# HG changeset patch # User Steve Dower # Date 1420711208 -3600 # Thu Jan 08 11:00:08 2015 +0100 # Node ID 4bc1ae6c516f4c2ef008f0493c79ef48a92a22a4 # Parent 7347686b2aab44e40080593b8a50eb9b01789ec3 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. diff --git a/Include/fileutils.h b/Include/fileutils.h --- a/Include/fileutils.h +++ b/Include/fileutils.h @@ -21,11 +21,40 @@ struct stat *buf); #endif +#if defined(HAVE_FSTAT) || defined(MS_WINDOWS) + +#ifdef MS_WINDOWS +struct _Py_stat_struct { + unsigned long st_dev; + __int64 st_ino; + unsigned short st_mode; + int st_nlink; + int st_uid; + int st_gid; + unsigned long st_rdev; + __int64 st_size; + time_t st_atime; + int st_atime_nsec; + time_t st_mtime; + int st_mtime_nsec; + time_t st_ctime; + int st_ctime_nsec; + unsigned long st_file_attributes; +}; +#else +# define _Py_stat_struct stat +#endif + +PyAPI_FUNC(int) _Py_fstat( + int fd, + struct _Py_stat_struct *stat); +#endif /* HAVE_FSTAT || MS_WINDOWS */ + #ifdef HAVE_STAT PyAPI_FUNC(int) _Py_stat( PyObject *path, struct stat *statbuf); -#endif +#endif /* HAVE_STAT */ #ifndef Py_LIMITED_API PyAPI_FUNC(int) _Py_open( diff --git a/Modules/main.c b/Modules/main.c --- a/Modules/main.c +++ b/Modules/main.c @@ -752,9 +752,8 @@ } } { - /* 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 --- a/Modules/mmapmodule.c +++ b/Modules/mmapmodule.c @@ -459,8 +459,8 @@ #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 @@ 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 @@ (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 --- a/Modules/posixmodule.c +++ b/Modules/posixmodule.c @@ -350,8 +350,8 @@ #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 @@ -1466,73 +1466,6 @@ 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) { @@ -1642,11 +1575,15 @@ return TRUE; } -static int -win32_xstat_impl_w(const wchar_t *path, struct win32_stat *result, +/* 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 _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; @@ -1742,7 +1679,7 @@ } 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; @@ -1838,7 +1775,7 @@ } 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. */ @@ -1848,7 +1785,7 @@ } 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. */ @@ -1870,80 +1807,29 @@ 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__, @@ -6320,6 +6206,11 @@ 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 --- a/Modules/signalmodule.c +++ b/Modules/signalmodule.c @@ -503,13 +503,13 @@ static PyObject * signal_set_wakeup_fd(PyObject *self, PyObject *args) { + struct _Py_stat_struct st; #ifdef MS_WINDOWS PyObject *fdobj; SOCKET_T fd, old_fd; 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 @@ return NULL; #else int fd, old_fd; - struct stat st; if (!PyArg_ParseTuple(args, "i:set_wakeup_fd", &fd)) return NULL; @@ -557,7 +556,7 @@ return NULL; } - if (fstat(fd, &st) != 0) { + if (_Py_fstat(fd, &st) != 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } @@ -589,7 +588,7 @@ return NULL; } - if (fstat(fd, &st) != 0) { + if (_Py_fstat(fd, &st) != 0) { PyErr_SetFromErrno(PyExc_OSError); return NULL; } diff --git a/Programs/_freeze_importlib.c b/Programs/_freeze_importlib.c --- a/Programs/_freeze_importlib.c +++ b/Programs/_freeze_importlib.c @@ -35,7 +35,7 @@ { char *inpath, *outpath; FILE *infile = NULL, *outfile = NULL; - struct stat st; + struct _Py_stat_struct st; size_t text_size, data_size, n; char *text = NULL; unsigned char *data; @@ -54,7 +54,7 @@ fprintf(stderr, "cannot open '%s' for reading\n", inpath); goto error; } - if (fstat(fileno(infile), &st)) { + if (_Py_fstat(fileno(infile), &st)) { fprintf(stderr, "cannot fstat '%s'\n", inpath); goto error; } diff --git a/Python/dynload_shlib.c b/Python/dynload_shlib.c --- a/Python/dynload_shlib.c +++ b/Python/dynload_shlib.c @@ -71,8 +71,8 @@ if (fp != NULL) { int i; - struct stat statb; - if (fstat(fileno(fp), &statb) == -1) { + struct _Py_stat_struct statb; + if (_Py_fstat(fileno(fp), &statb) == -1) { PyErr_SetFromErrno(PyExc_IOError); return NULL; } diff --git a/Python/fileutils.c b/Python/fileutils.c --- a/Python/fileutils.c +++ b/Python/fileutils.c @@ -544,8 +544,145 @@ } #endif + +#if defined(HAVE_FSTAT) || defined(MS_WINDOWS) + +#ifdef MS_WINDOWS +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); +} + +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; +} + +int +attribute_data_to_stat(BY_HANDLE_FILE_INFORMATION *info, ULONG reparse_tag, struct _Py_stat_struct *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; +} +#endif + +/* Return information about a file. + + On POSIX, use fstat(). + + On Windows, use GetFileType() and GetFileInformationByHandle() which support + files larger than 2 GB. fstat() may fail with EOVERFLOW on files larger + than 2 GB because the file size type is an signed 32-bit integer: see issue + #23152. + */ +int +_Py_fstat(int fd, struct _Py_stat_struct *result) +{ +#ifdef MS_WINDOWS + BY_HANDLE_FILE_INFORMATION info; + HANDLE h; + int type; + + if (!_PyVerify_fd(fd)) + h = INVALID_HANDLE_VALUE; + else + h = (HANDLE)_get_osfhandle(fd); + + /* 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; +#else + return fstat(fd, result); +#endif +} +#endif /* HAVE_FSTAT || MS_WINDOWS */ + + #ifdef HAVE_STAT - /* Call _wstat() on Windows, or encode the path to the filesystem encoding and call stat() otherwise. Only fill st_mode attribute on Windows. @@ -578,7 +715,8 @@ #endif } -#endif +#endif /* HAVE_STAT */ + static int get_inheritable(int fd, int raise) diff --git a/Python/marshal.c b/Python/marshal.c --- a/Python/marshal.c +++ b/Python/marshal.c @@ -1415,13 +1415,13 @@ return res; } -#ifdef HAVE_FSTAT +#if defined(HAVE_FSTAT) || defined(MS_WINDOWS) /* Return size of file in bytes; < 0 if unknown. */ static off_t getfilesize(FILE *fp) { - struct stat st; - if (fstat(fileno(fp), &st) != 0) + struct _Py_stat_struct st; + if (_Py_fstat(fileno(fp), &st) != 0) return -1; else return st.st_size; @@ -1439,7 +1439,7 @@ { /* REASONABLE_FILE_LIMIT is by defn something big enough for Tkinter.pyc. */ #define REASONABLE_FILE_LIMIT (1L << 18) -#ifdef HAVE_FSTAT +#if defined(HAVE_FSTAT) || defined(MS_WINDOWS) off_t filesize; filesize = getfilesize(fp); if (filesize > 0 && filesize <= REASONABLE_FILE_LIMIT) { diff --git a/Python/random.c b/Python/random.c --- a/Python/random.c +++ b/Python/random.c @@ -139,14 +139,14 @@ { int fd; Py_ssize_t n; - struct stat st; + struct _Py_stat_struct st; if (size <= 0) return 0; if (urandom_cache.fd >= 0) { /* Does the fd point to the same thing as before? (issue #21207) */ - if (fstat(urandom_cache.fd, &st) + if (_Py_fstat(urandom_cache.fd, &st) || st.st_dev != urandom_cache.st_dev || st.st_ino != urandom_cache.st_ino) { /* Something changed: forget the cached fd (but don't close it, @@ -178,7 +178,7 @@ fd = urandom_cache.fd; } else { - if (fstat(fd, &st)) { + if (_Py_fstat(fd, &st)) { PyErr_SetFromErrno(PyExc_OSError); close(fd); return -1; diff --git a/Python/sysmodule.c b/Python/sysmodule.c --- a/Python/sysmodule.c +++ b/Python/sysmodule.c @@ -1681,8 +1681,8 @@ the shell already prevents that. */ #if !defined(MS_WINDOWS) { - struct stat sb; - if (fstat(fileno(stdin), &sb) == 0 && + struct _Py_stat_struct sb; + if (_Py_fstat(fileno(stdin), &sb) == 0 && S_ISDIR(sb.st_mode)) { /* There's nothing more we can do. */ /* Py_FatalError() will core dump, so just exit. */