In openFileForRead, attempt to fetch the actual name of the file on disk -- including case -- so that clang can later warn about non-portable #include and #import directives.

Differential Revision: http://reviews.llvm.org/D19842
Corresponding clang patch: http://reviews.llvm.org/D19843

Re-commit after addressing issues with of generating too many warnings for Windows and asan test failures

Patch by Eric Niebler

llvm-svn: 272555

llvm/include/llvm/Support/FileSystem.h

@@ -604,6 +604,12 @@ std::error_code createTemporaryFile(const Twine &Prefix, StringRef Suffix,
 std::error_code createUniqueDirectory(const Twine &Prefix,
                                       SmallVectorImpl<char> &ResultPath);
 
+/// @brief Fetch a path to an open file, as specified by a file descriptor
+///
+/// @param FD File descriptor to a currently open file
+/// @param ResultPath The buffer into which to write the path
+std::error_code getPathFromOpenFD(int FD, SmallVectorImpl<char> &ResultPath);
+
 enum OpenFlags : unsigned {
   F_None = 0,
 
@@ -636,7 +642,8 @@ inline OpenFlags &operator|=(OpenFlags &A, OpenFlags B) {
 std::error_code openFileForWrite(const Twine &Name, int &ResultFD,
                                  OpenFlags Flags, unsigned Mode = 0666);
 
-std::error_code openFileForRead(const Twine &Name, int &ResultFD);
+std::error_code openFileForRead(const Twine &Name, int &ResultFD,
+                                SmallVectorImpl<char> *RealPath = nullptr);
 
 /// @brief Identify the type of a binary file based on how magical it is.
 file_magic identify_magic(StringRef magic);

llvm/lib/Support/Unix/Path.inc

@@ -25,6 +25,9 @@
 #if HAVE_FCNTL_H
 #include <fcntl.h>
 #endif
+#ifdef HAVE_UNISTD_H
+#include <unistd.h>
+#endif
 #ifdef HAVE_SYS_MMAN_H
 #include <sys/mman.h>
 #endif
@@ -47,6 +50,7 @@
 
 #ifdef __APPLE__
 #include <mach-o/dyld.h>
+#include <sys/attr.h>
 #endif
 
 // Both stdio.h and cstdio are included via different pathes and
@@ -544,13 +548,47 @@ std::error_code detail::directory_iterator_increment(detail::DirIterState &it) {
   return std::error_code();
 }
 
-std::error_code openFileForRead(const Twine &Name, int &ResultFD) {
+#if !defined(F_GETPATH)
+static bool hasProcSelfFD() {
+  // If we have a /proc filesystem mounted, we can quickly establish the
+  // real name of the file with readlink
+  static const bool Result = (::access("/proc/self/fd", R_OK) == 0);
+  return Result;
+}
+#endif
+
+std::error_code openFileForRead(const Twine &Name, int &ResultFD,
+                                SmallVectorImpl<char> *RealPath) {
   SmallString<128> Storage;
   StringRef P = Name.toNullTerminatedStringRef(Storage);
   while ((ResultFD = open(P.begin(), O_RDONLY)) < 0) {
     if (errno != EINTR)
       return std::error_code(errno, std::generic_category());
   }
+  // Attempt to get the real name of the file, if the user asked
+  if(!RealPath)
+    return std::error_code();
+  RealPath->clear();
+#if defined(F_GETPATH)
+  // When F_GETPATH is availble, it is the quickest way to get
+  // the real path name.
+  char Buffer[MAXPATHLEN];
+  if (::fcntl(ResultFD, F_GETPATH, Buffer) != -1)
+    RealPath->append(Buffer, Buffer + strlen(Buffer));
+#else
+  char Buffer[PATH_MAX];
+  if (hasProcSelfFD()) {
+    char ProcPath[64];
+    snprintf(ProcPath, sizeof(ProcPath), "/proc/self/fd/%d", ResultFD);
+    ssize_t CharCount = ::readlink(ProcPath, Buffer, sizeof(Buffer));
+    if (CharCount > 0)
+      RealPath->append(Buffer, Buffer + CharCount);
+  } else {
+    // Use ::realpath to get the real path name
+    if (::realpath(P.begin(), Buffer) != nullptr)
+      RealPath->append(Buffer, Buffer + strlen(Buffer));
+  }
+#endif
   return std::error_code();
 }
 
@@ -584,6 +622,53 @@ std::error_code openFileForWrite(const Twine &Name, int &ResultFD,
   return std::error_code();
 }
 
+std::error_code getPathFromOpenFD(int FD, SmallVectorImpl<char> &ResultPath) {
+  if (FD < 0)
+    return make_error_code(errc::bad_file_descriptor);
+
+#if defined(F_GETPATH)
+  // When F_GETPATH is availble, it is the quickest way to get
+  // the path from a file descriptor.
+  ResultPath.reserve(MAXPATHLEN);
+  if (::fcntl(FD, F_GETPATH, ResultPath.begin()) == -1)
+    return std::error_code(errno, std::generic_category());
+
+  ResultPath.set_size(strlen(ResultPath.begin()));
+#else
+  // If we have a /proc filesystem mounted, we can quickly establish the
+  // real name of the file with readlink. Otherwise, we don't know how to
+  // get the filename from a file descriptor. Give up.
+  if (!fs::hasProcSelfFD())
+    return make_error_code(errc::function_not_supported);
+
+  ResultPath.reserve(PATH_MAX);
+  char ProcPath[64];
+  snprintf(ProcPath, sizeof(ProcPath), "/proc/self/fd/%d", FD);
+  ssize_t CharCount = ::readlink(ProcPath, ResultPath.begin(), ResultPath.capacity());
+  if (CharCount < 0)
+      return std::error_code(errno, std::generic_category());
+
+  // Was the filename truncated?
+  if (static_cast<size_t>(CharCount) == ResultPath.capacity()) {
+    // Use lstat to get the size of the filename
+    struct stat sb;
+    if (::lstat(ProcPath, &sb) < 0)
+      return std::error_code(errno, std::generic_category());
+
+    ResultPath.reserve(sb.st_size + 1);
+    CharCount = ::readlink(ProcPath, ResultPath.begin(), ResultPath.capacity());
+    if (CharCount < 0)
+      return std::error_code(errno, std::generic_category());
+
+    // Test for race condition: did the link size change?
+    if (CharCount > sb.st_size)
+      return std::error_code(ENAMETOOLONG, std::generic_category());
+  }
+  ResultPath.set_size(static_cast<size_t>(CharCount));
+#endif
+  return std::error_code();
+}
+
 } // end namespace fs
 
 namespace path {

llvm/lib/Support/Windows/Path.inc

@@ -707,7 +707,8 @@ std::error_code detail::directory_iterator_increment(detail::DirIterState &it) {
   return std::error_code();
 }
 
-std::error_code openFileForRead(const Twine &Name, int &ResultFD) {
+std::error_code openFileForRead(const Twine &Name, int &ResultFD,
+                                SmallVectorImpl<char> *RealPath) {
   SmallVector<wchar_t, 128> PathUTF16;
 
   if (std::error_code EC = widenPath(Name, PathUTF16))
@@ -736,6 +737,22 @@ std::error_code openFileForRead(const Twine &Name, int &ResultFD) {
     return mapWindowsError(ERROR_INVALID_HANDLE);
   }
 
+  // Fetch the real name of the file, if the user asked
+  if (RealPath) {
+    RealPath->clear();
+    wchar_t RealPathUTF16[MAX_PATH];
+    DWORD CountChars =
+      ::GetFinalPathNameByHandleW(H, RealPathUTF16, MAX_PATH,
+                                  FILE_NAME_NORMALIZED);
+    if (CountChars > 0 && CountChars < MAX_PATH) {
+      // Convert the result from UTF-16 to UTF-8.
+      SmallString<MAX_PATH> RealPathUTF8;
+      if (!UTF16ToUTF8(RealPathUTF16, CountChars, RealPathUTF8))
+        RealPath->append(RealPathUTF8.data(),
+                         RealPathUTF8.data() + strlen(RealPathUTF8.data()));
+    }
+  }
+
   ResultFD = FD;
   return std::error_code();
 }
@@ -796,6 +813,32 @@ std::error_code openFileForWrite(const Twine &Name, int &ResultFD,
   ResultFD = FD;
   return std::error_code();
 }
+
+std::error_code getPathFromOpenFD(int FD, SmallVectorImpl<char> &ResultPath) {
+  HANDLE FileHandle = reinterpret_cast<HANDLE>(::_get_osfhandle(FD));
+  if (FileHandle == INVALID_HANDLE_VALUE)
+    return make_error_code(errc::bad_file_descriptor);
+
+  DWORD CharCount;
+  do {
+    CharCount = ::GetFinalPathNameByHandleA(FileHandle, ResultPath.begin(),
+                                            ResultPath.capacity(), FILE_NAME_NORMALIZED);
+    if (CharCount <= ResultPath.capacity())
+      break;
+    ResultPath.reserve(CharCount);
+  } while (true);
+
+  if (CharCount == 0)
+    return mapWindowsError(::GetLastError());
+
+  ResultPath.set_size(CharCount);
+
+  // On earlier Windows releases, the character count includes the terminating null.
+  if (ResultPath.back() == '\0')
+    ResultPath.pop_back();
+
+  return std::error_code();
+}
 } // end namespace fs
 
 namespace path {
@@ -930,6 +973,7 @@ std::error_code UTF16ToCurCP(const wchar_t *utf16, size_t utf16_len,
                              llvm::SmallVectorImpl<char> &utf8) {
   return UTF16ToCodePage(CP_ACP, utf16, utf16_len, utf8);
 }
+
 } // end namespace windows
 } // end namespace sys
 } // end namespace llvm

llvm/unittests/Support/Path.cpp

@@ -995,4 +995,61 @@ TEST(Support, ReplacePathPrefix) {
   path::replace_path_prefix(Path, OldPrefix, EmptyPrefix);
   EXPECT_EQ(Path, "/foo");
 }
+
+TEST_F(FileSystemTest, PathFromFD) {
+  // Create a temp file.
+  int FileDescriptor;
+  SmallString<64> TempPath;
+  ASSERT_NO_ERROR(
+      fs::createTemporaryFile("prefix", "temp", FileDescriptor, TempPath));
+
+  // Make sure it exists.
+  ASSERT_TRUE(sys::fs::exists(Twine(TempPath)));
+
+  // Try to get the path from the file descriptor
+  SmallString<64> ResultPath;
+  std::error_code ErrorCode =
+      fs::getPathFromOpenFD(FileDescriptor, ResultPath);
+
+  // If we succeeded, check that the paths are the same (modulo case):
+  if (!ErrorCode) {
+    // The paths returned by createTemporaryFile and getPathFromOpenFD
+    // should reference the same file on disk.
+    fs::UniqueID D1, D2;
+    ASSERT_NO_ERROR(fs::getUniqueID(Twine(TempPath), D1));
+    ASSERT_NO_ERROR(fs::getUniqueID(Twine(ResultPath), D2));
+    ASSERT_EQ(D1, D2);
+  }
+
+  ::close(FileDescriptor);
+}
+
+TEST_F(FileSystemTest, OpenFileForRead) {
+  // Create a temp file.
+  int FileDescriptor;
+  SmallString<64> TempPath;
+  ASSERT_NO_ERROR(
+      fs::createTemporaryFile("prefix", "temp", FileDescriptor, TempPath));
+
+  // Make sure it exists.
+  ASSERT_TRUE(sys::fs::exists(Twine(TempPath)));
+
+  // Open the file for read
+  int FileDescriptor2;
+  SmallString<64> ResultPath;
+  ASSERT_NO_ERROR(
+      fs::openFileForRead(Twine(TempPath), FileDescriptor2, &ResultPath))
+
+  // If we succeeded, check that the paths are the same (modulo case):
+  if (!ResultPath.empty()) {
+    // The paths returned by createTemporaryFile and getPathFromOpenFD
+    // should reference the same file on disk.
+    fs::UniqueID D1, D2;
+    ASSERT_NO_ERROR(fs::getUniqueID(Twine(TempPath), D1));
+    ASSERT_NO_ERROR(fs::getUniqueID(Twine(ResultPath), D2));
+    ASSERT_EQ(D1, D2);
+  }
+
+  ::close(FileDescriptor);
+}
 } // anonymous namespace