summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-10-06 09:52:23 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-06 09:52:23 -0700
commit14986a34e1289424811443a524cdd9e1688c7913 (patch)
tree5ec26b7b16802755eff052016ea47958098dc14b /kernel/cgroup.c
parent8d370595811e13378243832006f8c52bbc9cca5e (diff)
parent069d5ac9ae0d271903cc4607890616418118379a (diff)
downloadlinux-14986a34e1289424811443a524cdd9e1688c7913.tar.bz2
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull namespace updates from Eric Biederman: "This set of changes is a number of smaller things that have been overlooked in other development cycles focused on more fundamental change. The devpts changes are small things that were a distraction until we managed to kill off DEVPTS_MULTPLE_INSTANCES. There is an trivial regression fix to autofs for the unprivileged mount changes that went in last cycle. A pair of ioctls has been added by Andrey Vagin making it is possible to discover the relationships between namespaces when referring to them through file descriptors. The big user visible change is starting to add simple resource limits to catch programs that misbehave. With namespaces in general and user namespaces in particular allowing users to use more kinds of resources, it has become important to have something to limit errant programs. Because the purpose of these limits is to catch errant programs the code needs to be inexpensive to use as it always on, and the default limits need to be high enough that well behaved programs on well behaved systems don't encounter them. To this end, after some review I have implemented per user per user namespace limits, and use them to limit the number of namespaces. The limits being per user mean that one user can not exhause the limits of another user. The limits being per user namespace allow contexts where the limit is 0 and security conscious folks can remove from their threat anlysis the code used to manage namespaces (as they have historically done as it root only). At the same time the limits being per user namespace allow other parts of the system to use namespaces. Namespaces are increasingly being used in application sand boxing scenarios so an all or nothing disable for the entire system for the security conscious folks makes increasing use of these sandboxes impossible. There is also added a limit on the maximum number of mounts present in a single mount namespace. It is nontrivial to guess what a reasonable system wide limit on the number of mount structure in the kernel would be, especially as it various based on how a system is using containers. A limit on the number of mounts in a mount namespace however is much easier to understand and set. In most cases in practice only about 1000 mounts are used. Given that some autofs scenarious have the potential to be 30,000 to 50,000 mounts I have set the default limit for the number of mounts at 100,000 which is well above every known set of users but low enough that the mount hash tables don't degrade unreaonsably. These limits are a start. I expect this estabilishes a pattern that other limits for resources that namespaces use will follow. There has been interest in making inotify event limits per user per user namespace as well as interest expressed in making details about what is going on in the kernel more visible" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (28 commits) autofs: Fix automounts by using current_real_cred()->uid mnt: Add a per mount namespace limit on the number of mounts netns: move {inc,dec}_net_namespaces into #ifdef nsfs: Simplify __ns_get_path tools/testing: add a test to check nsfs ioctl-s nsfs: add ioctl to get a parent namespace nsfs: add ioctl to get an owning user namespace for ns file descriptor kernel: add a helper to get an owning user namespace for a namespace devpts: Change the owner of /dev/pts/ptmx to the mounter of /dev/pts devpts: Remove sync_filesystems devpts: Make devpts_kill_sb safe if fsi is NULL devpts: Simplify devpts_mount by using mount_nodev devpts: Move the creation of /dev/pts/ptmx into fill_super devpts: Move parse_mount_options into fill_super userns: When the per user per user namespace limit is reached return ENOSPC userns; Document per user per user namespace limits. mntns: Add a limit on the number of mount namespaces. netns: Add a limit on the number of net namespaces cgroupns: Add a limit on the number of cgroup namespaces ipcns: Add a limit on the number of ipc namespaces ...
Diffstat (limited to 'kernel/cgroup.c')
-rw-r--r--kernel/cgroup.c24
1 files changed, 24 insertions, 0 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9ba28310eab6..44066158f0d1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -6328,6 +6328,16 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
/* cgroup namespaces */
+static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns)
+{
+ return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES);
+}
+
+static void dec_cgroup_namespaces(struct ucounts *ucounts)
+{
+ dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES);
+}
+
static struct cgroup_namespace *alloc_cgroup_ns(void)
{
struct cgroup_namespace *new_ns;
@@ -6349,6 +6359,7 @@ static struct cgroup_namespace *alloc_cgroup_ns(void)
void free_cgroup_ns(struct cgroup_namespace *ns)
{
put_css_set(ns->root_cset);
+ dec_cgroup_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
ns_free_inum(&ns->ns);
kfree(ns);
@@ -6360,6 +6371,7 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
struct cgroup_namespace *old_ns)
{
struct cgroup_namespace *new_ns;
+ struct ucounts *ucounts;
struct css_set *cset;
BUG_ON(!old_ns);
@@ -6373,6 +6385,10 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
+ ucounts = inc_cgroup_namespaces(user_ns);
+ if (!ucounts)
+ return ERR_PTR(-ENOSPC);
+
/* It is not safe to take cgroup_mutex here */
spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
@@ -6382,10 +6398,12 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
new_ns = alloc_cgroup_ns();
if (IS_ERR(new_ns)) {
put_css_set(cset);
+ dec_cgroup_namespaces(ucounts);
return new_ns;
}
new_ns->user_ns = get_user_ns(user_ns);
+ new_ns->ucounts = ucounts;
new_ns->root_cset = cset;
return new_ns;
@@ -6436,12 +6454,18 @@ static void cgroupns_put(struct ns_common *ns)
put_cgroup_ns(to_cg_ns(ns));
}
+static struct user_namespace *cgroupns_owner(struct ns_common *ns)
+{
+ return to_cg_ns(ns)->user_ns;
+}
+
const struct proc_ns_operations cgroupns_operations = {
.name = "cgroup",
.type = CLONE_NEWCGROUP,
.get = cgroupns_get,
.put = cgroupns_put,
.install = cgroupns_install,
+ .owner = cgroupns_owner,
};
static __init int cgroup_namespaces_init(void)