Use __builtin_popcnt() to implement a BIT_COUNT() operation for bitsets and

use this to implement CPU_COUNT() to count the number of CPUs in a cpuset.

MFC after:	2 weeks

sys/sys/bitset.h

@@ -176,4 +176,14 @@
 	__bit;								\
 })
 
+#define	BIT_COUNT(_s, p) __extension__ ({				\
+	__size_t __i;							\
+	int __count;							\
+									\
+	__count = 0;							\
+	for (__i = 0; __i < __bitset_words((_s)); __i++)		\
+		__count += __builtin_popcount((p)->__bits[__i]);	\
+	__count;							\
+})
+	
 #endif /* !_SYS_BITSET_H_ */

sys/sys/cpuset.h

@@ -60,6 +60,7 @@
 #define	CPU_OR_ATOMIC(d, s)		BIT_OR_ATOMIC(CPU_SETSIZE, d, s)
 #define	CPU_COPY_STORE_REL(f, t)	BIT_COPY_STORE_REL(CPU_SETSIZE, f, t)
 #define	CPU_FFS(p)			BIT_FFS(CPU_SETSIZE, p)
+#define	CPU_COUNT(p)			BIT_COUNT(CPU_SETSIZE, p)
 
 /*
  * Valid cpulevel_t values.