lib/bitmap: add bitmap_weight_and()

The function calculates Hamming weight of (bitmap1 & bitmap2). Now we
have to do like this:
	tmp = bitmap_alloc(nbits);
	bitmap_and(tmp, map1, map2, nbits);
	weight = bitmap_weight(tmp, nbits);
	bitmap_free(tmp);

This requires additional memory, adds pressure on alloc subsystem, and
way less cache-friendly than just:
	weight = bitmap_weight_and(map1, map2, nbits);

The following patches apply it for cpumask functions.
Signed-off-by: Yury Norov <yury.norov@gmail.com>

include/linux/bitmap.h

@@ -51,6 +51,7 @@ struct device;
  *  bitmap_empty(src, nbits)                    Are all bits zero in *src?
  *  bitmap_full(src, nbits)                     Are all bits set in *src?
  *  bitmap_weight(src, nbits)                   Hamming Weight: number set bits
+ *  bitmap_weight_and(src1, src2, nbits)        Hamming Weight of and'ed bitmap
  *  bitmap_set(dst, pos, nbits)                 Set specified bit area
  *  bitmap_clear(dst, pos, nbits)               Clear specified bit area
  *  bitmap_find_next_zero_area(buf, len, pos, n, mask)  Find bit free area
@@ -164,6 +165,8 @@ bool __bitmap_intersects(const unsigned long *bitmap1,
 bool __bitmap_subset(const unsigned long *bitmap1,
 		     const unsigned long *bitmap2, unsigned int nbits);
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
+unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
+				 const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_set(unsigned long *map, unsigned int start, int len);
 void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 
@@ -439,6 +442,15 @@ unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits)
 	return __bitmap_weight(src, nbits);
 }
 
+static __always_inline
+unsigned long bitmap_weight_and(const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight_and(src1, src2, nbits);
+}
+
 static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 		unsigned int nbits)
 {

include/linux/cpumask.h

@@ -586,6 +586,17 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
 	return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits);
 }
 
+/**
+ * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2)
+ * @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
+ * @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
+ */
+static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
+						const struct cpumask *srcp2)
+{
+	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits);
+}
+
 /**
  * cpumask_shift_right - *dstp = *srcp >> n
  * @dstp: the cpumask result

lib/bitmap.c

@@ -333,20 +333,32 @@ bool __bitmap_subset(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
+#define BITMAP_WEIGHT(FETCH, bits)	\
+({										\
+	unsigned int __bits = (bits), idx, w = 0;				\
+										\
+	for (idx = 0; idx < __bits / BITS_PER_LONG; idx++)			\
+		w += hweight_long(FETCH);					\
+										\
+	if (__bits % BITS_PER_LONG)						\
+		w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits));	\
+										\
+	w;									\
+})
+
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 {
-	unsigned int k, lim = bits/BITS_PER_LONG, w = 0;
-
-	for (k = 0; k < lim; k++)
-		w += hweight_long(bitmap[k]);
-
-	if (bits % BITS_PER_LONG)
-		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
-
-	return w;
+	return BITMAP_WEIGHT(bitmap[idx], bits);
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
+unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
+				const unsigned long *bitmap2, unsigned int bits)
+{
+	return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits);
+}
+EXPORT_SYMBOL(__bitmap_weight_and);
+
 void __bitmap_set(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);