sparc64: SPARC optimized fls function

Defined SPARC optimized fls using lzcnt opcode.

Signed-off-by: Vijay Kumar <vijay.ac.kumar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/lib/Makefile

@@ -18,6 +18,7 @@ lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
 lib-$(CONFIG_SPARC64) += multi3.o
 lib-$(CONFIG_SPARC64) += fls.o
 lib-$(CONFIG_SPARC64) += fls64.o
+obj-$(CONFIG_SPARC64) += NG4fls.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
 lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o

arch/sparc/lib/NG4fls.S

@@ -0,0 +1,20 @@
+/* NG4fls.S: SPARC optimized fls and __fls for T4 and above.
+ *
+ * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved.
+ */
+
+#include <linux/linkage.h>
+
+#define LZCNT_O0_G2	\
+	.word	0x85b002e8
+
+	.text
+	.register	%g2, #scratch
+	.register	%g3, #scratch
+
+ENTRY(NG4fls)
+	LZCNT_O0_G2	!lzcnt	%o0, %g2
+	mov	64, %g3
+	retl
+	 sub	%g3, %g2, %o0
+ENDPROC(NG4fls)