Merge branch 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Several noteworthy changes.

   - Parav's rdma controller is finally merged. It is very straight
     forward and can limit the abosolute numbers of common rdma
     constructs used by different cgroups.

   - kernel/cgroup.c got too chubby and disorganized. Created
     kernel/cgroup/ subdirectory and moved all cgroup related files
     under kernel/ there and reorganized the core code. This hurts for
     backporting patches but was long overdue.

   - cgroup v2 process listing reimplemented so that it no longer
     depends on allocating a buffer large enough to cache the entire
     result to sort and uniq the output. v2 has always mangled the sort
     order to ensure that users don't depend on the sorted output, so
     this shouldn't surprise anybody. This makes the pid listing
     functions use the same iterators that are used internally, which
     have to have the same iterating capabilities anyway.

   - perf cgroup filtering now works automatically on cgroup v2. This
     patch was posted a long time ago but somehow fell through the
     cracks.

   - misc fixes asnd documentation updates"

* 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (27 commits)
  kernfs: fix locking around kernfs_ops->release() callback
  cgroup: drop the matching uid requirement on migration for cgroup v2
  cgroup, perf_event: make perf_event controller work on cgroup2 hierarchy
  cgroup: misc cleanups
  cgroup: call subsys->*attach() only for subsystems which are actually affected by migration
  cgroup: track migration context in cgroup_mgctx
  cgroup: cosmetic update to cgroup_taskset_add()
  rdmacg: Fixed uninitialized current resource usage
  cgroup: Add missing cgroup-v2 PID controller documentation.
  rdmacg: Added documentation for rdmacg
  IB/core: added support to use rdma cgroup controller
  rdmacg: Added rdma cgroup controller
  cgroup: fix a comment typo
  cgroup: fix RCU related sparse warnings
  cgroup: move namespace code to kernel/cgroup/namespace.c
  cgroup: rename functions for consistency
  cgroup: move v1 mount functions to kernel/cgroup/cgroup-v1.c
  cgroup: separate out cgroup1_kf_syscall_ops
  cgroup: refactor mount path and clearly distinguish v1 and v2 paths
  cgroup: move cgroup v1 specific code to kernel/cgroup/cgroup-v1.c
  ...

1 files changed, 155 insertions, 0 deletions

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);