We will store a flag in the lowest bit of sk->sk_memcg.
Then, directly dereferencing sk->sk_memcg will be illegal, and we
do not want to allow touching the raw sk->sk_memcg in many places.
Let's introduce mem_cgroup_from_sk().
Other places accessing the raw sk->sk_memcg will be converted later.
Note that we cannot define the helper as an inline function in
memcontrol.h as we cannot access any fields of struct sock there
due to circular dependency, so it is placed in sock.h.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
---
include/net/sock.h | 12 ++++++++++++
mm/memcontrol.c | 6 ++++--
net/ipv4/inet_connection_sock.c | 2 +-
net/mptcp/subflow.c | 2 +-
4 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index c8a4b283df6f..811f95ea8d00 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2594,6 +2594,18 @@ static inline gfp_t gfp_memcg_charge(void)
return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
}
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk)
+{
+ return sk->sk_memcg;
+}
+#else
+static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk)
+{
+ return NULL;
+}
+#endif
+
static inline long sock_rcvtimeo(const struct sock *sk, bool noblock)
{
return noblock ? 0 : READ_ONCE(sk->sk_rcvtimeo);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 450862e7fd7a..1717c3a50f66 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5023,8 +5023,10 @@ void mem_cgroup_sk_alloc(struct sock *sk)
void mem_cgroup_sk_free(struct sock *sk)
{
- if (sk->sk_memcg)
- css_put(&sk->sk_memcg->css);
+ struct mem_cgroup *memcg = mem_cgroup_from_sk(sk);
+
+ if (memcg)
+ css_put(&memcg->css);
}
/**
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 724bd9ed6cd4..93569bbe00f4 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -718,7 +718,7 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg)
lock_sock(newsk);
mem_cgroup_sk_alloc(newsk);
- if (newsk->sk_memcg) {
+ if (mem_cgroup_from_sk(newsk)) {
/* The socket has not been accepted yet, no need
* to look at newsk->sk_wmem_queued.
*/
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index a4809054ea6c..70c45c092d13 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1759,7 +1759,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
if (unlikely(!sk->sk_socket))
return -EINVAL;
- memcg = set_active_memcg(sk->sk_memcg);
+ memcg = set_active_memcg(mem_cgroup_from_sk(sk));
err = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &sf);
set_active_memcg(memcg);
if (err)
--
2.51.0.rc1.163.g2494970778-goog