382 lines
8.6 KiB
ArmAsm
382 lines
8.6 KiB
ArmAsm
/* NG4memcpy.S: Niagara-4 optimized memcpy.
|
|
*
|
|
* Copyright (C) 2012 David S. Miller (davem@davemloft.net)
|
|
*/
|
|
|
|
#ifdef __KERNEL__
|
|
#include <asm/visasm.h>
|
|
#include <asm/asi.h>
|
|
#define GLOBAL_SPARE %g7
|
|
#else
|
|
#define ASI_BLK_INIT_QUAD_LDD_P 0xe2
|
|
#define FPRS_FEF 0x04
|
|
|
|
/* On T4 it is very expensive to access ASRs like %fprs and
|
|
* %asi, avoiding a read or a write can save ~50 cycles.
|
|
*/
|
|
#define FPU_ENTER \
|
|
rd %fprs, %o5; \
|
|
andcc %o5, FPRS_FEF, %g0; \
|
|
be,a,pn %icc, 999f; \
|
|
wr %g0, FPRS_FEF, %fprs; \
|
|
999:
|
|
|
|
#ifdef MEMCPY_DEBUG
|
|
#define VISEntryHalf FPU_ENTER; \
|
|
clr %g1; clr %g2; clr %g3; clr %g5; subcc %g0, %g0, %g0;
|
|
#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs
|
|
#else
|
|
#define VISEntryHalf FPU_ENTER
|
|
#define VISExitHalf and %o5, FPRS_FEF, %o5; wr %o5, 0x0, %fprs
|
|
#endif
|
|
|
|
#define GLOBAL_SPARE %g5
|
|
#endif
|
|
|
|
#ifndef STORE_ASI
|
|
#ifndef SIMULATE_NIAGARA_ON_NON_NIAGARA
|
|
#define STORE_ASI ASI_BLK_INIT_QUAD_LDD_P
|
|
#else
|
|
#define STORE_ASI 0x80 /* ASI_P */
|
|
#endif
|
|
#endif
|
|
|
|
#if !defined(EX_LD) && !defined(EX_ST)
|
|
#define NON_USER_COPY
|
|
#endif
|
|
|
|
#ifndef EX_LD
|
|
#define EX_LD(x) x
|
|
#endif
|
|
#ifndef EX_LD_FP
|
|
#define EX_LD_FP(x) x
|
|
#endif
|
|
|
|
#ifndef EX_ST
|
|
#define EX_ST(x) x
|
|
#endif
|
|
#ifndef EX_ST_FP
|
|
#define EX_ST_FP(x) x
|
|
#endif
|
|
|
|
#ifndef EX_RETVAL
|
|
#define EX_RETVAL(x) x
|
|
#endif
|
|
|
|
#ifndef LOAD
|
|
#define LOAD(type,addr,dest) type [addr], dest
|
|
#endif
|
|
|
|
#ifndef STORE
|
|
#ifndef MEMCPY_DEBUG
|
|
#define STORE(type,src,addr) type src, [addr]
|
|
#else
|
|
#define STORE(type,src,addr) type##a src, [addr] %asi
|
|
#endif
|
|
#endif
|
|
|
|
#ifndef STORE_INIT
|
|
#define STORE_INIT(src,addr) stxa src, [addr] STORE_ASI
|
|
#endif
|
|
|
|
#ifndef FUNC_NAME
|
|
#define FUNC_NAME NG4memcpy
|
|
#endif
|
|
#ifndef PREAMBLE
|
|
#define PREAMBLE
|
|
#endif
|
|
|
|
#ifndef XCC
|
|
#define XCC xcc
|
|
#endif
|
|
|
|
.register %g2,#scratch
|
|
.register %g3,#scratch
|
|
|
|
.text
|
|
.align 64
|
|
|
|
.globl FUNC_NAME
|
|
.type FUNC_NAME,#function
|
|
FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
|
|
#ifdef MEMCPY_DEBUG
|
|
wr %g0, 0x80, %asi
|
|
#endif
|
|
srlx %o2, 31, %g2
|
|
cmp %g2, 0
|
|
tne %XCC, 5
|
|
PREAMBLE
|
|
mov %o0, %o3
|
|
brz,pn %o2, .Lexit
|
|
cmp %o2, 3
|
|
ble,pn %icc, .Ltiny
|
|
cmp %o2, 19
|
|
ble,pn %icc, .Lsmall
|
|
or %o0, %o1, %g2
|
|
cmp %o2, 128
|
|
bl,pn %icc, .Lmedium
|
|
nop
|
|
|
|
.Llarge:/* len >= 0x80 */
|
|
/* First get dest 8 byte aligned. */
|
|
sub %g0, %o0, %g1
|
|
and %g1, 0x7, %g1
|
|
brz,pt %g1, 51f
|
|
sub %o2, %g1, %o2
|
|
|
|
1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
|
|
add %o1, 1, %o1
|
|
subcc %g1, 1, %g1
|
|
add %o0, 1, %o0
|
|
bne,pt %icc, 1b
|
|
EX_ST(STORE(stb, %g2, %o0 - 0x01))
|
|
|
|
51: LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x0c0, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x100, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x140, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x180, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x1c0, #n_reads_strong)
|
|
LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
|
|
|
|
/* Check if we can use the straight fully aligned
|
|
* loop, or we require the alignaddr/faligndata variant.
|
|
*/
|
|
andcc %o1, 0x7, %o5
|
|
bne,pn %icc, .Llarge_src_unaligned
|
|
sub %g0, %o0, %g1
|
|
|
|
/* Legitimize the use of initializing stores by getting dest
|
|
* to be 64-byte aligned.
|
|
*/
|
|
and %g1, 0x3f, %g1
|
|
brz,pt %g1, .Llarge_aligned
|
|
sub %o2, %g1, %o2
|
|
|
|
1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
|
|
add %o1, 8, %o1
|
|
subcc %g1, 8, %g1
|
|
add %o0, 8, %o0
|
|
bne,pt %icc, 1b
|
|
EX_ST(STORE(stx, %g2, %o0 - 0x08))
|
|
|
|
.Llarge_aligned:
|
|
/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
|
|
andn %o2, 0x3f, %o4
|
|
sub %o2, %o4, %o2
|
|
|
|
1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
|
|
add %o1, 0x40, %o1
|
|
EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
|
|
subcc %o4, 0x40, %o4
|
|
EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
|
|
EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
|
|
EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
|
|
EX_ST(STORE_INIT(%g1, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_ST(STORE_INIT(%g2, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
|
|
EX_ST(STORE_INIT(%g3, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
|
|
EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
|
|
EX_ST(STORE_INIT(%o5, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_ST(STORE_INIT(%g2, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_ST(STORE_INIT(%g3, %o0))
|
|
add %o0, 0x08, %o0
|
|
EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
|
|
add %o0, 0x08, %o0
|
|
bne,pt %icc, 1b
|
|
LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
|
|
|
|
membar #StoreLoad | #StoreStore
|
|
|
|
brz,pn %o2, .Lexit
|
|
cmp %o2, 19
|
|
ble,pn %icc, .Lsmall_unaligned
|
|
nop
|
|
ba,a,pt %icc, .Lmedium_noprefetch
|
|
|
|
.Lexit: retl
|
|
mov EX_RETVAL(%o3), %o0
|
|
|
|
.Llarge_src_unaligned:
|
|
#ifdef NON_USER_COPY
|
|
VISEntryHalfFast(.Lmedium_vis_entry_fail)
|
|
#else
|
|
VISEntryHalf
|
|
#endif
|
|
andn %o2, 0x3f, %o4
|
|
sub %o2, %o4, %o2
|
|
alignaddr %o1, %g0, %g1
|
|
add %o1, %o4, %o1
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
|
|
1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
|
|
subcc %o4, 0x40, %o4
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
|
|
faligndata %f0, %f2, %f16
|
|
EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
|
|
faligndata %f2, %f4, %f18
|
|
add %g1, 0x40, %g1
|
|
faligndata %f4, %f6, %f20
|
|
faligndata %f6, %f8, %f22
|
|
faligndata %f8, %f10, %f24
|
|
faligndata %f10, %f12, %f26
|
|
faligndata %f12, %f14, %f28
|
|
faligndata %f14, %f0, %f30
|
|
EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
|
|
EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
|
|
EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
|
|
EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
|
|
EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
|
|
EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
|
|
EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
|
|
EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
|
|
add %o0, 0x40, %o0
|
|
bne,pt %icc, 1b
|
|
LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
|
|
#ifdef NON_USER_COPY
|
|
VISExitHalfFast
|
|
#else
|
|
VISExitHalf
|
|
#endif
|
|
brz,pn %o2, .Lexit
|
|
cmp %o2, 19
|
|
ble,pn %icc, .Lsmall_unaligned
|
|
nop
|
|
ba,a,pt %icc, .Lmedium_unaligned
|
|
|
|
#ifdef NON_USER_COPY
|
|
.Lmedium_vis_entry_fail:
|
|
or %o0, %o1, %g2
|
|
#endif
|
|
.Lmedium:
|
|
LOAD(prefetch, %o1 + 0x40, #n_reads_strong)
|
|
andcc %g2, 0x7, %g0
|
|
bne,pn %icc, .Lmedium_unaligned
|
|
nop
|
|
.Lmedium_noprefetch:
|
|
andncc %o2, 0x20 - 1, %o5
|
|
be,pn %icc, 2f
|
|
sub %o2, %o5, %o2
|
|
1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
|
|
EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
|
|
EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
|
|
EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
|
|
add %o1, 0x20, %o1
|
|
subcc %o5, 0x20, %o5
|
|
EX_ST(STORE(stx, %g1, %o0 + 0x00))
|
|
EX_ST(STORE(stx, %g2, %o0 + 0x08))
|
|
EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
|
|
EX_ST(STORE(stx, %o4, %o0 + 0x18))
|
|
bne,pt %icc, 1b
|
|
add %o0, 0x20, %o0
|
|
2: andcc %o2, 0x18, %o5
|
|
be,pt %icc, 3f
|
|
sub %o2, %o5, %o2
|
|
1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
|
|
add %o1, 0x08, %o1
|
|
add %o0, 0x08, %o0
|
|
subcc %o5, 0x08, %o5
|
|
bne,pt %icc, 1b
|
|
EX_ST(STORE(stx, %g1, %o0 - 0x08))
|
|
3: brz,pt %o2, .Lexit
|
|
cmp %o2, 0x04
|
|
bl,pn %icc, .Ltiny
|
|
nop
|
|
EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
|
|
add %o1, 0x04, %o1
|
|
add %o0, 0x04, %o0
|
|
subcc %o2, 0x04, %o2
|
|
bne,pn %icc, .Ltiny
|
|
EX_ST(STORE(stw, %g1, %o0 - 0x04))
|
|
ba,a,pt %icc, .Lexit
|
|
.Lmedium_unaligned:
|
|
/* First get dest 8 byte aligned. */
|
|
sub %g0, %o0, %g1
|
|
and %g1, 0x7, %g1
|
|
brz,pt %g1, 2f
|
|
sub %o2, %g1, %o2
|
|
|
|
1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
|
|
add %o1, 1, %o1
|
|
subcc %g1, 1, %g1
|
|
add %o0, 1, %o0
|
|
bne,pt %icc, 1b
|
|
EX_ST(STORE(stb, %g2, %o0 - 0x01))
|
|
2:
|
|
and %o1, 0x7, %g1
|
|
brz,pn %g1, .Lmedium_noprefetch
|
|
sll %g1, 3, %g1
|
|
mov 64, %g2
|
|
sub %g2, %g1, %g2
|
|
andn %o1, 0x7, %o1
|
|
EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
|
|
sllx %o4, %g1, %o4
|
|
andn %o2, 0x08 - 1, %o5
|
|
sub %o2, %o5, %o2
|
|
1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
|
|
add %o1, 0x08, %o1
|
|
subcc %o5, 0x08, %o5
|
|
srlx %g3, %g2, GLOBAL_SPARE
|
|
or GLOBAL_SPARE, %o4, GLOBAL_SPARE
|
|
EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
|
|
add %o0, 0x08, %o0
|
|
bne,pt %icc, 1b
|
|
sllx %g3, %g1, %o4
|
|
srl %g1, 3, %g1
|
|
add %o1, %g1, %o1
|
|
brz,pn %o2, .Lexit
|
|
nop
|
|
ba,pt %icc, .Lsmall_unaligned
|
|
|
|
.Ltiny:
|
|
EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
|
|
subcc %o2, 1, %o2
|
|
be,pn %icc, .Lexit
|
|
EX_ST(STORE(stb, %g1, %o0 + 0x00))
|
|
EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
|
|
subcc %o2, 1, %o2
|
|
be,pn %icc, .Lexit
|
|
EX_ST(STORE(stb, %g1, %o0 + 0x01))
|
|
EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
|
|
ba,pt %icc, .Lexit
|
|
EX_ST(STORE(stb, %g1, %o0 + 0x02))
|
|
|
|
.Lsmall:
|
|
andcc %g2, 0x3, %g0
|
|
bne,pn %icc, .Lsmall_unaligned
|
|
andn %o2, 0x4 - 1, %o5
|
|
sub %o2, %o5, %o2
|
|
1:
|
|
EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
|
|
add %o1, 0x04, %o1
|
|
subcc %o5, 0x04, %o5
|
|
add %o0, 0x04, %o0
|
|
bne,pt %icc, 1b
|
|
EX_ST(STORE(stw, %g1, %o0 - 0x04))
|
|
brz,pt %o2, .Lexit
|
|
nop
|
|
ba,a,pt %icc, .Ltiny
|
|
|
|
.Lsmall_unaligned:
|
|
1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
|
|
add %o1, 1, %o1
|
|
add %o0, 1, %o0
|
|
subcc %o2, 1, %o2
|
|
bne,pt %icc, 1b
|
|
EX_ST(STORE(stb, %g1, %o0 - 0x01))
|
|
ba,a,pt %icc, .Lexit
|
|
.size FUNC_NAME, .-FUNC_NAME
|