linux/net/core/netprio_cgroup.c

308 lines
6.9 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/module.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 <linux/sched/task.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>
#include <net/netprio_cgroup.h>
#include <linux/fdtable.h>
/*
* netprio allocates per-net_device priomap array which is indexed by
* css->id. Limiting css ID to 16bits doesn't lose anything.
*/
#define NETPRIO_ID_MAX USHRT_MAX
#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;
if (css->id > NETPRIO_ID_MAX)
return -ENOSPC;
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;
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-07 22:38:53 +00:00
cgroup_sk_alloc_disable();
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);
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-07 22:38:53 +00:00
if (sock) {
spin_lock(&cgroup_sk_update_lock);
sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
(unsigned long)v);
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-07 22:38:53 +00:00
spin_unlock(&cgroup_sk_update_lock);
}
return 0;
}
cgroup: fix handling of multi-destination migration from subtree_control enabling Consider the following v2 hierarchy. P0 (+memory) --- P1 (-memory) --- A \- B P0 has memory enabled in its subtree_control while P1 doesn't. If both A and B contain processes, they would belong to the memory css of P1. Now if memory is enabled on P1's subtree_control, memory csses should be created on both A and B and A's processes should be moved to the former and B's processes the latter. IOW, enabling controllers can cause atomic migrations into different csses. The core cgroup migration logic has been updated accordingly but the controller migration methods haven't and still assume that all tasks migrate to a single target css; furthermore, the methods were fed the css in which subtree_control was updated which is the parent of the target csses. pids controller depends on the migration methods to move charges and this made the controller attribute charges to the wrong csses often triggering the following warning by driving a counter negative. WARNING: CPU: 1 PID: 1 at kernel/cgroup_pids.c:97 pids_cancel.constprop.6+0x31/0x40() Modules linked in: CPU: 1 PID: 1 Comm: systemd Not tainted 4.4.0-rc1+ #29 ... ffffffff81f65382 ffff88007c043b90 ffffffff81551ffc 0000000000000000 ffff88007c043bc8 ffffffff810de202 ffff88007a752000 ffff88007a29ab00 ffff88007c043c80 ffff88007a1d8400 0000000000000001 ffff88007c043bd8 Call Trace: [<ffffffff81551ffc>] dump_stack+0x4e/0x82 [<ffffffff810de202>] warn_slowpath_common+0x82/0xc0 [<ffffffff810de2fa>] warn_slowpath_null+0x1a/0x20 [<ffffffff8118e031>] pids_cancel.constprop.6+0x31/0x40 [<ffffffff8118e0fd>] pids_can_attach+0x6d/0xf0 [<ffffffff81188a4c>] cgroup_taskset_migrate+0x6c/0x330 [<ffffffff81188e05>] cgroup_migrate+0xf5/0x190 [<ffffffff81189016>] cgroup_attach_task+0x176/0x200 [<ffffffff8118949d>] __cgroup_procs_write+0x2ad/0x460 [<ffffffff81189684>] cgroup_procs_write+0x14/0x20 [<ffffffff811854e5>] cgroup_file_write+0x35/0x1c0 [<ffffffff812e26f1>] kernfs_fop_write+0x141/0x190 [<ffffffff81265f88>] __vfs_write+0x28/0xe0 [<ffffffff812666fc>] vfs_write+0xac/0x1a0 [<ffffffff81267019>] SyS_write+0x49/0xb0 [<ffffffff81bcef32>] entry_SYSCALL_64_fastpath+0x12/0x76 This patch fixes the bug by removing @css parameter from the three migration methods, ->can_attach, ->cancel_attach() and ->attach() and updating cgroup_taskset iteration helpers also return the destination css in addition to the task being migrated. All controllers are updated accordingly. * Controllers which don't care whether there are one or multiple target csses can be converted trivially. cpu, io, freezer, perf, netclassid and netprio fall in this category. * cpuset's current implementation assumes that there's single source and destination and thus doesn't support v2 hierarchy already. The only change made by this patchset is how that single destination css is obtained. * memory migration path already doesn't do anything on v2. How the single destination css is obtained is updated and the prep stage of mem_cgroup_can_attach() is reordered to accomodate the change. * pids is the only controller which was affected by this bug. It now correctly handles multi-destination migrations and no longer causes counter underflow from incorrect accounting. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-and-tested-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Aleksa Sarai <cyphar@cyphar.com>
2015-12-03 15:18:21 +00:00
static void net_prio_attach(struct cgroup_taskset *tset)
{
struct task_struct *p;
cgroup: fix handling of multi-destination migration from subtree_control enabling Consider the following v2 hierarchy. P0 (+memory) --- P1 (-memory) --- A \- B P0 has memory enabled in its subtree_control while P1 doesn't. If both A and B contain processes, they would belong to the memory css of P1. Now if memory is enabled on P1's subtree_control, memory csses should be created on both A and B and A's processes should be moved to the former and B's processes the latter. IOW, enabling controllers can cause atomic migrations into different csses. The core cgroup migration logic has been updated accordingly but the controller migration methods haven't and still assume that all tasks migrate to a single target css; furthermore, the methods were fed the css in which subtree_control was updated which is the parent of the target csses. pids controller depends on the migration methods to move charges and this made the controller attribute charges to the wrong csses often triggering the following warning by driving a counter negative. WARNING: CPU: 1 PID: 1 at kernel/cgroup_pids.c:97 pids_cancel.constprop.6+0x31/0x40() Modules linked in: CPU: 1 PID: 1 Comm: systemd Not tainted 4.4.0-rc1+ #29 ... ffffffff81f65382 ffff88007c043b90 ffffffff81551ffc 0000000000000000 ffff88007c043bc8 ffffffff810de202 ffff88007a752000 ffff88007a29ab00 ffff88007c043c80 ffff88007a1d8400 0000000000000001 ffff88007c043bd8 Call Trace: [<ffffffff81551ffc>] dump_stack+0x4e/0x82 [<ffffffff810de202>] warn_slowpath_common+0x82/0xc0 [<ffffffff810de2fa>] warn_slowpath_null+0x1a/0x20 [<ffffffff8118e031>] pids_cancel.constprop.6+0x31/0x40 [<ffffffff8118e0fd>] pids_can_attach+0x6d/0xf0 [<ffffffff81188a4c>] cgroup_taskset_migrate+0x6c/0x330 [<ffffffff81188e05>] cgroup_migrate+0xf5/0x190 [<ffffffff81189016>] cgroup_attach_task+0x176/0x200 [<ffffffff8118949d>] __cgroup_procs_write+0x2ad/0x460 [<ffffffff81189684>] cgroup_procs_write+0x14/0x20 [<ffffffff811854e5>] cgroup_file_write+0x35/0x1c0 [<ffffffff812e26f1>] kernfs_fop_write+0x141/0x190 [<ffffffff81265f88>] __vfs_write+0x28/0xe0 [<ffffffff812666fc>] vfs_write+0xac/0x1a0 [<ffffffff81267019>] SyS_write+0x49/0xb0 [<ffffffff81bcef32>] entry_SYSCALL_64_fastpath+0x12/0x76 This patch fixes the bug by removing @css parameter from the three migration methods, ->can_attach, ->cancel_attach() and ->attach() and updating cgroup_taskset iteration helpers also return the destination css in addition to the task being migrated. All controllers are updated accordingly. * Controllers which don't care whether there are one or multiple target csses can be converted trivially. cpu, io, freezer, perf, netclassid and netprio fall in this category. * cpuset's current implementation assumes that there's single source and destination and thus doesn't support v2 hierarchy already. The only change made by this patchset is how that single destination css is obtained. * memory migration path already doesn't do anything on v2. How the single destination css is obtained is updated and the prep stage of mem_cgroup_can_attach() is reordered to accomodate the change. * pids is the only controller which was affected by this bug. It now correctly handles multi-destination migrations and no longer causes counter underflow from incorrect accounting. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-and-tested-by: Daniel Wagner <daniel.wagner@bmw-carit.de> Cc: Aleksa Sarai <cyphar@cyphar.com>
2015-12-03 15:18:21 +00:00
struct cgroup_subsys_state *css;
cgroup_taskset_for_each(p, css, tset) {
void *v = (void *)(unsigned long)css->cgroup->id;
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");