Merge branch 'for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Several notable changes this cycle:

   - Thread mode was merged. This will be used for cgroup2 support for
     CPU and possibly other controllers. Unfortunately, CPU controller
     cgroup2 support didn't make this pull request but most contentions
     have been resolved and the support is likely to be merged before
     the next merge window.

   - cgroup.stat now shows the number of descendant cgroups.

   - cpuset now can enable the easier-to-configure v2 behavior on v1
     hierarchy"

* 'for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  cpuset: Allow v2 behavior in v1 cgroup
  cgroup: Add mount flag to enable cpuset to use v2 behavior in v1 cgroup
  cgroup: remove unneeded checks
  cgroup: misc changes
  cgroup: short-circuit cset_cgroup_from_root() on the default hierarchy
  cgroup: re-use the parent pointer in cgroup_destroy_locked()
  cgroup: add cgroup.stat interface with basic hierarchy stats
  cgroup: implement hierarchy limits
  cgroup: keep track of number of descent cgroups
  cgroup: add comment to cgroup_enable_threaded()
  cgroup: remove unnecessary empty check when enabling threaded mode
  cgroup: update debug controller to print out thread mode information
  cgroup: implement cgroup v2 thread support
  cgroup: implement CSS_TASK_ITER_THREADED
  cgroup: introduce cgroup->dom_cgrp and threaded css_set handling
  cgroup: add @flags to css_task_iter_start() and implement CSS_TASK_ITER_PROCS
  cgroup: reorganize cgroup.procs / task write path
  cgroup: replace css_set walking populated test with testing cgrp->nr_populated_csets
  cgroup: distinguish local and children populated states
  cgroup: remove now unused list_head @pending in cgroup_apply_cftypes()
  ...

2 files changed, 101 insertions, 6 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 09f4c7df1478..ade4a78a54c2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -74,6 +74,11 @@ enum {
 	 * aren't writeable from inside the namespace.
 	 */
 	CGRP_ROOT_NS_DELEGATE	= (1 << 3),
+
+	/*
+	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
+	 */
+	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
 };
 
 /* cftype->flags */
@@ -172,6 +177,14 @@ struct css_set {
 	/* reference count */
 	refcount_t refcount;
 
+	/*
+	 * For a domain cgroup, the following points to self.  If threaded,
+	 * to the matching cset of the nearest domain ancestor.  The
+	 * dom_cset provides access to the domain cgroup and its csses to
+	 * which domain level resource consumptions should be charged.
+	 */
+	struct css_set *dom_cset;
+
 	/* the default cgroup associated with this css_set */
 	struct cgroup *dfl_cgrp;
 
@@ -200,6 +213,10 @@ struct css_set {
 	 */
 	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
 
+	/* all threaded csets whose ->dom_cset points to this cset */
+	struct list_head threaded_csets;
+	struct list_head threaded_csets_node;
+
 	/*
 	 * List running through all cgroup groups in the same hash
 	 * slot. Protected by css_set_lock
@@ -261,13 +278,35 @@ struct cgroup {
 	 */
 	int level;
 
+	/* Maximum allowed descent tree depth */
+	int max_depth;
+
+	/*
+	 * Keep track of total numbers of visible and dying descent cgroups.
+	 * Dying cgroups are cgroups which were deleted by a user,
+	 * but are still existing because someone else is holding a reference.
+	 * max_descendants is a maximum allowed number of descent cgroups.
+	 */
+	int nr_descendants;
+	int nr_dying_descendants;
+	int max_descendants;
+
 	/*
 	 * Each non-empty css_set associated with this cgroup contributes
-	 * one to populated_cnt.  All children with non-zero popuplated_cnt
-	 * of their own contribute one.  The count is zero iff there's no
-	 * task in this cgroup or its subtree.
+	 * one to nr_populated_csets.  The counter is zero iff this cgroup
+	 * doesn't have any tasks.
+	 *
+	 * All children which have non-zero nr_populated_csets and/or
+	 * nr_populated_children of their own contribute one to either
+	 * nr_populated_domain_children or nr_populated_threaded_children
+	 * depending on their type.  Each counter is zero iff all cgroups
+	 * of the type in the subtree proper don't have any tasks.
 	 */
-	int populated_cnt;
+	int nr_populated_csets;
+	int nr_populated_domain_children;
+	int nr_populated_threaded_children;
+
+	int nr_threaded_children;	/* # of live threaded child cgroups */
 
 	struct kernfs_node *kn;		/* cgroup kernfs entry */
 	struct cgroup_file procs_file;	/* handle for "cgroup.procs" */
@@ -306,6 +345,15 @@ struct cgroup {
 	struct list_head e_csets[CGROUP_SUBSYS_COUNT];
 
 	/*
+	 * If !threaded, self.  If threaded, it points to the nearest
+	 * domain ancestor.  Inside a threaded subtree, cgroups are exempt
+	 * from process granularity and no-internal-task constraint.
+	 * Domain level resource consumptions which aren't tied to a
+	 * specific task are charged to the dom_cgrp.
+	 */
+	struct cgroup *dom_cgrp;
+
+	/*
 	 * list of pidlists, up to two for each namespace (one for procs, one
 	 * for tasks); created on demand.
 	 */
@@ -492,6 +540,18 @@ struct cgroup_subsys {
 	bool implicit_on_dfl:1;
 
 	/*
+	 * If %true, the controller, supports threaded mode on the default
+	 * hierarchy.  In a threaded subtree, both process granularity and
+	 * no-internal-process constraint are ignored and a threaded
+	 * controllers should be able to handle that.
+	 *
+	 * Note that as an implicit controller is automatically enabled on
+	 * all cgroups on the default hierarchy, it should also be
+	 * threaded.  implicit && !threaded is not supported.
+	 */
+	bool threaded:1;
+
+	/*
 	 * If %false, this subsystem is properly hierarchical -
 	 * configuration, resource accounting and restriction on a parent
 	 * cgroup cover those of its children.  If %true, hierarchy support
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 710a005c6b7a..085056e562b1 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -36,18 +36,28 @@
 #define CGROUP_WEIGHT_DFL		100
 #define CGROUP_WEIGHT_MAX		10000
 
+/* walk only threadgroup leaders */
+#define CSS_TASK_ITER_PROCS		(1U << 0)
+/* walk all threaded css_sets in the domain */
+#define CSS_TASK_ITER_THREADED		(1U << 1)
+
 /* a css_task_iter should be treated as an opaque object */
 struct css_task_iter {
 	struct cgroup_subsys		*ss;
+	unsigned int			flags;
 
 	struct list_head		*cset_pos;
 	struct list_head		*cset_head;
 
+	struct list_head		*tcset_pos;
+	struct list_head		*tcset_head;
+
 	struct list_head		*task_pos;
 	struct list_head		*tasks_head;
 	struct list_head		*mg_tasks_head;
 
 	struct css_set			*cur_cset;
+	struct css_set			*cur_dcset;
 	struct task_struct		*cur_task;
 	struct list_head		iters_node;	/* css_set->task_iters */
 };
@@ -129,7 +139,7 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
 struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
 					struct cgroup_subsys_state **dst_cssp);
 
-void css_task_iter_start(struct cgroup_subsys_state *css,
+void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 			 struct css_task_iter *it);
 struct task_struct *css_task_iter_next(struct css_task_iter *it);
 void css_task_iter_end(struct css_task_iter *it);
@@ -388,6 +398,16 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
 		percpu_ref_put_many(&css->refcnt, n);
 }
 
+static inline void cgroup_get(struct cgroup *cgrp)
+{
+	css_get(&cgrp->self);
+}
+
+static inline bool cgroup_tryget(struct cgroup *cgrp)
+{
+	return css_tryget(&cgrp->self);
+}
+
 static inline void cgroup_put(struct cgroup *cgrp)
 {
 	css_put(&cgrp->self);
@@ -500,6 +520,20 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
 	return task_css(task, subsys_id)->cgroup;
 }
 
+static inline struct cgroup *task_dfl_cgroup(struct task_struct *task)
+{
+	return task_css_set(task)->dfl_cgrp;
+}
+
+static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
+{
+	struct cgroup_subsys_state *parent_css = cgrp->self.parent;
+
+	if (parent_css)
+		return container_of(parent_css, struct cgroup, self);
+	return NULL;
+}
+
 /**
  * cgroup_is_descendant - test ancestry
  * @cgrp: the cgroup to be tested
@@ -537,7 +571,8 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 /* no synchronization, the result can only be used as a hint */
 static inline bool cgroup_is_populated(struct cgroup *cgrp)
 {
-	return cgrp->populated_cnt;
+	return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children +
+		cgrp->nr_populated_threaded_children;
 }
 
 /* returns ino associated with a cgroup */