cgroup: add clone_children control file
The ns_cgroup is a control group interacting with the namespaces. When a
new namespace is created, a corresponding cgroup is automatically created
too. The cgroup name is the pid of the process who did 'unshare' or the
child of 'clone'.
This cgroup is tied with the namespace because it prevents a process to
escape the control group and use the post_clone callback, so the child
cgroup inherits the values of the parent cgroup.
Unfortunately, the more we use this cgroup and the more we are facing
problems with it:
(1) when a process unshares, the cgroup name may conflict with a
previous cgroup with the same pid, so unshare or clone return -EEXIST
(2) the cgroup creation is out of control because there may have an
application creating several namespaces where the system will
automatically create several cgroups in his back and let them on the
cgroupfs (eg. a vrf based on the network namespace).
(3) the mix of (1) and (2) force an administrator to regularly check
and clean these cgroups.
This patchset removes the ns_cgroup by adding a new flag to the cgroup and
the cgroupfs mount option. It enables the copy of the parent cgroup when
a child cgroup is created. We can then safely remove the ns_cgroup as
this flag brings a compatibility. We have now to manually create and add
the task to a cgroup, which is consistent with the cgroup framework.
This patch:
Sent as an answer to a previous thread around the ns_cgroup.
https://lists.linux-foundation.org/pipermail/containers/2009-June/018627.html
It adds a control file 'clone_children' for a cgroup. This control file
is a boolean specifying if the child cgroup should be a clone of the
parent cgroup or not. The default value is 'false'.
This flag makes the child cgroup to call the post_clone callback of all
the subsystem, if it is available.
At present, the cpuset is the only one which had implemented the
post_clone callback.
The option can be set at mount time by specifying the 'clone_children'
mount option.
Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr>
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Acked-by: Paul Menage <menage@google.com>
Reviewed-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jamal Hadi Salim <hadi@cyberus.ca>
Cc: Matt Helsley <matthltc@us.ibm.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9270d53..4b218a4 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -243,6 +243,11 @@
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}
+static int clone_children(const struct cgroup *cgrp)
+{
+ return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
/*
* for_each_subsys() allows you to iterate on each subsystem attached to
* an active hierarchy
@@ -1040,6 +1045,8 @@
seq_puts(seq, ",noprefix");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+ if (clone_children(&root->top_cgroup))
+ seq_puts(seq, ",clone_children");
if (strlen(root->name))
seq_printf(seq, ",name=%s", root->name);
mutex_unlock(&cgroup_mutex);
@@ -1050,6 +1057,7 @@
unsigned long subsys_bits;
unsigned long flags;
char *release_agent;
+ bool clone_children;
char *name;
/* User explicitly requested empty subsystem */
bool none;
@@ -1097,6 +1105,8 @@
opts->none = true;
} else if (!strcmp(token, "noprefix")) {
set_bit(ROOT_NOPREFIX, &opts->flags);
+ } else if (!strcmp(token, "clone_children")) {
+ opts->clone_children = true;
} else if (!strncmp(token, "release_agent=", 14)) {
/* Specifying two release agents is forbidden */
if (opts->release_agent)
@@ -1355,6 +1365,8 @@
strcpy(root->release_agent_path, opts->release_agent);
if (opts->name)
strcpy(root->name, opts->name);
+ if (opts->clone_children)
+ set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
return root;
}
@@ -3173,6 +3185,23 @@
return ret;
}
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+ struct cftype *cft)
+{
+ return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+ struct cftype *cft,
+ u64 val)
+{
+ if (val)
+ set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+ else
+ clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+ return 0;
+}
+
/*
* for the common functions, 'private' gives the type of file
*/
@@ -3203,6 +3232,11 @@
.write_string = cgroup_write_event_control,
.mode = S_IWUGO,
},
+ {
+ .name = "cgroup.clone_children",
+ .read_u64 = cgroup_clone_children_read,
+ .write_u64 = cgroup_clone_children_write,
+ },
};
static struct cftype cft_release_agent = {
@@ -3332,6 +3366,9 @@
if (notify_on_release(parent))
set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+ if (clone_children(parent))
+ set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
for_each_subsys(root, ss) {
struct cgroup_subsys_state *css = ss->create(ss, cgrp);
@@ -3346,6 +3383,8 @@
goto err_destroy;
}
/* At error, ->destroy() callback has to free assigned ID. */
+ if (clone_children(parent) && ss->post_clone)
+ ss->post_clone(ss, cgrp);
}
cgroup_lock_hierarchy(root);