[ELF] Linkerscript: symbol assignments with indentifiers on the right side of expression.

[grimar]

Summary

In symbol assignments symbol may appear on the right-hand side of the expression:
(https://svnweb.freebsd.org/base/head/sys/conf/ldscript.amd64?revision=284870&view=markup#l8)

 /* Read-only sections, merged into text segment: */
kernphys = CONSTANT (MAXPAGESIZE);
 . = kernbase + kernphys + SIZEOF_HEADERS;

Patch implements that.

[ruiu]

ELF/LinkerScript.cpp

807–809

Please do this.

uint64_t static getSymbolValue(StringRef S) {
  switch (Config->EKind) {
  case ELF32LEKind:
    if (SymbolBody *B = Symtab<ELF32LE>::X->find(S))
      return B->getVA<ELF32LE>();
    break;
  case ELF32BEKind:
    ...
  case ELF64LEKind:
    ...
  case ELF64BEKind:
    ...
  }
  error("symbol not found: " + S);
  return 0;
}

[grimar]

• Addressed review comments.
• Improved testcase.

[ruiu]

LGTM

ELF/LinkerScript.cpp

746

uint64_t static -> static uint64_t.

764–765

We don't need this guard.

851

Parse a symbol name or a number literal.

[grimar]

ELF/LinkerScript.cpp

746

Done.

764–765

Removed.

807–809

Done.

851

Fixed.

ELF/LinkerScript.cpp

SymbolAssignment *ScriptParser::readAssignment(StringRef Name) {
   Opt.Commands.emplace_back(Cmd);
   return Cmd;
 }
 
 // This is an operator-precedence parser to parse a linker
 // script expression.
 Expr ScriptParser::readExpr() { return readExpr1(readPrimary(), 0); }
 
+uint64_t static getSymbolValue(StringRef S) {
+  switch (Config->EKind) {
+  case ELF32LEKind:
+    if (SymbolBody *B = Symtab<ELF32LE>::X->find(S))
+      return B->getVA<ELF32LE>();
+    break;
+  case ELF32BEKind:
+    if (SymbolBody *B = Symtab<ELF32BE>::X->find(S))
+      return B->getVA<ELF32BE>();
+    break;
+  case ELF64LEKind:
+    if (SymbolBody *B = Symtab<ELF64LE>::X->find(S))
+      return B->getVA<ELF64LE>();
+    break;
+  case ELF64BEKind:
+    if (SymbolBody *B = Symtab<ELF64BE>::X->find(S))
+      return B->getVA<ELF64BE>();
+    break;
+  default:
+    llvm_unreachable("unknown ELF kind");
+  }
+  error("symbol not found: " + S);
+  return 0;
+}
+
 // This is a part of the operator-precedence parser. This function
 // assumes that the remaining token stream starts with an operator.
 Expr ScriptParser::readExpr1(Expr Lhs, int MinPrec) {
   while (!atEOF() && !Error) {
     // Read an operator and an expression.
     StringRef Op1 = peek();
     if (Op1 == "?")
       return readTernary(Lhs);

 
 uint64_t static getConstant(StringRef S) {
   if (S == "COMMONPAGESIZE" || S == "MAXPAGESIZE")
     return Target->PageSize;
   error("unknown constant: " + S);
   return 0;
 }
 
 Expr ScriptParser::readPrimary() {
   StringRef Tok = next();
 
   if (Tok == ".")
     return [](uint64_t Dot) { return Dot; };
 
   if (Tok == "(") {
     Expr E = readExpr();
     expect(")");
     return E;
   }
Expr ScriptParser::readPrimary() {
   }
   if (Tok == "DATA_SEGMENT_END") {
     expect("(");
     expect(".");
     expect(")");
     return [](uint64_t Dot) { return Dot; };
   }
 
   // Parse a number literal
   uint64_t V = 0;
-  if (Tok.getAsInteger(0, V))
+  if (Tok.getAsInteger(0, V)) {
+    if (!isValidCIdentifier(Tok))
       setError("malformed number: " + Tok);
+    return [=](uint64_t Dot) { return getSymbolValue(Tok); };
+  }
   return [=](uint64_t Dot) { return V; };
 }
 
 Expr ScriptParser::readTernary(Expr Cond) {
   next();
   Expr L = readExpr();
   expect(":");
   Expr R = readExpr();

test/ELF/linkerscript/linkerscript-symbol-assignexpr.s

+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t
+
+# RUN: echo "SECTIONS { \
+# RUN:         symbol = CONSTANT(MAXPAGESIZE); \
+# RUN:         symbol2 = symbol + 0x1234; \
+# RUN:         symbol3 = symbol2; \
+# RUN:       }" > %t.script
+# RUN: ld.lld -o %t1 --script %t.script %t
+# RUN: llvm-objdump -t %t1 | FileCheck %s
+
+# CHECK:      SYMBOL TABLE:
+# CHECK-NEXT: 0000000000000000 *UND* 00000000
+# CHECK-NEXT: 0000000000000120 .text 00000000 _start
+# CHECK-NEXT: 0000000000000121 .text 00000000 foo
+# CHECK-NEXT: 0000000000001000 *ABS* 00000000 symbol
+# CHECK-NEXT: 0000000000002234 *ABS* 00000000 symbol2
+# CHECK-NEXT: 0000000000002234 *ABS* 00000000 symbol3
+
+# RUN: echo "SECTIONS { \
+# RUN:         symbol2 = symbol; \
+# RUN:       }" > %t2.script
+# RUN: not ld.lld -o %t2 --script %t2.script %t 2>&1 \
+# RUN:  | FileCheck -check-prefix=ERR %s
+# ERR: symbol not found: symbol
+
+.global _start
+_start:
+ nop
+
+.global foo
+foo: