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.
This commit is contained in:
Steve Dower 2015-02-21 08:44:05 -08:00
parent 18d1924987
commit f2f373f593
12 changed files with 242 additions and 180 deletions

View file

@ -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]*/