Merge branch 'for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/tj/cgroup

Pull cgroup changes from Tejun Heo:

 - Waiman made the debug controller work and a lot more useful on
   cgroup2

 - There were a couple issues with cgroup subtree delegation. The
   documentation on delegating to a non-root user was missing some part
   and cgroup namespace support wasn't factoring in delegation at all.
   The documentation is updated and the now there is a mount option to
   make cgroup namespace fit for delegation

* 'for-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: implement "nsdelegate" mount option
  cgroup: restructure cgroup_procs_write_permission()
  cgroup: "cgroup.subtree_control" should be writeable by delegatee
  cgroup: fix lockdep warning in debug controller
  cgroup: refactor cgroup_masks_read() in the debug controller
  cgroup: make debug an implicit controller on cgroup2
  cgroup: Make debug cgroup support v2 and thread mode
  cgroup: Make Kconfig prompt of debug cgroup more accurate
  cgroup: Move debug cgroup to its own file
  cgroup: Keep accurate count of tasks in each css_set

Documentation/cgroup-v2.txt

@@ -149,6 +149,16 @@ during boot, before manual intervention is possible. To make testing
 and experimenting easier, the kernel parameter cgroup_no_v1= allows
 disabling controllers in v1 and make them always available in v2.
 
+cgroup v2 currently supports the following mount options.
+
+  nsdelegate
+
+	Consider cgroup namespaces as delegation boundaries.  This
+	option is system wide and can only be set on mount or modified
+	through remount from the init namespace.  The mount option is
+	ignored on non-init namespace mounts.  Please refer to the
+	Delegation section for details.
+
 
 2-2. Organizing Processes
 
@@ -308,18 +318,27 @@ file.
 
 2-5-1. Model of Delegation
 
-A cgroup can be delegated to a less privileged user by granting write
-access of the directory and its "cgroup.procs" file to the user.  Note
-that resource control interface files in a given directory control the
-distribution of the parent's resources and thus must not be delegated
-along with the directory.
-
-Once delegated, the user can build sub-hierarchy under the directory,
-organize processes as it sees fit and further distribute the resources
-it received from the parent.  The limits and other settings of all
-resource controllers are hierarchical and regardless of what happens
-in the delegated sub-hierarchy, nothing can escape the resource
-restrictions imposed by the parent.
+A cgroup can be delegated in two ways.  First, to a less privileged
+user by granting write access of the directory and its "cgroup.procs"
+and "cgroup.subtree_control" files to the user.  Second, if the
+"nsdelegate" mount option is set, automatically to a cgroup namespace
+on namespace creation.
+
+Because the resource control interface files in a given directory
+control the distribution of the parent's resources, the delegatee
+shouldn't be allowed to write to them.  For the first method, this is
+achieved by not granting access to these files.  For the second, the
+kernel rejects writes to all files other than "cgroup.procs" and
+"cgroup.subtree_control" on a namespace root from inside the
+namespace.
+
+The end results are equivalent for both delegation types.  Once
+delegated, the user can build sub-hierarchy under the directory,
+organize processes inside it as it sees fit and further distribute the
+resources it received from the parent.  The limits and other settings
+of all resource controllers are hierarchical and regardless of what
+happens in the delegated sub-hierarchy, nothing can escape the
+resource restrictions imposed by the parent.
 
 Currently, cgroup doesn't impose any restrictions on the number of
 cgroups in or nesting depth of a delegated sub-hierarchy; however,
@@ -329,10 +348,12 @@ this may be limited explicitly in the future.
 2-5-2. Delegation Containment
 
 A delegated sub-hierarchy is contained in the sense that processes
-can't be moved into or out of the sub-hierarchy by the delegatee.  For
-a process with a non-root euid to migrate a target process into a
-cgroup by writing its PID to the "cgroup.procs" file, the following
-conditions must be met.
+can't be moved into or out of the sub-hierarchy by the delegatee.
+
+For delegations to a less privileged user, this is achieved by
+requiring the following conditions for a process with a non-root euid
+to migrate a target process into a cgroup by writing its PID to the
+"cgroup.procs" file.
 
 - The writer must have write access to the "cgroup.procs" file.
 
@@ -359,6 +380,11 @@ destination cgroup C00 is above the points of delegation and U0 would
 not have write access to its "cgroup.procs" files and thus the write
 will be denied with -EACCES.
 
+For delegations to namespaces, containment is achieved by requiring
+that both the source and destination cgroups are reachable from the
+namespace of the process which is attempting the migration.  If either
+is not reachable, the migration is rejected with -ENOENT.
+
 
 2-6. Guidelines
 
@@ -1413,7 +1439,7 @@ D. Deprecated v1 Core Features
 
 - Multiple hierarchies including named ones are not supported.
 
-- All mount options and remounting are not supported.
+- All v1 mount options are not supported.
 
 - The "tasks" file is removed and "cgroup.procs" is not sorted.
 

include/linux/cgroup-defs.h

@@ -67,12 +67,21 @@ enum {
 enum {
 	CGRP_ROOT_NOPREFIX	= (1 << 1), /* mounted subsystems have no named prefix */
 	CGRP_ROOT_XATTR		= (1 << 2), /* supports extended attributes */
+
+	/*
+	 * Consider namespaces as delegation boundaries.  If this flag is
+	 * set, controller specific interface files in a namespace root
+	 * aren't writeable from inside the namespace.
+	 */
+	CGRP_ROOT_NS_DELEGATE	= (1 << 3),
 };
 
 /* cftype->flags */
 enum {
 	CFTYPE_ONLY_ON_ROOT	= (1 << 0),	/* only create on root cgrp */
 	CFTYPE_NOT_ON_ROOT	= (1 << 1),	/* don't create on root cgrp */
+	CFTYPE_NS_DELEGATABLE	= (1 << 2),	/* writeable beyond delegation boundaries */
+
 	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
 	CFTYPE_WORLD_WRITABLE	= (1 << 4),	/* (DON'T USE FOR NEW FILES) S_IWUGO */
 
@@ -166,6 +175,9 @@ struct css_set {
 	/* the default cgroup associated with this css_set */
 	struct cgroup *dfl_cgrp;
 
+	/* internal task count, protected by css_set_lock */
+	int nr_tasks;
+
 	/*
 	 * Lists running through all tasks using this cgroup group.
 	 * mg_tasks lists tasks which belong to this cset but are in the

init/Kconfig

@@ -859,11 +859,14 @@ config CGROUP_BPF
 	  inet sockets.
 
 config CGROUP_DEBUG
-	bool "Example controller"
+	bool "Debug controller"
 	default n
+	depends on DEBUG_KERNEL
 	help
 	  This option enables a simple controller that exports
-	  debugging information about the cgroups framework.
+	  debugging information about the cgroups framework. This
+	  controller is for control cgroup debugging only. Its
+	  interfaces are not stable.
 
 	  Say N.
 

kernel/cgroup/Makefile

@@ -4,3 +4,4 @@ obj-$(CONFIG_CGROUP_FREEZER) += freezer.o
 obj-$(CONFIG_CGROUP_PIDS) += pids.o
 obj-$(CONFIG_CGROUP_RDMA) += rdma.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
+obj-$(CONFIG_CGROUP_DEBUG) += debug.o

kernel/cgroup/cgroup-internal.h

@@ -192,6 +192,8 @@ int cgroup_rmdir(struct kernfs_node *kn);
 int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 		     struct kernfs_root *kf_root);
 
+int cgroup_task_count(const struct cgroup *cgrp);
+
 /*
  * namespace.c
  */

kernel/cgroup/cgroup-v1.c

@@ -334,19 +334,15 @@ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp,
 /**
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
- *
- * Return the number of tasks in the cgroup.  The returned number can be
- * higher than the actual number of tasks due to css_set references from
- * namespace roots and temporary usages.
  */
-static int cgroup_task_count(const struct cgroup *cgrp)
+int cgroup_task_count(const struct cgroup *cgrp)
 {
 	int count = 0;
 	struct cgrp_cset_link *link;
 
 	spin_lock_irq(&css_set_lock);
 	list_for_each_entry(link, &cgrp->cset_links, cset_link)
-		count += refcount_read(&link->cset->refcount);
+		count += link->cset->nr_tasks;
 	spin_unlock_irq(&css_set_lock);
 	return count;
 }
@@ -1263,150 +1259,3 @@ static int __init cgroup_no_v1(char *str)
 	return 1;
 }
 __setup("cgroup_no_v1=", cgroup_no_v1);
-
-
-#ifdef CONFIG_CGROUP_DEBUG
-static struct cgroup_subsys_state *
-debug_css_alloc(struct cgroup_subsys_state *parent_css)
-{
-	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
-
-	if (!css)
-		return ERR_PTR(-ENOMEM);
-
-	return css;
-}
-
-static void debug_css_free(struct cgroup_subsys_state *css)
-{
-	kfree(css);
-}
-
-static u64 debug_taskcount_read(struct cgroup_subsys_state *css,
-				struct cftype *cft)
-{
-	return cgroup_task_count(css->cgroup);
-}
-
-static u64 current_css_set_read(struct cgroup_subsys_state *css,
-				struct cftype *cft)
-{
-	return (u64)(unsigned long)current->cgroups;
-}
-
-static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css,
-					 struct cftype *cft)
-{
-	u64 count;
-
-	rcu_read_lock();
-	count = refcount_read(&task_css_set(current)->refcount);
-	rcu_read_unlock();
-	return count;
-}
-
-static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
-{
-	struct cgrp_cset_link *link;
-	struct css_set *cset;
-	char *name_buf;
-
-	name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
-	if (!name_buf)
-		return -ENOMEM;
-
-	spin_lock_irq(&css_set_lock);
-	rcu_read_lock();
-	cset = rcu_dereference(current->cgroups);
-	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
-		struct cgroup *c = link->cgrp;
-
-		cgroup_name(c, name_buf, NAME_MAX + 1);
-		seq_printf(seq, "Root %d group %s\n",
-			   c->root->hierarchy_id, name_buf);
-	}
-	rcu_read_unlock();
-	spin_unlock_irq(&css_set_lock);
-	kfree(name_buf);
-	return 0;
-}
-
-#define MAX_TASKS_SHOWN_PER_CSS 25
-static int cgroup_css_links_read(struct seq_file *seq, void *v)
-{
-	struct cgroup_subsys_state *css = seq_css(seq);
-	struct cgrp_cset_link *link;
-
-	spin_lock_irq(&css_set_lock);
-	list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
-		struct css_set *cset = link->cset;
-		struct task_struct *task;
-		int count = 0;
-
-		seq_printf(seq, "css_set %pK\n", cset);
-
-		list_for_each_entry(task, &cset->tasks, cg_list) {
-			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
-				goto overflow;
-			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
-		}
-
-		list_for_each_entry(task, &cset->mg_tasks, cg_list) {
-			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
-				goto overflow;
-			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
-		}
-		continue;
-	overflow:
-		seq_puts(seq, "  ...\n");
-	}
-	spin_unlock_irq(&css_set_lock);
-	return 0;
-}
-
-static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
-{
-	return (!cgroup_is_populated(css->cgroup) &&
-		!css_has_online_children(&css->cgroup->self));
-}
-
-static struct cftype debug_files[] =  {
-	{
-		.name = "taskcount",
-		.read_u64 = debug_taskcount_read,
-	},
-
-	{
-		.name = "current_css_set",
-		.read_u64 = current_css_set_read,
-	},
-
-	{
-		.name = "current_css_set_refcount",
-		.read_u64 = current_css_set_refcount_read,
-	},
-
-	{
-		.name = "current_css_set_cg_links",
-		.seq_show = current_css_set_cg_links_read,
-	},
-
-	{
-		.name = "cgroup_css_links",
-		.seq_show = cgroup_css_links_read,
-	},
-
-	{
-		.name = "releasable",
-		.read_u64 = releasable_read,
-	},
-
-	{ }	/* terminate */
-};
-
-struct cgroup_subsys debug_cgrp_subsys = {
-	.css_alloc = debug_css_alloc,
-	.css_free = debug_css_free,
-	.legacy_cftypes = debug_files,
-};
-#endif /* CONFIG_CGROUP_DEBUG */