forge/linux-pinenote
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
linux-pinenote/arch/sparc/lib/xor.S

637 lines
16 KiB
ArmAsm
Raw Normal View History

Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
/*
* arch/sparc64/lib/xor.S
*
* High speed xor_block operation for RAID4/5 utilizing the
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
* UltraSparc Visual Instruction Set and Niagara store-init/twin-load.
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
*
* Copyright (C) 1997, 1999 Jakub Jelinek (jj@ultra.linux.cz)
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
* Copyright (C) 2006 David S. Miller <davem@davemloft.net>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
*/
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
#include <linux/linkage.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
#include <asm/visasm.h>
#include <asm/asi.h>
#include <asm/dcu.h>
#include <asm/spitfire.h>
/*
* Requirements:
* !(((long)dest | (long)sourceN) & (64 - 1)) &&
* !(len & 127) && len >= 256
*/
.text
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
/* VIS versions. */
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_vis_2)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
rd %fprs, %o5
andcc %o5, FPRS_FEF|FPRS_DU, %g0
be,pt %icc, 0f
sethi %hi(VISenter), %g1
jmpl %g1 + %lo(VISenter), %g7
add %g7, 8, %g7
0: wr %g0, FPRS_FEF, %fprs
rd %asi, %g1
wr %g0, ASI_BLK_P, %asi
membar #LoadStore|#StoreLoad|#StoreStore
sub %o0, 128, %o0
ldda [%o1] %asi, %f0
ldda [%o2] %asi, %f16
2: ldda [%o1 + 64] %asi, %f32
fxor %f0, %f16, %f16
fxor %f2, %f18, %f18
fxor %f4, %f20, %f20
fxor %f6, %f22, %f22
fxor %f8, %f24, %f24
fxor %f10, %f26, %f26
fxor %f12, %f28, %f28
fxor %f14, %f30, %f30
stda %f16, [%o1] %asi
ldda [%o2 + 64] %asi, %f48
ldda [%o1 + 128] %asi, %f0
fxor %f32, %f48, %f48
fxor %f34, %f50, %f50
add %o1, 128, %o1
fxor %f36, %f52, %f52
add %o2, 128, %o2
fxor %f38, %f54, %f54
subcc %o0, 128, %o0
fxor %f40, %f56, %f56
fxor %f42, %f58, %f58
fxor %f44, %f60, %f60
fxor %f46, %f62, %f62
stda %f48, [%o1 - 64] %asi
bne,pt %xcc, 2b
ldda [%o2] %asi, %f16
ldda [%o1 + 64] %asi, %f32
fxor %f0, %f16, %f16
fxor %f2, %f18, %f18
fxor %f4, %f20, %f20
fxor %f6, %f22, %f22
fxor %f8, %f24, %f24
fxor %f10, %f26, %f26
fxor %f12, %f28, %f28
fxor %f14, %f30, %f30
stda %f16, [%o1] %asi
ldda [%o2 + 64] %asi, %f48
membar #Sync
fxor %f32, %f48, %f48
fxor %f34, %f50, %f50
fxor %f36, %f52, %f52
fxor %f38, %f54, %f54
fxor %f40, %f56, %f56
fxor %f42, %f58, %f58
fxor %f44, %f60, %f60
fxor %f46, %f62, %f62
stda %f48, [%o1 + 64] %asi
membar #Sync|#StoreStore|#StoreLoad
wr %g1, %g0, %asi
retl
wr %g0, 0, %fprs
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_vis_2)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_vis_3)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
rd %fprs, %o5
andcc %o5, FPRS_FEF|FPRS_DU, %g0
be,pt %icc, 0f
sethi %hi(VISenter), %g1
jmpl %g1 + %lo(VISenter), %g7
add %g7, 8, %g7
0: wr %g0, FPRS_FEF, %fprs
rd %asi, %g1
wr %g0, ASI_BLK_P, %asi
membar #LoadStore|#StoreLoad|#StoreStore
sub %o0, 64, %o0
ldda [%o1] %asi, %f0
ldda [%o2] %asi, %f16
3: ldda [%o3] %asi, %f32
fxor %f0, %f16, %f48
fxor %f2, %f18, %f50
add %o1, 64, %o1
fxor %f4, %f20, %f52
fxor %f6, %f22, %f54
add %o2, 64, %o2
fxor %f8, %f24, %f56
fxor %f10, %f26, %f58
fxor %f12, %f28, %f60
fxor %f14, %f30, %f62
ldda [%o1] %asi, %f0
fxor %f48, %f32, %f48
fxor %f50, %f34, %f50
fxor %f52, %f36, %f52
fxor %f54, %f38, %f54
add %o3, 64, %o3
fxor %f56, %f40, %f56
fxor %f58, %f42, %f58
subcc %o0, 64, %o0
fxor %f60, %f44, %f60
fxor %f62, %f46, %f62
stda %f48, [%o1 - 64] %asi
bne,pt %xcc, 3b
ldda [%o2] %asi, %f16
ldda [%o3] %asi, %f32
fxor %f0, %f16, %f48
fxor %f2, %f18, %f50
fxor %f4, %f20, %f52
fxor %f6, %f22, %f54
fxor %f8, %f24, %f56
fxor %f10, %f26, %f58
fxor %f12, %f28, %f60
fxor %f14, %f30, %f62
membar #Sync
fxor %f48, %f32, %f48
fxor %f50, %f34, %f50
fxor %f52, %f36, %f52
fxor %f54, %f38, %f54
fxor %f56, %f40, %f56
fxor %f58, %f42, %f58
fxor %f60, %f44, %f60
fxor %f62, %f46, %f62
stda %f48, [%o1] %asi
membar #Sync|#StoreStore|#StoreLoad
wr %g1, %g0, %asi
retl
wr %g0, 0, %fprs
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_vis_3)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_vis_4)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
rd %fprs, %o5
andcc %o5, FPRS_FEF|FPRS_DU, %g0
be,pt %icc, 0f
sethi %hi(VISenter), %g1
jmpl %g1 + %lo(VISenter), %g7
add %g7, 8, %g7
0: wr %g0, FPRS_FEF, %fprs
rd %asi, %g1
wr %g0, ASI_BLK_P, %asi
membar #LoadStore|#StoreLoad|#StoreStore
sub %o0, 64, %o0
ldda [%o1] %asi, %f0
ldda [%o2] %asi, %f16
4: ldda [%o3] %asi, %f32
fxor %f0, %f16, %f16
fxor %f2, %f18, %f18
add %o1, 64, %o1
fxor %f4, %f20, %f20
fxor %f6, %f22, %f22
add %o2, 64, %o2
fxor %f8, %f24, %f24
fxor %f10, %f26, %f26
fxor %f12, %f28, %f28
fxor %f14, %f30, %f30
ldda [%o4] %asi, %f48
fxor %f16, %f32, %f32
fxor %f18, %f34, %f34
fxor %f20, %f36, %f36
fxor %f22, %f38, %f38
add %o3, 64, %o3
fxor %f24, %f40, %f40
fxor %f26, %f42, %f42
fxor %f28, %f44, %f44
fxor %f30, %f46, %f46
ldda [%o1] %asi, %f0
fxor %f32, %f48, %f48
fxor %f34, %f50, %f50
fxor %f36, %f52, %f52
add %o4, 64, %o4
fxor %f38, %f54, %f54
fxor %f40, %f56, %f56
fxor %f42, %f58, %f58
subcc %o0, 64, %o0
fxor %f44, %f60, %f60
fxor %f46, %f62, %f62
stda %f48, [%o1 - 64] %asi
bne,pt %xcc, 4b
ldda [%o2] %asi, %f16
ldda [%o3] %asi, %f32
fxor %f0, %f16, %f16
fxor %f2, %f18, %f18
fxor %f4, %f20, %f20
fxor %f6, %f22, %f22
fxor %f8, %f24, %f24
fxor %f10, %f26, %f26
fxor %f12, %f28, %f28
fxor %f14, %f30, %f30
ldda [%o4] %asi, %f48
fxor %f16, %f32, %f32
fxor %f18, %f34, %f34
fxor %f20, %f36, %f36
fxor %f22, %f38, %f38
fxor %f24, %f40, %f40
fxor %f26, %f42, %f42
fxor %f28, %f44, %f44
fxor %f30, %f46, %f46
membar #Sync
fxor %f32, %f48, %f48
fxor %f34, %f50, %f50
fxor %f36, %f52, %f52
fxor %f38, %f54, %f54
fxor %f40, %f56, %f56
fxor %f42, %f58, %f58
fxor %f44, %f60, %f60
fxor %f46, %f62, %f62
stda %f48, [%o1] %asi
membar #Sync|#StoreStore|#StoreLoad
wr %g1, %g0, %asi
retl
wr %g0, 0, %fprs
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_vis_4)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_vis_5)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-16 15:20:36 -07:00
save %sp, -192, %sp
rd %fprs, %o5
andcc %o5, FPRS_FEF|FPRS_DU, %g0
be,pt %icc, 0f
sethi %hi(VISenter), %g1
jmpl %g1 + %lo(VISenter), %g7
add %g7, 8, %g7
0: wr %g0, FPRS_FEF, %fprs
rd %asi, %g1
wr %g0, ASI_BLK_P, %asi
membar #LoadStore|#StoreLoad|#StoreStore
sub %i0, 64, %i0
ldda [%i1] %asi, %f0
ldda [%i2] %asi, %f16
5: ldda [%i3] %asi, %f32
fxor %f0, %f16, %f48
fxor %f2, %f18, %f50
add %i1, 64, %i1
fxor %f4, %f20, %f52
fxor %f6, %f22, %f54
add %i2, 64, %i2
fxor %f8, %f24, %f56
fxor %f10, %f26, %f58
fxor %f12, %f28, %f60
fxor %f14, %f30, %f62
ldda [%i4] %asi, %f16
fxor %f48, %f32, %f48
fxor %f50, %f34, %f50
fxor %f52, %f36, %f52
fxor %f54, %f38, %f54
add %i3, 64, %i3
fxor %f56, %f40, %f56
fxor %f58, %f42, %f58
fxor %f60, %f44, %f60
fxor %f62, %f46, %f62
ldda [%i5] %asi, %f32
fxor %f48, %f16, %f48
fxor %f50, %f18, %f50
add %i4, 64, %i4
fxor %f52, %f20, %f52
fxor %f54, %f22, %f54
add %i5, 64, %i5
fxor %f56, %f24, %f56
fxor %f58, %f26, %f58
fxor %f60, %f28, %f60
fxor %f62, %f30, %f62
ldda [%i1] %asi, %f0
fxor %f48, %f32, %f48
fxor %f50, %f34, %f50
fxor %f52, %f36, %f52
fxor %f54, %f38, %f54
fxor %f56, %f40, %f56
fxor %f58, %f42, %f58
subcc %i0, 64, %i0
fxor %f60, %f44, %f60
fxor %f62, %f46, %f62
stda %f48, [%i1 - 64] %asi
bne,pt %xcc, 5b
ldda [%i2] %asi, %f16
ldda [%i3] %asi, %f32
fxor %f0, %f16, %f48
fxor %f2, %f18, %f50
fxor %f4, %f20, %f52
fxor %f6, %f22, %f54
fxor %f8, %f24, %f56
fxor %f10, %f26, %f58
fxor %f12, %f28, %f60
fxor %f14, %f30, %f62
ldda [%i4] %asi, %f16
fxor %f48, %f32, %f48
fxor %f50, %f34, %f50
fxor %f52, %f36, %f52
fxor %f54, %f38, %f54
fxor %f56, %f40, %f56
fxor %f58, %f42, %f58
fxor %f60, %f44, %f60
fxor %f62, %f46, %f62
ldda [%i5] %asi, %f32
fxor %f48, %f16, %f48
fxor %f50, %f18, %f50
fxor %f52, %f20, %f52
fxor %f54, %f22, %f54
fxor %f56, %f24, %f56
fxor %f58, %f26, %f58
fxor %f60, %f28, %f60
fxor %f62, %f30, %f62
membar #Sync
fxor %f48, %f32, %f48
fxor %f50, %f34, %f50
fxor %f52, %f36, %f52
fxor %f54, %f38, %f54
fxor %f56, %f40, %f56
fxor %f58, %f42, %f58
fxor %f60, %f44, %f60
fxor %f62, %f46, %f62
stda %f48, [%i1] %asi
membar #Sync|#StoreStore|#StoreLoad
wr %g1, %g0, %asi
wr %g0, 0, %fprs
ret
restore
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_vis_5)
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
/* Niagara versions. */
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_niagara_2) /* %o0=bytes, %o1=dest, %o2=src */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
save %sp, -192, %sp
prefetch [%i1], #n_writes
prefetch [%i2], #one_read
rd %asi, %g7
wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
srlx %i0, 6, %g1
mov %i1, %i0
mov %i2, %i1
1: ldda [%i1 + 0x00] %asi, %i2 /* %i2/%i3 = src + 0x00 */
ldda [%i1 + 0x10] %asi, %i4 /* %i4/%i5 = src + 0x10 */
ldda [%i1 + 0x20] %asi, %g2 /* %g2/%g3 = src + 0x20 */
ldda [%i1 + 0x30] %asi, %l0 /* %l0/%l1 = src + 0x30 */
prefetch [%i1 + 0x40], #one_read
ldda [%i0 + 0x00] %asi, %o0 /* %o0/%o1 = dest + 0x00 */
ldda [%i0 + 0x10] %asi, %o2 /* %o2/%o3 = dest + 0x10 */
ldda [%i0 + 0x20] %asi, %o4 /* %o4/%o5 = dest + 0x20 */
ldda [%i0 + 0x30] %asi, %l2 /* %l2/%l3 = dest + 0x30 */
prefetch [%i0 + 0x40], #n_writes
xor %o0, %i2, %o0
xor %o1, %i3, %o1
stxa %o0, [%i0 + 0x00] %asi
stxa %o1, [%i0 + 0x08] %asi
xor %o2, %i4, %o2
xor %o3, %i5, %o3
stxa %o2, [%i0 + 0x10] %asi
stxa %o3, [%i0 + 0x18] %asi
xor %o4, %g2, %o4
xor %o5, %g3, %o5
stxa %o4, [%i0 + 0x20] %asi
stxa %o5, [%i0 + 0x28] %asi
xor %l2, %l0, %l2
xor %l3, %l1, %l3
stxa %l2, [%i0 + 0x30] %asi
stxa %l3, [%i0 + 0x38] %asi
add %i0, 0x40, %i0
subcc %g1, 1, %g1
bne,pt %xcc, 1b
add %i1, 0x40, %i1
membar #Sync
wr %g7, 0x0, %asi
ret
restore
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_niagara_2)
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_niagara_3) /* %o0=bytes, %o1=dest, %o2=src1, %o3=src2 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
save %sp, -192, %sp
prefetch [%i1], #n_writes
prefetch [%i2], #one_read
prefetch [%i3], #one_read
rd %asi, %g7
wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
srlx %i0, 6, %g1
mov %i1, %i0
mov %i2, %i1
mov %i3, %l7
1: ldda [%i1 + 0x00] %asi, %i2 /* %i2/%i3 = src1 + 0x00 */
ldda [%i1 + 0x10] %asi, %i4 /* %i4/%i5 = src1 + 0x10 */
ldda [%l7 + 0x00] %asi, %g2 /* %g2/%g3 = src2 + 0x00 */
ldda [%l7 + 0x10] %asi, %l0 /* %l0/%l1 = src2 + 0x10 */
ldda [%i0 + 0x00] %asi, %o0 /* %o0/%o1 = dest + 0x00 */
ldda [%i0 + 0x10] %asi, %o2 /* %o2/%o3 = dest + 0x10 */
xor %g2, %i2, %g2
xor %g3, %i3, %g3
xor %o0, %g2, %o0
xor %o1, %g3, %o1
stxa %o0, [%i0 + 0x00] %asi
stxa %o1, [%i0 + 0x08] %asi
ldda [%i1 + 0x20] %asi, %i2 /* %i2/%i3 = src1 + 0x20 */
ldda [%l7 + 0x20] %asi, %g2 /* %g2/%g3 = src2 + 0x20 */
ldda [%i0 + 0x20] %asi, %o0 /* %o0/%o1 = dest + 0x20 */
xor %l0, %i4, %l0
xor %l1, %i5, %l1
xor %o2, %l0, %o2
xor %o3, %l1, %o3
stxa %o2, [%i0 + 0x10] %asi
stxa %o3, [%i0 + 0x18] %asi
ldda [%i1 + 0x30] %asi, %i4 /* %i4/%i5 = src1 + 0x30 */
ldda [%l7 + 0x30] %asi, %l0 /* %l0/%l1 = src2 + 0x30 */
ldda [%i0 + 0x30] %asi, %o2 /* %o2/%o3 = dest + 0x30 */
prefetch [%i1 + 0x40], #one_read
prefetch [%l7 + 0x40], #one_read
prefetch [%i0 + 0x40], #n_writes
xor %g2, %i2, %g2
xor %g3, %i3, %g3
xor %o0, %g2, %o0
xor %o1, %g3, %o1
stxa %o0, [%i0 + 0x20] %asi
stxa %o1, [%i0 + 0x28] %asi
xor %l0, %i4, %l0
xor %l1, %i5, %l1
xor %o2, %l0, %o2
xor %o3, %l1, %o3
stxa %o2, [%i0 + 0x30] %asi
stxa %o3, [%i0 + 0x38] %asi
add %i0, 0x40, %i0
add %i1, 0x40, %i1
subcc %g1, 1, %g1
bne,pt %xcc, 1b
add %l7, 0x40, %l7
membar #Sync
wr %g7, 0x0, %asi
ret
restore
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_niagara_3)
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_niagara_4) /* %o0=bytes, %o1=dest, %o2=src1, %o3=src2, %o4=src3 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
save %sp, -192, %sp
prefetch [%i1], #n_writes
prefetch [%i2], #one_read
prefetch [%i3], #one_read
prefetch [%i4], #one_read
rd %asi, %g7
wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
srlx %i0, 6, %g1
mov %i1, %i0
mov %i2, %i1
mov %i3, %l7
mov %i4, %l6
1: ldda [%i1 + 0x00] %asi, %i2 /* %i2/%i3 = src1 + 0x00 */
ldda [%l7 + 0x00] %asi, %i4 /* %i4/%i5 = src2 + 0x00 */
ldda [%l6 + 0x00] %asi, %g2 /* %g2/%g3 = src3 + 0x00 */
ldda [%i0 + 0x00] %asi, %l0 /* %l0/%l1 = dest + 0x00 */
xor %i4, %i2, %i4
xor %i5, %i3, %i5
ldda [%i1 + 0x10] %asi, %i2 /* %i2/%i3 = src1 + 0x10 */
xor %g2, %i4, %g2
xor %g3, %i5, %g3
[SPARC64]: Fix register usage in xor_raid_4(). Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is really really bad because those are the frame pointer and return PC. Based upon a raid5 crash report by Bertrand Joel. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-12 01:52:19 -07:00
ldda [%l7 + 0x10] %asi, %i4 /* %i4/%i5 = src2 + 0x10 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
xor %l0, %g2, %l0
xor %l1, %g3, %l1
stxa %l0, [%i0 + 0x00] %asi
stxa %l1, [%i0 + 0x08] %asi
[SPARC64]: Fix register usage in xor_raid_4(). Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is really really bad because those are the frame pointer and return PC. Based upon a raid5 crash report by Bertrand Joel. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-12 01:52:19 -07:00
ldda [%l6 + 0x10] %asi, %g2 /* %g2/%g3 = src3 + 0x10 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
ldda [%i0 + 0x10] %asi, %l0 /* %l0/%l1 = dest + 0x10 */
xor %i4, %i2, %i4
xor %i5, %i3, %i5
ldda [%i1 + 0x20] %asi, %i2 /* %i2/%i3 = src1 + 0x20 */
xor %g2, %i4, %g2
xor %g3, %i5, %g3
[SPARC64]: Fix register usage in xor_raid_4(). Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is really really bad because those are the frame pointer and return PC. Based upon a raid5 crash report by Bertrand Joel. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-12 01:52:19 -07:00
ldda [%l7 + 0x20] %asi, %i4 /* %i4/%i5 = src2 + 0x20 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
xor %l0, %g2, %l0
xor %l1, %g3, %l1
stxa %l0, [%i0 + 0x10] %asi
stxa %l1, [%i0 + 0x18] %asi
[SPARC64]: Fix register usage in xor_raid_4(). Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is really really bad because those are the frame pointer and return PC. Based upon a raid5 crash report by Bertrand Joel. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-12 01:52:19 -07:00
ldda [%l6 + 0x20] %asi, %g2 /* %g2/%g3 = src3 + 0x20 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
ldda [%i0 + 0x20] %asi, %l0 /* %l0/%l1 = dest + 0x20 */
xor %i4, %i2, %i4
xor %i5, %i3, %i5
ldda [%i1 + 0x30] %asi, %i2 /* %i2/%i3 = src1 + 0x30 */
xor %g2, %i4, %g2
xor %g3, %i5, %g3
[SPARC64]: Fix register usage in xor_raid_4(). Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is really really bad because those are the frame pointer and return PC. Based upon a raid5 crash report by Bertrand Joel. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-12 01:52:19 -07:00
ldda [%l7 + 0x30] %asi, %i4 /* %i4/%i5 = src2 + 0x30 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
xor %l0, %g2, %l0
xor %l1, %g3, %l1
stxa %l0, [%i0 + 0x20] %asi
stxa %l1, [%i0 + 0x28] %asi
[SPARC64]: Fix register usage in xor_raid_4(). Some typos led to using %i6/%i7 instead of %l6/%l7 in loads which is really really bad because those are the frame pointer and return PC. Based upon a raid5 crash report by Bertrand Joel. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-12 01:52:19 -07:00
ldda [%l6 + 0x30] %asi, %g2 /* %g2/%g3 = src3 + 0x30 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
ldda [%i0 + 0x30] %asi, %l0 /* %l0/%l1 = dest + 0x30 */
prefetch [%i1 + 0x40], #one_read
prefetch [%l7 + 0x40], #one_read
prefetch [%l6 + 0x40], #one_read
prefetch [%i0 + 0x40], #n_writes
xor %i4, %i2, %i4
xor %i5, %i3, %i5
xor %g2, %i4, %g2
xor %g3, %i5, %g3
xor %l0, %g2, %l0
xor %l1, %g3, %l1
stxa %l0, [%i0 + 0x30] %asi
stxa %l1, [%i0 + 0x38] %asi
add %i0, 0x40, %i0
add %i1, 0x40, %i1
add %l7, 0x40, %l7
subcc %g1, 1, %g1
bne,pt %xcc, 1b
add %l6, 0x40, %l6
membar #Sync
wr %g7, 0x0, %asi
ret
restore
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_niagara_4)
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENTRY(xor_niagara_5) /* %o0=bytes, %o1=dest, %o2=src1, %o3=src2, %o4=src3, %o5=src4 */
[SPARC64]: Niagara optimized XOR functions for RAID. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-02-25 17:16:29 -08:00
save %sp, -192, %sp
prefetch [%i1], #n_writes
prefetch [%i2], #one_read
prefetch [%i3], #one_read
prefetch [%i4], #one_read
prefetch [%i5], #one_read
rd %asi, %g7
wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
srlx %i0, 6, %g1
mov %i1, %i0
mov %i2, %i1
mov %i3, %l7
mov %i4, %l6
mov %i5, %l5
1: ldda [%i1 + 0x00] %asi, %i2 /* %i2/%i3 = src1 + 0x00 */
ldda [%l7 + 0x00] %asi, %i4 /* %i4/%i5 = src2 + 0x00 */
ldda [%l6 + 0x00] %asi, %g2 /* %g2/%g3 = src3 + 0x00 */
ldda [%l5 + 0x00] %asi, %l0 /* %l0/%l1 = src4 + 0x00 */
ldda [%i0 + 0x00] %asi, %l2 /* %l2/%l3 = dest + 0x00 */
xor %i4, %i2, %i4
xor %i5, %i3, %i5
ldda [%i1 + 0x10] %asi, %i2 /* %i2/%i3 = src1 + 0x10 */
xor %g2, %i4, %g2
xor %g3, %i5, %g3
ldda [%l7 + 0x10] %asi, %i4 /* %i4/%i5 = src2 + 0x10 */
xor %l0, %g2, %l0
xor %l1, %g3, %l1
ldda [%l6 + 0x10] %asi, %g2 /* %g2/%g3 = src3 + 0x10 */
xor %l2, %l0, %l2
xor %l3, %l1, %l3
stxa %l2, [%i0 + 0x00] %asi
stxa %l3, [%i0 + 0x08] %asi
ldda [%l5 + 0x10] %asi, %l0 /* %l0/%l1 = src4 + 0x10 */
ldda [%i0 + 0x10] %asi, %l2 /* %l2/%l3 = dest + 0x10 */
xor %i4, %i2, %i4
xor %i5, %i3, %i5
ldda [%i1 + 0x20] %asi, %i2 /* %i2/%i3 = src1 + 0x20 */
xor %g2, %i4, %g2
xor %g3, %i5, %g3
ldda [%l7 + 0x20] %asi, %i4 /* %i4/%i5 = src2 + 0x20 */
xor %l0, %g2, %l0
xor %l1, %g3, %l1
ldda [%l6 + 0x20] %asi, %g2 /* %g2/%g3 = src3 + 0x20 */
xor %l2, %l0, %l2
xor %l3, %l1, %l3
stxa %l2, [%i0 + 0x10] %asi
stxa %l3, [%i0 + 0x18] %asi
ldda [%l5 + 0x20] %asi, %l0 /* %l0/%l1 = src4 + 0x20 */
ldda [%i0 + 0x20] %asi, %l2 /* %l2/%l3 = dest + 0x20 */
xor %i4, %i2, %i4
xor %i5, %i3, %i5
ldda [%i1 + 0x30] %asi, %i2 /* %i2/%i3 = src1 + 0x30 */
xor %g2, %i4, %g2
xor %g3, %i5, %g3
ldda [%l7 + 0x30] %asi, %i4 /* %i4/%i5 = src2 + 0x30 */
xor %l0, %g2, %l0
xor %l1, %g3, %l1
ldda [%l6 + 0x30] %asi, %g2 /* %g2/%g3 = src3 + 0x30 */
xor %l2, %l0, %l2
xor %l3, %l1, %l3
stxa %l2, [%i0 + 0x20] %asi
stxa %l3, [%i0 + 0x28] %asi
ldda [%l5 + 0x30] %asi, %l0 /* %l0/%l1 = src4 + 0x30 */
ldda [%i0 + 0x30] %asi, %l2 /* %l2/%l3 = dest + 0x30 */
prefetch [%i1 + 0x40], #one_read
prefetch [%l7 + 0x40], #one_read
prefetch [%l6 + 0x40], #one_read
prefetch [%l5 + 0x40], #one_read
prefetch [%i0 + 0x40], #n_writes
xor %i4, %i2, %i4
xor %i5, %i3, %i5
xor %g2, %i4, %g2
xor %g3, %i5, %g3
xor %l0, %g2, %l0
xor %l1, %g3, %l1
xor %l2, %l0, %l2
xor %l3, %l1, %l3
stxa %l2, [%i0 + 0x30] %asi
stxa %l3, [%i0 + 0x38] %asi
add %i0, 0x40, %i0
add %i1, 0x40, %i1
add %l7, 0x40, %l7
add %l6, 0x40, %l6
subcc %g1, 1, %g1
bne,pt %xcc, 1b
add %l5, 0x40, %l5
membar #Sync
wr %g7, 0x0, %asi
ret
restore
sparc: Convert some assembler over to linakge.h's ENTRY/ENDPROC Use those, instead of doing it all by hand. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-11 20:33:22 -07:00
ENDPROC(xor_niagara_5)
Reference in a new issue Copy permalink