Received-SPF: pass (google.com: domain of linux-kernel+bounces-49444-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: Valentin Schneider <vschneid@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>,
	Mel Gorman <mgorman@suse.de>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	Phil Auld <pauld@redhat.com>,
	Clark Williams <williams@redhat.com>,
	Tomas Glozar <tglozar@redhat.com>
Subject: [RFC PATCH v2 5/5] sched/fair: Assert user/kernel/total nr invariants
Date: Fri,  2 Feb 2024 09:09:20 +0100
Message-ID: <20240202080920.3337862-6-vschneid@redhat.com>
In-Reply-To: <20240202080920.3337862-1-vschneid@redhat.com>
References: <20240202080920.3337862-1-vschneid@redhat.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Previous commits have added .h_kernel_running and .h_user_running to struct
cfs_rq, and are using them to play games with the hierarchical
h_nr_running.

Assert some count invariants under SCHED_DEBUG to improve debugging.

Signed-off-by: Valentin Schneider <vschneid@redhat.com>
---
 kernel/sched/fair.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2b54d3813d18d..52d0ee0e4d47c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5780,6 +5780,30 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 static void enqueue_kernel(struct cfs_rq *cfs_rq, struct sched_entity *se, int count);
 static void dequeue_kernel(struct cfs_rq *cfs_rq, struct sched_entity *se, int count);
 
+#ifdef CONFIG_CFS_BANDWIDTH
+static inline void assert_cfs_rq_counts(struct cfs_rq *cfs_rq)
+{
+	lockdep_assert_rq_held(rq_of(cfs_rq));
+
+	/*
+	 * When !throttle_pending, this is the normal operating mode, all tasks
+	 * are pickable, so:
+	 * nr_kernel_tasks + nr_user_tasks == nr_pickable_tasks
+	 */
+	SCHED_WARN_ON(!cfs_rq->throttle_pending &&
+		      (cfs_rq->h_kernel_running + cfs_rq->h_user_running !=
+		       cfs_rq->h_nr_running));
+	/*
+	 * When throttle_pending, only kernel tasks are pickable, so:
+	 * nr_kernel_tasks == nr_pickable_tasks
+	 */
+	SCHED_WARN_ON(cfs_rq->throttle_pending &&
+		      (cfs_rq->h_kernel_running != cfs_rq->h_nr_running));
+}
+#else
+static inline void assert_cfs_rq_counts(struct cfs_rq *cfs_rq) { }
+#endif
+
 static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
@@ -5894,6 +5918,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		dequeue_kernel(qcfs_rq, se, kernel_delta);
 		qcfs_rq->h_user_running -= user_delta;
 
+		assert_cfs_rq_counts(qcfs_rq);
 
 		if (qcfs_rq->load.weight) {
 			/* Avoid re-evaluating load for this entity: */
@@ -5918,6 +5943,8 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 		dequeue_kernel(qcfs_rq, se, kernel_delta);
 		qcfs_rq->h_user_running -= user_delta;
+
+		assert_cfs_rq_counts(qcfs_rq);
 	}
 
 	/* At this point se is NULL and we are at root level*/
@@ -6013,6 +6040,8 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 		enqueue_kernel(qcfs_rq, se, kernel_delta);
 		qcfs_rq->h_user_running += user_delta;
 
+		assert_cfs_rq_counts(qcfs_rq);
+
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(qcfs_rq))
 			goto unthrottle_throttle;
@@ -6950,6 +6979,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
 
+		assert_cfs_rq_counts(cfs_rq);
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
@@ -6965,6 +6995,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		se_update_runnable(se);
 		update_cfs_group(se);
 
+		assert_cfs_rq_counts(cfs_rq);
 
 		if (kernel_task || (!throttle_pending && !cfs_rq->throttle_pending))
 			cfs_rq->h_nr_running++;
@@ -6979,6 +7010,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
 
+		assert_cfs_rq_counts(cfs_rq);
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
@@ -7051,6 +7083,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
 
+		assert_cfs_rq_counts(cfs_rq);
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
@@ -7092,6 +7125,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_is_idle(cfs_rq))
 			idle_h_nr_running = 1;
 
+		assert_cfs_rq_counts(cfs_rq);
 
 		/* end evaluation on encountering a throttled cfs_rq */
 		if (cfs_rq_throttled(cfs_rq))
@@ -8631,6 +8665,8 @@ static void handle_kernel_task_prev(struct task_struct *prev)
 
 			throttle_pending |= cfs_rq->throttle_pending;
 
+			assert_cfs_rq_counts(cfs_rq);
+
 			if (cfs_rq_throttled(cfs_rq))
 				break;
 		}
@@ -8648,6 +8684,8 @@ static void handle_kernel_task_prev(struct task_struct *prev)
 
 			throttle_pending |= cfs_rq->throttle_pending;
 
+			assert_cfs_rq_counts(cfs_rq);
+
 			if (cfs_rq_throttled(cfs_rq))
 				break;
 		}
-- 
2.43.0