psi: Optimize task switch inside shared cgroups

The commit 36b238d5 ("psi: Optimize switching tasks inside shared
cgroups") only update cgroups whose state actually changes during a
task switch only in task preempt case, not in task sleep case.

We actually don't need to clear and set TSK_ONCPU state for common cgroups
of next and prev task in sleep case, that can save many psi_group_change
especially when most activity comes from one leaf cgroup.

sleep before:
psi_dequeue()
  while ((group = iterate_groups(prev)))  # all ancestors
    psi_group_change(prev, .clear=TSK_RUNNING|TSK_ONCPU)
psi_task_switch()
  while ((group = iterate_groups(next)))  # all ancestors
    psi_group_change(next, .set=TSK_ONCPU)

sleep after:
psi_dequeue()
  nop
psi_task_switch()
  while ((group = iterate_groups(next)))  # until (prev & next)
    psi_group_change(next, .set=TSK_ONCPU)
  while ((group = iterate_groups(prev)))  # all ancestors
    psi_group_change(prev, .clear=common?TSK_RUNNING:TSK_RUNNING|TSK_ONCPU)

When a voluntary sleep switches to another task, we remove one call of
psi_group_change() for every common cgroup ancestor of the two tasks.
Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-5-zhouchengming@bytedance.com

kernel/sched/psi.c

@@ -840,20 +840,35 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		}
 	}
 
-	/*
-	 * If this is a voluntary sleep, dequeue will have taken care
-	 * of the outgoing TSK_ONCPU alongside TSK_RUNNING already. We
-	 * only need to deal with it during preemption.
-	 */
-	if (sleep)
-		return;
-
 	if (prev->pid) {
-		psi_flags_change(prev, TSK_ONCPU, 0);
+		int clear = TSK_ONCPU, set = 0;
+
+		/*
+		 * When we're going to sleep, psi_dequeue() lets us handle
+		 * TSK_RUNNING and TSK_IOWAIT here, where we can combine it
+		 * with TSK_ONCPU and save walking common ancestors twice.
+		 */
+		if (sleep) {
+			clear |= TSK_RUNNING;
+			if (prev->in_iowait)
+				set |= TSK_IOWAIT;
+		}
+
+		psi_flags_change(prev, clear, set);
 
 		iter = NULL;
 		while ((group = iterate_groups(prev, &iter)) && group != common)
-			psi_group_change(group, cpu, TSK_ONCPU, 0, true);
+			psi_group_change(group, cpu, clear, set, true);
+
+		/*
+		 * TSK_ONCPU is handled up to the common ancestor. If we're tasked
+		 * with dequeuing too, finish that for the rest of the hierarchy.
+		 */
+		if (sleep) {
+			clear &= ~TSK_ONCPU;
+			for (; group; group = iterate_groups(prev, &iter))
+				psi_group_change(group, cpu, clear, set, true);
+		}
 	}
 }
 

kernel/sched/stats.h

@@ -84,28 +84,24 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
 
 static inline void psi_dequeue(struct task_struct *p, bool sleep)
 {
-	int clear = TSK_RUNNING, set = 0;
+	int clear = TSK_RUNNING;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	if (!sleep) {
-		if (p->in_memstall)
-			clear |= TSK_MEMSTALL;
-	} else {
-		/*
-		 * When a task sleeps, schedule() dequeues it before
-		 * switching to the next one. Merge the clearing of
-		 * TSK_RUNNING and TSK_ONCPU to save an unnecessary
-		 * psi_task_change() call in psi_sched_switch().
-		 */
-		clear |= TSK_ONCPU;
+	/*
+	 * A voluntary sleep is a dequeue followed by a task switch. To
+	 * avoid walking all ancestors twice, psi_task_switch() handles
+	 * TSK_RUNNING and TSK_IOWAIT for us when it moves TSK_ONCPU.
+	 * Do nothing here.
+	 */
+	if (sleep)
+		return;
 
-		if (p->in_iowait)
-			set |= TSK_IOWAIT;
-	}
+	if (p->in_memstall)
+		clear |= TSK_MEMSTALL;
 
-	psi_task_change(p, clear, set);
+	psi_task_change(p, clear, 0);
 }
 
 static inline void psi_ttwu_dequeue(struct task_struct *p)