Merge branch 'for-5.2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:
 "This has an unusually high density of tricky fixes:

   - task_get_css() could deadlock when it races against a dying cgroup.

   - cgroup.procs didn't list thread group leaders with live threads.

     This could mislead readers to think that a cgroup is empty when
     it's not. Fixed by making PROCS iterator include dead tasks. I made
     a couple mistakes making this change and this pull request contains
     a couple follow-up patches.

   - When cpusets run out of online cpus, it updates cpusmasks of member
     tasks in bizarre ways. Joel improved the behavior significantly"

* 'for-5.2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cpuset: restore sanity to cpuset_cpus_allowed_fallback()
  cgroup: Fix css_task_iter_advance_css_set() cset skip condition
  cgroup: css_task_iter_skip()'d iterators must be advanced before accessed
  cgroup: Include dying leaders with live threads in PROCS iterations
  cgroup: Implement css_task_iter_skip()
  cgroup: Call cgroup_release() before __exit_signal()
  docs cgroups: add another example size for hugetlb
  cgroup: Use css_tryget() instead of css_tryget_online() in task_get_css()

6 files changed, 117 insertions, 43 deletions

diff --git a/Documentation/cgroup-v1/hugetlb.txt b/Documentation/cgroup-v1/hugetlb.txt
index 106245c3aecc..1260e5369b9b 100644
--- a/Documentation/cgroup-v1/hugetlb.txt
+++ b/Documentation/cgroup-v1/hugetlb.txt
@@ -32,14 +32,18 @@ Brief summary of control files
  hugetlb.<hugepagesize>.usage_in_bytes     # show current usage for "hugepagesize" hugetlb
  hugetlb.<hugepagesize>.failcnt		   # show the number of allocation failure due to HugeTLB limit
 
-For a system supporting two hugepage size (16M and 16G) the control
+For a system supporting three hugepage sizes (64k, 32M and 1G), the control
 files include:
 
-hugetlb.16GB.limit_in_bytes
-hugetlb.16GB.max_usage_in_bytes
-hugetlb.16GB.usage_in_bytes
-hugetlb.16GB.failcnt
-hugetlb.16MB.limit_in_bytes
-hugetlb.16MB.max_usage_in_bytes
-hugetlb.16MB.usage_in_bytes
-hugetlb.16MB.failcnt
+hugetlb.1GB.limit_in_bytes
+hugetlb.1GB.max_usage_in_bytes
+hugetlb.1GB.usage_in_bytes
+hugetlb.1GB.failcnt
+hugetlb.64KB.limit_in_bytes
+hugetlb.64KB.max_usage_in_bytes
+hugetlb.64KB.usage_in_bytes
+hugetlb.64KB.failcnt
+hugetlb.32MB.limit_in_bytes
+hugetlb.32MB.max_usage_in_bytes
+hugetlb.32MB.usage_in_bytes
+hugetlb.32MB.failcnt
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 11e215d7937e..b4e766e93f6e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -221,6 +221,7 @@ struct css_set {
 	 */
 	struct list_head tasks;
 	struct list_head mg_tasks;
+	struct list_head dying_tasks;
 
 	/* all css_task_iters currently walking this cset */
 	struct list_head task_iters;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c0077adeea83..0297f930a56e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -43,6 +43,9 @@
 /* walk all threaded css_sets in the domain */
 #define CSS_TASK_ITER_THREADED		(1U << 1)
 
+/* internal flags */
+#define CSS_TASK_ITER_SKIPPED		(1U << 16)
+
 /* a css_task_iter should be treated as an opaque object */
 struct css_task_iter {
 	struct cgroup_subsys		*ss;
@@ -57,6 +60,7 @@ struct css_task_iter {
 	struct list_head		*task_pos;
 	struct list_head		*tasks_head;
 	struct list_head		*mg_tasks_head;
+	struct list_head		*dying_tasks_head;
 
 	struct css_set			*cur_cset;
 	struct css_set			*cur_dcset;
@@ -487,7 +491,7 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
  *
  * Find the css for the (@task, @subsys_id) combination, increment a
  * reference on and return it.  This function is guaranteed to return a
- * valid css.
+ * valid css.  The returned css may already have been offlined.
  */
 static inline struct cgroup_subsys_state *
 task_get_css(struct task_struct *task, int subsys_id)
@@ -497,7 +501,13 @@ task_get_css(struct task_struct *task, int subsys_id)
 	rcu_read_lock();
 	while (true) {
 		css = task_css(task, subsys_id);
-		if (likely(css_tryget_online(css)))
+		/*
+		 * Can't use css_tryget_online() here.  A task which has
+		 * PF_EXITING set may stay associated with an offline css.
+		 * If such task calls this function, css_tryget_online()
+		 * will keep failing.
+		 */
+		if (likely(css_tryget(css)))
 			break;
 		cpu_relax();
 	}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 426a0026225c..bf9dbffd46b1 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -215,7 +215,8 @@ static struct cftype cgroup_base_files[];
 
 static int cgroup_apply_control(struct cgroup *cgrp);
 static void cgroup_finalize_control(struct cgroup *cgrp, int ret);
-static void css_task_iter_advance(struct css_task_iter *it);
+static void css_task_iter_skip(struct css_task_iter *it,
+			       struct task_struct *task);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 					      struct cgroup_subsys *ss);
@@ -738,6 +739,7 @@ struct css_set init_css_set = {
 	.dom_cset		= &init_css_set,
 	.tasks			= LIST_HEAD_INIT(init_css_set.tasks),
 	.mg_tasks		= LIST_HEAD_INIT(init_css_set.mg_tasks),
+	.dying_tasks		= LIST_HEAD_INIT(init_css_set.dying_tasks),
 	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 	.threaded_csets		= LIST_HEAD_INIT(init_css_set.threaded_csets),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
@@ -843,6 +845,21 @@ static void css_set_update_populated(struct css_set *cset, bool populated)
 		cgroup_update_populated(link->cgrp, populated);
 }
 
+/*
+ * @task is leaving, advance task iterators which are pointing to it so
+ * that they can resume at the next position.  Advancing an iterator might
+ * remove it from the list, use safe walk.  See css_task_iter_skip() for
+ * details.
+ */
+static void css_set_skip_task_iters(struct css_set *cset,
+				    struct task_struct *task)
+{
+	struct css_task_iter *it, *pos;
+
+	list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node)
+		css_task_iter_skip(it, task);
+}
+
 /**
  * css_set_move_task - move a task from one css_set to another
  * @task: task being moved
@@ -868,22 +885,9 @@ static void css_set_move_task(struct task_struct *task,
 		css_set_update_populated(to_cset, true);
 
 	if (from_cset) {
-		struct css_task_iter *it, *pos;
-
 		WARN_ON_ONCE(list_empty(&task->cg_list));
 
-		/*
-		 * @task is leaving, advance task iterators which are
-		 * pointing to it so that they can resume at the next
-		 * position.  Advancing an iterator might remove it from
-		 * the list, use safe walk.  See css_task_iter_advance*()
-		 * for details.
-		 */
-		list_for_each_entry_safe(it, pos, &from_cset->task_iters,
-					 iters_node)
-			if (it->task_pos == &task->cg_list)
-				css_task_iter_advance(it);
-
+		css_set_skip_task_iters(from_cset, task);
 		list_del_init(&task->cg_list);
 		if (!css_set_populated(from_cset))
 			css_set_update_populated(from_cset, false);
@@ -1210,6 +1214,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	cset->dom_cset = cset;
 	INIT_LIST_HEAD(&cset->tasks);
 	INIT_LIST_HEAD(&cset->mg_tasks);
+	INIT_LIST_HEAD(&cset->dying_tasks);
 	INIT_LIST_HEAD(&cset->task_iters);
 	INIT_LIST_HEAD(&cset->threaded_csets);
 	INIT_HLIST_NODE(&cset->hlist);
@@ -4408,15 +4413,18 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 			it->task_pos = NULL;
 			return;
 		}
-	} while (!css_set_populated(cset));
+	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
 
 	if (!list_empty(&cset->tasks))
 		it->task_pos = cset->tasks.next;
-	else
+	else if (!list_empty(&cset->mg_tasks))
 		it->task_pos = cset->mg_tasks.next;
+	else
+		it->task_pos = cset->dying_tasks.next;
 
 	it->tasks_head = &cset->tasks;
 	it->mg_tasks_head = &cset->mg_tasks;
+	it->dying_tasks_head = &cset->dying_tasks;
 
 	/*
 	 * We don't keep css_sets locked across iteration steps and thus
@@ -4442,9 +4450,20 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 	list_add(&it->iters_node, &cset->task_iters);
 }
 
+static void css_task_iter_skip(struct css_task_iter *it,
+			       struct task_struct *task)
+{
+	lockdep_assert_held(&css_set_lock);
+
+	if (it->task_pos == &task->cg_list) {
+		it->task_pos = it->task_pos->next;
+		it->flags |= CSS_TASK_ITER_SKIPPED;
+	}
+}
+
 static void css_task_iter_advance(struct css_task_iter *it)
 {
-	struct list_head *next;
+	struct task_struct *task;
 
 	lockdep_assert_held(&css_set_lock);
 repeat:
@@ -4454,25 +4473,40 @@ repeat:
 		 * consumed first and then ->mg_tasks.  After ->mg_tasks,
 		 * we move onto the next cset.
 		 */
-		next = it->task_pos->next;
-
-		if (next == it->tasks_head)
-			next = it->mg_tasks_head->next;
+		if (it->flags & CSS_TASK_ITER_SKIPPED)
+			it->flags &= ~CSS_TASK_ITER_SKIPPED;
+		else
+			it->task_pos = it->task_pos->next;
 
-		if (next == it->mg_tasks_head)
+		if (it->task_pos == it->tasks_head)
+			it->task_pos = it->mg_tasks_head->next;
+		if (it->task_pos == it->mg_tasks_head)
+			it->task_pos = it->dying_tasks_head->next;
+		if (it->task_pos == it->dying_tasks_head)
 			css_task_iter_advance_css_set(it);
-		else
-			it->task_pos = next;
 	} else {
 		/* called from start, proceed to the first cset */
 		css_task_iter_advance_css_set(it);
 	}
 
-	/* if PROCS, skip over tasks which aren't group leaders */
-	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
-	    !thread_group_leader(list_entry(it->task_pos, struct task_struct,
-					    cg_list)))
-		goto repeat;
+	if (!it->task_pos)
+		return;
+
+	task = list_entry(it->task_pos, struct task_struct, cg_list);
+
+	if (it->flags & CSS_TASK_ITER_PROCS) {
+		/* if PROCS, skip over tasks which aren't group leaders */
+		if (!thread_group_leader(task))
+			goto repeat;
+
+		/* and dying leaders w/o live member threads */
+		if (!atomic_read(&task->signal->live))
+			goto repeat;
+	} else {
+		/* skip all dying ones */
+		if (task->flags & PF_EXITING)
+			goto repeat;
+	}
 }
 
 /**
@@ -4528,6 +4562,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 
 	spin_lock_irq(&css_set_lock);
 
+	/* @it may be half-advanced by skips, finish advancing */
+	if (it->flags & CSS_TASK_ITER_SKIPPED)
+		css_task_iter_advance(it);
+
 	if (it->task_pos) {
 		it->cur_task = list_entry(it->task_pos, struct task_struct,
 					  cg_list);
@@ -6009,6 +6047,7 @@ void cgroup_exit(struct task_struct *tsk)
 	if (!list_empty(&tsk->cg_list)) {
 		spin_lock_irq(&css_set_lock);
 		css_set_move_task(tsk, cset, NULL, false);
+		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 		cset->nr_tasks--;
 
 		WARN_ON_ONCE(cgroup_task_frozen(tsk));
@@ -6034,6 +6073,13 @@ void cgroup_release(struct task_struct *task)
 	do_each_subsys_mask(ss, ssid, have_release_callback) {
 		ss->release(task);
 	} while_each_subsys_mask();
+
+	if (use_task_css_set_links) {
+		spin_lock_irq(&css_set_lock);
+		css_set_skip_task_iters(task_css_set(task), task);
+		list_del_init(&task->cg_list);
+		spin_unlock_irq(&css_set_lock);
+	}
 }
 
 void cgroup_free(struct task_struct *task)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 6a1942ed781c..515525ff1cfd 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3254,10 +3254,23 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 
+/**
+ * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe.
+ * @tsk: pointer to task_struct with which the scheduler is struggling
+ *
+ * Description: In the case that the scheduler cannot find an allowed cpu in
+ * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy
+ * mode however, this value is the same as task_cs(tsk)->effective_cpus,
+ * which will not contain a sane cpumask during cases such as cpu hotplugging.
+ * This is the absolute last resort for the scheduler and it is only used if
+ * _every_ other avenue has been traveled.
+ **/
+
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
 	rcu_read_lock();
-	do_set_cpus_allowed(tsk, task_cs(tsk)->effective_cpus);
+	do_set_cpus_allowed(tsk, is_in_v2_mode() ?
+		task_cs(tsk)->cpus_allowed : cpu_possible_mask);
 	rcu_read_unlock();
 
 	/*
diff --git a/kernel/exit.c b/kernel/exit.c
index 1803efb2922f..a75b6a7f458a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -195,6 +195,7 @@ repeat:
 	rcu_read_unlock();
 
 	proc_flush_task(p);
+	cgroup_release(p);
 
 	write_lock_irq(&tasklist_lock);
 	ptrace_release_task(p);
@@ -220,7 +221,6 @@ repeat:
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	cgroup_release(p);
 	release_thread(p);
 	call_rcu(&p->rcu, delayed_put_task_struct);