[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240702084423.1717904-5-link@vivo.com>
Date: Tue, 2 Jul 2024 16:44:07 +0800
From: Huan Yang <link@...o.com>
To: Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Shakeel Butt <shakeel.butt@...ux.dev>,
Muchun Song <muchun.song@...ux.dev>,
Andrew Morton <akpm@...ux-foundation.org>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
David Hildenbrand <david@...hat.com>,
Ryan Roberts <ryan.roberts@....com>,
Chris Li <chrisl@...nel.org>,
Dan Schatzberg <schatzberg.dan@...il.com>,
Huan Yang <link@...o.com>,
Kairui Song <kasong@...cent.com>,
cgroups@...r.kernel.org,
linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Christian Brauner <brauner@...nel.org>,
Jan Kara <jack@...e.cz>
Cc: opensource.kernel@...o.com
Subject: [RFC PATCH 4/4] mm: memcg: pmc: support oom release
This patch let each enabled pmc's memcg register a oom listener,
so if oom will trigger, release all hold pages.
Signed-off-by: Huan Yang <link@...o.com>
---
include/linux/mmzone.h | 3 +++
mm/memcontrol.c | 31 +++++++++++++++++++++++++++++++
2 files changed, 34 insertions(+)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b56dd462232b..640a9cf51791 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -622,6 +622,9 @@ struct mem_cgroup_per_node_cache {
unsigned int reaper_wait;
struct delayed_work reaper_work;
+ /* listen oom event, release hold cache */
+ struct notifier_block oom_nb;
+
/* max number to hold page, unit page, default 100MB */
#define DEFAULT_PMC_HOLD_LIMIX ((100 << 20) >> PAGE_SHIFT)
unsigned int hold_limit;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae6917de91cc..3dfb2a17c1fd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7101,6 +7101,33 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
return nbytes;
}
+/**
+ * This function listen to oom event, if oom will trigger, check and release
+ * all holded pages.
+ */
+static int pmc_oom_notify(struct notifier_block *self,
+ unsigned long notused, void *nfreed)
+{
+ struct mem_cgroup_per_node_cache *node_cachep =
+ container_of(self, struct mem_cgroup_per_node_cache, oom_nb);
+ struct mem_cgroup *memcg = node_cachep->memcg;
+
+ unsigned long *nf = (unsigned long *)nfreed;
+
+ rcu_read_lock();
+ if (!css_tryget(&memcg->css)) {
+ rcu_read_unlock();
+ return NOTIFY_STOP;
+ }
+ rcu_read_unlock();
+
+ nf += mem_cgroup_release_cache(node_cachep);
+
+ css_put(&memcg->css);
+
+ return NOTIFY_OK;
+}
+
/**
* This function use to reaper all cache pages by cycling scan.
* The scan interval time depends on @reaper_wait which can set by `keys` nest
@@ -7176,6 +7203,9 @@ static int __enable_mem_cgroup_cache(struct mem_cgroup *memcg)
p->allow_watermark = DEFAULT_PMC_GAP_WATERMARK;
p->reaper_wait = DEFAULT_PMC_REAPER_TIME;
+ p->oom_nb.notifier_call = pmc_oom_notify;
+ register_oom_notifier(&p->oom_nb);
+
atomic_inc(&pmc_nr_enabled);
INIT_DELAYED_WORK(&p->reaper_work, pmc_reaper);
@@ -7222,6 +7252,7 @@ static int __disable_mem_cgroup_cache(struct mem_cgroup *memcg)
p = nodeinfo->cachep;
+ unregister_oom_notifier(&p->oom_nb);
cancel_delayed_work_sync(&p->reaper_work);
mem_cgroup_release_cache(p);
--
2.45.2
Powered by blists - more mailing lists