Merge branch 'for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "The cgroup core saw several significant updates this cycle:

   - percpu_rwsem for threadgroup locking is reinstated.  This was
     temporarily dropped due to down_write latency issues.  Oleg's
     rework of percpu_rwsem which is scheduled to be merged in this
     merge window resolves the issue.

   - On the v2 hierarchy, when controllers are enabled and disabled, all
     operations are atomic and can fail and revert cleanly.  This allows
     ->can_attach() failure which is necessary for cpu RT slices.

   - Tasks now stay associated with the original cgroups after exit
     until released.  This allows tracking resources held by zombies
     (e.g.  pids) and makes it easy to find out where zombies came from
     on the v2 hierarchy.  The pids controller was broken before these
     changes as zombies escaped the limits; unfortunately, updating this
     behavior required too many invasive changes and I don't think it's
     a good idea to backport them, so the pids controller on 4.3, the
     first version which included the pids controller, will stay broken
     at least until I'm sure about the cgroup core changes.

   - Optimization of a couple common tests using static_key"

* 'for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (38 commits)
  cgroup: fix race condition around termination check in css_task_iter_next()
  blkcg: don't create "io.stat" on the root cgroup
  cgroup: drop cgroup__DEVEL__legacy_files_on_dfl
  cgroup: replace error handling in cgroup_init() with WARN_ON()s
  cgroup: add cgroup_subsys->free() method and use it to fix pids controller
  cgroup: keep zombies associated with their original cgroups
  cgroup: make css_set_rwsem a spinlock and rename it to css_set_lock
  cgroup: don't hold css_set_rwsem across css task iteration
  cgroup: reorganize css_task_iter functions
  cgroup: factor out css_set_move_task()
  cgroup: keep css_set and task lists in chronological order
  cgroup: make cgroup_destroy_locked() test cgroup_is_populated()
  cgroup: make css_sets pin the associated cgroups
  cgroup: relocate cgroup_[try]get/put()
  cgroup: move check_for_release() invocation
  cgroup: replace cgroup_has_tasks() with cgroup_is_populated()
  cgroup: make cgroup->nr_populated count the number of populated css_sets
  cgroup: remove an unused parameter from cgroup_task_migrate()
  cgroup: fix too early usage of static_branch_disable()
  cgroup: make cgroup_update_dfl_csses() migrate all target processes atomically
  ...

1 files changed, 66 insertions, 63 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index eb7ca55f72ef..22e3754f89c5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -13,10 +13,10 @@
 #include <linux/nodemask.h>
 #include <linux/rculist.h>
 #include <linux/cgroupstats.h>
-#include <linux/rwsem.h>
 #include <linux/fs.h>
 #include <linux/seq_file.h>
 #include <linux/kernfs.h>
+#include <linux/jump_label.h>
 
 #include <linux/cgroup-defs.h>
 
@@ -41,6 +41,10 @@ struct css_task_iter {
         struct list_head                *task_pos;
         struct list_head                *tasks_head;
         struct list_head                *mg_tasks_head;
+
+        struct css_set                  *cur_cset;
+        struct task_struct              *cur_task;
+        struct list_head                iters_node;     /* css_set->task_iters */
 };
 
 extern struct cgroup_root cgrp_dfl_root;
@@ -50,6 +54,26 @@ extern struct css_set init_css_set;
 #include <linux/cgroup_subsys.h>
 #undef SUBSYS
 
+#define SUBSYS(_x)                                                              \
+        extern struct static_key_true _x ## _cgrp_subsys_enabled_key;           \
+        extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key;
+#include <linux/cgroup_subsys.h>
+#undef SUBSYS
+
+/**
+ * cgroup_subsys_enabled - fast test on whether a subsys is enabled
+ * @ss: subsystem in question
+ */
+#define cgroup_subsys_enabled(ss)                                               \
+        static_branch_likely(&ss ## _enabled_key)
+
+/**
+ * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy
+ * @ss: subsystem in question
+ */
+#define cgroup_subsys_on_dfl(ss)                                                \
+        static_branch_likely(&ss ## _on_dfl_key)
+
 bool css_has_online_children(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
 struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
@@ -78,6 +102,7 @@ extern void cgroup_cancel_fork(struct task_struct *p,
 extern void cgroup_post_fork(struct task_struct *p,
                              void *old_ss_priv[CGROUP_CANFORK_COUNT]);
 void cgroup_exit(struct task_struct *p);
+void cgroup_free(struct task_struct *p);
 
 int cgroup_init_early(void);
 int cgroup_init(void);
@@ -211,11 +236,33 @@ void css_task_iter_end(struct css_task_iter *it);
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
  * @tset: taskset to iterate
+ *
+ * @tset may contain multiple tasks and they may belong to multiple
+ * processes.  When there are multiple tasks in @tset, if a task of a
+ * process is in @tset, all tasks of the process are in @tset.  Also, all
+ * are guaranteed to share the same source and destination csses.
+ *
+ * Iteration is not in any specific order.
  */
 #define cgroup_taskset_for_each(task, tset)                             \
         for ((task) = cgroup_taskset_first((tset)); (task);             \
              (task) = cgroup_taskset_next((tset)))
 
+/**
+ * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
+ * @leader: the loop cursor
+ * @tset: takset to iterate
+ *
+ * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
+ * may not contain any.
+ */
+#define cgroup_taskset_for_each_leader(leader, tset)                    \
+        for ((leader) = cgroup_taskset_first((tset)); (leader);         \
+             (leader) = cgroup_taskset_next((tset)))                    \
+                if ((leader) != (leader)->group_leader)                 \
+                        ;                                               \
+                else
+
 /*
  * Inline functions.
  */
@@ -320,11 +367,11 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
  */
 #ifdef CONFIG_PROVE_RCU
 extern struct mutex cgroup_mutex;
-extern struct rw_semaphore css_set_rwsem;
+extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)                                   \
         rcu_dereference_check((task)->cgroups,                          \
                 lockdep_is_held(&cgroup_mutex) ||                       \
-                lockdep_is_held(&css_set_rwsem) ||                      \
+                lockdep_is_held(&css_set_lock) ||                       \
                 ((task)->flags & PF_EXITING) || (__c))
 #else
 #define task_css_set_check(task, __c)                                   \
@@ -412,68 +459,10 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
         return task_css(task, subsys_id)->cgroup;
 }
 
-/**
- * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
- * @cgrp: the cgroup of interest
- *
- * The default hierarchy is the v2 interface of cgroup and this function
- * can be used to test whether a cgroup is on the default hierarchy for
- * cases where a subsystem should behave differnetly depending on the
- * interface version.
- *
- * The set of behaviors which change on the default hierarchy are still
- * being determined and the mount option is prefixed with __DEVEL__.
- *
- * List of changed behaviors:
- *
- * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
- *   and "name" are disallowed.
- *
- * - When mounting an existing superblock, mount options should match.
- *
- * - Remount is disallowed.
- *
- * - rename(2) is disallowed.
- *
- * - "tasks" is removed.  Everything should be at process granularity.  Use
- *   "cgroup.procs" instead.
- *
- * - "cgroup.procs" is not sorted.  pids will be unique unless they got
- *   recycled inbetween reads.
- *
- * - "release_agent" and "notify_on_release" are removed.  Replacement
- *   notification mechanism will be implemented.
- *
- * - "cgroup.clone_children" is removed.
- *
- * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
- *   and its descendants contain no task; otherwise, 1.  The file also
- *   generates kernfs notification which can be monitored through poll and
- *   [di]notify when the value of the file changes.
- *
- * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
- *   take masks of ancestors with non-empty cpus/mems, instead of being
- *   moved to an ancestor.
- *
- * - cpuset: a task can be moved into an empty cpuset, and again it takes
- *   masks of ancestors.
- *
- * - memcg: use_hierarchy is on by default and the cgroup file for the flag
- *   is not created.
- *
- * - blkcg: blk-throttle becomes properly hierarchical.
- *
- * - debug: disallowed on the default hierarchy.
- */
-static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
-{
-        return cgrp->root == &cgrp_dfl_root;
-}
-
 /* no synchronization, the result can only be used as a hint */
-static inline bool cgroup_has_tasks(struct cgroup *cgrp)
+static inline bool cgroup_is_populated(struct cgroup *cgrp)
 {
-        return !list_empty(&cgrp->cset_links);
+        return cgrp->populated_cnt;
 }
 
 /* returns ino associated with a cgroup */
@@ -527,6 +516,19 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
         pr_cont_kernfs_path(cgrp->kn);
 }
 
+/**
+ * cgroup_file_notify - generate a file modified event for a cgroup_file
+ * @cfile: target cgroup_file
+ *
+ * @cfile must have been obtained by setting cftype->file_offset.
+ */
+static inline void cgroup_file_notify(struct cgroup_file *cfile)
+{
+        /* might not have been created due to one of the CFTYPE selector flags */
+        if (cfile->kn)
+                kernfs_notify(cfile->kn);
+}
+
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
@@ -546,6 +548,7 @@ static inline void cgroup_cancel_fork(struct task_struct *p,
 static inline void cgroup_post_fork(struct task_struct *p,
                                     void *ss_priv[CGROUP_CANFORK_COUNT]) {}
 static inline void cgroup_exit(struct task_struct *p) {}
+static inline void cgroup_free(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }