[lld/mac] Implement support for section$start and section$ end symbols

With this, libclang_rt.profile_osx.a can be linked, that is coverage
and PGO-instrumented builds should now work with lld.

section$start and section$end symbols can create non-existing sections.
They're also undefined symbols that are only magic if there isn't a
regular symbol with their name, which means the need to be handled
in treatUndefined() instead of just looping over all existing
sections and adding start and end symbols like the ELF port does.

To represent the actual symbols, this uses absolute symbols that
get their value updated once an output section is layed out.

segment$start and segment$end are still missing for now, but they produce a
nicer error message after this patch.

Main part of PR50760.

Differential Revision: https://reviews.llvm.org/D106629

Author: nico

lld/MachO/OutputSection.cpp

@@ -16,3 +16,10 @@ using namespace lld::macho;
 uint64_t OutputSection::getSegmentOffset() const {
   return addr - parent->addr;
 }
+
+void OutputSection::assignAddressesToStartEndSymbols() {
+  for (Defined *d : sectionStartSymbols)
+    d->value = addr;
+  for (Defined *d : sectionEndSymbols)
+    d->value = addr + getSize();
+}

lld/MachO/OutputSection.h

@@ -9,14 +9,17 @@
 #ifndef LLD_MACHO_OUTPUT_SECTION_H
 #define LLD_MACHO_OUTPUT_SECTION_H
 
+#include "Symbols.h"
 #include "lld/Common/LLVM.h"
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/TinyPtrVector.h"
 
 #include <limits>
 
 namespace lld {
 namespace macho {
 
+class Defined;
 class InputSection;
 class OutputSegment;
 
@@ -62,7 +65,11 @@ class OutputSection {
 
   virtual void writeTo(uint8_t *buf) const = 0;
 
+  void assignAddressesToStartEndSymbols();
+
   StringRef name;
+  llvm::TinyPtrVector<Defined *> sectionStartSymbols;
+  llvm::TinyPtrVector<Defined *> sectionEndSymbols;
   OutputSegment *parent = nullptr;
   // For output sections that don't have explicit ordering requirements, their
   // output order should be based on the order of the input sections they

lld/MachO/SymbolTable.cpp

@@ -7,9 +7,11 @@
 //===----------------------------------------------------------------------===//
 
 #include "SymbolTable.h"
+#include "ConcatOutputSection.h"
 #include "Config.h"
 #include "InputFiles.h"
 #include "Symbols.h"
+#include "SyntheticSections.h"
 #include "lld/Common/ErrorHandler.h"
 #include "lld/Common/Memory.h"
 
@@ -196,7 +198,73 @@ Defined *SymbolTable::addSynthetic(StringRef name, InputSection *isec,
   return s;
 }
 
+enum class Boundary {
+  Start,
+  End,
+};
+
+static void handleSectionBoundarySymbol(const Undefined &sym, StringRef segSect,
+                                        Boundary which) {
+  StringRef segName, sectName;
+  std::tie(segName, sectName) = segSect.split('$');
+
+  // Attach the symbol to any InputSection that will end up in the right
+  // OutputSection -- it doesn't matter which one we pick.
+  // Don't bother looking through inputSections for a matching
+  // ConcatInputSection -- we need to create ConcatInputSection for
+  // non-existing sections anyways, and that codepath works even if we should
+  // already have a ConcatInputSection with the right name.
+
+  OutputSection *osec = nullptr;
+  // This looks for __TEXT,__cstring etc.
+  for (SyntheticSection *ssec : syntheticSections)
+    if (ssec->segname == segName && ssec->name == sectName) {
+      osec = ssec->isec->parent;
+      break;
+    }
+
+  if (!osec) {
+    ConcatInputSection *isec = make<ConcatInputSection>(segName, sectName);
+
+    // This runs after markLive() and is only called for Undefineds that are
+    // live. Marking the isec live ensures an OutputSection is created that the
+    // start/end symbol can refer to.
+    assert(sym.isLive());
+    isec->live = true;
+
+    // This runs after gatherInputSections(), so need to explicitly set parent
+    // and add to inputSections.
+    osec = isec->parent = ConcatOutputSection::getOrCreateForInput(isec);
+    inputSections.push_back(isec);
+  }
+
+  Defined *boundarySym = symtab->addSynthetic(
+      sym.getName(), /*isec=*/nullptr, /*value=*/-1, /*isPrivateExtern=*/true,
+      /*includeInSymtab=*/false, /*referencedDynamically=*/false);
+  if (which == Boundary::Start)
+    osec->sectionStartSymbols.push_back(boundarySym);
+  else
+    osec->sectionEndSymbols.push_back(boundarySym);
+}
+
+static void handleSegmentBoundarySymbol(const Undefined &sym, StringRef segName,
+                                        Boundary which) {
+  // FIXME
+  error("segment$start$ and segment$end$ symbols are not yet implemented");
+}
+
 void lld::macho::treatUndefinedSymbol(const Undefined &sym, StringRef source) {
+  // Handle start/end symbols.
+  StringRef name = sym.getName();
+  if (name.consume_front("section$start$"))
+    return handleSectionBoundarySymbol(sym, name, Boundary::Start);
+  if (name.consume_front("section$end$"))
+    return handleSectionBoundarySymbol(sym, name, Boundary::End);
+  if (name.consume_front("segment$start$"))
+    return handleSegmentBoundarySymbol(sym, name, Boundary::Start);
+  if (name.consume_front("segment$end$"))
+    return handleSegmentBoundarySymbol(sym, name, Boundary::End);
+
   // Handle -U.
   if (config->explicitDynamicLookups.count(sym.getName())) {
     symtab->addDynamicLookup(sym.getName());

lld/MachO/Writer.cpp

@@ -630,7 +630,12 @@ static void prepareSymbolRelocation(Symbol *sym, const InputSection *isec,
 
 void Writer::scanRelocations() {
   TimeTraceScope timeScope("Scan relocations");
-  for (ConcatInputSection *isec : inputSections) {
+
+  // This can't use a for-each loop: It calls treatUndefinedSymbol(), which can
+  // add to inputSections, which invalidates inputSections's iterators.
+  for (size_t i = 0; i < inputSections.size(); ++i) {
+    ConcatInputSection *isec = inputSections[i];
+
     if (isec->shouldOmitFromOutput())
       continue;
 
@@ -1029,6 +1034,7 @@ void Writer::assignAddresses(OutputSegment *seg) {
     osec->addr = addr;
     osec->fileOff = isZeroFill(osec->flags) ? 0 : fileOff;
     osec->finalize();
+    osec->assignAddressesToStartEndSymbols();
 
     addr += osec->getSize();
     fileOff += osec->getFileSize();