[DEMO] - Demo prototype of "tree" view of linkerscript design.

[grimar]

Summary

This is demo of linker script tree representation.

Since SECTION can be:

SECTION {
assignment<>
outputsection<>
  assignment<>
  ...
  phds<>
assignment<>
outputsection<>
}

This classes hierarchy can keep something like that for parsing.

I took Phdrs command for example. Previously it was not section command, when it seems it should be.

[ruiu]

ELF/LinkerScript.h

47

Since you are trying to define a class to represent https://sourceware.org/binutils/docs/ld/Output-Section-Description.html#Output-Section-Description, you want to reflect the structure of the command. So I guess you want to define something like

struct OutputSectionDescription {
  std::vector<OutputSectionCommand> Commands;
  std::vector<StringRef> Phdrs;
  std::vector<uint8_t> Filler;
}

[grimar]

ELF/LinkerScript.h

47

I see. Thanks for clarification.
I`ll try to prepare the first real patch then. In a few hours I hope.

ELF/LinkerScript.h

struct SectionRule {
   StringRef Dest;
 
   StringRef SectionPattern;
 };
 
 // This enum represents what we can observe in SECTIONS tag of script:
 // ExprKind is a location counter change, like ". = . + 0x1000"
 // SectionKind is a description of output section, like ".data :..."
-enum SectionsCommandKind { SectionKind, AssignmentKind };
+enum SectionsCommandKind { OutputSectionKind, AssignmentKind, PhdrsKind };
+
+struct SectionsCommand;
+
+struct PhdrsCmd {
+  std::vector<StringRef> Phdrs;
+};
+
+struct OutputSectionCmd {
+  StringRef Name;
+  std::vector<SectionsCommand> Commands;
+};
+
+struct AssignmentCmd {
+  StringRef Name;
+  std::vector<StringRef> Expr;
+};
 
 struct SectionsCommand {
+  SectionsCommand(SectionsCommandKind Kind) : Kind(Kind) {}
   SectionsCommandKind Kind;
-  std::vector<StringRef> Expr;
-  StringRef Name;
-  std::vector<StringRef> Phdrs;
+
+  OutputSectionCmd OutputSection;
+  AssignmentCmd Assignment;
+  PhdrsCmd Phdrs;
 };
 
 struct PhdrsCommand {
   StringRef Name;
   unsigned Type;
   bool HasFilehdr;
   bool HasPhdrs;
 };

ELF/LinkerScript.cpp

void LinkerScript<ELFT>::assignAddresses(
   // Orphan sections are sections present in the input files which
   // are not explicitly placed into the output file by the linker script.
   // We place orphan sections at end of file.
   // Other linkers places them using some heuristics as described in
   // https://sourceware.org/binutils/docs/ld/Orphan-Sections.html#Orphan-Sections.
   for (OutputSectionBase<ELFT> *Sec : Sections) {
     StringRef Name = Sec->getName();
     if (getSectionIndex(Name) == INT_MAX)
-      Opt.Commands.push_back({SectionKind, {}, Name, {}});
+      Opt.Commands.emplace(Opt.Commands.end(), SectionsCommand(OutputSectionKind))
+          ->OutputSection.Name = Name;
   }
 
   // Assign addresses as instructed by linker script SECTIONS sub-commands.
   Dot = Out<ELFT>::ElfHeader->getSize() + Out<ELFT>::ProgramHeaders->getSize();
   uintX_t MinVA = std::numeric_limits<uintX_t>::max();
   uintX_t ThreadBssOffset = 0;
 
   for (SectionsCommand &Cmd : Opt.Commands) {
     if (Cmd.Kind == AssignmentKind) {
-      uint64_t Val = evalExpr(Cmd.Expr, Dot);
+      AssignmentCmd &A = Cmd.Assignment;
+      uint64_t Val = evalExpr(A.Expr, Dot);
 
-      if (Cmd.Name == ".") {
+      if (A.Name == ".") {
         Dot = Val;
       } else {
-        auto *D = cast<DefinedRegular<ELFT>>(Symtab<ELFT>::X->find(Cmd.Name));
+        auto *D = cast<DefinedRegular<ELFT>>(Symtab<ELFT>::X->find(A.Name));
         D->Value = Val;
       }
       continue;
     }
 
     // Find all the sections with required name. There can be more than
     // one section with such name, if the alignment, flags or type
     // attribute differs.
-    assert(Cmd.Kind == SectionKind);
+    assert(Cmd.Kind == OutputSectionKind);
     for (OutputSectionBase<ELFT> *Sec : Sections) {
-      if (Sec->getName() != Cmd.Name)
+      if (Sec->getName() != Cmd.OutputSection.Name)
         continue;
 
       if ((Sec->getFlags() & SHF_TLS) && Sec->getType() == SHT_NOBITS) {
         uintX_t TVA = Dot + ThreadBssOffset;
         TVA = alignTo(TVA, Sec->getAlignment());
         Sec->setVA(TVA);
         ThreadBssOffset = TVA - Dot + Sec->getSize();
         continue;
if (I == Opt.Filler.end())
     return {};
   return I->second;
 }
 
 // Returns the index of the given section name in linker script
 // SECTIONS commands. Sections are laid out as the same order as they
 // were in the script. If a given name did not appear in the script,
 // it returns INT_MAX, so that it will be laid out at end of file.
-template <class ELFT>
-int LinkerScript<ELFT>::getSectionIndex(StringRef Name) {
+template <class ELFT> int LinkerScript<ELFT>::getSectionIndex(StringRef Name) {
   auto Begin = Opt.Commands.begin();
   auto End = Opt.Commands.end();
   auto I = std::find_if(Begin, End, [&](SectionsCommand &N) {
-    return N.Kind == SectionKind && N.Name == Name;
+    return N.Kind == OutputSectionKind && N.OutputSection.Name == Name;
   });
   return I == End ? INT_MAX : (I - Begin);
 }
 
 // A compartor to sort output sections. Returns -1 or 1 if
 // A or B are mentioned in linker script. Otherwise, returns 0.
 template <class ELFT>
 int LinkerScript<ELFT>::compareSections(StringRef A, StringRef B) {
   int I = getSectionIndex(A);
   int J = getSectionIndex(B);
   if (I == INT_MAX && J == INT_MAX)
     return 0;
   return I < J ? -1 : 1;
 }
 
 template <class ELFT>
 void LinkerScript<ELFT>::addScriptedSymbols() {
-  for (SectionsCommand &Cmd : Opt.Commands)
-    if (Cmd.Kind == AssignmentKind)
-      if (Cmd.Name != "." && Symtab<ELFT>::X->find(Cmd.Name) == nullptr)
-        Symtab<ELFT>::X->addAbsolute(Cmd.Name, STV_DEFAULT);
+  for (SectionsCommand &Cmd : Opt.Commands) {
+    if (Cmd.Kind != AssignmentKind)
+      continue;
+    AssignmentCmd &A = Cmd.Assignment;
+    if (A.Name != "." && Symtab<ELFT>::X->find(A.Name) == nullptr)
+      Symtab<ELFT>::X->addAbsolute(A.Name, STV_DEFAULT);
+  }
 }
 
 template <class ELFT> bool LinkerScript<ELFT>::hasPhdrsCommands() {
   return !Opt.PhdrsCommands.empty();
 }
 
 // Returns indices of ELF headers containing specific section, identified
 // by Name. Each index is a zero based number of ELF header listed within
 // PHDRS {} script block.
 template <class ELFT>
 std::vector<size_t>
 LinkerScript<ELFT>::getPhdrIndicesForSection(StringRef Name) {
   for (SectionsCommand &Cmd : Opt.Commands) {
-    if (Cmd.Kind != SectionKind || Cmd.Name != Name)
+    if (Cmd.Kind != OutputSectionKind || Cmd.OutputSection.Name != Name)
       continue;
 
+    auto I = llvm::find_if(Cmd.OutputSection.Commands, [](SectionsCommand &C) {
+      return C.Kind == PhdrsKind;
+    });
+    if (I == Cmd.OutputSection.Commands.end())
+      return {};
+
     std::vector<size_t> Indices;
-    for (StringRef PhdrName : Cmd.Phdrs) {
+    for (StringRef PhdrName : I->Phdrs.Phdrs) {
       auto ItPhdr =
           std::find_if(Opt.PhdrsCommands.rbegin(), Opt.PhdrsCommands.rend(),
                        [&](PhdrsCommand &Cmd) { return Cmd.Name == PhdrName; });
       if (ItPhdr == Opt.PhdrsCommands.rend())
         error("section header '" + PhdrName + "' is not listed in PHDRS");
       else
         Indices.push_back(std::distance(ItPhdr, Opt.PhdrsCommands.rend()) - 1);
     }
else
       readOutputSectionDescription(Tok);
   }
 }
 
 void ScriptParser::readLocationCounterValue() {
   expect(".");
   expect("=");
   std::vector<StringRef> Expr = readSectionsCommandExpr();
-  if (Expr.empty())
+  if (Expr.empty()) {
     error("error in location counter expression");
-  else
-    Opt.Commands.push_back({AssignmentKind, std::move(Expr), ".", {}});
+    return;
+  }
+
+  Opt.Commands.push_back(SectionsCommand(AssignmentKind));
+  Opt.Commands.back().Assignment = { ".", std::move(Expr) };
 }
 
 void ScriptParser::readOutputSectionDescription(StringRef OutSec) {
-  Opt.Commands.push_back({SectionKind, {}, OutSec, {}});
-  SectionsCommand &Cmd = Opt.Commands.back();
+  OutputSectionCmd &S = Opt.Commands.emplace(Opt.Commands.end(),
+                                             SectionsCommand(OutputSectionKind))
+                            ->OutputSection;
+
+  S.Name = OutSec;
   expect(":");
   expect("{");
 
   while (!Error && !skip("}")) {
     StringRef Tok = next();
     if (Tok == "*") {
       expect("(");
       while (!Error && !skip(")"))
         Opt.Sections.emplace_back(OutSec, next());
     } else if (Tok == "KEEP") {
       expect("(");
       expect("*");
       expect("(");
       while (!Error && !skip(")")) {
         StringRef Sec = next();
         Opt.Sections.emplace_back(OutSec, Sec);
         Opt.KeptSections.push_back(Sec);
       }
       expect(")");
     } else {
       setError("unknown command " + Tok);
     }
   }
-  Cmd.Phdrs = readOutputSectionPhdrs();
+
+  S.Commands.emplace(S.Commands.end(), SectionsCommand(PhdrsKind))
+      ->Phdrs.Phdrs = readOutputSectionPhdrs();
 
   StringRef Tok = peek();
   if (Tok.startswith("=")) {
     if (!Tok.startswith("=0x")) {
       setError("filler should be a hexadecimal value");
       return;
     }
     Tok = Tok.substr(3);
     Opt.Filler[OutSec] = parseHex(Tok);
     next();
   }
 }
 
 void ScriptParser::readSymbolAssignment(StringRef Name) {
   expect("=");
   std::vector<StringRef> Expr = readSectionsCommandExpr();
-  if (Expr.empty())
+  if (Expr.empty()) {
     error("error in symbol assignment expression");
-  else
-    Opt.Commands.push_back({AssignmentKind, std::move(Expr), Name, {}});
+    return;
+  }
+
+  Opt.Commands.push_back(SectionsCommand(AssignmentKind));
+  Opt.Commands.back().Assignment = {Name, std::move(Expr)};
 }
 
 std::vector<StringRef> ScriptParser::readSectionsCommandExpr() {
   std::vector<StringRef> Expr;
   while (!Error) {
     StringRef Tok = next();
     if (Tok == ";")
       break;