linux/net/core/netprio_cgroup.c

289 lines
6.4 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
/*
* Extend @dev->priomap so that it's large enough to accommodate
* @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 21:50:15 +00:00
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 21:50:15 +00:00
return 0;
}
/**
* netprio_prio - return the effective netprio of a cgroup-net_device pair
* @css: css 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_subsys_state *css, struct net_device *dev)
{
struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
int id = css->cgroup->id;
if (map && id < map->priomap_len)
return map->priomap[id];
return 0;
}
/**
* netprio_set_prio - set netprio on a cgroup-net_device pair
* @css: css part of the target pair
* @dev: net_device part of the target pair
* @prio: prio to set
*
* Set netprio to @prio on @css-@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_subsys_state *css,
struct net_device *dev, u32 prio)
{
struct netprio_map *map;
int id = css->cgroup->id;
int ret;
/* avoid extending priomap for zero writes */
map = rtnl_dereference(dev->priomap);
if (!prio && (!map || map->priomap_len <= id))
return 0;
ret = extend_netdev_table(dev, id);
if (ret)
return ret;
map = rtnl_dereference(dev->priomap);
map->priomap[id] = prio;
return 0;
}
cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:23 +00:00
static struct cgroup_subsys_state *
cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cgroup_subsys_state *css;
css = kzalloc(sizeof(*css), GFP_KERNEL);
if (!css)
return ERR_PTR(-ENOMEM);
return css;
}
cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:23 +00:00
static int cgrp_css_online(struct cgroup_subsys_state *css)
{
struct cgroup_subsys_state *parent_css = css->parent;
struct net_device *dev;
int ret = 0;
cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:23 +00:00
if (!parent_css)
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_css, dev);
ret = netprio_set_prio(css, dev, prio);
if (ret)
break;
}
rtnl_unlock();
return ret;
}
cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:23 +00:00
static void cgrp_css_free(struct cgroup_subsys_state *css)
{
cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:23 +00:00
kfree(css);
}
cgroup: pass around cgroup_subsys_state instead of cgroup in file methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup. Please see the previous commit which converts the subsystem methods for rationale. This patch converts all cftype file operations to take @css instead of @cgroup. cftypes for the cgroup core files don't have their subsytem pointer set. These will automatically use the dummy_css added by the previous patch and can be converted the same way. Most subsystem conversions are straight forwards but there are some interesting ones. * freezer: update_if_frozen() is also converted to take @css instead of @cgroup for consistency. This will make the code look simpler too once iterators are converted to use css. * memory/vmpressure: mem_cgroup_from_css() needs to be exported to vmpressure while mem_cgroup_from_cont() can be made static. Updated accordingly. * cpu: cgroup_tg() doesn't have any user left. Removed. * cpuacct: cgroup_ca() doesn't have any user left. Removed. * hugetlb: hugetlb_cgroup_form_cgroup() doesn't have any user left. Removed. * net_cls: cgrp_cls_state() doesn't have any user left. Removed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:24 +00:00
static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft)
{
cgroup: pass around cgroup_subsys_state instead of cgroup in file methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup. Please see the previous commit which converts the subsystem methods for rationale. This patch converts all cftype file operations to take @css instead of @cgroup. cftypes for the cgroup core files don't have their subsytem pointer set. These will automatically use the dummy_css added by the previous patch and can be converted the same way. Most subsystem conversions are straight forwards but there are some interesting ones. * freezer: update_if_frozen() is also converted to take @css instead of @cgroup for consistency. This will make the code look simpler too once iterators are converted to use css. * memory/vmpressure: mem_cgroup_from_css() needs to be exported to vmpressure while mem_cgroup_from_cont() can be made static. Updated accordingly. * cpu: cgroup_tg() doesn't have any user left. Removed. * cpuacct: cgroup_ca() doesn't have any user left. Removed. * hugetlb: hugetlb_cgroup_form_cgroup() doesn't have any user left. Removed. * net_cls: cgrp_cls_state() doesn't have any user left. Removed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:24 +00:00
return css->cgroup->id;
}
static int read_priomap(struct seq_file *sf, void *v)
{
struct net_device *dev;
rcu_read_lock();
for_each_netdev_rcu(&init_net, dev)
seq_printf(sf, "%s %u\n", dev->name,
netprio_prio(seq_css(sf), dev));
rcu_read_unlock();
return 0;
}
static ssize_t write_priomap(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
char devname[IFNAMSIZ + 1];
struct net_device *dev;
u32 prio;
int ret;
if (sscanf(buf, "%"__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(of_css(of), 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 21:50:15 +00:00
rtnl_unlock();
dev_put(dev);
return ret ?: nbytes;
}
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;
}
cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods cgroup is currently in the process of transitioning to using struct cgroup_subsys_state * as the primary handle instead of struct cgroup * in subsystem implementations for the following reasons. * With unified hierarchy, subsystems will be dynamically bound and unbound from cgroups and thus css's (cgroup_subsys_state) may be created and destroyed dynamically over the lifetime of a cgroup, which is different from the current state where all css's are allocated and destroyed together with the associated cgroup. This in turn means that cgroup_css() should be synchronized and may return NULL, making it more cumbersome to use. * Differing levels of per-subsystem granularity in the unified hierarchy means that the task and descendant iterators should behave differently depending on the specific subsystem the iteration is being performed for. * In majority of the cases, subsystems only care about its part in the cgroup hierarchy - ie. the hierarchy of css's. Subsystem methods often obtain the matching css pointer from the cgroup and don't bother with the cgroup pointer itself. Passing around css fits much better. This patch converts all cgroup_subsys methods to take @css instead of @cgroup. The conversions are mostly straight-forward. A few noteworthy changes are * ->css_alloc() now takes css of the parent cgroup rather than the pointer to the new cgroup as the css for the new cgroup doesn't exist yet. Knowing the parent css is enough for all the existing subsystems. * In kernel/cgroup.c::offline_css(), unnecessary open coded css dereference is replaced with local variable access. This patch shouldn't cause any behavior differences. v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced with local variable @css as suggested by Li Zefan. Rebased on top of new for-3.12 which includes for-3.11-fixes so that ->css_free() invocation added by da0a12caff ("cgroup: fix a leak when percpu_ref_init() fails") is converted too. Suggested by Li Zefan. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Li Zefan <lizefan@huawei.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-08-09 00:11:23 +00:00
static void net_prio_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *p;
void *v = (void *)(unsigned long)css->cgroup->id;
cgroup_taskset_for_each(p, tset) {
task_lock(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",
.seq_show = read_priomap,
.write = write_priomap,
},
{ } /* terminate */
};
cgroup: clean up cgroup_subsys names and initialization cgroup_subsys is a bit messier than it needs to be. * The name of a subsys can be different from its internal identifier defined in cgroup_subsys.h. Most subsystems use the matching name but three - cpu, memory and perf_event - use different ones. * cgroup_subsys_id enums are postfixed with _subsys_id and each cgroup_subsys is postfixed with _subsys. cgroup.h is widely included throughout various subsystems, it doesn't and shouldn't have claim on such generic names which don't have any qualifier indicating that they belong to cgroup. * cgroup_subsys->subsys_id should always equal the matching cgroup_subsys_id enum; however, we require each controller to initialize it and then BUG if they don't match, which is a bit silly. This patch cleans up cgroup_subsys names and initialization by doing the followings. * cgroup_subsys_id enums are now postfixed with _cgrp_id, and each cgroup_subsys with _cgrp_subsys. * With the above, renaming subsys identifiers to match the userland visible names doesn't cause any naming conflicts. All non-matching identifiers are renamed to match the official names. cpu_cgroup -> cpu mem_cgroup -> memory perf -> perf_event * controllers no longer need to initialize ->subsys_id and ->name. They're generated in cgroup core and set automatically during boot. * Redundant cgroup_subsys declarations removed. * While updating BUG_ON()s in cgroup_init_early(), convert them to WARN()s. BUGging that early during boot is stupid - the kernel can't print anything, even through serial console and the trap handler doesn't even link stack frame properly for back-tracing. This patch doesn't introduce any behavior changes. v2: Rebased on top of fe1217c4f3f7 ("net: net_cls: move cgroupfs classid handling into core"). Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: "David S. Miller" <davem@davemloft.net> Acked-by: "Rafael J. Wysocki" <rjw@rjwysocki.net> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Ingo Molnar <mingo@redhat.com> Acked-by: Li Zefan <lizefan@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Thomas Graf <tgraf@suug.ch>
2014-02-08 15:36:58 +00:00
struct cgroup_subsys net_prio_cgrp_subsys = {
.css_alloc = cgrp_css_alloc,
.css_online = cgrp_css_online,
.css_free = cgrp_css_free,
.attach = net_prio_attach,
.legacy_cftypes = ss_files,
};
static int netprio_device_event(struct notifier_block *unused,
unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_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)
{
register_netdevice_notifier(&netprio_device_notifier);
return 0;
}
subsys_initcall(init_cgroup_netprio);
MODULE_LICENSE("GPL v2");