summaryrefslogtreecommitdiffstats
path: root/kernel/cgroup
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2017-06-27 14:30:28 -0400
committerTejun Heo <tj@kernel.org>2017-06-28 14:45:21 -0400
commit5136f6365ce3eace5a926e10f16ed2a233db5ba9 (patch)
treedcbc7414985c212f5a9fddb6bdcac553f6014928 /kernel/cgroup
parent824ecbe01c5d833b8c8a371c209e3ac3a76cd18a (diff)
downloadlinux-5136f6365ce3eace5a926e10f16ed2a233db5ba9.tar.bz2
cgroup: implement "nsdelegate" mount option
Currently, cgroup only supports delegation to !root users and cgroup namespaces don't get any special treatments. This limits the usefulness of cgroup namespaces as they by themselves can't be safe delegation boundaries. A process inside a cgroup can change the resource control knobs of the parent in the namespace root and may move processes in and out of the namespace if cgroups outside its namespace are visible somehow. This patch adds a new mount option "nsdelegate" which makes cgroup namespaces delegation boundaries. If set, cgroup behaves as if write permission based delegation took place at namespace boundaries - writes to the resource control knobs from the namespace root are denied and migration crossing the namespace boundary aren't allowed from inside the namespace. This allows cgroup namespace to function as a delegation boundary by itself. v2: Silently ignore nsdelegate specified on !init mounts. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Aravind Anbudurai <aru7@fb.com> Cc: Serge Hallyn <serge@hallyn.com> Cc: Eric Biederman <ebiederm@xmission.com>
Diffstat (limited to 'kernel/cgroup')
-rw-r--r--kernel/cgroup/cgroup.c88
1 files changed, 83 insertions, 5 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index d48069ee84c2..620794a20a33 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1547,10 +1547,56 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
return len;
}
+static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
+{
+ char *token;
+
+ *root_flags = 0;
+
+ if (!data)
+ return 0;
+
+ while ((token = strsep(&data, ",")) != NULL) {
+ if (!strcmp(token, "nsdelegate")) {
+ *root_flags |= CGRP_ROOT_NS_DELEGATE;
+ continue;
+ }
+
+ pr_err("cgroup2: unknown option \"%s\"\n", token);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void apply_cgroup_root_flags(unsigned int root_flags)
+{
+ if (current->nsproxy->cgroup_ns == &init_cgroup_ns) {
+ if (root_flags & CGRP_ROOT_NS_DELEGATE)
+ cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
+ else
+ cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
+ }
+}
+
+static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root)
+{
+ if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
+ seq_puts(seq, ",nsdelegate");
+ return 0;
+}
+
static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
{
- pr_err("remount is not allowed\n");
- return -EINVAL;
+ unsigned int root_flags;
+ int ret;
+
+ ret = parse_cgroup_root_flags(data, &root_flags);
+ if (ret)
+ return ret;
+
+ apply_cgroup_root_flags(root_flags);
+ return 0;
}
/*
@@ -1790,6 +1836,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
{
struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
struct dentry *dentry;
+ int ret;
get_cgroup_ns(ns);
@@ -1807,16 +1854,21 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
cgroup_enable_task_cg_lists();
if (fs_type == &cgroup2_fs_type) {
- if (data) {
- pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
+ unsigned int root_flags;
+
+ ret = parse_cgroup_root_flags(data, &root_flags);
+ if (ret) {
put_cgroup_ns(ns);
- return ERR_PTR(-EINVAL);
+ return ERR_PTR(ret);
}
+
cgrp_dfl_visible = true;
cgroup_get_live(&cgrp_dfl_root.cgrp);
dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root,
CGROUP2_SUPER_MAGIC, ns);
+ if (!IS_ERR(dentry))
+ apply_cgroup_root_flags(root_flags);
} else {
dentry = cgroup1_mount(&cgroup_fs_type, flags, data,
CGROUP_SUPER_MAGIC, ns);
@@ -2364,6 +2416,8 @@ static int cgroup_procs_write_permission(struct task_struct *task,
struct kernfs_open_file *of)
{
struct super_block *sb = of->file->f_path.dentry->d_sb;
+ struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
+ struct cgroup *root_cgrp = ns->root_cset->dfl_cgrp;
struct cgroup *src_cgrp, *com_cgrp;
struct inode *inode;
int ret;
@@ -2407,6 +2461,15 @@ static int cgroup_procs_write_permission(struct task_struct *task,
if (ret)
return ret;
+ /*
+ * If namespaces are delegation boundaries, %current must be able
+ * to see both source and destination cgroups from its namespace.
+ */
+ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) &&
+ (!cgroup_is_descendant(src_cgrp, root_cgrp) ||
+ !cgroup_is_descendant(dst_cgrp, root_cgrp)))
+ return -ENOENT;
+
return 0;
}
@@ -2971,11 +3034,23 @@ static void cgroup_file_release(struct kernfs_open_file *of)
static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
+ struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
struct cgroup *cgrp = of->kn->parent->priv;
struct cftype *cft = of->kn->priv;
struct cgroup_subsys_state *css;
int ret;
+ /*
+ * If namespaces are delegation boundaries, disallow writes to
+ * files in an non-init namespace root from inside the namespace
+ * except for the files explicitly marked delegatable -
+ * cgroup.procs and cgroup.subtree_control.
+ */
+ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) &&
+ !(cft->flags & CFTYPE_NS_DELEGATABLE) &&
+ ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp)
+ return -EPERM;
+
if (cft->write)
return cft->write(of, buf, nbytes, off);
@@ -3809,6 +3884,7 @@ static int cgroup_procs_show(struct seq_file *s, void *v)
static struct cftype cgroup_base_files[] = {
{
.name = "cgroup.procs",
+ .flags = CFTYPE_NS_DELEGATABLE,
.file_offset = offsetof(struct cgroup, procs_file),
.release = cgroup_procs_release,
.seq_start = cgroup_procs_start,
@@ -3822,6 +3898,7 @@ static struct cftype cgroup_base_files[] = {
},
{
.name = "cgroup.subtree_control",
+ .flags = CFTYPE_NS_DELEGATABLE,
.seq_show = cgroup_subtree_control_show,
.write = cgroup_subtree_control_write,
},
@@ -4410,6 +4487,7 @@ int cgroup_rmdir(struct kernfs_node *kn)
}
static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
+ .show_options = cgroup_show_options,
.remount_fs = cgroup_remount,
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,