2009-04-14 05:58:16 +00:00
|
|
|
/* strrchr (str, ch) -- Return pointer to last occurrence of CH in STR.
|
2021-01-02 19:32:25 +00:00
|
|
|
Copyright (C) 2013-2021 Free Software Foundation, Inc.
|
2009-04-14 05:58:16 +00:00
|
|
|
This file is part of the GNU C Library.
|
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
Lesser General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
2012-02-09 23:18:22 +00:00
|
|
|
License along with the GNU C Library; if not, see
|
Prefer https to http for gnu.org and fsf.org URLs
Also, change sources.redhat.com to sourceware.org.
This patch was automatically generated by running the following shell
script, which uses GNU sed, and which avoids modifying files imported
from upstream:
sed -ri '
s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g
s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g
' \
$(find $(git ls-files) -prune -type f \
! -name '*.po' \
! -name 'ChangeLog*' \
! -path COPYING ! -path COPYING.LIB \
! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \
! -path manual/texinfo.tex ! -path scripts/config.guess \
! -path scripts/config.sub ! -path scripts/install-sh \
! -path scripts/mkinstalldirs ! -path scripts/move-if-change \
! -path INSTALL ! -path locale/programs/charmap-kw.h \
! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \
! '(' -name configure \
-execdir test -f configure.ac -o -f configure.in ';' ')' \
! '(' -name preconfigure \
-execdir test -f preconfigure.ac ';' ')' \
-print)
and then by running 'make dist-prepare' to regenerate files built
from the altered files, and then executing the following to cleanup:
chmod a+x sysdeps/unix/sysv/linux/riscv/configure
# Omit irrelevant whitespace and comment-only changes,
# perhaps from a slightly-different Autoconf version.
git checkout -f \
sysdeps/csky/configure \
sysdeps/hppa/configure \
sysdeps/riscv/configure \
sysdeps/unix/sysv/linux/csky/configure
# Omit changes that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines
git checkout -f \
sysdeps/powerpc/powerpc64/ppc-mcount.S \
sysdeps/unix/sysv/linux/s390/s390-64/syscall.S
# Omit change that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline
git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
|
|
|
<https://www.gnu.org/licenses/>. */
|
2009-04-14 05:58:16 +00:00
|
|
|
|
2013-09-26 16:54:09 +00:00
|
|
|
|
2009-04-14 05:58:16 +00:00
|
|
|
#include <sysdep.h>
|
|
|
|
|
2022-04-22 01:52:28 +00:00
|
|
|
#ifndef STRRCHR
|
|
|
|
# define STRRCHR strrchr
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
# define PCMPEQ pcmpeqd
|
|
|
|
# define CHAR_SIZE 4
|
|
|
|
# define PMINU pminud
|
|
|
|
#else
|
|
|
|
# define PCMPEQ pcmpeqb
|
|
|
|
# define CHAR_SIZE 1
|
|
|
|
# define PMINU pminub
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#define PAGE_SIZE 4096
|
|
|
|
#define VEC_SIZE 16
|
|
|
|
|
2009-04-14 05:58:16 +00:00
|
|
|
.text
|
2022-04-22 01:52:28 +00:00
|
|
|
ENTRY(STRRCHR)
|
|
|
|
movd %esi, %xmm0
|
2013-09-26 16:54:09 +00:00
|
|
|
movq %rdi, %rax
|
2022-04-22 01:52:28 +00:00
|
|
|
andl $(PAGE_SIZE - 1), %eax
|
|
|
|
#ifndef USE_AS_WCSRCHR
|
|
|
|
punpcklbw %xmm0, %xmm0
|
|
|
|
punpcklwd %xmm0, %xmm0
|
|
|
|
#endif
|
|
|
|
pshufd $0, %xmm0, %xmm0
|
|
|
|
cmpl $(PAGE_SIZE - VEC_SIZE), %eax
|
2013-09-26 16:54:09 +00:00
|
|
|
ja L(cross_page)
|
2022-04-22 01:52:28 +00:00
|
|
|
|
|
|
|
L(cross_page_continue):
|
|
|
|
movups (%rdi), %xmm1
|
2013-09-26 16:54:09 +00:00
|
|
|
pxor %xmm2, %xmm2
|
2022-04-22 01:52:28 +00:00
|
|
|
PCMPEQ %xmm1, %xmm2
|
|
|
|
pmovmskb %xmm2, %ecx
|
|
|
|
testl %ecx, %ecx
|
|
|
|
jz L(aligned_more)
|
|
|
|
|
|
|
|
PCMPEQ %xmm0, %xmm1
|
|
|
|
pmovmskb %xmm1, %eax
|
|
|
|
leal -1(%rcx), %edx
|
|
|
|
xorl %edx, %ecx
|
|
|
|
andl %ecx, %eax
|
|
|
|
jz L(ret0)
|
|
|
|
bsrl %eax, %eax
|
2013-09-26 16:54:09 +00:00
|
|
|
addq %rdi, %rax
|
2022-04-22 01:52:28 +00:00
|
|
|
/* We are off by 3 for wcsrchr if search CHAR is non-zero. If
|
|
|
|
search CHAR is zero we are correct. Either way `andq
|
|
|
|
-CHAR_SIZE, %rax` gets the correct result. */
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
L(ret0):
|
2013-09-26 16:54:09 +00:00
|
|
|
ret
|
2009-04-14 05:58:16 +00:00
|
|
|
|
2022-04-22 01:52:28 +00:00
|
|
|
/* Returns for first vec x1/x2 have hard coded backward search
|
|
|
|
path for earlier matches. */
|
2013-10-08 13:46:48 +00:00
|
|
|
.p2align 4
|
2022-04-22 01:52:28 +00:00
|
|
|
L(first_vec_x0_test):
|
|
|
|
PCMPEQ %xmm0, %xmm1
|
|
|
|
pmovmskb %xmm1, %eax
|
|
|
|
testl %eax, %eax
|
|
|
|
jz L(ret0)
|
|
|
|
bsrl %eax, %eax
|
|
|
|
addq %r8, %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
2013-09-26 16:54:09 +00:00
|
|
|
ret
|
2009-04-14 05:58:16 +00:00
|
|
|
|
2013-10-08 13:46:48 +00:00
|
|
|
.p2align 4
|
2022-04-22 01:52:28 +00:00
|
|
|
L(first_vec_x1):
|
|
|
|
PCMPEQ %xmm0, %xmm2
|
|
|
|
pmovmskb %xmm2, %eax
|
|
|
|
leal -1(%rcx), %edx
|
|
|
|
xorl %edx, %ecx
|
|
|
|
andl %ecx, %eax
|
|
|
|
jz L(first_vec_x0_test)
|
|
|
|
bsrl %eax, %eax
|
|
|
|
leaq (VEC_SIZE)(%rdi, %rax), %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
ret
|
2013-09-26 16:54:09 +00:00
|
|
|
|
2013-10-08 13:46:48 +00:00
|
|
|
.p2align 4
|
2022-04-22 01:52:28 +00:00
|
|
|
L(first_vec_x1_test):
|
|
|
|
PCMPEQ %xmm0, %xmm2
|
|
|
|
pmovmskb %xmm2, %eax
|
2013-09-26 16:54:09 +00:00
|
|
|
testl %eax, %eax
|
2022-04-22 01:52:28 +00:00
|
|
|
jz L(first_vec_x0_test)
|
|
|
|
bsrl %eax, %eax
|
|
|
|
leaq (VEC_SIZE)(%rdi, %rax), %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
ret
|
|
|
|
|
|
|
|
.p2align 4
|
|
|
|
L(first_vec_x2):
|
|
|
|
PCMPEQ %xmm0, %xmm3
|
|
|
|
pmovmskb %xmm3, %eax
|
|
|
|
leal -1(%rcx), %edx
|
|
|
|
xorl %edx, %ecx
|
|
|
|
andl %ecx, %eax
|
|
|
|
jz L(first_vec_x1_test)
|
|
|
|
bsrl %eax, %eax
|
|
|
|
leaq (VEC_SIZE * 2)(%rdi, %rax), %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
ret
|
|
|
|
|
|
|
|
.p2align 4
|
|
|
|
L(aligned_more):
|
|
|
|
/* Save original pointer if match was in VEC 0. */
|
|
|
|
movq %rdi, %r8
|
|
|
|
andq $-VEC_SIZE, %rdi
|
|
|
|
|
|
|
|
movaps VEC_SIZE(%rdi), %xmm2
|
|
|
|
pxor %xmm3, %xmm3
|
|
|
|
PCMPEQ %xmm2, %xmm3
|
|
|
|
pmovmskb %xmm3, %ecx
|
|
|
|
testl %ecx, %ecx
|
|
|
|
jnz L(first_vec_x1)
|
|
|
|
|
|
|
|
movaps (VEC_SIZE * 2)(%rdi), %xmm3
|
|
|
|
pxor %xmm4, %xmm4
|
|
|
|
PCMPEQ %xmm3, %xmm4
|
|
|
|
pmovmskb %xmm4, %ecx
|
|
|
|
testl %ecx, %ecx
|
|
|
|
jnz L(first_vec_x2)
|
|
|
|
|
|
|
|
addq $VEC_SIZE, %rdi
|
|
|
|
/* Save pointer again before realigning. */
|
|
|
|
movq %rdi, %rsi
|
|
|
|
andq $-(VEC_SIZE * 2), %rdi
|
|
|
|
.p2align 4
|
|
|
|
L(first_loop):
|
|
|
|
/* Do 2x VEC at a time. */
|
|
|
|
movaps (VEC_SIZE * 2)(%rdi), %xmm4
|
|
|
|
movaps (VEC_SIZE * 3)(%rdi), %xmm5
|
|
|
|
/* Since SSE2 no pminud so wcsrchr needs seperate logic for
|
|
|
|
detecting zero. Note if this is found to be a bottleneck it
|
|
|
|
may be worth adding an SSE4.1 wcsrchr implementation. */
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
movaps %xmm5, %xmm6
|
|
|
|
pxor %xmm8, %xmm8
|
|
|
|
|
|
|
|
PCMPEQ %xmm8, %xmm5
|
|
|
|
PCMPEQ %xmm4, %xmm8
|
|
|
|
por %xmm5, %xmm8
|
|
|
|
#else
|
|
|
|
movaps %xmm5, %xmm6
|
|
|
|
PMINU %xmm4, %xmm5
|
|
|
|
#endif
|
|
|
|
|
|
|
|
movaps %xmm4, %xmm9
|
|
|
|
PCMPEQ %xmm0, %xmm4
|
|
|
|
PCMPEQ %xmm0, %xmm6
|
|
|
|
movaps %xmm6, %xmm7
|
|
|
|
por %xmm4, %xmm6
|
|
|
|
#ifndef USE_AS_WCSRCHR
|
|
|
|
pxor %xmm8, %xmm8
|
|
|
|
PCMPEQ %xmm5, %xmm8
|
|
|
|
#endif
|
|
|
|
pmovmskb %xmm8, %ecx
|
|
|
|
pmovmskb %xmm6, %eax
|
|
|
|
|
|
|
|
addq $(VEC_SIZE * 2), %rdi
|
|
|
|
/* Use `addl` 1) so we can undo it with `subl` and 2) it can
|
|
|
|
macro-fuse with `jz`. */
|
|
|
|
addl %ecx, %eax
|
|
|
|
jz L(first_loop)
|
|
|
|
|
|
|
|
/* Check if there is zero match. */
|
|
|
|
testl %ecx, %ecx
|
|
|
|
jz L(second_loop_match)
|
|
|
|
|
|
|
|
/* Check if there was a match in last iteration. */
|
|
|
|
subl %ecx, %eax
|
|
|
|
jnz L(new_match)
|
|
|
|
|
|
|
|
L(first_loop_old_match):
|
|
|
|
PCMPEQ %xmm0, %xmm2
|
|
|
|
PCMPEQ %xmm0, %xmm3
|
|
|
|
pmovmskb %xmm2, %ecx
|
|
|
|
pmovmskb %xmm3, %eax
|
|
|
|
addl %eax, %ecx
|
|
|
|
jz L(first_vec_x0_test)
|
|
|
|
/* NB: We could move this shift to before the branch and save a
|
|
|
|
bit of code size / performance on the fall through. The
|
|
|
|
branch leads to the null case which generally seems hotter
|
|
|
|
than char in first 3x VEC. */
|
|
|
|
sall $16, %eax
|
|
|
|
orl %ecx, %eax
|
|
|
|
|
|
|
|
bsrl %eax, %eax
|
|
|
|
addq %rsi, %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
ret
|
|
|
|
|
|
|
|
.p2align 4
|
|
|
|
L(new_match):
|
|
|
|
pxor %xmm6, %xmm6
|
|
|
|
PCMPEQ %xmm9, %xmm6
|
|
|
|
pmovmskb %xmm6, %eax
|
|
|
|
sall $16, %ecx
|
|
|
|
orl %eax, %ecx
|
|
|
|
|
|
|
|
/* We can't reuse either of the old comparisons as since we mask
|
|
|
|
of zeros after first zero (instead of using the full
|
|
|
|
comparison) we can't gurantee no interference between match
|
|
|
|
after end of string and valid match. */
|
|
|
|
pmovmskb %xmm4, %eax
|
|
|
|
pmovmskb %xmm7, %edx
|
|
|
|
sall $16, %edx
|
|
|
|
orl %edx, %eax
|
|
|
|
|
|
|
|
leal -1(%ecx), %edx
|
|
|
|
xorl %edx, %ecx
|
|
|
|
andl %ecx, %eax
|
|
|
|
jz L(first_loop_old_match)
|
|
|
|
bsrl %eax, %eax
|
|
|
|
addq %rdi, %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
2013-09-26 16:54:09 +00:00
|
|
|
ret
|
2009-04-14 05:58:16 +00:00
|
|
|
|
2022-04-22 01:52:28 +00:00
|
|
|
/* Save minimum state for getting most recent match. We can
|
|
|
|
throw out all previous work. */
|
2013-10-08 13:46:48 +00:00
|
|
|
.p2align 4
|
2022-04-22 01:52:28 +00:00
|
|
|
L(second_loop_match):
|
|
|
|
movq %rdi, %rsi
|
|
|
|
movaps %xmm4, %xmm2
|
|
|
|
movaps %xmm7, %xmm3
|
2013-09-26 16:54:09 +00:00
|
|
|
|
2013-10-08 13:46:48 +00:00
|
|
|
.p2align 4
|
2022-04-22 01:52:28 +00:00
|
|
|
L(second_loop):
|
|
|
|
movaps (VEC_SIZE * 2)(%rdi), %xmm4
|
|
|
|
movaps (VEC_SIZE * 3)(%rdi), %xmm5
|
|
|
|
/* Since SSE2 no pminud so wcsrchr needs seperate logic for
|
|
|
|
detecting zero. Note if this is found to be a bottleneck it
|
|
|
|
may be worth adding an SSE4.1 wcsrchr implementation. */
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
movaps %xmm5, %xmm6
|
|
|
|
pxor %xmm8, %xmm8
|
|
|
|
|
|
|
|
PCMPEQ %xmm8, %xmm5
|
|
|
|
PCMPEQ %xmm4, %xmm8
|
|
|
|
por %xmm5, %xmm8
|
|
|
|
#else
|
|
|
|
movaps %xmm5, %xmm6
|
|
|
|
PMINU %xmm4, %xmm5
|
|
|
|
#endif
|
|
|
|
|
|
|
|
movaps %xmm4, %xmm9
|
|
|
|
PCMPEQ %xmm0, %xmm4
|
|
|
|
PCMPEQ %xmm0, %xmm6
|
|
|
|
movaps %xmm6, %xmm7
|
|
|
|
por %xmm4, %xmm6
|
|
|
|
#ifndef USE_AS_WCSRCHR
|
|
|
|
pxor %xmm8, %xmm8
|
|
|
|
PCMPEQ %xmm5, %xmm8
|
|
|
|
#endif
|
|
|
|
|
|
|
|
pmovmskb %xmm8, %ecx
|
|
|
|
pmovmskb %xmm6, %eax
|
|
|
|
|
|
|
|
addq $(VEC_SIZE * 2), %rdi
|
|
|
|
/* Either null term or new occurence of CHAR. */
|
|
|
|
addl %ecx, %eax
|
|
|
|
jz L(second_loop)
|
|
|
|
|
|
|
|
/* No null term so much be new occurence of CHAR. */
|
|
|
|
testl %ecx, %ecx
|
|
|
|
jz L(second_loop_match)
|
|
|
|
|
|
|
|
|
|
|
|
subl %ecx, %eax
|
|
|
|
jnz L(second_loop_new_match)
|
|
|
|
|
|
|
|
L(second_loop_old_match):
|
|
|
|
pmovmskb %xmm2, %ecx
|
|
|
|
pmovmskb %xmm3, %eax
|
|
|
|
sall $16, %eax
|
|
|
|
orl %ecx, %eax
|
|
|
|
bsrl %eax, %eax
|
|
|
|
addq %rsi, %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
2013-09-26 16:54:09 +00:00
|
|
|
ret
|
2009-04-14 05:58:16 +00:00
|
|
|
|
2013-10-08 13:46:48 +00:00
|
|
|
.p2align 4
|
2022-04-22 01:52:28 +00:00
|
|
|
L(second_loop_new_match):
|
|
|
|
pxor %xmm6, %xmm6
|
|
|
|
PCMPEQ %xmm9, %xmm6
|
|
|
|
pmovmskb %xmm6, %eax
|
|
|
|
sall $16, %ecx
|
|
|
|
orl %eax, %ecx
|
|
|
|
|
|
|
|
/* We can't reuse either of the old comparisons as since we mask
|
|
|
|
of zeros after first zero (instead of using the full
|
|
|
|
comparison) we can't gurantee no interference between match
|
|
|
|
after end of string and valid match. */
|
|
|
|
pmovmskb %xmm4, %eax
|
|
|
|
pmovmskb %xmm7, %edx
|
|
|
|
sall $16, %edx
|
|
|
|
orl %edx, %eax
|
|
|
|
|
|
|
|
leal -1(%ecx), %edx
|
|
|
|
xorl %edx, %ecx
|
|
|
|
andl %ecx, %eax
|
|
|
|
jz L(second_loop_old_match)
|
|
|
|
bsrl %eax, %eax
|
|
|
|
addq %rdi, %rax
|
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
ret
|
|
|
|
|
|
|
|
.p2align 4,, 4
|
2013-09-26 16:54:09 +00:00
|
|
|
L(cross_page):
|
2022-04-22 01:52:28 +00:00
|
|
|
movq %rdi, %rsi
|
|
|
|
andq $-VEC_SIZE, %rsi
|
|
|
|
movaps (%rsi), %xmm1
|
|
|
|
pxor %xmm2, %xmm2
|
|
|
|
PCMPEQ %xmm1, %xmm2
|
|
|
|
pmovmskb %xmm2, %edx
|
2013-09-26 16:54:09 +00:00
|
|
|
movl %edi, %ecx
|
2022-04-22 01:52:28 +00:00
|
|
|
andl $(VEC_SIZE - 1), %ecx
|
|
|
|
sarl %cl, %edx
|
|
|
|
jz L(cross_page_continue)
|
|
|
|
PCMPEQ %xmm0, %xmm1
|
|
|
|
pmovmskb %xmm1, %eax
|
|
|
|
sarl %cl, %eax
|
|
|
|
leal -1(%rdx), %ecx
|
|
|
|
xorl %edx, %ecx
|
|
|
|
andl %ecx, %eax
|
|
|
|
jz L(ret1)
|
|
|
|
bsrl %eax, %eax
|
2013-09-26 16:54:09 +00:00
|
|
|
addq %rdi, %rax
|
2022-04-22 01:52:28 +00:00
|
|
|
#ifdef USE_AS_WCSRCHR
|
|
|
|
andq $-CHAR_SIZE, %rax
|
|
|
|
#endif
|
|
|
|
L(ret1):
|
2013-09-26 16:54:09 +00:00
|
|
|
ret
|
2022-04-22 01:52:28 +00:00
|
|
|
END(STRRCHR)
|
2009-04-14 05:58:16 +00:00
|
|
|
|
2022-04-22 01:52:28 +00:00
|
|
|
#ifndef USE_AS_WCSRCHR
|
|
|
|
weak_alias (STRRCHR, rindex)
|
|
|
|
libc_hidden_builtin_def (STRRCHR)
|
|
|
|
#endif
|