mm: Create/affine kswapd to its preferred node

kswapd is dedicated to a specific node. As such it wants to be
preferrably affine to it, memory and CPUs-wise.

Use the proper kthread API to achieve that. As a bonus it takes care of
CPU-hotplug events and CPU-isolation on its behalf.

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 76378bc257e383d8e12527adc9c605165615a15d..ec4eab23fb191b2f71d671cda309f0540f75a619 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -7182,10 +7182,6 @@ static int kswapd(void *p)
        unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
        pg_data_t *pgdat = (pg_data_t *)p;
        struct task_struct *tsk = current;
-       const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
-
-       if (!cpumask_empty(cpumask))
-               set_cpus_allowed_ptr(tsk, cpumask);
 
        /*
         * Tell the memory management that we're a "memory allocator",
@@ -7354,13 +7350,15 @@ void __meminit kswapd_run(int nid)
 
        pgdat_kswapd_lock(pgdat);
        if (!pgdat->kswapd) {
-               pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+               pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid);
                if (IS_ERR(pgdat->kswapd)) {
                        /* failure at boot is fatal */
                        pr_err("Failed to start kswapd on node %d，ret=%ld\n",
                                   nid, PTR_ERR(pgdat->kswapd));
                        BUG_ON(system_state < SYSTEM_RUNNING);
                        pgdat->kswapd = NULL;
+               } else {
+                       wake_up_process(pgdat->kswapd);
                }
        }
        pgdat_kswapd_unlock(pgdat);