diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 603aed229af78..46338f2360046 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -217,15 +217,34 @@ static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr)
  */
 static __inline__ int fls(unsigned int x)
 {
-	return 32 - __builtin_clz(x);
+	int lz;
+
+	if (__builtin_constant_p(x))
+		return x ? 32 - __builtin_clz(x) : 0;
+	asm("cntlzw %0,%1" : "=r" (lz) : "r" (x));
+	return 32 - lz;
 }
 
 #include <asm-generic/bitops/builtin-__fls.h>
 
+/*
+ * 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 CONFIG_PPC64
 static __inline__ int fls64(__u64 x)
 {
-	return 64 - __builtin_clzll(x);
+	int lz;
+
+	if (__builtin_constant_p(x))
+		return x ? 64 - __builtin_clzll(x) : 0;
+	asm("cntlzd %0,%1" : "=r" (lz) : "r" (x));
+	return 64 - lz;
 }
+#else
+#include <asm-generic/bitops/fls64.h>
+#endif
 
 #ifdef CONFIG_PPC64
 unsigned int __arch_hweight8(unsigned int w);