[PATCH 3/4] workqueue: Update workqueue's possible cpumask when a new node, coming up.

[Kamezawa Hiroyuki]

Workqueue keeps cpu<->node relationship including all possible cpus.
The original information was made at boot but it may change when
a new node is added.

Update information if a new node is ready with using node-hotplug callback.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
 include/linux/memory_hotplug.h |  2 ++
 kernel/workqueue.c             | 28 +++++++++++++++++++++++++++-
 mm/memory_hotplug.c            |  4 ++++
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 8f1a419..cd3cb67 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -270,4 +270,6 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 
+/* update for workqueues */
+void workqueue_node_register(int node);
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2fd0bd7..5499b76 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -266,7 +266,7 @@ struct workqueue_struct {
 static struct kmem_cache *pwq_cache;
 
 static cpumask_var_t *wq_numa_possible_cpumask;
-					/* possible CPUs of each node */
+					/* PL: possible CPUs of each node */
 
 static bool wq_disable_numa;
 module_param_named(disable_numa, wq_disable_numa, bool, 0444);
@@ -4559,6 +4559,32 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
 		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
 						  pool->attrs->cpumask) < 0);
 }
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+static void reflesh_wq_possible_mask(int cpu, int node)
+{
+	int oldnode;
+	for_each_node_state(oldnode, N_POSSIBLE)
+		cpumask_clear_cpu(cpu, wq_numa_possible_cpumask[oldnode]);
+	cpumask_set_cpu(cpu, wq_numa_possible_cpumask[node]);
+}
+/*
+ * When a cpu is physically added, cpu<->node relationship is established.
+ * We can catch the whole view when a new NODE_DATA() coming up.
+ * Update cpumask used for sched affinity of workers.
+ */
+void workqueue_node_register(int node)
+{
+	int cpu;
+	mutex_lock(&wq_pool_mutex);
+	for_each_possible_cpu(cpu) {
+		if (node == cpu_to_node(cpu))
+			reflesh_wq_possible_mask(cpu, node);
+	}
+	mutex_unlock(&wq_pool_mutex);
+}
+
+#endif
 
 /*
  * Workqueues should be brought up before normal priority CPU notifiers.
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1bf4807..d0c1ebb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1121,6 +1121,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	 * online_pages() and offline_pages().
 	 */
 	reset_node_present_pages(pgdat);
+	/*
+	 * Update workqueue's cpu/node affinity info.
+	 */
+	workqueue_node_register(nid);
 
 	return pgdat;
 }
-- 
1.8.3.1



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/