kernel-ark/arch/sparc/lib/NGpage.S
David S. Miller ae2c6ca641 sparc64: Add SPARC-T4 optimized memcpy.
Before		After
		--------------	--------------
bw_tcp:         1288.53 MB/sec	1637.77 MB/sec
bw_pipe:        1517.18 MB/sec	2107.61 MB/sec
bw_unix:        1838.38 MB/sec	2640.91 MB/sec

make -s -j128
allmodconfig	5min 49sec	5min 31sec

Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-27 00:35:11 -07:00

138 lines
3.5 KiB
ArmAsm

/* NGpage.S: Niagara optimize clear and copy page.
*
* Copyright (C) 2006 (davem@davemloft.net)
*/
#include <asm/asi.h>
#include <asm/page.h>
.text
.align 32
/* This is heavily simplified from the sun4u variants
* because Niagara does not have any D-cache aliasing issues
* and also we don't need to use the FPU in order to implement
* an optimal page copy/clear.
*/
NGcopy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */
save %sp, -192, %sp
rd %asi, %g3
wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
set PAGE_SIZE, %g7
prefetch [%i1 + 0x00], #one_read
prefetch [%i1 + 0x40], #one_read
1: prefetch [%i1 + 0x80], #one_read
prefetch [%i1 + 0xc0], #one_read
ldda [%i1 + 0x00] %asi, %o2
ldda [%i1 + 0x10] %asi, %o4
ldda [%i1 + 0x20] %asi, %l2
ldda [%i1 + 0x30] %asi, %l4
stxa %o2, [%i0 + 0x00] %asi
stxa %o3, [%i0 + 0x08] %asi
stxa %o4, [%i0 + 0x10] %asi
stxa %o5, [%i0 + 0x18] %asi
stxa %l2, [%i0 + 0x20] %asi
stxa %l3, [%i0 + 0x28] %asi
stxa %l4, [%i0 + 0x30] %asi
stxa %l5, [%i0 + 0x38] %asi
ldda [%i1 + 0x40] %asi, %o2
ldda [%i1 + 0x50] %asi, %o4
ldda [%i1 + 0x60] %asi, %l2
ldda [%i1 + 0x70] %asi, %l4
stxa %o2, [%i0 + 0x40] %asi
stxa %o3, [%i0 + 0x48] %asi
stxa %o4, [%i0 + 0x50] %asi
stxa %o5, [%i0 + 0x58] %asi
stxa %l2, [%i0 + 0x60] %asi
stxa %l3, [%i0 + 0x68] %asi
stxa %l4, [%i0 + 0x70] %asi
stxa %l5, [%i0 + 0x78] %asi
add %i1, 128, %i1
subcc %g7, 128, %g7
bne,pt %xcc, 1b
add %i0, 128, %i0
wr %g3, 0x0, %asi
membar #Sync
ret
restore
.align 32
.globl NGclear_page
.globl NGclear_user_page
NGclear_page: /* %o0=dest */
NGclear_user_page: /* %o0=dest, %o1=vaddr */
rd %asi, %g3
wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
set PAGE_SIZE, %g7
1: stxa %g0, [%o0 + 0x00] %asi
stxa %g0, [%o0 + 0x08] %asi
stxa %g0, [%o0 + 0x10] %asi
stxa %g0, [%o0 + 0x18] %asi
stxa %g0, [%o0 + 0x20] %asi
stxa %g0, [%o0 + 0x28] %asi
stxa %g0, [%o0 + 0x30] %asi
stxa %g0, [%o0 + 0x38] %asi
stxa %g0, [%o0 + 0x40] %asi
stxa %g0, [%o0 + 0x48] %asi
stxa %g0, [%o0 + 0x50] %asi
stxa %g0, [%o0 + 0x58] %asi
stxa %g0, [%o0 + 0x60] %asi
stxa %g0, [%o0 + 0x68] %asi
stxa %g0, [%o0 + 0x70] %asi
stxa %g0, [%o0 + 0x78] %asi
stxa %g0, [%o0 + 0x80] %asi
stxa %g0, [%o0 + 0x88] %asi
stxa %g0, [%o0 + 0x90] %asi
stxa %g0, [%o0 + 0x98] %asi
stxa %g0, [%o0 + 0xa0] %asi
stxa %g0, [%o0 + 0xa8] %asi
stxa %g0, [%o0 + 0xb0] %asi
stxa %g0, [%o0 + 0xb8] %asi
stxa %g0, [%o0 + 0xc0] %asi
stxa %g0, [%o0 + 0xc8] %asi
stxa %g0, [%o0 + 0xd0] %asi
stxa %g0, [%o0 + 0xd8] %asi
stxa %g0, [%o0 + 0xe0] %asi
stxa %g0, [%o0 + 0xe8] %asi
stxa %g0, [%o0 + 0xf0] %asi
stxa %g0, [%o0 + 0xf8] %asi
subcc %g7, 256, %g7
bne,pt %xcc, 1b
add %o0, 256, %o0
wr %g3, 0x0, %asi
membar #Sync
retl
nop
#define BRANCH_ALWAYS 0x10680000
#define NOP 0x01000000
#define NG_DO_PATCH(OLD, NEW) \
sethi %hi(NEW), %g1; \
or %g1, %lo(NEW), %g1; \
sethi %hi(OLD), %g2; \
or %g2, %lo(OLD), %g2; \
sub %g1, %g2, %g1; \
sethi %hi(BRANCH_ALWAYS), %g3; \
sll %g1, 11, %g1; \
srl %g1, 11 + 2, %g1; \
or %g3, %lo(BRANCH_ALWAYS), %g3; \
or %g3, %g1, %g3; \
stw %g3, [%g2]; \
sethi %hi(NOP), %g3; \
or %g3, %lo(NOP), %g3; \
stw %g3, [%g2 + 0x4]; \
flush %g2;
.globl niagara_patch_pageops
.type niagara_patch_pageops,#function
niagara_patch_pageops:
NG_DO_PATCH(copy_user_page, NGcopy_user_page)
NG_DO_PATCH(_clear_page, NGclear_page)
NG_DO_PATCH(clear_user_page, NGclear_user_page)
retl
nop
.size niagara_patch_pageops,.-niagara_patch_pageops