arch/sparc: Optimized memcpy, memset, copy_to_user, copy_from_user for M7/M8

New algorithm that takes advantage of the M7/M8 block init store
ASI, ie, overlapping pipelines and miss buffer filling.
Full details in code comments.
Signed-off-by: Babu Moger <babu.moger@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/kernel/head_64.S

@@ -603,10 +603,10 @@ niagara_tlb_fixup:
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_M7
-	be,pt	%xcc, niagara4_patch
+	be,pt	%xcc, sparc_m7_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_M8
-	be,pt	%xcc, niagara4_patch
+	be,pt	%xcc, sparc_m7_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_SPARC_SN
 	be,pt	%xcc, niagara4_patch
@@ -621,6 +621,18 @@ niagara_tlb_fixup:
 
 	ba,a,pt	%xcc, 80f
 	 nop
+
+sparc_m7_patch:
+	call	m7_patch_copyops
+	 nop
+	call	m7_patch_bzero
+	 nop
+	call	m7_patch_pageops
+	 nop
+
+	ba,a,pt	%xcc, 80f
+	 nop
+
 niagara4_patch:
 	call	niagara4_patch_copyops
 	 nop

arch/sparc/lib/M7copy_from_user.S

+/*
+ * M7copy_from_user.S: SPARC M7 optimized copy from userspace.
+ *
+ * Copyright (c) 2016, Oracle and/or its affiliates. All rights reserved.
+ */
+
+
+#define EX_LD(x)			\
+98:	x;				\
+	.section __ex_table,"a";	\
+	.align 4;			\
+	.word 98b, __restore_asi;	\
+	.text;				\
+	.align 4;
+
+#define EX_LD_FP(x)			\
+98:	x;				\
+	.section __ex_table,"a";	\
+	.align 4;			\
+	.word 98b, __restore_asi_fp;	\
+	.text;				\
+	.align 4;
+
+
+#ifndef ASI_AIUS
+#define ASI_AIUS	0x11
+#endif
+
+#define FUNC_NAME		M7copy_from_user
+#define LOAD(type,addr,dest)	type##a [addr] %asi, dest
+#define EX_RETVAL(x)		0
+
+#ifdef __KERNEL__
+#define PREAMBLE					\
+	rd		%asi, %g1;			\
+	cmp		%g1, ASI_AIUS;			\
+	bne,pn		%icc, raw_copy_in_user;		\
+	nop
+#endif
+
+#include "M7memcpy.S"

arch/sparc/lib/M7copy_to_user.S

+/*
+ * M7copy_to_user.S: SPARC M7 optimized copy to userspace.
+ *
+ * Copyright (c) 2016, Oracle and/or its affiliates. All rights reserved.
+ */
+
+
+#define EX_ST(x)			\
+98:	x;				\
+	.section __ex_table,"a";	\
+	.align 4;			\
+	.word 98b, __restore_asi;	\
+	.text;				\
+	.align 4;
+
+#define EX_ST_FP(x)			\
+98:	x;				\
+	.section __ex_table,"a";	\
+	.align 4;			\
+	.word 98b, __restore_asi_fp;	\
+	.text;				\
+	.align 4;
+
+
+#ifndef ASI_AIUS
+#define ASI_AIUS	0x11
+#endif
+
+#ifndef ASI_BLK_INIT_QUAD_LDD_AIUS
+#define ASI_BLK_INIT_QUAD_LDD_AIUS 0x23
+#endif
+
+#define FUNC_NAME		M7copy_to_user
+#define STORE(type,src,addr)	type##a src, [addr] %asi
+#define STORE_ASI		ASI_BLK_INIT_QUAD_LDD_AIUS
+#define	STORE_MRU_ASI		ASI_ST_BLKINIT_MRU_S
+#define EX_RETVAL(x)		0
+
+#ifdef __KERNEL__
+	/* Writing to %asi is _expensive_ so we hardcode it.
+	 * Reading %asi to check for KERNEL_DS is comparatively
+	 * cheap.
+	 */
+#define PREAMBLE					\
+	rd		%asi, %g1;			\
+	cmp		%g1, ASI_AIUS;			\
+	bne,pn		%icc, raw_copy_in_user;		\
+	nop
+#endif
+
+#include "M7memcpy.S"

arch/sparc/lib/M7patch.S

+/*
+ * M7patch.S: Patch generic routines with M7 variant.
+ *
+ * Copyright (c) 2016, Oracle and/or its affiliates.  All rights reserved.
+ */
+
+#include <linux/linkage.h>
+
+#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;
+
+ENTRY(m7_patch_copyops)
+	NG_DO_PATCH(memcpy, M7memcpy)
+	NG_DO_PATCH(raw_copy_from_user, M7copy_from_user)
+	NG_DO_PATCH(raw_copy_to_user, M7copy_to_user)
+	retl
+	 nop
+ENDPROC(m7_patch_copyops)
+
+ENTRY(m7_patch_bzero)
+	NG_DO_PATCH(memset, M7memset)
+	NG_DO_PATCH(__bzero, M7bzero)
+	NG_DO_PATCH(__clear_user, NGclear_user)
+	NG_DO_PATCH(tsb_init, NGtsb_init)
+	retl
+	 nop
+ENDPROC(m7_patch_bzero)
+
+ENTRY(m7_patch_pageops)
+	NG_DO_PATCH(copy_user_page, NG4copy_user_page)
+	NG_DO_PATCH(_clear_page, M7clear_page)
+	NG_DO_PATCH(clear_user_page, M7clear_user_page)
+	retl
+	 nop
+ENDPROC(m7_patch_pageops)

arch/sparc/lib/Makefile

@@ -38,6 +38,9 @@ lib-$(CONFIG_SPARC64) +=  NG4patch.o NG4copy_page.o NG4clear_page.o NG4memset.o
 
 lib-$(CONFIG_SPARC64) += Memcpy_utils.o
 
+lib-$(CONFIG_SPARC64) += M7memcpy.o M7copy_from_user.o M7copy_to_user.o
+lib-$(CONFIG_SPARC64) += M7patch.o M7memset.o
+
 lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
 lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o