Merge tag 'cgroup-for-7.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Last cycle deferred css teardown on cgroup removal until the cgroup
   depopulated, so a css is not taken offline while tasks can still
   reference it. Disabling a controller through cgroup.subtree_control
   still had the same problem. This reworks the deferral from per-cgroup
   to per-css so that path is covered too.

 - New RDMA controller monitoring files: rdma.peak for per-device peak
   usage and rdma.events / rdma.events.local for resource-limit
   exhaustion. The max-limit parser was rewritten, fixing two input
   parsing bugs.

 - cpuset: fix a sched-domain leak on the domain-rebuild failure path
   and skip a redundant hardwall ancestor scan on v2.

 - Misc: pair the remaining lockless cgroup.max.* reads with WRITE_ONCE,
   assorted selftest robustness fixes, and doc path corrections.

* tag 'cgroup-for-7.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (22 commits)
  cgroup: Migrate tasks to the root css when a controller is rebound
  docs: cgroup: Fix stale source file paths
  cgroup/cpuset: Free sched domains on rebuild guard failure
  cgroup: pair max limit READ_ONCE() with WRITE_ONCE()
  selftests/cgroup: enable memory controller in hugetlb memcg test
  cgroup/rdma: Drop unnecessary READ_ONCE() on event counters
  cgroup: Defer kill_css_finish() in cgroup_apply_control_disable()
  cgroup: Add per-subsys-css kill_css_finish deferral
  cgroup: Move populated counters to cgroup_subsys_state
  cgroup: Annotate unlocked nr_populated_* accesses with READ_ONCE/WRITE_ONCE
  cgroup: Inline cgroup_has_tasks() in cgroup.h
  cgroup/rdma: document rdma.peak, rdma.events and rdma.events.local
  cgroup/rdma: add rdma.events.local for per-cgroup allocation failure attribution
  cgroup/rdma: add rdma.events to track resource limit exhaustion
  cgroup/rdma: add rdma.peak for per-device peak usage tracking
  selftests/cgroup: check malloc return value in alloc_anon functions
  cgroup/cpuset: Skip hardwall ancestor scan in cpuset v2 in cpuset_current_node_allowed()
  selftests/cgroup: fix misleading debug message in test_cgfreezer_time_child
  selftests/cgroup: fix child process escaping to parent cleanup in test_cpucg_nice
  selftests/cgroup: Add NULL check after malloc in cgroup_util.c
  ...

3 files changed, 45 insertions, 16 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 50a784da7a81..de2cd6238c2a 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -254,6 +254,18 @@ struct cgroup_subsys_state {
 	int nr_descendants;
 
 	/*
+	 * Hierarchical populated state. For cgroup->self, nr_populated_csets
+	 * counts populated csets linked via cgrp_cset_link.
+	 * nr_populated_children counts immediate-child csses whose own
+	 * populated state is nonzero. Protected by css_set_lock.
+	 */
+	int nr_populated_csets;
+	int nr_populated_children;
+
+	/* deferred kill_css_finish() queued by css_update_populated() */
+	struct work_struct kill_finish_work;
+
+	/*
 	 * A singly-linked list of css structures to be rstat flushed.
 	 * This is a scratch field to be used exclusively by
 	 * css_rstat_flush().
@@ -504,17 +516,12 @@ struct cgroup {
 	int max_descendants;
 
 	/*
-	 * Each non-empty css_set associated with this cgroup contributes
-	 * 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.
+	 * Domain/threaded split of self.nr_populated_children: each counts
+	 * immediate-child cgroups whose subtree is populated and sums to
+	 * self.nr_populated_children. Kept as separate fields to allow readers
+	 * like cgroup_can_be_thread_root() unlocked access. Protected by
+	 * css_set_lock; updated by css_update_populated().
 	 */
-	int nr_populated_csets;
 	int nr_populated_domain_children;
 	int nr_populated_threaded_children;
 
@@ -611,9 +618,6 @@ struct cgroup {
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
 
-	/* defers killing csses after removal until cgroup is depopulated */
-	struct work_struct finish_destroy_work;
-
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c5648fcf74e2..f2aa46a4f871 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -640,11 +640,32 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 	return cgroup_is_descendant(cset->dfl_cgrp, ancestor);
 }
 
-/* no synchronization, the result can only be used as a hint */
+/*
+ * Populated counters: writes happen under css_set_lock. The accessors below
+ * may read unlocked. What an unpopulated result means depends on context:
+ *
+ * - No lock held. Just a snapshot. May race with concurrent updates and is
+ *   useful only as a hint.
+ *
+ * - cgroup_mutex held. Migration into the cgroup is blocked, so an observed
+ *   !populated stays !populated until cgroup_mutex is dropped.
+ *
+ * - CSS_DYING set. The css can no longer be repopulated, so !populated is
+ *   sticky once observed.
+ */
+static inline bool cgroup_has_tasks(struct cgroup *cgrp)
+{
+	return READ_ONCE(cgrp->self.nr_populated_csets);
+}
+
+static inline bool css_is_populated(struct cgroup_subsys_state *css)
+{
+	return READ_ONCE(css->nr_populated_csets) || READ_ONCE(css->nr_populated_children);
+}
+
 static inline bool cgroup_is_populated(struct cgroup *cgrp)
 {
-	return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children +
-		cgrp->nr_populated_threaded_children;
+	return css_is_populated(&cgrp->self);
 }
 
 /* returns ino associated with a cgroup */
diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h
index 80edae03c313..404e746552ca 100644
--- a/include/linux/cgroup_rdma.h
+++ b/include/linux/cgroup_rdma.h
@@ -24,6 +24,10 @@ struct rdma_cgroup {
 	 * that belongs to this cgroup.
 	 */
 	struct list_head		rpools;
+
+	/* Handles for rdma.events[.local] */
+	struct cgroup_file		events_file;
+	struct cgroup_file		events_local_file;
 };
 
 struct rdmacg_device {