| /* strlen -- find the length of a nul-terminated string. |
| Copyright (C) 2013-2014 Free Software Foundation, Inc. |
| 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> |
| |
| .syntax unified |
| .text |
| |
| ENTRY (strlen) |
| @ r0 = start of string |
| sfi_breg r0, \ |
| ldrb r2, [\B] @ load the first byte asap |
| |
| @ To cater to long strings, we want to search through a few |
| @ characters until we reach an aligned pointer. To cater to |
| @ small strings, we don't want to start doing word operations |
| @ immediately. The compromise is a maximum of 16 bytes less |
| @ whatever is required to end with an aligned pointer. |
| @ r3 = number of characters to search in alignment loop |
| and r3, r0, #7 |
| mov r1, r0 @ Save the input pointer |
| rsb r3, r3, #15 @ 16 - 1 peeled loop iteration |
| cmp r2, #0 |
| beq 99f |
| |
| @ Loop until we find ... |
| 1: sfi_breg r0, \ |
| ldrb r2, [\B, #1]! |
| subs r3, r3, #1 @ ... the aligment point |
| it ne |
| cmpne r2, #0 @ ... or EOS |
| bne 1b |
| |
| @ Disambiguate the exit possibilites above |
| cmp r2, #0 @ Found EOS |
| beq 99f |
| add r0, r0, #1 |
| |
| @ So now we're aligned. |
| sfi_breg r0, \ |
| ldrd r2, r3, [\B], #8 |
| #ifdef ARCH_HAS_T2 |
| movw ip, #0x0101 |
| sfi_pld r0, #64 |
| movt ip, #0x0101 |
| #else |
| ldr ip, =0x01010101 |
| sfi_pld r0, #64 |
| #endif |
| |
| @ Loop searching for EOS, 8 bytes at a time. |
| @ Subtracting (unsigned saturating) from 1 for any byte means that |
| @ we get 1 for any byte that was originally zero and 0 otherwise. |
| @ Therefore we consider the lsb of each byte the "found" bit. |
| .balign 16 |
| 2: uqsub8 r2, ip, r2 @ Find EOS |
| uqsub8 r3, ip, r3 |
| sfi_pld r0, #128 @ Prefetch 2 lines ahead |
| orrs r3, r3, r2 @ Combine the two words |
| it eq |
| sfi_breg r0, \ |
| ldrdeq r2, r3, [\B], #8 |
| beq 2b |
| |
| @ Found something. Disambiguate between first and second words. |
| @ Adjust r0 to point to the word containing the match. |
| @ Adjust r2 to the found bits for the word containing the match. |
| cmp r2, #0 |
| sub r0, r0, #4 |
| ite eq |
| moveq r2, r3 |
| subne r0, r0, #4 |
| |
| @ Find the bit-offset of the match within the word. Note that the |
| @ bit result from clz will be 7 higher than "true", but we'll |
| @ immediately discard those bits converting to a byte offset. |
| #ifdef __ARMEL__ |
| rev r2, r2 @ For LE, count from the little end |
| #endif |
| clz r2, r2 |
| add r0, r0, r2, lsr #3 @ Adjust the pointer to the found byte |
| 99: |
| sub r0, r0, r1 @ Subtract input to compute length |
| bx lr |
| |
| END (strlen) |
| |
| libc_hidden_builtin_def (strlen) |