sched/core: Further clarify sched_class::set_next_task()

It turns out there really is something special to the first
set_next_task() invocation. In specific the 'change' pattern really
should not cause balance callbacks.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: juri.lelli@redhat.com
Cc: ktkhai@virtuozzo.com
Cc: mgorman@suse.de
Cc: qais.yousef@arm.com
Cc: qperret@google.com
Cc: rostedt@goodmis.org
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Fixes: f95d4eaee6d0 ("sched/{rt,deadline}: Fix set_next_task vs pick_next_task")
Link: https://lkml.kernel.org/r/20191108131909.775434698@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f7fbb44279594205d935a7d73768166667c11ea1..43323f875cb9a8df5c247a95ea76f88b7604329b 100644 (file)
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1743,13 +1743,16 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 }
 #endif
 
-static void set_next_task_dl(struct rq *rq, struct task_struct *p)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 {
        p->se.exec_start = rq_clock_task(rq);
 
        /* You can't push away the running task */
        dequeue_pushable_dl_task(rq, p);
 
+       if (!first)
+               return;
+
        if (hrtick_enabled(rq))
                start_hrtick_dl(rq, p);
 
@@ -1782,7 +1785,7 @@ 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);
+       set_next_task_dl(rq, p, true);
        return p;
 }
 

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ba97d1a1b9760c393d6bcf425814338fa7f9560e..81eba554db8d6602ee7e5df2570269db5d150696 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10344,7 +10344,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
  * This routine is mostly called to set cfs_rq->curr field when a task
  * migrates between groups/classes.
  */
-static void set_next_task_fair(struct rq *rq, struct task_struct *p)
+static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 {
        struct sched_entity *se = &p->se;
 

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f88b79eeee1ece8e845854c5e1c00b214e93698f..428cd05c0b5df15db4a65ad03c63a5ff7cb4701c 100644 (file)
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -385,7 +385,7 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
 }
 
-static void set_next_task_idle(struct rq *rq, struct task_struct *next)
+static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
        update_idle_core(rq);
        schedstat_inc(rq->sched_goidle);
@@ -395,7 +395,7 @@ struct task_struct *pick_next_task_idle(struct rq *rq)
 {
        struct task_struct *next = rq->idle;
 
-       set_next_task_idle(rq, next);
+       set_next_task_idle(rq, next, true);
 
        return next;
 }

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 38027c04b04c26670fdf7a26a63f7b484f30b454..e591d40fd645e451e79946fc9801ee24e72ef68e 100644 (file)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1515,13 +1515,16 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 #endif
 }
 
-static inline void set_next_task_rt(struct rq *rq, struct task_struct *p)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
 {
        p->se.exec_start = rq_clock_task(rq);
 
        /* The running task is never eligible for pushing */
        dequeue_pushable_task(rq, p);
 
+       if (!first)
+               return;
+
        /*
         * If prev task was rt, put_prev_task() has already updated the
         * utilization. We only care of the case where we start to schedule a
@@ -1572,7 +1575,7 @@ 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);
+       set_next_task_rt(rq, p, true);
        return p;
 }
 

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 75d96cce149260cd80dab6c212533a1a916d1f80..05c282775f213ef9d4ef1f3dba1f223ccc0a31e2 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1716,7 +1716,7 @@ struct sched_class {
        struct task_struct *(*pick_next_task)(struct rq *rq);
 
        void (*put_prev_task)(struct rq *rq, struct task_struct *p);
-       void (*set_next_task)(struct rq *rq, struct task_struct *p);
+       void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
 #ifdef CONFIG_SMP
        int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
@@ -1768,7 +1768,7 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
 {
        WARN_ON_ONCE(rq->curr != next);
-       next->sched_class->set_next_task(rq, next);
+       next->sched_class->set_next_task(rq, next, false);
 }
 
 #ifdef CONFIG_SMP

diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 0aefdfb79b361c5b5d85a0f36430a03034a1b8fb..4c9e9975684fa8cd633ba05008493499994eb99a 100644 (file)
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -29,7 +29,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
        /* we're never preempted */
 }
 
-static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
+static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool first)
 {
        stop->se.exec_start = rq_clock_task(rq);
 }
@@ -39,7 +39,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
        if (!sched_stop_runnable(rq))
                return NULL;
 
-       set_next_task_stop(rq, rq->stop);
+       set_next_task_stop(rq, rq->stop, true);
        return rq->stop;
 }