LKML Archive on lore.kernel.org
 help / color / Atom feed
From: "tip-bot2 for Peter Zijlstra" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>,
	Don Hiatt <dhiatt@digitalocean.com>,
	Hongyu Ning <hongyu.ning@linux.intel.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	x86@kernel.org, linux-kernel@vger.kernel.org
Subject: [tip: sched/core] sched: Trivial forced-newidle balancer
Date: Wed, 12 May 2021 10:28:22 -0000
Message-ID: <162081530256.29796.9269859141153310893.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20210422123308.800048269@infradead.org>

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     d2dfa17bc7de67e99685c4d6557837bf801a102c
Gitweb:        https://git.kernel.org/tip/d2dfa17bc7de67e99685c4d6557837bf801a102c
Author:        Peter Zijlstra <peterz@infradead.org>
AuthorDate:    Tue, 17 Nov 2020 18:19:43 -05:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 12 May 2021 11:43:30 +02:00

sched: Trivial forced-newidle balancer

When a sibling is forced-idle to match the core-cookie; search for
matching tasks to fill the core.

rcu_read_unlock() can incur an infrequent deadlock in
sched_core_balance(). Fix this by using the RCU-sched flavor instead.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.800048269@infradead.org
---
 include/linux/sched.h |   1 +-
 kernel/sched/core.c   | 130 ++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/idle.c   |   1 +-
 kernel/sched/sched.h  |   6 ++-
 4 files changed, 137 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 45eedcc..9b822e3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -705,6 +705,7 @@ struct task_struct {
 #ifdef CONFIG_SCHED_CORE
 	struct rb_node			core_node;
 	unsigned long			core_cookie;
+	unsigned int			core_occupation;
 #endif
 
 #ifdef CONFIG_CGROUP_SCHED
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e45c1d2..b498888 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -204,6 +204,21 @@ static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
 	return __node_2_sc(node);
 }
 
+static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie)
+{
+	struct rb_node *node = &p->core_node;
+
+	node = rb_next(node);
+	if (!node)
+		return NULL;
+
+	p = container_of(node, struct task_struct, core_node);
+	if (p->core_cookie != cookie)
+		return NULL;
+
+	return p;
+}
+
 /*
  * Magic required such that:
  *
@@ -5389,8 +5404,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	const struct sched_class *class;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
+	int i, j, cpu, occ = 0;
 	bool need_sync;
-	int i, j, cpu;
 
 	if (!sched_core_enabled(rq))
 		return __pick_next_task(rq, prev, rf);
@@ -5512,6 +5527,9 @@ again:
 			if (!p)
 				continue;
 
+			if (!is_task_rq_idle(p))
+				occ++;
+
 			rq_i->core_pick = p;
 			if (rq_i->idle == p && rq_i->nr_running) {
 				rq->core->core_forceidle = true;
@@ -5543,6 +5561,7 @@ again:
 
 						cpu_rq(j)->core_pick = NULL;
 					}
+					occ = 1;
 					goto again;
 				}
 			}
@@ -5588,6 +5607,8 @@ again:
 		if (!(fi_before && rq->core->core_forceidle))
 			task_vruntime_update(rq_i, rq_i->core_pick, rq->core->core_forceidle);
 
+		rq_i->core_pick->core_occupation = occ;
+
 		if (i == cpu) {
 			rq_i->core_pick = NULL;
 			continue;
@@ -5609,6 +5630,113 @@ done:
 	return next;
 }
 
+static bool try_steal_cookie(int this, int that)
+{
+	struct rq *dst = cpu_rq(this), *src = cpu_rq(that);
+	struct task_struct *p;
+	unsigned long cookie;
+	bool success = false;
+
+	local_irq_disable();
+	double_rq_lock(dst, src);
+
+	cookie = dst->core->core_cookie;
+	if (!cookie)
+		goto unlock;
+
+	if (dst->curr != dst->idle)
+		goto unlock;
+
+	p = sched_core_find(src, cookie);
+	if (p == src->idle)
+		goto unlock;
+
+	do {
+		if (p == src->core_pick || p == src->curr)
+			goto next;
+
+		if (!cpumask_test_cpu(this, &p->cpus_mask))
+			goto next;
+
+		if (p->core_occupation > dst->idle->core_occupation)
+			goto next;
+
+		p->on_rq = TASK_ON_RQ_MIGRATING;
+		deactivate_task(src, p, 0);
+		set_task_cpu(p, this);
+		activate_task(dst, p, 0);
+		p->on_rq = TASK_ON_RQ_QUEUED;
+
+		resched_curr(dst);
+
+		success = true;
+		break;
+
+next:
+		p = sched_core_next(p, cookie);
+	} while (p);
+
+unlock:
+	double_rq_unlock(dst, src);
+	local_irq_enable();
+
+	return success;
+}
+
+static bool steal_cookie_task(int cpu, struct sched_domain *sd)
+{
+	int i;
+
+	for_each_cpu_wrap(i, sched_domain_span(sd), cpu) {
+		if (i == cpu)
+			continue;
+
+		if (need_resched())
+			break;
+
+		if (try_steal_cookie(cpu, i))
+			return true;
+	}
+
+	return false;
+}
+
+static void sched_core_balance(struct rq *rq)
+{
+	struct sched_domain *sd;
+	int cpu = cpu_of(rq);
+
+	preempt_disable();
+	rcu_read_lock();
+	raw_spin_rq_unlock_irq(rq);
+	for_each_domain(cpu, sd) {
+		if (need_resched())
+			break;
+
+		if (steal_cookie_task(cpu, sd))
+			break;
+	}
+	raw_spin_rq_lock_irq(rq);
+	rcu_read_unlock();
+	preempt_enable();
+}
+
+static DEFINE_PER_CPU(struct callback_head, core_balance_head);
+
+void queue_core_balance(struct rq *rq)
+{
+	if (!sched_core_enabled(rq))
+		return;
+
+	if (!rq->core->core_cookie)
+		return;
+
+	if (!rq->nr_running) /* not forced idle */
+		return;
+
+	queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance);
+}
+
 static inline void sched_core_cpu_starting(unsigned int cpu)
 {
 	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 43646e7..912b47a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -437,6 +437,7 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
 {
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
+	queue_core_balance(rq);
 }
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4a898ab..91ca1fe 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1170,6 +1170,8 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
 
 bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool fi);
 
+extern void queue_core_balance(struct rq *rq);
+
 #else /* !CONFIG_SCHED_CORE */
 
 static inline bool sched_core_enabled(struct rq *rq)
@@ -1192,6 +1194,10 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
 	return &rq->__lock;
 }
 
+static inline void queue_core_balance(struct rq *rq)
+{
+}
+
 #endif /* CONFIG_SCHED_CORE */
 
 static inline void lockdep_assert_rq_held(struct rq *rq)

  reply index

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-22 12:04 [PATCH 00/19] sched: Core Scheduling Peter Zijlstra
2021-04-22 12:05 ` [PATCH 01/19] sched/fair: Add a few assertions Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-05-13  8:56     ` Ning, Hongyu
2021-04-22 12:05 ` [PATCH 02/19] sched: Provide raw_spin_rq_*lock*() helpers Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 03/19] sched: Wrap rq::lock access Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 04/19] sched: Prepare for Core-wide rq->lock Peter Zijlstra
2021-04-24  1:22   ` Josh Don
2021-04-26  8:31     ` Peter Zijlstra
2021-04-26 22:21       ` Josh Don
2021-04-27 17:10         ` Don Hiatt
2021-04-27 23:35           ` Josh Don
2021-04-28  1:03             ` Aubrey Li
2021-04-28  6:05               ` Aubrey Li
2021-04-28 10:57                 ` Aubrey Li
2021-04-28 16:41                   ` Don Hiatt
2021-04-29 20:48                     ` Josh Don
2021-04-29 21:09                       ` Don Hiatt
2021-04-29 23:22                         ` Josh Don
2021-04-30 16:18                           ` Don Hiatt
2021-04-30  8:26                         ` Aubrey Li
2021-04-28 16:04             ` Don Hiatt
2021-04-27 23:30         ` Josh Don
2021-04-28  9:13           ` Peter Zijlstra
2021-04-28 10:35             ` Aubrey Li
2021-04-28 11:03               ` Peter Zijlstra
2021-04-28 14:18                 ` Paul E. McKenney
2021-04-29 20:11             ` Josh Don
2021-05-03 19:17               ` Peter Zijlstra
2021-04-28  7:13         ` Peter Zijlstra
2021-04-28  6:02   ` Aubrey Li
2021-04-29  8:03   ` Aubrey Li
2021-04-29 20:39     ` Josh Don
2021-04-30  8:20       ` Aubrey Li
2021-04-30  8:48         ` Josh Don
2021-04-30 14:15           ` Aubrey Li
2021-05-04  7:38       ` Peter Zijlstra
2021-05-05 16:20         ` Don Hiatt
2021-05-06 10:25           ` Peter Zijlstra
2021-05-07  9:50   ` [PATCH v2 " Peter Zijlstra
2021-05-08  8:07     ` Aubrey Li
2021-05-12  9:07       ` Peter Zijlstra
2021-04-22 12:05 ` [PATCH 05/19] sched: " Peter Zijlstra
2021-05-07  9:50   ` [PATCH v2 " Peter Zijlstra
2021-05-12 10:28     ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 06/19] sched: Optimize rq_lockp() usage Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 07/19] sched: Allow sched_core_put() from atomic context Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 08/19] sched: Introduce sched_class::pick_task() Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 09/19] sched: Basic tracking of matching tasks Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 10/19] sched: Add core wide task selection and scheduling Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 11/19] sched/fair: Fix forced idle sibling starvation corner case Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Vineeth Pillai
2021-04-22 12:05 ` [PATCH 12/19] sched: Fix priority inversion of cookied task with sibling Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Joel Fernandes (Google)
2021-04-22 12:05 ` [PATCH 13/19] sched/fair: Snapshot the min_vruntime of CPUs on force idle Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Joel Fernandes (Google)
2021-04-22 12:05 ` [PATCH 14/19] sched: Trivial forced-newidle balancer Peter Zijlstra
2021-05-12 10:28   ` tip-bot2 for Peter Zijlstra [this message]
2021-04-22 12:05 ` [PATCH 15/19] sched: Migration changes for core scheduling Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Aubrey Li
2021-04-22 12:05 ` [PATCH 16/19] sched: Trivial core scheduling cookie management Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 17/19] sched: Inherit task cookie on fork() Peter Zijlstra
2021-05-10 16:06   ` Joel Fernandes
2021-05-10 16:22     ` Chris Hyser
2021-05-10 20:47       ` Joel Fernandes
2021-05-10 21:38         ` Chris Hyser
2021-05-12  9:05           ` Peter Zijlstra
2021-05-12 20:20             ` Josh Don
2021-05-12 21:07               ` Don Hiatt
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2021-04-22 12:05 ` [PATCH 18/19] sched: prctl() core-scheduling interface Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Chris Hyser
2021-06-14 23:36   ` [PATCH 18/19] " Josh Don
2021-06-15 11:31     ` Joel Fernandes
2021-04-22 12:05 ` [PATCH 19/19] kselftest: Add test for core sched prctl interface Peter Zijlstra
2021-05-12 10:28   ` [tip: sched/core] " tip-bot2 for Chris Hyser
2021-04-22 16:43 ` [PATCH 00/19] sched: Core Scheduling Don Hiatt
2021-04-22 17:29   ` Peter Zijlstra
2021-04-30  6:47 ` Ning, Hongyu
2021-05-06 10:29   ` Peter Zijlstra
2021-05-06 12:53     ` Ning, Hongyu
2021-05-07 18:02 ` Joel Fernandes
2021-05-10 16:16 ` Vincent Guittot
2021-05-11  7:00   ` Vincent Guittot

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=162081530256.29796.9269859141153310893.tip-bot2@tip-bot2 \
    --to=tip-bot2@linutronix.de \
    --cc=dhiatt@digitalocean.com \
    --cc=hongyu.ning@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=vincent.guittot@linaro.org \
    --cc=x86@kernel.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

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
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git
	git clone --mirror https://lore.kernel.org/lkml/10 lkml/git/10.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