cpumask: Introduce for_each_cpu_andnot()

for_each_cpu_and() is very convenient as it saves having to allocate a
temporary cpumask to store the result of cpumask_and(). The same issue
applies to cpumask_andnot() which doesn't actually need temporary storage
for iteration purposes.

Following what has been done for for_each_cpu_and(), introduce
for_each_cpu_andnot().
Signed-off-by: Valentin Schneider <vschneid@redhat.com>

include/linux/cpumask.h

@@ -306,6 +306,24 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
 #define for_each_cpu_and(cpu, mask1, mask2)				\
 	for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits)
 
+/**
+ * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding
+ *			 those present in another.
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask1: the first cpumask pointer
+ * @mask2: the second cpumask pointer
+ *
+ * This saves a temporary CPU mask in many places.  It is equivalent to:
+ *	struct cpumask tmp;
+ *	cpumask_andnot(&tmp, &mask1, &mask2);
+ *	for_each_cpu(cpu, &tmp)
+ *		...
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_andnot(cpu, mask1, mask2)				\
+	for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), nr_cpumask_bits)
+
 /**
  * cpumask_any_but - return a "random" in a cpumask, but not this one.
  * @mask: the cpumask to search

include/linux/find.h

@@ -498,6 +498,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned
 	     (bit) = find_next_and_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
 	     (bit)++)
 
+#define for_each_andnot_bit(bit, addr1, addr2, size) \
+	for ((bit) = 0;									\
+	     (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\
+	     (bit)++)
+
 /* same as for_each_set_bit() but use bit as value to start with */
 #define for_each_set_bit_from(bit, addr, size) \
 	for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++)