[Support] Add a function to check if a file resides locally.

Differential Revision: https://reviews.llvm.org/D30010

llvm-svn: 295768

llvm/include/llvm/Support/FileSystem.h

@@ -464,6 +464,32 @@ inline bool equivalent(const Twine &A, const Twine &B) {
   return !equivalent(A, B, result) && result;
 }
 
+/// @brief Is the file mounted on a local filesystem?
+///
+/// @param path Input path.
+/// @param result Set to true if \a path is on fixed media such as a hard disk,
+///               false if it is not.
+/// @returns errc::success if result has been successfully set, otherwise a
+///          platform specific error_code.
+std::error_code is_local(const Twine &path, bool &result);
+
+/// @brief Version of is_local accepting an open file descriptor.
+std::error_code is_local(int FD, bool &result);
+
+/// @brief Simpler version of is_local for clients that don't need to
+///        differentiate between an error and false.
+inline bool is_local(const Twine &Path) {
+  bool Result;
+  return !is_local(Path, Result) && Result;
+}
+
+/// @brief Simpler version of is_local accepting an open file descriptor for
+///        clients that don't need to differentiate between an error and false.
+inline bool is_local(int FD) {
+  bool Result;
+  return !is_local(FD, Result) && Result;
+}
+
 /// @brief Does status represent a directory?
 ///
 /// @param status A file_status previously returned from status.

llvm/include/llvm/Support/MemoryBuffer.h

@@ -69,12 +69,12 @@ class MemoryBuffer {
   /// means that the client knows that the file exists and that it has the
   /// specified size.
   ///
-  /// \param IsVolatileSize Set to true to indicate that the file size may be
-  /// changing, e.g. when libclang tries to parse while the user is
-  /// editing/updating the file.
+  /// \param IsVolatile Set to true to indicate that the contents of the file
+  /// can change outside the user's control, e.g. when libclang tries to parse
+  /// while the user is editing/updating the file or if the file is on an NFS.
   static ErrorOr<std::unique_ptr<MemoryBuffer>>
   getFile(const Twine &Filename, int64_t FileSize = -1,
-          bool RequiresNullTerminator = true, bool IsVolatileSize = false);
+          bool RequiresNullTerminator = true, bool IsVolatile = false);
 
   /// Read all of the specified file into a MemoryBuffer as a stream
   /// (i.e. until EOF reached). This is useful for special files that
@@ -87,17 +87,17 @@ class MemoryBuffer {
   /// Since this is in the middle of a file, the buffer is not null terminated.
   static ErrorOr<std::unique_ptr<MemoryBuffer>>
   getOpenFileSlice(int FD, const Twine &Filename, uint64_t MapSize,
-                   int64_t Offset);
+                   int64_t Offset, bool IsVolatile = false);
 
   /// Given an already-open file descriptor, read the file and return a
   /// MemoryBuffer.
   ///
-  /// \param IsVolatileSize Set to true to indicate that the file size may be
-  /// changing, e.g. when libclang tries to parse while the user is
-  /// editing/updating the file.
+  /// \param IsVolatile Set to true to indicate that the contents of the file
+  /// can change outside the user's control, e.g. when libclang tries to parse
+  /// while the user is editing/updating the file or if the file is on an NFS.
   static ErrorOr<std::unique_ptr<MemoryBuffer>>
   getOpenFile(int FD, const Twine &Filename, uint64_t FileSize,
-              bool RequiresNullTerminator = true, bool IsVolatileSize = false);
+              bool RequiresNullTerminator = true, bool IsVolatile = false);
 
   /// Open the specified memory range as a MemoryBuffer. Note that InputData
   /// must be null terminated if RequiresNullTerminator is true.
@@ -136,7 +136,7 @@ class MemoryBuffer {
 
   /// Map a subrange of the specified file as a MemoryBuffer.
   static ErrorOr<std::unique_ptr<MemoryBuffer>>
-  getFileSlice(const Twine &Filename, uint64_t MapSize, uint64_t Offset);
+  getFileSlice(const Twine &Filename, uint64_t MapSize, uint64_t Offset, bool IsVolatile = false);
 
   //===--------------------------------------------------------------------===//
   // Provided for performance analysis.

llvm/lib/Support/MemoryBuffer.cpp

@@ -103,7 +103,7 @@ class MemoryBufferMem : public MemoryBuffer {
 
 static ErrorOr<std::unique_ptr<MemoryBuffer>>
 getFileAux(const Twine &Filename, int64_t FileSize, uint64_t MapSize, 
-           uint64_t Offset, bool RequiresNullTerminator, bool IsVolatileSize);
+           uint64_t Offset, bool RequiresNullTerminator, bool IsVolatile);
 
 std::unique_ptr<MemoryBuffer>
 MemoryBuffer::getMemBuffer(StringRef InputData, StringRef BufferName,
@@ -178,8 +178,8 @@ MemoryBuffer::getFileOrSTDIN(const Twine &Filename, int64_t FileSize,
 
 ErrorOr<std::unique_ptr<MemoryBuffer>>
 MemoryBuffer::getFileSlice(const Twine &FilePath, uint64_t MapSize, 
-                           uint64_t Offset) {
-  return getFileAux(FilePath, -1, MapSize, Offset, false, false);
+                           uint64_t Offset, bool IsVolatile) {
+  return getFileAux(FilePath, -1, MapSize, Offset, false, IsVolatile);
 }
 
 
@@ -254,27 +254,27 @@ getMemoryBufferForStream(int FD, const Twine &BufferName) {
 
 ErrorOr<std::unique_ptr<MemoryBuffer>>
 MemoryBuffer::getFile(const Twine &Filename, int64_t FileSize,
-                      bool RequiresNullTerminator, bool IsVolatileSize) {
+                      bool RequiresNullTerminator, bool IsVolatile) {
   return getFileAux(Filename, FileSize, FileSize, 0,
-                    RequiresNullTerminator, IsVolatileSize);
+                    RequiresNullTerminator, IsVolatile);
 }
 
 static ErrorOr<std::unique_ptr<MemoryBuffer>>
 getOpenFileImpl(int FD, const Twine &Filename, uint64_t FileSize,
                 uint64_t MapSize, int64_t Offset, bool RequiresNullTerminator,
-                bool IsVolatileSize);
+                bool IsVolatile);
 
 static ErrorOr<std::unique_ptr<MemoryBuffer>>
 getFileAux(const Twine &Filename, int64_t FileSize, uint64_t MapSize,
-           uint64_t Offset, bool RequiresNullTerminator, bool IsVolatileSize) {
+           uint64_t Offset, bool RequiresNullTerminator, bool IsVolatile) {
   int FD;
   std::error_code EC = sys::fs::openFileForRead(Filename, FD);
   if (EC)
     return EC;
 
   ErrorOr<std::unique_ptr<MemoryBuffer>> Ret =
       getOpenFileImpl(FD, Filename, FileSize, MapSize, Offset,
-                      RequiresNullTerminator, IsVolatileSize);
+                      RequiresNullTerminator, IsVolatile);
   close(FD);
   return Ret;
 }
@@ -285,11 +285,11 @@ static bool shouldUseMmap(int FD,
                           off_t Offset,
                           bool RequiresNullTerminator,
                           int PageSize,
-                          bool IsVolatileSize) {
+                          bool IsVolatile) {
   // mmap may leave the buffer without null terminator if the file size changed
   // by the time the last page is mapped in, so avoid it if the file size is
   // likely to change.
-  if (IsVolatileSize)
+  if (IsVolatile)
     return false;
 
   // We don't use mmap for small files because this can severely fragment our
@@ -300,7 +300,6 @@ static bool shouldUseMmap(int FD,
   if (!RequiresNullTerminator)
     return true;
 
-
   // If we don't know the file size, use fstat to find out.  fstat on an open
   // file descriptor is cheaper than stat on a random path.
   // FIXME: this chunk of code is duplicated, but it avoids a fstat when
@@ -338,7 +337,7 @@ static bool shouldUseMmap(int FD,
 static ErrorOr<std::unique_ptr<MemoryBuffer>>
 getOpenFileImpl(int FD, const Twine &Filename, uint64_t FileSize,
                 uint64_t MapSize, int64_t Offset, bool RequiresNullTerminator,
-                bool IsVolatileSize) {
+                bool IsVolatile) {
   static int PageSize = sys::Process::getPageSize();
 
   // Default is to map the full file.
@@ -365,7 +364,7 @@ getOpenFileImpl(int FD, const Twine &Filename, uint64_t FileSize,
   }
 
   if (shouldUseMmap(FD, FileSize, MapSize, Offset, RequiresNullTerminator,
-                    PageSize, IsVolatileSize)) {
+                    PageSize, IsVolatile)) {
     std::error_code EC;
     std::unique_ptr<MemoryBuffer> Result(
         new (NamedBufferAlloc(Filename))
@@ -415,17 +414,16 @@ getOpenFileImpl(int FD, const Twine &Filename, uint64_t FileSize,
 
 ErrorOr<std::unique_ptr<MemoryBuffer>>
 MemoryBuffer::getOpenFile(int FD, const Twine &Filename, uint64_t FileSize,
-                          bool RequiresNullTerminator, bool IsVolatileSize) {
+                          bool RequiresNullTerminator, bool IsVolatile) {
   return getOpenFileImpl(FD, Filename, FileSize, FileSize, 0,
-                         RequiresNullTerminator, IsVolatileSize);
+                         RequiresNullTerminator, IsVolatile);
 }
 
 ErrorOr<std::unique_ptr<MemoryBuffer>>
 MemoryBuffer::getOpenFileSlice(int FD, const Twine &Filename, uint64_t MapSize,
-                               int64_t Offset) {
+                               int64_t Offset, bool IsVolatile) {
   assert(MapSize != uint64_t(-1));
-  return getOpenFileImpl(FD, Filename, -1, MapSize, Offset, false,
-                         /*IsVolatileSize*/ false);
+  return getOpenFileImpl(FD, Filename, -1, MapSize, Offset, false, IsVolatile);
 }
 
 ErrorOr<std::unique_ptr<MemoryBuffer>> MemoryBuffer::getSTDIN() {

llvm/lib/Support/Unix/Path.inc

@@ -65,23 +65,32 @@
 #endif
 
 #include <sys/types.h>
-#if !defined(__APPLE__) && !defined(__OpenBSD__) && !defined(__ANDROID__)
+#if !defined(__APPLE__) && !defined(__OpenBSD__) && !defined(__FreeBSD__) &&   \
+    !defined(__linux__)
 #include <sys/statvfs.h>
 #define STATVFS statvfs
+#define FSTATVFS fstatvfs
 #define STATVFS_F_FRSIZE(vfs) vfs.f_frsize
 #else
-#ifdef __OpenBSD__
+#if defined(__OpenBSD__) || defined(__FreeBSD__)
 #include <sys/param.h>
 #include <sys/mount.h>
-#elif defined(__ANDROID__)
+#elif defined(__linux__)
+#include <linux/magic.h>
 #include <sys/vfs.h>
 #else
 #include <sys/mount.h>
 #endif
 #define STATVFS statfs
+#define FSTATVFS fstatfs
 #define STATVFS_F_FRSIZE(vfs) static_cast<uint64_t>(vfs.f_bsize)
 #endif
 
+#if defined(__NetBSD__)
+#define STATVFS_F_FLAG(vfs) (vfs).f_flag
+#else
+#define STATVFS_F_FLAG(vfs) (vfs).f_flags
+#endif
 
 using namespace llvm;
 
@@ -335,6 +344,40 @@ std::error_code remove(const Twine &path, bool IgnoreNonExisting) {
   return std::error_code();
 }
 
+static bool is_local_impl(struct STATVFS &Vfs) {
+#if defined(__linux__)
+  constexpr uint32_t CIFS_MAGIC_NUMBER = 0xFF534D42;
+  switch ((uint32_t)Vfs.f_type) {
+  case NFS_SUPER_MAGIC:
+  case SMB_SUPER_MAGIC:
+  case CIFS_MAGIC_NUMBER:
+    return false;
+  default:
+    return true;
+  }
+#else
+  return !!(STATVFS_F_FLAG(Vfs) & MNT_LOCAL);
+#endif
+}
+
+std::error_code is_local(const Twine &Path, bool &Result) {
+  struct STATVFS Vfs;
+  if (::STATVFS(Path.str().c_str(), &Vfs))
+    return std::error_code(errno, std::generic_category());
+
+  Result = is_local_impl(Vfs);
+  return std::error_code();
+}
+
+std::error_code is_local(int FD, bool &Result) {
+  struct STATVFS Vfs;
+  if (::FSTATVFS(FD, &Vfs))
+    return std::error_code(errno, std::generic_category());
+
+  Result = is_local_impl(Vfs);
+  return std::error_code();
+}
+
 std::error_code rename(const Twine &from, const Twine &to) {
   // Get arguments.
   SmallString<128> from_storage;
@@ -491,6 +534,23 @@ std::error_code mapped_file_region::init(int FD, uint64_t Offset,
 
   int flags = (Mode == readwrite) ? MAP_SHARED : MAP_PRIVATE;
   int prot = (Mode == readonly) ? PROT_READ : (PROT_READ | PROT_WRITE);
+#if defined(__APPLE__)
+//----------------------------------------------------------------------
+// Newer versions of MacOSX have a flag that will allow us to read from
+// binaries whose code signature is invalid without crashing by using
+// the MAP_RESILIENT_CODESIGN flag. Also if a file from removable media
+// is mapped we can avoid crashing and return zeroes to any pages we try
+// to read if the media becomes unavailable by using the
+// MAP_RESILIENT_MEDIA flag.
+//----------------------------------------------------------------------
+#if defined(MAP_RESILIENT_CODESIGN)
+  flags |= MAP_RESILIENT_CODESIGN;
+#endif
+#if defined(MAP_RESILIENT_MEDIA)
+  flags |= MAP_RESILIENT_MEDIA;
+#endif
+#endif // #if defined (__APPLE__)
+
   Mapping = ::mmap(nullptr, Size, prot, flags, FD, Offset);
   if (Mapping == MAP_FAILED)
     return std::error_code(errno, std::generic_category());

llvm/lib/Support/Windows/Path.inc

@@ -277,6 +277,80 @@ std::error_code remove(const Twine &path, bool IgnoreNonExisting) {
   return std::error_code();
 }
 
+static std::error_code is_local_internal(SmallVectorImpl<wchar_t> &Path,
+                                         bool &Result) {
+  SmallVector<wchar_t, 128> VolumePath;
+  size_t Len = 128;
+  while (true) {
+    VolumePath.resize(Len);
+    BOOL Success =
+        ::GetVolumePathNameW(Path.data(), VolumePath.data(), VolumePath.size());
+
+    if (Success)
+      break;
+
+    DWORD Err = ::GetLastError();
+    if (Err != ERROR_INSUFFICIENT_BUFFER)
+      return mapWindowsError(Err);
+
+    Len *= 2;
+  }
+  // If the output buffer has exactly enough space for the path name, but not
+  // the null terminator, it will leave the output unterminated.  Push a null
+  // terminator onto the end to ensure that this never happens.
+  VolumePath.push_back(L'\0');
+  VolumePath.set_size(wcslen(VolumePath.data()));
+  const wchar_t *P = VolumePath.data();
+
+  UINT Type = ::GetDriveTypeW(P);
+  switch (Type) {
+  case DRIVE_FIXED:
+    Result = true;
+    return std::error_code();
+  case DRIVE_REMOTE:
+  case DRIVE_CDROM:
+  case DRIVE_RAMDISK:
+  case DRIVE_REMOVABLE:
+    Result = false;
+    return std::error_code();
+  default:
+    return make_error_code(errc::no_such_file_or_directory);
+  }
+  llvm_unreachable("Unreachable!");
+}
+
+std::error_code is_local(const Twine &path, bool &result) {
+  if (!llvm::sys::fs::exists(path) || !llvm::sys::path::has_root_path(path))
+    return make_error_code(errc::no_such_file_or_directory);
+
+  SmallString<128> Storage;
+  StringRef P = path.toStringRef(Storage);
+
+  // Convert to utf-16.
+  SmallVector<wchar_t, 128> WidePath;
+  if (std::error_code ec = widenPath(P, WidePath))
+    return ec;
+  return is_local_internal(WidePath, result);
+}
+
+std::error_code is_local(int FD, bool &Result) {
+  SmallVector<wchar_t, 128> FinalPath;
+  HANDLE Handle = reinterpret_cast<HANDLE>(_get_osfhandle(FD));
+
+  size_t Len = 128;
+  do {
+    FinalPath.reserve(Len);
+    Len = ::GetFinalPathNameByHandleW(Handle, FinalPath.data(),
+                                      FinalPath.capacity() - 1, VOLUME_NAME_NT);
+    if (Len == 0)
+      return mapWindowsError(::GetLastError());
+  } while (Len > FinalPath.capacity());
+
+  FinalPath.set_size(Len);
+
+  return is_local_internal(FinalPath, Result);
+}
+
 std::error_code rename(const Twine &from, const Twine &to) {
   // Convert to utf-16.
   SmallVector<wchar_t, 128> wide_from;