[RFC 57/60] cosched: Add sysfs interface to configure coscheduling on cgroups

[Jan H. SchÃnherr]

Add the sysfs interface to configure the scheduling domain hierarchy
level at which coscheduling should happen for a cgroup. By default,
task groups are created with a value of zero corresponding to regular
task groups without any coscheduling.

Note, that you cannot specify a value that goes beyond that of the
root task group. The value for the root task group cannot be configured
via this interface. It has to be configured with a command line
argument, which will be added later.

The function sdrq_update_root() will be filled in a follow-up commit.

Signed-off-by: Jan H. SchÃnherr <jschoenh@xxxxxxxxx>
---
 kernel/sched/core.c    | 44 +++++++++++++++++++++++++++++++++++++++++
 kernel/sched/cosched.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h   |  4 ++++
 3 files changed, 101 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 75de3b83a8c6..ad2ff9bc535c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6336,6 +6336,9 @@ void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
 
+	/* Don't let offlining/destruction worry about coscheduling aspects */
+	cosched_set_scheduled(tg, 0);
+
 	/* End participation in shares distribution: */
 	unregister_fair_sched_group(tg);
 
@@ -6529,7 +6532,33 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
 
 	return (u64) scale_load_down(tg->shares);
 }
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+#ifdef CONFIG_COSCHEDULING
+static int cpu_scheduled_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype,
+				   u64 val)
+{
+	struct task_group *tg = css_tg(css);
+
+	if (tg == &root_task_group)
+		return -EACCES;
+
+	if (val > root_task_group.scheduled)
+		return -EINVAL;
+
+	cosched_set_scheduled(tg, val);
+	return 0;
+}
 
+static u64 cpu_scheduled_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct task_group *tg = css_tg(css);
+
+	return cosched_get_scheduled(tg);
+}
+#endif /* !CONFIG_COSCHEDULING */
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_CFS_BANDWIDTH
 static DEFINE_MUTEX(cfs_constraints_mutex);
 
@@ -6825,6 +6854,13 @@ static struct cftype cpu_legacy_files[] = {
 		.write_u64 = cpu_shares_write_u64,
 	},
 #endif
+#ifdef CONFIG_COSCHEDULING
+	{
+		.name = "scheduled",
+		.read_u64 = cpu_scheduled_read_u64,
+		.write_u64 = cpu_scheduled_write_u64,
+	},
+#endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.name = "cfs_quota_us",
@@ -7012,6 +7048,14 @@ static struct cftype cpu_files[] = {
 		.write_s64 = cpu_weight_nice_write_s64,
 	},
 #endif
+#ifdef CONFIG_COSCHEDULING
+	/* FIXME: This is not conform to cgroup-v2 conventions. */
+	{
+		.name = "scheduled",
+		.read_u64 = cpu_scheduled_read_u64,
+		.write_u64 = cpu_scheduled_write_u64,
+	},
+#endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.name = "max",
diff --git a/kernel/sched/cosched.c b/kernel/sched/cosched.c
index f2d51079b3db..7c8b8c8d2814 100644
--- a/kernel/sched/cosched.c
+++ b/kernel/sched/cosched.c
@@ -515,6 +515,59 @@ void cosched_offline_group(struct task_group *tg)
 		list_del_rcu(&cfs->sdrq.tg_siblings);
 }
 
+static void sdrq_update_root(struct sdrq *sdrq)
+{
+	/* TBD */
+}
+
+void cosched_set_scheduled(struct task_group *tg, int level)
+{
+	struct cfs_rq *cfs_rq;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&tg->lock, flags);
+
+	/*
+	 * Update the is_root-fields of all hierarchical CFS runqueues in this
+	 * task group. To avoid repetitive enqueues and dequeues on every level
+	 * change, we chose pre- or post-order traversal.
+	 */
+	if (level > tg->scheduled) {
+		/*
+		 * roots move upwards: start reconfiguration at the top, so
+		 * that everything is dequeued/enqueued only when we reach
+		 * the previous scheduling level.
+		 */
+		tg->scheduled = level;
+		taskgroup_for_each_cfsrq_topdown(tg, cfs_rq)
+			sdrq_update_root(&cfs_rq->sdrq);
+	}
+	if (level < tg->scheduled) {
+		/*
+		 * roots move downwards: start reconfiguration at the bottom,
+		 * so that we do the dequeuing/enqueuing immediately, when we
+		 * reach the new scheduling level.
+		 */
+		tg->scheduled = level;
+		taskgroup_for_each_cfsrq(tg, cfs_rq)
+			sdrq_update_root(&cfs_rq->sdrq);
+	}
+
+	raw_spin_unlock_irqrestore(&tg->lock, flags);
+}
+
+int cosched_get_scheduled(struct task_group *tg)
+{
+	unsigned long flags;
+	int level;
+
+	raw_spin_lock_irqsave(&tg->lock, flags);
+	level = tg->scheduled;
+	raw_spin_unlock_irqrestore(&tg->lock, flags);
+
+	return level;
+}
+
 /*****************************************************************************
  * Locking related functions
  *****************************************************************************/
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f6146feb7e55..e257451e05a5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1212,6 +1212,8 @@ void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs,
 		       struct cfs_rq *sd_parent, struct cfs_rq *tg_parent);
 void cosched_online_group(struct task_group *tg);
 void cosched_offline_group(struct task_group *tg);
+void cosched_set_scheduled(struct task_group *tg, int level);
+int cosched_get_scheduled(struct task_group *tg);
 struct rq *rq_lock_owned(struct rq *rq, struct rq_owner_flags *orf);
 void rq_unlock_owned(struct rq *rq, struct rq_owner_flags *orf);
 void rq_chain_init(struct rq_chain *rc, struct rq *rq);
@@ -1226,6 +1228,8 @@ static inline void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs,
 				     struct cfs_rq *tg_parent) { }
 static inline void cosched_online_group(struct task_group *tg) { }
 static inline void cosched_offline_group(struct task_group *tg) { }
+static inline void cosched_set_scheduled(struct task_group *tg, int level) { }
+static inline int cosched_get_scheduled(struct task_group *tg) { return 0; }
 static inline struct rq *rq_lock_owned(struct rq *rq, struct rq_owner_flags *orf) { return rq; }
 static inline void rq_unlock_owned(struct rq *rq, struct rq_owner_flags *orf) { }
 static inline void rq_chain_init(struct rq_chain *rc, struct rq *rq) { }
-- 
2.9.3.1.gcba166c.dirty