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>

arch/sparc/kernel/head_64.S

@@ -559,7 +559,7 @@ niagara2_patch:
 	 nop
 	call	niagara_patch_bzero
 	 nop
-	call	niagara2_patch_pageops
+	call	niagara_patch_pageops
 	 nop
 
 	ba,a,pt	%xcc, 80f

arch/sparc/lib/Makefile

@@ -31,7 +31,7 @@ lib-$(CONFIG_SPARC64) += NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o
 lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o
 
 lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o
-lib-$(CONFIG_SPARC64) +=  NG2patch.o NG2page.o
+lib-$(CONFIG_SPARC64) +=  NG2patch.o
 
 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o

arch/sparc/lib/NG2page.S

-/* NG2page.S: Niagara-2 optimized clear and copy page.
- *
- * Copyright (C) 2007 (davem@davemloft.net)
- */
-
-#include <asm/asi.h>
-#include <asm/page.h>
-#include <asm/visasm.h>
-
-	.text
-	.align	32
-
-	/* This is heavily simplified from the sun4u variants
-	 * because Niagara-2 does not have any D-cache aliasing issues.
-	 */
-NG2copy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
-	prefetch	[%o1 + 0x00], #one_read
-	prefetch	[%o1 + 0x40], #one_read
-	VISEntryHalf
-	set		PAGE_SIZE, %g7
-	sub		%o0, %o1, %g3
-1:	stxa		%g0, [%o1 + %g3] ASI_BLK_INIT_QUAD_LDD_P
-	subcc		%g7, 64, %g7
-	ldda		[%o1] ASI_BLK_P, %f0
-	stda		%f0, [%o1 + %g3] ASI_BLK_P
-	add		%o1, 64, %o1
-	bne,pt		%xcc, 1b
-	 prefetch	[%o1 + 0x40], #one_read
-	membar		#Sync
-	VISExitHalf
-	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	niagara2_patch_pageops
-	.type	niagara2_patch_pageops,#function
-niagara2_patch_pageops:
-	NG_DO_PATCH(copy_user_page, NG2copy_user_page)
-	NG_DO_PATCH(_clear_page, NGclear_page)
-	NG_DO_PATCH(clear_user_page, NGclear_user_page)
-	retl
-	 nop
-	.size	niagara2_patch_pageops,.-niagara2_patch_pageops

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