All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kuniyuki Iwashima <kuniyu@google.com>
To: "David S. Miller" <davem@davemloft.net>,
	"Eric Dumazet" <edumazet@google.com>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"Neal Cardwell" <ncardwell@google.com>,
	"Paolo Abeni" <pabeni@redhat.com>,
	"Willem de Bruijn" <willemb@google.com>,
	"Matthieu Baerts" <matttbe@kernel.org>,
	"Mat Martineau" <martineau@kernel.org>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"Michal Hocko" <mhocko@kernel.org>,
	"Roman Gushchin" <roman.gushchin@linux.dev>,
	"Shakeel Butt" <shakeel.butt@linux.dev>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Michal Koutný" <mkoutny@suse.com>, "Tejun Heo" <tj@kernel.org>
Cc: Simon Horman <horms@kernel.org>,
	Geliang Tang <geliang@kernel.org>,
	 Muchun Song <muchun.song@linux.dev>,
	Mina Almasry <almasrymina@google.com>,
	 Kuniyuki Iwashima <kuniyu@google.com>,
	Kuniyuki Iwashima <kuni1840@gmail.com>,
	netdev@vger.kernel.org,  mptcp@lists.linux.dev,
	cgroups@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v2 net-next 11/12] net-memcg: Store MEMCG_SOCK_ISOLATED in sk->sk_memcg.
Date: Mon, 11 Aug 2025 17:30:39 +0000	[thread overview]
Message-ID: <20250811173116.2829786-12-kuniyu@google.com> (raw)
In-Reply-To: <20250811173116.2829786-1-kuniyu@google.com>

We will decouple sockets from the global protocol memory accounting
if the cgroup's memory.max is not "max" (PAGE_COUNTER_MAX).

memory.max can change at any time, so we must snapshot the state
for each socket to ensure consistency.

Given sk->sk_memcg can be accessed in the fast path, it would
be preferable to place the flag field in the same cache line as
sk->sk_memcg.

However, struct sock does not have such a 1-byte hole.

Let's store the flag in the lowest bit of sk->sk_memcg and add
a helper to check the bit.

In the next patch, if mem_cgroup_sk_isolated() returns true,
the socket will not be charged to sk->sk_prot->memory_allocated.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
v2:
  * Set MEMCG_SOCK_ISOLATED based on memory.max instead of
    a dedicated knob
---
 include/net/sock.h | 23 ++++++++++++++++++++++-
 mm/memcontrol.c    | 14 ++++++++++++--
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 1c49ea13af4a..29ba5fdaafd6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2597,9 +2597,18 @@ static inline gfp_t gfp_memcg_charge(void)
 }
 
 #ifdef CONFIG_MEMCG
+
+#define MEMCG_SOCK_ISOLATED	1UL
+#define MEMCG_SOCK_FLAG_MASK	MEMCG_SOCK_ISOLATED
+#define MEMCG_SOCK_PTR_MASK	~(MEMCG_SOCK_FLAG_MASK)
+
 static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk)
 {
-	return sk->sk_memcg;
+	unsigned long val = (unsigned long)sk->sk_memcg;
+
+	val &= MEMCG_SOCK_PTR_MASK;
+
+	return (struct mem_cgroup *)val;
 }
 
 static inline bool mem_cgroup_sk_enabled(const struct sock *sk)
@@ -2607,6 +2616,13 @@ static inline bool mem_cgroup_sk_enabled(const struct sock *sk)
 	return mem_cgroup_sockets_enabled && mem_cgroup_from_sk(sk);
 }
 
+static inline bool mem_cgroup_sk_isolated(const struct sock *sk)
+{
+	struct mem_cgroup *memcg = sk->sk_memcg;
+
+	return (unsigned long)memcg & MEMCG_SOCK_ISOLATED;
+}
+
 static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_sk(sk);
@@ -2634,6 +2650,11 @@ static inline bool mem_cgroup_sk_enabled(const struct sock *sk)
 	return false;
 }
 
+static inline bool mem_cgroup_sk_isolated(const struct sock *sk)
+{
+	return false;
+}
+
 static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk)
 {
 	return false;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d32b7a547f42..cb5b8a9d21db 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4995,6 +4995,16 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new)
 DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
 EXPORT_SYMBOL(memcg_sockets_enabled_key);
 
+static void mem_cgroup_sk_set(struct sock *sk, const struct mem_cgroup *memcg)
+{
+	unsigned long val = (unsigned long)memcg;
+
+	if (READ_ONCE(memcg->memory.max) != PAGE_COUNTER_MAX)
+		val |= MEMCG_SOCK_ISOLATED;
+
+	sk->sk_memcg = (struct mem_cgroup *)val;
+}
+
 void mem_cgroup_sk_alloc(struct sock *sk)
 {
 	struct mem_cgroup *memcg;
@@ -5013,7 +5023,7 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg1_tcpmem_active(memcg))
 		goto out;
 	if (css_tryget(&memcg->css))
-		sk->sk_memcg = memcg;
+		mem_cgroup_sk_set(sk, memcg);
 out:
 	rcu_read_unlock();
 }
@@ -5035,7 +5045,7 @@ void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk)
 
 	mem_cgroup_sk_free(newsk);
 	css_get(&memcg->css);
-	newsk->sk_memcg = memcg;
+	mem_cgroup_sk_set(newsk, memcg);
 }
 
 /**
-- 
2.51.0.rc0.155.g4a0f42376b-goog


  parent reply	other threads:[~2025-08-11 17:31 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-11 17:30 [PATCH v2 net-next 00/12] net-memcg: Decouple controlled memcg from sk->sk_prot->memory_allocated Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 01/12] mptcp: Fix up subflow's memcg when CONFIG_SOCK_CGROUP_DATA=n Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 02/12] mptcp: Use tcp_under_memory_pressure() in mptcp_epollin_ready() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 03/12] tcp: Simplify error path in inet_csk_accept() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 04/12] net: Call trace_sock_exceed_buf_limit() for memcg failure with SK_MEM_RECV Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 05/12] net: Clean up __sk_mem_raise_allocated() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 06/12] net-memcg: Introduce mem_cgroup_from_sk() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 07/12] net-memcg: Introduce mem_cgroup_sk_enabled() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 08/12] net-memcg: Pass struct sock to mem_cgroup_sk_(un)?charge() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 09/12] net-memcg: Pass struct sock to mem_cgroup_sk_under_memory_pressure() Kuniyuki Iwashima
2025-08-11 17:30 ` [PATCH v2 net-next 10/12] net: Define sk_memcg under CONFIG_MEMCG Kuniyuki Iwashima
2025-08-11 17:30 ` Kuniyuki Iwashima [this message]
2025-08-11 17:30 ` [PATCH v2 net-next 12/12] net-memcg: Decouple controlled memcg from global protocol memory accounting Kuniyuki Iwashima
2025-08-12 15:08   ` kernel test robot
2025-08-12 15:55     ` Kuniyuki Iwashima
2025-08-11 20:05 ` [PATCH v2 net-next 00/12] net-memcg: Decouple controlled memcg from sk->sk_prot->memory_allocated MPTCP CI
2025-08-12  7:46 ` [syzbot ci] " syzbot ci

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=20250811173116.2829786-12-kuniyu@google.com \
    --to=kuniyu@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=almasrymina@google.com \
    --cc=cgroups@vger.kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=geliang@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuni1840@gmail.com \
    --cc=linux-mm@kvack.org \
    --cc=martineau@kernel.org \
    --cc=matttbe@kernel.org \
    --cc=mhocko@kernel.org \
    --cc=mkoutny@suse.com \
    --cc=mptcp@lists.linux.dev \
    --cc=muchun.song@linux.dev \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=tj@kernel.org \
    --cc=willemb@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.