[RFC PATCH v2 01/25] sched/deadline: Remove fair-servers from real-time task's bandwidth accounting

[Yuri Andriaccio <yurand2000@gmail.com>]

Fair-servers are currently used in place of the old RT_THROTTLING mechanism to
prevent the starvation of SCHED_OTHER (and other lower priority) tasks when
real-time FIFO/RR processes are trying to fully utilize the CPU. To allow the
RT_THROTTLING mechanism, the maximum allocatable bandwidth for real-time tasks
has been limited to 95% of the CPU-time.

The RT_THROTTLING mechanism is now removed in favor of fair-servers, which are
currently set to use, as expected, 5% of the CPU-time. Still, they share the
same bandwidth that allows to run real-time tasks, and which is still set to 95%
of the total CPU-time. This means that by removing the RT_THROTTLING mechanism,
the bandwidth remaning for real-time SCHED_DEADLINE tasks and other dl-servers
(FIFO/RR are not affected) is only 90%.

This patch reclaims the 5% lost CPU-time, which is definitely reserved for
SCHED_OTHER tasks, but should not be accounted togheter with the other real-time
tasks. More generally, the fair-servers' bandwidth must not be accounted with
other real-time tasks.

Updates:
- Make the fair-servers' bandwidth not be accounted into the total allocated
  bandwidth for real-time tasks.
- Remove the admission control test when allocating a fair-server.
- Do not account for fair-servers in the GRUB's bandwidth reclaiming mechanism.
- Limit the max bandwidth to (BW_UNIT - max_rt_bw) when changing the parameters
  of a fair-server, preventing overcommitment.
- Add dl_bw_fair, which computes the total allocated bandwidth of the
  fair-servers in the given root-domain.
- Update admission tests (in sched_dl_global_validate) when changing the
  maximum allocatable bandwidth for real-time tasks, preventing overcommitment.

Since the fair-server's bandwidth can be changed through debugfs, it has not
been enforced that a fair-server's bw must be always equal to (BW_UNIT -
max_rt_bw), rather it must be less or equal to this value. This allows retaining
the fair-servers' settings changed through the debugfs when chaning the
max_rt_bw.

This also means that in order to increase the maximum bandwidth for real-time
tasks, the bw of fair-servers must be first decreased through debugfs otherwise
admission tests will fail, and viceversa, to increase the bw of fair-servers,
the bw of real-time tasks must be reduced beforehand.

This v2 version addresses the compilation error on i386 reported at:
https://lore.kernel.org/oe-kbuild-all/202507220727.BmA1Osdg-lkp@intel.com/

v1: https://lore.kernel.org/all/20250721111131.309388-1-yurand2000@gmail.com/

Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
 kernel/sched/deadline.c | 66 ++++++++++++++++++-----------------------
 kernel/sched/sched.h    |  1 -
 kernel/sched/topology.c |  8 -----
 3 files changed, 29 insertions(+), 46 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e2d51f4306b..8ba6bf3ef68 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -141,6 +141,24 @@ static inline int dl_bw_cpus(int i)
 	return cpus;
 }
 
+static inline u64 dl_bw_fair(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	u64 fair_server_bw = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+
+	if (cpumask_subset(rd->span, cpu_active_mask))
+		i = cpumask_first(rd->span);
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask) {
+		fair_server_bw += cpu_rq(i)->fair_server.dl_bw;
+	}
+
+	return fair_server_bw;
+}
+
 static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
 {
 	unsigned long cap = 0;
@@ -1657,25 +1675,9 @@ void sched_init_dl_servers(void)
 	}
 }
 
-void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq)
-{
-	u64 new_bw = dl_se->dl_bw;
-	int cpu = cpu_of(rq);
-	struct dl_bw *dl_b;
-
-	dl_b = dl_bw_of(cpu_of(rq));
-	guard(raw_spinlock)(&dl_b->lock);
-
-	if (!dl_bw_cpus(cpu))
-		return;
-
-	__dl_add(dl_b, new_bw, dl_bw_cpus(cpu));
-}
-
 int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init)
 {
-	u64 old_bw = init ? 0 : to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-	u64 new_bw = to_ratio(period, runtime);
+	u64 max_bw, new_bw = to_ratio(period, runtime);
 	struct rq *rq = dl_se->rq;
 	int cpu = cpu_of(rq);
 	struct dl_bw *dl_b;
@@ -1688,17 +1690,14 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio
 
 	cpus = dl_bw_cpus(cpu);
 	cap = dl_bw_capacity(cpu);
+	max_bw = div64_ul(cap_scale(BW_UNIT - dl_b->bw, cap), (unsigned long)cpus);
 
-	if (__dl_overflow(dl_b, cap, old_bw, new_bw))
+	if (new_bw > max_bw)
 		return -EBUSY;
 
 	if (init) {
 		__add_rq_bw(new_bw, &rq->dl);
-		__dl_add(dl_b, new_bw, cpus);
 	} else {
-		__dl_sub(dl_b, dl_se->dl_bw, cpus);
-		__dl_add(dl_b, new_bw, cpus);
-
 		dl_rq_change_utilization(rq, dl_se, new_bw);
 	}
 
@@ -2939,17 +2938,6 @@ void dl_clear_root_domain(struct root_domain *rd)
 	rd->dl_bw.total_bw = 0;
 	for_each_cpu(i, rd->span)
 		cpu_rq(i)->dl.extra_bw = cpu_rq(i)->dl.max_bw;
-
-	/*
-	 * dl_servers are not tasks. Since dl_add_task_root_domain ignores
-	 * 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;
-
-		if (dl_server(dl_se) && cpu_active(i))
-			__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(i));
-	}
 }
 
 void dl_clear_root_domain_cpu(int cpu)
@@ -3133,9 +3121,10 @@ int sched_dl_global_validate(void)
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	u64 cookie = ++dl_cookie;
+	u64 fair_bw;
 	struct dl_bw *dl_b;
-	int cpu, cpus, ret = 0;
-	unsigned long flags;
+	int cpu, ret = 0;
+	unsigned long cap, flags;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
@@ -3149,10 +3138,13 @@ int sched_dl_global_validate(void)
 			goto next;
 
 		dl_b = dl_bw_of(cpu);
-		cpus = dl_bw_cpus(cpu);
+		cap = dl_bw_capacity(cpu);
+		fair_bw = dl_bw_fair(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw * cpus < dl_b->total_bw)
+		if (cap_scale(new_bw, cap) < dl_b->total_bw)
+			ret = -EBUSY;
+		if (cap_scale(new_bw, cap) + fair_bw > cap_scale(BW_UNIT, cap))
 			ret = -EBUSY;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d3f33d10c58..8719ab8a817 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -390,7 +390,6 @@ extern void sched_init_dl_servers(void);
 extern void dl_server_update_idle_time(struct rq *rq,
 		    struct task_struct *p);
 extern void fair_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);
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 977e133bb8a..4ea3365984a 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -500,14 +500,6 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
-	/*
-	 * Because the rq is not a task, dl_add_task_root_domain() did not
-	 * move the fair server bw to the rd if it already started.
-	 * Add it now.
-	 */
-	if (rq->fair_server.dl_server)
-		__dl_server_attach_root(&rq->fair_server, rq);
-
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)
-- 
2.50.1