From: Serge Hallyn <serge.hal...@ubuntu.com>
This patch enables cgroup mounting inside userns when a process
as appropriate privileges. The cgroup filesystem mounted is
rooted at the cgroupns-root. Thus, in a container-setup, only
the hierarchy under the cgroupns-root is exposed inside the container.
This allows container management tools to run inside the containers
without depending on any global state.
Signed-off-by: Serge Hallyn <serge.hal...@canonical.com>
---
Changelog:
20151116 - Don't allow user namespaces to bind new subsystems
20151118 - postpone the FS_USERNS_MOUNT flag until the
last patch, until we can convince ourselves it
is safe.
20151207 - Switch to walking up the kernfs path from kn root.
- Group initialized variables
- Explain the capable(CAP_SYS_ADMIN) check
- Style fixes
20160104 - kernfs_node_dentry: lock inode for lookup_one_len()
Signed-off-by: Serge Hallyn <serge.hal...@ubuntu.com>
---
fs/kernfs/mount.c | 2 ++
kernel/cgroup.c | 40 +++++++++++++++++++++++++++++++++++++++-
2 files changed, 41 insertions(+), 1 deletion(-)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 7224296..074bb8b 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -120,7 +120,9 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
kntmp = find_next_ancestor(kn, knparent);
if (WARN_ON(!kntmp))
return ERR_PTR(-EINVAL);
+ mutex_lock(&d_inode(dentry)->i_mutex);
dtmp = lookup_one_len(kntmp->name, dentry, strlen(kntmp->name));
+ mutex_unlock(&d_inode(dentry)->i_mutex);
dput(dentry);
if (IS_ERR(dtmp))
return dtmp;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2bb58a1..d0bed8f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1983,6 +1983,7 @@ static struct dentry *cgroup_mount(struct
file_system_type *fs_type,
{
bool is_v2 = fs_type == &cgroup2_fs_type;
struct super_block *pinned_sb = NULL;
+ struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
struct cgroup_subsys *ss;
struct cgroup_root *root;
struct cgroup_sb_opts opts;
@@ -1991,6 +1992,14 @@ static struct dentry *cgroup_mount(struct
file_system_type *fs_type,
int i;
bool new_sb;
+ get_cgroup_ns(ns);
+
+ /* Check if the caller has permission to mount. */
+ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
+ put_cgroup_ns(ns);
+ return ERR_PTR(-EPERM);
+ }
+
/*
* The first time anyone tries to mount a cgroup, enable the list
* linking each css_set to its tasks and fix up all existing tasks.
@@ -2106,6 +2115,16 @@ static struct dentry *cgroup_mount(struct
file_system_type *fs_type,
goto out_unlock;
}
+ /*
+ * We know this subsystem has not yet been bound. Users in a non-init
+ * user namespace may only mount hierarchies with no bound subsystems,
+ * i.e. 'none,name=user1'
+ */
+ if (!opts.none && !capable(CAP_SYS_ADMIN)) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
root = kzalloc(sizeof(*root), GFP_KERNEL);
if (!root) {
ret = -ENOMEM;
@@ -2124,12 +2143,30 @@ out_free:
kfree(opts.release_agent);
kfree(opts.name);
- if (ret)
+ if (ret) {
+ put_cgroup_ns(ns);
return ERR_PTR(ret);
+ }
out_mount:
dentry = kernfs_mount(fs_type, flags, root->kf_root,
is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
&new_sb);
+
+ /*
+ * In non-init cgroup namespace, instead of root cgroup's
+ * dentry, we return the dentry corresponding to the
+ * cgroupns->root_cgrp.
+ */
+ if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
+ struct dentry *nsdentry;
+ struct cgroup *cgrp;
+
+ cgrp = cset_cgroup_from_root(ns->root_cset, root);
+ nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
+ dput(dentry);
+ dentry = nsdentry;
+ }
+
if (IS_ERR(dentry) || !new_sb)
cgroup_put(&root->cgrp);
@@ -2142,6 +2179,7 @@ out_mount:
deactivate_super(pinned_sb);
}
+ put_cgroup_ns(ns);
return dentry;
}
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
