Message-ID: <20240604020549.1017540-7-yuanchu@google.com>
Date: Mon,  3 Jun 2024 19:05:47 -0700
From: Yuanchu Xie <yuanchu@...gle.com>
To: David Hildenbrand <david@...hat.com>, "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>, 
	Khalid Aziz <khalid.aziz@...cle.com>, Henry Huang <henry.hj@...group.com>, 
	Yu Zhao <yuzhao@...gle.com>, Dan Williams <dan.j.williams@...el.com>, 
	Gregory Price <gregory.price@...verge.com>, Huang Ying <ying.huang@...el.com>, 
	Muhammad Usama Anjum <usama.anjum@...labora.com>
Cc: Kalesh Singh <kaleshsingh@...gle.com>, Wei Xu <weixugc@...gle.com>, 
	David Rientjes <rientjes@...gle.com>, Greg Kroah-Hartman <gregkh@...uxfoundation.org>, 
	"Rafael J. Wysocki" <rafael@...nel.org>, Andrew Morton <akpm@...ux-foundation.org>, 
	Johannes Weiner <hannes@...xchg.org>, Michal Hocko <mhocko@...nel.org>, 
	Roman Gushchin <roman.gushchin@...ux.dev>, Muchun Song <muchun.song@...ux.dev>, 
	Shuah Khan <shuah@...nel.org>, Yosry Ahmed <yosryahmed@...gle.com>, 
	Matthew Wilcox <willy@...radead.org>, Sudarshan Rajagopalan <quic_sudaraja@...cinc.com>, 
	Kairui Song <kasong@...cent.com>, "Michael S. Tsirkin" <mst@...hat.com>, 
	Vasily Averin <vasily.averin@...ux.dev>, Nhat Pham <nphamcs@...il.com>, 
	Miaohe Lin <linmiaohe@...wei.com>, Qi Zheng <zhengqi.arch@...edance.com>, 
	Abel Wu <wuyun.abel@...edance.com>, "Vishal Moola (Oracle)" <vishal.moola@...il.com>, 
	Kefeng Wang <wangkefeng.wang@...wei.com>, Yuanchu Xie <yuanchu@...gle.com>, 
	linux-kernel@...r.kernel.org, linux-mm@...ck.org, cgroups@...r.kernel.org, 
	linux-kselftest@...r.kernel.org
Subject: [PATCH v2 6/8] mm: add kernel aging thread for workingset reporting

For reliable and timely aging on memcgs, one has to read the page age
histograms on time. A kernel thread makes it easier by aging memcgs with
valid refresh_interval when they can be refreshed, and also reduces the
latency of any userspace consumers of the page age histogram.

The kerne aging thread is gated behind CONFIG_WORKINGSET_REPORT_AGING.
Debugging stats may be added in the future for when aging cannot
keep up with the configured refresh_interval.

Signed-off-by: Yuanchu Xie <yuanchu@...gle.com>
---
 include/linux/workingset_report.h |  11 ++-
 mm/Kconfig                        |   6 ++
 mm/Makefile                       |   1 +
 mm/memcontrol.c                   |   8 +-
 mm/workingset_report.c            |  15 +++-
 mm/workingset_report_aging.c      | 127 ++++++++++++++++++++++++++++++
 6 files changed, 162 insertions(+), 6 deletions(-)
 create mode 100644 mm/workingset_report_aging.c

diff --git a/include/linux/workingset_report.h b/include/linux/workingset_report.h
index ae412d408037..9294023db5a8 100644
--- a/include/linux/workingset_report.h
+++ b/include/linux/workingset_report.h
@@ -63,7 +63,16 @@ void wsr_remove_sysfs(struct node *node);
  * 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);
+			struct pglist_data *pgdat, unsigned long *refresh_time);
+
+#ifdef CONFIG_WORKINGSET_REPORT_AGING
+void wsr_wakeup_aging_thread(void);
+#else /* CONFIG_WORKINGSET_REPORT_AGING */
+static inline void wsr_wakeup_aging_thread(void)
+{
+}
+#endif /* CONFIG_WORKINGSET_REPORT_AGING */
+
 #else
 static inline void wsr_init_lruvec(struct lruvec *lruvec)
 {
diff --git a/mm/Kconfig b/mm/Kconfig
index 03927ed2adbd..f8ff41408b9c 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1258,6 +1258,12 @@ config WORKINGSET_REPORT
 	  This option exports stats and events giving the user more insight
 	  into its memory working set.
 
+config WORKINGSET_REPORT_AGING
+	bool "Workingset report kernel aging thread"
+	depends on WORKINGSET_REPORT
+	help
+	  Performs aging on memcgs with their configured refresh intervals.
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/Makefile b/mm/Makefile
index ed05af2bb3e3..e9c9048e1e09 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -97,6 +97,7 @@ 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
+obj-$(CONFIG_WORKINGSET_REPORT_AGING) += workingset_report_aging.o
 ifdef CONFIG_SWAP
 obj-$(CONFIG_MEMCG) += swap_cgroup.o
 endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 48cdc9422794..547a2161b7e2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -7281,12 +7281,12 @@ static ssize_t memory_ws_refresh_interval_write(struct kernfs_open_file *of,
 {
 	unsigned int nid, msecs;
 	struct wsr_state *wsr;
+	unsigned long old_interval;
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	ssize_t ret = memory_wsr_threshold_parse(buf, nbytes, &nid, &msecs);
 
 	if (ret < 0)
 		return ret;
-
 	wsr = &mem_cgroup_lruvec(memcg, NODE_DATA(nid))->wsr;
 
 	mutex_lock(&wsr->page_age_lock);
@@ -7305,9 +7305,13 @@ static ssize_t memory_ws_refresh_interval_write(struct kernfs_open_file *of,
 		wsr->page_age = NULL;
 	}
 
+	old_interval = READ_ONCE(wsr->refresh_interval);
 	WRITE_ONCE(wsr->refresh_interval, msecs_to_jiffies(msecs));
 unlock:
 	mutex_unlock(&wsr->page_age_lock);
+	if (ret > 0 && msecs &&
+	    (!old_interval || jiffies_to_msecs(old_interval) > msecs))
+		wsr_wakeup_aging_thread();
 	return ret;
 }
 
@@ -7358,7 +7362,7 @@ static int memory_ws_page_age_show(struct seq_file *m, void *v)
 		if (!READ_ONCE(wsr->page_age))
 			continue;
 
-		wsr_refresh_report(wsr, memcg, NODE_DATA(nid));
+		wsr_refresh_report(wsr, memcg, NODE_DATA(nid), NULL);
 		mutex_lock(&wsr->page_age_lock);
 		if (!wsr->page_age)
 			goto unlock;
diff --git a/mm/workingset_report.c b/mm/workingset_report.c
index 72f2cad85a0d..15118c4aecb1 100644
--- a/mm/workingset_report.c
+++ b/mm/workingset_report.c
@@ -274,7 +274,7 @@ static void copy_node_bins(struct pglist_data *pgdat,
 }
 
 bool wsr_refresh_report(struct wsr_state *wsr, struct mem_cgroup *root,
-			struct pglist_data *pgdat)
+			struct pglist_data *pgdat, unsigned long *refresh_time)
 {
 	struct wsr_page_age_histo *page_age;
 	unsigned long refresh_interval = READ_ONCE(wsr->refresh_interval);
@@ -291,10 +291,14 @@ bool wsr_refresh_report(struct wsr_state *wsr, struct mem_cgroup *root,
 		goto unlock;
 	if (page_age->timestamp &&
 	    time_is_after_jiffies(page_age->timestamp + refresh_interval))
-		goto unlock;
+		goto time;
 	refresh_scan(wsr, root, pgdat, refresh_interval);
 	copy_node_bins(pgdat, page_age);
 	refresh_aggregate(page_age, root, pgdat);
+
+time:
+	if (refresh_time)
+		*refresh_time = page_age->timestamp + refresh_interval;
 unlock:
 	mutex_unlock(&wsr->page_age_lock);
 	return !!page_age;
@@ -357,6 +361,7 @@ static ssize_t refresh_interval_store(struct kobject *kobj,
 	unsigned int interval;
 	int err;
 	struct wsr_state *wsr = kobj_to_wsr(kobj);
+	unsigned long old_interval = 0;
 
 	err = kstrtouint(buf, 0, &interval);
 	if (err)
@@ -378,9 +383,13 @@ static ssize_t refresh_interval_store(struct kobject *kobj,
 		wsr->page_age = NULL;
 	}
 
+	old_interval = READ_ONCE(wsr->refresh_interval);
 	WRITE_ONCE(wsr->refresh_interval, msecs_to_jiffies(interval));
 unlock:
 	mutex_unlock(&wsr->page_age_lock);
+	if (!err && interval &&
+	    (!old_interval || jiffies_to_msecs(old_interval) > interval))
+		wsr_wakeup_aging_thread();
 	return err ?: len;
 }
 
@@ -470,7 +479,7 @@ static ssize_t page_age_show(struct kobject *kobj, struct kobj_attribute *attr,
 	int ret = 0;
 	struct wsr_state *wsr = kobj_to_wsr(kobj);
 
-	wsr_refresh_report(wsr, NULL, kobj_to_pgdat(kobj));
+	wsr_refresh_report(wsr, NULL, kobj_to_pgdat(kobj), NULL);
 
 	mutex_lock(&wsr->page_age_lock);
 	if (!wsr->page_age)
diff --git a/mm/workingset_report_aging.c b/mm/workingset_report_aging.c
new file mode 100644
index 000000000000..91ad5020778a
--- /dev/null
+++ b/mm/workingset_report_aging.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Workingset report kernel aging thread
+ *
+ * Performs aging on behalf of memcgs with their configured refresh interval.
+ * While a userspace program can periodically read the page age breakdown
+ * per-memcg and trigger aging, the kernel performing aging is less overhead,
+ * more consistent, and more reliable for the use case where every memcg should
+ * be aged according to their refresh interval.
+ */
+#define pr_fmt(fmt) "workingset report aging: " fmt
+
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/kthread.h>
+#include <linux/memcontrol.h>
+#include <linux/swap.h>
+#include <linux/wait.h>
+#include <linux/mmzone.h>
+#include <linux/workingset_report.h>
+
+static DECLARE_WAIT_QUEUE_HEAD(aging_wait);
+static bool refresh_pending;
+
+static bool do_aging_node(int nid, unsigned long *next_wake_time)
+{
+	struct mem_cgroup *memcg;
+	bool should_wait = true;
+	struct pglist_data *pgdat = NODE_DATA(nid);
+
+	memcg = mem_cgroup_iter(NULL, NULL, NULL);
+	do {
+		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+		struct wsr_state *wsr = &lruvec->wsr;
+		unsigned long refresh_time;
+
+		/* use returned time to decide when to wake up next */
+		if (wsr_refresh_report(wsr, memcg, pgdat, &refresh_time)) {
+			if (should_wait) {
+				should_wait = false;
+				*next_wake_time = refresh_time;
+			} else if (time_before(refresh_time, *next_wake_time)) {
+				*next_wake_time = refresh_time;
+			}
+		}
+
+		cond_resched();
+	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+
+	return should_wait;
+}
+
+static int do_aging(void *unused)
+{
+	while (!kthread_should_stop()) {
+		int nid;
+		long timeout_ticks;
+		unsigned long next_wake_time;
+		bool should_wait = true;
+
+		WRITE_ONCE(refresh_pending, false);
+		for_each_node_state(nid, N_MEMORY) {
+			unsigned long node_next_wake_time;
+
+			if (do_aging_node(nid, &node_next_wake_time))
+				continue;
+			if (should_wait) {
+				should_wait = false;
+				next_wake_time = node_next_wake_time;
+			} else if (time_before(node_next_wake_time,
+					       next_wake_time)) {
+				next_wake_time = node_next_wake_time;
+			}
+		}
+
+		if (should_wait) {
+			wait_event_interruptible(aging_wait, refresh_pending);
+			continue;
+		}
+
+		/* sleep until next aging */
+		timeout_ticks = next_wake_time - jiffies;
+		if (timeout_ticks > 0 &&
+		    timeout_ticks != MAX_SCHEDULE_TIMEOUT) {
+			schedule_timeout_idle(timeout_ticks);
+			continue;
+		}
+	}
+	return 0;
+}
+
+/* Invoked when refresh_interval shortens or changes to a non-zero value. */
+void wsr_wakeup_aging_thread(void)
+{
+	WRITE_ONCE(refresh_pending, true);
+	wake_up_interruptible(&aging_wait);
+}
+
+static struct task_struct *aging_thread;
+
+static int aging_init(void)
+{
+	struct task_struct *task;
+
+	task = kthread_run(do_aging, NULL, "kagingd");
+
+	if (IS_ERR(task)) {
+		pr_err("Failed to create aging kthread\n");
+		return PTR_ERR(task);
+	}
+
+	aging_thread = task;
+	pr_info("module loaded\n");
+	return 0;
+}
+
+static void aging_exit(void)
+{
+	kthread_stop(aging_thread);
+	aging_thread = NULL;
+	pr_info("module unloaded\n");
+}
+
+module_init(aging_init);
+module_exit(aging_exit);
-- 
2.45.1.467.gbab1589fc0-goog

Powered by blists - more mailing lists