Add a MCObjectFormat class so that code common to all targets that use a

single object format can be shared.

This also adds support for

mov zed+(bar-foo), %eax

on ELF and COFF targets.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116675 91177308-0d34-0410-b5e6-96231b3b80d8

12 files changed, 194 insertions, 63 deletions

diff --git a/include/llvm/MC/MCExpr.h b/include/llvm/MC/MCExpr.h
index 06f9cd3bc4..f85650fc90 100644
--- a/include/llvm/MC/MCExpr.h
+++ b/include/llvm/MC/MCExpr.h
@@ -43,6 +43,8 @@ private:
 protected:
   explicit MCExpr(ExprKind _Kind) : Kind(_Kind) {}
 
+  bool EvaluateAsRelocatableImpl(MCValue &Res, const MCAsmLayout *Layout,
+                                 bool InSet) const;
 public:
   /// @name Accessors
   /// @{
diff --git a/include/llvm/MC/MCObjectFormat.h b/include/llvm/MC/MCObjectFormat.h
new file mode 100644
index 0000000000..80b7295f1f
--- /dev/null
+++ b/include/llvm/MC/MCObjectFormat.h
@@ -0,0 +1,52 @@
+//===-- llvm/MC/MCObjectFormat.h - Object Format Info -----------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_MC_MCOBJECTFORMAT_H
+#define LLVM_MC_MCOBJECTFORMAT_H
+
+namespace llvm {
+class MCSymbol;
+
+class MCObjectFormat {
+public:
+  /// isAbsolute - Check if A - B is an absolute value
+  ///
+  /// \param InSet - True if this expression is in a set. For example:
+  ///   a:
+  ///   ...
+  ///   b:
+  ///   tmp = a - b
+  ///       .long tmp
+  /// \param A - LHS
+  /// \param B - RHS
+  virtual bool isAbsolute(bool InSet, const MCSymbol &A,
+                          const MCSymbol &B) const = 0;
+};
+
+class MCELFObjectFormat : public MCObjectFormat {
+public:
+  virtual bool isAbsolute(bool InSet, const MCSymbol &A,
+                          const MCSymbol &B) const;
+};
+
+class MCMachOObjectFormat : public MCObjectFormat {
+public:
+  virtual bool isAbsolute(bool InSet, const MCSymbol &A,
+                          const MCSymbol &B) const;
+};
+
+class MCCOFFObjectFormat : public MCObjectFormat {
+public:
+  virtual bool isAbsolute(bool InSet, const MCSymbol &A,
+                          const MCSymbol &B) const;
+};
+
+}  // End llvm namespace
+
+#endif
diff --git a/include/llvm/Target/TargetAsmBackend.h b/include/llvm/Target/TargetAsmBackend.h
index b0a7af6371..b424dea4a5 100644
--- a/include/llvm/Target/TargetAsmBackend.h
+++ b/include/llvm/Target/TargetAsmBackend.h
@@ -16,6 +16,7 @@ namespace llvm {
 class MCDataFragment;
 class MCFixup;
 class MCInst;
+class MCObjectFormat;
 class MCObjectWriter;
 class MCSection;
 template<typename T>
@@ -33,7 +34,6 @@ protected: // Can only create subclasses.
   /// TheTarget - The Target that this machine was created for.
   const Target &TheTarget;
 
-  unsigned HasAbsolutizedSet : 1;
   unsigned HasReliableSymbolDifference : 1;
   unsigned HasScatteredSymbols : 1;
 
@@ -42,23 +42,12 @@ public:
 
   const Target &getTarget() const { return TheTarget; }
 
+  virtual const MCObjectFormat &getObjectFormat() const = 0;
+
   /// createObjectWriter - Create a new MCObjectWriter instance for use by the
   /// assembler backend to emit the final object file.
   virtual MCObjectWriter *createObjectWriter(raw_ostream &OS) const = 0;
 
-  /// hasAbsolutizedSet - Check whether this target "absolutizes"
-  /// assignments. That is, given code like:
-  ///   a:
-  ///   ...
-  ///   b:
-  ///   tmp = a - b
-  ///       .long tmp
-  /// will the value of 'tmp' be a relocatable expression, or the assembly time
-  /// value of L0 - L1. This distinction is only relevant for platforms that
-  /// support scattered symbols, since in the absence of scattered symbols (a -
-  /// b) cannot change after assembly.
-  bool hasAbsolutizedSet() const { return HasAbsolutizedSet; }
-
   /// hasReliableSymbolDifference - Check whether this target implements
   /// accurate relocations for differences between symbols. If not, differences
   /// between symbols will always be relocatable expressions and any references
@@ -68,7 +57,7 @@ public:
   /// This should always be true (since it results in fewer relocations with no
   /// loss of functionality), but is currently supported as a way to maintain
   /// exact object compatibility with Darwin 'as' (on non-x86_64). It should
-  /// eventually should be eliminated. See also \see hasAbsolutizedSet.
+  /// eventually should be eliminated.
   bool hasReliableSymbolDifference() const {
     return HasReliableSymbolDifference;
   }
diff --git a/lib/MC/CMakeLists.txt b/lib/MC/CMakeLists.txt
index 60a3a3e3e3..5856e07168 100644
--- a/lib/MC/CMakeLists.txt
+++ b/lib/MC/CMakeLists.txt
@@ -18,6 +18,7 @@ add_llvm_library(LLVMMC
   MCMachOStreamer.cpp
   MCNullStreamer.cpp
   MCObjectStreamer.cpp
+  MCObjectFormat.cpp
   MCObjectWriter.cpp
   MCSection.cpp
   MCSectionCOFF.cpp
diff --git a/lib/MC/ELFObjectWriter.cpp b/lib/MC/ELFObjectWriter.cpp
index d249c92dad..5a4f89d8d7 100644
--- a/lib/MC/ELFObjectWriter.cpp
+++ b/lib/MC/ELFObjectWriter.cpp
@@ -472,22 +472,11 @@ void ELFObjectWriterImpl::WriteSymbol(MCDataFragment *F, ELFSymbolData &MSD,
       const MCBinaryExpr *BE = static_cast<const MCBinaryExpr *>(ESize);
 
       if (BE->EvaluateAsRelocatable(Res, &Layout)) {
-        uint64_t AddressA = 0;
-        uint64_t AddressB = 0;
-        const MCSymbol &SymA = Res.getSymA()->getSymbol();
-        const MCSymbol &SymB = Res.getSymB()->getSymbol();
-
-        if (SymA.isDefined()) {
-          MCSymbolData &A = Layout.getAssembler().getSymbolData(SymA);
-          AddressA = Layout.getSymbolAddress(&A);
-        }
-
-        if (SymB.isDefined()) {
-          MCSymbolData &B = Layout.getAssembler().getSymbolData(SymB);
-          AddressB = Layout.getSymbolAddress(&B);
-        }
-
-        Size = AddressA - AddressB;
+        const llvm::MCSymbolRefExpr *A = Res.getSymA();
+        const llvm::MCSymbolRefExpr *B = Res.getSymA();
+        assert(!A || !A->getSymbol().isDefined());
+        assert(!B || !B->getSymbol().isDefined());
+        Size = Res.getConstant();
       }
     } else if (ESize->getKind() == MCExpr::Constant) {
       Size = static_cast<const MCConstantExpr *>(ESize)->getValue();
diff --git a/lib/MC/MCExpr.cpp b/lib/MC/MCExpr.cpp
index e9a6062fe7..3524b8035c 100644
--- a/lib/MC/MCExpr.cpp
+++ b/lib/MC/MCExpr.cpp
@@ -14,6 +14,7 @@
 #include "llvm/MC/MCAsmLayout.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCObjectFormat.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/MC/MCValue.h"
 #include "llvm/Support/Debug.h"
@@ -237,7 +238,8 @@ bool MCExpr::EvaluateAsAbsolute(int64_t &Res, const MCAsmLayout *Layout) const {
   return true;
 }
 
-static bool EvaluateSymbolicAdd(const MCValue &LHS,const MCSymbolRefExpr *RHS_A,
+static bool EvaluateSymbolicAdd(const MCAsmLayout *Layout, bool InSet,
+                                const MCValue &LHS,const MCSymbolRefExpr *RHS_A,
                                 const MCSymbolRefExpr *RHS_B, int64_t RHS_Cst,
                                 MCValue &Res) {
   // We can't add or subtract two symbols.
@@ -255,12 +257,40 @@ static bool EvaluateSymbolicAdd(const MCValue &LHS,const MCSymbolRefExpr *RHS_A,
     if (!A)
       return false;
   }
+
+  // Absolutize symbol differences between defined symbols when we have a
+  // layout object and the target requests it.
+
+  if (Layout && A && B) {
+    const MCSymbol &SA = A->getSymbol();
+    const MCSymbol &SB = B->getSymbol();
+    const MCObjectFormat &F =
+      Layout->getAssembler().getBackend().getObjectFormat();
+    if (SA.isDefined() && SB.isDefined() && F.isAbsolute(InSet, SA, SB)) {
+      const MCAssembler &Asm = Layout->getAssembler();
+      MCSymbolData &AD = Asm.getSymbolData(A->getSymbol());
+      MCSymbolData &BD = Asm.getSymbolData(B->getSymbol());
+      Res = MCValue::get(+ Layout->getSymbolAddress(&AD)
+                         - Layout->getSymbolAddress(&BD)
+                         + LHS.getConstant()
+                         + RHS_Cst);
+      return true;
+    }
+  }
+
+
   Res = MCValue::get(A, B, LHS.getConstant() + RHS_Cst);
   return true;
 }
 
 bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
                                    const MCAsmLayout *Layout) const {
+  return EvaluateAsRelocatableImpl(Res, Layout, false);
+}
+
+bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
+                                       const MCAsmLayout *Layout,
+                                       bool InSet) const {
   ++stats::MCExprEvaluate;
 
   switch (getKind()) {
@@ -276,27 +306,9 @@ bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
     const MCSymbol &Sym = SRE->getSymbol();
 
     // Evaluate recursively if this is a variable.
-    if (Sym.isVariable()) {
-      if (!Sym.getVariableValue()->EvaluateAsRelocatable(Res, Layout))
-        return false;
-
-      // Absolutize symbol differences between defined symbols when we have a
-      // layout object and the target requests it.
-      if (Layout && Res.getSymB() &&
-          Layout->getAssembler().getBackend().hasAbsolutizedSet() &&
-          Res.getSymA()->getSymbol().isDefined() &&
-          Res.getSymB()->getSymbol().isDefined()) {
-        MCSymbolData &A =
-          Layout->getAssembler().getSymbolData(Res.getSymA()->getSymbol());
-        MCSymbolData &B =
-          Layout->getAssembler().getSymbolData(Res.getSymB()->getSymbol());
-        Res = MCValue::get(+ Layout->getSymbolAddress(&A)
-                           - Layout->getSymbolAddress(&B)
-                           + Res.getConstant());
-      }
-
-      return true;
-    }
+    if (Sym.isVariable())
+      return Sym.getVariableValue()->EvaluateAsRelocatableImpl(Res, Layout,
+                                                               true);
 
     Res = MCValue::get(SRE, 0, 0);
     return true;
@@ -306,7 +318,7 @@ bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
     const MCUnaryExpr *AUE = cast<MCUnaryExpr>(this);
     MCValue Value;
 
-    if (!AUE->getSubExpr()->EvaluateAsRelocatable(Value, Layout))
+    if (!AUE->getSubExpr()->EvaluateAsRelocatableImpl(Value, Layout, InSet))
       return false;
 
     switch (AUE->getOpcode()) {
@@ -339,8 +351,8 @@ bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
     const MCBinaryExpr *ABE = cast<MCBinaryExpr>(this);
     MCValue LHSValue, RHSValue;
 
-    if (!ABE->getLHS()->EvaluateAsRelocatable(LHSValue, Layout) ||
-        !ABE->getRHS()->EvaluateAsRelocatable(RHSValue, Layout))
+    if (!ABE->getLHS()->EvaluateAsRelocatableImpl(LHSValue, Layout, InSet) ||
+        !ABE->getRHS()->EvaluateAsRelocatableImpl(RHSValue, Layout, InSet))
       return false;
 
     // We only support a few operations on non-constant expressions, handle
@@ -351,13 +363,13 @@ bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
         return false;
       case MCBinaryExpr::Sub:
         // Negate RHS and add.
-        return EvaluateSymbolicAdd(LHSValue,
+        return EvaluateSymbolicAdd(Layout, InSet, LHSValue,
                                    RHSValue.getSymB(), RHSValue.getSymA(),
                                    -RHSValue.getConstant(),
                                    Res);
 
       case MCBinaryExpr::Add:
-        return EvaluateSymbolicAdd(LHSValue,
+        return EvaluateSymbolicAdd(Layout, InSet, LHSValue,
                                    RHSValue.getSymA(), RHSValue.getSymB(),
                                    RHSValue.getConstant(),
                                    Res);
diff --git a/lib/MC/MCObjectFormat.cpp b/lib/MC/MCObjectFormat.cpp
new file mode 100644
index 0000000000..07d361c8a4
--- /dev/null
+++ b/lib/MC/MCObjectFormat.cpp
@@ -0,0 +1,31 @@
+//===- lib/MC/MCObjectFormat.cpp - MCObjectFormat implementation ----------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/MC/MCObjectFormat.h"
+#include "llvm/MC/MCSymbol.h"
+
+using namespace llvm;
+
+bool MCELFObjectFormat::isAbsolute(bool IsSet, const MCSymbol &A,
+                                   const MCSymbol &B) const {
+  // On ELF A - B is absolute if A and B are in the same section.
+  return &A.getSection() == &B.getSection();
+}
+
+bool MCMachOObjectFormat::isAbsolute(bool IsSet, const MCSymbol &A,
+                                     const MCSymbol &B) const  {
+  // On MachO A - B is absolute only if in a set.
+  return IsSet;
+}
+
+bool MCCOFFObjectFormat::isAbsolute(bool IsSet, const MCSymbol &A,
+                                    const MCSymbol &B) const  {
+  // On COFF A - B is absolute if A and B are in the same section.
+  return &A.getSection() == &B.getSection();
+}
diff --git a/lib/MC/TargetAsmBackend.cpp b/lib/MC/TargetAsmBackend.cpp
index bbfddbe9e7..1f104105c1 100644
--- a/lib/MC/TargetAsmBackend.cpp
+++ b/lib/MC/TargetAsmBackend.cpp
@@ -12,7 +12,6 @@ using namespace llvm;
 
 TargetAsmBackend::TargetAsmBackend(const Target &T)
   : TheTarget(T),
-    HasAbsolutizedSet(false),
     HasReliableSymbolDifference(false),
     HasScatteredSymbols(false)
 {
diff --git a/lib/Target/ARM/ARMAsmBackend.cpp b/lib/Target/ARM/ARMAsmBackend.cpp
index df439a41b3..d113cf5b9e 100644
--- a/lib/Target/ARM/ARMAsmBackend.cpp
+++ b/lib/Target/ARM/ARMAsmBackend.cpp
@@ -14,6 +14,7 @@
 #include "llvm/MC/ELFObjectWriter.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCObjectFormat.h"
 #include "llvm/MC/MCObjectWriter.h"
 #include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCSectionMachO.h"
@@ -66,14 +67,19 @@ namespace {
 // FIXME: This should be in a separate file.
 // ELF is an ELF of course...
 class ELFARMAsmBackend : public ARMAsmBackend {
+  MCELFObjectFormat Format;
+
 public:
   Triple::OSType OSType;
   ELFARMAsmBackend(const Target &T, Triple::OSType _OSType)
     : ARMAsmBackend(T), OSType(_OSType) {
-    HasAbsolutizedSet = true;
     HasScatteredSymbols = true;
   }
 
+  virtual const MCObjectFormat &getObjectFormat() const {
+    return Format;
+  }
+
   void ApplyFixup(const MCFixup &Fixup, MCDataFragment &DF,
                   uint64_t Value) const;
 
@@ -98,14 +104,19 @@ void ELFARMAsmBackend::ApplyFixup(const MCFixup &Fixup, MCDataFragment &DF,
 
 // FIXME: This should be in a separate file.
 class DarwinARMAsmBackend : public ARMAsmBackend {
+  MCMachOObjectFormat Format;
+
 public:
   DarwinARMAsmBackend(const Target &T)
     : ARMAsmBackend(T) {
-    HasAbsolutizedSet = true;
     HasScatteredSymbols = true;
     assert(0 && "DarwinARMAsmBackend::DarwinARMAsmBackend() unimplemented");
   }
 
+  virtual const MCObjectFormat &getObjectFormat() const {
+    return Format;
+  }
+
   void ApplyFixup(const MCFixup &Fixup, MCDataFragment &DF,
                   uint64_t Value) const;
 
diff --git a/lib/Target/X86/X86AsmBackend.cpp b/lib/Target/X86/X86AsmBackend.cpp
index e641500abf..853d3ed159 100644
--- a/lib/Target/X86/X86AsmBackend.cpp
+++ b/lib/Target/X86/X86AsmBackend.cpp
@@ -14,6 +14,7 @@
 #include "llvm/MC/ELFObjectWriter.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCExpr.h"
+#include "llvm/MC/MCObjectFormat.h"
 #include "llvm/MC/MCObjectWriter.h"
 #include "llvm/MC/MCSectionCOFF.h"
 #include "llvm/MC/MCSectionELF.h"
@@ -186,15 +187,20 @@ bool X86AsmBackend::WriteNopData(uint64_t Count, MCObjectWriter *OW) const {
 
 namespace {
 class ELFX86AsmBackend : public X86AsmBackend {
+  MCELFObjectFormat Format;
+
 public:
   Triple::OSType OSType;
   ELFX86AsmBackend(const Target &T, Triple::OSType _OSType)
     : X86AsmBackend(T), OSType(_OSType) {
-    HasAbsolutizedSet = true;
     HasScatteredSymbols = true;
     HasReliableSymbolDifference = true;
   }
 
+  virtual const MCObjectFormat &getObjectFormat() const {
+    return Format;
+  }
+
   virtual bool doesSectionRequireSymbols(const MCSection &Section) const {
     const MCSectionELF &ES = static_cast<const MCSectionELF&>(Section);
     return ES.getFlags() & MCSectionELF::SHF_MERGE;
@@ -242,6 +248,8 @@ public:
 
 class WindowsX86AsmBackend : public X86AsmBackend {
   bool Is64Bit;
+  MCCOFFObjectFormat Format;
+
 public:
   WindowsX86AsmBackend(const Target &T, bool is64Bit)
     : X86AsmBackend(T)
@@ -249,6 +257,10 @@ public:
     HasScatteredSymbols = true;
   }
 
+  virtual const MCObjectFormat &getObjectFormat() const {
+    return Format;
+  }
+
   unsigned getPointerSize() const {
     if (Is64Bit)
       return 8;
@@ -267,13 +279,18 @@ public:
 };
 
 class DarwinX86AsmBackend : public X86AsmBackend {
+  MCMachOObjectFormat Format;
+
 public:
   DarwinX86AsmBackend(const Target &T)
     : X86AsmBackend(T) {
-    HasAbsolutizedSet = true;
     HasScatteredSymbols = true;
   }
 
+  virtual const MCObjectFormat &getObjectFormat() const {
+    return Format;
+  }
+
   bool isVirtualSection(const MCSection &Section) const {
     const MCSectionMachO &SMO = static_cast<const MCSectionMachO&>(Section);
     return (SMO.getType() == MCSectionMachO::S_ZEROFILL ||
diff --git a/test/MC/ELF/diff.s b/test/MC/ELF/diff.s
new file mode 100644
index 0000000000..671652cf4a
--- /dev/null
+++ b/test/MC/ELF/diff.s
@@ -0,0 +1,15 @@
+// RUN: llvm-mc -filetype=obj -triple x86_64-pc-linux-gnu %s -o - | elf-dump  | FileCheck %s
+
+        .global zed
+foo:
+        nop
+bar:
+        nop
+zed:
+        mov zed+(bar-foo), %eax
+
+// CHECK:       # Relocation 0
+// CHECK-NEXT:  (('r_offset', 5)
+// CHECK-NEXT:   ('r_sym', 6)
+// CHECK-NEXT:   ('r_type', 11)
+// CHECK-NEXT:   ('r_addend', 1)
diff --git a/test/MC/ELF/diff2.s b/test/MC/ELF/diff2.s
new file mode 100644
index 0000000000..4a9fbd1d83
--- /dev/null
+++ b/test/MC/ELF/diff2.s
@@ -0,0 +1,13 @@
+// RUN: not llvm-mc -filetype=obj -triple x86_64-pc-linux-gnu %s 2> %t
+// RUN: FileCheck -input-file %t %s
+
+.global zed
+        .data
+foo:
+        .text
+        nop
+bar:
+        nop
+zed:
+// CHECK: expected relocatable expression
+        mov zed+(bar-foo), %eax