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, 20 insertions, 7 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c57c4423c688..b732edfddb76 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -434,7 +434,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 
         memcg = page->mem_cgroup;
 
-        if (!memcg || !cgroup_on_dfl(memcg->css.cgroup))
+        if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
                 memcg = root_mem_cgroup;
 
         rcu_read_unlock();
@@ -2926,7 +2926,7 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg,
          * of course permitted.
          */
         mutex_lock(&memcg_create_mutex);
-        if (cgroup_has_tasks(memcg->css.cgroup) ||
+        if (cgroup_is_populated(memcg->css.cgroup) ||
             (memcg->use_hierarchy && memcg_has_children(memcg)))
                 err = -EBUSY;
         mutex_unlock(&memcg_create_mutex);
@@ -4066,8 +4066,7 @@ static struct cftype mem_cgroup_legacy_files[] = {
         {
                 .name = "cgroup.event_control",         /* XXX: for compat */
                 .write = memcg_write_event_control,
-                .flags = CFTYPE_NO_PREFIX,
-                .mode = S_IWUGO,
+                .flags = CFTYPE_NO_PREFIX | CFTYPE_WORLD_WRITABLE,
         },
         {
                 .name = "swappiness",
@@ -4834,7 +4833,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 {
         struct mem_cgroup *memcg = mem_cgroup_from_css(css);
         struct mem_cgroup *from;
-        struct task_struct *p;
+        struct task_struct *leader, *p;
         struct mm_struct *mm;
         unsigned long move_flags;
         int ret = 0;
@@ -4848,7 +4847,20 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
         if (!move_flags)
                 return 0;
 
-        p = cgroup_taskset_first(tset);
+        /*
+         * Multi-process migrations only happen on the default hierarchy
+         * where charge immigration is not used.  Perform charge
+         * immigration if @tset contains a leader and whine if there are
+         * multiple.
+         */
+        p = NULL;
+        cgroup_taskset_for_each_leader(leader, tset) {
+                WARN_ON_ONCE(p);
+                p = leader;
+        }
+        if (!p)
+                return 0;
+
         from = mem_cgroup_from_task(p);
 
         VM_BUG_ON(from == memcg);
@@ -5064,7 +5076,7 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
          * guarantees that @root doesn't have any children, so turning it
          * on for the root memcg is enough.
          */
-        if (cgroup_on_dfl(root_css->cgroup))
+        if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
                 root_mem_cgroup->use_hierarchy = true;
         else
                 root_mem_cgroup->use_hierarchy = false;
@@ -5208,6 +5220,7 @@ static struct cftype memory_files[] = {
         {
                 .name = "events",
                 .flags = CFTYPE_NOT_ON_ROOT,
+                .file_offset = offsetof(struct mem_cgroup, events_file),
                 .seq_show = memory_events_show,
         },
         { }     /* terminate */