From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, tglx@linutronix.de, pjt@google.com,
tim.c.chen@linux.intel.com, torvalds@linux-foundation.org
Cc: linux-kernel@vger.kernel.org, subhra.mazumdar@oracle.com,
fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
"Peter Zijlstra (Intel)" <peterz@infradead.org>
Subject: [RFC][PATCH 08/16] sched: Rework pick_next_task() slow-path
Date: Mon, 18 Feb 2019 17:56:28 +0100 [thread overview]
Message-ID: <20190218173514.359026684@infradead.org> (raw)
In-Reply-To: 20190218165620.383905466@infradead.org
Avoid the RETRY_TASK case in the pick_next_task() slow path.
By doing the put_prev_task() early, we get the rt/deadline pull done,
and by testing rq->nr_running we know if we need newidle_balance().
This then gives a stable state to pick a task from.
Since the fast-path is fair only; it means the other classes will
always have pick_next_task(.prev=NULL, .rf=NULL) and we can simplify.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
kernel/sched/core.c | 19 ++++++++++++-------
kernel/sched/deadline.c | 30 ++----------------------------
kernel/sched/fair.c | 9 ++++++---
kernel/sched/idle.c | 4 +++-
kernel/sched/rt.c | 29 +----------------------------
kernel/sched/sched.h | 13 ++++++++-----
kernel/sched/stop_task.c | 3 ++-
7 files changed, 34 insertions(+), 73 deletions(-)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3360,7 +3360,7 @@ pick_next_task(struct rq *rq, struct tas
p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
- goto again;
+ goto restart;
/* Assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
@@ -3369,14 +3369,19 @@ pick_next_task(struct rq *rq, struct tas
return p;
}
-again:
+restart:
+ /*
+ * Ensure that we put DL/RT tasks before the pick loop, such that they
+ * can PULL higher prio tasks when we lower the RQ 'priority'.
+ */
+ prev->sched_class->put_prev_task(rq, prev, rf);
+ if (!rq->nr_running)
+ newidle_balance(rq, rf);
+
for_each_class(class) {
- p = class->pick_next_task(rq, prev, rf);
- if (p) {
- if (unlikely(p == RETRY_TASK))
- goto again;
+ p = class->pick_next_task(rq, NULL, NULL);
+ if (p)
return p;
- }
}
/* The idle class should always have a runnable task: */
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1730,39 +1730,13 @@ pick_next_task_dl(struct rq *rq, struct
struct task_struct *p;
struct dl_rq *dl_rq;
- dl_rq = &rq->dl;
-
- if (need_pull_dl_task(rq, prev)) {
- /*
- * 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're
- * being very careful to re-start the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_dl_task(rq);
- rq_repin_lock(rq, rf);
- /*
- * pull_dl_task() can drop (and re-acquire) rq->lock; this
- * means a stop task can slip in, in which case we need to
- * re-start task selection.
- */
- if (rq->stop && task_on_rq_queued(rq->stop))
- return RETRY_TASK;
- }
+ WARN_ON_ONCE(prev || rf);
- /*
- * When prev is DL, we may throttle it in put_prev_task().
- * So, we update time before we check for dl_nr_running.
- */
- if (prev->sched_class == &dl_sched_class)
- update_curr_dl(rq);
+ dl_rq = &rq->dl;
if (unlikely(!dl_rq->dl_nr_running))
return NULL;
- put_prev_task(rq, prev);
-
dl_se = pick_next_dl_entity(rq, dl_rq);
BUG_ON(!dl_se);
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6949,7 +6949,7 @@ pick_next_task_fair(struct rq *rq, struc
goto idle;
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (prev->sched_class != &fair_sched_class)
+ if (!prev || prev->sched_class != &fair_sched_class)
goto simple;
/*
@@ -7026,8 +7026,8 @@ pick_next_task_fair(struct rq *rq, struc
goto done;
simple:
#endif
-
- put_prev_task(rq, prev);
+ if (prev)
+ put_prev_task(rq, prev);
do {
se = pick_next_entity(cfs_rq, NULL);
@@ -7055,6 +7055,9 @@ done: __maybe_unused;
return p;
idle:
+ if (!rf)
+ return NULL;
+
new_tasks = newidle_balance(rq, rf);
/*
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -388,7 +388,9 @@ pick_next_task_idle(struct rq *rq, struc
{
struct task_struct *next = rq->idle;
- put_prev_task(rq, prev);
+ if (prev)
+ put_prev_task(rq, prev);
+
set_next_task_idle(rq, next);
return next;
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1554,38 +1554,11 @@ pick_next_task_rt(struct rq *rq, struct
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
- if (need_pull_rt_task(rq, prev)) {
- /*
- * 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're
- * being very careful to re-start the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_rt_task(rq);
- rq_repin_lock(rq, rf);
- /*
- * pull_rt_task() can drop (and re-acquire) rq->lock; this
- * means a dl or stop task can slip in, in which case we need
- * to re-start task selection.
- */
- if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
- rq->dl.dl_nr_running))
- return RETRY_TASK;
- }
-
- /*
- * We may dequeue prev's rt_rq in put_prev_task().
- * So, we update time before rt_queued check.
- */
- if (prev->sched_class == &rt_sched_class)
- update_curr_rt(rq);
+ WARN_ON_ONCE(prev || rf);
if (!rt_rq->rt_queued)
return NULL;
- put_prev_task(rq, prev);
-
p = _pick_next_task_rt(rq);
set_next_task_rt(rq, p);
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1665,12 +1665,15 @@ struct sched_class {
void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
/*
- * It is the responsibility of the pick_next_task() method that will
- * return the next task to call put_prev_task() on the @prev task or
- * something equivalent.
+ * Both @prev and @rf are optional and may be NULL, in which case the
+ * caller must already have invoked put_prev_task(rq, prev, rf).
*
- * May return RETRY_TASK when it finds a higher prio class has runnable
- * tasks.
+ * Otherwise it is the responsibility of the pick_next_task() to call
+ * put_prev_task() on the @prev task or something equivalent, IFF it
+ * returns a next task.
+ *
+ * In that case (@rf != NULL) it may return RETRY_TASK when it finds a
+ * higher prio class has runnable tasks.
*/
struct task_struct * (*pick_next_task)(struct rq *rq,
struct task_struct *prev,
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -33,10 +33,11 @@ pick_next_task_stop(struct rq *rq, struc
{
struct task_struct *stop = rq->stop;
+ WARN_ON_ONCE(prev || rf);
+
if (!stop || !task_on_rq_queued(stop))
return NULL;
- put_prev_task(rq, prev);
set_next_task_stop(rq, stop);
return stop;
next prev parent reply other threads:[~2019-02-18 17:41 UTC|newest]
Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-18 16:56 [RFC][PATCH 00/16] sched: Core scheduling Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 01/16] stop_machine: Fix stop_cpus_in_progress ordering Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 02/16] sched: Fix kerneldoc comment for ia64_set_curr_task Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 03/16] sched: Wrap rq::lock access Peter Zijlstra
2019-02-19 16:13 ` Phil Auld
2019-02-19 16:22 ` Peter Zijlstra
2019-02-19 16:37 ` Phil Auld
2019-03-18 15:41 ` Julien Desfossez
2019-03-20 2:29 ` Subhra Mazumdar
2019-03-21 21:20 ` Julien Desfossez
2019-03-22 13:34 ` Peter Zijlstra
2019-03-22 20:59 ` Julien Desfossez
2019-03-23 0:06 ` Subhra Mazumdar
2019-03-27 1:02 ` Subhra Mazumdar
2019-03-29 13:35 ` Julien Desfossez
2019-03-29 22:23 ` Subhra Mazumdar
2019-04-01 21:35 ` Subhra Mazumdar
2019-04-03 20:16 ` Julien Desfossez
2019-04-05 1:30 ` Subhra Mazumdar
2019-04-02 7:42 ` Peter Zijlstra
2019-03-22 23:28 ` Tim Chen
2019-03-22 23:44 ` Tim Chen
2019-02-18 16:56 ` [RFC][PATCH 04/16] sched/{rt,deadline}: Fix set_next_task vs pick_next_task Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 05/16] sched: Add task_struct pointer to sched_class::set_curr_task Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 06/16] sched/fair: Export newidle_balance() Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 07/16] sched: Allow put_prev_task() to drop rq->lock Peter Zijlstra
2019-02-18 16:56 ` Peter Zijlstra [this message]
2019-02-18 16:56 ` [RFC][PATCH 09/16] sched: Introduce sched_class::pick_task() Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 10/16] sched: Core-wide rq->lock Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 11/16] sched: Basic tracking of matching tasks Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 12/16] sched: A quick and dirty cgroup tagging interface Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 13/16] sched: Add core wide task selection and scheduling Peter Zijlstra
[not found] ` <20190402064612.GA46500@aaronlu>
2019-04-02 8:28 ` Peter Zijlstra
2019-04-02 13:20 ` Aaron Lu
2019-04-05 14:55 ` Aaron Lu
2019-04-09 18:09 ` Tim Chen
2019-04-10 4:36 ` Aaron Lu
2019-04-10 14:18 ` Aubrey Li
2019-04-11 2:11 ` Aaron Lu
2019-04-10 14:44 ` Peter Zijlstra
2019-04-11 3:05 ` Aaron Lu
2019-04-11 9:19 ` Peter Zijlstra
2019-04-10 8:06 ` Peter Zijlstra
2019-04-10 19:58 ` Vineeth Remanan Pillai
2019-04-15 16:59 ` Julien Desfossez
2019-04-16 13:43 ` Aaron Lu
2019-04-09 18:38 ` Julien Desfossez
2019-04-10 15:01 ` Peter Zijlstra
2019-04-11 0:11 ` Subhra Mazumdar
2019-04-19 8:40 ` Ingo Molnar
2019-04-19 23:16 ` Subhra Mazumdar
2019-02-18 16:56 ` [RFC][PATCH 14/16] sched/fair: Add a few assertions Peter Zijlstra
2019-02-18 16:56 ` [RFC][PATCH 15/16] sched: Trivial forced-newidle balancer Peter Zijlstra
2019-02-21 16:19 ` Valentin Schneider
2019-02-21 16:41 ` Peter Zijlstra
2019-02-21 16:47 ` Peter Zijlstra
2019-02-21 18:28 ` Valentin Schneider
2019-04-04 8:31 ` Aubrey Li
2019-04-06 1:36 ` Aubrey Li
2019-02-18 16:56 ` [RFC][PATCH 16/16] sched: Debug bits Peter Zijlstra
2019-02-18 17:49 ` [RFC][PATCH 00/16] sched: Core scheduling Linus Torvalds
2019-02-18 20:40 ` Peter Zijlstra
2019-02-19 0:29 ` Linus Torvalds
2019-02-19 15:15 ` Ingo Molnar
2019-02-22 12:17 ` Paolo Bonzini
2019-02-22 14:20 ` Peter Zijlstra
2019-02-22 19:26 ` Tim Chen
2019-02-26 8:26 ` Aubrey Li
2019-02-27 7:54 ` Aubrey Li
2019-02-21 2:53 ` Subhra Mazumdar
2019-02-21 14:03 ` Peter Zijlstra
2019-02-21 18:44 ` Subhra Mazumdar
2019-02-22 0:34 ` Subhra Mazumdar
2019-02-22 12:45 ` Mel Gorman
2019-02-22 16:10 ` Mel Gorman
2019-03-08 19:44 ` Subhra Mazumdar
2019-03-11 4:23 ` Aubrey Li
2019-03-11 18:34 ` Subhra Mazumdar
2019-03-11 23:33 ` Subhra Mazumdar
2019-03-12 0:20 ` Greg Kerr
2019-03-12 0:47 ` Subhra Mazumdar
2019-03-12 7:33 ` Aaron Lu
2019-03-12 7:45 ` Aubrey Li
2019-03-13 5:55 ` Aubrey Li
2019-03-14 0:35 ` Tim Chen
2019-03-14 5:30 ` Aubrey Li
2019-03-14 6:07 ` Li, Aubrey
2019-03-18 6:56 ` Aubrey Li
2019-03-12 19:07 ` Pawan Gupta
2019-03-26 7:32 ` Aaron Lu
2019-03-26 7:56 ` Aaron Lu
2019-02-19 22:07 ` Greg Kerr
2019-02-20 9:42 ` Peter Zijlstra
2019-02-20 18:33 ` Greg Kerr
2019-02-22 14:10 ` Peter Zijlstra
2019-03-07 22:06 ` Paolo Bonzini
2019-02-20 18:43 ` Subhra Mazumdar
2019-03-01 2:54 ` Subhra Mazumdar
2019-03-14 15:28 ` Julien Desfossez
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=20190218173514.359026684@infradead.org \
--to=peterz@infradead.org \
--cc=fweisbec@gmail.com \
--cc=keescook@chromium.org \
--cc=kerrnel@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=pjt@google.com \
--cc=subhra.mazumdar@oracle.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).