mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-13 07:56:47 +07:00
6de5a8bfca
RESOURCE_MAX is far too general name, change it to RES_COUNTER_MAX. Signed-off-by: Sha Zhengju <handai.szj@taobao.com> Signed-off-by: Qiang Huang <h.huangqiang@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Jeff Liu <jeff.liu@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
289 lines
7.1 KiB
C
289 lines
7.1 KiB
C
#include <net/tcp.h>
|
|
#include <net/tcp_memcontrol.h>
|
|
#include <net/sock.h>
|
|
#include <net/ip.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/module.h>
|
|
|
|
static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
|
|
{
|
|
return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
|
|
}
|
|
|
|
static void memcg_tcp_enter_memory_pressure(struct sock *sk)
|
|
{
|
|
if (sk->sk_cgrp->memory_pressure)
|
|
*sk->sk_cgrp->memory_pressure = 1;
|
|
}
|
|
EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
|
|
|
|
int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
|
|
{
|
|
/*
|
|
* The root cgroup does not use res_counters, but rather,
|
|
* rely on the data already collected by the network
|
|
* subsystem
|
|
*/
|
|
struct res_counter *res_parent = NULL;
|
|
struct cg_proto *cg_proto, *parent_cg;
|
|
struct tcp_memcontrol *tcp;
|
|
struct mem_cgroup *parent = parent_mem_cgroup(memcg);
|
|
struct net *net = current->nsproxy->net_ns;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return 0;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
|
|
tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0];
|
|
tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1];
|
|
tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2];
|
|
tcp->tcp_memory_pressure = 0;
|
|
|
|
parent_cg = tcp_prot.proto_cgroup(parent);
|
|
if (parent_cg)
|
|
res_parent = parent_cg->memory_allocated;
|
|
|
|
res_counter_init(&tcp->tcp_memory_allocated, res_parent);
|
|
percpu_counter_init(&tcp->tcp_sockets_allocated, 0);
|
|
|
|
cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure;
|
|
cg_proto->memory_pressure = &tcp->tcp_memory_pressure;
|
|
cg_proto->sysctl_mem = tcp->tcp_prot_mem;
|
|
cg_proto->memory_allocated = &tcp->tcp_memory_allocated;
|
|
cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
|
|
cg_proto->memcg = memcg;
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(tcp_init_cgroup);
|
|
|
|
void tcp_destroy_cgroup(struct mem_cgroup *memcg)
|
|
{
|
|
struct cg_proto *cg_proto;
|
|
struct tcp_memcontrol *tcp;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
percpu_counter_destroy(&tcp->tcp_sockets_allocated);
|
|
}
|
|
EXPORT_SYMBOL(tcp_destroy_cgroup);
|
|
|
|
static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
|
|
{
|
|
struct net *net = current->nsproxy->net_ns;
|
|
struct tcp_memcontrol *tcp;
|
|
struct cg_proto *cg_proto;
|
|
u64 old_lim;
|
|
int i;
|
|
int ret;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return -EINVAL;
|
|
|
|
if (val > RES_COUNTER_MAX)
|
|
val = RES_COUNTER_MAX;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
|
|
old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
|
|
ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val);
|
|
if (ret)
|
|
return ret;
|
|
|
|
for (i = 0; i < 3; i++)
|
|
tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
|
|
net->ipv4.sysctl_tcp_mem[i]);
|
|
|
|
if (val == RES_COUNTER_MAX)
|
|
clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
|
|
else if (val != RES_COUNTER_MAX) {
|
|
/*
|
|
* The active bit needs to be written after the static_key
|
|
* update. This is what guarantees that the socket activation
|
|
* function is the last one to run. See sock_update_memcg() for
|
|
* details, and note that we don't mark any socket as belonging
|
|
* to this memcg until that flag is up.
|
|
*
|
|
* We need to do this, because static_keys will span multiple
|
|
* sites, but we can't control their order. If we mark a socket
|
|
* as accounted, but the accounting functions are not patched in
|
|
* yet, we'll lose accounting.
|
|
*
|
|
* We never race with the readers in sock_update_memcg(),
|
|
* because when this value change, the code to process it is not
|
|
* patched in yet.
|
|
*
|
|
* The activated bit is used to guarantee that no two writers
|
|
* will do the update in the same memcg. Without that, we can't
|
|
* properly shutdown the static key.
|
|
*/
|
|
if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags))
|
|
static_key_slow_inc(&memcg_socket_limit_enabled);
|
|
set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
|
|
const char *buffer)
|
|
{
|
|
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
|
|
unsigned long long val;
|
|
int ret = 0;
|
|
|
|
switch (cft->private) {
|
|
case RES_LIMIT:
|
|
/* see memcontrol.c */
|
|
ret = res_counter_memparse_write_strategy(buffer, &val);
|
|
if (ret)
|
|
break;
|
|
ret = tcp_update_limit(memcg, val);
|
|
break;
|
|
default:
|
|
ret = -EINVAL;
|
|
break;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
|
|
{
|
|
struct tcp_memcontrol *tcp;
|
|
struct cg_proto *cg_proto;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return default_val;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
return res_counter_read_u64(&tcp->tcp_memory_allocated, type);
|
|
}
|
|
|
|
static u64 tcp_read_usage(struct mem_cgroup *memcg)
|
|
{
|
|
struct tcp_memcontrol *tcp;
|
|
struct cg_proto *cg_proto;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
|
|
}
|
|
|
|
static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
|
|
{
|
|
struct mem_cgroup *memcg = mem_cgroup_from_css(css);
|
|
u64 val;
|
|
|
|
switch (cft->private) {
|
|
case RES_LIMIT:
|
|
val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
|
|
break;
|
|
case RES_USAGE:
|
|
val = tcp_read_usage(memcg);
|
|
break;
|
|
case RES_FAILCNT:
|
|
case RES_MAX_USAGE:
|
|
val = tcp_read_stat(memcg, cft->private, 0);
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
return val;
|
|
}
|
|
|
|
static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
struct tcp_memcontrol *tcp;
|
|
struct cg_proto *cg_proto;
|
|
|
|
memcg = mem_cgroup_from_css(css);
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return 0;
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
|
|
switch (event) {
|
|
case RES_MAX_USAGE:
|
|
res_counter_reset_max(&tcp->tcp_memory_allocated);
|
|
break;
|
|
case RES_FAILCNT:
|
|
res_counter_reset_failcnt(&tcp->tcp_memory_allocated);
|
|
break;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
unsigned long long tcp_max_memory(const struct mem_cgroup *memcg)
|
|
{
|
|
struct tcp_memcontrol *tcp;
|
|
struct cg_proto *cg_proto;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg);
|
|
if (!cg_proto)
|
|
return 0;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
|
|
}
|
|
|
|
void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
|
|
{
|
|
struct tcp_memcontrol *tcp;
|
|
struct cg_proto *cg_proto;
|
|
|
|
cg_proto = tcp_prot.proto_cgroup(memcg);
|
|
if (!cg_proto)
|
|
return;
|
|
|
|
tcp = tcp_from_cgproto(cg_proto);
|
|
|
|
tcp->tcp_prot_mem[idx] = val;
|
|
}
|
|
|
|
static struct cftype tcp_files[] = {
|
|
{
|
|
.name = "kmem.tcp.limit_in_bytes",
|
|
.write_string = tcp_cgroup_write,
|
|
.read_u64 = tcp_cgroup_read,
|
|
.private = RES_LIMIT,
|
|
},
|
|
{
|
|
.name = "kmem.tcp.usage_in_bytes",
|
|
.read_u64 = tcp_cgroup_read,
|
|
.private = RES_USAGE,
|
|
},
|
|
{
|
|
.name = "kmem.tcp.failcnt",
|
|
.private = RES_FAILCNT,
|
|
.trigger = tcp_cgroup_reset,
|
|
.read_u64 = tcp_cgroup_read,
|
|
},
|
|
{
|
|
.name = "kmem.tcp.max_usage_in_bytes",
|
|
.private = RES_MAX_USAGE,
|
|
.trigger = tcp_cgroup_reset,
|
|
.read_u64 = tcp_cgroup_read,
|
|
},
|
|
{ } /* terminate */
|
|
};
|
|
|
|
static int __init tcp_memcontrol_init(void)
|
|
{
|
|
WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files));
|
|
return 0;
|
|
}
|
|
__initcall(tcp_memcontrol_init);
|