6934cf8a3e
Adapt the suggestions for the assembly string functions that Andrew suggested but that I didn't manage to include into the series that got applied. This includes improvements to two comments, removal of unneeded labels and moving one instruction slightly higher to contradict an explanatory comment. Suggested-by: Andrew Jones <ajones@ventanamicro.com> Signed-off-by: Heiko Stuebner <heiko.stuebner@vrull.eu> Reviewed-by: Andrew Jones <ajones@ventanamicro.com> Tested-by: Conor Dooley <conor.dooley@microchip.com> Link: https://lore.kernel.org/r/20230208225328.1636017-3-heiko@sntech.de Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
124 lines
2.0 KiB
ArmAsm
124 lines
2.0 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/asm.h>
|
|
#include <asm-generic/export.h>
|
|
#include <asm/alternative-macros.h>
|
|
#include <asm/errata_list.h>
|
|
|
|
/* int strcmp(const char *cs, const char *ct) */
|
|
SYM_FUNC_START(strcmp)
|
|
|
|
ALTERNATIVE("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, CONFIG_RISCV_ISA_ZBB)
|
|
|
|
/*
|
|
* Returns
|
|
* a0 - comparison result, value like strcmp
|
|
*
|
|
* Parameters
|
|
* a0 - string1
|
|
* a1 - string2
|
|
*
|
|
* Clobbers
|
|
* t0, t1
|
|
*/
|
|
1:
|
|
lbu t0, 0(a0)
|
|
lbu t1, 0(a1)
|
|
addi a0, a0, 1
|
|
addi a1, a1, 1
|
|
bne t0, t1, 2f
|
|
bnez t0, 1b
|
|
li a0, 0
|
|
ret
|
|
2:
|
|
/*
|
|
* strcmp only needs to return (< 0, 0, > 0) values
|
|
* not necessarily -1, 0, +1
|
|
*/
|
|
sub a0, t0, t1
|
|
ret
|
|
|
|
/*
|
|
* Variant of strcmp using the ZBB extension if available.
|
|
* The code was published as part of the bitmanip manual
|
|
* in Appendix A.
|
|
*/
|
|
#ifdef CONFIG_RISCV_ISA_ZBB
|
|
strcmp_zbb:
|
|
|
|
.option push
|
|
.option arch,+zbb
|
|
|
|
/*
|
|
* Returns
|
|
* a0 - comparison result, value like strcmp
|
|
*
|
|
* Parameters
|
|
* a0 - string1
|
|
* a1 - string2
|
|
*
|
|
* Clobbers
|
|
* t0, t1, t2, t3, t4
|
|
*/
|
|
|
|
or t2, a0, a1
|
|
li t4, -1
|
|
and t2, t2, SZREG-1
|
|
bnez t2, 3f
|
|
|
|
/* Main loop for aligned string. */
|
|
.p2align 3
|
|
1:
|
|
REG_L t0, 0(a0)
|
|
REG_L t1, 0(a1)
|
|
orc.b t3, t0
|
|
bne t3, t4, 2f
|
|
addi a0, a0, SZREG
|
|
addi a1, a1, SZREG
|
|
beq t0, t1, 1b
|
|
|
|
/*
|
|
* Words don't match, and no null byte in the first
|
|
* word. Get bytes in big-endian order and compare.
|
|
*/
|
|
#ifndef CONFIG_CPU_BIG_ENDIAN
|
|
rev8 t0, t0
|
|
rev8 t1, t1
|
|
#endif
|
|
|
|
/* Synthesize (t0 >= t1) ? 1 : -1 in a branchless sequence. */
|
|
sltu a0, t0, t1
|
|
neg a0, a0
|
|
ori a0, a0, 1
|
|
ret
|
|
|
|
2:
|
|
/*
|
|
* Found a null byte.
|
|
* If words don't match, fall back to simple loop.
|
|
*/
|
|
bne t0, t1, 3f
|
|
|
|
/* Otherwise, strings are equal. */
|
|
li a0, 0
|
|
ret
|
|
|
|
/* Simple loop for misaligned strings. */
|
|
.p2align 3
|
|
3:
|
|
lbu t0, 0(a0)
|
|
lbu t1, 0(a1)
|
|
addi a0, a0, 1
|
|
addi a1, a1, 1
|
|
bne t0, t1, 4f
|
|
bnez t0, 3b
|
|
|
|
4:
|
|
sub a0, t0, t1
|
|
ret
|
|
|
|
.option pop
|
|
#endif
|
|
SYM_FUNC_END(strcmp)
|