[llvm-ar] Fix support for archives with members larger than 4GB

[gbreynoo]

Summary

llvm-ar outputs a strange error message when handling archives with members larger than 4GB due to not checking file size when passing the value as an unsigned 32 bit integer. This overflow issue caused malformed archives to be created.:

https://bugs.llvm.org/show_bug.cgi?id=38058

This change allows for members above 4GB and will error in a case that is over the formats size limit, a 10 digit decimal integer.

[MaskRay]

include/llvm/Object/Archive.h

224

I am curious why you want to handle a file whose size is within [4294967296,9999999999] (4G is a bit unusual as a binary. But you don't allow it to be larger..).

[gbreynoo]

I have not included a test for this change due to how large the test files would need to be.

[gbreynoo]

include/llvm/Object/Archive.h

224

In the past we have had a user that required support for members larger 4gb, and when experimenting with gnu-ar on my Ubuntu machine, it supports members over that size.

The maximum size value 9999999999 is a limit of the file format itself. The file size in bytes is stored as a 10 digit decimal integer, meaning MaxMemberSize is the largest member size the format supports.

[rupprecht]

I tried patching this, and it looks like you have \r\n endings that conflict w/ the checked in \n. Did you use --config core.autocrlf=false on your initial clone? (http://llvm.org/docs/GettingStarted.html#getting-started-quickly-a-summary)

[rupprecht]

The patch tests out fine when piping through dos2unix (there's probably an equivalent on Windows), so LGTM if you can strip \r before submitting

[gbreynoo]

Thanks rupprecht, I'll fix my clone before committing.

include/llvm/Object/Archive.h

public:
   // ArchiveMemberHeader() = default;
 
   /// Get the name without looking up long names.
   Expected<StringRef> getRawName() const;
 
   /// Get the name looking up long names.
   Expected<StringRef> getName(uint64_t Size) const;
 
-  /// Members are not larger than 4GB.
-  Expected<uint32_t> getSize() const;
+  Expected<uint64_t> getSize() const;
 
   Expected<sys::fs::perms> getAccessMode() const;
   Expected<sys::TimePoint<std::chrono::seconds>> getLastModified() const;
 
   StringRef getRawLastModified() const {
     return StringRef(ArMemHdr->LastModified,
                      sizeof(ArMemHdr->LastModified)).rtrim(' ');
   }
symbol_iterator& operator++() {  // Preincrement
       symbol = symbol.getNext();
       return *this;
     }
   };
 
   Archive(MemoryBufferRef Source, Error &Err);
   static Expected<std::unique_ptr<Archive>> create(MemoryBufferRef Source);
 
+  /// Size field is 10 decimal digits long
+  static const uint64_t MaxMemberSize = 9999999999;
+
   enum Kind {
     K_GNU,
     K_GNU64,
     K_BSD,
     K_DARWIN,
     K_DARWIN64,
     K_COFF
   };

lib/Object/Archive.cpp

Expected<StringRef> ArchiveMemberHeader::getName(uint64_t Size) const {
   // It is not a long name so trim the blanks at the end of the name.
   if (Name[Name.size() - 1] != '/')
     return Name.rtrim(' ');
 
   // It's a simple name.
   return Name.drop_back(1);
 }
 
-Expected<uint32_t> ArchiveMemberHeader::getSize() const {
-  uint32_t Ret;
+Expected<uint64_t> ArchiveMemberHeader::getSize() const {
+  uint64_t Ret;
   if (StringRef(ArMemHdr->Size,
                 sizeof(ArMemHdr->Size)).rtrim(" ").getAsInteger(10, Ret)) {
     std::string Buf;
     raw_string_ostream OS(Buf);
     OS.write_escaped(StringRef(ArMemHdr->Size,
                                sizeof(ArMemHdr->Size)).rtrim(" "));
     OS.flush();
     uint64_t Offset = reinterpret_cast<const char *>(ArMemHdr) -

lib/Object/ArchiveWriter.cpp

 //===----------------------------------------------------------------------===//
 
 #include "llvm/Object/ArchiveWriter.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/BinaryFormat/Magic.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/Object/Archive.h"
+#include "llvm/Object/Error.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Object/SymbolicFile.h"
 #include "llvm/Support/EndianStream.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/ToolOutputFile.h"

 template <class T>
 static void print(raw_ostream &Out, object::Archive::Kind Kind, T Val) {
   support::endian::write(Out, Val,
                          isBSDLike(Kind) ? support::little : support::big);
 }
 
 static void printRestOfMemberHeader(
     raw_ostream &Out, const sys::TimePoint<std::chrono::seconds> &ModTime,
-    unsigned UID, unsigned GID, unsigned Perms, unsigned Size) {
+    unsigned UID, unsigned GID, unsigned Perms, uint64_t Size) {
   printWithSpacePadding(Out, sys::toTimeT(ModTime), 12);
 
   // The format has only 6 chars for uid and gid. Truncate if the provided
   // values don't fit.
   printWithSpacePadding(Out, UID % 1000000, 6);
   printWithSpacePadding(Out, GID % 1000000, 6);
 
   printWithSpacePadding(Out, format("%o", Perms), 8);
   printWithSpacePadding(Out, Size, 10);
   Out << "`\n";
 }
 
 static void
 printGNUSmallMemberHeader(raw_ostream &Out, StringRef Name,
                           const sys::TimePoint<std::chrono::seconds> &ModTime,
                           unsigned UID, unsigned GID, unsigned Perms,
-                          unsigned Size) {
+                          uint64_t Size) {
   printWithSpacePadding(Out, Twine(Name) + "/", 16);
   printRestOfMemberHeader(Out, ModTime, UID, GID, Perms, Size);
 }
 
 static void
 printBSDMemberHeader(raw_ostream &Out, uint64_t Pos, StringRef Name,
                      const sys::TimePoint<std::chrono::seconds> &ModTime,
-                     unsigned UID, unsigned GID, unsigned Perms,
-                     unsigned Size) {
+                     unsigned UID, unsigned GID, unsigned Perms, uint64_t Size) {
   uint64_t PosAfterHeader = Pos + 60 + Name.size();
   // Pad so that even 64 bit object files are aligned.
   unsigned Pad = OffsetToAlignment(PosAfterHeader, 8);
   unsigned NameWithPadding = Name.size() + Pad;
   printWithSpacePadding(Out, Twine("#1/") + Twine(NameWithPadding), 16);
   printRestOfMemberHeader(Out, ModTime, UID, GID, Perms,
                           NameWithPadding + Size);
   Out << Name;
static bool is64BitKind(object::Archive::Kind Kind) {
   }
   llvm_unreachable("not supported for writting");
 }
 
 static void
 printMemberHeader(raw_ostream &Out, uint64_t Pos, raw_ostream &StringTable,
                   StringMap<uint64_t> &MemberNames, object::Archive::Kind Kind,
                   bool Thin, const NewArchiveMember &M,
-                  sys::TimePoint<std::chrono::seconds> ModTime, unsigned Size) {
+                  sys::TimePoint<std::chrono::seconds> ModTime, uint64_t Size) {
   if (isBSDLike(Kind))
     return printBSDMemberHeader(Out, Pos, M.MemberName, ModTime, M.UID, M.GID,
                                 M.Perms, Size);
   if (!useStringTable(Thin, M.MemberName))
     return printGNUSmallMemberHeader(Out, M.MemberName, ModTime, M.UID, M.GID,
                                      M.Perms, Size);
   Out << '/';
   uint64_t NamePos;
for (const NewArchiveMember &M : NewMembers) {
     StringRef Padding = StringRef(PaddingData, MemberPadding + TailPadding);
 
     sys::TimePoint<std::chrono::seconds> ModTime;
     if (UniqueTimestamps)
       // Increment timestamp for each file of a given name.
       ModTime = sys::toTimePoint(FilenameCount[M.MemberName]++);
     else
       ModTime = M.ModTime;
+
+    uint64_t Size = Buf.getBufferSize() + MemberPadding;
+    if (Size > object::Archive::MaxMemberSize) {
+      std::string StringMsg =
+          "File " + M.MemberName.str() + " exceeds size limit";
+      return make_error<object::GenericBinaryError>(
+          std::move(StringMsg), object::object_error::parse_failed);
+    }
+
     printMemberHeader(Out, Pos, StringTable, MemberNames, Kind, Thin, M,
-                      ModTime, Buf.getBufferSize() + MemberPadding);
+                      ModTime, Size);
     Out.flush();
 
     Expected<std::vector<unsigned>> Symbols =
         getSymbols(Buf, SymNames, HasObject);
     if (auto E = Symbols.takeError())
       return std::move(E);
 
     Pos += Header.size() + Data.size() + Padding.size();