From 7c268eaeec6388b7bee36aef3fb5e62c9222ad3b Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 14 Oct 2025 23:54:55 +0000 Subject: net: Allow opt-out from global protocol memory accounting. Some protocols (e.g., TCP, UDP) implement memory accounting for socket buffers and charge memory to per-protocol global counters pointed to by sk->sk_proto->memory_allocated. Sometimes, system processes do not want that limitation. For a similar purpose, there is SO_RESERVE_MEM for sockets under memcg. Also, by opting out of the per-protocol accounting, sockets under memcg can avoid paying costs for two orthogonal memory accounting mechanisms. A microbenchmark result is in the subsequent bpf patch. Let's allow opt-out from the per-protocol memory accounting if sk->sk_bypass_prot_mem is true. sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache line, and sk_has_account() always fetches sk->sk_prot before accessing sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch. The following patches will set sk->sk_bypass_prot_mem to true, and then, the per-protocol memory accounting will be skipped. Note that this does NOT disable memcg, but rather the per-protocol one. Another option not to use the hole in struct sock_common is create sk_prot variants like tcp_prot_bypass, but this would complicate SOCKMAP logic, tcp_bpf_prots etc. Signed-off-by: Kuniyuki Iwashima Signed-off-by: Martin KaFai Lau Reviewed-by: Shakeel Butt Reviewed-by: Eric Dumazet Acked-by: Roman Gushchin Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com --- include/net/proto_memory.h | 3 +++ include/net/sock.h | 3 +++ include/net/tcp.h | 3 +++ 3 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/proto_memory.h b/include/net/proto_memory.h index 8e91a8fa31b5..ad6d703ce6fe 100644 --- a/include/net/proto_memory.h +++ b/include/net/proto_memory.h @@ -35,6 +35,9 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) mem_cgroup_sk_under_memory_pressure(sk)) return true; + if (sk->sk_bypass_prot_mem) + return false; + return !!READ_ONCE(*sk->sk_prot->memory_pressure); } diff --git a/include/net/sock.h b/include/net/sock.h index 30ac2eb4ef9b..415e7381aa50 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -118,6 +118,7 @@ typedef __u64 __bitwise __addrpair; * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting + * @skc_bypass_prot_mem: bypass the per-protocol memory accounting for skb * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol @@ -174,6 +175,7 @@ struct sock_common { unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; + unsigned char skc_bypass_prot_mem:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; @@ -381,6 +383,7 @@ struct sock { #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt +#define sk_bypass_prot_mem __sk_common.skc_bypass_prot_mem #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e547138f4fb..439e327fdbfa 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -303,6 +303,9 @@ static inline bool tcp_under_memory_pressure(const struct sock *sk) mem_cgroup_sk_under_memory_pressure(sk)) return true; + if (sk->sk_bypass_prot_mem) + return false; + return READ_ONCE(tcp_memory_pressure); } /* -- cgit v1.2.3