forked from OSchip/llvm-project
157 lines
4.2 KiB
ArmAsm
157 lines
4.2 KiB
ArmAsm
/*
|
|
* strnlen - calculate the length of a string with limit.
|
|
*
|
|
* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
* See https://llvm.org/LICENSE.txt for license information.
|
|
* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
*/
|
|
|
|
/* Assumptions:
|
|
*
|
|
* ARMv8-a, AArch64
|
|
*/
|
|
|
|
#include "../asmdefs.h"
|
|
|
|
/* Arguments and results. */
|
|
#define srcin x0
|
|
#define len x0
|
|
#define limit x1
|
|
|
|
/* Locals and temporaries. */
|
|
#define src x2
|
|
#define data1 x3
|
|
#define data2 x4
|
|
#define data2a x5
|
|
#define has_nul1 x6
|
|
#define has_nul2 x7
|
|
#define tmp1 x8
|
|
#define tmp2 x9
|
|
#define tmp3 x10
|
|
#define tmp4 x11
|
|
#define zeroones x12
|
|
#define pos x13
|
|
#define limit_wd x14
|
|
|
|
#define REP8_01 0x0101010101010101
|
|
#define REP8_7f 0x7f7f7f7f7f7f7f7f
|
|
#define REP8_80 0x8080808080808080
|
|
|
|
.text
|
|
.p2align 6
|
|
L(start):
|
|
/* Pre-pad to ensure critical loop begins an icache line. */
|
|
.rep 7
|
|
nop
|
|
.endr
|
|
/* Put this code here to avoid wasting more space with pre-padding. */
|
|
L(hit_limit):
|
|
mov len, limit
|
|
ret
|
|
|
|
ENTRY_ALIGN (__strnlen_aarch64, 0)
|
|
cbz limit, L(hit_limit)
|
|
mov zeroones, #REP8_01
|
|
bic src, srcin, #15
|
|
ands tmp1, srcin, #15
|
|
b.ne L(misaligned)
|
|
/* 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. */
|
|
|
|
/* Start of critical section -- keep to one 64Byte cache line. */
|
|
L(loop):
|
|
ldp data1, data2, [src], #16
|
|
L(realigned):
|
|
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 L(loop)
|
|
/* End of critical section -- keep to one 64Byte cache line. */
|
|
|
|
orr tmp1, has_nul1, has_nul2
|
|
cbz tmp1, L(hit_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, L(nul_in_data2)
|
|
#ifdef __AARCH64EB__
|
|
mov data2, data1
|
|
#endif
|
|
sub len, len, #8
|
|
mov has_nul2, has_nul1
|
|
L(nul_in_data2):
|
|
#ifdef __AARCH64EB__
|
|
/* 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. */
|
|
rev data2, data2
|
|
sub tmp1, data2, zeroones
|
|
orr tmp2, data2, #REP8_7f
|
|
bic has_nul2, tmp1, tmp2
|
|
#endif
|
|
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
|
|
|
|
L(misaligned):
|
|
/* 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. */
|
|
sub limit_wd, limit, #1
|
|
neg tmp4, tmp1
|
|
cmp tmp1, #8
|
|
|
|
and tmp3, limit_wd, #15
|
|
lsr limit_wd, limit_wd, #4
|
|
mov tmp2, #~0
|
|
|
|
ldp data1, data2, [src], #16
|
|
lsl tmp4, tmp4, #3 /* Bytes beyond alignment -> bits. */
|
|
add tmp3, tmp3, tmp1
|
|
|
|
#ifdef __AARCH64EB__
|
|
/* Big-endian. Early bytes are at MSB. */
|
|
lsl tmp2, tmp2, tmp4 /* Shift (tmp1 & 63). */
|
|
#else
|
|
/* Little-endian. Early bytes are at LSB. */
|
|
lsr tmp2, tmp2, tmp4 /* Shift (tmp1 & 63). */
|
|
#endif
|
|
add limit_wd, limit_wd, tmp3, lsr #4
|
|
|
|
orr data1, data1, tmp2
|
|
orr data2a, data2, tmp2
|
|
|
|
csinv data1, data1, xzr, le
|
|
csel data2, data2, data2a, le
|
|
b L(realigned)
|
|
|
|
END (__strnlen_aarch64)
|