Add an option for evaluating past symbols.

When evaluating an assembly expression for a relocation, we want to
stop at MCSymbols that are in the symbol table, even if they are variables.
This is needed since the semantics may require that the relocation use them.

That is not the case when computing the value of a symbol in the symbol table.
There are no relocations in this case and we have to keep going until we hit
a section or find out that the expression doesn't have an assembly time
value.

llvm-svn: 207445

4 files changed, 98 insertions, 21 deletions

diff --git a/llvm/include/llvm/MC/MCExpr.h b/llvm/include/llvm/MC/MCExpr.h
index 0033a54e422..f28adfa8652 100644
--- a/llvm/include/llvm/MC/MCExpr.h
+++ b/llvm/include/llvm/MC/MCExpr.h
@@ -53,8 +53,9 @@ protected:
 
   bool EvaluateAsRelocatableImpl(MCValue &Res, const MCAssembler *Asm,
                                  const MCAsmLayout *Layout,
-                                 const SectionAddrMap *Addrs,
-                                 bool InSet) const;
+                                 const SectionAddrMap *Addrs, bool InSet,
+                                 bool ForceVarExpansion) const;
+
 public:
   /// @name Accessors
   /// @{
@@ -93,6 +94,14 @@ public:
   /// @result - True on success.
   bool EvaluateAsRelocatable(MCValue &Res, const MCAsmLayout *Layout) const;
 
+  /// \brief Try to evaluate the expression to the form (a - b + constant) where
+  /// neither a nor b are variables.
+  ///
+  /// This is a more aggressive variant of EvaluateAsRelocatable. The intended
+  /// use is for when relocations are not available, like the symbol value in
+  /// the symbol table.
+  bool EvaluateAsValue(MCValue &Res, const MCAsmLayout *Layout) const;
+
   /// FindAssociatedSection - Find the "associated section" for this expression,
   /// which is currently defined as the absolute section for constants, or
   /// otherwise the section associated with the first defined symbol in the
diff --git a/llvm/lib/MC/ELFObjectWriter.cpp b/llvm/lib/MC/ELFObjectWriter.cpp
index 68e28cf4d4c..1b7ac642589 100644
--- a/llvm/lib/MC/ELFObjectWriter.cpp
+++ b/llvm/lib/MC/ELFObjectWriter.cpp
@@ -496,7 +496,7 @@ uint64_t ELFObjectWriter::SymbolValue(MCSymbolData &OrigData,
   if (Symbol->isVariable()) {
     const MCExpr *Expr = Symbol->getVariableValue();
     MCValue Value;
-    if (!Expr->EvaluateAsRelocatable(Value, &Layout))
+    if (!Expr->EvaluateAsValue(Value, &Layout))
       llvm_unreachable("Invalid expression");
 
     assert(!Value.getSymB());
@@ -606,7 +606,7 @@ static const MCSymbol *getBaseSymbol(const MCAsmLayout &Layout,
 
   const MCExpr *Expr = Symbol.getVariableValue();
   MCValue Value;
-  if (!Expr->EvaluateAsRelocatable(Value, &Layout))
+  if (!Expr->EvaluateAsValue(Value, &Layout))
     llvm_unreachable("Invalid Expression");
   const MCSymbolRefExpr *RefB = Value.getSymB();
   if (RefB) {
diff --git a/llvm/lib/MC/MCExpr.cpp b/llvm/lib/MC/MCExpr.cpp
index 300613530ae..5a45c652660 100644
--- a/llvm/lib/MC/MCExpr.cpp
+++ b/llvm/lib/MC/MCExpr.cpp
@@ -478,7 +478,8 @@ bool MCExpr::EvaluateAsAbsolute(int64_t &Res, const MCAssembler *Asm,
   // absolutize differences across sections and that is what the MachO writer
   // uses Addrs for.
   bool IsRelocatable =
-    EvaluateAsRelocatableImpl(Value, Asm, Layout, Addrs, /*InSet*/ Addrs);
+      EvaluateAsRelocatableImpl(Value, Asm, Layout, Addrs, /*InSet*/ Addrs,
+                                /*ForceVarExpansion*/ false);
 
   // Record the current value.
   Res = Value.getConstant();
@@ -629,14 +630,20 @@ static bool EvaluateSymbolicAdd(const MCAssembler *Asm,
 bool MCExpr::EvaluateAsRelocatable(MCValue &Res,
                                    const MCAsmLayout *Layout) const {
   MCAssembler *Assembler = Layout ? &Layout->getAssembler() : nullptr;
-  return EvaluateAsRelocatableImpl(Res, Assembler, Layout, nullptr, false);
+  return EvaluateAsRelocatableImpl(Res, Assembler, Layout, nullptr, false,
+                                   /*ForceVarExpansion*/ false);
 }
 
-bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
-                                       const MCAssembler *Asm,
+bool MCExpr::EvaluateAsValue(MCValue &Res, const MCAsmLayout *Layout) const {
+  MCAssembler *Assembler = Layout ? &Layout->getAssembler() : nullptr;
+  return EvaluateAsRelocatableImpl(Res, Assembler, Layout, nullptr, false,
+                                   /*ForceVarExpansion*/ true);
+}
+
+bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res, const MCAssembler *Asm,
                                        const MCAsmLayout *Layout,
-                                       const SectionAddrMap *Addrs,
-                                       bool InSet) const {
+                                       const SectionAddrMap *Addrs, bool InSet,
+                                       bool ForceVarExpansion) const {
   ++stats::MCExprEvaluate;
 
   switch (getKind()) {
@@ -649,13 +656,14 @@ bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
 
   case SymbolRef: {
     const MCSymbolRefExpr *SRE = cast<MCSymbolRefExpr>(this);
+    bool IsWeakRef = SRE->getKind() == MCSymbolRefExpr::VK_WEAKREF;
     const MCSymbol &Sym = SRE->getSymbol();
     const MCAsmInfo &MCAsmInfo = SRE->getMCAsmInfo();
 
     // Evaluate recursively if this is a variable.
-    if (Sym.isVariable()) {
-      if (Sym.getVariableValue()->EvaluateAsRelocatableImpl(Res, Asm, Layout,
-                                                            Addrs, true)) {
+    if (Sym.isVariable() && !IsWeakRef) {
+      if (Sym.getVariableValue()->EvaluateAsRelocatableImpl(
+              Res, Asm, Layout, Addrs, true, ForceVarExpansion)) {
         const MCSymbolRefExpr *A = Res.getSymA();
         const MCSymbolRefExpr *B = Res.getSymB();
 
@@ -669,9 +677,10 @@ bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
           if (!A && !B)
             return true;
         } else {
+          if (ForceVarExpansion)
+            return true;
           bool IsSymbol = A && A->getSymbol().isDefined();
-          bool IsWeakRef = SRE->getKind() == MCSymbolRefExpr::VK_WEAKREF;
-          if (!IsSymbol && !IsWeakRef)
+          if (!IsSymbol)
             return true;
         }
       }
@@ -685,8 +694,8 @@ bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
     const MCUnaryExpr *AUE = cast<MCUnaryExpr>(this);
     MCValue Value;
 
-    if (!AUE->getSubExpr()->EvaluateAsRelocatableImpl(Value, Asm, Layout,
-                                                      Addrs, InSet))
+    if (!AUE->getSubExpr()->EvaluateAsRelocatableImpl(Value, Asm, Layout, Addrs,
+                                                      InSet, ForceVarExpansion))
       return false;
 
     switch (AUE->getOpcode()) {
@@ -719,10 +728,10 @@ bool MCExpr::EvaluateAsRelocatableImpl(MCValue &Res,
     const MCBinaryExpr *ABE = cast<MCBinaryExpr>(this);
     MCValue LHSValue, RHSValue;
 
-    if (!ABE->getLHS()->EvaluateAsRelocatableImpl(LHSValue, Asm, Layout,
-                                                  Addrs, InSet) ||
-        !ABE->getRHS()->EvaluateAsRelocatableImpl(RHSValue, Asm, Layout,
-                                                  Addrs, InSet))
+    if (!ABE->getLHS()->EvaluateAsRelocatableImpl(LHSValue, Asm, Layout, Addrs,
+                                                  InSet, ForceVarExpansion) ||
+        !ABE->getRHS()->EvaluateAsRelocatableImpl(RHSValue, Asm, Layout, Addrs,
+                                                  InSet, ForceVarExpansion))
       return false;
 
     // We only support a few operations on non-constant expressions, handle
diff --git a/llvm/test/MC/ELF/offset.s b/llvm/test/MC/ELF/offset.s
index a412619143f..f4483329949 100644
--- a/llvm/test/MC/ELF/offset.s
+++ b/llvm/test/MC/ELF/offset.s
@@ -71,3 +71,62 @@ sym_f = sym_a + (1 - 1)
 // CHECK-NEXT:    Other: 0
 // CHECK-NEXT:    Section: .data
 // CHECK-NEXT:  }
+
+
+        .globl test2_a
+        .globl test2_b
+        .globl test2_c
+        .globl test2_d
+        .globl test2_e
+test2_a:
+    .long 0
+test2_b = test2_a
+test2_c:
+    .long 0
+test2_d = test2_c
+test2_e = test2_d - test2_b
+// CHECK:      Symbol {
+// CHECK:        Name: test2_a
+// CHECK-NEXT:   Value: 0x5
+// CHECK-NEXT:   Size: 0
+// CHECK-NEXT:   Binding: Global
+// CHECK-NEXT:   Type: None
+// CHECK-NEXT:   Other: 0
+// CHECK-NEXT:   Section: .data
+// CHECK-NEXT: }
+// CHECK-NEXT: Symbol {
+// CHECK-NEXT:   Name: test2_b
+// CHECK-NEXT:   Value: 0x5
+// CHECK-NEXT:   Size: 0
+// CHECK-NEXT:   Binding: Global
+// CHECK-NEXT:   Type: None
+// CHECK-NEXT:   Other: 0
+// CHECK-NEXT:   Section: .data
+// CHECK-NEXT: }
+// CHECK-NEXT: Symbol {
+// CHECK-NEXT:   Name: test2_c
+// CHECK-NEXT:   Value: 0x9
+// CHECK-NEXT:   Size: 0
+// CHECK-NEXT:   Binding: Global
+// CHECK-NEXT:   Type: None
+// CHECK-NEXT:   Other: 0
+// CHECK-NEXT:   Section: .data
+// CHECK-NEXT: }
+// CHECK-NEXT: Symbol {
+// CHECK-NEXT:   Name: test2_d
+// CHECK-NEXT:   Value: 0x9
+// CHECK-NEXT:   Size: 0
+// CHECK-NEXT:   Binding: Global
+// CHECK-NEXT:   Type: None
+// CHECK-NEXT:   Other: 0
+// CHECK-NEXT:   Section: .data
+// CHECK-NEXT: }
+// CHECK-NEXT: Symbol {
+// CHECK-NEXT:   Name: test2_e
+// CHECK-NEXT:   Value: 0x4
+// CHECK-NEXT:   Size: 0
+// CHECK-NEXT:   Binding: Global
+// CHECK-NEXT:   Type: None
+// CHECK-NEXT:   Other: 0
+// CHECK-NEXT:   Section: Absolute
+// CHECK-NEXT: }