[PATCH -tip 02/32] sched: Introduce sched_class::pick_task()

From: Joel Fernandes (Google)
Date: Tue Nov 17 2020 - 18:20:49 EST

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Because sched_class::pick_next_task() also implies
sched_class::set_next_task() (and possibly put_prev_task() and
newidle_balance) it is not state invariant. This makes it unsuitable
for remote task selection.

Tested-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Vineeth Remanan Pillai <viremana@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
---
kernel/sched/deadline.c | 16 ++++++++++++++--
kernel/sched/fair.c | 32 +++++++++++++++++++++++++++++++-
kernel/sched/idle.c | 8 ++++++++
kernel/sched/rt.c | 15 +++++++++++++--
kernel/sched/sched.h | 3 +++
kernel/sched/stop_task.c | 14 ++++++++++++--
6 files changed, 81 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0f2ea0a3664c..abfc8b505d0d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1867,7 +1867,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
return rb_entry(left, struct sched_dl_entity, rb_node);
}

-static struct task_struct *pick_next_task_dl(struct rq *rq)
+static struct task_struct *pick_task_dl(struct rq *rq)
{
struct sched_dl_entity *dl_se;
struct dl_rq *dl_rq = &rq->dl;
@@ -1879,7 +1879,18 @@ static struct task_struct *pick_next_task_dl(struct rq *rq)
dl_se = pick_next_dl_entity(rq, dl_rq);
BUG_ON(!dl_se);
p = dl_task_of(dl_se);
- set_next_task_dl(rq, p, true);
+
+ return p;
+}
+
+static struct task_struct *pick_next_task_dl(struct rq *rq)
+{
+ struct task_struct *p;
+
+ p = pick_task_dl(rq);
+ if (p)
+ set_next_task_dl(rq, p, true);
+
return p;
}

@@ -2551,6 +2562,7 @@ DEFINE_SCHED_CLASS(dl) = {

#ifdef CONFIG_SMP
.balance = balance_dl,
+ .pick_task = pick_task_dl,
.select_task_rq = select_task_rq_dl,
.migrate_task_rq = migrate_task_rq_dl,
.set_cpus_allowed = set_cpus_allowed_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 52ddfec7cea6..12cf068eeec8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4459,7 +4459,7 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
* Avoid running the skip buddy, if running something else can
* be done without getting too unfair.
*/
- if (cfs_rq->skip == se) {
+ if (cfs_rq->skip && cfs_rq->skip == se) {
struct sched_entity *second;

if (se == curr) {
@@ -7017,6 +7017,35 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
set_last_buddy(se);
}

+#ifdef CONFIG_SMP
+static struct task_struct *pick_task_fair(struct rq *rq)
+{
+ struct cfs_rq *cfs_rq = &rq->cfs;
+ struct sched_entity *se;
+
+ if (!cfs_rq->nr_running)
+ return NULL;
+
+ do {
+ struct sched_entity *curr = cfs_rq->curr;
+
+ se = pick_next_entity(cfs_rq, NULL);
+
+ if (curr) {
+ if (se && curr->on_rq)
+ update_curr(cfs_rq);
+
+ if (!se || entity_before(curr, se))
+ se = curr;
+ }
+
+ cfs_rq = group_cfs_rq(se);
+ } while (cfs_rq);
+
+ return task_of(se);
+}
+#endif
+
struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
@@ -11219,6 +11248,7 @@ DEFINE_SCHED_CLASS(fair) = {

#ifdef CONFIG_SMP
.balance = balance_fair,
+ .pick_task = pick_task_fair,
.select_task_rq = select_task_rq_fair,
.migrate_task_rq = migrate_task_rq_fair,

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 50e128b899c4..33864193a2f9 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -406,6 +406,13 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
schedstat_inc(rq->sched_goidle);
}

+#ifdef CONFIG_SMP
+static struct task_struct *pick_task_idle(struct rq *rq)
+{
+ return rq->idle;
+}
+#endif
+
struct task_struct *pick_next_task_idle(struct rq *rq)
{
struct task_struct *next = rq->idle;
@@ -473,6 +480,7 @@ DEFINE_SCHED_CLASS(idle) = {

#ifdef CONFIG_SMP
.balance = balance_idle,
+ .pick_task = pick_task_idle,
.select_task_rq = select_task_rq_idle,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a6f9d132c24f..a0e245b0c4bd 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1626,7 +1626,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
return rt_task_of(rt_se);
}

-static struct task_struct *pick_next_task_rt(struct rq *rq)
+static struct task_struct *pick_task_rt(struct rq *rq)
{
struct task_struct *p;

@@ -1634,7 +1634,17 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
return NULL;

p = _pick_next_task_rt(rq);
- set_next_task_rt(rq, p, true);
+
+ return p;
+}
+
+static struct task_struct *pick_next_task_rt(struct rq *rq)
+{
+ struct task_struct *p = pick_task_rt(rq);
+
+ if (p)
+ set_next_task_rt(rq, p, true);
+
return p;
}

@@ -2483,6 +2493,7 @@ DEFINE_SCHED_CLASS(rt) = {

#ifdef CONFIG_SMP
.balance = balance_rt,
+ .pick_task = pick_task_rt,
.select_task_rq = select_task_rq_rt,
.set_cpus_allowed = set_cpus_allowed_common,
.rq_online = rq_online_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f794c9337047..5a0dd2b312aa 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1839,6 +1839,9 @@ struct sched_class {
#ifdef CONFIG_SMP
int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
+
+ struct task_struct * (*pick_task)(struct rq *rq);
+
void (*migrate_task_rq)(struct task_struct *p, int new_cpu);

void (*task_woken)(struct rq *this_rq, struct task_struct *task);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 55f39125c0e1..f988ebe3febb 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -34,15 +34,24 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool fir
stop->se.exec_start = rq_clock_task(rq);
}

-static struct task_struct *pick_next_task_stop(struct rq *rq)
+static struct task_struct *pick_task_stop(struct rq *rq)
{
if (!sched_stop_runnable(rq))
return NULL;

- set_next_task_stop(rq, rq->stop, true);
return rq->stop;
}

+static struct task_struct *pick_next_task_stop(struct rq *rq)
+{
+ struct task_struct *p = pick_task_stop(rq);
+
+ if (p)
+ set_next_task_stop(rq, p, true);
+
+ return p;
+}
+
static void
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
@@ -123,6 +132,7 @@ DEFINE_SCHED_CLASS(stop) = {

#ifdef CONFIG_SMP
.balance = balance_stop,
+ .pick_task = pick_task_stop,
.select_task_rq = select_task_rq_stop,
.set_cpus_allowed = set_cpus_allowed_common,
#endif
--
2.29.2.299.gdc1121823c-goog