From: Vineeth Remanan Pillai <vpillai@digitalocean.com>
To: Nishanth Aravamudan <naravamudan@digitalocean.com>,
Julien Desfossez <jdesfossez@digitalocean.com>,
Peter Zijlstra <peterz@infradead.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
mingo@kernel.org, tglx@linutronix.de, pjt@google.com,
torvalds@linux-foundation.org
Cc: linux-kernel@vger.kernel.org, Dario Faggioli <dfaggioli@suse.com>,
fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
Phil Auld <pauld@redhat.com>, Aaron Lu <aaron.lwe@gmail.com>,
Aubrey Li <aubrey.intel@gmail.com>,
Valentin Schneider <valentin.schneider@arm.com>,
Mel Gorman <mgorman@techsingularity.net>,
Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
Paolo Bonzini <pbonzini@redhat.com>
Subject: [RFC PATCH v4 08/19] sched: Rework pick_next_task() slow-path
Date: Wed, 30 Oct 2019 18:33:21 +0000 [thread overview]
Message-ID: <13460d224a949977935be948d007f4e11938cabd.1572437285.git.vpillai@digitalocean.com> (raw)
In-Reply-To: <cover.1572437285.git.vpillai@digitalocean.com>
In-Reply-To: <cover.1572437285.git.vpillai@digitalocean.com>
From: Peter Zijlstra <peterz@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(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3fa7d37f2879..1f40211ff29a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3739,7 +3739,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
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))
@@ -3748,14 +3748,19 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
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: */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 416e06c97e98..0c7a51745813 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1729,39 +1729,13 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
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);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ee57472d88e..850e235c9209 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6799,7 +6799,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
goto idle;
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (prev->sched_class != &fair_sched_class)
+ if (!prev || prev->sched_class != &fair_sched_class)
goto simple;
/*
@@ -6876,8 +6876,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
goto done;
simple:
#endif
-
- put_prev_task(rq, prev);
+ if (prev)
+ put_prev_task(rq, prev);
do {
se = pick_next_entity(cfs_rq, NULL);
@@ -6905,6 +6905,9 @@ done: __maybe_unused;
return p;
idle:
+ if (!rf)
+ return NULL;
+
new_tasks = newidle_balance(rq, rf);
/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 5848ae3d5210..5bb8d44fbff9 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -389,7 +389,9 @@ pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
{
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;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a7d9656f70b5..09c317a916aa 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1554,38 +1554,11 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
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);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8b86b24a3ccd..16c9654ac750 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1708,12 +1708,15 @@ 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,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 8f414018d5e0..7e1cee4e65b2 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -33,10 +33,11 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
{
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;
--
2.17.1
next prev parent reply other threads:[~2019-10-30 18:34 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-30 18:33 [RFC PATCH v4 00/19] Core scheduling v4 Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 01/19] stop_machine: Fix stop_cpus_in_progress ordering Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 02/19] sched: Fix kerneldoc comment for ia64_set_curr_task Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 03/19] sched: Wrap rq::lock access Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 04/19] sched/{rt,deadline}: Fix set_next_task vs pick_next_task Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 05/19] sched: Add task_struct pointer to sched_class::set_curr_task Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 06/19] sched/fair: Export newidle_balance() Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 07/19] sched: Allow put_prev_task() to drop rq->lock Vineeth Remanan Pillai
2019-10-30 18:33 ` Vineeth Remanan Pillai [this message]
2019-10-30 18:33 ` [RFC PATCH v4 09/19] sched: Introduce sched_class::pick_task() Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 10/19] sched: Core-wide rq->lock Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 11/19] sched: Basic tracking of matching tasks Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 12/19] sched: A quick and dirty cgroup tagging interface Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 13/19] sched: Add core wide task selection and scheduling Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 14/19] sched/fair: Add a few assertions Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 15/19] sched: Trivial forced-newidle balancer Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 16/19] sched: Debug bits Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 17/19] sched/fair: wrapper for cfs_rq->min_vruntime Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 18/19] sched/fair: core wide vruntime comparison Vineeth Remanan Pillai
2019-10-30 18:33 ` [RFC PATCH v4 19/19] sched/fair : Wake up forced idle siblings if needed Vineeth Remanan Pillai
2019-10-31 11:42 ` [RFC PATCH v4 00/19] Core scheduling v4 Li, Aubrey
2019-11-01 11:33 ` Li, Aubrey
2019-11-08 3:20 ` Li, Aubrey
2019-10-31 18:42 ` Phil Auld
2019-11-01 14:03 ` Vineeth Remanan Pillai
2019-11-01 16:35 ` Greg Kerr
2019-11-01 18:07 ` Dario Faggioli
2019-11-12 1:45 ` Dario Faggioli
2019-11-13 17:16 ` Tim Chen
2020-01-02 2:28 ` Aubrey Li
2020-01-10 23:19 ` Tim Chen
2019-11-11 19:10 ` Tim Chen
2020-01-14 1:12 ` Tim Chen
2020-01-14 15:40 ` Vineeth Remanan Pillai
2020-01-15 3:43 ` Li, Aubrey
2020-01-15 19:33 ` Tim Chen
2020-01-16 1:45 ` Aubrey Li
2020-01-17 16:00 ` Vineeth Remanan Pillai
2020-01-22 18:04 ` Gruza, Agata
2020-01-28 2:40 ` Dario Faggioli
[not found] ` <CANaguZDDpzrzdTmvjXvCmV2c+wBt6mXWSz4Vn-LJ-onc_Oj=yw@mail.gmail.com>
2020-02-01 15:31 ` Dario Faggioli
2020-02-06 0:28 ` Tim Chen
2020-02-06 22:37 ` Julien Desfossez
2020-02-12 23:07 ` Julien Desfossez
2020-02-13 18:37 ` Tim Chen
2020-02-14 6:10 ` Aubrey Li
[not found] ` <CANaguZC40mDHfL1H_9AA7H8cyd028t9PQVRqQ3kB4ha8R7hhqg@mail.gmail.com>
2020-02-15 6:01 ` Aubrey Li
[not found] ` <CANaguZBj_x_2+9KwbHCQScsmraC_mHdQB6uRqMTYMmvhBYfv2Q@mail.gmail.com>
2020-02-21 23:20 ` Julien Desfossez
2020-03-17 0:55 ` Joel Fernandes
2020-03-17 19:07 ` Tim Chen
2020-03-17 20:18 ` Tim Chen
2020-03-18 1:10 ` Joel Fernandes
2020-03-17 21:17 ` Thomas Gleixner
2020-03-17 21:58 ` Tim Chen
2020-03-18 1:03 ` Joel Fernandes
2020-03-18 2:30 ` Joel Fernandes
2020-03-18 0:52 ` Joel Fernandes
2020-03-18 11:53 ` Thomas Gleixner
2020-03-19 1:54 ` Joel Fernandes
2020-02-25 3:44 ` Aaron Lu
2020-02-25 5:32 ` Aubrey Li
2020-02-25 7:34 ` Aaron Lu
2020-02-25 10:40 ` Aubrey Li
2020-02-25 11:21 ` Aaron Lu
2020-02-25 13:41 ` Aubrey Li
[not found] ` <CANaguZD205ccu1V_2W-QuMRrJA9SjJ5ng1do4NCdLy8NDKKrbA@mail.gmail.com>
2020-02-26 3:13 ` Aaron Lu
2020-02-26 7:21 ` Aubrey Li
[not found] ` <CANaguZDQZg-Z6aNpeLcjQ-cGm3X8CQOkZ_hnJNUyqDRM=yVDFQ@mail.gmail.com>
2020-02-27 4:45 ` Aubrey Li
2020-02-28 23:55 ` Tim Chen
2020-03-03 14:59 ` Li, Aubrey
2020-03-03 23:54 ` Li, Aubrey
2020-03-05 4:33 ` Aaron Lu
2020-03-05 6:10 ` Li, Aubrey
2020-03-05 8:52 ` Aaron Lu
2020-02-27 2:04 ` Aaron Lu
2020-02-27 14:10 ` Phil Auld
2020-02-27 14:37 ` Aubrey Li
2020-02-28 2:54 ` Aaron Lu
2020-03-05 13:45 ` Aubrey Li
2020-03-06 2:41 ` Aaron Lu
2020-03-06 18:06 ` Tim Chen
2020-03-06 18:33 ` Phil Auld
2020-03-06 21:44 ` Tim Chen
2020-03-07 3:13 ` Aaron Lu
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=13460d224a949977935be948d007f4e11938cabd.1572437285.git.vpillai@digitalocean.com \
--to=vpillai@digitalocean.com \
--cc=aaron.lwe@gmail.com \
--cc=aubrey.intel@gmail.com \
--cc=dfaggioli@suse.com \
--cc=fweisbec@gmail.com \
--cc=jdesfossez@digitalocean.com \
--cc=keescook@chromium.org \
--cc=kerrnel@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@kernel.org \
--cc=naravamudan@digitalocean.com \
--cc=pauld@redhat.com \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
--cc=valentin.schneider@arm.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
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).