[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4334e29b-1cd0-48ba-9afa-54d01b1b7143@linux.dev>
Date: Tue, 2 Sep 2025 13:16:50 -0700
From: Martin KaFai Lau <martin.lau@...ux.dev>
To: Kuniyuki Iwashima <kuniyu@...gle.com>,
Shakeel Butt <shakeel.butt@...ux.dev>
Cc: Alexei Starovoitov <ast@...nel.org>, Andrii Nakryiko <andrii@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
John Fastabend <john.fastabend@...il.com>,
Stanislav Fomichev <sdf@...ichev.me>, Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...nel.org>, Roman Gushchin <roman.gushchin@...ux.dev>,
"David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
Neal Cardwell <ncardwell@...gle.com>, Willem de Bruijn <willemb@...gle.com>,
Mina Almasry <almasrymina@...gle.com>, Kuniyuki Iwashima
<kuni1840@...il.com>, bpf@...r.kernel.org, netdev@...r.kernel.org
Subject: Re: [PATCH v4 bpf-next/net 4/5] net-memcg: Allow decoupling memcg
from global protocol memory accounting.
On 8/28/25 6:00 PM, Kuniyuki Iwashima wrote:
> +static inline bool sk_should_enter_memory_pressure(struct sock *sk)
> +{
> + return !mem_cgroup_sk_enabled(sk) || !mem_cgroup_sk_isolated(sk);
> +}
> +
> static inline long
> proto_memory_allocated(const struct proto *prot)
> {
> @@ -3154,8 +3158,11 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
> if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
> return true;
>
> - sk_enter_memory_pressure(sk);
> + if (sk_should_enter_memory_pressure(sk))
> + sk_enter_memory_pressure(sk);
> +
> sk_stream_moderate_sndbuf(sk);
> +
> return false;
> }
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 71a956fbfc55..dcbd49e2f8af 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -908,7 +908,8 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
> }
> __kfree_skb(skb);
> } else {
> - sk->sk_prot->enter_memory_pressure(sk);
> + if (sk_should_enter_memory_pressure(sk))
> + tcp_enter_memory_pressure(sk);
This change from sk_prot->enter_memory_pressure to tcp_enter_memory_pressure
looks fine. A qq / nit, have you thought about checking
sk_should_enter_memory_pressure inside the tcp_enter_memory_pressure(sk) /
sk_enter_memory_pressure(sk) ?
Other changes of patch 4 lgtm.
Shakeel, you have ack-ed patch 1. Will you take a look at patch 3 and patch 4 also?
> sk_stream_moderate_sndbuf(sk);
> }
> @@ -1016,7 +1017,7 @@ static void mptcp_enter_memory_pressure(struct sock *sk)
> mptcp_for_each_subflow(msk, subflow) {
> struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
>
> - if (first)
> + if (first && sk_should_enter_memory_pressure(ssk))
> tcp_enter_memory_pressure(ssk);
> sk_stream_moderate_sndbuf(ssk);
>
> diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
> index f672a62a9a52..6696ef837116 100644
> --- a/net/tls/tls_device.c
> +++ b/net/tls/tls_device.c
> @@ -35,6 +35,7 @@
> #include <linux/netdevice.h>
> #include <net/dst.h>
> #include <net/inet_connection_sock.h>
> +#include <net/proto_memory.h>
> #include <net/tcp.h>
> #include <net/tls.h>
> #include <linux/skbuff_ref.h>
> @@ -371,7 +372,8 @@ static int tls_do_allocation(struct sock *sk,
> if (!offload_ctx->open_record) {
> if (unlikely(!skb_page_frag_refill(prepend_size, pfrag,
> sk->sk_allocation))) {
> - READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk);
> + if (sk_should_enter_memory_pressure(sk))
> + READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk);
> sk_stream_moderate_sndbuf(sk);
> return -ENOMEM;
> }
Powered by blists - more mailing lists