From nobody Wed Dec 17 21:01:14 2025 Received: from mail-ot1-f74.google.com (mail-ot1-f74.google.com [209.85.210.74]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id BADCD13C9A6 for ; Wed, 27 Nov 2024 02:57:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.210.74 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1732676274; cv=none; b=FMq/XXFowj+BzU2+ZinA9jmLEgB9a8pmYTEde1pZrYgbovI+2xIo6MEScn4nSb6P28yrRXDchBEew76pFCCvcpaqo/WDKSADnskkTkISb5PiFDXia+Omrig5/kuZOO7l/a5D0BrJxSq4EUIK95umBAFtvqVr1EtqbGJqwD/+MKU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1732676274; c=relaxed/simple; bh=V6k0txrQlFv9KlwsPqEDYN3s9mdMxMCtyYB6v1OxMUM=; h=Date:In-Reply-To:Mime-Version:References:Message-ID:Subject:From: To:Cc:Content-Type; b=OzBCUkIV4ZS4Sbz8WUX48T0JrwjJQCrOD8jfPPwo2bbsWmmwhXsXI6CZryzI+8eCFOhMlftIncGZx2iNc5m8ZwnURMF3hqPJ9a/2NgAg2/YGyTBCJvaZG4s7JmBaAQXNYoVNvYSqwym/mJf/bzucAUeabd4UUHuVc931CXbQGOM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com; spf=pass smtp.mailfrom=flex--yuanchu.bounces.google.com; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b=qxOhoxnL; arc=none smtp.client-ip=209.85.210.74 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--yuanchu.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="qxOhoxnL" Received: by mail-ot1-f74.google.com with SMTP id 46e09a7af769-71d557437e0so1959458a34.3 for ; Tue, 26 Nov 2024 18:57:51 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1732676271; x=1733281071; darn=vger.kernel.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=nc9u6Gr3t/eex7ob4WWy8qTSgpDGth3PA2eslkY0ahg=; b=qxOhoxnLYDHR4Xgo5CxCeOucqTNPCWKooHyNfGYK+/clEqAwdX/B8nFqYS4Jw/Lq2l rKo8elFKlO4Ctj5x7HAueZC6EQ412iLYfGwks6jIKYSgVgq0sf1n1xp76xkXlobmmAoH 97YEPkwE3EEBe8+fhzWVi9jgVitMrtfDjceVi97sIk7UJ5HhUez2K/DM850yA2Wkk4e9 +QYTV88T+ELiJe8+DfHixh7CD86kN4EqUpa8daYOmnUrMsai2tpQMKrHfSwaw3BtBX2i JAeRSngZeywaD5/ZKGQ+zHxOLjTHTNIX4RaB8xYbBya/+K2at9bFlzSWNkj3wEI7NzGA NuUQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1732676271; x=1733281071; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=nc9u6Gr3t/eex7ob4WWy8qTSgpDGth3PA2eslkY0ahg=; b=eY7gR8dT4pu7wjxXQMFXYM/cNK8f1bwygrwNj8QK26sGg8VAHeSvWvqExd5c3RGTT9 eS6OLihms0oApTVqlZzLUK+1uudarJ5xo6OY6zPXoY9pwP1J4tigYUJWJxDUANKoWv/y 7EnyEt0b8S+/4tE5FIZFEHI09/bNNE7++X81tiZXpuVsT1Dl86oVIKVxvMVRkfmpJeKn Jtd5rd+XmfoLqqu6QGfqfMwrpswHCKE+sdyLtBNAGVuUKTe/J3K4zEyT9y4LalBdVSvb Y1P/yDsarTolW+w/JwaWpvfXqi7yyZehU3Rarv6FUgAaTH/vJwdJM393H69t8QHymrG4 8DqQ== X-Forwarded-Encrypted: i=1; AJvYcCW9LrF1+mjqojCkkYuuP9cxBREDpgPz0e+UxcIVfMtkUDbLWdELG8aCqlLKCPE2qFSOZXO4eOmTBHkhqNw=@vger.kernel.org X-Gm-Message-State: AOJu0YwEv9uQqezO1DP7cLI6jOubX+zoNOpGPZJ/Q5Yd70zOiXdlg2eY 4hGedWjSl0yvLr0rZMlXiUuWEMF8dqeCuDcJRm2M6MwqEzjwOkvFHND4TwgUDzBOH29iua9qg/S 3ObwYTg== X-Google-Smtp-Source: AGHT+IHgj0Am4IyS+M4OwpOyz4MtxJ9EoZ2BKJ1SYuM2EnZPBNIt4U8MU/D28Yi7V0kFKazRJu4A5wWgVUd3 X-Received: from pgbcz4.prod.google.com ([2002:a05:6a02:2304:b0:7fc:26c4:ff6c]) (user=yuanchu job=prod-delivery.src-stubby-dispatcher) by 2002:a05:6359:4ca0:b0:1ca:9e4a:d06 with SMTP id e5c5f4694b2df-1cab15f4bd5mr150435955d.13.1732676270571; Tue, 26 Nov 2024 18:57:50 -0800 (PST) Date: Tue, 26 Nov 2024 18:57:23 -0800 In-Reply-To: <20241127025728.3689245-1-yuanchu@google.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20241127025728.3689245-1-yuanchu@google.com> X-Mailer: git-send-email 2.47.0.338.g60cca15819-goog Message-ID: <20241127025728.3689245-5-yuanchu@google.com> Subject: [PATCH v4 4/9] mm: extend workingset reporting to memcgs From: Yuanchu Xie To: Andrew Morton , David Hildenbrand , "Aneesh Kumar K.V" , Khalid Aziz , Henry Huang , Yu Zhao , Dan Williams , Gregory Price , Huang Ying , Lance Yang , Randy Dunlap , Muhammad Usama Anjum Cc: Tejun Heo , Johannes Weiner , "=?UTF-8?q?Michal=20Koutn=C3=BD?=" , Jonathan Corbet , Greg Kroah-Hartman , "Rafael J. Wysocki" , "Michael S. Tsirkin" , Jason Wang , Xuan Zhuo , "=?UTF-8?q?Eugenio=20P=C3=A9rez?=" , Michal Hocko , Roman Gushchin , Shakeel Butt , Muchun Song , Mike Rapoport , Shuah Khan , Christian Brauner , Daniel Watson , Yuanchu Xie , cgroups@vger.kernel.org, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux.dev, linux-mm@kvack.org, linux-kselftest@vger.kernel.org Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Break down the system-wide workingset report into per-memcg reports, which aggregages its children hierarchically. The per-node workingset reporting histograms and refresh/report threshold files are presented as memcg files, showing a report containing all the nodes. The per-node page age interval is configurable in sysfs and not available per-memcg, while the refresh interval and report threshold are configured per-memcg. Memcg interface: /sys/fs/cgroup/.../memory.workingset.page_age The memcg equivalent of the sysfs workingset page age histogram breaks down the workingset of this memcg and its children into page age intervals. Each node is prefixed with a node header and a newline. Non-proactive direct reclaim on this memcg can also wake up userspace agents that are waiting on this file. e.g. N0 1000 anon=3D0 file=3D0 2000 anon=3D0 file=3D0 3000 anon=3D0 file=3D0 4000 anon=3D0 file=3D0 5000 anon=3D0 file=3D0 18446744073709551615 anon=3D0 file=3D0 /sys/fs/cgroup/.../memory.workingset.refresh_interval The memcg equivalent of the sysfs refresh interval. A per-node number of how much time a page age histogram is valid for, in milliseconds. e.g. echo N0=3D2000 > memory.workingset.refresh_interval /sys/fs/cgroup/.../memory.workingset.report_threshold The memcg equivalent of the sysfs report threshold. A per-node number of how often userspace agent waiting on the page age histogram can be woken up, in milliseconds. e.g. echo N0=3D1000 > memory.workingset.report_threshold Signed-off-by: Yuanchu Xie --- include/linux/memcontrol.h | 21 ++++ include/linux/workingset_report.h | 15 ++- mm/internal.h | 2 + mm/memcontrol.c | 160 +++++++++++++++++++++++++++++- mm/workingset_report.c | 50 +++++++--- 5 files changed, 230 insertions(+), 18 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e1b41554a5fb..fd595b33a54d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -323,6 +323,11 @@ struct mem_cgroup { spinlock_t event_list_lock; #endif /* CONFIG_MEMCG_V1 */ =20 +#ifdef CONFIG_WORKINGSET_REPORT + /* memory.workingset.page_age file */ + struct cgroup_file workingset_page_age_file; +#endif + struct mem_cgroup_per_node *nodeinfo[]; }; =20 @@ -1094,6 +1099,16 @@ static inline void memcg_memory_event_mm(struct mm_s= truct *mm, =20 void split_page_memcg(struct page *head, int old_order, int new_order); =20 +static inline struct cgroup_file * +mem_cgroup_page_age_file(struct mem_cgroup *memcg) +{ +#ifdef CONFIG_WORKINGSET_REPORT + return &memcg->workingset_page_age_file; +#else + return NULL; +#endif +} + #else /* CONFIG_MEMCG */ =20 #define MEM_CGROUP_ID_SHIFT 0 @@ -1511,6 +1526,12 @@ void count_memcg_event_mm(struct mm_struct *mm, enum= vm_event_item idx) static inline void split_page_memcg(struct page *head, int old_order, int = new_order) { } + +static inline struct cgroup_file * +mem_cgroup_page_age_file(struct mem_cgroup *memcg) +{ + return NULL; +} #endif /* CONFIG_MEMCG */ =20 /* diff --git a/include/linux/workingset_report.h b/include/linux/workingset_r= eport.h index 2ec8b927b200..616be6469768 100644 --- a/include/linux/workingset_report.h +++ b/include/linux/workingset_report.h @@ -9,6 +9,8 @@ struct mem_cgroup; struct pglist_data; struct node; struct lruvec; +struct cgroup_file; +struct wsr_state; =20 #ifdef CONFIG_WORKINGSET_REPORT =20 @@ -40,7 +42,10 @@ struct wsr_state { unsigned long report_threshold; unsigned long refresh_interval; =20 - struct kernfs_node *page_age_sys_file; + union { + struct kernfs_node *page_age_sys_file; + struct cgroup_file *page_age_cgroup_file; + }; =20 /* breakdown of workingset by page age */ struct mutex page_age_lock; @@ -60,6 +65,9 @@ void wsr_remove_sysfs(struct node *node); */ bool wsr_refresh_report(struct wsr_state *wsr, struct mem_cgroup *root, struct pglist_data *pgdat); + +int wsr_set_refresh_interval(struct wsr_state *wsr, + unsigned long refresh_interval); #else static inline void wsr_init_lruvec(struct lruvec *lruvec) { @@ -79,6 +87,11 @@ static inline void wsr_init_sysfs(struct node *node) static inline void wsr_remove_sysfs(struct node *node) { } +static inline int wsr_set_refresh_interval(struct wsr_state *wsr, + unsigned long refresh_interval) +{ + return 0; +} #endif /* CONFIG_WORKINGSET_REPORT */ =20 #endif /* _LINUX_WORKINGSET_REPORT_H */ diff --git a/mm/internal.h b/mm/internal.h index 508b7d9937d6..50ca0c6e651c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -484,6 +484,8 @@ void set_task_reclaim_state(struct task_struct *task, s= truct reclaim_state *rs); * in mm/wsr.c */ void notify_workingset(struct mem_cgroup *memcg, struct pglist_data *pgdat= ); +int workingset_report_intervals_parse(char *src, + struct wsr_report_bins *bins); #else static inline void notify_workingset(struct mem_cgroup *memcg, struct pglist_data *pgdat) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 096856b35fbc..d1032c6efc66 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4348,6 +4348,144 @@ static ssize_t memory_reclaim(struct kernfs_open_fi= le *of, char *buf, return nbytes; } =20 +#ifdef CONFIG_WORKINGSET_REPORT +static int memory_ws_refresh_interval_show(struct seq_file *m, void *v) +{ + int nid; + struct mem_cgroup *memcg =3D mem_cgroup_from_seq(m); + + for_each_node_state(nid, N_MEMORY) { + struct wsr_state *wsr =3D + &mem_cgroup_lruvec(memcg, NODE_DATA(nid))->wsr; + + seq_printf(m, "N%d=3D%u ", nid, + jiffies_to_msecs(READ_ONCE(wsr->refresh_interval))); + } + seq_putc(m, '\n'); + + return 0; +} + +static ssize_t memory_wsr_threshold_parse(char *buf, size_t nbytes, + unsigned int *nid_out, + unsigned int *msecs) +{ + char *node, *threshold; + unsigned int nid; + int err; + + buf =3D strstrip(buf); + threshold =3D buf; + node =3D strsep(&threshold, "=3D"); + + if (*node !=3D 'N') + return -EINVAL; + + err =3D kstrtouint(node + 1, 0, &nid); + if (err) + return err; + + if (nid >=3D nr_node_ids || !node_state(nid, N_MEMORY)) + return -EINVAL; + + err =3D kstrtouint(threshold, 0, msecs); + if (err) + return err; + + *nid_out =3D nid; + + return nbytes; +} + +static ssize_t memory_ws_refresh_interval_write(struct kernfs_open_file *o= f, + char *buf, size_t nbytes, + loff_t off) +{ + unsigned int nid, msecs; + struct wsr_state *wsr; + struct mem_cgroup *memcg =3D mem_cgroup_from_css(of_css(of)); + ssize_t ret =3D memory_wsr_threshold_parse(buf, nbytes, &nid, &msecs); + + if (ret < 0) + return ret; + + wsr =3D &mem_cgroup_lruvec(memcg, NODE_DATA(nid))->wsr; + + ret =3D wsr_set_refresh_interval(wsr, msecs); + return ret ?: nbytes; +} + +static int memory_ws_report_threshold_show(struct seq_file *m, void *v) +{ + int nid; + struct mem_cgroup *memcg =3D mem_cgroup_from_seq(m); + + for_each_node_state(nid, N_MEMORY) { + struct wsr_state *wsr =3D + &mem_cgroup_lruvec(memcg, NODE_DATA(nid))->wsr; + + seq_printf(m, "N%d=3D%u ", nid, + jiffies_to_msecs(READ_ONCE(wsr->report_threshold))); + } + seq_putc(m, '\n'); + + return 0; +} + +static ssize_t memory_ws_report_threshold_write(struct kernfs_open_file *o= f, + char *buf, size_t nbytes, + loff_t off) +{ + unsigned int nid, msecs; + struct wsr_state *wsr; + struct mem_cgroup *memcg =3D mem_cgroup_from_css(of_css(of)); + ssize_t ret =3D memory_wsr_threshold_parse(buf, nbytes, &nid, &msecs); + + if (ret < 0) + return ret; + + wsr =3D &mem_cgroup_lruvec(memcg, NODE_DATA(nid))->wsr; + WRITE_ONCE(wsr->report_threshold, msecs_to_jiffies(msecs)); + return ret; +} + +static int memory_ws_page_age_show(struct seq_file *m, void *v) +{ + int nid; + struct mem_cgroup *memcg =3D mem_cgroup_from_seq(m); + + for_each_node_state(nid, N_MEMORY) { + struct wsr_state *wsr =3D + &mem_cgroup_lruvec(memcg, NODE_DATA(nid))->wsr; + struct wsr_report_bin *bin; + + if (!READ_ONCE(wsr->page_age)) + continue; + + wsr_refresh_report(wsr, memcg, NODE_DATA(nid)); + mutex_lock(&wsr->page_age_lock); + if (!wsr->page_age) + goto unlock; + seq_printf(m, "N%d\n", nid); + for (bin =3D wsr->page_age->bins; + bin->idle_age !=3D WORKINGSET_INTERVAL_MAX; bin++) + seq_printf(m, "%u anon=3D%lu file=3D%lu\n", + jiffies_to_msecs(bin->idle_age), + bin->nr_pages[0] * PAGE_SIZE, + bin->nr_pages[1] * PAGE_SIZE); + + seq_printf(m, "%lu anon=3D%lu file=3D%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 0; +} +#endif + static struct cftype memory_files[] =3D { { .name =3D "current", @@ -4419,7 +4557,27 @@ static struct cftype memory_files[] =3D { .flags =3D CFTYPE_NS_DELEGATABLE, .write =3D memory_reclaim, }, - { } /* terminate */ +#ifdef CONFIG_WORKINGSET_REPORT + { + .name =3D "workingset.refresh_interval", + .flags =3D CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE, + .seq_show =3D memory_ws_refresh_interval_show, + .write =3D memory_ws_refresh_interval_write, + }, + { + .name =3D "workingset.report_threshold", + .flags =3D CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE, + .seq_show =3D memory_ws_report_threshold_show, + .write =3D memory_ws_report_threshold_write, + }, + { + .name =3D "workingset.page_age", + .flags =3D CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE, + .file_offset =3D offsetof(struct mem_cgroup, workingset_page_age_file), + .seq_show =3D memory_ws_page_age_show, + }, +#endif + {} /* terminate */ }; =20 struct cgroup_subsys memory_cgrp_subsys =3D { diff --git a/mm/workingset_report.c b/mm/workingset_report.c index bbefb0046669..1e1bdb8bf75b 100644 --- a/mm/workingset_report.c +++ b/mm/workingset_report.c @@ -37,9 +37,12 @@ void wsr_destroy_pgdat(struct pglist_data *pgdat) void wsr_init_lruvec(struct lruvec *lruvec) { struct wsr_state *wsr =3D &lruvec->wsr; + struct mem_cgroup *memcg =3D lruvec_memcg(lruvec); =20 memset(wsr, 0, sizeof(*wsr)); mutex_init(&wsr->page_age_lock); + if (memcg && !mem_cgroup_is_root(memcg)) + wsr->page_age_cgroup_file =3D mem_cgroup_page_age_file(memcg); } =20 void wsr_destroy_lruvec(struct lruvec *lruvec) @@ -51,8 +54,8 @@ void wsr_destroy_lruvec(struct lruvec *lruvec) memset(wsr, 0, sizeof(*wsr)); } =20 -static int workingset_report_intervals_parse(char *src, - struct wsr_report_bins *bins) +int workingset_report_intervals_parse(char *src, + struct wsr_report_bins *bins) { int err =3D 0, i =3D 0; char *cur, *next =3D strim(src); @@ -356,20 +359,14 @@ static ssize_t refresh_interval_show(struct kobject *= kobj, return sysfs_emit(buf, "%u\n", jiffies_to_msecs(interval)); } =20 -static ssize_t refresh_interval_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t len) +int wsr_set_refresh_interval(struct wsr_state *wsr, + unsigned long refresh_interval) { - unsigned int interval; - int err; - struct wsr_state *wsr =3D kobj_to_wsr(kobj); - - err =3D kstrtouint(buf, 0, &interval); - if (err) - return err; + int err =3D 0; + unsigned long old_interval =3D 0; =20 mutex_lock(&wsr->page_age_lock); - if (interval && !wsr->page_age) { + if (refresh_interval && !wsr->page_age) { struct wsr_page_age_histo *page_age =3D kzalloc(sizeof(struct wsr_page_age_histo), GFP_KERNEL); =20 @@ -377,16 +374,34 @@ static ssize_t refresh_interval_store(struct kobject = *kobj, err =3D -ENOMEM; goto unlock; } + page_age->bins[0].idle_age =3D WORKINGSET_INTERVAL_MAX; wsr->page_age =3D page_age; } - if (!interval && wsr->page_age) { + if (!refresh_interval && wsr->page_age) { kfree(wsr->page_age); wsr->page_age =3D NULL; } =20 - WRITE_ONCE(wsr->refresh_interval, msecs_to_jiffies(interval)); + old_interval =3D READ_ONCE(wsr->refresh_interval); + WRITE_ONCE(wsr->refresh_interval, msecs_to_jiffies(refresh_interval)); unlock: mutex_unlock(&wsr->page_age_lock); + return err; +} + +static ssize_t refresh_interval_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + unsigned int interval; + int err; + struct wsr_state *wsr =3D kobj_to_wsr(kobj); + + err =3D kstrtouint(buf, 0, &interval); + if (err) + return err; + + err =3D wsr_set_refresh_interval(wsr, interval); return err ?: len; } =20 @@ -551,5 +566,8 @@ void notify_workingset(struct mem_cgroup *memcg, struct= pglist_data *pgdat) { struct wsr_state *wsr =3D &mem_cgroup_lruvec(memcg, pgdat)->wsr; =20 - kernfs_notify(wsr->page_age_sys_file); + if (mem_cgroup_is_root(memcg)) + kernfs_notify(wsr->page_age_sys_file); + else + cgroup_file_notify(wsr->page_age_cgroup_file); } --=20 2.47.0.338.g60cca15819-goog