x86: Fallback {str|wcs}cmp RTM in the ncmp overflow case [BZ #28896]

In the overflow fallback strncmp-avx2-rtm and wcsncmp-avx2-rtm would
call strcmp-avx2 and wcscmp-avx2 respectively. This would have
not checks around vzeroupper and would trigger spurious
aborts. This commit fixes that.

test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass on
AVX2 machines with and without RTM.

Co-authored-by: H.J. Lu <hjl.tools@gmail.com>

(cherry picked from commit c6272098323153db373f2986c67786ea8c85f1cf)

7 files changed, 22 insertions, 5 deletions

diff --git a/sysdeps/x86/Makefile b/sysdeps/x86/Makefile
index a93139b790..b0ac1a61d0 100644
--- a/sysdeps/x86/Makefile
+++ b/sysdeps/x86/Makefile
@@ -43,7 +43,7 @@ CFLAGS-tst-memset-rtm.c += -mrtm
 CFLAGS-tst-strchr-rtm.c += -mrtm
 CFLAGS-tst-strcpy-rtm.c += -mrtm
 CFLAGS-tst-strlen-rtm.c += -mrtm
-CFLAGS-tst-strncmp-rtm.c += -mrtm
+CFLAGS-tst-strncmp-rtm.c += -mrtm -Wno-error
 CFLAGS-tst-strrchr-rtm.c += -mrtm
 endif
 
diff --git a/sysdeps/x86/tst-strncmp-rtm.c b/sysdeps/x86/tst-strncmp-rtm.c
index 236ad951b5..4d0004b58a 100644
--- a/sysdeps/x86/tst-strncmp-rtm.c
+++ b/sysdeps/x86/tst-strncmp-rtm.c
@@ -16,6 +16,7 @@
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
+#include <stdint.h>
 #include <tst-string-rtm.h>
 
 #define LOOP 3000
@@ -45,8 +46,22 @@ function (void)
     return 1;
 }
 
+__attribute__ ((noinline, noclone))
+static int
+function_overflow (void)
+{
+  if (strncmp (string1, string2, SIZE_MAX) == 0)
+    return 0;
+  else
+    return 1;
+}
+
 static int
 do_test (void)
 {
-  return do_test_1 ("strncmp", LOOP, prepare, function);
+  int status = do_test_1 ("strncmp", LOOP, prepare, function);
+  if (status != EXIT_SUCCESS)
+    return status;
+  status = do_test_1 ("strncmp", LOOP, prepare, function_overflow);
+  return status;
 }
diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S
index a1b429d99a..4d434fd14e 100644
--- a/sysdeps/x86_64/multiarch/strcmp-avx2.S
+++ b/sysdeps/x86_64/multiarch/strcmp-avx2.S
@@ -95,7 +95,7 @@ ENTRY (STRCMP)
 	   length to bound a valid memory region. In these cases just use
 	   'wcscmp'.  */
 	shrq	$56, %rcx
-	jnz	__wcscmp_avx2
+	jnz	OVERFLOW_STRCMP
 #  endif
 	/* Convert units: from wide to byte char.  */
 	shl	$2, %RDX_LP
diff --git a/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S b/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
index 37d1224bb9..68bad365ba 100644
--- a/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
+++ b/sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
@@ -1,3 +1,4 @@
 #define STRCMP	__strncmp_avx2_rtm
 #define USE_AS_STRNCMP 1
+#define OVERFLOW_STRCMP	__strcmp_avx2_rtm
 #include "strcmp-avx2-rtm.S"
diff --git a/sysdeps/x86_64/multiarch/strncmp-avx2.S b/sysdeps/x86_64/multiarch/strncmp-avx2.S
index 1678bcc235..f138e9f1fd 100644
--- a/sysdeps/x86_64/multiarch/strncmp-avx2.S
+++ b/sysdeps/x86_64/multiarch/strncmp-avx2.S
@@ -1,3 +1,4 @@
 #define STRCMP	__strncmp_avx2
 #define USE_AS_STRNCMP 1
+#define OVERFLOW_STRCMP __strcmp_avx2
 #include "strcmp-avx2.S"
diff --git a/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S b/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
index 4e88c70cc6..f467582cbe 100644
--- a/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
+++ b/sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
@@ -1,5 +1,5 @@
 #define STRCMP __wcsncmp_avx2_rtm
 #define USE_AS_STRNCMP 1
 #define USE_AS_WCSCMP 1
-
+#define OVERFLOW_STRCMP	__wcscmp_avx2_rtm
 #include "strcmp-avx2-rtm.S"
diff --git a/sysdeps/x86_64/multiarch/wcsncmp-avx2.S b/sysdeps/x86_64/multiarch/wcsncmp-avx2.S
index 4fa1de4d3f..e9ede522b8 100644
--- a/sysdeps/x86_64/multiarch/wcsncmp-avx2.S
+++ b/sysdeps/x86_64/multiarch/wcsncmp-avx2.S
@@ -1,5 +1,5 @@
 #define STRCMP __wcsncmp_avx2
 #define USE_AS_STRNCMP 1
 #define USE_AS_WCSCMP 1
-
+#define OVERFLOW_STRCMP	__wcscmp_avx2
 #include "strcmp-avx2.S"