Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   Daniel Bristot de Oliveira <bristot@kernel.org>
To:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>
Cc:     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>,
        Valentin Schneider <vschneid@redhat.com>,
        linux-kernel@vger.kernel.org,
        Luca Abeni <luca.abeni@santannapisa.it>,
        Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it>,
        Thomas Gleixner <tglx@linutronix.de>,
        Joel Fernandes <joel@joelfernandes.org>,
        Vineeth Pillai <vineeth@bitbyteword.org>,
        Shuah Khan <skhan@linuxfoundation.org>, bristot@kernel.org,
        Phil Auld <pauld@redhat.com>
Subject: [PATCH v5 1/7] sched: Unify runtime accounting across classes
Date:   Sat,  4 Nov 2023 11:59:18 +0100
Message-Id: <54d148a144f26d9559698c4dd82d8859038a7380.1699095159.git.bristot@kernel.org>
In-Reply-To: <cover.1699095159.git.bristot@kernel.org>
References: <cover.1699095159.git.bristot@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Peter Zijlstra <peterz@infradead.org>

All classes use sched_entity::exec_start to track runtime and have
copies of the exact same code around to compute runtime.

Collapse all that.

Reviewed-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 include/linux/sched.h    |  2 +-
 kernel/sched/deadline.c  | 15 +++--------
 kernel/sched/fair.c      | 57 ++++++++++++++++++++++++++++++----------
 kernel/sched/rt.c        | 15 +++--------
 kernel/sched/sched.h     | 12 ++-------
 kernel/sched/stop_task.c | 13 +--------
 6 files changed, 53 insertions(+), 61 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 12ec109ce8c9..31eee8b03dcd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -523,7 +523,7 @@ struct sched_statistics {
 	u64				block_max;
 	s64				sum_block_runtime;
 
-	u64				exec_max;
+	s64				exec_max;
 	u64				slice_max;
 
 	u64				nr_migrations_cold;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b28114478b82..de79719c63c0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1275,9 +1275,8 @@ static void update_curr_dl(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_dl_entity *dl_se = &curr->dl;
-	u64 delta_exec, scaled_delta_exec;
+	s64 delta_exec, scaled_delta_exec;
 	int cpu = cpu_of(rq);
-	u64 now;
 
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
@@ -1290,21 +1289,13 @@ static void update_curr_dl(struct rq *rq)
 	 * natural solution, but the full ramifications of this
 	 * approach need further study.
 	 */
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0)) {
+	delta_exec = update_curr_common(rq);
+	if (unlikely(delta_exec <= 0)) {
 		if (unlikely(dl_se->dl_yielded))
 			goto throttle;
 		return;
 	}
 
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
-	update_current_exec_runtime(curr, now, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8767988242ee..2613704a2d2d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1129,23 +1129,17 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_SMP */
 
-/*
- * Update the current task's runtime statistics.
- */
-static void update_curr(struct cfs_rq *cfs_rq)
+static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
 {
-	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_clock_task(rq_of(cfs_rq));
-	u64 delta_exec;
-
-	if (unlikely(!curr))
-		return;
+	u64 now = rq_clock_task(rq);
+	s64 delta_exec;
 
 	delta_exec = now - curr->exec_start;
-	if (unlikely((s64)delta_exec <= 0))
-		return;
+	if (unlikely(delta_exec <= 0))
+		return delta_exec;
 
 	curr->exec_start = now;
+	curr->sum_exec_runtime += delta_exec;
 
 	if (schedstat_enabled()) {
 		struct sched_statistics *stats;
@@ -1155,8 +1149,43 @@ static void update_curr(struct cfs_rq *cfs_rq)
 				max(delta_exec, stats->exec_max));
 	}
 
-	curr->sum_exec_runtime += delta_exec;
-	schedstat_add(cfs_rq->exec_clock, delta_exec);
+	return delta_exec;
+}
+
+/*
+ * Used by other classes to account runtime.
+ */
+s64 update_curr_common(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	s64 delta_exec;
+
+	delta_exec = update_curr_se(rq, &curr->se);
+	if (unlikely(delta_exec <= 0))
+		return delta_exec;
+
+	trace_sched_stat_runtime(curr, delta_exec, 0);
+
+	account_group_exec_runtime(curr, delta_exec);
+	cgroup_account_cputime(curr, delta_exec);
+
+	return delta_exec;
+}
+
+/*
+ * Update the current task's runtime statistics.
+ */
+static void update_curr(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *curr = cfs_rq->curr;
+	s64 delta_exec;
+
+	if (unlikely(!curr))
+		return;
+
+	delta_exec = update_curr_se(rq_of(cfs_rq), curr);
+	if (unlikely(delta_exec <= 0))
+		return;
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
 	update_deadline(cfs_rq, curr);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6aaf0a3d6081..3261b067b67e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1002,24 +1002,15 @@ static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_rt_entity *rt_se = &curr->rt;
-	u64 delta_exec;
-	u64 now;
+	s64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0))
+	delta_exec = update_curr_common(rq);
+	if (unlikely(delta_exec <= 0))
 		return;
 
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
-	update_current_exec_runtime(curr, now, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2e5a95486a42..3e0e4fc8734b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2212,6 +2212,8 @@ struct affinity_context {
 	unsigned int flags;
 };
 
+extern s64 update_curr_common(struct rq *rq);
+
 struct sched_class {
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -3261,16 +3263,6 @@ extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
 
-static inline void update_current_exec_runtime(struct task_struct *curr,
-						u64 now, u64 delta_exec)
-{
-	curr->se.sum_exec_runtime += delta_exec;
-	account_group_exec_runtime(curr, delta_exec);
-
-	curr->se.exec_start = now;
-	cgroup_account_cputime(curr, delta_exec);
-}
-
 #ifdef CONFIG_SCHED_MM_CID
 
 #define SCHED_MM_CID_PERIOD_NS	(100ULL * 1000000)	/* 100ms */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 6cf7304e6449..b1b8fe61c532 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -70,18 +70,7 @@ static void yield_task_stop(struct rq *rq)
 
 static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *curr = rq->curr;
-	u64 now, delta_exec;
-
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec < 0))
-		delta_exec = 0;
-
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	update_current_exec_runtime(curr, now, delta_exec);
+	update_curr_common(rq);
 }
 
 /*
-- 
2.40.1