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>
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 78e0211..bf9a5acc 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -603,10 +603,10 @@
 	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 @@
 
 	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