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>

sysdeps/x86/Makefile

@@ -109,7 +109,7 @@ 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
 

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;
 }

sysdeps/x86_64/multiarch/strcmp-avx2.S

@@ -193,10 +193,10 @@ L(ret_zero):
 	.p2align 4,, 5
 L(one_or_less):
 	jb	L(ret_zero)
-#  ifdef USE_AS_WCSCMP
 	/* 'nbe' covers the case where length is negative (large
 	   unsigned).  */
-	jnbe	__wcscmp_avx2
+	jnbe	OVERFLOW_STRCMP
+#  ifdef USE_AS_WCSCMP
 	movl	(%rdi), %edx
 	xorl	%eax, %eax
 	cmpl	(%rsi), %edx
@@ -205,10 +205,6 @@ L(one_or_less):
 	negl	%eax
 	orl	$1, %eax
 #  else
-	/* 'nbe' covers the case where length is negative (large
-	   unsigned).  */
-
-	jnbe	__strcmp_avx2
 	movzbl	(%rdi), %eax
 	movzbl	(%rsi), %ecx
 	subl	%ecx, %eax

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"

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"

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"

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"