Readd the arch ffz functions

May as well use the single op version if we have them, it's
generally a lot faster than the generic_ffz()

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/arch/arch-x86.h b/arch/arch-x86.h
index 4d7ea49..a396c85 100644
--- a/arch/arch-x86.h
+++ b/arch/arch-x86.h
@@ -32,4 +32,11 @@
 #define nop		__asm__ __volatile__("rep;nop": : :"memory")
 #define read_barrier()	asm volatile ("": : :"memory")
 
+static inline unsigned long arch_ffz(unsigned long bitmask)
+{
+	__asm__("bsfl %1,%0" :"=r" (bitmask) :"r" (~bitmask));
+	return bitmask;
+}
+#define ARCH_HAVE_FFZ
+
 #endif