[PATCH 09/14] sched/deadline: Account ext server bandwidth

[Andrea Righi <arighi@nvidia.com>]

Always account for both the ext_server and fair_server bandwidths,
especially during CPU hotplug operations. Ignoring either can lead to
imbalances in total_bw when sched_ext schedulers are active and CPUs are
brought online / offline.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/deadline.c | 29 +++++++++++++++++++++--------
 kernel/sched/topology.c |  5 +++++
 2 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d585be4014427..ba2d58bfc82c8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2984,9 +2984,17 @@ void dl_clear_root_domain(struct root_domain *rd)
 	 * them, we need to account for them here explicitly.
 	 */
 	for_each_cpu(i, rd->span) {
-		struct sched_dl_entity *dl_se = &cpu_rq(i)->fair_server;
+		struct sched_dl_entity *dl_se;
 
-		if (dl_server(dl_se) && cpu_active(i))
+		if (!cpu_active(i))
+			continue;
+
+		dl_se = &cpu_rq(i)->fair_server;
+		if (dl_server(dl_se))
+			__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(i));
+
+		dl_se = &cpu_rq(i)->ext_server;
+		if (dl_server(dl_se))
 			__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(i));
 	}
 }
@@ -3485,6 +3493,7 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 	struct dl_bw *dl_b;
 	bool overflow = 0;
 	u64 fair_server_bw = 0;
+	u64 ext_server_bw = 0;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
@@ -3517,27 +3526,31 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 		cap -= arch_scale_cpu_capacity(cpu);
 
 		/*
-		 * cpu is going offline and NORMAL tasks will be moved away
-		 * from it. We can thus discount dl_server bandwidth
-		 * contribution as it won't need to be servicing tasks after
-		 * the cpu is off.
+		 * cpu is going offline and NORMAL and EXT tasks will be
+		 * moved away from it. We can thus discount dl_server
+		 * bandwidth contribution as it won't need to be servicing
+		 * tasks after the cpu is off.
 		 */
 		if (cpu_rq(cpu)->fair_server.dl_server)
 			fair_server_bw = cpu_rq(cpu)->fair_server.dl_bw;
 
+		if (cpu_rq(cpu)->ext_server.dl_server)
+			ext_server_bw = cpu_rq(cpu)->ext_server.dl_bw;
+
 		/*
 		 * Not much to check if no DEADLINE bandwidth is present.
 		 * dl_servers we can discount, as tasks will be moved out the
 		 * offlined CPUs anyway.
 		 */
-		if (dl_b->total_bw - fair_server_bw > 0) {
+		if (dl_b->total_bw - fair_server_bw - ext_server_bw > 0) {
 			/*
 			 * Leaving at least one CPU for DEADLINE tasks seems a
 			 * wise thing to do. As said above, cpu is not offline
 			 * yet, so account for that.
 			 */
 			if (dl_bw_cpus(cpu) - 1)
-				overflow = __dl_overflow(dl_b, cap, fair_server_bw, 0);
+				overflow = __dl_overflow(dl_b, cap,
+							 fair_server_bw + ext_server_bw, 0);
 			else
 				overflow = 1;
 		}
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 711076aa49801..1ec8e74b80219 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -508,6 +508,11 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (rq->fair_server.dl_server)
 		__dl_server_attach_root(&rq->fair_server, rq);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (rq->ext_server.dl_server)
+		__dl_server_attach_root(&rq->ext_server, rq);
+#endif
+
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)
-- 
2.51.0