@@ -37,7 +37,11 @@ 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;
@@ -479,6 +479,18 @@ bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, bool can_swap,
bool force_scan);
void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs);
+#ifdef CONFIG_WORKINGSET_REPORT
+/*
+ * in mm/wsr.c
+ */
+void notify_workingset(struct mem_cgroup *memcg, struct pglist_data *pgdat);
+#else
+static inline void notify_workingset(struct mem_cgroup *memcg,
+ struct pglist_data *pgdat)
+{
+}
+#endif
+
/*
* in mm/rmap.c:
*/
@@ -2578,6 +2578,15 @@ 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
@@ -4004,6 +4013,8 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
set_initial_priority(pgdat, sc);
+ try_to_report_workingset(pgdat, sc);
+
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
@@ -5649,6 +5660,38 @@ static int __init init_lru_gen(void)
};
late_initcall(init_lru_gen);
+#ifdef CONFIG_WORKINGSET_REPORT
+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 */
static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
@@ -6200,6 +6243,9 @@ 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);
}
@@ -320,6 +320,33 @@ 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)
{
@@ -474,6 +501,7 @@ 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,
@@ -495,8 +523,13 @@ void wsr_init_sysfs(struct node *node)
wsr = kobj_to_wsr(kobj);
- if (sysfs_create_group(kobj, &workingset_report_attr_group))
+ if (sysfs_create_group(kobj, &workingset_report_attr_group)) {
pr_warn("Workingset report failed to create sysfs files\n");
+ return;
+ }
+
+ wsr->page_age_sys_file =
+ kernfs_walk_and_get(kobj->sd, "workingset_report/page_age");
}
EXPORT_SYMBOL_GPL(wsr_init_sysfs);
@@ -509,6 +542,14 @@ void wsr_remove_sysfs(struct node *node)
return;
wsr = kobj_to_wsr(kobj);
+ kernfs_put(wsr->page_age_sys_file);
sysfs_remove_group(kobj, &workingset_report_attr_group);
}
EXPORT_SYMBOL_GPL(wsr_remove_sysfs);
+
+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);
+}
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 | 12 ++++++++ mm/vmscan.c | 46 +++++++++++++++++++++++++++++++ mm/workingset_report.c | 43 ++++++++++++++++++++++++++++- 4 files changed, 104 insertions(+), 1 deletion(-)