sparc64: Use sparc optimized fls and __fls for T4 and above

For T4 and above, patch fls and __fls functions
at the boot time to use lzcnt instruction.

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

arch/sparc/kernel/head_64.S

@@ -640,6 +640,8 @@ niagara4_patch:
 	 nop
 	call	niagara4_patch_pageops
 	 nop
+	call	niagara4_patch_fls
+	 nop
 
 	ba,a,pt	%xcc, 80f
 	 nop

arch/sparc/lib/NG4patch.S

@@ -3,6 +3,8 @@
  * Copyright (C) 2012 David S. Miller <davem@davemloft.net>
  */
 
+#include <linux/linkage.h>
+
 #define BRANCH_ALWAYS	0x10680000
 #define NOP		0x01000000
 #define NG_DO_PATCH(OLD, NEW)	\
@@ -52,3 +54,10 @@ niagara4_patch_pageops:
 	retl
 	 nop
 	.size	niagara4_patch_pageops,.-niagara4_patch_pageops
+
+ENTRY(niagara4_patch_fls)
+	NG_DO_PATCH(fls, NG4fls)
+	NG_DO_PATCH(__fls, __NG4fls)
+	retl
+	 nop
+ENDPROC(niagara4_patch_fls)