sparc: Minor tweaks to Niagara page copy/clear.
Don't use floating point on Niagara2, use the traditional
plain Niagara code instead.
Unroll Niagara loops to 128 bytes for copy, and 256 bytes
for clear.
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/arch/sparc/lib/NGpage.S b/arch/sparc/lib/NGpage.S
index 428920d..b9e790b 100644
--- a/arch/sparc/lib/NGpage.S
+++ b/arch/sparc/lib/NGpage.S
@@ -16,55 +16,91 @@
*/
NGcopy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */
- prefetch [%o1 + 0x00], #one_read
- mov 8, %g1
- mov 16, %g2
- mov 24, %g3
+ 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: ldda [%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
- ldda [%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
- prefetch [%o1 + 0x40], #one_read
- add %o1, 32, %o1
- stxa %o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- ldda [%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2
- stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- ldda [%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4
- add %o1, 32, %o1
- add %o0, 32, %o0
- stxa %o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- subcc %g7, 64, %g7
+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 %o0, 32, %o0
+ add %i0, 128, %i0
+ wr %g3, 0x0, %asi
membar #Sync
- retl
- nop
+ ret
+ restore
- .globl NGclear_page, NGclear_user_page
+ .align 32
NGclear_page: /* %o0=dest */
NGclear_user_page: /* %o0=dest, %o1=vaddr */
- mov 8, %g1
- mov 16, %g2
- mov 24, %g3
+ rd %asi, %g3
+ wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi
set PAGE_SIZE, %g7
-1: stxa %g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- add %o0, 32, %o0
- stxa %g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
- stxa %g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
- subcc %g7, 64, %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, 32, %o0
+ add %o0, 256, %o0
+ wr %g3, 0x0, %asi
membar #Sync
retl
nop
