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

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.

Differential Revision: https://reviews.llvm.org/D65093

llvm-svn: 366813

Author: Owen Reynolds

llvm/include/llvm/Object/Archive.h

@@ -48,8 +48,7 @@ class ArchiveMemberHeader {
   /// 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;
@@ -221,6 +220,9 @@ class Archive : public Binary {
   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,

llvm/lib/Object/Archive.cpp

@@ -223,8 +223,8 @@ Expected<StringRef> ArchiveMemberHeader::getName(uint64_t Size) const {
   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;

llvm/lib/Object/ArchiveWriter.cpp

@@ -16,6 +16,7 @@
 #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"
@@ -147,7 +148,7 @@ static void print(raw_ostream &Out, object::Archive::Kind Kind, T Val) {
 
 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
@@ -164,16 +165,15 @@ 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);
@@ -208,7 +208,7 @@ 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);
@@ -474,8 +474,17 @@ computeMemberData(raw_ostream &StringTable, raw_ostream &SymNames,
       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 =