Merge tag 'sched-urgent-2021-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Thomas Gleixner:
 "A set of scheduler updates:

   - Prevent PSI state corruption when schedule() races with cgroup
     move.

     A recent commit combined two PSI callbacks to reduce the number of
     cgroup tree updates, but missed that schedule() can drop rq::lock
     for load balancing, which opens the race window for
     cgroup_move_task() which then observes half updated state.

     The fix is to solely use task::ps_flags instead of looking at the
     potentially mismatching scheduler state

   - Prevent an out-of-bounds access in uclamp caused bu a rounding
     division which can lead to an off-by-one error exceeding the
     buckets array size.

   - Prevent unfairness caused by missing load decay when a task is
     attached to a cfs runqueue.

     The old load of the task was attached to the runqueue and never
     removed. Fix it by enforcing the load update through the hierarchy
     for unthrottled run queue instances.

   - A documentation fix fot the 'sched_verbose' command line option"

* tag 'sched-urgent-2021-05-09' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix unfairness caused by missing load decay
  sched: Fix out-of-bound access in uclamp
  psi: Fix psi state corruption when schedule() races with cgroup move
  sched,doc: sched_debug_verbose cmdline should be sched_verbose

3 files changed, 36 insertions, 14 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9143163fa678..5226cc26a095 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -938,7 +938,7 @@ DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
 
 static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
 {
-	return clamp_value / UCLAMP_BUCKET_DELTA;
+	return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1);
 }
 
 static inline unsigned int uclamp_none(enum uclamp_id clamp_id)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1d75af1ecfb4..20aa234ffe04 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10878,16 +10878,22 @@ static void propagate_entity_cfs_rq(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq;
 
+	list_add_leaf_cfs_rq(cfs_rq_of(se));
+
 	/* Start to propagate at parent */
 	se = se->parent;
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 
-		if (cfs_rq_throttled(cfs_rq))
-			break;
+		if (!cfs_rq_throttled(cfs_rq)){
+			update_load_avg(cfs_rq, se, UPDATE_TG);
+			list_add_leaf_cfs_rq(cfs_rq);
+			continue;
+		}
 
-		update_load_avg(cfs_rq, se, UPDATE_TG);
+		if (list_add_leaf_cfs_rq(cfs_rq))
+			break;
 	}
 }
 #else
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index db27b69fa92a..cc25a3cff41f 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -972,7 +972,7 @@ void psi_cgroup_free(struct cgroup *cgroup)
  */
 void cgroup_move_task(struct task_struct *task, struct css_set *to)
 {
-	unsigned int task_flags = 0;
+	unsigned int task_flags;
 	struct rq_flags rf;
 	struct rq *rq;
 
@@ -987,15 +987,31 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to)
 
 	rq = task_rq_lock(task, &rf);
 
-	if (task_on_rq_queued(task)) {
-		task_flags = TSK_RUNNING;
-		if (task_current(rq, task))
-			task_flags |= TSK_ONCPU;
-	} else if (task->in_iowait)
-		task_flags = TSK_IOWAIT;
-
-	if (task->in_memstall)
-		task_flags |= TSK_MEMSTALL;
+	/*
+	 * We may race with schedule() dropping the rq lock between
+	 * deactivating prev and switching to next. Because the psi
+	 * updates from the deactivation are deferred to the switch
+	 * callback to save cgroup tree updates, the task's scheduling
+	 * state here is not coherent with its psi state:
+	 *
+	 * schedule()                   cgroup_move_task()
+	 *   rq_lock()
+	 *   deactivate_task()
+	 *     p->on_rq = 0
+	 *     psi_dequeue() // defers TSK_RUNNING & TSK_IOWAIT updates
+	 *   pick_next_task()
+	 *     rq_unlock()
+	 *                                rq_lock()
+	 *                                psi_task_change() // old cgroup
+	 *                                task->cgroups = to
+	 *                                psi_task_change() // new cgroup
+	 *                                rq_unlock()
+	 *     rq_lock()
+	 *   psi_sched_switch() // does deferred updates in new cgroup
+	 *
+	 * Don't rely on the scheduling state. Use psi_flags instead.
+	 */
+	task_flags = task->psi_flags;
 
 	if (task_flags)
 		psi_task_change(task, task_flags, 0);