summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--kernel/cgroup/Makefile2
-rw-r--r--kernel/cgroup/cgroup-internal.h32
-rw-r--r--kernel/cgroup/cgroup.c175
-rw-r--r--kernel/cgroup/namespace.c155
4 files changed, 189 insertions, 175 deletions
diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile
index 719588cb18cd..6d42a3211164 100644
--- a/kernel/cgroup/Makefile
+++ b/kernel/cgroup/Makefile
@@ -1,4 +1,4 @@
-obj-y := cgroup.o cgroup-v1.o
+obj-y := cgroup.o namespace.o cgroup-v1.o
obj-$(CONFIG_CGROUP_FREEZER) += freezer.o
obj-$(CONFIG_CGROUP_PIDS) += pids.o
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index a890c92cb688..589b0e7013ec 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -65,6 +65,33 @@ static inline bool notify_on_release(const struct cgroup *cgrp)
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}
+void put_css_set_locked(struct css_set *cset);
+
+static inline void put_css_set(struct css_set *cset)
+{
+ unsigned long flags;
+
+ /*
+ * Ensure that the refcount doesn't hit zero while any readers
+ * can see it. Similar to atomic_dec_and_lock(), but for an
+ * rwlock
+ */
+ if (atomic_add_unless(&cset->refcount, -1, 1))
+ return;
+
+ spin_lock_irqsave(&css_set_lock, flags);
+ put_css_set_locked(cset);
+ spin_unlock_irqrestore(&css_set_lock, flags);
+}
+
+/*
+ * refcounted get/put for css_set objects
+ */
+static inline void get_css_set(struct css_set *cset)
+{
+ atomic_inc(&cset->refcount);
+}
+
bool cgroup_ssid_enabled(int ssid);
bool cgroup_on_dfl(const struct cgroup *cgrp);
@@ -108,6 +135,11 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
struct kernfs_root *kf_root);
/*
+ * namespace.c
+ */
+extern const struct proc_ns_operations cgroupns_operations;
+
+/*
* cgroup-v1.c
*/
extern struct cftype cgroup1_base_files[];
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a05a2dacf5dc..b6b9068ef468 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -718,7 +718,7 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
return key;
}
-static void put_css_set_locked(struct css_set *cset)
+void put_css_set_locked(struct css_set *cset)
{
struct cgrp_cset_link *link, *tmp_link;
struct cgroup_subsys *ss;
@@ -748,31 +748,6 @@ static void put_css_set_locked(struct css_set *cset)
kfree_rcu(cset, rcu_head);
}
-static void put_css_set(struct css_set *cset)
-{
- unsigned long flags;
-
- /*
- * Ensure that the refcount doesn't hit zero while any readers
- * can see it. Similar to atomic_dec_and_lock(), but for an
- * rwlock
- */
- if (atomic_add_unless(&cset->refcount, -1, 1))
- return;
-
- spin_lock_irqsave(&css_set_lock, flags);
- put_css_set_locked(cset);
- spin_unlock_irqrestore(&css_set_lock, flags);
-}
-
-/*
- * refcounted get/put for css_set objects
- */
-static inline void get_css_set(struct css_set *cset)
-{
- atomic_inc(&cset->refcount);
-}
-
/**
* compare_css_sets - helper function for find_existing_css_set().
* @cset: candidate css_set being tested
@@ -5109,154 +5084,6 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
#endif /* CONFIG_SOCK_CGROUP_DATA */
-/* 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;
- int ret;
-
- new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
- if (!new_ns)
- return ERR_PTR(-ENOMEM);
- ret = ns_alloc_inum(&new_ns->ns);
- if (ret) {
- kfree(new_ns);
- return ERR_PTR(ret);
- }
- atomic_set(&new_ns->count, 1);
- new_ns->ns.ops = &cgroupns_operations;
- return new_ns;
-}
-
-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);
-}
-EXPORT_SYMBOL(free_cgroup_ns);
-
-struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
- struct user_namespace *user_ns,
- struct cgroup_namespace *old_ns)
-{
- struct cgroup_namespace *new_ns;
- struct ucounts *ucounts;
- struct css_set *cset;
-
- BUG_ON(!old_ns);
-
- if (!(flags & CLONE_NEWCGROUP)) {
- get_cgroup_ns(old_ns);
- return old_ns;
- }
-
- /* Allow only sysadmin to create cgroup namespace. */
- 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);
- get_css_set(cset);
- spin_unlock_irq(&css_set_lock);
-
- 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;
-}
-
-static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
-{
- return container_of(ns, struct cgroup_namespace, ns);
-}
-
-static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns)
-{
- struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
-
- if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) ||
- !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
- return -EPERM;
-
- /* Don't need to do anything if we are attaching to our own cgroupns. */
- if (cgroup_ns == nsproxy->cgroup_ns)
- return 0;
-
- get_cgroup_ns(cgroup_ns);
- put_cgroup_ns(nsproxy->cgroup_ns);
- nsproxy->cgroup_ns = cgroup_ns;
-
- return 0;
-}
-
-static struct ns_common *cgroupns_get(struct task_struct *task)
-{
- struct cgroup_namespace *ns = NULL;
- struct nsproxy *nsproxy;
-
- task_lock(task);
- nsproxy = task->nsproxy;
- if (nsproxy) {
- ns = nsproxy->cgroup_ns;
- get_cgroup_ns(ns);
- }
- task_unlock(task);
-
- return ns ? &ns->ns : NULL;
-}
-
-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)
-{
- return 0;
-}
-subsys_initcall(cgroup_namespaces_init);
-
#ifdef CONFIG_CGROUP_BPF
void cgroup_bpf_update(struct cgroup *cgrp,
struct bpf_prog *prog,
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
new file mode 100644
index 000000000000..cff7ea62c38f
--- /dev/null
+++ b/kernel/cgroup/namespace.c
@@ -0,0 +1,155 @@
+#include "cgroup-internal.h"
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/nsproxy.h>
+#include <linux/proc_ns.h>
+
+
+/* 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;
+ int ret;
+
+ new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
+ if (!new_ns)
+ return ERR_PTR(-ENOMEM);
+ ret = ns_alloc_inum(&new_ns->ns);
+ if (ret) {
+ kfree(new_ns);
+ return ERR_PTR(ret);
+ }
+ atomic_set(&new_ns->count, 1);
+ new_ns->ns.ops = &cgroupns_operations;
+ return new_ns;
+}
+
+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);
+}
+EXPORT_SYMBOL(free_cgroup_ns);
+
+struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
+ struct user_namespace *user_ns,
+ struct cgroup_namespace *old_ns)
+{
+ struct cgroup_namespace *new_ns;
+ struct ucounts *ucounts;
+ struct css_set *cset;
+
+ BUG_ON(!old_ns);
+
+ if (!(flags & CLONE_NEWCGROUP)) {
+ get_cgroup_ns(old_ns);
+ return old_ns;
+ }
+
+ /* Allow only sysadmin to create cgroup namespace. */
+ 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);
+ get_css_set(cset);
+ spin_unlock_irq(&css_set_lock);
+
+ 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;
+}
+
+static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
+{
+ return container_of(ns, struct cgroup_namespace, ns);
+}
+
+static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+{
+ struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
+
+ if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) ||
+ !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /* Don't need to do anything if we are attaching to our own cgroupns. */
+ if (cgroup_ns == nsproxy->cgroup_ns)
+ return 0;
+
+ get_cgroup_ns(cgroup_ns);
+ put_cgroup_ns(nsproxy->cgroup_ns);
+ nsproxy->cgroup_ns = cgroup_ns;
+
+ return 0;
+}
+
+static struct ns_common *cgroupns_get(struct task_struct *task)
+{
+ struct cgroup_namespace *ns = NULL;
+ struct nsproxy *nsproxy;
+
+ task_lock(task);
+ nsproxy = task->nsproxy;
+ if (nsproxy) {
+ ns = nsproxy->cgroup_ns;
+ get_cgroup_ns(ns);
+ }
+ task_unlock(task);
+
+ return ns ? &ns->ns : NULL;
+}
+
+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)
+{
+ return 0;
+}
+subsys_initcall(cgroup_namespaces_init);