x86: Fix wcsnlen-avx2 page cross length comparison [BZ #29591]

Previous implementation was adjusting length (rsi) to match
bytes (eax), but since there is no bound to length this can cause
overflow.

Fix is to just convert the byte-count (eax) to length by dividing by
sizeof (wchar_t) before the comparison.

Full check passes on x86-64 and build succeeds w/ and w/o multiarch.

(cherry picked from commit b0969fa53a28b4ab2159806bf6c99a98999502ee)

2 files changed, 43 insertions, 28 deletions

diff --git a/string/test-strnlen.c b/string/test-strnlen.c
index 0383cb073a..275801221c 100644
--- a/string/test-strnlen.c
+++ b/string/test-strnlen.c
@@ -75,7 +75,7 @@ do_test (size_t align, size_t len, size_t maxlen, int max_char)
 {
   size_t i;
 
-  align &= 63;
+  align &= (getpagesize () / sizeof (CHAR) - 1);
   if ((align + len) * sizeof (CHAR) >= page_size)
     return;
 
@@ -92,32 +92,50 @@ do_test (size_t align, size_t len, size_t maxlen, int max_char)
 static void
 do_overflow_tests (void)
 {
-  size_t i, j, len;
+  size_t i, j, al_idx, repeats, len;
   const size_t one = 1;
   uintptr_t buf_addr = (uintptr_t) buf1;
+  const size_t alignments[] = { 0, 1, 7, 9, 31, 33, 63, 65, 95, 97, 127, 129 };
 
-  for (i = 0; i < 750; ++i)
+  for (al_idx = 0; al_idx < sizeof (alignments) / sizeof (alignments[0]);
+       al_idx++)
     {
-      do_test (0, i, SIZE_MAX - i, BIG_CHAR);
-      do_test (0, i, i - buf_addr, BIG_CHAR);
-      do_test (0, i, -buf_addr - i, BIG_CHAR);
-      do_test (0, i, SIZE_MAX - buf_addr - i, BIG_CHAR);
-      do_test (0, i, SIZE_MAX - buf_addr + i, BIG_CHAR);
-
-      len = 0;
-      for (j = 8 * sizeof(size_t) - 1; j ; --j)
-        {
-          len |= one << j;
-          do_test (0, i, len - i, BIG_CHAR);
-          do_test (0, i, len + i, BIG_CHAR);
-          do_test (0, i, len - buf_addr - i, BIG_CHAR);
-          do_test (0, i, len - buf_addr + i, BIG_CHAR);
-
-          do_test (0, i, ~len - i, BIG_CHAR);
-          do_test (0, i, ~len + i, BIG_CHAR);
-          do_test (0, i, ~len - buf_addr - i, BIG_CHAR);
-          do_test (0, i, ~len - buf_addr + i, BIG_CHAR);
-        }
+      for (repeats = 0; repeats < 2; ++repeats)
+	{
+	  size_t align = repeats ? (getpagesize () - alignments[al_idx])
+				 : alignments[al_idx];
+	  align /= sizeof (CHAR);
+	  for (i = 0; i < 750; ++i)
+	    {
+	      do_test (align, i, SIZE_MAX, BIG_CHAR);
+
+	      do_test (align, i, SIZE_MAX - i, BIG_CHAR);
+	      do_test (align, i, i - buf_addr, BIG_CHAR);
+	      do_test (align, i, -buf_addr - i, BIG_CHAR);
+	      do_test (align, i, SIZE_MAX - buf_addr - i, BIG_CHAR);
+	      do_test (align, i, SIZE_MAX - buf_addr + i, BIG_CHAR);
+
+	      len = 0;
+	      for (j = 8 * sizeof (size_t) - 1; j; --j)
+		{
+		  len |= one << j;
+		  do_test (align, i, len, BIG_CHAR);
+		  do_test (align, i, len - i, BIG_CHAR);
+		  do_test (align, i, len + i, BIG_CHAR);
+		  do_test (align, i, len - buf_addr - i, BIG_CHAR);
+		  do_test (align, i, len - buf_addr + i, BIG_CHAR);
+
+		  do_test (align, i, ~len - i, BIG_CHAR);
+		  do_test (align, i, ~len + i, BIG_CHAR);
+		  do_test (align, i, ~len - buf_addr - i, BIG_CHAR);
+		  do_test (align, i, ~len - buf_addr + i, BIG_CHAR);
+
+		  do_test (align, i, -buf_addr, BIG_CHAR);
+		  do_test (align, i, j - buf_addr, BIG_CHAR);
+		  do_test (align, i, -buf_addr - j, BIG_CHAR);
+		}
+	    }
+	}
     }
 }
 
diff --git a/sysdeps/x86_64/multiarch/strlen-avx2.S b/sysdeps/x86_64/multiarch/strlen-avx2.S
index 376889668d..2a314f07da 100644
--- a/sysdeps/x86_64/multiarch/strlen-avx2.S
+++ b/sysdeps/x86_64/multiarch/strlen-avx2.S
@@ -542,14 +542,11 @@ L(return_vzeroupper):
 L(cross_page_less_vec):
 	tzcntl	%eax, %eax
 #  ifdef USE_AS_WCSLEN
-	/* NB: Multiply length by 4 to get byte count.  */
-	sall	$2, %esi
+	/* NB: Divide by 4 to convert from byte-count to length.  */
+	shrl	$2, %eax
 #  endif
 	cmpq	%rax, %rsi
 	cmovb	%esi, %eax
-#  ifdef USE_AS_WCSLEN
-	shrl	$2, %eax
-#  endif
 	VZEROUPPER_RETURN
 # endif