[RFC][PATCH 07/13] sched: Allow put_prev_task() to drop rq->lock

[Peter Zijlstra <peterz@infradead.org>]

Currently the pick_next_task() loop is convoluted and ugly because of
how it can drop the rq->lock and needs to restart the picking.

For the RT/Deadline classes, it is put_prev_task() where we do
balancing, and we could do this before the picking loop. Make this
possible.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c      |    2 +-
 kernel/sched/deadline.c  |   14 +++++++++++++-
 kernel/sched/fair.c      |    2 +-
 kernel/sched/idle.c      |    2 +-
 kernel/sched/rt.c        |   14 +++++++++++++-
 kernel/sched/sched.h     |    4 ++--
 kernel/sched/stop_task.c |    2 +-
 7 files changed, 32 insertions(+), 8 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6012,7 +6012,7 @@ static void calc_load_migrate(struct rq
 		atomic_long_add(delta, &calc_load_tasks);
 }
 
-static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_fake(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 }
 
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1772,13 +1772,25 @@ pick_next_task_dl(struct rq *rq, struct
 	return p;
 }
 
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 {
 	update_curr_dl(rq);
 
 	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
+
+	if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+		/*
+		 * This is OK, because current is on_cpu, which avoids it being
+		 * picked for load-balance and preemption/IRQs are still
+		 * disabled avoiding further scheduler activity on it and we've
+		 * not yet started the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_dl_task(rq);
+		rq_repin_lock(rq, rf);
+	}
 }
 
 /*
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6871,7 +6871,7 @@ done: __maybe_unused;
 /*
  * Account for a descheduled task:
  */
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct sched_entity *se = &prev->se;
 	struct cfs_rq *cfs_rq;
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -374,7 +374,7 @@ static void check_preempt_curr_idle(stru
 	resched_curr(rq);
 }
 
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 }
 
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1593,7 +1593,7 @@ pick_next_task_rt(struct rq *rq, struct
 	return p;
 }
 
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 {
 	update_curr_rt(rq);
 
@@ -1605,6 +1605,18 @@ static void put_prev_task_rt(struct rq *
 	 */
 	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
+
+	if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+		/*
+		 * This is OK, because current is on_cpu, which avoids it being
+		 * picked for load-balance and preemption/IRQs are still
+		 * disabled avoiding further scheduler activity on it and we've
+		 * not yet started the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_rt_task(rq);
+		rq_repin_lock(rq, rf);
+	}
 }
 
 #ifdef CONFIG_SMP
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1714,7 +1714,7 @@ struct sched_class {
 	struct task_struct * (*pick_next_task)(struct rq *rq,
 					       struct task_struct *prev,
 					       struct rq_flags *rf);
-	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
@@ -1760,7 +1760,7 @@ struct sched_class {
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->curr != prev);
-	prev->sched_class->put_prev_task(rq, prev);
+	prev->sched_class->put_prev_task(rq, prev, NULL);
 }
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -59,7 +59,7 @@ static void yield_task_stop(struct rq *r
 	BUG(); /* the stop task should never yield, its pointless. */
 }
 
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct task_struct *curr = rq->curr;
 	u64 delta_exec;