From 6cc0359cb665b07f6b89ca258a5942e0806e5e2f Mon Sep 17 00:00:00 2001
From: Yury Norov <yury.norov@gmail.com>
Date: Sun, 30 Apr 2023 10:18:05 -0700
Subject: [PATCH] sched/topology: add for_each_numa_{,online}_cpu() macro

for_each_cpu() is widely used in the kernel, and it's beneficial to
create a NUMA-aware version of the macro to improve on node locality..

Recently added for_each_numa_hop_mask() works, but switching existing
codebase to using it is not an easy process.

New for_each_numa_cpu() is designed to be similar to the for_each_cpu().
It allows to convert existing code to NUMA-aware as simple as adding a
hop iterator variable and passing it inside new macro. for_each_numa_cpu()
takes care of the rest.

At the moment, we have 2 users of NUMA-aware enumerators. One is
Melanox's in-tree driver, and another is Intel's in-review driver:

https://lore.kernel.org/lkml/20230216145455.661709-1-pawel.chmielewski@intel.com/

Both real-life examples follow the same pattern:

	for_each_numa_hop_mask(cpus, prev, node) {
 		for_each_cpu_andnot(cpu, cpus, prev) {
 			if (cnt++ == max_num)
 				goto out;
 			do_something(cpu);
 		}
		prev = cpus;
 	}

With the new macro, it would look like this:

	for_each_numa_online_cpu(cpu, hop, node) {
		if (cnt++ == max_num)
			break;
		do_something(cpu);
 	}

Straight conversion of existing for_each_cpu() codebase to NUMA-aware
version with for_each_numa_hop_mask() is difficult because it doesn't
take a user-provided cpu mask, and eventually ends up with open-coded
double loop. With for_each_numa_cpu() it shouldn't be a brainteaser.
Consider the NUMA-ignorant example:

	cpumask_t cpus = get_mask();
	int cnt = 0, cpu;

	for_each_cpu(cpu, cpus) {
		if (cnt++ == max_num)
			break;
		do_something(cpu);
 	}

Converting it to NUMA-aware version would be as simple as:

	cpumask_t cpus = get_mask();
	int node = get_node();
	int cnt = 0, hop, cpu;

	rcu_read_lock();
	for_each_numa_cpu(cpu, hop, node, cpus) {
		if (cnt++ == max_num)
			break;
		do_something(cpu);
 	}
	rcu_read_unlock();

The latter looks more verbose and avoids from open-coding that annoying
double loop. Another advantage is that it works with a 'hop' parameter with
the clear meaning of NUMA distance, and doesn't make people not familiar
to enumerator internals bothering with current and previous masks machinery.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/topology.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/include/linux/topology.h b/include/linux/topology.h
index da92fea385858..7d878f5f35cfb 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -291,4 +291,28 @@ sched_numa_hop_mask(unsigned int node, unsigned int hops)
 	     !IS_ERR_OR_NULL(mask);					       \
 	     __hops++)
 
+/**
+ * for_each_numa_cpu - iterate over cpus in increasing order taking into account
+ *		       NUMA distances from a given node.
+ * @cpu: the (optionally unsigned) integer iterator
+ * @hop: the iterator variable for nodes, i.e. proximity order to the @node
+ * @node: the NUMA node to start the search from.
+ * @mask: the cpumask pointer
+ *
+ * Where considered as a replacement to for_each_cpu(), the following should be
+ * taken into consideration:
+ *  - Only accessible (i.e. online) CPUs are enumerated.
+ *  - CPUs enumeration may not be a monotonic increasing sequence;
+ *
+ * rcu_lock must be held;
+ */
+#define for_each_numa_cpu(cpu, hop, node, mask)					\
+	for ((cpu) = 0, (hop) = 0;						\
+		(cpu) = sched_numa_find_next_cpu((mask), (cpu), (node), &(hop)),\
+		(cpu) < nr_cpu_ids;						\
+		(cpu)++)
+
+#define for_each_numa_online_cpu(cpu, hop, node)				\
+	for_each_numa_cpu(cpu, hop, node, cpu_online_mask)
+
 #endif /* _LINUX_TOPOLOGY_H */