Issue #23152: Implement _Py_fstat() to support files larger than 2 GB on Windows.

fstat() may fail with EOVERFLOW on files larger than 2 GB because the file size type is an signed 32-bit integer.

5 files changed, 53 insertions, 162 deletions

diff --git a/Modules/_io/fileio.c b/Modules/_io/fileio.c
index 9c67394..ff88e40 100644
--- a/Modules/_io/fileio.c
+++ b/Modules/_io/fileio.c
@@ -180,9 +180,9 @@ fileio_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
 static int
 check_fd(int fd)
 {
-#if defined(HAVE_FSTAT)
-    struct stat buf;
-    if (!_PyVerify_fd(fd) || (fstat(fd, &buf) < 0 && errno == EBADF)) {
+#if defined(HAVE_FSTAT) || defined(MS_WINDOWS)
+    struct _Py_stat_struct buf;
+    if (!_PyVerify_fd(fd) || (_Py_fstat(fd, &buf) < 0 && errno == EBADF)) {
         PyObject *exc;
         char *msg = strerror(EBADF);
         exc = PyObject_CallFunction(PyExc_OSError, "(is)",
@@ -222,8 +222,8 @@ fileio_init(PyObject *oself, PyObject *args, PyObject *kwds)
 #elif !defined(MS_WINDOWS)
     int *atomic_flag_works = NULL;
 #endif
-#ifdef HAVE_FSTAT
-    struct stat fdfstat;
+#if defined(HAVE_FSTAT) || defined(MS_WINDOWS)
+    struct _Py_stat_struct fdfstat;
 #endif
     int async_err = 0;
 
@@ -420,9 +420,11 @@ fileio_init(PyObject *oself, PyObject *args, PyObject *kwds)
     }
 
     self->blksize = DEFAULT_BUFFER_SIZE;
-#ifdef HAVE_FSTAT
-    if (fstat(self->fd, &fdfstat) < 0)
+#if defined(HAVE_FSTAT) || defined(MS_WINDOWS)
+    if (_Py_fstat(self->fd, &fdfstat) < 0) {
+        PyErr_SetFromErrno(PyExc_OSError);
         goto error;
+    }
 #if defined(S_ISDIR) && defined(EISDIR)
     /* On Unix, open will succeed for directories.
        In Python, there should be no file objects referring to
@@ -437,7 +439,7 @@ fileio_init(PyObject *oself, PyObject *args, PyObject *kwds)
     if (fdfstat.st_blksize > 1)
         self->blksize = fdfstat.st_blksize;
 #endif /* HAVE_STRUCT_STAT_ST_BLKSIZE */
-#endif /* HAVE_FSTAT */
+#endif /* HAVE_FSTAT || MS_WINDOWS */
 
 #if defined(MS_WINDOWS) || defined(__CYGWIN__)
     /* don't translate newlines (\r\n <=> \n) */
@@ -603,17 +605,7 @@ fileio_readinto(fileio *self, PyObject *args)
     return PyLong_FromSsize_t(n);
 }
 
-#ifndef HAVE_FSTAT
-
-static PyObject *
-fileio_readall(fileio *self)
-{
-    _Py_IDENTIFIER(readall);
-    return _PyObject_CallMethodId((PyObject*)&PyRawIOBase_Type,
-                                  &PyId_readall, "O", self);
-}
-
-#else
+#if defined(HAVE_FSTAT) || defined(MS_WINDOWS)
 
 static size_t
 new_buffersize(fileio *self, size_t currentsize)
@@ -637,7 +629,7 @@ new_buffersize(fileio *self, size_t currentsize)
 static PyObject *
 fileio_readall(fileio *self)
 {
-    struct stat st;
+    struct _Py_stat_struct st;
     Py_off_t pos, end;
     PyObject *result;
     Py_ssize_t bytes_read = 0;
@@ -655,7 +647,7 @@ fileio_readall(fileio *self)
 #else
     pos = lseek(self->fd, 0L, SEEK_CUR);
 #endif
-    if (fstat(self->fd, &st) == 0)
+    if (_Py_fstat(self->fd, &st) == 0)
         end = st.st_size;
     else
         end = (Py_off_t)-1;
@@ -729,7 +721,17 @@ fileio_readall(fileio *self)
     return result;
 }
 
-#endif /* HAVE_FSTAT */
+#else
+
+static PyObject *
+fileio_readall(fileio *self)
+{
+    _Py_IDENTIFIER(readall);
+    return _PyObject_CallMethodId((PyObject*)&PyRawIOBase_Type,
+                                  &PyId_readall, "O", self);
+}
+
+#endif /* HAVE_FSTAT || MS_WINDOWS */
 
 static PyObject *
 fileio_read(fileio *self, PyObject *args)
diff --git a/Modules/main.c b/Modules/main.c
index c4883c9..83538c4 100644
--- a/Modules/main.c
+++ b/Modules/main.c
@@ -752,9 +752,8 @@ Py_Main(int argc, wchar_t **argv)
                 }
             }
             {
-                /* XXX: does this work on Win/Win64? (see posix_fstat) */
-                struct stat sb;
-                if (fstat(fileno(fp), &sb) == 0 &&
+                struct _Py_stat_struct sb;
+                if (_Py_fstat(fileno(fp), &sb) == 0 &&
                     S_ISDIR(sb.st_mode)) {
                     fprintf(stderr, "%ls: '%ls' is a directory, cannot continue\n", argv[0], filename);
                     fclose(fp);
diff --git a/Modules/mmapmodule.c b/Modules/mmapmodule.c
index 1371424..ac134b8 100644
--- a/Modules/mmapmodule.c
+++ b/Modules/mmapmodule.c
@@ -459,8 +459,8 @@ mmap_size_method(mmap_object *self,
 
 #ifdef UNIX
     {
-        struct stat buf;
-        if (-1 == fstat(self->fd, &buf)) {
+        struct _Py_stat_struct buf;
+        if (-1 == _Py_fstat(self->fd, &buf)) {
             PyErr_SetFromErrno(PyExc_OSError);
             return NULL;
         }
@@ -1107,7 +1107,7 @@ static PyObject *
 new_mmap_object(PyTypeObject *type, PyObject *args, PyObject *kwdict)
 {
 #ifdef HAVE_FSTAT
-    struct stat st;
+    struct _Py_stat_struct st;
 #endif
     mmap_object *m_obj;
     PyObject *map_size_obj = NULL;
@@ -1174,7 +1174,7 @@ new_mmap_object(PyTypeObject *type, PyObject *args, PyObject *kwdict)
         (void)fcntl(fd, F_FULLFSYNC);
 #endif
 #ifdef HAVE_FSTAT
-    if (fd != -1 && fstat(fd, &st) == 0 && S_ISREG(st.st_mode)) {
+    if (fd != -1 && _Py_fstat(fd, &st) == 0 && S_ISREG(st.st_mode)) {
         if (map_size == 0) {
             if (st.st_size == 0) {
                 PyErr_SetString(PyExc_ValueError,
diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c
index c019b16..cf59724 100644
--- a/Modules/posixmodule.c
+++ b/Modules/posixmodule.c
@@ -350,8 +350,8 @@ static int win32_can_symlink = 0;
 #ifdef MS_WINDOWS
 #       define STAT win32_stat
 #       define LSTAT win32_lstat
-#       define FSTAT win32_fstat
-#       define STRUCT_STAT struct win32_stat
+#       define FSTAT _Py_fstat
+#       define STRUCT_STAT struct _Py_stat_struct
 #else
 #       define STAT stat
 #       define LSTAT lstat
@@ -1469,73 +1469,6 @@ struct win32_stat{
     unsigned long st_file_attributes;
 };
 
-static __int64 secs_between_epochs = 11644473600; /* Seconds between 1.1.1601 and 1.1.1970 */
-
-static void
-FILE_TIME_to_time_t_nsec(FILETIME *in_ptr, time_t *time_out, int* nsec_out)
-{
-    /* XXX endianness. Shouldn't matter, as all Windows implementations are little-endian */
-    /* Cannot simply cast and dereference in_ptr,
-       since it might not be aligned properly */
-    __int64 in;
-    memcpy(&in, in_ptr, sizeof(in));
-    *nsec_out = (int)(in % 10000000) * 100; /* FILETIME is in units of 100 nsec. */
-    *time_out = Py_SAFE_DOWNCAST((in / 10000000) - secs_between_epochs, __int64, time_t);
-}
-
-static void
-time_t_to_FILE_TIME(time_t time_in, int nsec_in, FILETIME *out_ptr)
-{
-    /* XXX endianness */
-    __int64 out;
-    out = time_in + secs_between_epochs;
-    out = out * 10000000 + nsec_in / 100;
-    memcpy(out_ptr, &out, sizeof(out));
-}
-
-/* Below, we *know* that ugo+r is 0444 */
-#if _S_IREAD != 0400
-#error Unsupported C library
-#endif
-static int
-attributes_to_mode(DWORD attr)
-{
-    int m = 0;
-    if (attr & FILE_ATTRIBUTE_DIRECTORY)
-        m |= _S_IFDIR | 0111; /* IFEXEC for user,group,other */
-    else
-        m |= _S_IFREG;
-    if (attr & FILE_ATTRIBUTE_READONLY)
-        m |= 0444;
-    else
-        m |= 0666;
-    return m;
-}
-
-static int
-attribute_data_to_stat(BY_HANDLE_FILE_INFORMATION *info, ULONG reparse_tag, struct win32_stat *result)
-{
-    memset(result, 0, sizeof(*result));
-    result->st_mode = attributes_to_mode(info->dwFileAttributes);
-    result->st_size = (((__int64)info->nFileSizeHigh)<<32) + info->nFileSizeLow;
-    result->st_dev = info->dwVolumeSerialNumber;
-    result->st_rdev = result->st_dev;
-    FILE_TIME_to_time_t_nsec(&info->ftCreationTime, &result->st_ctime, &result->st_ctime_nsec);
-    FILE_TIME_to_time_t_nsec(&info->ftLastWriteTime, &result->st_mtime, &result->st_mtime_nsec);
-    FILE_TIME_to_time_t_nsec(&info->ftLastAccessTime, &result->st_atime, &result->st_atime_nsec);
-    result->st_nlink = info->nNumberOfLinks;
-    result->st_ino = (((__int64)info->nFileIndexHigh)<<32) + info->nFileIndexLow;
-    if (reparse_tag == IO_REPARSE_TAG_SYMLINK) {
-        /* first clear the S_IFMT bits */
-        result->st_mode ^= (result->st_mode & S_IFMT);
-        /* now set the bits that make this a symlink */
-        result->st_mode |= S_IFLNK;
-    }
-    result->st_file_attributes = info->dwFileAttributes;
-
-    return 0;
-}
-
 static BOOL
 attributes_from_dir(LPCSTR pszFile, BY_HANDLE_FILE_INFORMATION *info, ULONG *reparse_tag)
 {
@@ -1645,11 +1578,15 @@ get_target_path(HANDLE hdl, wchar_t **target_path)
     return TRUE;
 }
 
+/* defined in fileutils.c */
+int
+attribute_data_to_stat(BY_HANDLE_FILE_INFORMATION *info, ULONG reparse_tag, struct _Py_stat_struct *result);
+
 static int
-win32_xstat_impl_w(const wchar_t *path, struct win32_stat *result,
+win32_xstat_impl_w(const wchar_t *path, struct _Py_stat_struct *result,
                    BOOL traverse);
 static int
-win32_xstat_impl(const char *path, struct win32_stat *result,
+win32_xstat_impl(const char *path, struct _Py_stat_struct *result,
                  BOOL traverse)
 {
     int code;
@@ -1745,7 +1682,7 @@ win32_xstat_impl(const char *path, struct win32_stat *result,
 }
 
 static int
-win32_xstat_impl_w(const wchar_t *path, struct win32_stat *result,
+win32_xstat_impl_w(const wchar_t *path, struct _Py_stat_struct *result,
                    BOOL traverse)
 {
     int code;
@@ -1841,7 +1778,7 @@ win32_xstat_impl_w(const wchar_t *path, struct win32_stat *result,
 }
 
 static int
-win32_xstat(const char *path, struct win32_stat *result, BOOL traverse)
+win32_xstat(const char *path, struct _Py_stat_struct *result, BOOL traverse)
 {
     /* Protocol violation: we explicitly clear errno, instead of
        setting it to a POSIX error. Callers should use GetLastError. */
@@ -1851,7 +1788,7 @@ win32_xstat(const char *path, struct win32_stat *result, BOOL traverse)
 }
 
 static int
-win32_xstat_w(const wchar_t *path, struct win32_stat *result, BOOL traverse)
+win32_xstat_w(const wchar_t *path, struct _Py_stat_struct *result, BOOL traverse)
 {
     /* Protocol violation: we explicitly clear errno, instead of
        setting it to a POSIX error. Callers should use GetLastError. */
@@ -1873,80 +1810,29 @@ win32_xstat_w(const wchar_t *path, struct win32_stat *result, BOOL traverse)
    The _w represent Unicode equivalents of the aforementioned ANSI functions. */
 
 static int
-win32_lstat(const char* path, struct win32_stat *result)
+win32_lstat(const char* path, struct _Py_stat_struct *result)
 {
     return win32_xstat(path, result, FALSE);
 }
 
 static int
-win32_lstat_w(const wchar_t* path, struct win32_stat *result)
+win32_lstat_w(const wchar_t* path, struct _Py_stat_struct *result)
 {
     return win32_xstat_w(path, result, FALSE);
 }
 
 static int
-win32_stat(const char* path, struct win32_stat *result)
+win32_stat(const char* path, struct _Py_stat_struct *result)
 {
     return win32_xstat(path, result, TRUE);
 }
 
 static int
-win32_stat_w(const wchar_t* path, struct win32_stat *result)
+win32_stat_w(const wchar_t* path, struct _Py_stat_struct *result)
 {
     return win32_xstat_w(path, result, TRUE);
 }
 
-static int
-win32_fstat(int file_number, struct win32_stat *result)
-{
-    BY_HANDLE_FILE_INFORMATION info;
-    HANDLE h;
-    int type;
-
-    if (!_PyVerify_fd(file_number))
-        h = INVALID_HANDLE_VALUE;
-    else
-        h = (HANDLE)_get_osfhandle(file_number);
-
-    /* Protocol violation: we explicitly clear errno, instead of
-       setting it to a POSIX error. Callers should use GetLastError. */
-    errno = 0;
-
-    if (h == INVALID_HANDLE_VALUE) {
-        /* This is really a C library error (invalid file handle).
-           We set the Win32 error to the closes one matching. */
-        SetLastError(ERROR_INVALID_HANDLE);
-        return -1;
-    }
-    memset(result, 0, sizeof(*result));
-
-    type = GetFileType(h);
-    if (type == FILE_TYPE_UNKNOWN) {
-        DWORD error = GetLastError();
-        if (error != 0) {
-            return -1;
-        }
-        /* else: valid but unknown file */
-    }
-
-    if (type != FILE_TYPE_DISK) {
-        if (type == FILE_TYPE_CHAR)
-            result->st_mode = _S_IFCHR;
-        else if (type == FILE_TYPE_PIPE)
-            result->st_mode = _S_IFIFO;
-        return 0;
-    }
-
-    if (!GetFileInformationByHandle(h, &info)) {
-        return -1;
-    }
-
-    attribute_data_to_stat(&info, 0, result);
-    /* specific to fstat() */
-    result->st_ino = (((__int64)info.nFileIndexHigh)<<32) + info.nFileIndexLow;
-    return 0;
-}
-
 #endif /* MS_WINDOWS */
 
 PyDoc_STRVAR(stat_result__doc__,
@@ -6333,6 +6219,11 @@ exit:
     return return_value;
 }
 
+#ifdef MS_WINDOWS
+void
+time_t_to_FILE_TIME(time_t time_in, int nsec_in, FILETIME *out_ptr);
+#endif
+
 static PyObject *
 os_utime_impl(PyModuleDef *module, path_t *path, PyObject *times, PyObject *ns, int dir_fd, int follow_symlinks)
 /*[clinic end generated code: output=891489c35cc68c5d input=1f18c17d5941aa82]*/
diff --git a/Modules/signalmodule.c b/Modules/signalmodule.c
index 2f2b260..598bc8a 100644
--- a/Modules/signalmodule.c
+++ b/Modules/signalmodule.c
@@ -503,13 +503,13 @@ signal_siginterrupt(PyObject *self, PyObject *args)
 static PyObject *
 signal_set_wakeup_fd(PyObject *self, PyObject *args)
 {
+    struct _Py_stat_struct st;
 #ifdef MS_WINDOWS
     PyObject *fdobj;
     SOCKET_T sockfd, old_sockfd;
     int res;
     int res_size = sizeof res;
     PyObject *mod;
-    struct stat st;
     int is_socket;
 
     if (!PyArg_ParseTuple(args, "O:set_wakeup_fd", &fdobj))
@@ -520,7 +520,6 @@ signal_set_wakeup_fd(PyObject *self, PyObject *args)
         return NULL;
 #else
     int fd, old_fd;
-    struct stat st;
 
     if (!PyArg_ParseTuple(args, "i:set_wakeup_fd", &fd))
         return NULL;
@@ -560,7 +559,7 @@ signal_set_wakeup_fd(PyObject *self, PyObject *args)
                 return NULL;
             }
 
-            if (fstat(fd, &st) != 0) {
+            if (_Py_fstat(fd, &st) != 0) {
                 PyErr_SetFromErrno(PyExc_OSError);
                 return NULL;
             }
@@ -592,7 +591,7 @@ signal_set_wakeup_fd(PyObject *self, PyObject *args)
             return NULL;
         }
 
-        if (fstat(fd, &st) != 0) {
+        if (_Py_fstat(fd, &st) != 0) {
             PyErr_SetFromErrno(PyExc_OSError);
             return NULL;
         }