Commit 3aaabe23 authored by Glauber Costa's avatar Glauber Costa Committed by David S. Miller

tcp buffer limitation: per-cgroup limit

This patch uses the "tcp.limit_in_bytes" field of the kmem_cgroup to
effectively control the amount of kernel memory pinned by a cgroup.

This value is ignored in the root cgroup, and in all others,
caps the value specified by the admin in the net namespaces'
view of tcp_sysctl_mem.

If namespaces are being used, the admin is allowed to set a
value bigger than cgroup's maximum, the same way it is allowed
to set pretty much unlimited values in a real box.
Signed-off-by: default avatarGlauber Costa <glommer@parallels.com>
Reviewed-by: default avatarHiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>
CC: David S. Miller <davem@davemloft.net>
CC: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 3dc43e3e
...@@ -78,6 +78,7 @@ Brief summary of control files. ...@@ -78,6 +78,7 @@ Brief summary of control files.
memory.independent_kmem_limit # select whether or not kernel memory limits are memory.independent_kmem_limit # select whether or not kernel memory limits are
independent of user limits independent of user limits
memory.kmem.tcp.limit_in_bytes # set/show hard limit for tcp buf memory
1. History 1. History
......
...@@ -14,4 +14,6 @@ struct tcp_memcontrol { ...@@ -14,4 +14,6 @@ struct tcp_memcontrol {
struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss); void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
#endif /* _TCP_MEMCG_H */ #endif /* _TCP_MEMCG_H */
...@@ -24,6 +24,7 @@ ...@@ -24,6 +24,7 @@
#include <net/cipso_ipv4.h> #include <net/cipso_ipv4.h>
#include <net/inet_frag.h> #include <net/inet_frag.h>
#include <net/ping.h> #include <net/ping.h>
#include <net/tcp_memcontrol.h>
static int zero; static int zero;
static int tcp_retr1_max = 255; static int tcp_retr1_max = 255;
...@@ -182,6 +183,9 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, ...@@ -182,6 +183,9 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
int ret; int ret;
unsigned long vec[3]; unsigned long vec[3];
struct net *net = current->nsproxy->net_ns; struct net *net = current->nsproxy->net_ns;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
struct mem_cgroup *memcg;
#endif
ctl_table tmp = { ctl_table tmp = {
.data = &vec, .data = &vec,
...@@ -198,6 +202,16 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, ...@@ -198,6 +202,16 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
if (ret) if (ret)
return ret; return ret;
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
tcp_prot_mem(memcg, vec[0], 0);
tcp_prot_mem(memcg, vec[1], 1);
tcp_prot_mem(memcg, vec[2], 2);
rcu_read_unlock();
#endif
net->ipv4.sysctl_tcp_mem[0] = vec[0]; net->ipv4.sysctl_tcp_mem[0] = vec[0];
net->ipv4.sysctl_tcp_mem[1] = vec[1]; net->ipv4.sysctl_tcp_mem[1] = vec[1];
net->ipv4.sysctl_tcp_mem[2] = vec[2]; net->ipv4.sysctl_tcp_mem[2] = vec[2];
......
...@@ -6,6 +6,19 @@ ...@@ -6,6 +6,19 @@
#include <linux/memcontrol.h> #include <linux/memcontrol.h>
#include <linux/module.h> #include <linux/module.h>
static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft);
static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
const char *buffer);
static struct cftype tcp_files[] = {
{
.name = "kmem.tcp.limit_in_bytes",
.write_string = tcp_cgroup_write,
.read_u64 = tcp_cgroup_read,
.private = RES_LIMIT,
},
};
static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
{ {
return container_of(cg_proto, struct tcp_memcontrol, cg_proto); return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
...@@ -34,7 +47,7 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) ...@@ -34,7 +47,7 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
cg_proto = tcp_prot.proto_cgroup(memcg); cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto) if (!cg_proto)
return 0; goto create_files;
tcp = tcp_from_cgproto(cg_proto); tcp = tcp_from_cgproto(cg_proto);
...@@ -57,7 +70,9 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) ...@@ -57,7 +70,9 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
cg_proto->memcg = memcg; cg_proto->memcg = memcg;
return 0; create_files:
return cgroup_add_files(cgrp, ss, tcp_files,
ARRAY_SIZE(tcp_files));
} }
EXPORT_SYMBOL(tcp_init_cgroup); EXPORT_SYMBOL(tcp_init_cgroup);
...@@ -66,6 +81,7 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) ...@@ -66,6 +81,7 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
struct cg_proto *cg_proto; struct cg_proto *cg_proto;
struct tcp_memcontrol *tcp; struct tcp_memcontrol *tcp;
u64 val;
cg_proto = tcp_prot.proto_cgroup(memcg); cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto) if (!cg_proto)
...@@ -73,5 +89,122 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) ...@@ -73,5 +89,122 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
tcp = tcp_from_cgproto(cg_proto); tcp = tcp_from_cgproto(cg_proto);
percpu_counter_destroy(&tcp->tcp_sockets_allocated); percpu_counter_destroy(&tcp->tcp_sockets_allocated);
val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
if (val != RESOURCE_MAX)
jump_label_dec(&memcg_socket_limit_enabled);
} }
EXPORT_SYMBOL(tcp_destroy_cgroup); 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 > RESOURCE_MAX)
val = RESOURCE_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 == RESOURCE_MAX && old_lim != RESOURCE_MAX)
jump_label_dec(&memcg_socket_limit_enabled);
else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
jump_label_inc(&memcg_socket_limit_enabled);
return 0;
}
static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
const char *buffer)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
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_cgroup_read(struct cgroup *cont, struct cftype *cft)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
u64 val;
switch (cft->private) {
case RES_LIMIT:
val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX);
break;
default:
BUG();
}
return val;
}
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;
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment