From d1a2117dc18dbcf87685891de7e2898108b66fc9 Mon Sep 17 00:00:00 2001
From: Joan Bruguera <joanbrugueram@gmail.com>
Date: Thu, 23 Mar 2023 02:24:30 +0000
Subject: [PATCH] glocalfile: Sum apparent size only for files and symlinks

Since GNU Coreutils 9.2 (commit 110bcd28386b1f47a4cd876098acb708fdcbbb25),
`du --apparent-size` (including `du --bytes`) no longer counts all kinds of
files (directories, FIFOs, etc.), but only those for which `st_size` in
`struct stat` is defined by POSIX, namely regular files and symlinks
(and also rarely supported memory objects).

This aligns the behaviour of GLib's `G_FILE_MEASURE_APPARENT_SIZE` flag
with the new GNU Coreutils `du` and correct POSIX use.

Note that this may be a breaking change for some uses.

Link: https://lists.gnu.org/archive/html/bug-coreutils/2023-03/msg00007.html
Fixes: https://gitlab.gnome.org/GNOME/glib/-/issues/2965

Upstream-Status: Backport
Signed-off-by: Alexander Kanavin <alex@linutronix.de>
---
 gio/gioenums.h   |  3 +++
 gio/glocalfile.c | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/gio/gioenums.h b/gio/gioenums.h
index 7fd74a43e..c820cd36d 100644
--- a/gio/gioenums.h
+++ b/gio/gioenums.h
@@ -224,6 +224,9 @@ typedef enum {
  *   sizes.  Normally, the block-size is used, if available, as this is a
  *   more accurate representation of disk space used.
  *   Compare with `du --apparent-size`.
+ *   Since GLib 2.78. and similarly to `du` since GNU Coreutils 9.2, this will
+ *   ignore the sizes of file types other than regular files and links, as the
+ *   sizes of other file types are not specified in a standard way.
  * @G_FILE_MEASURE_NO_XDEV: Do not cross mount point boundaries.
  *   Compare with `du -x`.
  *
diff --git a/gio/glocalfile.c b/gio/glocalfile.c
index 67d4b99fb..dbb56902d 100644
--- a/gio/glocalfile.c
+++ b/gio/glocalfile.c
@@ -86,6 +86,9 @@
 #define FILE_READ_ONLY_VOLUME           0x00080000
 #endif
 
+#ifndef S_ISREG
+#define S_ISREG(m) (((m) & _S_IFMT) == _S_IFREG)
+#endif
 #ifndef S_ISDIR
 #define S_ISDIR(m) (((m) & _S_IFMT) == _S_IFDIR)
 #endif
@@ -2777,6 +2780,39 @@ g_local_file_measure_size_of_contents (gint           fd,
                                        MeasureState  *state,
                                        GError       **error);
 
+/*
+ * _g_stat_is_size_usable:
+ * @buf: a #GLocalFileStat.
+ *
+ * Checks if the file type is such that the `st_size` field of `struct stat` is
+ * well-defined by POSIX.
+ * (see https://pubs.opengroup.org/onlinepubs/009696799/basedefs/sys/stat.h.html)
+ *
+ * This behaviour is aligned with `du` from GNU Coreutils 9.2+
+ * (see https://lists.gnu.org/archive/html/bug-coreutils/2023-03/msg00007.html)
+ * and makes apparent size sums well-defined; formerly, they depended on the
+ * implementation, and could differ across filesystems.
+ *
+ * Returns: %TRUE if the size field is well-defined, %FALSE otherwise.
+ **/
+inline static gboolean
+_g_stat_is_size_usable (const GLocalFileStat *buf)
+{
+#ifndef HAVE_STATX
+  /* Memory objects are defined by POSIX, but are not supported by statx nor Windows */
+#ifdef S_TYPEISSHM
+  if (S_TYPEISSHM (buf))
+    return TRUE;
+#endif
+#ifdef S_TYPEISTMO
+  if (S_TYPEISTMO (buf))
+    return TRUE;
+#endif
+#endif
+
+  return S_ISREG (_g_stat_mode (buf)) || S_ISLNK (_g_stat_mode (buf));
+}
+
 static gboolean
 g_local_file_measure_size_of_file (gint           parent_fd,
                                    GSList        *name,
@@ -2836,6 +2872,7 @@ g_local_file_measure_size_of_file (gint           parent_fd,
     state->disk_usage += _g_stat_blocks (&buf) * G_GUINT64_CONSTANT (512);
   else
 #endif
+  if (_g_stat_is_size_usable (&buf))
     state->disk_usage += _g_stat_size (&buf);
 
   if (S_ISDIR (_g_stat_mode (&buf)))
-- 
2.39.2