arm64: lib: Implement optimized memset routine
This patch, based on Linaro's Cortex Strings library, improves the performance of the assembly optimized memset() function. Signed-off-by: Zhichang Yuan <zhichang.yuan@linaro.org> Signed-off-by: Deepak Saxena <dsaxena@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This commit is contained in:
zhichang.yuan
Catalin Marinas
parent
280adc1951
commit
b29a51fe0e
|
|
@ -1,5 +1,13 @@
|
|||
/*
|
||||
* Copyright (C) 2013 ARM Ltd.
|
||||
* Copyright (C) 2013 Linaro.
|
||||
*
|
||||
* This code is based on glibc cortex strings work originally authored by Linaro
|
||||
* and re-licensed under GPLv2 for the Linux kernel. The original code can
|
||||
* be found @
|
||||
*
|
||||
* http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
|
||||
* files/head:/src/aarch64/
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License version 2 as
|
||||
|
|
@ -16,6 +24,7 @@
|
|||
|
||||
#include <linux/linkage.h>
|
||||
#include <asm/assembler.h>
|
||||
#include <asm/cache.h>
|
||||
|
||||
/*
|
||||
* Fill in the buffer with character c (alignment handled by the hardware)
|
||||
|
|
@ -27,27 +36,181 @@
|
|||
* Returns:
|
||||
* x0 - buf
|
||||
*/
|
||||
|
||||
dstin .req x0
|
||||
val .req w1
|
||||
count .req x2
|
||||
tmp1 .req x3
|
||||
tmp1w .req w3
|
||||
tmp2 .req x4
|
||||
tmp2w .req w4
|
||||
zva_len_x .req x5
|
||||
zva_len .req w5
|
||||
zva_bits_x .req x6
|
||||
|
||||
A_l .req x7
|
||||
A_lw .req w7
|
||||
dst .req x8
|
||||
tmp3w .req w9
|
||||
tmp3 .req x9
|
||||
|
||||
ENTRY(memset)
|
||||
mov x4, x0
|
||||
and w1, w1, #0xff
|
||||
orr w1, w1, w1, lsl #8
|
||||
orr w1, w1, w1, lsl #16
|
||||
orr x1, x1, x1, lsl #32
|
||||
subs x2, x2, #8
|
||||
b.mi 2f
|
||||
1: str x1, [x4], #8
|
||||
subs x2, x2, #8
|
||||
b.pl 1b
|
||||
2: adds x2, x2, #4
|
||||
b.mi 3f
|
||||
sub x2, x2, #4
|
||||
str w1, [x4], #4
|
||||
3: adds x2, x2, #2
|
||||
b.mi 4f
|
||||
sub x2, x2, #2
|
||||
strh w1, [x4], #2
|
||||
4: adds x2, x2, #1
|
||||
b.mi 5f
|
||||
strb w1, [x4]
|
||||
5: ret
|
||||
mov dst, dstin /* Preserve return value. */
|
||||
and A_lw, val, #255
|
||||
orr A_lw, A_lw, A_lw, lsl #8
|
||||
orr A_lw, A_lw, A_lw, lsl #16
|
||||
orr A_l, A_l, A_l, lsl #32
|
||||
|
||||
cmp count, #15
|
||||
b.hi .Lover16_proc
|
||||
/*All store maybe are non-aligned..*/
|
||||
tbz count, #3, 1f
|
||||
str A_l, [dst], #8
|
||||
1:
|
||||
tbz count, #2, 2f
|
||||
str A_lw, [dst], #4
|
||||
2:
|
||||
tbz count, #1, 3f
|
||||
strh A_lw, [dst], #2
|
||||
3:
|
||||
tbz count, #0, 4f
|
||||
strb A_lw, [dst]
|
||||
4:
|
||||
ret
|
||||
|
||||
.Lover16_proc:
|
||||
/*Whether the start address is aligned with 16.*/
|
||||
neg tmp2, dst
|
||||
ands tmp2, tmp2, #15
|
||||
b.eq .Laligned
|
||||
/*
|
||||
* The count is not less than 16, we can use stp to store the start 16 bytes,
|
||||
* then adjust the dst aligned with 16.This process will make the current
|
||||
* memory address at alignment boundary.
|
||||
*/
|
||||
stp A_l, A_l, [dst] /*non-aligned store..*/
|
||||
/*make the dst aligned..*/
|
||||
sub count, count, tmp2
|
||||
add dst, dst, tmp2
|
||||
|
||||
.Laligned:
|
||||
cbz A_l, .Lzero_mem
|
||||
|
||||
.Ltail_maybe_long:
|
||||
cmp count, #64
|
||||
b.ge .Lnot_short
|
||||
.Ltail63:
|
||||
ands tmp1, count, #0x30
|
||||
b.eq 3f
|
||||
cmp tmp1w, #0x20
|
||||
b.eq 1f
|
||||
b.lt 2f
|
||||
stp A_l, A_l, [dst], #16
|
||||
1:
|
||||
stp A_l, A_l, [dst], #16
|
||||
2:
|
||||
stp A_l, A_l, [dst], #16
|
||||
/*
|
||||
* The last store length is less than 16,use stp to write last 16 bytes.
|
||||
* It will lead some bytes written twice and the access is non-aligned.
|
||||
*/
|
||||
3:
|
||||
ands count, count, #15
|
||||
cbz count, 4f
|
||||
add dst, dst, count
|
||||
stp A_l, A_l, [dst, #-16] /* Repeat some/all of last store. */
|
||||
4:
|
||||
ret
|
||||
|
||||
/*
|
||||
* Critical loop. Start at a new cache line boundary. Assuming
|
||||
* 64 bytes per line, this ensures the entire loop is in one line.
|
||||
*/
|
||||
.p2align L1_CACHE_SHIFT
|
||||
.Lnot_short:
|
||||
sub dst, dst, #16/* Pre-bias. */
|
||||
sub count, count, #64
|
||||
1:
|
||||
stp A_l, A_l, [dst, #16]
|
||||
stp A_l, A_l, [dst, #32]
|
||||
stp A_l, A_l, [dst, #48]
|
||||
stp A_l, A_l, [dst, #64]!
|
||||
subs count, count, #64
|
||||
b.ge 1b
|
||||
tst count, #0x3f
|
||||
add dst, dst, #16
|
||||
b.ne .Ltail63
|
||||
.Lexitfunc:
|
||||
ret
|
||||
|
||||
/*
|
||||
* For zeroing memory, check to see if we can use the ZVA feature to
|
||||
* zero entire 'cache' lines.
|
||||
*/
|
||||
.Lzero_mem:
|
||||
cmp count, #63
|
||||
b.le .Ltail63
|
||||
/*
|
||||
* For zeroing small amounts of memory, it's not worth setting up
|
||||
* the line-clear code.
|
||||
*/
|
||||
cmp count, #128
|
||||
b.lt .Lnot_short /*count is at least 128 bytes*/
|
||||
|
||||
mrs tmp1, dczid_el0
|
||||
tbnz tmp1, #4, .Lnot_short
|
||||
mov tmp3w, #4
|
||||
and zva_len, tmp1w, #15 /* Safety: other bits reserved. */
|
||||
lsl zva_len, tmp3w, zva_len
|
||||
|
||||
ands tmp3w, zva_len, #63
|
||||
/*
|
||||
* ensure the zva_len is not less than 64.
|
||||
* It is not meaningful to use ZVA if the block size is less than 64.
|
||||
*/
|
||||
b.ne .Lnot_short
|
||||
.Lzero_by_line:
|
||||
/*
|
||||
* Compute how far we need to go to become suitably aligned. We're
|
||||
* already at quad-word alignment.
|
||||
*/
|
||||
cmp count, zva_len_x
|
||||
b.lt .Lnot_short /* Not enough to reach alignment. */
|
||||
sub zva_bits_x, zva_len_x, #1
|
||||
neg tmp2, dst
|
||||
ands tmp2, tmp2, zva_bits_x
|
||||
b.eq 2f /* Already aligned. */
|
||||
/* Not aligned, check that there's enough to copy after alignment.*/
|
||||
sub tmp1, count, tmp2
|
||||
/*
|
||||
* grantee the remain length to be ZVA is bigger than 64,
|
||||
* avoid to make the 2f's process over mem range.*/
|
||||
cmp tmp1, #64
|
||||
ccmp tmp1, zva_len_x, #8, ge /* NZCV=0b1000 */
|
||||
b.lt .Lnot_short
|
||||
/*
|
||||
* We know that there's at least 64 bytes to zero and that it's safe
|
||||
* to overrun by 64 bytes.
|
||||
*/
|
||||
mov count, tmp1
|
||||
1:
|
||||
stp A_l, A_l, [dst]
|
||||
stp A_l, A_l, [dst, #16]
|
||||
stp A_l, A_l, [dst, #32]
|
||||
subs tmp2, tmp2, #64
|
||||
stp A_l, A_l, [dst, #48]
|
||||
add dst, dst, #64
|
||||
b.ge 1b
|
||||
/* We've overrun a bit, so adjust dst downwards.*/
|
||||
add dst, dst, tmp2
|
||||
2:
|
||||
sub count, count, zva_len_x
|
||||
3:
|
||||
dc zva, dst
|
||||
add dst, dst, zva_len_x
|
||||
subs count, count, zva_len_x
|
||||
b.ge 3b
|
||||
ands count, count, zva_bits_x
|
||||
b.ne .Ltail_maybe_long
|
||||
ret
|
||||
ENDPROC(memset)
|
||||
|
|
|
|||
Loading…
Reference in New Issue