x86: Remove unnecessary overflow check from wcsnlen-sse4_1.S

No bug. The way wcsnlen will check if near the end of maxlen
is the following macro:

	mov	%r11, %rsi;	\
	subq	%rax, %rsi;	\
	andq	$-64, %rax;	\
	testq	$-64, %rsi;	\
	je	L(strnlen_ret)

Which words independently of s + maxlen overflowing. So the
second overflow check is unnecissary for correctness and
just extra overhead in the common no overflow case.

test-strlen.c, test-wcslen.c, test-strnlen.c and test-wcsnlen.c are
all passing

Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
This commit is contained in:
Noah Goldstein 2021-06-23 19:19:34 -04:00
parent bd3a2b3ed1
commit 08cbcd4dbc

View File

@ -71,19 +71,12 @@ L(n_nonzero):
suffice. */
mov %RSI_LP, %R10_LP
sar $62, %R10_LP
test %R10_LP, %R10_LP
jnz __wcslen_sse4_1
sal $2, %RSI_LP
# endif
/* Initialize long lived registers. */
add %RDI_LP, %RSI_LP
# ifdef AS_WCSLEN
/* Check for overflow again from s + maxlen * sizeof(wchar_t). */
jbe __wcslen_sse4_1
# endif
mov %RSI_LP, %R10_LP
and $-64, %R10_LP
mov %RSI_LP, %R11_LP