diff --git a/include/linux/psi.h b/include/linux/psi.h
index 1b9c0e5955bc0616d5ea5ad9ce7115f3af7d2998..d290f0493c3335cddcc9153d4cdf36499866c0b4 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -22,7 +22,6 @@ void psi_task_change(struct task_struct *task, int clear, int set);
 void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		     bool sleep);
 
-void psi_memstall_tick(struct task_struct *task, int cpu);
 void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 56be8d1c7f69435de1eabaa6cd3e80a9f6b480a5..0fd88dc7660f8cb1afb5b221e028544783405ae6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4048,7 +4048,6 @@ void scheduler_tick(void)
 	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
 	curr->sched_class->task_tick(rq, curr, 0);
 	calc_global_load_tick(rq);
-	psi_task_tick(rq);
 
 	rq_unlock(rq, &rf);
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 2cc518b136ad2b9212ef29b44fe0d2bf3f3551e9..f27518bdc6c9d14af17a1aad03863407e0fe9e7b 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -651,8 +651,7 @@ static void poll_timer_fn(struct timer_list *t)
 	wake_up_interruptible(&group->poll_wait);
 }
 
-static void record_times(struct psi_group_cpu *groupc, int cpu,
-			 bool memstall_tick)
+static void record_times(struct psi_group_cpu *groupc, int cpu)
 {
 	u32 delta;
 	u64 now;
@@ -671,23 +670,6 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
 		groupc->times[PSI_MEM_SOME] += delta;
 		if (groupc->state_mask & (1 << PSI_MEM_FULL))
 			groupc->times[PSI_MEM_FULL] += delta;
-		else if (memstall_tick) {
-			u32 sample;
-			/*
-			 * Since we care about lost potential, a
-			 * memstall is FULL when there are no other
-			 * working tasks, but also when the CPU is
-			 * actively reclaiming and nothing productive
-			 * could run even if it were runnable.
-			 *
-			 * When the timer tick sees a reclaiming CPU,
-			 * regardless of runnable tasks, sample a FULL
-			 * tick (or less if it hasn't been a full tick
-			 * since the last state change).
-			 */
-			sample = min(delta, (u32)jiffies_to_nsecs(1));
-			groupc->times[PSI_MEM_FULL] += sample;
-		}
 	}
 
 	if (groupc->state_mask & (1 << PSI_CPU_SOME)) {
@@ -721,7 +703,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
 	 */
 	write_seqcount_begin(&groupc->seq);
 
-	record_times(groupc, cpu, false);
+	record_times(groupc, cpu);
 
 	for (t = 0, m = clear; m; m &= ~(1 << t), t++) {
 		if (!(m & (1 << t)))
@@ -746,6 +728,18 @@ static void psi_group_change(struct psi_group *group, int cpu,
 		if (test_state(groupc->tasks, s))
 			state_mask |= (1 << s);
 	}
+
+	/*
+	 * Since we care about lost potential, a memstall is FULL
+	 * when there are no other working tasks, but also when
+	 * the CPU is actively reclaiming and nothing productive
+	 * could run even if it were runnable. So when the current
+	 * task in a cgroup is in_memstall, the corresponding groupc
+	 * on that cpu is in PSI_MEM_FULL state.
+	 */
+	if (groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall)
+		state_mask |= (1 << PSI_MEM_FULL);
+
 	groupc->state_mask = state_mask;
 
 	write_seqcount_end(&groupc->seq);
@@ -845,17 +839,21 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 	void *iter;
 
 	if (next->pid) {
+		bool identical_state;
+
 		psi_flags_change(next, 0, TSK_ONCPU);
 		/*
-		 * When moving state between tasks, the group that
-		 * contains them both does not change: we can stop
-		 * updating the tree once we reach the first common
-		 * ancestor. Iterate @next's ancestors until we
-		 * encounter @prev's state.
+		 * When switching between tasks that have an identical
+		 * runtime state, the cgroup that contains both tasks
+		 * runtime state, the cgroup that contains both tasks
+		 * we reach the first common ancestor. Iterate @next's
+		 * ancestors only until we encounter @prev's ONCPU.
 		 */
+		identical_state = prev->psi_flags == next->psi_flags;
 		iter = NULL;
 		while ((group = iterate_groups(next, &iter))) {
-			if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
+			if (identical_state &&
+			    per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) {
 				common = group;
 				break;
 			}
@@ -881,21 +879,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 	}
 }
 
-void psi_memstall_tick(struct task_struct *task, int cpu)
-{
-	struct psi_group *group;
-	void *iter = NULL;
-
-	while ((group = iterate_groups(task, &iter))) {
-		struct psi_group_cpu *groupc;
-
-		groupc = per_cpu_ptr(group->pcpu, cpu);
-		write_seqcount_begin(&groupc->seq);
-		record_times(groupc, cpu, true);
-		write_seqcount_end(&groupc->seq);
-	}
-}
-
 /**
  * psi_memstall_enter - mark the beginning of a memory stall section
  * @flags: flags to handle nested sections
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 06cf8202c178a059055abf0f782ca342ae83c05b..c676af28347b683d9a4b7ef5b393475559f756bd 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -164,14 +164,6 @@ static inline void psi_sched_switch(struct task_struct *prev,
 	psi_task_switch(prev, next, sleep);
 }
 
-static inline void psi_task_tick(struct rq *rq)
-{
-	if (static_branch_likely(&psi_disabled))
-		return;
-
-	if (unlikely(rq->curr->in_memstall))
-		psi_memstall_tick(rq->curr, cpu_of(rq));
-}
 #else /* CONFIG_PSI */
 static inline void psi_enqueue(struct task_struct *p, bool wakeup) {}
 static inline void psi_dequeue(struct task_struct *p, bool sleep) {}
@@ -179,7 +171,6 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {}
 static inline void psi_sched_switch(struct task_struct *prev,
 				    struct task_struct *next,
 				    bool sleep) {}
-static inline void psi_task_tick(struct rq *rq) {}
 #endif /* CONFIG_PSI */
 
 #ifdef CONFIG_SCHED_INFO