x86: Fix strncat-avx2.S reading past length [BZ #30065]

Occurs when `src` has no null-term.

Two cases:

1) Zero-length check is doing:
```
    test    %rdx, %rdx
    jl      L(zero_len)
```
which doesn't actually check zero (was at some point `decq` and the
flag never got updated).

The fix is just make the flag `jle` i.e:
```
    test    %rdx, %rdx
    jle     L(zero_len)
```

2) Length check in page-cross case checking if we should continue is
doing:
```
    cmpq    %r8, %rdx
    jb      L(page_cross_small)
```
which means we will continue searching for null-term if length ends at
the end of a page and there was no null-term in `src`.

The fix is to make the flag:
```
    cmpq    %r8, %rdx
    jbe     L(page_cross_small)
```

2 files changed, 26 insertions, 3 deletions

diff --git a/string/test-strncat.c b/string/test-strncat.c
index e03d329..c0cde20 100644
--- a/string/test-strncat.c
+++ b/string/test-strncat.c
@@ -28,6 +28,7 @@
 # define CHAR char
 # define UCHAR unsigned char
 # define SIMPLE_STRNCAT simple_strncat
+# define STRNLEN strnlen
 # define STRLEN strlen
 # define MEMSET memset
 # define MEMCPY memcpy
@@ -40,6 +41,7 @@
 # define CHAR wchar_t
 # define UCHAR wchar_t
 # define SIMPLE_STRNCAT simple_wcsncat
+# define STRNLEN wcsnlen
 # define STRLEN wcslen
 # define MEMSET wmemset
 # define MEMCPY wmemcpy
@@ -78,7 +80,7 @@ do_one_test (impl_t *impl, CHAR *dst, const CHAR *src, size_t n)
       return;
     }
 
-  size_t len = STRLEN (src);
+  size_t len = STRNLEN (src, n);
   if (MEMCMP (dst + k, src, len + 1 > n ? n : len + 1) != 0)
     {
       error (0, 0, "Incorrect concatenation in function %s",
@@ -96,6 +98,26 @@ do_one_test (impl_t *impl, CHAR *dst, const CHAR *src, size_t n)
 }
 
 static void
+do_test_src_no_nullterm_bz30065 (void)
+{
+  /* NB: "src does not need to be null-terminated if it contains n or more
+   * bytes." */
+  CHAR *s1, *s2;
+  size_t bound = page_size / sizeof (CHAR);
+  s1 = (CHAR *) (buf1 + BUF1PAGES * page_size);
+  s2 = (CHAR *) buf2;
+  MEMSET (s1 - bound, -1, bound);
+  for (size_t n = 0; n < bound; ++n)
+    {
+      FOR_EACH_IMPL (impl, 0)
+	{
+	  s2[0] = '\0';
+	  do_one_test (impl, s2, s1 - n, n);
+	}
+    }
+}
+
+static void
 do_test (size_t align1, size_t align2, size_t len1, size_t len2,
 	 size_t n, int max_char)
 {
@@ -372,6 +394,7 @@ test_main (void)
 
   do_random_tests ();
   do_overflow_tests ();
+  do_test_src_no_nullterm_bz30065 ();
   return ret;
 }
 
diff --git a/sysdeps/x86_64/multiarch/strncat-avx2.S b/sysdeps/x86_64/multiarch/strncat-avx2.S
index b380e8e..c2ff202 100644
--- a/sysdeps/x86_64/multiarch/strncat-avx2.S
+++ b/sysdeps/x86_64/multiarch/strncat-avx2.S
@@ -66,7 +66,7 @@ ENTRY(STRNCAT)
 	salq	$2, %rdx
 # else
 	test	%rdx, %rdx
-	jl	L(zero_len)
+	jle	L(zero_len)
 # endif
 	vpxor	%VZERO_128, %VZERO_128, %VZERO_128
 
@@ -387,7 +387,7 @@ L(page_cross):
 	subl	%esi, %r8d
 	andl	$(VEC_SIZE - 1), %r8d
 	cmpq	%r8, %rdx
-	jb	L(page_cross_small)
+	jbe	L(page_cross_small)
 
 	/* Optimizing more aggressively for space as this is very cold
 	   code. This saves 2x cache lines.  */