[PATCH v8 -tip 03/26] sched: Core-wide rq->lock

["Joel Fernandes (Google)" <joel@joelfernandes.org>]

From: Peter Zijlstra <peterz@infradead.org>

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

Tested-by: Julien Desfossez <jdesfossez@digitalocean.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Julien Desfossez <jdesfossez@digitalocean.com>
Signed-off-by: Vineeth Remanan Pillai <vpillai@digitalocean.com>
---
 kernel/Kconfig.preempt |   6 +++
 kernel/sched/core.c    | 109 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h   |  31 ++++++++++++
 3 files changed, 146 insertions(+)

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index bf82259cff96..4488fbf4d3a8 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -80,3 +80,9 @@ config PREEMPT_COUNT
 config PREEMPTION
        bool
        select PREEMPT_COUNT
+
+config SCHED_CORE
+	bool "Core Scheduling for SMT"
+	default y
+	depends on SCHED_SMT
+
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 97181b3d12eb..cecbf91cb477 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,6 +74,70 @@ unsigned int sysctl_sched_rt_period = 1000000;
 
 __read_mostly int scheduler_running;
 
+#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 */
+
 /*
  * part of the period that we allow rt tasks to run in us.
  * default: 0.95s
@@ -4363,6 +4427,43 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	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;
+			init_sched_core_irq_work(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;
+		}
+	}
+
+	printk("core: %d -> %d\n", cpu, cpu_of(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.
  *
@@ -6963,6 +7064,9 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
+
+	sched_core_cpu_starting(cpu);
+
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -7193,6 +7297,11 @@ 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 54bfac702805..85c8472b5d00 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1048,6 +1048,12 @@ 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
@@ -1075,11 +1081,36 @@ 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);
 
-- 
2.29.0.rc1.297.gfa9743e501-goog