@@ -20,6 +20,8 @@
#include <linux/pm_runtime.h>
#include <linux/swap.h>
#include <linux/slab.h>
+#include <linux/memcontrol.h>
+#include <linux/workingset_report.h>
static const struct bus_type node_subsys = {
.name = "node",
@@ -626,6 +628,7 @@ static int register_node(struct node *node, int num)
} else {
hugetlb_register_node(node);
compaction_register_node(node);
+ wsr_init_sysfs(node);
}
return error;
@@ -642,6 +645,9 @@ void unregister_node(struct node *node)
{
hugetlb_unregister_node(node);
compaction_unregister_node(node);
+ wsr_remove_sysfs(node);
+ wsr_destroy_lruvec(mem_cgroup_lruvec(NULL, NODE_DATA(node->dev.id)));
+ wsr_destroy_pgdat(NODE_DATA(node->dev.id));
node_remove_accesses(node);
node_remove_caches(node);
device_unregister(&node->dev);
@@ -24,6 +24,7 @@
#include <linux/local_lock.h>
#include <linux/zswap.h>
#include <asm/page.h>
+#include <linux/workingset_report.h>
/* Free memory management - zoned buddy allocator. */
#ifndef CONFIG_ARCH_FORCE_MAX_ORDER
@@ -631,6 +632,9 @@ struct lruvec {
struct lru_gen_mm_state mm_state;
#endif
#endif /* CONFIG_LRU_GEN */
+#ifdef CONFIG_WORKINGSET_REPORT
+ struct wsr_state wsr;
+#endif /* CONFIG_WORKINGSET_REPORT */
#ifdef CONFIG_MEMCG
struct pglist_data *pgdat;
#endif
@@ -1404,6 +1408,11 @@ typedef struct pglist_data {
struct lru_gen_memcg memcg_lru;
#endif
+#ifdef CONFIG_WORKINGSET_REPORT
+ struct mutex wsr_update_mutex;
+ struct wsr_report_bins __rcu *wsr_page_age_bins;
+#endif
+
CACHELINE_PADDING(_pad2_);
/* Per-node vmstats */
new file mode 100644
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_WORKINGSET_REPORT_H
+#define _LINUX_WORKINGSET_REPORT_H
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+
+struct mem_cgroup;
+struct pglist_data;
+struct node;
+struct lruvec;
+
+#ifdef CONFIG_WORKINGSET_REPORT
+
+#define WORKINGSET_REPORT_MIN_NR_BINS 2
+#define WORKINGSET_REPORT_MAX_NR_BINS 32
+
+#define WORKINGSET_INTERVAL_MAX ((unsigned long)-1)
+#define ANON_AND_FILE 2
+
+struct wsr_report_bin {
+ unsigned long idle_age;
+ unsigned long nr_pages[ANON_AND_FILE];
+};
+
+struct wsr_report_bins {
+ /* excludes the WORKINGSET_INTERVAL_MAX bin */
+ unsigned long nr_bins;
+ /* last bin contains WORKINGSET_INTERVAL_MAX */
+ unsigned long idle_age[WORKINGSET_REPORT_MAX_NR_BINS];
+ struct rcu_head rcu;
+};
+
+struct wsr_page_age_histo {
+ unsigned long timestamp;
+ struct wsr_report_bin bins[WORKINGSET_REPORT_MAX_NR_BINS];
+};
+
+struct wsr_state {
+ /* breakdown of workingset by page age */
+ struct mutex page_age_lock;
+ struct wsr_page_age_histo *page_age;
+};
+
+void wsr_init_lruvec(struct lruvec *lruvec);
+void wsr_destroy_lruvec(struct lruvec *lruvec);
+void wsr_init_pgdat(struct pglist_data *pgdat);
+void wsr_destroy_pgdat(struct pglist_data *pgdat);
+void wsr_init_sysfs(struct node *node);
+void wsr_remove_sysfs(struct node *node);
+
+/*
+ * Returns true if the wsr is configured to be refreshed.
+ * The next refresh time is stored in refresh_time.
+ */
+bool wsr_refresh_report(struct wsr_state *wsr, struct mem_cgroup *root,
+ struct pglist_data *pgdat);
+#else
+static inline void wsr_init_lruvec(struct lruvec *lruvec)
+{
+}
+static inline void wsr_destroy_lruvec(struct lruvec *lruvec)
+{
+}
+static inline void wsr_init_pgdat(struct pglist_data *pgdat)
+{
+}
+static inline void wsr_destroy_pgdat(struct pglist_data *pgdat)
+{
+}
+static inline void wsr_init_sysfs(struct node *node)
+{
+}
+static inline void wsr_remove_sysfs(struct node *node)
+{
+}
+#endif /* CONFIG_WORKINGSET_REPORT */
+
+#endif /* _LINUX_WORKINGSET_REPORT_H */
@@ -1249,6 +1249,15 @@ config IOMMU_MM_DATA
config EXECMEM
bool
+config WORKINGSET_REPORT
+ bool "Working set reporting"
+ depends on LRU_GEN && SYSFS
+ help
+ Report system and per-memcg working set to userspace.
+
+ This option exports stats and events giving the user more insight
+ into its memory working set.
+
source "mm/damon/Kconfig"
endmenu
@@ -96,6 +96,7 @@ obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
+obj-$(CONFIG_WORKINGSET_REPORT) += workingset_report.o
ifdef CONFIG_SWAP
obj-$(CONFIG_MEMCG) += swap_cgroup.o
endif
@@ -389,11 +389,15 @@ extern unsigned long highest_memmap_pfn;
/*
* in mm/vmscan.c:
*/
+struct scan_control;
bool isolate_lru_page(struct page *page);
bool folio_isolate_lru(struct folio *folio);
void putback_lru_page(struct page *page);
void folio_putback_lru(struct folio *folio);
extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
+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);
/*
* in mm/rmap.c:
@@ -66,6 +66,7 @@
#include <linux/seq_buf.h>
#include <linux/sched/isolation.h>
#include <linux/kmemleak.h>
+#include <linux/workingset_report.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
@@ -5671,6 +5672,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
if (!pn)
return;
+ wsr_destroy_lruvec(&pn->lruvec);
free_percpu(pn->lruvec_stats_percpu);
kfree(pn->lruvec_stats);
kfree(pn);
@@ -29,6 +29,7 @@
#include <linux/cma.h>
#include <linux/crash_dump.h>
#include <linux/execmem.h>
+#include <linux/workingset_report.h>
#include "internal.h"
#include "slab.h"
#include "shuffle.h"
@@ -1373,6 +1374,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
pgdat_page_ext_init(pgdat);
lruvec_init(&pgdat->__lruvec);
+ wsr_init_pgdat(pgdat);
}
static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
@@ -90,6 +90,8 @@ void lruvec_init(struct lruvec *lruvec)
*/
list_del(&lruvec->lists[LRU_UNEVICTABLE]);
+ wsr_init_lruvec(lruvec);
+
lru_gen_init_lruvec(lruvec);
}
@@ -56,6 +56,7 @@
#include <linux/khugepaged.h>
#include <linux/rculist_nulls.h>
#include <linux/random.h>
+#include <linux/workingset_report.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -250,8 +251,7 @@ static bool writeback_throttling_sane(struct scan_control *sc)
}
#endif
-static void set_task_reclaim_state(struct task_struct *task,
- struct reclaim_state *rs)
+void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs)
{
/* Check for an overwrite */
WARN_ON_ONCE(rs && task->reclaim_state);
@@ -3842,8 +3842,8 @@ static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq,
return success;
}
-static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
- bool can_swap, bool force_scan)
+bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, bool can_swap,
+ bool force_scan)
{
bool success;
struct lru_gen_mm_walk *walk;
@@ -5628,6 +5628,8 @@ static int __init init_lru_gen(void)
if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
pr_err("lru_gen: failed to create sysfs group\n");
+ wsr_init_sysfs(NULL);
+
debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops);
debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops);
new file mode 100644
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/lockdep.h>
+#include <linux/jiffies.h>
+#include <linux/kernfs.h>
+#include <linux/memcontrol.h>
+#include <linux/rcupdate.h>
+#include <linux/mutex.h>
+#include <linux/err.h>
+#include <linux/atomic.h>
+#include <linux/node.h>
+#include <linux/mmzone.h>
+#include <linux/mm.h>
+#include <linux/mm_inline.h>
+#include <linux/workingset_report.h>
+
+#include "internal.h"
+
+void wsr_init_pgdat(struct pglist_data *pgdat)
+{
+ mutex_init(&pgdat->wsr_update_mutex);
+ RCU_INIT_POINTER(pgdat->wsr_page_age_bins, NULL);
+}
+
+void wsr_destroy_pgdat(struct pglist_data *pgdat)
+{
+ struct wsr_report_bins __rcu *bins;
+
+ mutex_lock(&pgdat->wsr_update_mutex);
+ bins = rcu_replace_pointer(pgdat->wsr_page_age_bins, NULL,
+ lockdep_is_held(&pgdat->wsr_update_mutex));
+ kfree_rcu(bins, rcu);
+ mutex_unlock(&pgdat->wsr_update_mutex);
+ mutex_destroy(&pgdat->wsr_update_mutex);
+}
+
+void wsr_init_lruvec(struct lruvec *lruvec)
+{
+ struct wsr_state *wsr = &lruvec->wsr;
+
+ memset(wsr, 0, sizeof(*wsr));
+ mutex_init(&wsr->page_age_lock);
+}
+
+void wsr_destroy_lruvec(struct lruvec *lruvec)
+{
+ struct wsr_state *wsr = &lruvec->wsr;
+
+ mutex_destroy(&wsr->page_age_lock);
+ kfree(wsr->page_age);
+ memset(wsr, 0, sizeof(*wsr));
+}
+
+static int workingset_report_intervals_parse(char *src,
+ struct wsr_report_bins *bins)
+{
+ int err = 0, i = 0;
+ char *cur, *next = strim(src);
+
+ if (*next == '\0')
+ return 0;
+
+ while ((cur = strsep(&next, ","))) {
+ unsigned int interval;
+
+ err = kstrtouint(cur, 0, &interval);
+ if (err)
+ goto out;
+
+ bins->idle_age[i] = msecs_to_jiffies(interval);
+ if (i > 0 && bins->idle_age[i] <= bins->idle_age[i - 1]) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (++i == WORKINGSET_REPORT_MAX_NR_BINS) {
+ err = -ERANGE;
+ goto out;
+ }
+ }
+
+ if (i && i < WORKINGSET_REPORT_MIN_NR_BINS - 1) {
+ err = -ERANGE;
+ goto out;
+ }
+
+ bins->nr_bins = i;
+ bins->idle_age[i] = WORKINGSET_INTERVAL_MAX;
+out:
+ return err ?: i;
+}
+
+static unsigned long get_gen_start_time(const struct lru_gen_folio *lrugen,
+ unsigned long seq,
+ unsigned long max_seq,
+ unsigned long curr_timestamp)
+{
+ int younger_gen;
+
+ if (seq == max_seq)
+ return curr_timestamp;
+ younger_gen = lru_gen_from_seq(seq + 1);
+ return READ_ONCE(lrugen->timestamps[younger_gen]);
+}
+
+static void collect_page_age_type(const struct lru_gen_folio *lrugen,
+ struct wsr_report_bin *bin,
+ unsigned long max_seq, unsigned long min_seq,
+ unsigned long curr_timestamp, int type)
+{
+ unsigned long seq;
+
+ for (seq = max_seq; seq + 1 > min_seq; seq--) {
+ int gen, zone;
+ unsigned long gen_end, gen_start, size = 0;
+
+ gen = lru_gen_from_seq(seq);
+
+ for (zone = 0; zone < MAX_NR_ZONES; zone++)
+ size += max(
+ READ_ONCE(lrugen->nr_pages[gen][type][zone]),
+ 0L);
+
+ gen_start = get_gen_start_time(lrugen, seq, max_seq,
+ curr_timestamp);
+ gen_end = READ_ONCE(lrugen->timestamps[gen]);
+
+ while (bin->idle_age != WORKINGSET_INTERVAL_MAX &&
+ time_before(gen_end + bin->idle_age, curr_timestamp)) {
+ unsigned long gen_in_bin = (long)gen_start -
+ (long)curr_timestamp +
+ (long)bin->idle_age;
+ unsigned long gen_len = (long)gen_start - (long)gen_end;
+
+ if (!gen_len)
+ break;
+ if (gen_in_bin) {
+ unsigned long split_bin =
+ size / gen_len * gen_in_bin;
+
+ bin->nr_pages[type] += split_bin;
+ size -= split_bin;
+ }
+ gen_start = curr_timestamp - bin->idle_age;
+ bin++;
+ }
+ bin->nr_pages[type] += size;
+ }
+}
+
+/*
+ * proportionally aggregate Multi-gen LRU bins into a working set report
+ * MGLRU generations:
+ * current time
+ * | max_seq timestamp
+ * | | max_seq - 1 timestamp
+ * | | | unbounded
+ * | | | |
+ * --------------------------------
+ * | max_seq | ... | ... | min_seq
+ * --------------------------------
+ *
+ * Bins:
+ *
+ * current time
+ * | current - idle_age[0]
+ * | | current - idle_age[1]
+ * | | | unbounded
+ * | | | |
+ * ------------------------------
+ * | bin 0 | ... | ... | bin n-1
+ * ------------------------------
+ *
+ * Assume the heuristic that pages are in the MGLRU generation
+ * through uniform accesses, so we can aggregate them
+ * proportionally into bins.
+ */
+static void collect_page_age(struct wsr_page_age_histo *page_age,
+ const struct lruvec *lruvec)
+{
+ int type;
+ const struct lru_gen_folio *lrugen = &lruvec->lrugen;
+ unsigned long curr_timestamp = jiffies;
+ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq);
+ unsigned long min_seq[ANON_AND_FILE] = {
+ READ_ONCE(lruvec->lrugen.min_seq[LRU_GEN_ANON]),
+ READ_ONCE(lruvec->lrugen.min_seq[LRU_GEN_FILE]),
+ };
+ struct wsr_report_bin *bin = &page_age->bins[0];
+
+ for (type = 0; type < ANON_AND_FILE; type++)
+ collect_page_age_type(lrugen, bin, max_seq, min_seq[type],
+ curr_timestamp, type);
+}
+
+/* First step: hierarchically scan child memcgs. */
+static void refresh_scan(struct wsr_state *wsr, struct mem_cgroup *root,
+ struct pglist_data *pgdat)
+{
+ struct mem_cgroup *memcg;
+ unsigned int flags;
+ struct reclaim_state rs = { 0 };
+
+ set_task_reclaim_state(current, &rs);
+ flags = memalloc_noreclaim_save();
+
+ memcg = mem_cgroup_iter(root, NULL, NULL);
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq);
+
+ /*
+ * setting can_swap=true and force_scan=true ensures
+ * proper workingset stats when the system cannot swap.
+ */
+ try_to_inc_max_seq(lruvec, max_seq, true, true);
+ cond_resched();
+ } while ((memcg = mem_cgroup_iter(root, memcg, NULL)));
+
+ memalloc_noreclaim_restore(flags);
+ set_task_reclaim_state(current, NULL);
+}
+
+/* Second step: aggregate child memcgs into the page age histogram. */
+static void refresh_aggregate(struct wsr_page_age_histo *page_age,
+ struct mem_cgroup *root,
+ struct pglist_data *pgdat)
+{
+ struct mem_cgroup *memcg;
+ struct wsr_report_bin *bin;
+
+ for (bin = page_age->bins;
+ bin->idle_age != WORKINGSET_INTERVAL_MAX; bin++) {
+ bin->nr_pages[0] = 0;
+ bin->nr_pages[1] = 0;
+ }
+ /* the last used bin has idle_age == WORKINGSET_INTERVAL_MAX. */
+ bin->nr_pages[0] = 0;
+ bin->nr_pages[1] = 0;
+
+ memcg = mem_cgroup_iter(root, NULL, NULL);
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+ collect_page_age(page_age, lruvec);
+ cond_resched();
+ } while ((memcg = mem_cgroup_iter(root, memcg, NULL)));
+ WRITE_ONCE(page_age->timestamp, jiffies);
+}
+
+static void copy_node_bins(struct pglist_data *pgdat,
+ struct wsr_page_age_histo *page_age)
+{
+ struct wsr_report_bins *node_page_age_bins;
+ int i = 0;
+
+ rcu_read_lock();
+ node_page_age_bins = rcu_dereference(pgdat->wsr_page_age_bins);
+ if (!node_page_age_bins)
+ goto nocopy;
+ for (i = 0; i < node_page_age_bins->nr_bins; ++i)
+ page_age->bins[i].idle_age = node_page_age_bins->idle_age[i];
+
+nocopy:
+ page_age->bins[i].idle_age = WORKINGSET_INTERVAL_MAX;
+ rcu_read_unlock();
+}
+
+bool wsr_refresh_report(struct wsr_state *wsr, struct mem_cgroup *root,
+ struct pglist_data *pgdat)
+{
+ struct wsr_page_age_histo *page_age;
+
+ if (!READ_ONCE(wsr->page_age))
+ return false;
+
+ refresh_scan(wsr, root, pgdat);
+ mutex_lock(&wsr->page_age_lock);
+ page_age = READ_ONCE(wsr->page_age);
+ if (page_age) {
+ copy_node_bins(pgdat, page_age);
+ refresh_aggregate(page_age, root, pgdat);
+ }
+ mutex_unlock(&wsr->page_age_lock);
+ return !!page_age;
+}
+EXPORT_SYMBOL_GPL(wsr_refresh_report);
+
+static struct pglist_data *kobj_to_pgdat(struct kobject *kobj)
+{
+ int nid = IS_ENABLED(CONFIG_NUMA) ? kobj_to_dev(kobj)->id :
+ first_memory_node;
+
+ return NODE_DATA(nid);
+}
+
+static struct wsr_state *kobj_to_wsr(struct kobject *kobj)
+{
+ return &mem_cgroup_lruvec(NULL, kobj_to_pgdat(kobj))->wsr;
+}
+
+static ssize_t page_age_intervals_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct wsr_report_bins *bins;
+ int len = 0;
+ struct pglist_data *pgdat = kobj_to_pgdat(kobj);
+
+ rcu_read_lock();
+ bins = rcu_dereference(pgdat->wsr_page_age_bins);
+ if (bins) {
+ int i;
+ int nr_bins = bins->nr_bins;
+
+ for (i = 0; i < bins->nr_bins; ++i) {
+ len += sysfs_emit_at(
+ buf, len, "%u",
+ jiffies_to_msecs(bins->idle_age[i]));
+ if (i + 1 < nr_bins)
+ len += sysfs_emit_at(buf, len, ",");
+ }
+ }
+ len += sysfs_emit_at(buf, len, "\n");
+ rcu_read_unlock();
+
+ return len;
+}
+
+static ssize_t page_age_intervals_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *src, size_t len)
+{
+ struct wsr_report_bins *bins = NULL, __rcu *old;
+ char *buf = NULL;
+ int err = 0;
+ struct pglist_data *pgdat = kobj_to_pgdat(kobj);
+
+ buf = kstrdup(src, GFP_KERNEL);
+ if (!buf) {
+ err = -ENOMEM;
+ goto failed;
+ }
+
+ bins =
+ kzalloc(sizeof(struct wsr_report_bins), GFP_KERNEL);
+
+ if (!bins) {
+ err = -ENOMEM;
+ goto failed;
+ }
+
+ err = workingset_report_intervals_parse(buf, bins);
+ if (err < 0)
+ goto failed;
+
+ if (err == 0) {
+ kfree(bins);
+ bins = NULL;
+ }
+
+ mutex_lock(&pgdat->wsr_update_mutex);
+ old = rcu_replace_pointer(pgdat->wsr_page_age_bins, bins,
+ lockdep_is_held(&pgdat->wsr_update_mutex));
+ mutex_unlock(&pgdat->wsr_update_mutex);
+ kfree_rcu(old, rcu);
+ kfree(buf);
+ return len;
+failed:
+ kfree(bins);
+ kfree(buf);
+
+ return err;
+}
+
+static struct kobj_attribute page_age_intervals_attr =
+ __ATTR_RW(page_age_intervals);
+
+static ssize_t page_age_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct wsr_report_bin *bin;
+ int ret = 0;
+ struct wsr_state *wsr = kobj_to_wsr(kobj);
+
+
+ mutex_lock(&wsr->page_age_lock);
+ if (!wsr->page_age)
+ wsr->page_age =
+ kzalloc(sizeof(struct wsr_page_age_histo), GFP_KERNEL);
+ mutex_unlock(&wsr->page_age_lock);
+
+ wsr_refresh_report(wsr, NULL, kobj_to_pgdat(kobj));
+
+ mutex_lock(&wsr->page_age_lock);
+ if (!wsr->page_age)
+ goto unlock;
+ for (bin = wsr->page_age->bins;
+ bin->idle_age != WORKINGSET_INTERVAL_MAX; bin++)
+ ret += sysfs_emit_at(buf, ret, "%u anon=%lu file=%lu\n",
+ jiffies_to_msecs(bin->idle_age),
+ bin->nr_pages[0] * PAGE_SIZE,
+ bin->nr_pages[1] * PAGE_SIZE);
+
+ ret += sysfs_emit_at(buf, ret, "%lu anon=%lu file=%lu\n",
+ WORKINGSET_INTERVAL_MAX,
+ bin->nr_pages[0] * PAGE_SIZE,
+ bin->nr_pages[1] * PAGE_SIZE);
+
+unlock:
+ mutex_unlock(&wsr->page_age_lock);
+ return ret;
+}
+
+static struct kobj_attribute page_age_attr = __ATTR_RO(page_age);
+
+static struct attribute *workingset_report_attrs[] = {
+ &page_age_intervals_attr.attr, &page_age_attr.attr, NULL
+};
+
+static const struct attribute_group workingset_report_attr_group = {
+ .name = "workingset_report",
+ .attrs = workingset_report_attrs,
+};
+
+void wsr_init_sysfs(struct node *node)
+{
+ struct kobject *kobj = node ? &node->dev.kobj : mm_kobj;
+ struct wsr_state *wsr;
+
+ if (IS_ENABLED(CONFIG_NUMA) && !node)
+ return;
+
+ wsr = kobj_to_wsr(kobj);
+
+ if (sysfs_create_group(kobj, &workingset_report_attr_group))
+ pr_warn("Workingset report failed to create sysfs files\n");
+}
+EXPORT_SYMBOL_GPL(wsr_init_sysfs);
+
+void wsr_remove_sysfs(struct node *node)
+{
+ struct kobject *kobj = &node->dev.kobj;
+ struct wsr_state *wsr;
+
+ if (IS_ENABLED(CONFIG_NUMA) && !node)
+ return;
+
+ wsr = kobj_to_wsr(kobj);
+ sysfs_remove_group(kobj, &workingset_report_attr_group);
+}
+EXPORT_SYMBOL_GPL(wsr_remove_sysfs);
Hierarchically aggregate all memcgs' MGLRU generations and their page counts into working set page age histograms. The histograms break down the system's working set per-node, per-anon/file. The sysfs interfaces are as follows: /sys/devices/system/node/nodeX/page_age A per-node page age histogram, showing an aggregate of the node's lruvecs. The information is extracted from MGLRU's per-generation page counters. Reading this file causes a hierarchical aging of all lruvecs, scanning pages and creates a new generation in each lruvec. For example: 1000 anon=0 file=0 2000 anon=0 file=0 100000 anon=5533696 file=5566464 18446744073709551615 anon=0 file=0 /sys/devices/system/node/nodeX/page_age_interval A comma separated list of time in milliseconds that configures what the page age histogram uses for aggregation. Signed-off-by: Yuanchu Xie <yuanchu@google.com> --- drivers/base/node.c | 6 + include/linux/mmzone.h | 9 + include/linux/workingset_report.h | 79 ++++++ mm/Kconfig | 9 + mm/Makefile | 1 + mm/internal.h | 4 + mm/memcontrol.c | 2 + mm/mm_init.c | 2 + mm/mmzone.c | 2 + mm/vmscan.c | 10 +- mm/workingset_report.c | 451 ++++++++++++++++++++++++++++++ 11 files changed, 571 insertions(+), 4 deletions(-) create mode 100644 include/linux/workingset_report.h create mode 100644 mm/workingset_report.c