[llvm-dlltool] Implement the --identify option (#127465)

This option prints the name of the DLL that gets imported, when linking
against an import library.

This is implemented using the same strategy as GNU dlltool does; looking
for the contents of .idata$6 or .idata$7 chunks. The right section name
to check for is chosen by identifying whether the library is GNU or LLVM
style. In the case of GNU import libraries, the DLL name is in an
.idata$7 chunk. However there are also other chunks with that section
name (for entries for the IAT or ILT); identify these by looking for
whether a chunk contains relocations.

Alternatively, one could also just look for .idata$2 chunks, look for
relocations at the right offset, and locate data at the symbol that the
relocation points at (which may be in the same or in another object
file).

Author: mstorsjo

llvm/lib/ToolDrivers/llvm-dlltool/DlltoolDriver.cpp

@@ -12,6 +12,7 @@
 
 #include "llvm/ToolDrivers/llvm-dlltool/DlltoolDriver.h"
 #include "llvm/ADT/StringSwitch.h"
+#include "llvm/Object/Archive.h"
 #include "llvm/Object/COFF.h"
 #include "llvm/Object/COFFImportFile.h"
 #include "llvm/Object/COFFModuleDefinition.h"
@@ -158,6 +159,143 @@ bool parseModuleDefinition(StringRef DefFileName, MachineTypes Machine,
   return true;
 }
 
+int printError(llvm::Error E, Twine File) {
+  if (!E)
+    return 0;
+  handleAllErrors(std::move(E), [&](const llvm::ErrorInfoBase &EIB) {
+    llvm::errs() << "error opening " << File << ": " << EIB.message() << "\n";
+  });
+  return 1;
+}
+
+template <typename Callable>
+int forEachCoff(object::Archive &Archive, StringRef Name, Callable Callback) {
+  Error Err = Error::success();
+  for (auto &C : Archive.children(Err)) {
+    Expected<StringRef> NameOrErr = C.getName();
+    if (!NameOrErr)
+      return printError(NameOrErr.takeError(), Name);
+    StringRef Name = *NameOrErr;
+
+    Expected<MemoryBufferRef> ChildMB = C.getMemoryBufferRef();
+    if (!ChildMB)
+      return printError(ChildMB.takeError(), Name);
+
+    if (identify_magic(ChildMB->getBuffer()) == file_magic::coff_object) {
+      auto Obj = object::COFFObjectFile::create(*ChildMB);
+      if (!Obj)
+        return printError(Obj.takeError(), Name);
+      if (!Callback(*Obj->get(), Name))
+        return 1;
+    }
+  }
+  if (Err)
+    return printError(std::move(Err), Name);
+  return 0;
+}
+
+// To find the named of the imported DLL from an import library, we can either
+// inspect the object files that form the import table entries, or we could
+// just look at the archive member names, for MSVC style import libraries.
+// Looking at the archive member names doesn't work for GNU style import
+// libraries though, while inspecting the import table entries works for
+// both. (MSVC style import libraries contain a couple regular object files
+// for the header/trailers.)
+//
+// This implementation does the same as GNU dlltool does; look at the
+// content of ".idata$7" sections, or for MSVC style libraries, look
+// at ".idata$6" sections.
+//
+// For GNU style import libraries, there are also other data chunks in sections
+// named ".idata$7" (entries to the IAT or ILT); these are distinguished
+// by seeing that they contain relocations. (They also look like an empty
+// string when looking for null termination.)
+//
+// Alternatively, we could do things differently - look for any .idata$2
+// section; this would be import directory entries. At offset 0xc in them
+// there is the RVA of the import DLL name; look for a relocation at this
+// spot and locate the symbol that it points at. That symbol may either
+// be within the same object file (in the case of MSVC style import libraries)
+// or another object file (in the case of GNU import libraries).
+bool identifyImportName(const COFFObjectFile &Obj, StringRef ObjName,
+                        std::vector<StringRef> &Names, bool IsMsStyleImplib) {
+  StringRef TargetName = IsMsStyleImplib ? ".idata$6" : ".idata$7";
+  for (const auto &S : Obj.sections()) {
+    Expected<StringRef> NameOrErr = S.getName();
+    if (!NameOrErr) {
+      printError(NameOrErr.takeError(), ObjName);
+      return false;
+    }
+    StringRef Name = *NameOrErr;
+    if (Name != TargetName)
+      continue;
+
+    // GNU import libraries contain .idata$7 section in the per function
+    // objects too, but they contain relocations.
+    if (!IsMsStyleImplib && !S.relocations().empty())
+      continue;
+
+    Expected<StringRef> ContentsOrErr = S.getContents();
+    if (!ContentsOrErr) {
+      printError(ContentsOrErr.takeError(), ObjName);
+      return false;
+    }
+    StringRef Contents = *ContentsOrErr;
+    Contents = Contents.substr(0, Contents.find('\0'));
+    if (Contents.empty())
+      continue;
+    Names.push_back(Contents);
+    return true;
+  }
+  return true;
+}
+
+int doIdentify(StringRef File, bool IdentifyStrict) {
+  ErrorOr<std::unique_ptr<MemoryBuffer>> MaybeBuf = MemoryBuffer::getFile(
+      File, /*IsText=*/false, /*RequiredNullTerminator=*/false);
+  if (!MaybeBuf)
+    return printError(errorCodeToError(MaybeBuf.getError()), File);
+  if (identify_magic(MaybeBuf.get()->getBuffer()) != file_magic::archive) {
+    llvm::errs() << File << " is not a library\n";
+    return 1;
+  }
+
+  std::unique_ptr<MemoryBuffer> B = std::move(MaybeBuf.get());
+  Error Err = Error::success();
+  object::Archive Archive(B->getMemBufferRef(), Err);
+  if (Err)
+    return printError(std::move(Err), B->getBufferIdentifier());
+
+  bool IsMsStyleImplib = false;
+  for (const auto &S : Archive.symbols()) {
+    if (S.getName() == "__NULL_IMPORT_DESCRIPTOR") {
+      IsMsStyleImplib = true;
+      break;
+    }
+  }
+  std::vector<StringRef> Names;
+  if (forEachCoff(Archive, B->getBufferIdentifier(),
+                  [&](const COFFObjectFile &Obj, StringRef ObjName) -> bool {
+                    return identifyImportName(Obj, ObjName, Names,
+                                              IsMsStyleImplib);
+                  }))
+    return 1;
+
+  if (Names.empty()) {
+    llvm::errs() << "No DLL import name found in " << File << "\n";
+    return 1;
+  }
+  if (Names.size() > 1 && IdentifyStrict) {
+    llvm::errs() << File << "contains imports for two or more DLLs\n";
+    return 1;
+  }
+
+  for (StringRef S : Names)
+    llvm::outs() << S << "\n";
+
+  return 0;
+}
+
 } // namespace
 
 int llvm::dlltoolDriverMain(llvm::ArrayRef<const char *> ArgsArr) {
@@ -173,7 +311,8 @@ int llvm::dlltoolDriverMain(llvm::ArrayRef<const char *> ArgsArr) {
 
   // Handle when no input or output is specified
   if (Args.hasArgNoClaim(OPT_INPUT) ||
-      (!Args.hasArgNoClaim(OPT_d) && !Args.hasArgNoClaim(OPT_l))) {
+      (!Args.hasArgNoClaim(OPT_d) && !Args.hasArgNoClaim(OPT_l) &&
+       !Args.hasArgNoClaim(OPT_I))) {
     Table.printHelp(outs(), "llvm-dlltool [options] file...", "llvm-dlltool",
                     false);
     llvm::outs()
@@ -185,6 +324,11 @@ int llvm::dlltoolDriverMain(llvm::ArrayRef<const char *> ArgsArr) {
     llvm::errs() << "ignoring unknown argument: " << Arg->getAsString(Args)
                  << "\n";
 
+  if (Args.hasArg(OPT_I)) {
+    return doIdentify(Args.getLastArg(OPT_I)->getValue(),
+                      Args.hasArg(OPT_identify_strict));
+  }
+
   if (!Args.hasArg(OPT_d)) {
     llvm::errs() << "no definition file specified\n";
     return 1;

llvm/lib/ToolDrivers/llvm-dlltool/Options.td

@@ -21,6 +21,11 @@ def k_alias: Flag<["--"], "kill-at">, Alias<k>;
 def no_leading_underscore: Flag<["--"], "no-leading-underscore">,
     HelpText<"Don't add leading underscores on symbols">;
 
+def I: JoinedOrSeparate<["-"], "I">, HelpText<"Identify DLL name from import library">;
+def I_long : JoinedOrSeparate<["--"], "identify">, Alias<I>;
+
+def identify_strict : Flag<["--"], "identify-strict">, HelpText<"Error out if the --identify option detects more than one DLL">;
+
 //==============================================================================
 // The flags below do nothing. They are defined only for dlltool compatibility.
 //==============================================================================

llvm/test/tools/llvm-dlltool/Inputs/gnu_foo_lib_h.yaml

@@ -0,0 +1,133 @@
+--- !COFF
+header:
+  Machine:         IMAGE_FILE_MACHINE_I386
+  Characteristics: [ IMAGE_FILE_LINE_NUMS_STRIPPED, IMAGE_FILE_32BIT_MACHINE ]
+sections:
+  - Name:            .text
+    Characteristics: [ IMAGE_SCN_CNT_CODE, IMAGE_SCN_MEM_EXECUTE, IMAGE_SCN_MEM_READ ]
+    Alignment:       4
+    SectionData:     ''
+  - Name:            .data
+    Characteristics: [ IMAGE_SCN_CNT_INITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
+    Alignment:       4
+    SectionData:     ''
+  - Name:            .bss
+    Characteristics: [ IMAGE_SCN_CNT_UNINITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
+    Alignment:       4
+    SectionData:     ''
+  - Name:            '.idata$2'
+    Characteristics: [ IMAGE_SCN_CNT_INITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
+    Alignment:       4
+    SectionData:     '0000000000000000000000000000000000000000'
+    SizeOfRawData:   20
+    Relocations:
+      - VirtualAddress:  0
+        SymbolName:      '.idata$4'
+        Type:            IMAGE_REL_I386_DIR32NB
+      - VirtualAddress:  12
+        SymbolName:      __foo_lib_iname
+        Type:            IMAGE_REL_I386_DIR32NB
+      - VirtualAddress:  16
+        SymbolName:      '.idata$5'
+        Type:            IMAGE_REL_I386_DIR32NB
+  - Name:            '.idata$5'
+    Characteristics: [ IMAGE_SCN_CNT_INITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
+    Alignment:       4
+    SectionData:     ''
+  - Name:            '.idata$4'
+    Characteristics: [ IMAGE_SCN_CNT_INITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
+    Alignment:       4
+    SectionData:     ''
+symbols:
+  - Name:            .file
+    Value:           0
+    SectionNumber:   -2
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_FILE
+    File:            fake
+  - Name:            hname
+    Value:           0
+    SectionNumber:   6
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+  - Name:            fthunk
+    Value:           0
+    SectionNumber:   5
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+  - Name:            .text
+    Value:           0
+    SectionNumber:   1
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+    SectionDefinition:
+      Length:          0
+      NumberOfRelocations: 0
+      NumberOfLinenumbers: 0
+      CheckSum:        0
+      Number:          0
+  - Name:            .data
+    Value:           0
+    SectionNumber:   2
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+    SectionDefinition:
+      Length:          0
+      NumberOfRelocations: 0
+      NumberOfLinenumbers: 0
+      CheckSum:        0
+      Number:          0
+  - Name:            .bss
+    Value:           0
+    SectionNumber:   3
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+    SectionDefinition:
+      Length:          0
+      NumberOfRelocations: 0
+      NumberOfLinenumbers: 0
+      CheckSum:        0
+      Number:          0
+  - Name:            '.idata$2'
+    Value:           0
+    SectionNumber:   4
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+    SectionDefinition:
+      Length:          20
+      NumberOfRelocations: 3
+      NumberOfLinenumbers: 0
+      CheckSum:        0
+      Number:          0
+  - Name:            '.idata$4'
+    Value:           0
+    SectionNumber:   6
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+  - Name:            '.idata$5'
+    Value:           0
+    SectionNumber:   5
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+  - Name:            __head_foo_lib
+    Value:           0
+    SectionNumber:   4
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_EXTERNAL
+  - Name:            __foo_lib_iname
+    Value:           0
+    SectionNumber:   0
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_EXTERNAL
+...