linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Huan Yang <link@vivo.com>
To: Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Roman Gushchin <roman.gushchin@linux.dev>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	Muchun Song <muchun.song@linux.dev>,
	Andrew Morton <akpm@linux-foundation.org>,
	Petr Mladek <pmladek@suse.com>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Huan Yang <link@vivo.com>, Francesco Valla <francesco@valla.it>,
	Huang Shijie <shijie@os.amperecomputing.com>,
	KP Singh <kpsingh@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Rasmus Villemoes <linux@rasmusvillemoes.dk>,
	"Uladzislau Rezki (Sony)" <urezki@gmail.com>,
	Guo Weikang <guoweikang.kernel@gmail.com>,
	Raul E Rangel <rrangel@chromium.org>,
	cgroups@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, Boqun Feng <boqun.feng@gmail.com>,
	Geert Uytterhoeven <geert@linux-m68k.org>,
	Paul Moore <paul@paul-moore.com>,
	"Mike Rapoport (Microsoft)" <rppt@kernel.org>
Cc: opensource.kernel@vivo.com
Subject: [PATCH v2 3/3] mm/memcg: introduce mem_cgroup_early_init
Date: Thu, 24 Apr 2025 20:09:29 +0800	[thread overview]
Message-ID: <20250424120937.96164-4-link@vivo.com> (raw)
In-Reply-To: <20250424120937.96164-1-link@vivo.com>

When cgroup_init() creates root_mem_cgroup through css_online callback,
some critical resources might not be fully initialized, forcing later
operations to perform conditional checks for resource availability.

This patch introduces mem_cgroup_early_init() to address the init order,
it invoke before cgroup_init, so, compare mem_cgroup_init which invoked
by initcall, mem_cgroup_early_init can use to prepare some key resources
before root_mem_cgroup alloc.

Signed-off-by: Huan Yang <link@vivo.com>
Suggested-by: Shakeel Butt <shakeel.butt@linux.dev>
---
 include/linux/memcontrol.h |  5 +++++
 init/main.c                |  2 ++
 mm/memcontrol.c            | 40 +++++++++++++++++++++++---------------
 3 files changed, 31 insertions(+), 16 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5264d148bdd9..231f3c577294 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1057,6 +1057,7 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
 	return id;
 }
 
+extern void mem_cgroup_early_init(void);
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
@@ -1472,6 +1473,10 @@ static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
 {
 	return 0;
 }
+
+static inline void mem_cgroup_early_init(void)
+{
+}
 #endif /* CONFIG_MEMCG */
 
 /*
diff --git a/init/main.c b/init/main.c
index 6b14e6116a1f..fd59d5ba2dc7 100644
--- a/init/main.c
+++ b/init/main.c
@@ -50,6 +50,7 @@
 #include <linux/writeback.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
+#include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/efi.h>
 #include <linux/tick.h>
@@ -1087,6 +1088,7 @@ void start_kernel(void)
 	nsfs_init();
 	pidfs_init();
 	cpuset_init();
+	mem_cgroup_early_init();
 	cgroup_init();
 	taskstats_init_early();
 	delayacct_init();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e8797382aeb4..bef1be3aad6f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3602,10 +3602,8 @@ static bool alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
 
-	pn = likely(memcg_pn_cachep) ?
-		     kmem_cache_alloc_node(memcg_pn_cachep,
-					   GFP_KERNEL | __GFP_ZERO, node) :
-		     kzalloc_node(sizeof(*pn), GFP_KERNEL, node);
+	pn = kmem_cache_alloc_node(memcg_pn_cachep, GFP_KERNEL | __GFP_ZERO,
+				   node);
 	if (!pn)
 		return false;
 
@@ -3658,10 +3656,7 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 	int __maybe_unused i;
 	long error;
 
-	memcg = likely(memcg_cachep) ?
-			kmem_cache_zalloc(memcg_cachep, GFP_KERNEL) :
-			kzalloc(struct_size(memcg, nodeinfo, nr_node_ids),
-				GFP_KERNEL);
+	memcg = kmem_cache_zalloc(memcg_cachep, GFP_KERNEL);
 	if (!memcg)
 		return ERR_PTR(-ENOMEM);
 
@@ -5037,6 +5032,27 @@ static int __init cgroup_memory(char *s)
 }
 __setup("cgroup.memory=", cgroup_memory);
 
+/**
+ * Before cgroup_init() create root_mem_cgroup, we can prepare
+ * something in here which root_mem_cgroup may need.
+ * This currently initializes:
+ *   1) memcg_cachep  - kmem_cache for mem_cgroup struct allocations
+ *   2) memcg_pn_cachep - kmem_cache for mem_cgroup_per_node structs
+ *      (one per NUMA node)
+ */
+void __init mem_cgroup_early_init(void)
+{
+	struct mem_cgroup *memcg;
+	unsigned int memcg_size;
+
+	memcg_size = struct_size(memcg, nodeinfo, nr_node_ids);
+	memcg_cachep = kmem_cache_create("mem_cgroup", memcg_size, 0,
+					 SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL);
+
+	memcg_pn_cachep = KMEM_CACHE(mem_cgroup_per_node,
+				     SLAB_PANIC | SLAB_HWCACHE_ALIGN);
+}
+
 /*
  * subsys_initcall() for memory controller.
  *
@@ -5048,7 +5064,6 @@ __setup("cgroup.memory=", cgroup_memory);
 static int __init mem_cgroup_init(void)
 {
 	int cpu;
-	unsigned int memcg_size;
 
 	/*
 	 * Currently s32 type (can refer to struct batched_lruvec_stat) is
@@ -5065,13 +5080,6 @@ static int __init mem_cgroup_init(void)
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
 			  drain_local_stock);
 
-	memcg_size = struct_size_t(struct mem_cgroup, nodeinfo, nr_node_ids);
-	memcg_cachep = kmem_cache_create("mem_cgroup", memcg_size, 0,
-					 SLAB_PANIC | SLAB_HWCACHE_ALIGN, NULL);
-
-	memcg_pn_cachep = KMEM_CACHE(mem_cgroup_per_node,
-				     SLAB_PANIC | SLAB_HWCACHE_ALIGN);
-
 	return 0;
 }
 subsys_initcall(mem_cgroup_init);
-- 
2.48.1



  parent reply	other threads:[~2025-04-24 12:12 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-24 12:09 [PATCH v2 0/3] Use kmem_cache for memcg alloc Huan Yang
2025-04-24 12:09 ` [PATCH v2 1/3] mm/memcg: use kmem_cache when alloc memcg Huan Yang
2025-04-24 12:09 ` [PATCH v2 2/3] mm/memcg: use kmem_cache when alloc memcg pernode info Huan Yang
2025-04-24 12:09 ` Huan Yang [this message]
2025-04-24 16:00   ` [PATCH v2 3/3] mm/memcg: introduce mem_cgroup_early_init Shakeel Butt
2025-04-24 23:00     ` Shakeel Butt
2025-04-25  1:11       ` Huan Yang
2025-04-25  1:30         ` Shakeel Butt
2025-04-25  1:55           ` Huan Yang
2025-04-25  1:11     ` Huan Yang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250424120937.96164-4-link@vivo.com \
    --to=link@vivo.com \
    --cc=akpm@linux-foundation.org \
    --cc=bigeasy@linutronix.de \
    --cc=boqun.feng@gmail.com \
    --cc=cgroups@vger.kernel.org \
    --cc=francesco@valla.it \
    --cc=geert@linux-m68k.org \
    --cc=guoweikang.kernel@gmail.com \
    --cc=hannes@cmpxchg.org \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@rasmusvillemoes.dk \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=opensource.kernel@vivo.com \
    --cc=paul@paul-moore.com \
    --cc=paulmck@kernel.org \
    --cc=pmladek@suse.com \
    --cc=roman.gushchin@linux.dev \
    --cc=rppt@kernel.org \
    --cc=rrangel@chromium.org \
    --cc=shakeel.butt@linux.dev \
    --cc=shijie@os.amperecomputing.com \
    --cc=urezki@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox