[PATCH 33/34] sched_ext: Add rhashtable lookup for sub-schedulers

[Tejun Heo]

Add rhashtable-based lookup for sub-schedulers indexed by cgroup_id to
enable efficient scheduler discovery in preparation for multiple scheduler
support. The hash table allows quick lookup of the appropriate scheduler
instance when processing tasks from different cgroups.

This extends scx_link_sched() to register sub-schedulers in the hash table
and scx_unlink_sched() to remove them. A new scx_find_sub_sched() function
provides the lookup interface.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
---
 kernel/sched/ext.c          | 50 +++++++++++++++++++++++++++++++++----
 kernel/sched/ext_internal.h |  2 ++
 2 files changed, 47 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5d08971b0832..eccb67a78e90 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -27,6 +27,16 @@ struct scx_sched __rcu *scx_root;
  */
 static LIST_HEAD(scx_sched_all);
 
+#ifdef CONFIG_EXT_SUB_SCHED
+static const struct rhashtable_params scx_sched_hash_params = {
+	.key_len		= sizeof_field(struct scx_sched, ops.sub_cgroup_id),
+	.key_offset		= offsetof(struct scx_sched, ops.sub_cgroup_id),
+	.head_offset		= offsetof(struct scx_sched, hash_node),
+};
+
+static struct rhashtable scx_sched_hash;
+#endif
+
 /*
  * During exit, a task may schedule after losing its PIDs. When disabling the
  * BPF scheduler, we need to be able to iterate tasks in every state to
@@ -285,6 +295,12 @@ static struct scx_sched *scx_next_descendant_pre(struct scx_sched *pos,
 	return NULL;
 }
 
+static struct scx_sched *scx_find_sub_sched(u64 cgroup_id)
+{
+	return rhashtable_lookup(&scx_sched_hash, &cgroup_id,
+				 scx_sched_hash_params);
+}
+
 static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch)
 {
 	rcu_assign_pointer(p->scx.sched, sch);
@@ -292,6 +308,7 @@ static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch)
 #else	/* CONFIG_EXT_SUB_SCHED */
 static struct scx_sched *scx_parent(struct scx_sched *sch) { return NULL; }
 static struct scx_sched *scx_next_descendant_pre(struct scx_sched *pos, struct scx_sched *root) { return pos ? NULL : root; }
+static struct scx_sched *scx_find_sub_sched(u64 cgroup_id) { return NULL; }
 static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch) {}
 #endif	/* CONFIG_EXT_SUB_SCHED */
 
@@ -4806,26 +4823,41 @@ static void refresh_watchdog(void)
 		cancel_delayed_work_sync(&scx_watchdog_work);
 }
 
-static void scx_link_sched(struct scx_sched *sch)
+static s32 scx_link_sched(struct scx_sched *sch)
 {
 	scoped_guard(raw_spinlock_irq, &scx_sched_lock) {
 #ifdef CONFIG_EXT_SUB_SCHED
 		struct scx_sched *parent = scx_parent(sch);
-		if (parent)
+		s32 ret;
+
+		if (parent) {
+			ret = rhashtable_lookup_insert_fast(&scx_sched_hash,
+					&sch->hash_node, scx_sched_hash_params);
+			if (ret) {
+				scx_error(sch, "failed to insert into scx_sched_hash (%d)", ret);
+				return ret;
+			}
+
 			list_add_tail(&sch->sibling, &parent->children);
+		}
 #endif	/* CONFIG_EXT_SUB_SCHED */
+
 		list_add_tail_rcu(&sch->all, &scx_sched_all);
 	}
 
 	refresh_watchdog();
+	return 0;
 }
 
 static void scx_unlink_sched(struct scx_sched *sch)
 {
 	scoped_guard(raw_spinlock_irq, &scx_sched_lock) {
 #ifdef CONFIG_EXT_SUB_SCHED
-		if (scx_parent(sch))
+		if (scx_parent(sch)) {
+			rhashtable_remove_fast(&scx_sched_hash, &sch->hash_node,
+					       scx_sched_hash_params);
 			list_del_init(&sch->sibling);
+		}
 #endif	/* CONFIG_EXT_SUB_SCHED */
 		list_del_rcu(&sch->all);
 	}
@@ -5873,7 +5905,9 @@ static s32 scx_root_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	 */
 	rcu_assign_pointer(scx_root, sch);
 
-	scx_link_sched(sch);
+	ret = scx_link_sched(sch);
+	if (ret)
+		goto err_disable;
 
 	scx_idle_enable(ops);
 
@@ -6134,7 +6168,9 @@ static s32 scx_sub_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		goto out_put_cgrp;
 	}
 
-	scx_link_sched(sch);
+	ret = scx_link_sched(sch);
+	if (ret)
+		goto err_disable;
 
 	if (sch->level >= SCX_SUB_MAX_DEPTH) {
 		scx_error(sch, "max nesting depth %d violated",
@@ -6925,6 +6961,10 @@ void __init init_sched_ext_class(void)
 	register_sysrq_key('S', &sysrq_sched_ext_reset_op);
 	register_sysrq_key('D', &sysrq_sched_ext_dump_op);
 	INIT_DELAYED_WORK(&scx_watchdog_work, scx_watchdog_workfn);
+
+#ifdef CONFIG_EXT_SUB_SCHED
+	BUG_ON(rhashtable_init(&scx_sched_hash, &scx_sched_hash_params));
+#endif	/* CONFIG_EXT_SUB_SCHED */
 }
 
 
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 99c8a304b726..52ef7f68d298 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1014,6 +1014,8 @@ struct scx_sched {
 	struct list_head	all;
 
 #ifdef CONFIG_EXT_SUB_SCHED
+	struct rhash_head	hash_node;
+
 	struct list_head	children;
 	struct list_head	sibling;
 	struct cgroup		*cgrp;
-- 
2.53.0