[RFC PATCH v2 09/17] sched: Introduce sched_class::pick_task()

[Vineeth Remanan Pillai]

From: "Peter Zijlstra (Intel)" <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.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Vineeth Remanan Pillai <vpillai@xxxxxxxxxxxxxxxx>
Signed-off-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxxxxxx>
---

Changes in v2
-------------
- Fixes a NULL pointer dereference crash
  - Subhra Mazumdar
  - Tim Chen

---
 kernel/sched/deadline.c  | 21 ++++++++++++++++-----
 kernel/sched/fair.c      | 39 ++++++++++++++++++++++++++++++++++++---
 kernel/sched/idle.c      | 10 +++++++++-
 kernel/sched/rt.c        | 21 ++++++++++++++++-----
 kernel/sched/sched.h     |  2 ++
 kernel/sched/stop_task.c | 21 ++++++++++++++++-----
 6 files changed, 95 insertions(+), 19 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 249310e68592..010234908cc0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1723,15 +1723,12 @@ 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, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_task_dl(struct rq *rq)
 {
 	struct sched_dl_entity *dl_se;
 	struct task_struct *p;
 	struct dl_rq *dl_rq;
 
-	WARN_ON_ONCE(prev || rf);
-
 	dl_rq = &rq->dl;
 
 	if (unlikely(!dl_rq->dl_nr_running))
@@ -1742,7 +1739,19 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	p = dl_task_of(dl_se);
 
-	set_next_task_dl(rq, p);
+	return p;
+}
+
+static struct task_struct *
+pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	struct task_struct *p;
+
+	WARN_ON_ONCE(prev || rf);
+
+	p = pick_task_dl(rq);
+	if (p)
+		set_next_task_dl(rq, p);
 
 	return p;
 }
@@ -2389,6 +2398,8 @@ const struct sched_class dl_sched_class = {
 	.set_next_task		= set_next_task_dl,
 
 #ifdef CONFIG_SMP
+	.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 c055bad249a9..45d86b862750 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4132,7 +4132,7 @@ 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) {
@@ -4150,13 +4150,13 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	/*
 	 * Prefer last buddy, try to return the CPU to a preempted task.
 	 */
-	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+	if (left && cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
 		se = cfs_rq->last;
 
 	/*
 	 * Someone really wants this to run. If it's not unfair, run it.
 	 */
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+	if (left && cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
 		se = cfs_rq->next;
 
 	clear_buddies(cfs_rq, se);
@@ -6937,6 +6937,37 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		set_last_buddy(se);
 }
 
+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 (!(se || curr))
+			return 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);
+}
+
 static struct task_struct *
 pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
@@ -10648,6 +10679,8 @@ const struct sched_class fair_sched_class = {
 	.set_next_task          = set_next_task_fair,
 
 #ifdef CONFIG_SMP
+	.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 7ece8e820b5d..e7f38da60373 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -373,6 +373,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 	resched_curr(rq);
 }
 
+static struct task_struct *
+pick_task_idle(struct rq *rq)
+{
+	return rq->idle;
+}
+
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 }
@@ -386,11 +392,12 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next)
 static struct task_struct *
 pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct task_struct *next = rq->idle;
+	struct task_struct *next;
 
 	if (prev)
 		put_prev_task(rq, prev);
 
+	next = pick_task_idle(rq);
 	set_next_task_idle(rq, next);
 
 	return next;
@@ -458,6 +465,7 @@ const struct sched_class idle_sched_class = {
 	.set_next_task          = set_next_task_idle,
 
 #ifdef CONFIG_SMP
+	.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 79f2e60516ef..81557224548c 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1548,20 +1548,29 @@ 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, struct task_struct *prev, struct rq_flags *rf)
+static struct task_struct *pick_task_rt(struct rq *rq)
 {
 	struct task_struct *p;
 	struct rt_rq *rt_rq = &rq->rt;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!rt_rq->rt_queued)
 		return NULL;
 
 	p = _pick_next_task_rt(rq);
 
-	set_next_task_rt(rq, p);
+	return p;
+}
+
+static struct task_struct *
+pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	struct task_struct *p;
+
+	WARN_ON_ONCE(prev || rf);
+
+	p = pick_task_rt(rq);
+	if (p)
+		set_next_task_rt(rq, p);
 
 	return p;
 }
@@ -2364,6 +2373,8 @@ const struct sched_class rt_sched_class = {
 	.set_next_task          = set_next_task_rt,
 
 #ifdef CONFIG_SMP
+	.pick_task		= pick_task_rt,
+
 	.select_task_rq		= select_task_rq_rt,
 
 	.set_cpus_allowed       = set_cpus_allowed_common,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 460dd04e76af..a024dd80eeb3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1682,6 +1682,8 @@ struct sched_class {
 	void (*set_next_task)(struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
+	struct task_struct * (*pick_task)(struct rq *rq);
+
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 7e1cee4e65b2..fb6c436cba6c 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -29,20 +29,30 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
 }
 
 static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+pick_task_stop(struct rq *rq)
 {
 	struct task_struct *stop = rq->stop;
 
-	WARN_ON_ONCE(prev || rf);
-
 	if (!stop || !task_on_rq_queued(stop))
 		return NULL;
 
-	set_next_task_stop(rq, stop);
-
 	return stop;
 }
 
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	struct task_struct *p;
+
+	WARN_ON_ONCE(prev || rf);
+
+	p = pick_task_stop(rq);
+	if (p)
+		set_next_task_stop(rq, p);
+
+	return p;
+}
+
 static void
 enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
 {
@@ -129,6 +139,7 @@ const struct sched_class stop_sched_class = {
 	.set_next_task          = set_next_task_stop,
 
 #ifdef CONFIG_SMP
+	.pick_task		= pick_task_stop,
 	.select_task_rq		= select_task_rq_stop,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
-- 
2.17.1