Merge tag 'sched_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Borislav Petkov:
 "Mostly minor things this time; some highlights:

   - core-sched: Add 'Forced Idle' accounting; this allows to track how
     much CPU time is 'lost' due to core scheduling constraints.

   - psi: Fix for MEM_FULL; a task running reclaim would be counted as a
     runnable task and prevent MEM_FULL from being reported.

   - cpuacct: Long standing fixes for some cgroup accounting issues.

   - rt: Bandwidth timer could, under unusual circumstances, be failed
     to armed, leading to indefinite throttling."

[ Description above by Peter Zijlstra ]

* tag 'sched_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Replace CFS internal cpu_util() with cpu_util_cfs()
  sched/fair: Cleanup task_util and capacity type
  sched/rt: Try to restart rt period timer when rt runtime exceeded
  sched/fair: Document the slow path and fast path in select_task_rq_fair
  sched/fair: Fix per-CPU kthread and wakee stacking for asym CPU capacity
  sched/fair: Fix detection of per-CPU kthreads waking a task
  sched/cpuacct: Make user/system times in cpuacct.stat more precise
  sched/cpuacct: Fix user/system in shown cpuacct.usage*
  cpuacct: Convert BUG_ON() to WARN_ON_ONCE()
  cputime, cpuacct: Include guest time in user time in cpuacct.stat
  psi: Fix PSI_MEM_FULL state when tasks are in memstall and doing reclaim
  sched/core: Forced idle accounting
  psi: Add a missing SPDX license header
  psi: Remove repeated verbose comment

Author: torvalds

include/linux/psi.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_PSI_H
 #define _LINUX_PSI_H
 

include/linux/psi_types.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_PSI_TYPES_H
 #define _LINUX_PSI_TYPES_H
 
@@ -21,14 +22,25 @@ enum psi_task_count {
 	 * don't have to special case any state tracking for it.
 	 */
 	NR_ONCPU,
-	NR_PSI_TASK_COUNTS = 4,
+	/*
+	 * For IO and CPU stalls the presence of running/oncpu tasks
+	 * in the domain means a partial rather than a full stall.
+	 * For memory it's not so simple because of page reclaimers:
+	 * they are running/oncpu while representing a stall. To tell
+	 * whether a domain has productivity left or not, we need to
+	 * distinguish between regular running (i.e. productive)
+	 * threads and memstall ones.
+	 */
+	NR_MEMSTALL_RUNNING,
+	NR_PSI_TASK_COUNTS = 5,
 };
 
 /* Task state bitmasks */
 #define TSK_IOWAIT	(1 << NR_IOWAIT)
 #define TSK_MEMSTALL	(1 << NR_MEMSTALL)
 #define TSK_RUNNING	(1 << NR_RUNNING)
 #define TSK_ONCPU	(1 << NR_ONCPU)
+#define TSK_MEMSTALL_RUNNING	(1 << NR_MEMSTALL_RUNNING)
 
 /* Resources that workloads could be stalled on */
 enum psi_res {

include/linux/sched.h

@@ -523,7 +523,11 @@ struct sched_statistics {
 	u64				nr_wakeups_affine_attempts;
 	u64				nr_wakeups_passive;
 	u64				nr_wakeups_idle;
+
+#ifdef CONFIG_SCHED_CORE
+	u64				core_forceidle_sum;
 #endif
+#endif /* CONFIG_SCHEDSTATS */
 } ____cacheline_aligned;
 
 struct sched_entity {

kernel/sched/core.c

@@ -144,7 +144,7 @@ static inline bool __sched_core_less(struct task_struct *a, struct task_struct *
 		return false;
 
 	/* flip prio, so high prio is leftmost */
-	if (prio_less(b, a, task_rq(a)->core->core_forceidle))
+	if (prio_less(b, a, !!task_rq(a)->core->core_forceidle_count))
 		return true;
 
 	return false;
@@ -181,15 +181,23 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p)
 	rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less);
 }
 
-void sched_core_dequeue(struct rq *rq, struct task_struct *p)
+void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
 {
 	rq->core->core_task_seq++;
 
-	if (!sched_core_enqueued(p))
-		return;
+	if (sched_core_enqueued(p)) {
+		rb_erase(&p->core_node, &rq->core_tree);
+		RB_CLEAR_NODE(&p->core_node);
+	}
 
-	rb_erase(&p->core_node, &rq->core_tree);
-	RB_CLEAR_NODE(&p->core_node);
+	/*
+	 * Migrating the last task off the cpu, with the cpu in forced idle
+	 * state. Reschedule to create an accounting edge for forced idle,
+	 * and re-examine whether the core is still in forced idle state.
+	 */
+	if (!(flags & DEQUEUE_SAVE) && rq->nr_running == 1 &&
+	    rq->core->core_forceidle_count && rq->curr == rq->idle)
+		resched_curr(rq);
 }
 
 /*
@@ -280,6 +288,8 @@ static void __sched_core_flip(bool enabled)
 		for_each_cpu(t, smt_mask)
 			cpu_rq(t)->core_enabled = enabled;
 
+		cpu_rq(cpu)->core->core_forceidle_start = 0;
+
 		sched_core_unlock(cpu, &flags);
 
 		cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask);
@@ -364,7 +374,8 @@ void sched_core_put(void)
 #else /* !CONFIG_SCHED_CORE */
 
 static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { }
-static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p) { }
+static inline void
+sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
 
 #endif /* CONFIG_SCHED_CORE */
 
@@ -2005,7 +2016,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (sched_core_enabled(rq))
-		sched_core_dequeue(rq, p);
+		sched_core_dequeue(rq, p, flags);
 
 	if (!(flags & DEQUEUE_NOCLOCK))
 		update_rq_clock(rq);
@@ -5244,6 +5255,7 @@ void scheduler_tick(void)
 	if (sched_feat(LATENCY_WARN))
 		resched_latency = cpu_resched_latency(rq);
 	calc_global_load_tick(rq);
+	sched_core_tick(rq);
 
 	rq_unlock(rq, &rf);
 
@@ -5656,6 +5668,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *next, *p, *max = NULL;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
+	bool core_clock_updated = (rq == rq->core);
 	unsigned long cookie;
 	int i, cpu, occ = 0;
 	struct rq *rq_i;
@@ -5708,10 +5721,18 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	/* reset state */
 	rq->core->core_cookie = 0UL;
-	if (rq->core->core_forceidle) {
+	if (rq->core->core_forceidle_count) {
+		if (!core_clock_updated) {
+			update_rq_clock(rq->core);
+			core_clock_updated = true;
+		}
+		sched_core_account_forceidle(rq);
+		/* reset after accounting force idle */
+		rq->core->core_forceidle_start = 0;
+		rq->core->core_forceidle_count = 0;
+		rq->core->core_forceidle_occupation = 0;
 		need_sync = true;
 		fi_before = true;
-		rq->core->core_forceidle = false;
 	}
 
 	/*
@@ -5753,7 +5774,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	for_each_cpu_wrap(i, smt_mask, cpu) {
 		rq_i = cpu_rq(i);
 
-		if (i != cpu)
+		/*
+		 * Current cpu always has its clock updated on entrance to
+		 * pick_next_task(). If the current cpu is not the core,
+		 * the core may also have been updated above.
+		 */
+		if (i != cpu && (rq_i != rq->core || !core_clock_updated))
 			update_rq_clock(rq_i);
 
 		p = rq_i->core_pick = pick_task(rq_i);
@@ -5783,7 +5809,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		if (p == rq_i->idle) {
 			if (rq_i->nr_running) {
-				rq->core->core_forceidle = true;
+				rq->core->core_forceidle_count++;
 				if (!fi_before)
 					rq->core->core_forceidle_seq++;
 			}
@@ -5792,6 +5818,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 	}
 
+	if (schedstat_enabled() && rq->core->core_forceidle_count) {
+		if (cookie)
+			rq->core->core_forceidle_start = rq_clock(rq->core);
+		rq->core->core_forceidle_occupation = occ;
+	}
+
 	rq->core->core_pick_seq = rq->core->core_task_seq;
 	next = rq->core_pick;
 	rq->core_sched_seq = rq->core->core_pick_seq;
@@ -5828,8 +5860,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		 *  1            0       1
 		 *  1            1       0
 		 */
-		if (!(fi_before && rq->core->core_forceidle))
-			task_vruntime_update(rq_i, rq_i->core_pick, rq->core->core_forceidle);
+		if (!(fi_before && rq->core->core_forceidle_count))
+			task_vruntime_update(rq_i, rq_i->core_pick, !!rq->core->core_forceidle_count);
 
 		rq_i->core_pick->core_occupation = occ;
 
@@ -6033,11 +6065,19 @@ static void sched_core_cpu_deactivate(unsigned int cpu)
 		goto unlock;
 
 	/* copy the shared state to the new leader */
-	core_rq->core_task_seq      = rq->core_task_seq;
-	core_rq->core_pick_seq      = rq->core_pick_seq;
-	core_rq->core_cookie        = rq->core_cookie;
-	core_rq->core_forceidle     = rq->core_forceidle;
-	core_rq->core_forceidle_seq = rq->core_forceidle_seq;
+	core_rq->core_task_seq             = rq->core_task_seq;
+	core_rq->core_pick_seq             = rq->core_pick_seq;
+	core_rq->core_cookie               = rq->core_cookie;
+	core_rq->core_forceidle_count      = rq->core_forceidle_count;
+	core_rq->core_forceidle_seq        = rq->core_forceidle_seq;
+	core_rq->core_forceidle_occupation = rq->core_forceidle_occupation;
+
+	/*
+	 * Accounting edge for forced idle is handled in pick_next_task().
+	 * Don't need another one here, since the hotplug thread shouldn't
+	 * have a cookie.
+	 */
+	core_rq->core_forceidle_start = 0;
 
 	/* install new leader */
 	for_each_cpu(t, smt_mask) {
@@ -7126,7 +7166,7 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 
 unsigned long sched_cpu_util(int cpu, unsigned long max)
 {
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu_rq(cpu)), max,
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu), max,
 				  ENERGY_UTIL, NULL);
 }
 #endif /* CONFIG_SMP */
@@ -9409,7 +9449,9 @@ void __init sched_init(void)
 		rq->core_pick = NULL;
 		rq->core_enabled = 0;
 		rq->core_tree = RB_ROOT;
-		rq->core_forceidle = false;
+		rq->core_forceidle_count = 0;
+		rq->core_forceidle_occupation = 0;
+		rq->core_forceidle_start = 0;
 
 		rq->core_cookie = 0UL;
 #endif

kernel/sched/core_sched.c

@@ -73,7 +73,7 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
 
 	enqueued = sched_core_enqueued(p);
 	if (enqueued)
-		sched_core_dequeue(rq, p);
+		sched_core_dequeue(rq, p, DEQUEUE_SAVE);
 
 	old_cookie = p->core_cookie;
 	p->core_cookie = cookie;
@@ -85,6 +85,10 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
 	 * If task is currently running, it may not be compatible anymore after
 	 * the cookie change, so enter the scheduler on its CPU to schedule it
 	 * away.
+	 *
+	 * Note that it is possible that as a result of this cookie change, the
+	 * core has now entered/left forced idle state. Defer accounting to the
+	 * next scheduling edge, rather than always forcing a reschedule here.
 	 */
 	if (task_running(rq, p))
 		resched_curr(rq);
@@ -232,3 +236,63 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type,
 	return err;
 }
 
+#ifdef CONFIG_SCHEDSTATS
+
+/* REQUIRES: rq->core's clock recently updated. */
+void __sched_core_account_forceidle(struct rq *rq)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq));
+	u64 delta, now = rq_clock(rq->core);
+	struct rq *rq_i;
+	struct task_struct *p;
+	int i;
+
+	lockdep_assert_rq_held(rq);
+
+	WARN_ON_ONCE(!rq->core->core_forceidle_count);
+
+	if (rq->core->core_forceidle_start == 0)
+		return;
+
+	delta = now - rq->core->core_forceidle_start;
+	if (unlikely((s64)delta <= 0))
+		return;
+
+	rq->core->core_forceidle_start = now;
+
+	if (WARN_ON_ONCE(!rq->core->core_forceidle_occupation)) {
+		/* can't be forced idle without a running task */
+	} else if (rq->core->core_forceidle_count > 1 ||
+		   rq->core->core_forceidle_occupation > 1) {
+		/*
+		 * For larger SMT configurations, we need to scale the charged
+		 * forced idle amount since there can be more than one forced
+		 * idle sibling and more than one running cookied task.
+		 */
+		delta *= rq->core->core_forceidle_count;
+		delta = div_u64(delta, rq->core->core_forceidle_occupation);
+	}
+
+	for_each_cpu(i, smt_mask) {
+		rq_i = cpu_rq(i);
+		p = rq_i->core_pick ?: rq_i->curr;
+
+		if (!p->core_cookie)
+			continue;
+
+		__schedstat_add(p->stats.core_forceidle_sum, delta);
+	}
+}
+
+void __sched_core_tick(struct rq *rq)
+{
+	if (!rq->core->core_forceidle_count)
+		return;
+
+	if (rq != rq->core)
+		update_rq_clock(rq->core);
+
+	__sched_core_account_forceidle(rq);
+}
+
+#endif /* CONFIG_SCHEDSTATS */