x86: Fix bug in strncmp-evex and strncmp-avx2 [BZ #28895]

Logic can read before the start of `s1` / `s2` if both `s1` and `s2`
are near the start of a page. To avoid having the result contimated by
these comparisons the `strcmp` variants would mask off these
comparisons. This was missing in the `strncmp` variants causing
the bug. This commit adds the masking to `strncmp` so that out of
range comparisons don't affect the result.

test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass as
well a full xcheck on x86_64 linux.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

string/test-strncmp.c

@@ -423,6 +423,28 @@ check3 (void)
 	}
 }
 
+static void
+check4 (void)
+{
+  /* To trigger bug 28895; We need 1) both s1 and s2 to be within 32 bytes of
+     the end of the page. 2) For there to be no mismatch/null byte before the
+     first page cross. 3) For length (`n`) to be large enough for one string to
+     cross the page. And 4) for there to be either mismatch/null bytes before
+     the start of the strings.  */
+
+  size_t size = 10;
+  size_t addr_mask = (getpagesize () - 1) ^ (sizeof (CHAR) - 1);
+  CHAR *s1 = (CHAR *)(buf1 + (addr_mask & 0xffa));
+  CHAR *s2 = (CHAR *)(buf2 + (addr_mask & 0xfed));
+  int exp_result;
+
+  STRCPY (s1, L ("tst-tlsmod%"));
+  STRCPY (s2, L ("tst-tls-manydynamic73mod"));
+  exp_result = SIMPLE_STRNCMP (s1, s2, size);
+  FOR_EACH_IMPL (impl, 0)
+  check_result (impl, s1, s2, size, exp_result);
+}
+
 static void
 check_overflow (void)
 {
@@ -546,6 +568,7 @@ test_main (void)
   check1 ();
   check2 ();
   check3 ();
+  check4 ();
 
   printf ("%23s", "");
   FOR_EACH_IMPL (impl, 0)

sysdeps/x86_64/multiarch/strcmp-avx2.S

@@ -661,6 +661,7 @@ L(ret8):
 # ifdef USE_AS_STRNCMP
 	.p2align 4,, 10
 L(return_page_cross_end_check):
+	andl	%r10d, %ecx
 	tzcntl	%ecx, %ecx
 	leal	-VEC_SIZE(%rax, %rcx), %ecx
 	cmpl	%ecx, %edx

sysdeps/x86_64/multiarch/strcmp-evex.S

@@ -689,6 +689,7 @@ L(ret8):
 # ifdef USE_AS_STRNCMP
 	.p2align 4,, 10
 L(return_page_cross_end_check):
+	andl	%r10d, %ecx
 	tzcntl	%ecx, %ecx
 	leal	-VEC_SIZE(%rax, %rcx, SIZE_OF_CHAR), %ecx
 #  ifdef USE_AS_WCSCMP