LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: joel@joelfernandes.org, chris.hyser@oracle.com,
	joshdon@google.com, mingo@kernel.org, vincent.guittot@linaro.org,
	valentin.schneider@arm.com, mgorman@suse.de
Cc: linux-kernel@vger.kernel.org, peterz@infradead.org, tglx@linutronix.de
Subject: [PATCH 05/19] sched: Core-wide rq->lock
Date: Thu, 22 Apr 2021 14:05:04 +0200
Message-ID: <20210422123308.256677625@infradead.org> (raw)
In-Reply-To: <20210422120459.447350175@infradead.org>

Introduce the basic infrastructure to have a core wide rq->lock.

This relies on the rq->__lock order being in increasing CPU number. It
is also constrained to SMT8 per lockdep (and SMT256 per preempt_count).

Luckily SMT8 is the max supported SMT count for Linux (Mips, Sparc and
Power are known to have this).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/Kconfig.preempt |    6 ++
 kernel/sched/core.c    |  139 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h   |   37 +++++++++++++
 3 files changed, 182 insertions(+)

--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -99,3 +99,9 @@ config PREEMPT_DYNAMIC
 
 	  Interesting if you want the same pre-built kernel should be used for
 	  both Server and Desktop workloads.
+
+config SCHED_CORE
+	bool "Core Scheduling for SMT"
+	default y
+	depends on SCHED_SMT
+
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -84,6 +84,103 @@ unsigned int sysctl_sched_rt_period = 10
 
 __read_mostly int scheduler_running;
 
+#ifdef CONFIG_SCHED_CORE
+
+DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);
+
+/*
+ * Magic required such that:
+ *
+ *	raw_spin_rq_lock(rq);
+ *	...
+ *	raw_spin_rq_unlock(rq);
+ *
+ * ends up locking and unlocking the _same_ lock, and all CPUs
+ * always agree on what rq has what lock.
+ *
+ * XXX entirely possible to selectively enable cores, don't bother for now.
+ */
+
+static DEFINE_MUTEX(sched_core_mutex);
+static int sched_core_count;
+static struct cpumask sched_core_mask;
+
+static void __sched_core_flip(bool enabled)
+{
+	int cpu, t, i;
+
+	cpus_read_lock();
+
+	/*
+	 * Toggle the online cores, one by one.
+	 */
+	cpumask_copy(&sched_core_mask, cpu_online_mask);
+	for_each_cpu(cpu, &sched_core_mask) {
+		const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+
+		i = 0;
+		local_irq_disable();
+		for_each_cpu(t, smt_mask) {
+			/* supports up to SMT8 */
+			raw_spin_lock_nested(&cpu_rq(t)->__lock, i++);
+		}
+
+		for_each_cpu(t, smt_mask)
+			cpu_rq(t)->core_enabled = enabled;
+
+		for_each_cpu(t, smt_mask)
+			raw_spin_unlock(&cpu_rq(t)->__lock);
+		local_irq_enable();
+
+		cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask);
+	}
+
+	/*
+	 * Toggle the offline CPUs.
+	 */
+	cpumask_copy(&sched_core_mask, cpu_possible_mask);
+	cpumask_andnot(&sched_core_mask, &sched_core_mask, cpu_online_mask);
+
+	for_each_cpu(cpu, &sched_core_mask)
+		cpu_rq(cpu)->core_enabled = enabled;
+
+	cpus_read_unlock();
+}
+
+static void __sched_core_enable(void)
+{
+	// XXX verify there are no cookie tasks (yet)
+
+	static_branch_enable(&__sched_core_enabled);
+	__sched_core_flip(true);
+}
+
+static void __sched_core_disable(void)
+{
+	// XXX verify there are no cookie tasks (left)
+
+	__sched_core_flip(false);
+	static_branch_disable(&__sched_core_enabled);
+}
+
+void sched_core_get(void)
+{
+	mutex_lock(&sched_core_mutex);
+	if (!sched_core_count++)
+		__sched_core_enable();
+	mutex_unlock(&sched_core_mutex);
+}
+
+void sched_core_put(void)
+{
+	mutex_lock(&sched_core_mutex);
+	if (!--sched_core_count)
+		__sched_core_disable();
+	mutex_unlock(&sched_core_mutex);
+}
+
+#endif /* CONFIG_SCHED_CORE */
+
 /*
  * part of the period that we allow rt tasks to run in us.
  * default: 0.95s
@@ -5042,6 +5139,40 @@ pick_next_task(struct rq *rq, struct tas
 	BUG();
 }
 
+#ifdef CONFIG_SCHED_CORE
+
+static inline void sched_core_cpu_starting(unsigned int cpu)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	struct rq *rq, *core_rq = NULL;
+	int i;
+
+	core_rq = cpu_rq(cpu)->core;
+
+	if (!core_rq) {
+		for_each_cpu(i, smt_mask) {
+			rq = cpu_rq(i);
+			if (rq->core && rq->core == rq)
+				core_rq = rq;
+		}
+
+		if (!core_rq)
+			core_rq = cpu_rq(cpu);
+
+		for_each_cpu(i, smt_mask) {
+			rq = cpu_rq(i);
+
+			WARN_ON_ONCE(rq->core && rq->core != core_rq);
+			rq->core = core_rq;
+		}
+	}
+}
+#else /* !CONFIG_SCHED_CORE */
+
+static inline void sched_core_cpu_starting(unsigned int cpu) {}
+
+#endif /* CONFIG_SCHED_CORE */
+
 /*
  * __schedule() is the main scheduler function.
  *
@@ -8006,6 +8137,7 @@ static void sched_rq_cpu_starting(unsign
 
 int sched_cpu_starting(unsigned int cpu)
 {
+	sched_core_cpu_starting(cpu);
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -8290,6 +8424,11 @@ void __init sched_init(void)
 #endif /* CONFIG_SMP */
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
+
+#ifdef CONFIG_SCHED_CORE
+		rq->core = NULL;
+		rq->core_enabled = 0;
+#endif
 	}
 
 	set_load_weight(&init_task, false);
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1075,6 +1075,12 @@ struct rq {
 #endif
 	unsigned int		push_busy;
 	struct cpu_stop_work	push_work;
+
+#ifdef CONFIG_SCHED_CORE
+	/* per rq */
+	struct rq		*core;
+	unsigned int		core_enabled;
+#endif
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1113,6 +1119,35 @@ static inline bool is_migration_disabled
 #endif
 }
 
+#ifdef CONFIG_SCHED_CORE
+
+DECLARE_STATIC_KEY_FALSE(__sched_core_enabled);
+
+static inline bool sched_core_enabled(struct rq *rq)
+{
+	return static_branch_unlikely(&__sched_core_enabled) && rq->core_enabled;
+}
+
+static inline bool sched_core_disabled(void)
+{
+	return !static_branch_unlikely(&__sched_core_enabled);
+}
+
+static inline raw_spinlock_t *rq_lockp(struct rq *rq)
+{
+	if (sched_core_enabled(rq))
+		return &rq->core->__lock;
+
+	return &rq->__lock;
+}
+
+#else /* !CONFIG_SCHED_CORE */
+
+static inline bool sched_core_enabled(struct rq *rq)
+{
+	return false;
+}
+
 static inline bool sched_core_disabled(void)
 {
 	return true;
@@ -1123,6 +1158,8 @@ static inline raw_spinlock_t *rq_lockp(s
 	return &rq->__lock;
 }
 
+#endif /* CONFIG_SCHED_CORE */
+
 static inline void lockdep_assert_rq_held(struct rq *rq)
 {
 	lockdep_assert_held(rq_lockp(rq));



  parent 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 ` Peter Zijlstra [this message]
2021-05-07  9:50   ` [PATCH v2 05/19] sched: " 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: sched/core] " tip-bot2 for Peter Zijlstra
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=20210422123308.256677625@infradead.org \
    --to=peterz@infradead.org \
    --cc=chris.hyser@oracle.com \
    --cc=joel@joelfernandes.org \
    --cc=joshdon@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.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