[PATCH v3 07/14] sched: Unify runtime accounting across classes

From: John Stultz
Date: Tue Apr 11 2023 - 00:26:04 EST


From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

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.

Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E . McKenney" <paulmck@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
[fix conflicts, fold in update_current_exec_runtime]
Signed-off-by: Connor O'Brien <connoro@xxxxxxxxxx>
[jstultz: rebased, resovling minor conflicts]
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
include/linux/sched.h | 2 +-
kernel/sched/deadline.c | 13 +++-------
kernel/sched/fair.c | 56 ++++++++++++++++++++++++++++++----------
kernel/sched/rt.c | 13 +++-------
kernel/sched/sched.h | 12 ++-------
kernel/sched/stop_task.c | 13 +---------
6 files changed, 52 insertions(+), 57 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9d46ca8ac221..6d22542d3648 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -519,7 +519,7 @@ 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 71b24371a6f7..5a7c4edd5b13 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1308,9 +1308,8 @@ 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;
@@ -1323,21 +1322,15 @@ 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 6986ea31c984..bea9a31c76ff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -891,23 +891,17 @@ 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;
@@ -917,9 +911,43 @@ 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;
+
+ 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;
+
+ schedstat_add(cfs_rq->exec_clock, delta_exec);
curr->vruntime += calc_delta_fair(delta_exec, curr);
update_min_vruntime(cfs_rq);

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0a11f44adee5..18eb6ce60c5c 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1046,24 +1046,17 @@ 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 3e8df6d31c1e..d18e3c3a3f40 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2166,6 +2166,8 @@ struct affinity_context {
unsigned int flags;
};

+extern s64 update_curr_common(struct rq *rq);
+
struct sched_class {

#ifdef CONFIG_UCLAMP_TASK
@@ -3238,16 +3240,6 @@ 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
static inline int __mm_cid_get(struct mm_struct *mm)
{
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 85590599b4d6..7595494ceb6d 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);
}

/*
--
2.40.0.577.gac1e443424-goog