mirror of
https://github.com/torvalds/linux.git
synced 2025-12-07 20:06:24 +00:00
7c268eaeec
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 <kuniyu@google.com> Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org> Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev> Reviewed-by: Eric Dumazet <edumazet@google.com> Acked-by: Roman Gushchin <roman.gushchin@linux.dev> Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
87 lines
1.9 KiB
C
87 lines
1.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
#ifndef _PROTO_MEMORY_H
|
|
#define _PROTO_MEMORY_H
|
|
|
|
#include <net/sock.h>
|
|
#include <net/hotdata.h>
|
|
|
|
/* 1 MB per cpu, in page units */
|
|
#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT))
|
|
|
|
static inline bool sk_has_memory_pressure(const struct sock *sk)
|
|
{
|
|
return sk->sk_prot->memory_pressure != NULL;
|
|
}
|
|
|
|
static inline bool
|
|
proto_memory_pressure(const struct proto *prot)
|
|
{
|
|
if (!prot->memory_pressure)
|
|
return false;
|
|
return !!READ_ONCE(*prot->memory_pressure);
|
|
}
|
|
|
|
static inline bool sk_under_global_memory_pressure(const struct sock *sk)
|
|
{
|
|
return proto_memory_pressure(sk->sk_prot);
|
|
}
|
|
|
|
static inline bool sk_under_memory_pressure(const struct sock *sk)
|
|
{
|
|
if (!sk->sk_prot->memory_pressure)
|
|
return false;
|
|
|
|
if (mem_cgroup_sk_enabled(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);
|
|
}
|
|
|
|
static inline long
|
|
proto_memory_allocated(const struct proto *prot)
|
|
{
|
|
return max(0L, atomic_long_read(prot->memory_allocated));
|
|
}
|
|
|
|
static inline long
|
|
sk_memory_allocated(const struct sock *sk)
|
|
{
|
|
return proto_memory_allocated(sk->sk_prot);
|
|
}
|
|
|
|
static inline void proto_memory_pcpu_drain(struct proto *proto)
|
|
{
|
|
int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0);
|
|
|
|
if (val)
|
|
atomic_long_add(val, proto->memory_allocated);
|
|
}
|
|
|
|
static inline void
|
|
sk_memory_allocated_add(const struct sock *sk, int val)
|
|
{
|
|
struct proto *proto = sk->sk_prot;
|
|
|
|
val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val);
|
|
|
|
if (unlikely(val >= READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv)))
|
|
proto_memory_pcpu_drain(proto);
|
|
}
|
|
|
|
static inline void
|
|
sk_memory_allocated_sub(const struct sock *sk, int val)
|
|
{
|
|
struct proto *proto = sk->sk_prot;
|
|
|
|
val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val);
|
|
|
|
if (unlikely(val <= -READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv)))
|
|
proto_memory_pcpu_drain(proto);
|
|
}
|
|
|
|
#endif /* _PROTO_MEMORY_H */
|