linux/net/core/netprio_cgroup.c

323 lines
7.1 KiB
C
Raw Normal View History

/*
* net/core/netprio_cgroup.c Priority Control Group
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Neil Horman <nhorman@tuxdriver.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/cgroup.h>
#include <linux/rcupdate.h>
#include <linux/atomic.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>
#include <net/netprio_cgroup.h>
#include <linux/fdtable.h>
#define PRIOMAP_MIN_SZ 128
static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
{
return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id),
struct cgroup_netprio_state, css);
}
/*
* Extend @dev->priomap so that it's large enough to accomodate
* @target_idx. @dev->priomap.priomap_len > @target_idx after successful
* return. Must be called under rtnl lock.
*/
static int extend_netdev_table(struct net_device *dev, u32 target_idx)
{
struct netprio_map *old, *new;
size_t new_sz, new_len;
/* is the existing priomap large enough? */
old = rtnl_dereference(dev->priomap);
if (old && old->priomap_len > target_idx)
return 0;
/*
* Determine the new size. Let's keep it power-of-two. We start
* from PRIOMAP_MIN_SZ and double it until it's large enough to
* accommodate @target_idx.
*/
new_sz = PRIOMAP_MIN_SZ;
while (true) {
new_len = (new_sz - offsetof(struct netprio_map, priomap)) /
sizeof(new->priomap[0]);
if (new_len > target_idx)
break;
new_sz *= 2;
/* overflowed? */
if (WARN_ON(new_sz < PRIOMAP_MIN_SZ))
return -ENOSPC;
}
/* allocate & copy */
new = kzalloc(new_sz, GFP_KERNEL);
if (!new)
net: cgroup: fix access the unallocated memory in netprio cgroup there are some out of bound accesses in netprio cgroup. now before accessing the dev->priomap.priomap array,we only check if the dev->priomap exist.and because we don't want to see additional bound checkings in fast path, so we should make sure that dev->priomap is null or array size of dev->priomap.priomap is equal to max_prioidx + 1; so in write_priomap logic,we should call extend_netdev_table when dev->priomap is null and dev->priomap.priomap_len < max_len. and in cgrp_create->update_netdev_tables logic,we should call extend_netdev_table only when dev->priomap exist and dev->priomap.priomap_len < max_len. and it's not needed to call update_netdev_tables in write_priomap, we can only allocate the net device's priomap which we change through net_prio.ifpriomap. this patch also add a return value for update_netdev_tables & extend_netdev_table, so when new_priomap is allocated failed, write_priomap will stop to access the priomap,and return -ENOMEM back to the userspace to tell the user what happend. Change From v3: 1. add rtnl protect when reading max_prioidx in write_priomap. 2. only call extend_netdev_table when map->priomap_len < max_len, this will make sure array size of dev->map->priomap always bigger than any prioidx. 3. add a function write_update_netdev_table to make codes clear. Change From v2: 1. protect extend_netdev_table by RTNL. 2. when extend_netdev_table failed,call dev_put to reduce device's refcount. Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 23:50:15 +02:00
return -ENOMEM;
if (old)
memcpy(new->priomap, old->priomap,
old->priomap_len * sizeof(old->priomap[0]));
new->priomap_len = new_len;
/* install the new priomap */
rcu_assign_pointer(dev->priomap, new);
if (old)
kfree_rcu(old, rcu);
net: cgroup: fix access the unallocated memory in netprio cgroup there are some out of bound accesses in netprio cgroup. now before accessing the dev->priomap.priomap array,we only check if the dev->priomap exist.and because we don't want to see additional bound checkings in fast path, so we should make sure that dev->priomap is null or array size of dev->priomap.priomap is equal to max_prioidx + 1; so in write_priomap logic,we should call extend_netdev_table when dev->priomap is null and dev->priomap.priomap_len < max_len. and in cgrp_create->update_netdev_tables logic,we should call extend_netdev_table only when dev->priomap exist and dev->priomap.priomap_len < max_len. and it's not needed to call update_netdev_tables in write_priomap, we can only allocate the net device's priomap which we change through net_prio.ifpriomap. this patch also add a return value for update_netdev_tables & extend_netdev_table, so when new_priomap is allocated failed, write_priomap will stop to access the priomap,and return -ENOMEM back to the userspace to tell the user what happend. Change From v3: 1. add rtnl protect when reading max_prioidx in write_priomap. 2. only call extend_netdev_table when map->priomap_len < max_len, this will make sure array size of dev->map->priomap always bigger than any prioidx. 3. add a function write_update_netdev_table to make codes clear. Change From v2: 1. protect extend_netdev_table by RTNL. 2. when extend_netdev_table failed,call dev_put to reduce device's refcount. Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 23:50:15 +02:00
return 0;
}
/**
* netprio_prio - return the effective netprio of a cgroup-net_device pair
* @cgrp: cgroup part of the target pair
* @dev: net_device part of the target pair
*
* Should be called under RCU read or rtnl lock.
*/
static u32 netprio_prio(struct cgroup *cgrp, struct net_device *dev)
{
struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
if (map && cgrp->id < map->priomap_len)
return map->priomap[cgrp->id];
return 0;
}
/**
* netprio_set_prio - set netprio on a cgroup-net_device pair
* @cgrp: cgroup part of the target pair
* @dev: net_device part of the target pair
* @prio: prio to set
*
* Set netprio to @prio on @cgrp-@dev pair. Should be called under rtnl
* lock and may fail under memory pressure for non-zero @prio.
*/
static int netprio_set_prio(struct cgroup *cgrp, struct net_device *dev,
u32 prio)
{
struct netprio_map *map;
int ret;
/* avoid extending priomap for zero writes */
map = rtnl_dereference(dev->priomap);
if (!prio && (!map || map->priomap_len <= cgrp->id))
return 0;
ret = extend_netdev_table(dev, cgrp->id);
if (ret)
return ret;
map = rtnl_dereference(dev->priomap);
map->priomap[cgrp->id] = prio;
return 0;
}
static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
{
struct cgroup_netprio_state *cs;
cs = kzalloc(sizeof(*cs), GFP_KERNEL);
if (!cs)
return ERR_PTR(-ENOMEM);
return &cs->css;
}
static int cgrp_css_online(struct cgroup *cgrp)
{
struct cgroup *parent = cgrp->parent;
struct net_device *dev;
int ret = 0;
if (!parent)
return 0;
rtnl_lock();
/*
* Inherit prios from the parent. As all prios are set during
* onlining, there is no need to clear them on offline.
*/
for_each_netdev(&init_net, dev) {
u32 prio = netprio_prio(parent, dev);
ret = netprio_set_prio(cgrp, dev, prio);
if (ret)
break;
}
rtnl_unlock();
return ret;
}
static void cgrp_css_free(struct cgroup *cgrp)
{
kfree(cgrp_netprio_state(cgrp));
}
static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
{
return cgrp->id;
}
static int read_priomap(struct cgroup *cont, struct cftype *cft,
struct cgroup_map_cb *cb)
{
struct net_device *dev;
rcu_read_lock();
for_each_netdev_rcu(&init_net, dev)
cb->fill(cb, dev->name, netprio_prio(cont, dev));
rcu_read_unlock();
return 0;
}
static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
const char *buffer)
{
char devname[IFNAMSIZ + 1];
struct net_device *dev;
u32 prio;
int ret;
if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
return -EINVAL;
dev = dev_get_by_name(&init_net, devname);
if (!dev)
return -ENODEV;
rtnl_lock();
ret = netprio_set_prio(cgrp, dev, prio);
net: cgroup: fix access the unallocated memory in netprio cgroup there are some out of bound accesses in netprio cgroup. now before accessing the dev->priomap.priomap array,we only check if the dev->priomap exist.and because we don't want to see additional bound checkings in fast path, so we should make sure that dev->priomap is null or array size of dev->priomap.priomap is equal to max_prioidx + 1; so in write_priomap logic,we should call extend_netdev_table when dev->priomap is null and dev->priomap.priomap_len < max_len. and in cgrp_create->update_netdev_tables logic,we should call extend_netdev_table only when dev->priomap exist and dev->priomap.priomap_len < max_len. and it's not needed to call update_netdev_tables in write_priomap, we can only allocate the net device's priomap which we change through net_prio.ifpriomap. this patch also add a return value for update_netdev_tables & extend_netdev_table, so when new_priomap is allocated failed, write_priomap will stop to access the priomap,and return -ENOMEM back to the userspace to tell the user what happend. Change From v3: 1. add rtnl protect when reading max_prioidx in write_priomap. 2. only call extend_netdev_table when map->priomap_len < max_len, this will make sure array size of dev->map->priomap always bigger than any prioidx. 3. add a function write_update_netdev_table to make codes clear. Change From v2: 1. protect extend_netdev_table by RTNL. 2. when extend_netdev_table failed,call dev_put to reduce device's refcount. Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Eric Dumazet <edumazet@google.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 23:50:15 +02:00
rtnl_unlock();
dev_put(dev);
return ret;
}
static int update_netprio(const void *v, struct file *file, unsigned n)
{
int err;
struct socket *sock = sock_from_file(file, &err);
if (sock)
sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v;
return 0;
}
static void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
{
struct task_struct *p;
void *v;
cgroup_taskset_for_each(p, cgrp, tset) {
task_lock(p);
v = (void *)(unsigned long)task_netprioidx(p);
iterate_fd(p->files, 0, update_netprio, v);
task_unlock(p);
}
}
static struct cftype ss_files[] = {
{
.name = "prioidx",
.read_u64 = read_prioidx,
},
{
.name = "ifpriomap",
.read_map = read_priomap,
.write_string = write_priomap,
},
{ } /* terminate */
};
struct cgroup_subsys net_prio_subsys = {
.name = "net_prio",
.css_alloc = cgrp_css_alloc,
.css_online = cgrp_css_online,
.css_free = cgrp_css_free,
.attach = net_prio_attach,
.subsys_id = net_prio_subsys_id,
.base_cftypes = ss_files,
cgroup: mark subsystems with broken hierarchy support and whine if cgroups are nested for them Currently, cgroup hierarchy support is a mess. cpu related subsystems behave correctly - configuration, accounting and control on a parent properly cover its children. blkio and freezer completely ignore hierarchy and treat all cgroups as if they're directly under the root cgroup. Others show yet different behaviors. These differing interpretations of cgroup hierarchy make using cgroup confusing and it impossible to co-mount controllers into the same hierarchy and obtain sane behavior. Eventually, we want full hierarchy support from all subsystems and probably a unified hierarchy. Users using separate hierarchies expecting completely different behaviors depending on the mounted subsystem is deterimental to making any progress on this front. This patch adds cgroup_subsys.broken_hierarchy and sets it to %true for controllers which are lacking in hierarchy support. The goal of this patch is two-fold. * Move users away from using hierarchy on currently non-hierarchical subsystems, so that implementing proper hierarchy support on those doesn't surprise them. * Keep track of which controllers are broken how and nudge the subsystems to implement proper hierarchy support. For now, start with a single warning message. We can whine louder later on. v2: Fixed a typo spotted by Michal. Warning message updated. v3: Updated memcg part so that it doesn't generate warning in the cases where .use_hierarchy=false doesn't make the behavior different from root.use_hierarchy=true. Fixed a typo spotted by Glauber. v4: Check ->broken_hierarchy after cgroup creation is complete so that ->create() can affect the result per Michal. Dropped unnecessary memcg root handling per Michal. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Glauber Costa <glommer@parallels.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Turner <pjt@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Thomas Graf <tgraf@suug.ch> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
2012-09-13 21:20:58 +02:00
.module = THIS_MODULE,
};
static int netprio_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
struct netprio_map *old;
/*
* Note this is called with rtnl_lock held so we have update side
* protection on our rcu assignments
*/
switch (event) {
case NETDEV_UNREGISTER:
old = rtnl_dereference(dev->priomap);
RCU_INIT_POINTER(dev->priomap, NULL);
if (old)
kfree_rcu(old, rcu);
break;
}
return NOTIFY_DONE;
}
static struct notifier_block netprio_device_notifier = {
.notifier_call = netprio_device_event
};
static int __init init_cgroup_netprio(void)
{
int ret;
ret = cgroup_load_subsys(&net_prio_subsys);
if (ret)
goto out;
register_netdevice_notifier(&netprio_device_notifier);
out:
return ret;
}
static void __exit exit_cgroup_netprio(void)
{
struct netprio_map *old;
struct net_device *dev;
unregister_netdevice_notifier(&netprio_device_notifier);
cgroup_unload_subsys(&net_prio_subsys);
rtnl_lock();
for_each_netdev(&init_net, dev) {
old = rtnl_dereference(dev->priomap);
RCU_INIT_POINTER(dev->priomap, NULL);
if (old)
kfree_rcu(old, rcu);
}
rtnl_unlock();
}
module_init(init_cgroup_netprio);
module_exit(exit_cgroup_netprio);
MODULE_LICENSE("GPL v2");