ELF: Introduce a separate bit for tracking whether an output section has ever had an input section added to it. NFCI.

[pcc]

Summary

We currently (ab)use the Live bit on output sections to track whether
the section has ever had an input section added to it, and then later
use it during orphan placement. This will conflict with one of my upcoming
partition-related changes that will assign all output sections to a partition
(thus marking them as live) so that they can be added to the correct segment
by the code that creates program headers.

Instead of using the Live bit for this purpose, create a new flag and
start using it to track the property explicitly.

Depends on D60353

[grimar]

For me - looks good.

[ruiu]

LGTM

lld/trunk/ELF/LinkerScript.cpp

for (BaseCommand *&Cmd : SectionCommands) {
     if (!Sec)
       continue;
 
     // Handle align (e.g. ".foo : ALIGN(16) { ... }").
     if (Sec->AlignExpr)
       Sec->Alignment =
           std::max<uint32_t>(Sec->Alignment, Sec->AlignExpr().getValue());
 
-    // A live output section means that some input section was added to it. It
-    // might have been removed (if it was empty synthetic section), but we at
-    // least know the flags.
-    if (Sec->isLive())
+    // The input section might have been removed (if it was an empty synthetic
+    // section), but we at least know the flags.
+    if (Sec->HasInputSections)
       Flags = Sec->Flags;
 
     // We do not want to keep any special flags for output section
     // in case it is empty.
     bool IsEmpty = getInputSections(Sec).empty();
     if (IsEmpty)
       Sec->Flags = Flags & ((Sec->NonAlloc ? 0 : (uint64_t)SHF_ALLOC) |
                             SHF_WRITE | SHF_EXECINSTR);

lld/trunk/ELF/OutputSections.h

public:
   std::string MemoryRegionName;
   std::string LMARegionName;
   bool NonAlloc = false;
   bool Noload = false;
   bool ExpressionsUseSymbols = false;
   bool UsedInExpression = false;
   bool InOverlay = false;
 
+  // Tracks whether the section has ever had an input section added to it, even
+  // if the section was later removed (e.g. because it is a synthetic section
+  // that wasn't needed). This is needed for orphan placement.
+  bool HasInputSections = false;
+
   void finalize();
   template <class ELFT> void writeTo(uint8_t *Buf);
   template <class ELFT> void maybeCompress();
 
   void sort(llvm::function_ref<int(InputSectionBase *S)> Order);
   void sortInitFini();
   void sortCtorsDtors();
 

lld/trunk/ELF/OutputSections.cpp

 // seem to be a harm in merging them.
 static bool canMergeToProgbits(unsigned Type) {
   return Type == SHT_NOBITS || Type == SHT_PROGBITS || Type == SHT_INIT_ARRAY ||
          Type == SHT_PREINIT_ARRAY || Type == SHT_FINI_ARRAY ||
          Type == SHT_NOTE;
 }
 
 void OutputSection::addSection(InputSection *IS) {
-  if (!isLive()) {
+  if (!HasInputSections) {
     // If IS is the first section to be added to this section,
     // initialize Partition, Type, Entsize and flags from IS.
+    HasInputSections = true;
     Partition = IS->Partition;
     Type = IS->Type;
     Entsize = IS->Entsize;
     Flags = IS->Flags;
   } else {
     // Otherwise, check if new type or flags are compatible with existing ones.
     unsigned Mask = SHF_TLS | SHF_LINK_ORDER;
     if ((Flags & Mask) != (IS->Flags & Mask))

lld/trunk/ELF/Writer.cpp

 // Since each branch corresponds to a bit flag, we can just use
 // countLeadingZeros.
 static int getRankProximityAux(OutputSection *A, OutputSection *B) {
   return countLeadingZeros(A->SortRank ^ B->SortRank);
 }
 
 static int getRankProximity(OutputSection *A, BaseCommand *B) {
   auto *Sec = dyn_cast<OutputSection>(B);
-  return (Sec && Sec->isLive()) ? getRankProximityAux(A, Sec) : -1;
+  return (Sec && Sec->HasInputSections) ? getRankProximityAux(A, Sec) : -1;
 }
 
 // When placing orphan sections, we want to place them after symbol assignments
 // so that an orphan after
 //   begin_foo = .;
 //   foo : { *(foo) }
 //   end_foo = .;
 // doesn't break the intended meaning of the begin/end symbols.
findOrphanPos(std::vector<BaseCommand *>::iterator B,
   });
   if (I == E)
     return E;
 
   // Consider all existing sections with the same proximity.
   int Proximity = getRankProximity(Sec, *I);
   for (; I != E; ++I) {
     auto *CurSec = dyn_cast<OutputSection>(*I);
-    if (!CurSec || !CurSec->isLive())
+    if (!CurSec || !CurSec->HasInputSections)
       continue;
     if (getRankProximity(Sec, CurSec) != Proximity ||
         Sec->SortRank < CurSec->SortRank)
       break;
   }
 
-  auto IsLiveOutputSec = [](BaseCommand *Cmd) {
+  auto IsOutputSecWithInputSections = [](BaseCommand *Cmd) {
     auto *OS = dyn_cast<OutputSection>(Cmd);
-    return OS && OS->isLive();
+    return OS && OS->HasInputSections;
   };
   auto J = std::find_if(llvm::make_reverse_iterator(I),
-                        llvm::make_reverse_iterator(B), IsLiveOutputSec);
+                        llvm::make_reverse_iterator(B),
+                        IsOutputSecWithInputSections);
   I = J.base();
 
   // As a special case, if the orphan section is the last section, put
   // it at the very end, past any other commands.
   // This matches bfd's behavior and is convenient when the linker script fully
   // specifies the start of the file, but doesn't care about the end (the non
   // alloc sections for example).
-  auto NextSec = std::find_if(I, E, IsLiveOutputSec);
+  auto NextSec = std::find_if(I, E, IsOutputSecWithInputSections);
   if (NextSec == E)
     return E;
 
   while (I != E && shouldSkip(*I))
     ++I;
   return I;
 }