llvm-lto2: Add a dump-symtab subcommand.

[pcc]

Summary

This allows us to test the symbol table APIs for LTO input files.

Depends on D31410

[tejohnson]

llvm/tools/llvm-lto2/llvm-lto2.cpp

297

What if not COFF? Should this line be suppressed?

318

Why 'M'? Maybe 'O' for Omitted?

[pcc]

• Address review comments

llvm/tools/llvm-lto2/llvm-lto2.cpp

297

It will just print the empty string (same for the fallback below). Not a big deal for now, but we can suppress it once we add the target triple to the irsymtab and the LTO API.

318

Yes, I like 'O' better, done.

[tejohnson]

LGTM with one suggestion below.

llvm/tools/llvm-lto2/llvm-lto2.cpp

297

Can you add "(COFF only)" or something to the output string? I think it would be good to distinguish between COFF with no linker opts vs linker opts not available for this format.

llvm/test/LTO/Resolution/X86/symtab.ll

+; RUN: llvm-as -o %t %s
+; RUN: llvm-lto2 dump-symtab %t | FileCheck %s
+
+target triple = "i686-pc-windows-msvc18.0.0"
+target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
+
+; CHECK: source filename: src.c
+source_filename = "src.c"
+
+; CHECK: linker opts: /include:foo
+!0 = !{i32 6, !"Linker Options", !{!{!"/include:foo"}}}
+!llvm.module.flags = !{ !0 }
+
+; CHECK: H------ _g1
+@g1 = hidden global i32 0
+
+; CHECK: P------ _g2
+@g2 = protected global i32 0
+
+; CHECK: D------ _g3
+@g3 = global i32 0
+
+; CHECK: DU----- _g4
+@g4 = external global i32
+
+; CHECK: D--W--- _g5
+@g5 = weak global i32 0
+
+; CHECK: D--W-M- _g6
+@g6 = linkonce_odr unnamed_addr global i32 0
+
+; CHECK: D-----T _g7
+@g7 = thread_local global i32 0
+
+; CHECK: D-C---- _g8
+; CHECK-NEXT: size 4 align 8
+@g8 = common global i32 0, align 8
+
+; CHECK: D------ _g9
+; CHECK-NEXT: comdat g9
+$g9 = comdat any
+@g9 = global i32 0, comdat
+
+; CHECK: D--WI-- _g10
+; CHECK-NEXT: comdat g9
+; CHECK-NEXT: fallback _g9
+@g10 = weak alias i32, i32* @g9

llvm/tools/llvm-lto2/llvm-lto2.cpp

 template <typename T> static T check(ErrorOr<T> E, std::string Msg) {
   if (E)
     return std::move(*E);
   check(E.getError(), Msg);
   return T();
 }
 
 static int usage() {
-  errs() << "Available subcommands: run\n";
+  errs() << "Available subcommands: dump-symtab run\n";
   return 1;
 }
 
 static int run(int argc, char **argv) {
   cl::ParseCommandLineOptions(argc, argv, "Resolution-based LTO test harness");
 
   // FIXME: Workaround PR30396 which means that a symbol can appear
   // more than once if it is defined in module-level assembly and
static int run(int argc, char **argv) {
   NativeObjectCache Cache;
   if (!CacheDir.empty())
     Cache = check(localCache(CacheDir, AddBuffer), "failed to create cache");
 
   check(Lto.run(AddStream, Cache), "LTO::run failed");
   return 0;
 }
 
+static int dumpSymtab(int argc, char **argv) {
+  for (StringRef F : make_range(argv + 1, argv + argc)) {
+    std::unique_ptr<MemoryBuffer> MB = check(MemoryBuffer::getFile(F), F);
+    std::unique_ptr<InputFile> Input =
+        check(InputFile::create(MB->getMemBufferRef()), F);
+
+    outs() << "source filename: " << Input->getSourceFileName() << '\n';
+    outs() << "linker opts: " << Input->getCOFFLinkerOpts() << '\n';
+
+    std::vector<StringRef> ComdatTable = Input->getComdatTable();
+    for (const InputFile::Symbol &Sym : Input->symbols()) {
+      switch (Sym.getVisibility()) {
+      case GlobalValue::HiddenVisibility:
+        outs() << 'H';
+        break;
+      case GlobalValue::ProtectedVisibility:
+        outs() << 'P';
+        break;
+      case GlobalValue::DefaultVisibility:
+        outs() << 'D';
+        break;
+      }
+
+      auto PrintBool = [&](char C, bool B) { outs() << (B ? C : '-'); };
+      PrintBool('U', Sym.isUndefined());
+      PrintBool('C', Sym.isCommon());
+      PrintBool('W', Sym.isWeak());
+      PrintBool('I', Sym.isIndirect());
+      PrintBool('M', Sym.canBeOmittedFromSymbolTable());
+      PrintBool('T', Sym.isTLS());
+      outs() << ' ' << Sym.getName() << '\n';
+
+      if (Sym.isCommon())
+        outs() << "        size " << Sym.getCommonSize() << " align "
+               << Sym.getCommonAlignment() << '\n';
+
+      int Comdat = Sym.getComdatIndex();
+      if (Comdat != -1)
+        outs() << "        comdat " << ComdatTable[Comdat] << '\n';
+
+      if (Sym.isWeak() && Sym.isIndirect())
+        outs() << "        fallback " << Sym.getCOFFWeakExternalFallback() << '\n';
+    }
+
+    outs() << '\n';
+  }
+
+  return 0;
+}
+
 int main(int argc, char **argv) {
   InitializeAllTargets();
   InitializeAllTargetMCs();
   InitializeAllAsmPrinters();
   InitializeAllAsmParsers();
 
   // FIXME: This should use llvm::cl subcommands, but it isn't currently
   // possible to pass an argument not associated with a subcommand to a
   // subcommand (e.g. -lto-use-new-pm).
   if (argc < 2)
     return usage();
 
   StringRef Subcommand = argv[1];
   // Ensure that argv[0] is correct after adjusting argv/argc.
   argv[1] = argv[0];
+  if (Subcommand == "dump-symtab")
+    return dumpSymtab(argc - 1, argv + 1);
   if (Subcommand == "run")
     return run(argc - 1, argv + 1);
   return usage();
 }