[LLD][ELF] Extract allocateHeaders() from assignAddresses()

[peter.smith]

Summary

The allocateHeaders() function is called at the end of assignAddresses(), it decides whether the ELF header and program header table can be allocated to
a PT_LOAD program header. As the function alters state, it prevents assignAddresses() from being called multiple times. This change splits out the call to allocateHeaders() from assignAddresses() this will permit assignAddresses() to be called while processing range extension thunks without trying to allocateHeaders().

This change on its own is insufficient to allow assignAddresses() to be called multiple times in all cases, I'll send a follow up patch that resets the state accumulated during the assignAddresses().

[peter.smith]

This is patch 3/11 of range thunks although it can be applied independently.

[jhenderson]

ELF/LinkerScript.cpp

828–829

Unnecessary return.

[peter.smith]

Thanks for the comment, I've removed the redundant return.

[peter.smith]

Rebased to account for r307039

ELF/LinkerScript.h

public:
   std::vector<PhdrEntry> createPhdrs();
   bool ignoreInterpSection();
 
   bool hasLMA(OutputSection *Sec);
   bool shouldKeep(InputSectionBase *S);
   void assignOffsets(OutputSectionCommand *Cmd);
   void createOrphanCommands();
   void processNonSectionCommands();
-  void assignAddresses(std::vector<PhdrEntry> &Phdrs);
-
+  void assignAddresses();
+  void allocateHeaders(std::vector<PhdrEntry> &Phdrs);
   void addSymbol(SymbolAssignment *Cmd);
   void processCommands(OutputSectionFactory &Factory);
 
   // Parsed linker script configurations are set to this struct.
   ScriptConfiguration Opt;
 };
 
 extern LinkerScript *Script;
 
 } // end namespace elf
 } // end namespace lld
 
 #endif // LLD_ELF_LINKER_SCRIPT_H

ELF/LinkerScript.cpp

void LinkerScript::processNonSectionCommands() {
   for (BaseCommand *Base : Opt.Commands) {
     if (auto *Cmd = dyn_cast<SymbolAssignment>(Base))
       assignSymbol(Cmd, false);
     else if (auto *Cmd = dyn_cast<AssertCommand>(Base))
       Cmd->Expression();
   }
 }
 
-static bool
-allocateHeaders(std::vector<PhdrEntry> &Phdrs,
-                ArrayRef<OutputSectionCommand *> OutputSectionCommands,
-                uint64_t Min) {
+void LinkerScript::allocateHeaders(std::vector<PhdrEntry> &Phdrs) {
+  uint64_t Min = std::numeric_limits<uint64_t>::max();
+  for (OutputSectionCommand *Cmd : OutputSectionCommands) {
+    OutputSection *Sec = Cmd->Sec;
+    if (Sec->Flags & SHF_ALLOC)
+      Min = std::min<uint64_t>(Min, Sec->Addr);
+  }
+
   auto FirstPTLoad =
       std::find_if(Phdrs.begin(), Phdrs.end(),
                    [](const PhdrEntry &E) { return E.p_type == PT_LOAD; });
   if (FirstPTLoad == Phdrs.end())
-    return false;
+    return;
 
   uint64_t HeaderSize = getHeaderSize();
   if (HeaderSize <= Min || Script->hasPhdrsCommands()) {
     Min = alignDown(Min - HeaderSize, Config->MaxPageSize);
     Out::ElfHeader->Addr = Min;
     Out::ProgramHeaders->Addr = Min + Out::ElfHeader->Size;
-    return true;
+    return;
   }
 
   assert(FirstPTLoad->First == Out::ElfHeader);
   OutputSection *ActualFirst = nullptr;
   for (OutputSectionCommand *Cmd : OutputSectionCommands) {
     OutputSection *Sec = Cmd->Sec;
     if (Sec->FirstInPtLoad == Out::ElfHeader) {
       ActualFirst = Sec;
void LinkerScript::allocateHeaders(std::vector<PhdrEntry> &Phdrs) {
   } else {
     Phdrs.erase(FirstPTLoad);
   }
 
   auto PhdrI = std::find_if(Phdrs.begin(), Phdrs.end(), [](const PhdrEntry &E) {
     return E.p_type == PT_PHDR;
   });
   if (PhdrI != Phdrs.end())
     Phdrs.erase(PhdrI);
-  return false;
 }
 
-void LinkerScript::assignAddresses(std::vector<PhdrEntry> &Phdrs) {
+void LinkerScript::assignAddresses() {
   // Assign addresses as instructed by linker script SECTIONS sub-commands.
   Dot = 0;
   ErrorOnMissingSection = true;
   switchTo(Aether);
 
   for (BaseCommand *Base : Opt.Commands) {
     if (auto *Cmd = dyn_cast<SymbolAssignment>(Base)) {
       assignSymbol(Cmd, false);
       continue;
     }
 
     if (auto *Cmd = dyn_cast<AssertCommand>(Base)) {
       Cmd->Expression();
       continue;
     }
 
     auto *Cmd = cast<OutputSectionCommand>(Base);
     assignOffsets(Cmd);
   }
-
-  uint64_t MinVA = std::numeric_limits<uint64_t>::max();
-  for (OutputSectionCommand *Cmd : OutputSectionCommands) {
-    OutputSection *Sec = Cmd->Sec;
-    if (Sec->Flags & SHF_ALLOC)
-      MinVA = std::min<uint64_t>(MinVA, Sec->Addr);
-  }
-
-  allocateHeaders(Phdrs, OutputSectionCommands, MinVA);
 }
 
 // Creates program headers as instructed by PHDRS linker script command.
 std::vector<PhdrEntry> LinkerScript::createPhdrs() {
   std::vector<PhdrEntry> Ret;
 
   // Process PHDRS and FILEHDR keywords because they are not
   // real output sections and cannot be added in the following loop.

ELF/Writer.cpp

template <class ELFT> void Writer<ELFT>::run() {
 
   // If -compressed-debug-sections is specified, we need to compress
   // .debug_* sections. Do it right now because it changes the size of
   // output sections.
   parallelForEach(
       OutputSectionCommands.begin(), OutputSectionCommands.end(),
       [](OutputSectionCommand *Cmd) { Cmd->maybeCompress<ELFT>(); });
 
-  Script->assignAddresses(Phdrs);
+  Script->assignAddresses();
+  Script->allocateHeaders(Phdrs);
 
   // Remove empty PT_LOAD to avoid causing the dynamic linker to try to mmap a
   // 0 sized region. This has to be done late since only after assignAddresses
   // we know the size of the sections.
   removeEmptyPTLoad();
 
   if (!Config->OFormatBinary)
     assignFileOffsets();