[PATCH v4] sched/core: Minor optimize ttwu_runnable()

[PATCH v4] sched/core: Minor optimize ttwu_runnable()

[Chengming Zhou]

ttwu_runnable() is used as a fast wakeup path when the wakee task
is running on CPU or runnable on RQ, in both cases we can just
set its state to TASK_RUNNING to prevent a sleep.

If the wakee task is on_cpu running, we don't need to update_rq_clock()
or check_preempt_curr().

But if the wakee task is on_rq && !on_cpu (e.g. an IRQ hit before
the task got to schedule() and the task been preempted), we should
check_preempt_curr() to see if it can preempt the current running.

Reorganize ttwu_do_wakeup() and ttwu_do_activate() to make
ttwu_do_wakeup() only mark the task runnable, so it can be used
in ttwu_runnable() and try_to_wake_up() fast paths.

This also removes the class->task_woken() callback from ttwu_runnable(),
which wasn't required per the RT/DL implementations: any required push
operation would have been queued during class->set_next_task() when p
got preempted.

ttwu_runnable() also loses the update to rq->idle_stamp, as by definition
the rq cannot be idle in this scenario.

Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Suggested-by: Valentin Schneider <vschneid@redhat.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
---
v4:
 - s/This patch reorg/Reorganize/ per Bagas Sanjaya. Thanks!

v3:
 - Improve the changelog per Valentin Schneider. Thanks!

v2:
 - keep check_preempt_curr() for on_rq && !on_cpu case in ttwu_runnable(),
   per Valentin Schneider.
 - reorg ttwu_do_wakeup() and ttwu_do_activate() code, so ttwu_do_wakeup()
   can be reused in ttwu_runnable(), per Peter Zijlstra.
 - reuse ttwu_do_wakeup() in try_to_wake_up() (p == current) fast path too,
   so ttwu_do_wakeup() become the only place we mark task runnable.
---
 kernel/sched/core.c | 73 ++++++++++++++++++++++++---------------------
 1 file changed, 39 insertions(+), 34 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 314c2c0219d9..d8216485b0ad 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3623,14 +3623,39 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 }
 
 /*
- * Mark the task runnable and perform wakeup-preemption.
+ * Mark the task runnable.
  */
-static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
-			   struct rq_flags *rf)
+static inline void ttwu_do_wakeup(struct task_struct *p)
 {
-	check_preempt_curr(rq, p, wake_flags);
 	WRITE_ONCE(p->__state, TASK_RUNNING);
 	trace_sched_wakeup(p);
+}
+
+static void
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
+		 struct rq_flags *rf)
+{
+	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
+
+	lockdep_assert_rq_held(rq);
+
+	if (p->sched_contributes_to_load)
+		rq->nr_uninterruptible--;
+
+#ifdef CONFIG_SMP
+	if (wake_flags & WF_MIGRATED)
+		en_flags |= ENQUEUE_MIGRATED;
+	else
+#endif
+	if (p->in_iowait) {
+		delayacct_blkio_end(p);
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
+	activate_task(rq, p, en_flags);
+	check_preempt_curr(rq, p, wake_flags);
+
+	ttwu_do_wakeup(p);
 
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
@@ -3660,31 +3685,6 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 #endif
 }
 
-static void
-ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
-		 struct rq_flags *rf)
-{
-	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
-
-	lockdep_assert_rq_held(rq);
-
-	if (p->sched_contributes_to_load)
-		rq->nr_uninterruptible--;
-
-#ifdef CONFIG_SMP
-	if (wake_flags & WF_MIGRATED)
-		en_flags |= ENQUEUE_MIGRATED;
-	else
-#endif
-	if (p->in_iowait) {
-		delayacct_blkio_end(p);
-		atomic_dec(&task_rq(p)->nr_iowait);
-	}
-
-	activate_task(rq, p, en_flags);
-	ttwu_do_wakeup(rq, p, wake_flags, rf);
-}
-
 /*
  * Consider @p being inside a wait loop:
  *
@@ -3718,9 +3718,15 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 
 	rq = __task_rq_lock(p, &rf);
 	if (task_on_rq_queued(p)) {
-		/* check_preempt_curr() may use rq clock */
-		update_rq_clock(rq);
-		ttwu_do_wakeup(rq, p, wake_flags, &rf);
+		if (!task_on_cpu(rq, p)) {
+			/*
+			 * When on_rq && !on_cpu the task is preempted, see if
+			 * it should preempt whatever is current there now.
+			 */
+			update_rq_clock(rq);
+			check_preempt_curr(rq, p, wake_flags);
+		}
+		ttwu_do_wakeup(p);
 		ret = 1;
 	}
 	__task_rq_unlock(rq, &rf);
@@ -4086,8 +4092,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		trace_sched_waking(p);
-		WRITE_ONCE(p->__state, TASK_RUNNING);
-		trace_sched_wakeup(p);
+		ttwu_do_wakeup(p);
 		goto out;
 	}
 
-- 
2.37.2

Re: [PATCH v4] sched/core: Minor optimize ttwu_runnable()

[Chen Yu]

On 2022-12-02 at 16:06:44 +0800, Chengming Zhou wrote:
> ttwu_runnable() is used as a fast wakeup path when the wakee task
> is running on CPU or runnable on RQ, in both cases we can just
> set its state to TASK_RUNNING to prevent a sleep.
> 
> If the wakee task is on_cpu running, we don't need to update_rq_clock()
> or check_preempt_curr().
> 
> But if the wakee task is on_rq && !on_cpu (e.g. an IRQ hit before
> the task got to schedule() and the task been preempted), we should
> check_preempt_curr() to see if it can preempt the current running.
> 
> Reorganize ttwu_do_wakeup() and ttwu_do_activate() to make
> ttwu_do_wakeup() only mark the task runnable, so it can be used
> in ttwu_runnable() and try_to_wake_up() fast paths.
> 
> This also removes the class->task_woken() callback from ttwu_runnable(),
> which wasn't required per the RT/DL implementations: any required push
> operation would have been queued during class->set_next_task() when p
> got preempted.
> 
> ttwu_runnable() also loses the update to rq->idle_stamp, as by definition
> the rq cannot be idle in this scenario.
> 
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
> Suggested-by: Valentin Schneider <vschneid@redhat.com>
> Suggested-by: Peter Zijlstra <peterz@infradead.org>
> Reviewed-by: Valentin Schneider <vschneid@redhat.com>
> ---
> v4:
>  - s/This patch reorg/Reorganize/ per Bagas Sanjaya. Thanks!
> 
> v3:
>  - Improve the changelog per Valentin Schneider. Thanks!
> 
> v2:
>  - keep check_preempt_curr() for on_rq && !on_cpu case in ttwu_runnable(),
>    per Valentin Schneider.
>  - reorg ttwu_do_wakeup() and ttwu_do_activate() code, so ttwu_do_wakeup()
>    can be reused in ttwu_runnable(), per Peter Zijlstra.
>  - reuse ttwu_do_wakeup() in try_to_wake_up() (p == current) fast path too,
>    so ttwu_do_wakeup() become the only place we mark task runnable.
> ---
>  kernel/sched/core.c | 73 ++++++++++++++++++++++++---------------------
>  1 file changed, 39 insertions(+), 34 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 314c2c0219d9..d8216485b0ad 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3623,14 +3623,39 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
>  }
>  
>  /*
> - * Mark the task runnable and perform wakeup-preemption.
> + * Mark the task runnable.
>   */
> -static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
> -			   struct rq_flags *rf)
> +static inline void ttwu_do_wakeup(struct task_struct *p)
>  {
> -	check_preempt_curr(rq, p, wake_flags);
>  	WRITE_ONCE(p->__state, TASK_RUNNING);
>  	trace_sched_wakeup(p);
> +}
> +
> +static void
> +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
> +		 struct rq_flags *rf)
> +{
> +	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
> +
> +	lockdep_assert_rq_held(rq);
> +
> +	if (p->sched_contributes_to_load)
> +		rq->nr_uninterruptible--;
> +
> +#ifdef CONFIG_SMP
> +	if (wake_flags & WF_MIGRATED)
> +		en_flags |= ENQUEUE_MIGRATED;
> +	else
> +#endif
> +	if (p->in_iowait) {
> +		delayacct_blkio_end(p);
> +		atomic_dec(&task_rq(p)->nr_iowait);
> +	}
> +
> +	activate_task(rq, p, en_flags);
> +	check_preempt_curr(rq, p, wake_flags);
> +
> +	ttwu_do_wakeup(p);
>  
>  #ifdef CONFIG_SMP
>  	if (p->sched_class->task_woken) {
> @@ -3660,31 +3685,6 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
>  #endif
>  }
>  
> -static void
> -ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
> -		 struct rq_flags *rf)
> -{
> -	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
> -
> -	lockdep_assert_rq_held(rq);
> -
> -	if (p->sched_contributes_to_load)
> -		rq->nr_uninterruptible--;
> -
> -#ifdef CONFIG_SMP
> -	if (wake_flags & WF_MIGRATED)
> -		en_flags |= ENQUEUE_MIGRATED;
> -	else
> -#endif
> -	if (p->in_iowait) {
> -		delayacct_blkio_end(p);
> -		atomic_dec(&task_rq(p)->nr_iowait);
> -	}
> -
> -	activate_task(rq, p, en_flags);
> -	ttwu_do_wakeup(rq, p, wake_flags, rf);
> -}
> -
>  /*
>   * Consider @p being inside a wait loop:
>   *
> @@ -3718,9 +3718,15 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
>  
>  	rq = __task_rq_lock(p, &rf);
>  	if (task_on_rq_queued(p)) {
> -		/* check_preempt_curr() may use rq clock */
> -		update_rq_clock(rq);
> -		ttwu_do_wakeup(rq, p, wake_flags, &rf);
> +		if (!task_on_cpu(rq, p)) {
> +			/*
> +			 * When on_rq && !on_cpu the task is preempted, see if
> +			 * it should preempt whatever is current there now.
> +			 */
> +			update_rq_clock(rq);
> +			check_preempt_curr(rq, p, wake_flags);
> +		}
> +		ttwu_do_wakeup(p);
>  		ret = 1;
>  	}
>  	__task_rq_unlock(rq, &rf);
> @@ -4086,8 +4092,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
>  			goto out;
>  
>  		trace_sched_waking(p);
> -		WRITE_ONCE(p->__state, TASK_RUNNING);
> -		trace_sched_wakeup(p);
> +		ttwu_do_wakeup(p);
>  		goto out;
>  	}
>
Just wonder if we could split the reorganization and optimization into two patches,
so we can track the code change a little easier in the future?

thanks,
Chenyu

Re: [PATCH v4] sched/core: Minor optimize ttwu_runnable()

[Chengming Zhou]

On 2022/12/3 15:55, Chen Yu wrote:
> On 2022-12-02 at 16:06:44 +0800, Chengming Zhou wrote:
>> ttwu_runnable() is used as a fast wakeup path when the wakee task
>> is running on CPU or runnable on RQ, in both cases we can just
>> set its state to TASK_RUNNING to prevent a sleep.
>>
>> If the wakee task is on_cpu running, we don't need to update_rq_clock()
>> or check_preempt_curr().
>>
>> But if the wakee task is on_rq && !on_cpu (e.g. an IRQ hit before
>> the task got to schedule() and the task been preempted), we should
>> check_preempt_curr() to see if it can preempt the current running.
>>
>> Reorganize ttwu_do_wakeup() and ttwu_do_activate() to make
>> ttwu_do_wakeup() only mark the task runnable, so it can be used
>> in ttwu_runnable() and try_to_wake_up() fast paths.
>>
>> This also removes the class->task_woken() callback from ttwu_runnable(),
>> which wasn't required per the RT/DL implementations: any required push
>> operation would have been queued during class->set_next_task() when p
>> got preempted.
>>
>> ttwu_runnable() also loses the update to rq->idle_stamp, as by definition
>> the rq cannot be idle in this scenario.
>>
>> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
>> Suggested-by: Valentin Schneider <vschneid@redhat.com>
>> Suggested-by: Peter Zijlstra <peterz@infradead.org>
>> Reviewed-by: Valentin Schneider <vschneid@redhat.com>
>> ---
>> v4:
>>  - s/This patch reorg/Reorganize/ per Bagas Sanjaya. Thanks!
>>
>> v3:
>>  - Improve the changelog per Valentin Schneider. Thanks!
>>
>> v2:
>>  - keep check_preempt_curr() for on_rq && !on_cpu case in ttwu_runnable(),
>>    per Valentin Schneider.
>>  - reorg ttwu_do_wakeup() and ttwu_do_activate() code, so ttwu_do_wakeup()
>>    can be reused in ttwu_runnable(), per Peter Zijlstra.
>>  - reuse ttwu_do_wakeup() in try_to_wake_up() (p == current) fast path too,
>>    so ttwu_do_wakeup() become the only place we mark task runnable.
>> ---
>>  kernel/sched/core.c | 73 ++++++++++++++++++++++++---------------------
>>  1 file changed, 39 insertions(+), 34 deletions(-)
>>
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index 314c2c0219d9..d8216485b0ad 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -3623,14 +3623,39 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
>>  }
>>  
>>  /*
>> - * Mark the task runnable and perform wakeup-preemption.
>> + * Mark the task runnable.
>>   */
>> -static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
>> -			   struct rq_flags *rf)
>> +static inline void ttwu_do_wakeup(struct task_struct *p)
>>  {
>> -	check_preempt_curr(rq, p, wake_flags);
>>  	WRITE_ONCE(p->__state, TASK_RUNNING);
>>  	trace_sched_wakeup(p);
>> +}
>> +
>> +static void
>> +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
>> +		 struct rq_flags *rf)
>> +{
>> +	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
>> +
>> +	lockdep_assert_rq_held(rq);
>> +
>> +	if (p->sched_contributes_to_load)
>> +		rq->nr_uninterruptible--;
>> +
>> +#ifdef CONFIG_SMP
>> +	if (wake_flags & WF_MIGRATED)
>> +		en_flags |= ENQUEUE_MIGRATED;
>> +	else
>> +#endif
>> +	if (p->in_iowait) {
>> +		delayacct_blkio_end(p);
>> +		atomic_dec(&task_rq(p)->nr_iowait);
>> +	}
>> +
>> +	activate_task(rq, p, en_flags);
>> +	check_preempt_curr(rq, p, wake_flags);
>> +
>> +	ttwu_do_wakeup(p);
>>  
>>  #ifdef CONFIG_SMP
>>  	if (p->sched_class->task_woken) {
>> @@ -3660,31 +3685,6 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
>>  #endif
>>  }
>>  
>> -static void
>> -ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
>> -		 struct rq_flags *rf)
>> -{
>> -	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
>> -
>> -	lockdep_assert_rq_held(rq);
>> -
>> -	if (p->sched_contributes_to_load)
>> -		rq->nr_uninterruptible--;
>> -
>> -#ifdef CONFIG_SMP
>> -	if (wake_flags & WF_MIGRATED)
>> -		en_flags |= ENQUEUE_MIGRATED;
>> -	else
>> -#endif
>> -	if (p->in_iowait) {
>> -		delayacct_blkio_end(p);
>> -		atomic_dec(&task_rq(p)->nr_iowait);
>> -	}
>> -
>> -	activate_task(rq, p, en_flags);
>> -	ttwu_do_wakeup(rq, p, wake_flags, rf);
>> -}
>> -
>>  /*
>>   * Consider @p being inside a wait loop:
>>   *
>> @@ -3718,9 +3718,15 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
>>  
>>  	rq = __task_rq_lock(p, &rf);
>>  	if (task_on_rq_queued(p)) {
>> -		/* check_preempt_curr() may use rq clock */
>> -		update_rq_clock(rq);
>> -		ttwu_do_wakeup(rq, p, wake_flags, &rf);
>> +		if (!task_on_cpu(rq, p)) {
>> +			/*
>> +			 * When on_rq && !on_cpu the task is preempted, see if
>> +			 * it should preempt whatever is current there now.
>> +			 */
>> +			update_rq_clock(rq);
>> +			check_preempt_curr(rq, p, wake_flags);
>> +		}
>> +		ttwu_do_wakeup(p);
>>  		ret = 1;
>>  	}
>>  	__task_rq_unlock(rq, &rf);
>> @@ -4086,8 +4092,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
>>  			goto out;
>>  
>>  		trace_sched_waking(p);
>> -		WRITE_ONCE(p->__state, TASK_RUNNING);
>> -		trace_sched_wakeup(p);
>> +		ttwu_do_wakeup(p);
>>  		goto out;
>>  	}
>>
> Just wonder if we could split the reorganization and optimization into two patches,
> so we can track the code change a little easier in the future?

Thanks for your suggestion.

I'll try to split into two patches later and resend.

Thanks.

> 
> thanks,
> Chenyu