[PATCH] psi: Optimize task switch inside shared cgroups

[Chengming Zhou]

The commit 36b238d57172 ("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.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
---
 kernel/sched/psi.c   | 27 +++++++++++++++++----------
 kernel/sched/stats.h | 17 +++--------------
 2 files changed, 20 insertions(+), 24 deletions(-)

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 6e46d9eb279b..6061e87089ac 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -836,20 +836,27 @@ 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 = 0, set = 0;
+
+		if (sleep) {
+			clear |= TSK_RUNNING;
+			if (prev->in_iowait)
+				set |= TSK_IOWAIT;
+		}
+
+		psi_flags_change(prev, clear | TSK_ONCPU, 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 | TSK_ONCPU, set, true);
+
+		if (sleep) {
+			while (group) {
+				psi_group_change(group, cpu, clear, set, true);
+				group = iterate_groups(prev, &iter);
+			}
+		}
 	}
 }
 
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 9e4e67a94731..2d92c8467678 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -84,28 +84,17 @@ 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;
-
 	if (static_branch_likely(&psi_disabled))
 		return;
 
 	if (!sleep) {
+		int clear = TSK_RUNNING;
+
 		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;
 
-		if (p->in_iowait)
-			set |= TSK_IOWAIT;
+		psi_task_change(p, clear, 0);
 	}
-
-	psi_task_change(p, clear, set);
 }
 
 static inline void psi_ttwu_dequeue(struct task_struct *p)
-- 
2.11.0