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, subhra.mazumdar@oracle.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 v3 08/16] sched: Rework pick_next_task() slow-path
Date: Wed, 29 May 2019 20:36:44 +0000 [thread overview]
Message-ID: <aa34d24b36547139248f32a30138791ac6c02bd6.1559129225.git.vpillai@digitalocean.com> (raw)
In-Reply-To: <cover.1559129225.git.vpillai@digitalocean.com>
In-Reply-To: <cover.1559129225.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 9dfa0c53deb3..b883c70674ba 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3363,7 +3363,7 @@ 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))
@@ -3372,14 +3372,19 @@ 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 45425f971eec..d3904168857a 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 8e3eb243fd9f..e65f2dfda77a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6979,7 +6979,7 @@ 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;
/*
@@ -7056,8 +7056,8 @@ 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);
@@ -7085,6 +7085,9 @@ 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 1b65a4c3683e..7ece8e820b5d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -388,7 +388,9 @@ 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 51ee87c5a28a..79f2e60516ef 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 4cbe2bef92e4..460dd04e76af 100644
--- 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,
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:[~2019-05-29 20:37 UTC|newest]
Thread overview: 161+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-29 20:36 [RFC PATCH v3 00/16] Core scheduling v3 Vineeth Remanan Pillai
2019-05-29 20:36 ` [RFC PATCH v3 01/16] stop_machine: Fix stop_cpus_in_progress ordering Vineeth Remanan Pillai
2019-08-08 10:54 ` [tip:sched/core] " tip-bot for Peter Zijlstra
2019-08-26 16:19 ` [RFC PATCH v3 01/16] " mark gross
2019-08-26 16:59 ` Peter Zijlstra
2019-05-29 20:36 ` [RFC PATCH v3 02/16] sched: Fix kerneldoc comment for ia64_set_curr_task Vineeth Remanan Pillai
2019-08-08 10:55 ` [tip:sched/core] " tip-bot for Peter Zijlstra
2019-08-26 16:20 ` [RFC PATCH v3 02/16] " mark gross
2019-05-29 20:36 ` [RFC PATCH v3 03/16] sched: Wrap rq::lock access Vineeth Remanan Pillai
2019-05-29 20:36 ` [RFC PATCH v3 04/16] sched/{rt,deadline}: Fix set_next_task vs pick_next_task Vineeth Remanan Pillai
2019-08-08 10:55 ` [tip:sched/core] " tip-bot for Peter Zijlstra
2019-05-29 20:36 ` [RFC PATCH v3 05/16] sched: Add task_struct pointer to sched_class::set_curr_task Vineeth Remanan Pillai
2019-08-08 10:57 ` [tip:sched/core] " tip-bot for Peter Zijlstra
2019-05-29 20:36 ` [RFC PATCH v3 06/16] sched/fair: Export newidle_balance() Vineeth Remanan Pillai
2019-08-08 10:58 ` [tip:sched/core] sched/fair: Expose newidle_balance() tip-bot for Peter Zijlstra
2019-05-29 20:36 ` [RFC PATCH v3 07/16] sched: Allow put_prev_task() to drop rq->lock Vineeth Remanan Pillai
2019-08-08 10:58 ` [tip:sched/core] " tip-bot for Peter Zijlstra
2019-08-26 16:51 ` [RFC PATCH v3 07/16] " mark gross
2019-05-29 20:36 ` Vineeth Remanan Pillai [this message]
2019-08-08 10:59 ` [tip:sched/core] sched: Rework pick_next_task() slow-path tip-bot for Peter Zijlstra
2019-08-26 17:01 ` [RFC PATCH v3 08/16] " mark gross
2019-05-29 20:36 ` [RFC PATCH v3 09/16] sched: Introduce sched_class::pick_task() Vineeth Remanan Pillai
2019-08-26 17:14 ` mark gross
2019-05-29 20:36 ` [RFC PATCH v3 10/16] sched: Core-wide rq->lock Vineeth Remanan Pillai
2019-05-31 11:08 ` Peter Zijlstra
2019-05-31 15:23 ` Vineeth Pillai
2019-05-29 20:36 ` [RFC PATCH v3 11/16] sched: Basic tracking of matching tasks Vineeth Remanan Pillai
2019-08-26 20:59 ` mark gross
2019-05-29 20:36 ` [RFC PATCH v3 12/16] sched: A quick and dirty cgroup tagging interface Vineeth Remanan Pillai
2019-05-29 20:36 ` [RFC PATCH v3 13/16] sched: Add core wide task selection and scheduling Vineeth Remanan Pillai
2019-06-07 23:36 ` Pawan Gupta
2019-05-29 20:36 ` [RFC PATCH v3 14/16] sched/fair: Add a few assertions Vineeth Remanan Pillai
2019-05-29 20:36 ` [RFC PATCH v3 15/16] sched: Trivial forced-newidle balancer Vineeth Remanan Pillai
2019-05-29 20:36 ` [RFC PATCH v3 16/16] sched: Debug bits Vineeth Remanan Pillai
2019-05-29 21:02 ` Peter Oskolkov
2019-05-30 14:04 ` [RFC PATCH v3 00/16] Core scheduling v3 Aubrey Li
2019-05-30 14:17 ` Julien Desfossez
2019-05-31 4:55 ` Aubrey Li
2019-05-31 3:01 ` Aaron Lu
2019-05-31 5:12 ` Aubrey Li
2019-05-31 6:09 ` Aaron Lu
2019-05-31 6:53 ` Aubrey Li
2019-05-31 7:44 ` Aaron Lu
2019-05-31 8:26 ` Aubrey Li
2019-05-31 21:08 ` Julien Desfossez
2019-06-06 15:26 ` Julien Desfossez
2019-06-12 1:52 ` Li, Aubrey
2019-06-12 16:06 ` Julien Desfossez
2019-06-12 16:33 ` Julien Desfossez
2019-06-13 0:03 ` Subhra Mazumdar
2019-06-13 3:22 ` Julien Desfossez
2019-06-17 2:51 ` Aubrey Li
2019-06-19 18:33 ` Julien Desfossez
2019-07-18 10:07 ` Aaron Lu
2019-07-18 23:27 ` Tim Chen
2019-07-19 5:52 ` Aaron Lu
2019-07-19 11:48 ` Aubrey Li
2019-07-19 18:33 ` Tim Chen
2019-07-22 10:26 ` Aubrey Li
2019-07-22 10:43 ` Aaron Lu
2019-07-23 2:52 ` Aubrey Li
2019-07-25 14:30 ` Aaron Lu
2019-07-25 14:31 ` [RFC PATCH 1/3] wrapper for cfs_rq->min_vruntime Aaron Lu
2019-07-25 14:32 ` [PATCH 2/3] core vruntime comparison Aaron Lu
2019-08-06 14:17 ` Peter Zijlstra
2019-07-25 14:33 ` [PATCH 3/3] temp hack to make tick based schedule happen Aaron Lu
2019-07-25 21:42 ` [RFC PATCH v3 00/16] Core scheduling v3 Li, Aubrey
2019-07-26 15:21 ` Julien Desfossez
2019-07-26 21:29 ` Tim Chen
2019-07-31 2:42 ` Li, Aubrey
2019-08-02 15:37 ` Julien Desfossez
2019-08-05 15:55 ` Tim Chen
2019-08-06 3:24 ` Aaron Lu
2019-08-06 6:56 ` Aubrey Li
2019-08-06 7:04 ` Aaron Lu
2019-08-06 12:24 ` Vineeth Remanan Pillai
2019-08-06 13:49 ` Aaron Lu
2019-08-06 16:14 ` Vineeth Remanan Pillai
2019-08-06 14:16 ` Peter Zijlstra
2019-08-06 15:53 ` Vineeth Remanan Pillai
2019-08-06 17:03 ` Tim Chen
2019-08-06 17:12 ` Peter Zijlstra
2019-08-06 21:19 ` Tim Chen
2019-08-08 6:47 ` Aaron Lu
2019-08-08 17:27 ` Tim Chen
2019-08-08 21:42 ` Tim Chen
2019-08-10 14:15 ` Aaron Lu
2019-08-12 15:38 ` Vineeth Remanan Pillai
2019-08-13 2:24 ` Aaron Lu
2019-08-08 12:55 ` Aaron Lu
2019-08-08 16:39 ` Tim Chen
2019-08-10 14:18 ` Aaron Lu
2019-08-05 20:09 ` Phil Auld
2019-08-06 13:54 ` Aaron Lu
2019-08-06 14:17 ` Phil Auld
2019-08-06 14:41 ` Aaron Lu
2019-08-06 14:55 ` Phil Auld
2019-08-07 8:58 ` Dario Faggioli
2019-08-07 17:10 ` Tim Chen
2019-08-15 16:09 ` Dario Faggioli
2019-08-16 2:33 ` Aaron Lu
2019-09-05 1:44 ` Julien Desfossez
2019-09-06 22:17 ` Tim Chen
2019-09-18 21:27 ` Tim Chen
2019-09-06 18:30 ` Tim Chen
2019-09-11 14:02 ` Aaron Lu
2019-09-11 16:19 ` Tim Chen
2019-09-11 16:47 ` Vineeth Remanan Pillai
2019-09-12 12:35 ` Aaron Lu
2019-09-12 17:29 ` Tim Chen
2019-09-13 14:15 ` Aaron Lu
2019-09-13 17:13 ` Tim Chen
2019-09-30 11:53 ` Vineeth Remanan Pillai
2019-10-02 20:48 ` Vineeth Remanan Pillai
2019-10-10 13:54 ` Aaron Lu
2019-10-10 14:29 ` Vineeth Remanan Pillai
2019-10-11 7:33 ` Aaron Lu
2019-10-11 11:32 ` Vineeth Remanan Pillai
2019-10-11 12:01 ` Aaron Lu
2019-10-11 12:10 ` Vineeth Remanan Pillai
2019-10-12 3:55 ` Aaron Lu
2019-10-13 12:44 ` Vineeth Remanan Pillai
2019-10-14 9:57 ` Aaron Lu
2019-10-21 12:30 ` Vineeth Remanan Pillai
2019-09-12 12:04 ` Aaron Lu
2019-09-12 17:05 ` Tim Chen
2019-09-13 13:57 ` Aaron Lu
2019-09-12 23:12 ` Aubrey Li
2019-09-15 14:14 ` Aaron Lu
2019-09-18 1:33 ` Aubrey Li
2019-09-18 20:40 ` Tim Chen
2019-09-18 22:16 ` Aubrey Li
2019-09-30 14:36 ` Vineeth Remanan Pillai
2019-10-29 20:40 ` Julien Desfossez
2019-11-01 21:42 ` Tim Chen
2019-10-29 9:11 ` Dario Faggioli
2019-10-29 9:15 ` Dario Faggioli
2019-10-29 9:16 ` Dario Faggioli
2019-10-29 9:17 ` Dario Faggioli
2019-10-29 9:18 ` Dario Faggioli
2019-10-29 9:18 ` Dario Faggioli
2019-10-29 9:19 ` Dario Faggioli
2019-10-29 9:20 ` Dario Faggioli
2019-10-29 20:34 ` Julien Desfossez
2019-11-15 16:30 ` Dario Faggioli
2019-09-25 2:40 ` Aubrey Li
2019-09-25 17:24 ` Tim Chen
2019-09-25 22:07 ` Aubrey Li
2019-09-30 15:22 ` Julien Desfossez
2019-08-27 21:14 ` Matthew Garrett
2019-08-27 21:50 ` Peter Zijlstra
2019-08-28 15:30 ` Phil Auld
2019-08-28 16:01 ` Peter Zijlstra
2019-08-28 16:37 ` Tim Chen
2019-08-29 14:30 ` Phil Auld
2019-08-29 14:38 ` Peter Zijlstra
2019-09-10 14:27 ` Julien Desfossez
2019-09-18 21:12 ` Tim Chen
2019-08-28 15:59 ` Tim Chen
2019-08-28 16:16 ` Peter Zijlstra
2019-08-27 23:24 ` Aubrey Li
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=aa34d24b36547139248f32a30138791ac6c02bd6.1559129225.git.vpillai@digitalocean.com \
--to=vpillai@digitalocean.com \
--cc=aaron.lwe@gmail.com \
--cc=aubrey.intel@gmail.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=subhra.mazumdar@oracle.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).