[PATCH v3 net-next 11/12] net-memcg: Store MEMCG_SOCK_ISOLATED in sk->sk_memcg.
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: 2025-08-12 17:59:29
Also in:
cgroups, linux-mm, mptcp
Subsystem:
control group - memory resource controller (memcg), memory management, networking [general], networking [sockets], the rest · Maintainers:
Johannes Weiner, Michal Hocko, Roman Gushchin, Shakeel Butt, Andrew Morton, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Kuniyuki Iwashima, Willem de Bruijn, Linus Torvalds
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.rc0.205.g4a044479a3-goog