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>
This commit is contained in:
Gao feng 2012-07-11 21:50:15 +00:00 committed by David S. Miller
parent 936597631d
commit ef209f1598
1 changed files with 55 additions and 18 deletions

View File

@ -65,7 +65,7 @@ static void put_prioidx(u32 idx)
spin_unlock_irqrestore(&prioidx_map_lock, flags); spin_unlock_irqrestore(&prioidx_map_lock, flags);
} }
static void extend_netdev_table(struct net_device *dev, u32 new_len) static int extend_netdev_table(struct net_device *dev, u32 new_len)
{ {
size_t new_size = sizeof(struct netprio_map) + size_t new_size = sizeof(struct netprio_map) +
((sizeof(u32) * new_len)); ((sizeof(u32) * new_len));
@ -77,7 +77,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
if (!new_priomap) { if (!new_priomap) {
pr_warn("Unable to alloc new priomap!\n"); pr_warn("Unable to alloc new priomap!\n");
return; return -ENOMEM;
} }
for (i = 0; for (i = 0;
@ -90,46 +90,79 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
rcu_assign_pointer(dev->priomap, new_priomap); rcu_assign_pointer(dev->priomap, new_priomap);
if (old_priomap) if (old_priomap)
kfree_rcu(old_priomap, rcu); kfree_rcu(old_priomap, rcu);
return 0;
} }
static void update_netdev_tables(void) static int write_update_netdev_table(struct net_device *dev)
{ {
struct net_device *dev; int ret = 0;
u32 max_len = atomic_read(&max_prioidx) + 1; u32 max_len;
struct netprio_map *map; struct netprio_map *map;
rtnl_lock(); rtnl_lock();
max_len = atomic_read(&max_prioidx) + 1;
map = rtnl_dereference(dev->priomap);
if (!map || map->priomap_len < max_len)
ret = extend_netdev_table(dev, max_len);
rtnl_unlock();
return ret;
}
static int update_netdev_tables(void)
{
int ret = 0;
struct net_device *dev;
u32 max_len;
struct netprio_map *map;
rtnl_lock();
max_len = atomic_read(&max_prioidx) + 1;
for_each_netdev(&init_net, dev) { for_each_netdev(&init_net, dev) {
map = rtnl_dereference(dev->priomap); map = rtnl_dereference(dev->priomap);
if ((!map) || /*
(map->priomap_len < max_len)) * don't allocate priomap if we didn't
extend_netdev_table(dev, max_len); * change net_prio.ifpriomap (map == NULL),
* this will speed up skb_update_prio.
*/
if (map && map->priomap_len < max_len) {
ret = extend_netdev_table(dev, max_len);
if (ret < 0)
break;
}
} }
rtnl_unlock(); rtnl_unlock();
return ret;
} }
static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
{ {
struct cgroup_netprio_state *cs; struct cgroup_netprio_state *cs;
int ret; int ret = -EINVAL;
cs = kzalloc(sizeof(*cs), GFP_KERNEL); cs = kzalloc(sizeof(*cs), GFP_KERNEL);
if (!cs) if (!cs)
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
kfree(cs); goto out;
return ERR_PTR(-EINVAL);
}
ret = get_prioidx(&cs->prioidx); ret = get_prioidx(&cs->prioidx);
if (ret != 0) { if (ret < 0) {
pr_warn("No space in priority index array\n"); pr_warn("No space in priority index array\n");
kfree(cs); goto out;
return ERR_PTR(ret); }
ret = update_netdev_tables();
if (ret < 0) {
put_prioidx(cs->prioidx);
goto out;
} }
return &cs->css; return &cs->css;
out:
kfree(cs);
return ERR_PTR(ret);
} }
static void cgrp_destroy(struct cgroup *cgrp) static void cgrp_destroy(struct cgroup *cgrp)
@ -221,13 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
if (!dev) if (!dev)
goto out_free_devname; goto out_free_devname;
update_netdev_tables(); ret = write_update_netdev_table(dev);
ret = 0; if (ret < 0)
goto out_put_dev;
rcu_read_lock(); rcu_read_lock();
map = rcu_dereference(dev->priomap); map = rcu_dereference(dev->priomap);
if (map) if (map)
map->priomap[prioidx] = priority; map->priomap[prioidx] = priority;
rcu_read_unlock(); rcu_read_unlock();
out_put_dev:
dev_put(dev); dev_put(dev);
out_free_devname: out_free_devname: