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, 157 insertions, 15 deletions

diff --git a/Python/dynload_shlib.c b/Python/dynload_shlib.c
index 5cd1efd..659adac 100644
--- a/Python/dynload_shlib.c
+++ b/Python/dynload_shlib.c
@@ -71,8 +71,8 @@ dl_funcptr _PyImport_GetDynLoadFunc(const char *shortname,
 
     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
index c5c8d4e..8f3fdca 100644
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -544,8 +544,145 @@ _Py_wstat(const wchar_t* path, struct stat *buf)
 }
 #endif
 
-#ifdef HAVE_STAT
 
+#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 @@ _Py_stat(PyObject *path, struct stat *statbuf)
 #endif
 }
 
-#endif
+#endif   /* HAVE_STAT */
+
 
 static int
 get_inheritable(int fd, int raise)
diff --git a/Python/marshal.c b/Python/marshal.c
index d26a997..93d9d1d 100644
--- a/Python/marshal.c
+++ b/Python/marshal.c
@@ -1481,16 +1481,20 @@ PyMarshal_ReadLongFromFile(FILE *fp)
     return res;
 }
 
-#ifdef HAVE_FSTAT
-/* Return size of file in bytes; < 0 if unknown. */
+#if defined(HAVE_FSTAT) || defined(MS_WINDOWS)
+/* Return size of file in bytes; < 0 if unknown or INT_MAX if too big */
 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;
+#if SIZEOF_OFF_T == 4
+    else if (st.st_size >= INT_MAX)
+        return (off_t)INT_MAX;
+#endif
     else
-        return st.st_size;
+        return (off_t)st.st_size;
 }
 #endif
 
@@ -1505,7 +1509,7 @@ PyMarshal_ReadLastObjectFromFile(FILE *fp)
 {
 /* 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
index 93d300d..031d887 100644
--- a/Python/random.c
+++ b/Python/random.c
@@ -139,14 +139,14 @@ dev_urandom_python(char *buffer, Py_ssize_t size)
 {
     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 @@ dev_urandom_python(char *buffer, Py_ssize_t size)
             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
index 0639231..292830b 100644
--- a/Python/sysmodule.c
+++ b/Python/sysmodule.c
@@ -1681,8 +1681,8 @@ _PySys_Init(void)
     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. */