2013-01-23 16:32:33 +00:00
|
|
|
/* strnlen - calculate the length of a string with limit.
|
|
|
|
|
2017-01-01 00:14:16 +00:00
|
|
|
Copyright (C) 2013-2017 Free Software Foundation, Inc.
|
2013-01-23 16:32:33 +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
|
|
|
|
License along with the GNU C Library. If not, see
|
|
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
|
|
|
|
#include <sysdep.h>
|
|
|
|
|
|
|
|
/* Assumptions:
|
|
|
|
*
|
|
|
|
* ARMv8-a, AArch64
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* 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
|
|
|
|
|
|
|
|
ENTRY_ALIGN_AND_PAD (__strnlen, 6, 9)
|
Partial ILP32 support for aarch64.
* sysdeps/aarch64/crti.S: Add include of sysdep.h.
(call_weak_fn): Use PTR_REG to get correct reg name in ILP32.
* sysdeps/aarch64/dl-irel.h: Add include of sysdep.h.
(elf_irela): Use AARCH64_R macro to get correct relocation in ILP32.
* sysdeps/aarch64/dl-machine.h: Add include of sysdep.h.
(elf_machine_load_address, RTLD_START, RTLD_START_1, RTLD_START,
elf_machine_type_class, ELF_MACHINE_JMP_SLOT, elf_machine_rela,
elf_machine_lazy_rel): Add ifdef's for ILP32 support.
* sysdeps/aarch64/dl-tlsdesc.S (_dl_tlsdesc_return,
_dl_tlsdesc_return_lazy, _dl_tlsdesc_dynamic,
_dl_tlsdesc_resolve_hold): Extend pointers in ILP32, use PTR_REG
to get correct reg name for ILP32.
* sysdeps/aarch64/dl-trampoline.S (ip01): New Macro.
(RELA_SIZE): New Macro.
(_dl_runtime_resolve, _dl_runtime_profile): Use new macros and PTR_REG
to support ILP32.
* sysdeps/aarch64/jmpbuf-unwind.h (_JMPBUF_CFA_UNWINDS_ADJ): Add
cast for ILP32 mode.
* sysdeps/aarch64/memcmp.S (memcmp): Extend arg pointers for ILP32 mode.
* sysdeps/aarch64/memcpy.S (memmove, memcpy): Ditto.
* sysdeps/aarch64/memset.S (__memset): Ditto.
* sysdeps/aarch64/strchr.S (strchr): Ditto.
* sysdeps/aarch64/strchrnul.S (__strchrnul): Ditto.
* sysdeps/aarch64/strcmp.S (strcmp): Ditto.
* sysdeps/aarch64/strcpy.S (strcpy): Ditto.
* sysdeps/aarch64/strlen.S (__strlen): Ditto.
* sysdeps/aarch64/strncmp.S (strncmp): Ditto.
* sysdeps/aarch64/strnlen.S (strnlen): Ditto.
* sysdeps/aarch64/strrchr.S (strrchr): Ditto.
* sysdeps/unix/sysv/linux/aarch64/clone.S: Ditto.
* sysdeps/unix/sysv/linux/aarch64/setcontext.S (__setcontext): Ditto.
* sysdeps/unix/sysv/linux/aarch64/swapcontext.S (__swapcontext): Ditto.
* sysdeps/aarch64/__longjmp.S (__longjmp): Extend pointers in ILP32,
change PTR_MANGLE call to use register numbers instead of names.
* sysdeps/unix/sysv/linux/aarch64/getcontext.S (__getcontext): Ditto.
* sysdeps/aarch64/setjmp.S (__sigsetjmp): Extend arg pointers for
ILP32 mode, change PTR_MANGLE calls to use register numbers.
* sysdeps/aarch64/start.S (_start): Ditto.
* sysdeps/aarch64/nptl/bits/pthreadtypes.h
(__PTHREAD_RWLOCK_INT_FLAGS_SHARED): New define.
(__SIZEOF_PTHREAD_ATTR_T, __SIZEOF_PTHREAD_MUTEX_T,
__SIZEOF_PTHREAD_MUTEXATTR_T, __SIZEOF_PTHREAD_COND_T,
__SIZEOF_PTHREAD_COND_COMPAT_T, __SIZEOF_PTHREAD_CONDATTR_T,
__SIZEOF_PTHREAD_RWLOCK_T, __SIZEOF_PTHREAD_RWLOCKATTR_T,
__SIZEOF_PTHREAD_BARRIER_T, __SIZEOF_PTHREAD_BARRIERATTR_T):
Make defined values dependent on __ILP32__.
* sysdeps/aarch64/nptl/bits/semaphore.h (__SIZEOF_SEM_T): Change define.
(sem_t): Change __align type.
* sysdeps/aarch64/sysdep.h (AARCH64_R, PTR_REG, PTR_LOG_SIZE, DELOUSE,
PTR_SIZE): New Macros.
(LDST_PCREL, LDST_GLOBAL) Update to use PTR_REG.
* sysdeps/unix/sysv/linux/aarch64/bits/fcntl.h (O_LARGEFILE):
Set when in ILP32 mode.
(F_GETLK64, F_SETLK64, F_SETLKW64): Only set in LP64 mode.
* sysdeps/unix/sysv/linux/aarch64/dl-cache.h (DL_CACHE_DEFAULT_ID):
Set elf flags for ILP32.
(add_system_dir): Set ILP32 library directories.
* sysdeps/unix/sysv/linux/aarch64/init-first.c
(_libc_vdso_platform_setup): Set minimum kernel version for ILP32.
* sysdeps/unix/sysv/linux/aarch64/ldconfig.h
(SYSDEP_KNOWN_INTERPRETER_NAMES): Add ILP32 names.
* sysdeps/unix/sysv/linux/aarch64/sigcontextinfo.h (GET_PC, SET_PC):
New Macros.
* sysdeps/unix/sysv/linux/aarch64/sysdep.h: Handle ILP32 pointers.
2016-11-28 17:01:23 +00:00
|
|
|
DELOUSE (0)
|
|
|
|
DELOUSE (1)
|
|
|
|
DELOUSE (2)
|
2013-01-23 16:32:33 +00:00
|
|
|
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 critial 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)
|
|
|
|
|
|
|
|
L(hit_limit):
|
|
|
|
mov len, limit
|
|
|
|
RET
|
|
|
|
END (__strnlen)
|
2015-06-02 20:24:25 +00:00
|
|
|
libc_hidden_def (__strnlen)
|
2013-01-23 16:32:33 +00:00
|
|
|
weak_alias (__strnlen, strnlen)
|
|
|
|
libc_hidden_def (strnlen)
|