topology: make for_each_node_with_cpus() O(N)

for_each_node_with_cpus() calls nr_cpus_node() at every iteration, which
makes it O(N^2). Kernel tracks such nodes with N_CPU record in node_states
array. Switching to it makes for_each_node_with_cpus() O(N).

Andrea:

Now we can include also offline nodes with CPUs assigned (assuming it's
possible). If checking the online state is required, the user must use
node_online() within the loop.

CC: Andrea Righi <arighi@nvidia.com>
CC:Tejun Heo <tj@kernel.org>
Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>

Author: YuryNorov

include/linux/nodemask.h

@@ -522,6 +522,7 @@ static __always_inline int node_random(const nodemask_t *maskp)
 
 #define for_each_node(node)	   for_each_node_state(node, N_POSSIBLE)
 #define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
+#define for_each_node_with_cpus(node)	for_each_node_state(node, N_CPU)
 
 /*
  * For nodemask scratch area.

include/linux/topology.h

@@ -29,6 +29,7 @@
 
 #include <linux/arch_topology.h>
 #include <linux/cpumask.h>
+#include <linux/nodemask.h>
 #include <linux/bitops.h>
 #include <linux/mmzone.h>
 #include <linux/smp.h>
@@ -39,10 +40,6 @@
 #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
 #endif
 
-#define for_each_node_with_cpus(node)			\
-	for_each_online_node(node)			\
-		if (nr_cpus_node(node))
-
 int arch_update_cpu_topology(void);
 
 /* Conform to ACPI 2.0 SLIT distance definitions */