+++ /dev/null
-From 3444b7294c4455310b55a9f0b60d3de6480c71cb Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Fri, 27 Jun 2025 13:51:14 +0200
-Subject: sched/deadline: Initialize dl_servers after SMP
-
-From: Juri Lelli <juri.lelli@redhat.com>
-
-[ Upstream commit 9f239df55546ee1d28f0976130136ffd1cad0fd7 ]
-
-dl-servers are currently initialized too early at boot when CPUs are not
-fully up (only boot CPU is). This results in miscalculation of per
-runqueue DEADLINE variables like extra_bw (which needs a stable CPU
-count).
-
-Move initialization of dl-servers later on after SMP has been
-initialized and CPUs are all online, so that CPU count is stable and
-DEADLINE variables can be computed correctly.
-
-Fixes: d741f297bceaf ("sched/fair: Fair server interface")
-Reported-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk>
-Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Acked-by: Waiman Long <longman@redhat.com>
-Tested-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk> # nuc & rock5b
-Link: https://lore.kernel.org/r/20250627115118.438797-2-juri.lelli@redhat.com
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- kernel/sched/core.c | 2 ++
- kernel/sched/deadline.c | 48 +++++++++++++++++++++++++----------------
- kernel/sched/sched.h | 1 +
- 3 files changed, 33 insertions(+), 18 deletions(-)
-
-diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index 7d5f51e2f761..333743f143aa 100644
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -8501,6 +8501,8 @@ void __init sched_init_smp(void)
- init_sched_rt_class();
- init_sched_dl_class();
-
-+ sched_init_dl_servers();
-+
- sched_smp_initialized = true;
- }
-
-diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
-index 094134c9b135..ef5b5c045769 100644
---- a/kernel/sched/deadline.c
-+++ b/kernel/sched/deadline.c
-@@ -824,6 +824,8 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
- struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
- struct rq *rq = rq_of_dl_rq(dl_rq);
-
-+ update_rq_clock(rq);
-+
- WARN_ON(is_dl_boosted(dl_se));
- WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
-
-@@ -1652,23 +1654,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
- {
- struct rq *rq = dl_se->rq;
-
-- /*
-- * XXX: the apply do not work fine at the init phase for the
-- * fair server because things are not yet set. We need to improve
-- * this before getting generic.
-- */
-- if (!dl_server(dl_se)) {
-- u64 runtime = 50 * NSEC_PER_MSEC;
-- u64 period = 1000 * NSEC_PER_MSEC;
--
-- dl_server_apply_params(dl_se, runtime, period, 1);
--
-- dl_se->dl_server = 1;
-- dl_se->dl_defer = 1;
-- setup_new_dl_entity(dl_se);
-- }
--
-- if (!dl_se->dl_runtime || dl_se->dl_server_active)
-+ if (!dl_server(dl_se) || dl_se->dl_server_active)
- return;
-
- dl_se->dl_server_active = 1;
-@@ -1679,7 +1665,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
-
- void dl_server_stop(struct sched_dl_entity *dl_se)
- {
-- if (!dl_se->dl_runtime)
-+ if (!dl_server(dl_se) || !dl_server_active(dl_se))
- return;
-
- dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
-@@ -1712,6 +1698,32 @@ void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
- dl_se->server_pick_task = pick_task;
- }
-
-+void sched_init_dl_servers(void)
-+{
-+ int cpu;
-+ struct rq *rq;
-+ struct sched_dl_entity *dl_se;
-+
-+ for_each_online_cpu(cpu) {
-+ u64 runtime = 50 * NSEC_PER_MSEC;
-+ u64 period = 1000 * NSEC_PER_MSEC;
-+
-+ rq = cpu_rq(cpu);
-+
-+ guard(rq_lock_irq)(rq);
-+
-+ dl_se = &rq->fair_server;
-+
-+ WARN_ON(dl_server(dl_se));
-+
-+ dl_server_apply_params(dl_se, runtime, period, 1);
-+
-+ dl_se->dl_server = 1;
-+ dl_se->dl_defer = 1;
-+ setup_new_dl_entity(dl_se);
-+ }
-+}
-+
- void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq)
- {
- u64 new_bw = dl_se->dl_bw;
-diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
-index d6f82833f652..063f29a228ad 100644
---- a/kernel/sched/sched.h
-+++ b/kernel/sched/sched.h
-@@ -384,6 +384,7 @@ extern void dl_server_stop(struct sched_dl_entity *dl_se);
- extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
- dl_server_has_tasks_f has_tasks,
- dl_server_pick_f pick_task);
-+extern void sched_init_dl_servers(void);
-
- extern void dl_server_update_idle_time(struct rq *rq,
- struct task_struct *p);
---
-2.39.5
-
+++ /dev/null
-From c0a825f92d92fdccff156fd030efa068df138577 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 20 May 2025 11:19:30 +0200
-Subject: sched/deadline: Less agressive dl_server handling
-
-From: Peter Zijlstra <peterz@infradead.org>
-
-[ Upstream commit cccb45d7c4295bbfeba616582d0249f2d21e6df5 ]
-
-Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default
-bandwidth control") caused a significant dip in his favourite
-benchmark of the day. Simply disabling dl_server cured things.
-
-His workload hammers the 0->1, 1->0 transitions, and the
-dl_server_{start,stop}() overhead kills it -- fairly obviously a bad
-idea in hind sight and all that.
-
-Change things around to only disable the dl_server when there has not
-been a fair task around for a whole period. Since the default period
-is 1 second, this ensures the benchmark never trips this, overhead
-gone.
-
-Fixes: 557a6bfc662c ("sched/fair: Add trivial fair server")
-Reported-by: Chris Mason <clm@meta.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
-Acked-by: Juri Lelli <juri.lelli@redhat.com>
-Link: https://lkml.kernel.org/r/20250702121158.465086194@infradead.org
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/sched.h | 1 +
- kernel/sched/deadline.c | 25 ++++++++++++++++++++++---
- kernel/sched/fair.c | 9 ---------
- 3 files changed, 23 insertions(+), 12 deletions(-)
-
-diff --git a/include/linux/sched.h b/include/linux/sched.h
-index f96ac1982893..1f92572b20c0 100644
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -702,6 +702,7 @@ struct sched_dl_entity {
- unsigned int dl_defer : 1;
- unsigned int dl_defer_armed : 1;
- unsigned int dl_defer_running : 1;
-+ unsigned int dl_server_idle : 1;
-
- /*
- * Bandwidth enforcement timer. Each -deadline task has its
-diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
-index 89019a140826..094134c9b135 100644
---- a/kernel/sched/deadline.c
-+++ b/kernel/sched/deadline.c
-@@ -1215,6 +1215,8 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
- /* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
- static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
-
-+static bool dl_server_stopped(struct sched_dl_entity *dl_se);
-+
- static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
- {
- struct rq *rq = rq_of_dl_se(dl_se);
-@@ -1234,6 +1236,7 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
-
- if (!dl_se->server_has_tasks(dl_se)) {
- replenish_dl_entity(dl_se);
-+ dl_server_stopped(dl_se);
- return HRTIMER_NORESTART;
- }
-
-@@ -1639,8 +1642,10 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
- void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
- {
- /* 0 runtime = fair server disabled */
-- if (dl_se->dl_runtime)
-+ if (dl_se->dl_runtime) {
-+ dl_se->dl_server_idle = 0;
- update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
-+ }
- }
-
- void dl_server_start(struct sched_dl_entity *dl_se)
-@@ -1663,7 +1668,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
- setup_new_dl_entity(dl_se);
- }
-
-- if (!dl_se->dl_runtime)
-+ if (!dl_se->dl_runtime || dl_se->dl_server_active)
- return;
-
- dl_se->dl_server_active = 1;
-@@ -1684,6 +1689,20 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
- dl_se->dl_server_active = 0;
- }
-
-+static bool dl_server_stopped(struct sched_dl_entity *dl_se)
-+{
-+ if (!dl_se->dl_server_active)
-+ return false;
-+
-+ if (dl_se->dl_server_idle) {
-+ dl_server_stop(dl_se);
-+ return true;
-+ }
-+
-+ dl_se->dl_server_idle = 1;
-+ return false;
-+}
-+
- void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
- dl_server_has_tasks_f has_tasks,
- dl_server_pick_f pick_task)
-@@ -2435,7 +2454,7 @@ static struct task_struct *__pick_task_dl(struct rq *rq)
- if (dl_server(dl_se)) {
- p = dl_se->server_pick_task(dl_se);
- if (!p) {
-- if (dl_server_active(dl_se)) {
-+ if (!dl_server_stopped(dl_se)) {
- dl_se->dl_yielded = 1;
- update_curr_dl_se(rq, dl_se, 0);
- }
-diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
-index 138d9f4658d5..9746eff2eff7 100644
---- a/kernel/sched/fair.c
-+++ b/kernel/sched/fair.c
-@@ -5886,7 +5886,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
- struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
- struct sched_entity *se;
- long queued_delta, runnable_delta, idle_delta, dequeue = 1;
-- long rq_h_nr_queued = rq->cfs.h_nr_queued;
-
- raw_spin_lock(&cfs_b->lock);
- /* This will start the period timer if necessary */
-@@ -5970,10 +5969,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
-
- /* At this point se is NULL and we are at root level*/
- sub_nr_running(rq, queued_delta);
--
-- /* Stop the fair server if throttling resulted in no runnable tasks */
-- if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
-- dl_server_stop(&rq->fair_server);
- done:
- /*
- * Note: distribution will already see us throttled via the
-@@ -7067,7 +7062,6 @@ static void set_next_buddy(struct sched_entity *se);
- static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
- {
- bool was_sched_idle = sched_idle_rq(rq);
-- int rq_h_nr_queued = rq->cfs.h_nr_queued;
- bool task_sleep = flags & DEQUEUE_SLEEP;
- bool task_delayed = flags & DEQUEUE_DELAYED;
- struct task_struct *p = NULL;
-@@ -7151,9 +7145,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
-
- sub_nr_running(rq, h_nr_queued);
-
-- if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
-- dl_server_stop(&rq->fair_server);
--
- /* balance early to pull high priority tasks */
- if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
- rq->next_balance = jiffies;
---
-2.39.5
-
projects / thirdparty / kernel / stable-queue.git / commitdiff
