/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 ARM Ltd. * Copyright (C) 2013 Linaro. * * This code is based on glibc cortex strings work originally authored by Linaro * be found @ * * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ * files/head:/src/aarch64/
*/
SYM_FUNC_START(__pi_strnlen)
cbz limit, .Lhit_limit
mov zeroones, #REP8_01
bic src, srcin, #15
ands tmp1, srcin, #15
b.ne .Lmisaligned /* Calculate the number of full and partial words -1. */ sub limit_wd, limit, #1/* Limit != 0, so no underflow. */
lsr limit_wd, limit_wd, #4/* Convert to Qwords. */
/* * NUL detection works on the principle that (X - 1) & (~X) & 0x80 * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and * can be done in parallel across the entire word.
*/ /* * The inner loop deals with two Dwords at a time. This has a * slightly higher start-up cost, but we should win quite quickly, * especially on cores with a high number of issue slots per * cycle, as we get much better parallelism out of the operations.
*/
.Lloop:
ldp data1, data2, [src], #16
.Lrealigned: sub tmp1, data1, zeroones
orr tmp2, data1, #REP8_7f sub tmp3, data2, zeroones
orr tmp4, data2, #REP8_7f
bic has_nul1, tmp1, tmp2
bic has_nul2, tmp3, tmp4
subs limit_wd, limit_wd, #1
orr tmp1, has_nul1, has_nul2
ccmp tmp1, #0, #0, pl /* NZCV = 0000 */
b.eq .Lloop
cbz tmp1, .Lhit_limit /* No null in final Qword. */
/* * We know there's a null in the final Qword. The easiest thing * to do now is work out the length of the string and return * MIN (len, limit).
*/ sub len, src, srcin
cbz has_nul1, .Lnul_in_data2
CPU_BE( mov data2, data1 ) /*perpare data to re-calculate the syndrome*/
sub len, len, #8
mov has_nul2, has_nul1
.Lnul_in_data2: /* * For big-endian, carry propagation (if the final byte in the * string is 0x01) means we cannot use has_nul directly. The * easiest way to get the correct byte is to byte-swap the data * and calculate the syndrome a second time.
*/
CPU_BE( rev data2, data2 )
CPU_BE( sub tmp1, data2, zeroones )
CPU_BE( orr tmp2, data2, #REP8_7f )
CPU_BE( bic has_nul2, tmp1, tmp2 )
sub len, len, #8
rev has_nul2, has_nul2
clz pos, has_nul2
add len, len, pos, lsr #3/* Bits to bytes. */
cmp len, limit
csel len, len, limit, ls /* Return the lower value. */
ret
.Lmisaligned: /* * Deal with a partial first word. * We're doing two things in parallel here; * 1) Calculate the number of words (but avoiding overflow if * limit is near ULONG_MAX) - to do this we need to work out * limit + tmp1 - 1 as a 65-bit value before shifting it; * 2) Load and mask the initial data words - we force the bytes * before the ones we are interested in to 0xff - this ensures * early bytes will not hit any zero detection.
*/
ldp data1, data2, [src], #16
sub limit_wd, limit, #1
and tmp3, limit_wd, #15
lsr limit_wd, limit_wd, #4
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.