From cf982177ddc7fbeb9a958812b23685bdfbd5c939 Mon Sep 17 00:00:00 2001
From: Philip Withnall <pwithnall@gnome.org>
Date: Tue, 22 Oct 2024 12:46:16 +0100
Subject: [PATCH] gutf8: Add ifunc resolver for g_str_is_ascii() too

Just like how commit ad572e77802c3c383619fe63a4832b5c75dbea82 added an
ifunc resolver for `g_utf8_validate()`, we also need to add one for
`g_str_is_ascii()`, as it also calls into the c-utf8 SIMD validation
code which causes false-positive buffer read overflow warnings from
valgrind and asan.

I thought about just adding the `strlen()` call into `g_str_is_ascii()`
unconditionally, as a simpler fix, but from a quick
codesearch.debian.net, it appears `g_str_is_ascii()` is used quite
widely, so this would have an unacceptable performance impact.

This should fix the valgrind failures on the `search-utils` test seen
here: https://gitlab.gnome.org/GNOME/glib/-/jobs/4423753.

Signed-off-by: Philip Withnall <pwithnall@gnome.org>
---
 glib/gutf8.c | 43 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/glib/gutf8.c b/glib/gutf8.c
index b245d5ffd..bca3358c2 100644
--- a/glib/gutf8.c
+++ b/glib/gutf8.c
@@ -1969,6 +1969,38 @@ g_utf8_validate_len (const char   *str,
   return max_len == 0;
 }
 
+static gboolean
+g_str_is_ascii_native (const char *str)
+{
+  utf8_verify_ascii (&str, NULL);
+
+  return *str == 0;
+}
+
+#ifdef HAVE_WORKING_IFUNC_ATTRIBUTE
+/* See above comment about `ifunc` use for g_utf8_validate(). */
+static gboolean
+g_str_is_ascii_valgrind (const char *str)
+{
+  size_t len = strlen (str);
+
+  utf8_verify_ascii (&str, &len);
+
+  return *str == 0;
+}
+
+typedef gboolean (*GStrIsAsciiFunc) (const char *str);
+
+static GStrIsAsciiFunc
+resolve_g_str_is_ascii (void)
+{
+  if (RUNNING_ON_VALGRIND)
+    return g_str_is_ascii_valgrind;
+  else
+    return g_str_is_ascii_native;
+}
+#endif  /* HAVE_WORKING_IFUNC_ATTRIBUTE */
+
 /**
  * g_str_is_ascii:
  * @str: a string
@@ -1980,13 +2012,18 @@ g_utf8_validate_len (const char   *str,
  *
  * Since: 2.40
  */
+#if g_macro__has_attribute(no_sanitize_address)
+  __attribute__((no_sanitize_address))
+#endif
 gboolean
 g_str_is_ascii (const gchar *str)
+#ifdef HAVE_WORKING_IFUNC_ATTRIBUTE
+  __attribute__((ifunc ("resolve_g_str_is_ascii")));
+#else
 {
-  utf8_verify_ascii (&str, NULL);
-
-  return *str == 0;
+  return g_str_is_ascii_native (str);
 }
+#endif
 
 /**
  * g_unichar_validate: