Received-SPF: pass (google.com: domain of linux-kernel+bounces-122029-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Wed, 27 Mar 2024 14:31:03 -0700
In-Reply-To: <20240327213108.2384666-1-yuanchu@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240327213108.2384666-1-yuanchu@google.com>
Message-ID: <20240327213108.2384666-5-yuanchu@google.com>
Subject: [RFC PATCH v3 4/8] mm: report workingset during memory pressure
 driven scanning
From: Yuanchu Xie <yuanchu@google.com>
To: David Hildenbrand <david@redhat.com>, "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>, 
	Khalid Aziz <khalid.aziz@oracle.com>, Henry Huang <henry.hj@antgroup.com>, 
	Yu Zhao <yuzhao@google.com>, Dan Williams <dan.j.williams@intel.com>, 
	Gregory Price <gregory.price@memverge.com>, Huang Ying <ying.huang@intel.com>
Cc: Wei Xu <weixugc@google.com>, David Rientjes <rientjes@google.com>, 
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>, "Rafael J. Wysocki" <rafael@kernel.org>, 
	Andrew Morton <akpm@linux-foundation.org>, Johannes Weiner <hannes@cmpxchg.org>, 
	Michal Hocko <mhocko@kernel.org>, Roman Gushchin <roman.gushchin@linux.dev>, 
	Muchun Song <muchun.song@linux.dev>, Shuah Khan <shuah@kernel.org>, 
	Yosry Ahmed <yosryahmed@google.com>, Matthew Wilcox <willy@infradead.org>, 
	Sudarshan Rajagopalan <quic_sudaraja@quicinc.com>, Kairui Song <kasong@tencent.com>, 
	"Michael S. Tsirkin" <mst@redhat.com>, Vasily Averin <vasily.averin@linux.dev>, Nhat Pham <nphamcs@gmail.com>, 
	Miaohe Lin <linmiaohe@huawei.com>, Qi Zheng <zhengqi.arch@bytedance.com>, 
	Abel Wu <wuyun.abel@bytedance.com>, "Vishal Moola (Oracle)" <vishal.moola@gmail.com>, 
	Kefeng Wang <wangkefeng.wang@huawei.com>, Yuanchu Xie <yuanchu@google.com>, 
	linux-kernel@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, 
	linux-kselftest@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"

When a node reaches its low watermarks and wakes up kswapd, notify all
userspace programs waiting on the workingset page age histogram of the
memory pressure, so a userspace agent can read the workingset report in
time and make policy decisions, such as logging, oom-killing, or
migration.

Sysfs interface:
/sys/devices/system/node/nodeX/workingset_report/report_threshold
	time in milliseconds that specifies how often the userspace
	agent can be notified for node memory pressure.

Signed-off-by: Yuanchu Xie <yuanchu@google.com>
---
 include/linux/workingset_report.h |  4 +++
 mm/internal.h                     |  6 +++++
 mm/vmscan.c                       | 44 +++++++++++++++++++++++++++++++
 mm/workingset_report.c            | 39 +++++++++++++++++++++++++++
 4 files changed, 93 insertions(+)

diff --git a/include/linux/workingset_report.h b/include/linux/workingset_report.h
index 23d2ae747a31..589d240d6251 100644
--- a/include/linux/workingset_report.h
+++ b/include/linux/workingset_report.h
@@ -35,7 +35,11 @@ struct wsr_page_age_histo {
 };
 
 struct wsr_state {
+	unsigned long report_threshold;
 	unsigned long refresh_interval;
+
+	struct kernfs_node *page_age_sys_file;
+
 	/* breakdown of workingset by page age */
 	struct mutex page_age_lock;
 	struct wsr_page_age_histo *page_age;
diff --git a/mm/internal.h b/mm/internal.h
index 151f09c6983e..36480c7ac0dd 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -209,8 +209,14 @@ extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason
 /*
  * in mm/wsr.c
  */
+void notify_workingset(struct mem_cgroup *memcg, struct pglist_data *pgdat);
 /* Requires wsr->page_age_lock held */
 void wsr_refresh_scan(struct lruvec *lruvec, unsigned long refresh_interval);
+#else
+static inline void notify_workingset(struct mem_cgroup *memcg,
+				     struct pglist_data *pgdat)
+{
+}
 #endif
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5f04a04f5261..c6acd5265b3f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2535,6 +2535,15 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
 	return can_demote(pgdat->node_id, sc);
 }
 
+#ifdef CONFIG_WORKINGSET_REPORT
+static void try_to_report_workingset(struct pglist_data *pgdat, struct scan_control *sc);
+#else
+static inline void try_to_report_workingset(struct pglist_data *pgdat,
+					    struct scan_control *sc)
+{
+}
+#endif
+
 #ifdef CONFIG_LRU_GEN
 
 #ifdef CONFIG_LRU_GEN_ENABLED
@@ -3936,6 +3945,8 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 	if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY)
 		return;
 
+	try_to_report_workingset(pgdat, sc);
+
 	memcg = mem_cgroup_iter(NULL, NULL, NULL);
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
@@ -5650,6 +5661,36 @@ void wsr_refresh_scan(struct lruvec *lruvec, unsigned long refresh_interval)
 		}
 	}
 }
+
+static void try_to_report_workingset(struct pglist_data *pgdat,
+				     struct scan_control *sc)
+{
+	struct mem_cgroup *memcg = sc->target_mem_cgroup;
+	struct wsr_state *wsr = &mem_cgroup_lruvec(memcg, pgdat)->wsr;
+	unsigned long threshold = READ_ONCE(wsr->report_threshold);
+
+	if (sc->priority == DEF_PRIORITY)
+		return;
+
+	if (!threshold)
+		return;
+
+	if (!mutex_trylock(&wsr->page_age_lock))
+		return;
+
+	if (!wsr->page_age) {
+		mutex_unlock(&wsr->page_age_lock);
+		return;
+	}
+
+	if (time_is_after_jiffies(wsr->page_age->timestamp + threshold)) {
+		mutex_unlock(&wsr->page_age_lock);
+		return;
+	}
+
+	mutex_unlock(&wsr->page_age_lock);
+	notify_workingset(memcg, pgdat);
+}
 #endif /* CONFIG_WORKINGSET_REPORT */
 
 #else /* !CONFIG_LRU_GEN */
@@ -6177,6 +6218,9 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		if (zone->zone_pgdat == last_pgdat)
 			continue;
 		last_pgdat = zone->zone_pgdat;
+
+		if (!sc->proactive)
+			try_to_report_workingset(zone->zone_pgdat, sc);
 		shrink_node(zone->zone_pgdat, sc);
 	}
 
diff --git a/mm/workingset_report.c b/mm/workingset_report.c
index 370e7d355604..3ed3b0e8f8ad 100644
--- a/mm/workingset_report.c
+++ b/mm/workingset_report.c
@@ -269,6 +269,33 @@ static struct wsr_state *kobj_to_wsr(struct kobject *kobj)
 	return &mem_cgroup_lruvec(NULL, kobj_to_pgdat(kobj))->wsr;
 }
 
+static ssize_t report_threshold_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *buf)
+{
+	struct wsr_state *wsr = kobj_to_wsr(kobj);
+	unsigned int threshold = READ_ONCE(wsr->report_threshold);
+
+	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(threshold));
+}
+
+static ssize_t report_threshold_store(struct kobject *kobj,
+				      struct kobj_attribute *attr,
+				      const char *buf, size_t len)
+{
+	unsigned int threshold;
+	struct wsr_state *wsr = kobj_to_wsr(kobj);
+
+	if (kstrtouint(buf, 0, &threshold))
+		return -EINVAL;
+
+	WRITE_ONCE(wsr->report_threshold, msecs_to_jiffies(threshold));
+
+	return len;
+}
+
+static struct kobj_attribute report_threshold_attr =
+	__ATTR_RW(report_threshold);
+
 static ssize_t refresh_interval_show(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *buf)
 {
@@ -412,6 +439,7 @@ static ssize_t page_age_show(struct kobject *kobj, struct kobj_attribute *attr,
 static struct kobj_attribute page_age_attr = __ATTR_RO(page_age);
 
 static struct attribute *workingset_report_attrs[] = {
+	&report_threshold_attr.attr,
 	&refresh_interval_attr.attr,
 	&page_age_intervals_attr.attr,
 	&page_age_attr.attr,
@@ -437,6 +465,9 @@ void wsr_register_node(struct node *node)
 		pr_warn("WSR failed to created group");
 		return;
 	}
+
+	wsr->page_age_sys_file =
+		kernfs_walk_and_get(kobj->sd, "workingset_report/page_age");
 }
 EXPORT_SYMBOL_GPL(wsr_register_node);
 
@@ -450,6 +481,14 @@ void wsr_unregister_node(struct node *node)
 
 	wsr = kobj_to_wsr(kobj);
 	sysfs_remove_group(kobj, &workingset_report_attr_group);
+	kernfs_put(wsr->page_age_sys_file);
 	wsr_destroy(mem_cgroup_lruvec(NULL, kobj_to_pgdat(kobj)));
 }
 EXPORT_SYMBOL_GPL(wsr_unregister_node);
+
+void notify_workingset(struct mem_cgroup *memcg, struct pglist_data *pgdat)
+{
+	struct wsr_state *wsr = &mem_cgroup_lruvec(memcg, pgdat)->wsr;
+
+	kernfs_notify(wsr->page_age_sys_file);
+}
-- 
2.44.0.396.g6e790dbe36-goog