LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, juri.lelli@redhat.com
Cc: linux-kernel@vger.kernel.org, dietmar.eggemann@arm.com,
	luca.abeni@santannapisa.it, bristot@redhat.com,
	balsini@android.com, dvyukov@google.com, tglx@linutronix.de,
	vpillai@digitalocean.com, rostedt@goodmis.org,
	peterz@infradead.org
Subject: [RFC][PATCH 07/13] sched: Allow put_prev_task() to drop rq->lock
Date: Fri, 26 Jul 2019 16:54:16 +0200
Message-ID: <20190726161357.755285526@infradead.org> (raw)
In-Reply-To: <20190726145409.947503076@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;



  parent reply index

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-26 14:54 [RFC][PATCH 00/13] SCHED_DEADLINE server infrastructure Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 01/13] sched/deadline: Impose global limits on sched_attr::sched_period Peter Zijlstra
2019-07-29  8:57   ` Juri Lelli
2019-07-29 11:45     ` Daniel Bristot de Oliveira
2019-08-02 17:21   ` Alessio Balsini
2019-08-05 11:53     ` Peter Zijlstra
2019-08-22 12:29       ` Alessio Balsini
2019-08-22 16:51         ` Peter Zijlstra
2019-08-31 14:41           ` Alessio Balsini
2019-09-02  9:16             ` Peter Zijlstra
2019-09-02 12:31               ` Peter Zijlstra
2019-09-04 10:16               ` Steven Rostedt
2019-09-04 11:30                 ` Peter Zijlstra
2019-09-04 13:24                   ` Joel Fernandes
2019-09-04 14:11                     ` Will Deacon
2019-09-04 14:35                       ` Joel Fernandes
2019-09-04 15:52                     ` Peter Zijlstra
2019-10-23 17:17       ` [PATCH 4.4 4.9 4.14] loop: Add LOOP_SET_DIRECT_IO to compat ioctl Alessio Balsini
2019-10-23 17:22         ` Alessio Balsini
2019-10-25  0:17         ` Sasha Levin
2020-05-20 18:38   ` [RFC][PATCH 01/13] sched/deadline: Impose global limits on sched_attr::sched_period Juri Lelli
2020-05-21 13:45     ` Daniel Bristot de Oliveira
2020-06-16 12:21   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 02/13] stop_machine: Fix stop_cpus_in_progress ordering Peter Zijlstra
2019-07-30 13:16   ` Phil Auld
2019-07-30 13:22   ` Steven Rostedt
2019-07-26 14:54 ` [RFC][PATCH 03/13] sched: Fix kerneldoc comment for ia64_set_curr_task Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 04/13] sched/{rt,deadline}: Fix set_next_task vs pick_next_task Peter Zijlstra
2019-07-29  9:25   ` Juri Lelli
2019-07-29 11:15     ` Peter Zijlstra
2019-07-29 11:27       ` Juri Lelli
2019-07-29 13:04         ` Peter Zijlstra
2019-07-29 13:17           ` Juri Lelli
2019-07-29 14:40             ` Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 05/13] sched: Add task_struct pointer to sched_class::set_curr_task Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 06/13] sched/fair: Export newidle_balance() Peter Zijlstra
2019-07-26 14:54 ` Peter Zijlstra [this message]
2019-07-26 14:54 ` [RFC][PATCH 08/13] sched: Rework pick_next_task() slow-path Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 09/13] sched: Unify runtime accounting across classes Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 10/13] sched/deadline: Collect sched_dl_entity initialization Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 11/13] sched/deadline: Move bandwidth accounting into {en,de}queue_dl_entity Peter Zijlstra
2019-07-26 14:54 ` [RFC][PATCH 12/13] sched/deadline: Introduce deadline servers Peter Zijlstra
2019-08-07 16:31   ` Dietmar Eggemann
2019-08-08  6:52     ` Juri Lelli
2019-08-08  7:52       ` Dietmar Eggemann
2019-08-08  7:56     ` Peter Zijlstra
2019-08-08  8:11       ` Dietmar Eggemann
2019-08-08  8:46         ` Juri Lelli
2019-08-08  8:57           ` Dietmar Eggemann
2019-08-08  9:27             ` Juri Lelli
2019-08-08  9:45               ` Juri Lelli
2019-08-30 11:24                 ` Peter Zijlstra
2019-09-06  9:36                   ` Juri Lelli
2019-08-08 10:31           ` Peter Zijlstra
2019-08-09  7:13             ` Juri Lelli
2019-08-08  6:59   ` Juri Lelli
2019-08-09  9:17   ` Dietmar Eggemann
2019-08-09 12:16     ` Juri Lelli
2019-07-26 14:54 ` [RFC][PATCH 13/13] sched/fair: Add trivial fair server Peter Zijlstra
2019-07-26 20:01 ` [RFC][PATCH 00/13] SCHED_DEADLINE server infrastructure luca abeni
2019-09-03 14:27 ` Alessio Balsini
2019-09-04 10:50   ` Juri Lelli
2019-09-04 11:32     ` Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190726161357.755285526@infradead.org \
    --to=peterz@infradead.org \
    --cc=balsini@android.com \
    --cc=bristot@redhat.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=dvyukov@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luca.abeni@santannapisa.it \
    --cc=mingo@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=vpillai@digitalocean.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git