[POWERPC] Optimize fls64() on 64-bit processors
64-bit powerpc processors can find the leftmost 1 bit in a 64-bit
doubleword in one instruction, so use that rather than using the
generic fls64(), which does two 32-bit fls() calls.
Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/include/asm-powerpc/bitops.h b/include/asm-powerpc/bitops.h
index 36c8f3a..a99a749 100644
--- a/include/asm-powerpc/bitops.h
+++ b/include/asm-powerpc/bitops.h
@@ -312,7 +312,24 @@
asm ("cntlzw %0,%1" : "=r" (lz) : "r" (x));
return 32 - lz;
}
+
+/*
+ * 64-bit can do this using one cntlzd (count leading zeroes doubleword)
+ * instruction; for 32-bit we use the generic version, which does two
+ * 32-bit fls calls.
+ */
+#ifdef __powerpc64__
+static __inline__ int fls64(__u64 x)
+{
+ int lz;
+
+ asm ("cntlzd %0,%1" : "=r" (lz) : "r" (x));
+ return 64 - lz;
+}
+#else
#include <asm-generic/bitops/fls64.h>
+#endif /* __powerpc64__ */
+
#include <asm-generic/bitops/hweight.h>
#include <asm-generic/bitops/find.h>