linux-kernel - [RFC PATCH 7/8] memcg: add sysctl and config option to control memory recharging

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230720070825.992023-8-yosryahmed@google.com>
Date:   Thu, 20 Jul 2023 07:08:24 +0000
From:   Yosry Ahmed <yosryahmed@...gle.com>
To:     Andrew Morton <akpm@...ux-foundation.org>,
        Johannes Weiner <hannes@...xchg.org>,
        Michal Hocko <mhocko@...nel.org>,
        Roman Gushchin <roman.gushchin@...ux.dev>,
        Shakeel Butt <shakeelb@...gle.com>
Cc:     Muchun Song <muchun.song@...ux.dev>,
        "Matthew Wilcox (Oracle)" <willy@...radead.org>,
        Tejun Heo <tj@...nel.org>, Zefan Li <lizefan.x@...edance.com>,
        Yu Zhao <yuzhao@...gle.com>,
        Luis Chamberlain <mcgrof@...nel.org>,
        Kees Cook <keescook@...omium.org>,
        Iurii Zaikin <yzaikin@...gle.com>,
        "T.J. Mercier" <tjmercier@...gle.com>,
        Greg Thelen <gthelen@...gle.com>, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, cgroups@...r.kernel.org,
        Yosry Ahmed <yosryahmed@...gle.com>
Subject: [RFC PATCH 7/8] memcg: add sysctl and config option to control memory recharging

Add a sysctl to enable/disable memory recharging for offline memcgs. Add
a config option to control whether or not it is enabled by default.

Signed-off-by: Yosry Ahmed <yosryahmed@...gle.com>
---
 include/linux/memcontrol.h |  2 ++
 kernel/sysctl.c            | 11 +++++++++++
 mm/Kconfig                 | 12 ++++++++++++
 mm/memcontrol.c            |  9 ++++++++-
 4 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 59b653d4a76e..ae9f09ee90cb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -60,6 +60,8 @@ struct mem_cgroup_reclaim_cookie {
 
 #ifdef CONFIG_MEMCG
 
+extern int sysctl_recharge_offline_memcgs;
+
 #define MEM_CGROUP_ID_SHIFT	16
 #define MEM_CGROUP_ID_MAX	USHRT_MAX
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 354a2d294f52..1735d1d95652 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2249,6 +2249,17 @@ static struct ctl_table vm_table[] = {
 		.extra2		= (void *)&mmap_rnd_compat_bits_max,
 	},
 #endif
+#ifdef CONFIG_MEMCG
+	{
+		.procname	= "recharge_offline_memcgs",
+		.data		= &sysctl_recharge_offline_memcgs,
+		.maxlen		= sizeof(sysctl_recharge_offline_memcgs),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_MEMCG */
 	{ }
 };
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 09130434e30d..9462c4b598d9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1236,6 +1236,18 @@ config LOCK_MM_AND_FIND_VMA
 	bool
 	depends on !STACK_GROWSUP
 
+config MEMCG_RECHARGE_OFFLINE_ENABLED
+	bool "Recharge memory charged to offline memcgs"
+	depends on MEMCG
+	help
+	  When a memory cgroup is removed by userspace, try to recharge any
+	  memory still charged to it to avoid having it live on as an offline
+	  memcg. Offline memcgs potentially consume memory and limit scalability
+	  of some operations.
+
+	  This option enables the above behavior by default. It can be override
+	  at runtime through /proc/sys/vm/recharge_offline_memcgs.
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2fe9c6f1be80..25cdb17eaaa3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -96,6 +96,9 @@ static bool cgroup_memory_nobpf __ro_after_init;
 static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
 #endif
 
+int sysctl_recharge_offline_memcgs __read_mostly = IS_ENABLED(
+		CONFIG_MEMCG_RECHARGE_OFFLINE_ENABLED);
+
 static struct workqueue_struct *memcg_recharge_wq;
 
 /* Whether legacy memory+swap accounting is active */
@@ -6592,7 +6595,8 @@ static void memcg_recharge_mapped_folios(struct mem_cgroup *memcg)
 	INIT_DELAYED_WORK(&memcg->recharge_mapped_work.dwork,
 			  memcg_do_recharge_mapped_folios);
 
-	if (memcg_recharge_wq && memcg_nr_local_mapped_pages(memcg)) {
+	if (sysctl_recharge_offline_memcgs &&
+	    memcg_recharge_wq && memcg_nr_local_mapped_pages(memcg)) {
 		memcg->recharge_mapped_work.retries = 0;
 		queue_delayed_work(memcg_recharge_wq,
 				   &memcg->recharge_mapped_work.dwork, 0);
@@ -6605,6 +6609,9 @@ static bool should_do_deferred_recharge(struct folio *folio)
 	struct mem_cgroup *memcg;
 	bool ret;
 
+	if (!sysctl_recharge_offline_memcgs)
+		return false;
+
 	rcu_read_lock();
 	memcg = folio_memcg_rcu(folio);
 	ret = memcg && !!(memcg->css.flags & CSS_DYING);
-- 
2.41.0.255.g8b1d071c50-goog