ha
        addi r2, r2, (.TOC.-func)@l
        .localentry func, .-func

Note that according to the ABI, when calling the global entry point,
r12 must be set to point the global entry point address itself; while
when calling the local entry point, r2 must be set to point to the TOC
base.  The two instructions between the global and local entry point in
the above example translate the first requirement into the second.

This patch implements support in the PowerPC MC streamers to emit the
.localentry directive (both into assembler and ELF object output), as
well as support in the assembler parser to parse that directive.

In addition, there is another change required in MC fixup/relocation
handling to properly deal with relocations targeting function symbols
with two entry points: When the target function is known local, the MC
layer would immediately handle the fixup by inserting the target
address -- this is wrong, since the call may need to go to the local
entry point instead.  The GNU assembler handles this case by *not*
directly resolving fixups targeting functions with two entry points,
but always emits the relocation and relies on the linker to handle
this case correctly.  This patch changes LLVM MC to do the same (this
is done via the processFixupValue routine).

Similarly, there are cases where the assembler would normally emit a
relocation, but "simplify" it to a relocation targeting a *section*
instead of the actual symbol.  For the same reason as above, this
may be wrong when the target symbol has two entry points.  The GNU
assembler again handles this case by not performing this simplification
in that case, but leaving the relocation targeting the full symbol,
which is then resolved by the linker.  This patch changes LLVM MC
to do the same (via the needsRelocateWithSymbol routine).
NOTE: The method used in this patch is overly pessimistic, since the
needsRelocateWithSymbol routine currently does not have access to the
actual target symbol, and thus must always assume that it might have
two entry points.  This will be improved upon by a follow-on patch
that modifies common code to pass the target symbol when calling
needsRelocateWithSymbol.

Reviewed by Hal Finkel.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213485 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Support/ELF.h

@@ -505,6 +505,28 @@ enum {
   EF_PPC64_ABI = 3
 };
 
+// Special values for the st_other field in the symbol table entry for PPC64.
+enum {
+  STO_PPC64_LOCAL_BIT = 5,
+  STO_PPC64_LOCAL_MASK = (7 << STO_PPC64_LOCAL_BIT)
+};
+static inline int64_t
+decodePPC64LocalEntryOffset(unsigned Other) {
+  unsigned Val = (Other & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT;
+  return ((1 << Val) >> 2) << 2;
+}
+static inline unsigned
+encodePPC64LocalEntryOffset(int64_t Offset) {
+  unsigned Val = (Offset >= 4 * 4
+                  ? (Offset >= 8 * 4
+                     ? (Offset >= 16 * 4 ? 6 : 5)
+                     : 4)
+                  : (Offset >= 2 * 4
+                     ? 3
+                     : (Offset >= 1 * 4 ? 2 : 0)));
+  return Val << STO_PPC64_LOCAL_BIT;
+}
+
 // ELF Relocation types for PPC64
 enum {
   R_PPC64_NONE                = 0,

lib/Target/PowerPC/AsmParser/PPCAsmParser.cpp

@@ -15,6 +15,7 @@
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/ADT/Twine.h"
+#include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstrInfo.h"
@@ -245,6 +246,7 @@ class PPCAsmParser : public MCTargetAsmParser {
   bool ParseDirectiveMachine(SMLoc L);
   bool ParseDarwinDirectiveMachine(SMLoc L);
   bool ParseDirectiveAbiVersion(SMLoc L);
+  bool ParseDirectiveLocalEntry(SMLoc L);
 
   bool MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode,
                                OperandVector &Operands, MCStreamer &Out,
@@ -1415,6 +1417,8 @@ bool PPCAsmParser::ParseDirective(AsmToken DirectiveID) {
       return ParseDirectiveMachine(DirectiveID.getLoc());
     if (IDVal == ".abiversion")
       return ParseDirectiveAbiVersion(DirectiveID.getLoc());
+    if (IDVal == ".localentry")
+      return ParseDirectiveLocalEntry(DirectiveID.getLoc());
   } else {
     if (IDVal == ".machine")
       return ParseDarwinDirectiveMachine(DirectiveID.getLoc());
@@ -1558,6 +1562,43 @@ bool PPCAsmParser::ParseDirectiveAbiVersion(SMLoc L) {
   return false;
 }
 
+/// ParseDirectiveLocalEntry
+///  ::= .localentry symbol, expression
+bool PPCAsmParser::ParseDirectiveLocalEntry(SMLoc L) {
+  StringRef Name;
+  if (getParser().parseIdentifier(Name)) {
+    Error(L, "expected identifier in directive");
+    return false;
+  }
+  MCSymbol *Sym = getContext().GetOrCreateSymbol(Name);
+
+  if (getLexer().isNot(AsmToken::Comma)) {
+    Error(L, "unexpected token in directive");
+    return false;
+  }
+  Lex();
+
+  const MCExpr *Expr;
+  if (getParser().parseExpression(Expr)) {
+    Error(L, "expected expression");
+    return false;
+  }
+
+  if (getLexer().isNot(AsmToken::EndOfStatement)) {
+    Error(L, "unexpected token in directive");
+    return false;
+  }
+
+  PPCTargetStreamer &TStreamer =
+      *static_cast<PPCTargetStreamer *>(
+           getParser().getStreamer().getTargetStreamer());
+  TStreamer.emitLocalEntry(Sym, Expr);
+
+  return false;
+}
+
+
+
 /// Force static initialization.
 extern "C" void LLVMInitializePowerPCAsmParser() {
   RegisterMCAsmParser<PPCAsmParser> A(ThePPC32Target);

lib/Target/PowerPC/MCTargetDesc/PPCAsmBackend.cpp

@@ -9,7 +9,9 @@
 
 #include "MCTargetDesc/PPCMCTargetDesc.h"
 #include "MCTargetDesc/PPCFixupKinds.h"
+#include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCAsmBackend.h"
+#include "llvm/MC/MCELF.h"
 #include "llvm/MC/MCELFObjectWriter.h"
 #include "llvm/MC/MCFixupKindInfo.h"
 #include "llvm/MC/MCMachObjectWriter.h"
@@ -128,6 +130,30 @@ public:
     }
   }
 
+  void processFixupValue(const MCAssembler &Asm, const MCAsmLayout &Layout,
+                         const MCFixup &Fixup, const MCFragment *DF,
+                         const MCValue &Target, uint64_t &Value,
+                         bool &IsResolved) override {
+    switch ((PPC::Fixups)Fixup.getKind()) {
+    default: break;
+    case PPC::fixup_ppc_br24:
+    case PPC::fixup_ppc_br24abs:
+      // If the target symbol has a local entry point we must not attempt
+      // to resolve the fixup directly.  Emit a relocation and leave
+      // resolution of the final target address to the linker.
+      if (const MCSymbolRefExpr *A = Target.getSymA()) {
+        const MCSymbolData &Data = Asm.getSymbolData(A->getSymbol());
+        // The "other" values are stored in the last 6 bits of the second byte.
+        // The traditional defines for STO values assume the full byte and thus
+        // the shift to pack it.
+        unsigned Other = MCELF::getOther(Data) << 2;
+        if ((Other & ELF::STO_PPC64_LOCAL_MASK) != 0)
+          IsResolved = false;
+      }
+      break;
+    }
+  }
+
   bool mayNeedRelaxation(const MCInst &Inst) const override {
     // FIXME.
     return false;

lib/Target/PowerPC/MCTargetDesc/PPCELFObjectWriter.cpp

@@ -30,6 +30,8 @@ namespace {
                                        bool IsPCRel) const;
     unsigned GetRelocType(const MCValue &Target, const MCFixup &Fixup,
                           bool IsPCRel) const override;
+
+    bool needsRelocateWithSymbol(unsigned Type) const override;
   };
 }
 
@@ -387,6 +389,19 @@ unsigned PPCELFObjectWriter::GetRelocType(const MCValue &Target,
   return getRelocTypeInner(Target, Fixup, IsPCRel);
 }
 
+bool PPCELFObjectWriter::needsRelocateWithSymbol(unsigned Type) const {
+  switch (Type) {
+    default:
+      return false;
+
+    case ELF::R_PPC_REL24:
+      // FIXME: We only need to keep the target symbol of the relocation
+      // if the symbol uses a local entry point.  Unfortunately, we do not
+      // have access to the symbol here ...
+      return true;
+  }
+}
+
 MCObjectWriter *llvm::createPPCELFObjectWriter(raw_ostream &OS,
                                                bool Is64Bit,
                                                bool IsLittleEndian,

lib/Target/PowerPC/MCTargetDesc/PPCMCTargetDesc.cpp

@@ -16,7 +16,9 @@
 #include "PPCMCAsmInfo.h"
 #include "PPCTargetStreamer.h"
 #include "llvm/MC/MCCodeGenInfo.h"
+#include "llvm/MC/MCELF.h"
 #include "llvm/MC/MCELFStreamer.h"
+#include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCStreamer.h"
@@ -130,6 +132,9 @@ public:
   virtual void emitAbiVersion(int AbiVersion) override {
     OS << "\t.abiversion " << AbiVersion << '\n';
   }
+  virtual void emitLocalEntry(MCSymbol *S, const MCExpr *LocalOffset) {
+    OS << "\t.localentry\t" << *S << ", " << *LocalOffset << '\n';
+  }
 };
 
 class PPCTargetELFStreamer : public PPCTargetStreamer {
@@ -153,6 +158,32 @@ public:
     Flags |= (AbiVersion & ELF::EF_PPC64_ABI);
     MCA.setELFHeaderEFlags(Flags);
   }
+  virtual void emitLocalEntry(MCSymbol *S, const MCExpr *LocalOffset) {
+    MCAssembler &MCA = getStreamer().getAssembler();
+    MCSymbolData &Data = getStreamer().getOrCreateSymbolData(S);
+
+    int64_t Res;
+    if (!LocalOffset->EvaluateAsAbsolute(Res, MCA))
+      report_fatal_error(".localentry expression must be absolute.");
+
+    unsigned Encoded = ELF::encodePPC64LocalEntryOffset(Res);
+    if (Res != ELF::decodePPC64LocalEntryOffset(Encoded))
+      report_fatal_error(".localentry expression cannot be encoded.");
+
+    // The "other" values are stored in the last 6 bits of the second byte.
+    // The traditional defines for STO values assume the full byte and thus
+    // the shift to pack it.
+    unsigned Other = MCELF::getOther(Data) << 2;
+    Other &= ~ELF::STO_PPC64_LOCAL_MASK;
+    Other |= Encoded;
+    MCELF::setOther(Data, Other >> 2);
+
+    // For GAS compatibility, unless we already saw a .abiversion directive,
+    // set e_flags to indicate ELFv2 ABI.
+    unsigned Flags = MCA.getELFHeaderEFlags();
+    if ((Flags & ELF::EF_PPC64_ABI) == 0)
+      MCA.setELFHeaderEFlags(Flags | 2);
+  }
 };
 
 class PPCTargetMachOStreamer : public PPCTargetStreamer {
@@ -168,6 +199,9 @@ public:
   virtual void emitAbiVersion(int AbiVersion) override {
     llvm_unreachable("Unknown pseudo-op: .abiversion");
   }
+  virtual void emitLocalEntry(MCSymbol *S, const MCExpr *LocalOffset) {
+    llvm_unreachable("Unknown pseudo-op: .localentry");
+  }
 };
 }
 

lib/Target/PowerPC/PPCTargetStreamer.h

@@ -20,6 +20,7 @@ public:
   virtual void emitTCEntry(const MCSymbol &S) = 0;
   virtual void emitMachine(StringRef CPU) = 0;
   virtual void emitAbiVersion(int AbiVersion) = 0;
+  virtual void emitLocalEntry(MCSymbol *S, const MCExpr *LocalOffset) = 0;
 };
 }
 

test/MC/PowerPC/ppc64-localentry-error1.s

@@ -0,0 +1,11 @@
+
+# RUN: not llvm-mc -triple powerpc64-unknown-unknown -filetype=obj < %s 2> %t
+# RUN: FileCheck < %t %s
+# RUN: not llvm-mc -triple powerpc64le-unknown-unknown -filetype=obj < %s 2> %t
+# RUN: FileCheck < %t %s
+
+sym:
+	.localentry sym, 123
+
+# CHECK: LLVM ERROR: .localentry expression cannot be encoded.
+

test/MC/PowerPC/ppc64-localentry-error2.s

@@ -0,0 +1,12 @@
+
+# RUN: not llvm-mc -triple powerpc64-unknown-unknown -filetype=obj < %s 2> %t
+# RUN: FileCheck < %t %s
+# RUN: not llvm-mc -triple powerpc64le-unknown-unknown -filetype=obj < %s 2> %t
+# RUN: FileCheck < %t %s
+
+	.globl remote_sym
+sym:
+	.localentry sym, remote_sym
+
+# CHECK: LLVM ERROR: .localentry expression must be absolute.
+

test/MC/PowerPC/ppc64-localentry.s

@@ -0,0 +1,58 @@
+
+# RUN: llvm-mc -triple powerpc64-unknown-unknown -filetype=obj %s | \
+# RUN: llvm-readobj -h -r -symbols | FileCheck %s
+# RUN: llvm-mc -triple powerpc64le-unknown-unknown -filetype=obj %s | \
+# RUN: llvm-readobj -h -r -symbols | FileCheck %s
+
+	.type callee1, @function
+callee1:
+	nop
+	nop
+	.localentry callee1, .-callee1
+	nop
+	nop
+	.size callee1, .-callee1
+
+	.type callee2, @function
+callee2:
+	nop
+	nop
+	.size callee2, .-callee2
+
+	.type caller, @function
+caller:
+	bl callee1
+	nop
+	bl callee2
+	nop
+	.size caller, .-caller
+
+# Verify that use of .localentry implies ABI version 2
+# CHECK: ElfHeader {
+# CHECK: Flags [ (0x2)
+
+# Verify that fixups to local function symbols are performed only
+# if the target symbol does not use .localentry
+# CHECK: Relocations [
+# CHECK: Section ({{[0-9]*}}) .rela.text {
+# CHECK-NEXT: R_PPC64_REL24 callee1
+# CHECK-NEXT: }
+# CHECK-NOT: R_PPC64_REL24 callee2
+
+# Verify that .localentry is encoded in the Other field.
+# CHECK: Symbols [
+# CHECK:       Name: callee1
+# CHECK-NEXT:  Value:
+# CHECK-NEXT:  Size: 16
+# CHECK-NEXT:  Binding: Local
+# CHECK-NEXT:  Type: Function
+# CHECK-NEXT:  Other: 96
+# CHECK-NEXT:  Section: .text
+# CHECK:       Name: callee2
+# CHECK-NEXT:  Value:
+# CHECK-NEXT:  Size: 8
+# CHECK-NEXT:  Binding: Local
+# CHECK-NEXT:  Type: Function
+# CHECK-NEXT:  Other: 0
+# CHECK-NEXT:  Section: .text
+