[PATCH 06/11] sched_ext: Add a DL server for sched_ext tasks

[Andrea Righi <arighi@nvidia.com>]

sched_ext currently suffers starvation due to RT. The same workload when
converted to EXT can get zero runtime if RT is 100% running, causing EXT
processes to stall. Fix it by adding a DL server for EXT.

A kselftest is also provided later to verify:

 # ./runner -t rt_stall
 ===== START =====
 TEST: rt_stall
 DESCRIPTION: Verify that RT tasks cannot stall SCHED_EXT tasks
 OUTPUT:
 # Runtime of EXT task (PID 23338) is 0.250000 seconds
 # Runtime of RT task (PID 23339) is 4.750000 seconds
 # EXT task got 5.00% of total runtime
 ok 1 PASS: EXT task got more than 4.00% of runtime
 =====  END  =====

v3: - clarify that fair is not the only dl_server (Juri Lelli)
    - remove explicit stop to reduce timer reprogramming overhead
      (Juri Lelli)
    - do not restart pick_task() when it's invoked by the dl_server
      (Tejun Heo)
    - depend on CONFIG_SCHED_CLASS_EXT (Andrea Righi)
v2: - drop ->balance() now that pick_task() has an rf argument
      (Andrea Righi)

Cc: Luigi De Matteis <ldematteis123@gmail.com>
Co-developed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c  |  3 +++
 kernel/sched/ext.c   | 45 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |  2 ++
 3 files changed, 50 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 096e8d03d85e7..31a9c9381c63f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8679,6 +8679,9 @@ void __init sched_init(void)
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
 		fair_server_init(rq);
+#ifdef CONFIG_SCHED_CLASS_EXT
+		ext_server_init(rq);
+#endif
 
 #ifdef CONFIG_SCHED_CORE
 		rq->core = rq;
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index d1ef5bda95aec..2a25749c54ba1 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -902,6 +902,9 @@ static void update_curr_scx(struct rq *rq)
 		if (!curr->scx.slice)
 			touch_core_sched(rq, curr);
 	}
+
+	if (dl_server_active(&rq->ext_server))
+		dl_server_update(&rq->ext_server, delta_exec);
 }
 
 static bool scx_dsq_priq_less(struct rb_node *node_a,
@@ -1409,6 +1412,15 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
 	if (enq_flags & SCX_ENQ_WAKEUP)
 		touch_core_sched(rq, p);
 
+	if (rq->scx.nr_running == 1) {
+		/* Account for idle runtime */
+		if (!rq->nr_running)
+			dl_server_update_idle_time(rq, rq->curr, &rq->ext_server);
+
+		/* Start dl_server if this is the first task being enqueued */
+		dl_server_start(&rq->ext_server);
+	}
+
 	do_enqueue_task(rq, p, enq_flags, sticky_cpu);
 out:
 	rq->scx.flags &= ~SCX_RQ_IN_WAKEUP;
@@ -2444,6 +2456,30 @@ static struct task_struct *pick_task_scx(struct rq *rq, struct rq_flags *rf)
 	return do_pick_task_scx(rq, rf, false);
 }
 
+/*
+ * Select the next task to run from the ext scheduling class.
+ *
+ * Use do_pick_task_scx() directly with @force_scx enabled, since the
+ * dl_server must always select a sched_ext task.
+ */
+static struct task_struct *
+ext_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf)
+{
+	return do_pick_task_scx(dl_se->rq, rf, true);
+}
+
+/*
+ * Initialize the ext server deadline entity.
+ */
+void ext_server_init(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se = &rq->ext_server;
+
+	init_dl_entity(dl_se);
+
+	dl_server_init(dl_se, rq, ext_server_pick_task);
+}
+
 #ifdef CONFIG_SCHED_CORE
 /**
  * scx_prio_less - Task ordering for core-sched
@@ -3023,6 +3059,15 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p)
 static void switched_from_scx(struct rq *rq, struct task_struct *p)
 {
 	scx_disable_task(p);
+
+	/*
+	 * After class switch, if the DL server is still active, restart it so
+	 * that DL timers will be queued, in case SCX switched to higher class.
+	 */
+	if (dl_server_active(&rq->ext_server)) {
+		dl_server_stop(&rq->ext_server);
+		dl_server_start(&rq->ext_server);
+	}
 }
 
 static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index eaae470841dea..002e5c1808014 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -415,6 +415,7 @@ extern void dl_server_update_idle_time(struct rq *rq,
 		    struct task_struct *p,
 		    struct sched_dl_entity *rq_dl_server);
 extern void fair_server_init(struct rq *rq);
+extern void ext_server_init(struct rq *rq);
 extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
 		    u64 runtime, u64 period, bool init);
@@ -1154,6 +1155,7 @@ struct rq {
 	struct dl_rq		dl;
 #ifdef CONFIG_SCHED_CLASS_EXT
 	struct scx_rq		scx;
+	struct sched_dl_entity	ext_server;
 #endif
 
 	struct sched_dl_entity	fair_server;
-- 
2.51.2