lld-link: Demangle symbols from archives in diagnostics

[thakis]

Summary

Also add test coverage for thin archives (which are the only way I could
come up with to test at least some of the diagnostic changes).

[ruiu]

LGTM

lld/COFF/SymbolTable.h

86

nit: & -> &

[thakis]

lld/COFF/SymbolTable.h

86

Ran git diff master | clang/tools/clang-format/clang-format-diff.py -p1 and fixed most things it printed (mostly this, in .h and .cc), thanks!

lld/COFF/Driver.h

 class LinkerDriver {
 public:
   void link(llvm::ArrayRef<const char *> args);
 
   // Used by the resolver to parse .drectve section contents.
   void parseDirectives(InputFile *file);
 
   // Used by ArchiveFile to enqueue members.
-  void enqueueArchiveMember(const Archive::Child &c, StringRef symName,
+  void enqueueArchiveMember(const Archive::Child &c, const Archive::Symbol &sym,
                             StringRef parentName);
 
   MemoryBufferRef takeBuffer(std::unique_ptr<MemoryBuffer> mb);
 
   void enqueuePath(StringRef path, bool wholeArchive);
 
 private:
   std::unique_ptr<llvm::TarWriter> tar; // for /linkrepro

lld/COFF/Driver.cpp

void LinkerDriver::addArchiveBuffer(MemoryBufferRef mb, StringRef symName,
   }
 
   obj->parentName = parentName;
   symtab->addFile(obj);
   log("Loaded " + toString(obj) + " for " + symName);
 }
 
 void LinkerDriver::enqueueArchiveMember(const Archive::Child &c,
-                                        StringRef symName,
+                                        const Archive::Symbol &sym,
                                         StringRef parentName) {
 
   auto reportBufferError = [=](Error &&e,
                               StringRef childName) {
     fatal("could not get the buffer for the member defining symbol " +
-          symName + ": " + parentName + "(" + childName + "): " +
+          toString(sym) + ": " + parentName + "(" + childName + "): " +
           toString(std::move(e)));
   };
 
   if (!c.getParent()->isThin()) {
     uint64_t offsetInArchive = c.getChildOffset();
     Expected<MemoryBufferRef> mbOrErr = c.getMemoryBufferRef();
     if (!mbOrErr)
       reportBufferError(mbOrErr.takeError(), check(c.getFullName()));
     MemoryBufferRef mb = mbOrErr.get();
     enqueueTask([=]() {
-      driver->addArchiveBuffer(mb, symName, parentName, offsetInArchive);
+      driver->addArchiveBuffer(mb, toString(sym), parentName, offsetInArchive);
     });
     return;
   }
 
   std::string childName = CHECK(
       c.getFullName(),
       "could not get the filename for the member defining symbol " +
-      symName);
+      toString(sym));
   auto future = std::make_shared<std::future<MBErrPair>>(
       createFutureForFile(childName));
   enqueueTask([=]() {
     auto mbOrErr = future->get();
     if (mbOrErr.second)
       reportBufferError(errorCodeToError(mbOrErr.second), childName);
-    driver->addArchiveBuffer(takeBuffer(std::move(mbOrErr.first)), symName,
-                             parentName, /* OffsetInArchive */ 0);
+    driver->addArchiveBuffer(takeBuffer(std::move(mbOrErr.first)),
+                             toString(sym), parentName, /*OffsetInArchive=*/0);
   });
 }
 
 static bool isDecorated(StringRef sym) {
   return sym.startswith("@") || sym.contains("@@") || sym.startswith("?") ||
          (!config->mingw && sym.contains('@'));
 }
 

lld/COFF/InputFiles.h

 public:
   explicit ArchiveFile(MemoryBufferRef m);
   static bool classof(const InputFile *f) { return f->kind() == ArchiveKind; }
   void parse() override;
 
   // Enqueues an archive member load for the given symbol. If we've already
   // enqueued a load for the same archive member, this function does nothing,
   // which ensures that we don't load the same member more than once.
-  void addMember(const Archive::Symbol *sym);
+  void addMember(const Archive::Symbol &sym);
 
 private:
   std::unique_ptr<Archive> file;
   llvm::DenseSet<uint64_t> seen;
 };
 
 // .obj or .o file. This may be a member of an archive file.
 class ObjFile : public InputFile {

lld/COFF/InputFiles.cpp

void ArchiveFile::parse() {
   file = CHECK(Archive::create(mb), this);
 
   // Read the symbol table to construct Lazy objects.
   for (const Archive::Symbol &sym : file->symbols())
     symtab->addLazy(this, sym);
 }
 
 // Returns a buffer pointing to a member file containing a given symbol.
-void ArchiveFile::addMember(const Archive::Symbol *sym) {
-  const Archive::Child &c =
-      CHECK(sym->getMember(),
-            "could not get the member for symbol " + sym->getName());
+void ArchiveFile::addMember(const Archive::Symbol &sym) {
+  const Archive::Child &c = CHECK(
+      sym.getMember(), "could not get the member for symbol " + toString(sym));
 
   // Return an empty buffer if we have already returned the same buffer.
   if (!seen.insert(c.getChildOffset()).second)
     return;
 
-  driver->enqueueArchiveMember(c, sym->getName(), getName());
+  driver->enqueueArchiveMember(c, sym, getName());
 }
 
 std::vector<MemoryBufferRef> getArchiveMembers(Archive *file) {
   std::vector<MemoryBufferRef> v;
   Error err = Error::success();
   for (const ErrorOr<Archive::Child> &cOrErr : file->children(err)) {
     Archive::Child c =
         CHECK(cOrErr,

lld/COFF/SymbolTable.h

public:
 
   // Creates an Undefined symbol for a given name.
   Symbol *addUndefined(StringRef name);
 
   Symbol *addSynthetic(StringRef n, Chunk *c);
   Symbol *addAbsolute(StringRef n, uint64_t va);
 
   Symbol *addUndefined(StringRef name, InputFile *f, bool isWeakAlias);
-  void addLazy(ArchiveFile *f, const Archive::Symbol sym);
+  void addLazy(ArchiveFile *f, const Archive::Symbol& sym);
   Symbol *addAbsolute(StringRef n, COFFSymbolRef s);
   Symbol *addRegular(InputFile *f, StringRef n,
                      const llvm::object::coff_symbol_generic *s = nullptr,
                      SectionChunk *c = nullptr);
   std::pair<DefinedRegular *, bool>
   addComdat(InputFile *f, StringRef n,
             const llvm::object::coff_symbol_generic *s = nullptr);
   Symbol *addCommon(InputFile *f, StringRef n, uint64_t size,

lld/COFF/SymbolTable.cpp

for (auto &i : symMap) {
     // symbol we could load from file, make sure to load that.
     Lazy *l = dyn_cast_or_null<Lazy>(find(("__imp_" + name).str()));
     if (!l || l->pendingArchiveLoad)
       continue;
 
     log("Loading lazy " + l->getName() + " from " + l->file->getName() +
         " for automatic import");
     l->pendingArchiveLoad = true;
-    l->file->addMember(&l->sym);
+    l->file->addMember(l->sym);
   }
 }
 
 bool SymbolTable::handleMinGWAutomaticImport(Symbol *sym, StringRef name) {
   if (name.startswith("__imp_"))
     return false;
   Defined *imp = dyn_cast_or_null<Defined>(find(("__imp_" + name).str()));
   if (!imp)
Symbol *SymbolTable::addUndefined(StringRef name, InputFile *f,
   std::tie(s, wasInserted) = insert(name, f);
   if (wasInserted || (isa<Lazy>(s) && isWeakAlias)) {
     replaceSymbol<Undefined>(s, name);
     return s;
   }
   if (auto *l = dyn_cast<Lazy>(s)) {
     if (!s->pendingArchiveLoad) {
       s->pendingArchiveLoad = true;
-      l->file->addMember(&l->sym);
+      l->file->addMember(l->sym);
     }
   }
   return s;
 }
 
-void SymbolTable::addLazy(ArchiveFile *f, const Archive::Symbol sym) {
+void SymbolTable::addLazy(ArchiveFile *f, const Archive::Symbol& sym) {
   StringRef name = sym.getName();
   Symbol *s;
   bool wasInserted;
   std::tie(s, wasInserted) = insert(name);
   if (wasInserted) {
     replaceSymbol<Lazy>(s, f, sym);
     return;
   }
   auto *u = dyn_cast<Undefined>(s);
   if (!u || u->weakAlias || s->pendingArchiveLoad)
     return;
   s->pendingArchiveLoad = true;
-  f->addMember(&sym);
+  f->addMember(sym);
 }
 
 void SymbolTable::reportDuplicate(Symbol *existing, InputFile *newFile) {
   std::string msg = "duplicate symbol: " + toString(*existing) + " in " +
                     toString(existing->getFile()) + " and in " +
                     toString(newFile);
 
   if (config->forceMultiple)

lld/COFF/Symbols.h

static_assert(alignof(T) <= alignof(SymbolUnion),
                 "SymbolUnion not aligned enough");
   assert(static_cast<Symbol *>(static_cast<T *>(nullptr)) == nullptr &&
          "Not a Symbol");
   new (s) T(std::forward<ArgT>(arg)...);
 }
 } // namespace coff
 
 std::string toString(coff::Symbol &b);
+std::string toString(const coff::Archive::Symbol &b);
 } // namespace lld
 
 #endif

lld/COFF/Symbols.cpp

 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 using namespace llvm::object;
 
 using namespace lld::coff;
 
+namespace lld {
+
 static_assert(sizeof(SymbolUnion) <= 48,
               "symbols should be optimized for memory usage");
 
 // Returns a symbol name for an error message.
-std::string lld::toString(coff::Symbol &b) {
+static std::string demangle(StringRef symName) {
   if (config->demangle)
-    if (Optional<std::string> s = lld::demangleMSVC(b.getName()))
+    if (Optional<std::string> s = demangleMSVC(symName))
       return *s;
-  return b.getName();
+  return symName;
 }
+std::string toString(coff::Symbol &b) { return demangle(b.getName()); }
+std::string toString(const Archive::Symbol &b) { return demangle(b.getName()); }
 
-namespace lld {
 namespace coff {
 
 StringRef Symbol::getName() {
   // COFF symbol names are read lazily for a performance reason.
   // Non-external symbol names are never used by the linker except for logging
   // or debugging. Their internal references are resolved not by name but by
   // symbol index. And because they are not external, no one can refer them by
   // name. Object files contain lots of non-external symbols, and creating

lld/test/COFF/Inputs/mangled-symbol.s

+  .text
+
+  .def "?f@@YAHXZ"
+    .scl 2
+    .type 32
+  .endef
+  .global "?f@@YAHXZ"
+"?f@@YAHXZ":
+  retq $0

lld/test/COFF/thin-archive.s

+# REQUIRES: x86
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-windows-msvc -o %t.main.obj %s
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-windows-msvc -o %t.lib.obj \
+# RUN:     %S/Inputs/mangled-symbol.s
+# RUN: lld-link /lib /out:%t.lib %t.lib.obj
+# RUN: lld-link /lib /llvmlibthin /out:%t_thin.lib %t.lib.obj
+
+# RUN: lld-link /entry:main %t.main.obj %t.lib /out:%t.exe 2>&1 | \
+# RUN:     FileCheck --allow-empty %s
+# RUN: lld-link /entry:main %t.main.obj %t_thin.lib /out:%t.exe 2>&1 | \
+# RUN:     FileCheck --allow-empty %s
+
+# RUN: rm %t.lib.obj
+# RUN: lld-link /entry:main %t.main.obj %t.lib /out:%t.exe 2>&1 | \
+# RUN:     FileCheck --allow-empty %s
+# RUN: not lld-link /entry:main %t.main.obj %t_thin.lib /out:%t.exe 2>&1 | \
+# RUN:     FileCheck --check-prefix=NOOBJ %s
+# RUN: not lld-link /entry:main %t.main.obj %t_thin.lib /out:%t.exe \
+# RUN:     /demangle:no 2>&1 | FileCheck --check-prefix=NOOBJNODEMANGLE %s
+
+# CHECK-NOT: error: could not get the buffer for the member defining
+# NOOBJ: error: could not get the buffer for the member defining symbol int __cdecl f(void): {{.*}}.lib({{.*}}.lib.obj):
+# NOOBJNODEMANGLE: error: could not get the buffer for the member defining symbol ?f@@YAHXZ: {{.*}}.lib({{.*}}.lib.obj):
+
+  .text
+
+  .def main
+    .scl 2
+    .type 32
+  .endef
+  .global main
+main:
+  call "?f@@YAHXZ"
+  retq $0