Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
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 v2 10/17] sched: Core-wide rq->lock
Date:   Tue, 23 Apr 2019 16:18:15 +0000
Message-Id: <5ecde9c230993481c45fd690e0cd896382fe953e.1556025155.git.vpillai@digitalocean.com>
In-Reply-To: <cover.1556025155.git.vpillai@digitalocean.com>
References: <cover.1556025155.git.vpillai@digitalocean.com>
In-Reply-To: <cover.1556025155.git.vpillai@digitalocean.com>
References: <cover.1556025155.git.vpillai@digitalocean.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Peter Zijlstra (Intel) <peterz@infradead.org>

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

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/Kconfig.preempt |  7 +++-
 kernel/sched/core.c    | 91 ++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h   | 31 ++++++++++++++
 3 files changed, 128 insertions(+), 1 deletion(-)

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 0fee5fe6c899..02fe0bf26676 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -57,4 +57,9 @@ config PREEMPT
 endchoice
 
 config PREEMPT_COUNT
-       bool
+	bool
+
+config SCHED_CORE
+	bool
+	default y
+	depends on SCHED_SMT
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b883c70674ba..2f559d706b8e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -60,6 +60,70 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+#ifdef CONFIG_SCHED_CORE
+
+DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);
+
+/*
+ * The static-key + stop-machine variable are needed such that:
+ *
+ *	spin_lock(rq_lockp(rq));
+ *	...
+ *	spin_unlock(rq_lockp(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 int __sched_core_stopper(void *data)
+{
+	bool enabled = !!(unsigned long)data;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		cpu_rq(cpu)->core_enabled = enabled;
+
+	return 0;
+}
+
+static DEFINE_MUTEX(sched_core_mutex);
+static int sched_core_count;
+
+static void __sched_core_enable(void)
+{
+	// XXX verify there are no cookie tasks (yet)
+
+	static_branch_enable(&__sched_core_enabled);
+	stop_machine(__sched_core_stopper, (void *)true, NULL);
+}
+
+static void __sched_core_disable(void)
+{
+	// XXX verify there are no cookie tasks (left)
+
+	stop_machine(__sched_core_stopper, (void *)false, NULL);
+	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 */
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -5865,6 +5929,28 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
+#ifdef CONFIG_SCHED_CORE
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	struct rq *rq, *core_rq = NULL;
+	int i;
+
+	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;
+	}
+#endif /* CONFIG_SCHED_CORE */
+
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -6091,6 +6177,11 @@ 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);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a024dd80eeb3..eb38063221d0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -952,6 +952,12 @@ struct rq {
 	/* Must be inspected within a rcu lock section */
 	struct cpuidle_state	*idle_state;
 #endif
+
+#ifdef CONFIG_SCHED_CORE
+	/* per rq */
+	struct rq		*core;
+	unsigned int		core_enabled;
+#endif
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -979,11 +985,36 @@ static inline int cpu_of(struct rq *rq)
 #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 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 raw_spinlock_t *rq_lockp(struct rq *rq)
 {
 	return &rq->__lock;
 }
 
+#endif /* CONFIG_SCHED_CORE */
+
 #ifdef CONFIG_SCHED_SMT
 extern void __update_idle_core(struct rq *rq);
 
-- 
2.17.1