* [RFC PATCH v7 01/29] sched/deadline: Introduce dl_freq_invariant flag for fair/ext servers
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 02/29] sched/deadline: Do not access dl_se->rq directly Yuri Andriaccio
` (27 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
The fair/ext servers are by design frequency and capacity invariant, i.e. their
maximum allowed runtime is fixed, regardless of the frequency the CPU is
running. (See also https://lore.kernel.org/all/20250702021440.2594736-1-kuyo.chang@mediatek.com/)
This inevitably broke non-fair dl_servers, which would want to instead scale
their execution time to be consistent with CBS and GRUB-PA.
The newly added flag allows deadline servers to adopt the frequency invariance
behaviour as fair/ext servers.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
include/linux/sched.h | 4 ++++
kernel/sched/deadline.c | 5 ++++-
2 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1c93da75226e..b78ca828f694 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -706,6 +706,9 @@ struct sched_dl_entity {
* contributes to the root domain's total_bw. Only meaningful for server
* entities (@dl_server == 1). Allows toggling the reservation on/off
* without losing the configured @dl_runtime/@dl_period.
+ *
+ * @dl_freq_invariant tells if this server's runtime must NOT be scaled
+ * by the CPU's frequency and capacity.
*/
unsigned int dl_throttled : 1;
unsigned int dl_yielded : 1;
@@ -718,6 +721,7 @@ struct sched_dl_entity {
unsigned int dl_defer_running : 1;
unsigned int dl_defer_idle : 1;
unsigned int dl_bw_attached : 1;
+ unsigned int dl_freq_invariant : 1;
/*
* Bandwidth enforcement timer. Each -deadline task has its
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index c0ebdcde5fe5..57c7a8802d8e 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1432,7 +1432,7 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
return;
scaled_delta_exec = delta_exec;
- if (!dl_server(dl_se))
+ if (!dl_server(dl_se) || !dl_se->dl_freq_invariant)
scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
dl_se->runtime -= scaled_delta_exec;
@@ -1862,6 +1862,7 @@ void sched_init_dl_servers(void)
dl_se->dl_server = 1;
dl_se->dl_defer = 1;
+ dl_se->dl_freq_invariant = 1;
setup_new_dl_entity(dl_se);
#ifdef CONFIG_SCHED_CLASS_EXT
@@ -1873,6 +1874,7 @@ void sched_init_dl_servers(void)
dl_se->dl_server = 1;
dl_se->dl_defer = 1;
+ dl_se->dl_freq_invariant = 1;
setup_new_dl_entity(dl_se);
/*
@@ -3957,6 +3959,7 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se)
dl_se->dl_defer = 0;
dl_se->dl_defer_running = 0;
dl_se->dl_defer_armed = 0;
+ dl_se->dl_freq_invariant = 0;
#ifdef CONFIG_RT_MUTEXES
dl_se->pi_se = dl_se;
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 02/29] sched/deadline: Do not access dl_se->rq directly
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 01/29] sched/deadline: Introduce dl_freq_invariant flag for fair/ext servers Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 03/29] sched/deadline: Distinguish between dl_rq and my_q Yuri Andriaccio
` (26 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Make deadline.c code access the runqueue of a scheduling entity saved in
the sched_dl_entity data structure. This allows future patches to save
different runqueues in sched_dl_entity other than the global runqueues.
Move dl_server_apply_params call in sched_init_dl_servers as the rq_of_dl_se
function will return the correct deadline entity only if the dl_server flag
is set.
Add a WARN_ON on the return value of dl_server_apply_params in
sched_init_dl_servers as this function may fail if the kernel is not
configured correctly.
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/deadline.c | 46 ++++++++++++++++++++---------------------
1 file changed, 23 insertions(+), 23 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 57c7a8802d8e..00f584c7bbd5 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -869,7 +869,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
* and arm the defer timer.
*/
if (dl_se->dl_defer && !dl_se->dl_defer_running &&
- dl_time_before(rq_clock(dl_se->rq), dl_se->deadline - dl_se->runtime)) {
+ dl_time_before(rq_clock(rq), dl_se->deadline - dl_se->runtime)) {
if (!is_dl_boosted(dl_se)) {
/*
@@ -1171,11 +1171,11 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
* of time. The dl_server_min_res serves as a limit to avoid
* forwarding the timer for a too small amount of time.
*/
- if (dl_time_before(rq_clock(dl_se->rq),
+ if (dl_time_before(rq_clock(rq),
(dl_se->deadline - dl_se->runtime - dl_server_min_res))) {
/* reset the defer timer */
- fw = dl_se->deadline - rq_clock(dl_se->rq) - dl_se->runtime;
+ fw = dl_se->deadline - rq_clock(rq) - dl_se->runtime;
hrtimer_forward_now(timer, ns_to_ktime(fw));
return HRTIMER_RESTART;
@@ -1186,7 +1186,7 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
- if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &dl_se->rq->curr->dl))
+ if (!dl_task(rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
resched_curr(rq);
__push_dl_task(rq, rf);
@@ -1482,7 +1482,7 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
hrtimer_try_to_cancel(&dl_se->dl_timer);
- replenish_dl_new_period(dl_se, dl_se->rq);
+ replenish_dl_new_period(dl_se, rq);
if (idle)
dl_se->dl_defer_idle = 1;
@@ -1579,14 +1579,14 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec)
{
if (dl_se->dl_server_active && dl_se->dl_runtime && dl_se->dl_defer)
- update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+ update_curr_dl_se(rq_of_dl_se(dl_se), dl_se, delta_exec);
}
void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
{
/* 0 runtime = fair server disabled */
if (dl_se->dl_server_active && dl_se->dl_runtime)
- update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+ update_curr_dl_se(rq_of_dl_se(dl_se), dl_se, delta_exec);
}
/*
@@ -1795,7 +1795,7 @@ void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
*/
void dl_server_start(struct sched_dl_entity *dl_se)
{
- struct rq *rq = dl_se->rq;
+ struct rq *rq;
dl_se->dl_defer_idle = 0;
if (!dl_server(dl_se) || dl_se->dl_server_active || !dl_se->dl_runtime ||
@@ -1805,16 +1805,16 @@ void dl_server_start(struct sched_dl_entity *dl_se)
/*
* Update the current task to 'now'.
*/
+ rq = rq_of_dl_se(dl_se);
rq->donor->sched_class->update_curr(rq);
-
if (WARN_ON_ONCE(!cpu_online(cpu_of(rq))))
return;
trace_sched_dl_server_start_tp(dl_se, cpu_of(rq), dl_get_type(dl_se, rq));
dl_se->dl_server_active = 1;
enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
- if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
- resched_curr(dl_se->rq);
+ if (!dl_task(rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
+ resched_curr(rq);
}
void dl_server_stop(struct sched_dl_entity *dl_se)
@@ -1858,9 +1858,9 @@ void sched_init_dl_servers(void)
WARN_ON(dl_server(dl_se));
- dl_server_apply_params(dl_se, runtime, period, 1);
-
dl_se->dl_server = 1;
+ WARN_ON(dl_server_apply_params(dl_se, runtime, period, 1));
+
dl_se->dl_defer = 1;
dl_se->dl_freq_invariant = 1;
setup_new_dl_entity(dl_se);
@@ -1870,9 +1870,9 @@ void sched_init_dl_servers(void)
WARN_ON(dl_server(dl_se));
- dl_server_apply_params(dl_se, runtime, period, 1);
-
dl_se->dl_server = 1;
+ WARN_ON(dl_server_apply_params(dl_se, runtime, period, 1));
+
dl_se->dl_defer = 1;
dl_se->dl_freq_invariant = 1;
setup_new_dl_entity(dl_se);
@@ -1910,7 +1910,7 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio
u64 old_bw = (init || !dl_se->dl_bw_attached) ? 0 :
to_ratio(dl_se->dl_period, dl_se->dl_runtime);
u64 new_bw = to_ratio(period, runtime);
- struct rq *rq = dl_se->rq;
+ struct rq *rq = rq_of_dl_se(dl_se);
int cpu = cpu_of(rq);
struct dl_bw *dl_b;
unsigned long cap;
@@ -1957,7 +1957,7 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio
static int __dl_server_attach_bw_locked(struct sched_dl_entity *dl_se,
struct dl_bw *dl_b, int cpus)
{
- struct rq *rq = dl_se->rq;
+ struct rq *rq = rq_of_dl_se(dl_se);
unsigned long cap;
/*
@@ -1985,7 +1985,7 @@ static int __dl_server_attach_bw_locked(struct sched_dl_entity *dl_se,
static void __dl_server_detach_bw_locked(struct sched_dl_entity *dl_se,
struct dl_bw *dl_b, int cpus)
{
- struct rq *rq = dl_se->rq;
+ struct rq *rq = rq_of_dl_se(dl_se);
/*
* If the server is still active (on_rq), dequeue it via
@@ -2030,7 +2030,7 @@ static void __dl_server_detach_bw_locked(struct sched_dl_entity *dl_se,
*/
int dl_server_attach_bw(struct sched_dl_entity *dl_se)
{
- struct rq *rq = dl_se->rq;
+ struct rq *rq = rq_of_dl_se(dl_se);
int cpu = cpu_of(rq);
struct dl_bw *dl_b;
int cpus, ret;
@@ -2071,7 +2071,7 @@ int dl_server_attach_bw(struct sched_dl_entity *dl_se)
*/
void dl_server_detach_bw(struct sched_dl_entity *dl_se)
{
- int cpu = cpu_of(dl_se->rq);
+ int cpu = cpu_of(rq_of_dl_se(dl_se));
struct dl_bw *dl_b;
int cpus;
@@ -2096,12 +2096,12 @@ void dl_server_detach_bw(struct sched_dl_entity *dl_se)
int dl_server_swap_bw(struct sched_dl_entity *detach_se,
struct sched_dl_entity *attach_se)
{
- struct rq *rq = detach_se->rq;
+ struct rq *rq = rq_of_dl_se(detach_se);
int cpu = cpu_of(rq);
struct dl_bw *dl_b;
int cpus, ret;
- WARN_ON_ONCE(attach_se->rq != rq);
+ WARN_ON_ONCE(rq_of_dl_se(attach_se) != rq);
scoped_guard (raw_spinlock, &dl_bw_of(cpu)->lock) {
dl_b = dl_bw_of(cpu);
@@ -2162,7 +2162,7 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
p = dl_task_of(dl_se);
rq = task_rq_lock(p, &rf);
} else {
- rq = dl_se->rq;
+ rq = rq_of_dl_se(dl_se);
rq_lock(rq, &rf);
}
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 03/29] sched/deadline: Distinguish between dl_rq and my_q
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 01/29] sched/deadline: Introduce dl_freq_invariant flag for fair/ext servers Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 02/29] sched/deadline: Do not access dl_se->rq directly Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 04/29] sched/rt: Pass an rt_rq instead of an rq where needed Yuri Andriaccio
` (25 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Split the single runqueue pointer in sched_dl_entity into two separate
pointers, following the existing pattern used by sched_rt_entity:
- dl_rq: Points to the deadline runqueue where this entity is queued
(global runqueue).
- my_q: Points to the runqueue that this entity serves (for servers).
This distinction is currently redundant for the fair_server and ext_servers
(both point to the same CPU's structures), but is essential for future RT
cgroup support where deadline servers will be queued on the global dl_rq while
serving tasks from cgroup-specific runqueues.
Update rq_of_dl_se() to use container_of_const() to recover the global rq from
dl_rq, and update fair.c and ext.c to explicitly use my_q (local rq) when
accessing the served runqueue.
Update dl_server_init() to take a dl_rq pointer (use to retrieve the
global runqueue where the dl_server is scheduled) and a rq pointer (for
the local runqueue served by the server).
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
include/linux/sched.h | 6 ++++--
kernel/sched/deadline.c | 17 ++++++++++++-----
kernel/sched/ext/ext.c | 4 ++--
kernel/sched/fair.c | 4 ++--
kernel/sched/sched.h | 3 ++-
5 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b78ca828f694..febc03b02fa4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -742,9 +742,11 @@ struct sched_dl_entity {
* Bits for DL-server functionality. Also see the comment near
* dl_server_update().
*
- * @rq the runqueue this server is for
+ * @dl_rq the runqueue on which this entity is (to be) queued
+ * @my_q the runqueue "owned" by this entity
*/
- struct rq *rq;
+ struct dl_rq *dl_rq;
+ struct rq *my_q;
dl_server_pick_f server_pick_task;
#ifdef CONFIG_RT_MUTEXES
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 00f584c7bbd5..d24a1e14dd21 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -65,10 +65,12 @@ static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
static inline struct rq *rq_of_dl_se(struct sched_dl_entity *dl_se)
{
- struct rq *rq = dl_se->rq;
+ struct rq *rq;
if (!dl_server(dl_se))
rq = task_rq(dl_task_of(dl_se));
+ else
+ rq = container_of_const(dl_se->dl_rq, struct rq, dl);
return rq;
}
@@ -1819,11 +1821,14 @@ void dl_server_start(struct sched_dl_entity *dl_se)
void dl_server_stop(struct sched_dl_entity *dl_se)
{
+ struct rq *rq;
+
if (!dl_server(dl_se) || !dl_server_active(dl_se))
return;
- trace_sched_dl_server_stop_tp(dl_se, cpu_of(dl_se->rq),
- dl_get_type(dl_se, dl_se->rq));
+ rq = rq_of_dl_se(dl_se);
+ trace_sched_dl_server_stop_tp(dl_se, cpu_of(rq),
+ dl_get_type(dl_se, rq));
dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
hrtimer_try_to_cancel(&dl_se->dl_timer);
dl_se->dl_defer_armed = 0;
@@ -1832,10 +1837,12 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
dl_se->dl_server_active = 0;
}
-void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+void dl_server_init(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq,
+ struct rq *served_rq,
dl_server_pick_f pick_task)
{
- dl_se->rq = rq;
+ dl_se->dl_rq = dl_rq;
+ dl_se->my_q = served_rq;
dl_se->server_pick_task = pick_task;
}
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index f74ffb3b1aca..3dd7d8998924 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -4099,7 +4099,7 @@ ext_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf)
if (!scx_enabled())
return NULL;
- return do_pick_task_scx(dl_se->rq, rf, true);
+ return do_pick_task_scx(dl_se->my_q, rf, true);
}
/*
@@ -4111,7 +4111,7 @@ void ext_server_init(struct rq *rq)
init_dl_entity(dl_se);
- dl_server_init(dl_se, rq, ext_server_pick_task);
+ dl_server_init(dl_se, &rq->dl, rq, ext_server_pick_task);
}
#ifdef CONFIG_SCHED_CORE
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cfc982205b98..a8e547c144af 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10311,7 +10311,7 @@ static struct task_struct *
fair_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf)
__must_hold(__rq_lockp(dl_se->rq))
{
- return pick_task_fair(dl_se->rq, rf);
+ return pick_task_fair(dl_se->my_q, rf);
}
void fair_server_init(struct rq *rq)
@@ -10320,7 +10320,7 @@ void fair_server_init(struct rq *rq)
init_dl_entity(dl_se);
- dl_server_init(dl_se, rq, fair_server_pick_task);
+ dl_server_init(dl_se, &rq->dl, rq, fair_server_pick_task);
}
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6c7c5633524a..1b04b4c40ae9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -412,7 +412,8 @@ extern void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec)
extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
extern void dl_server_start(struct sched_dl_entity *dl_se);
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,
+extern void dl_server_init(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq,
+ struct rq *served_rq,
dl_server_pick_f pick_task);
extern void sched_init_dl_servers(void);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 04/29] sched/rt: Pass an rt_rq instead of an rq where needed
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (2 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 03/29] sched/deadline: Distinguish between dl_rq and my_q Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 05/29] sched/rt: Move functions from rt.c to sched.h Yuri Andriaccio
` (24 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Make rt.c code access the runqueue through the rt_rq data structure rather
than passing an rq pointer directly. This allows future patches to define
rt_rq data structures which do not refer only to the global runqueue, but
also to local cgroup runqueues (as rt_rq will not be always equal to
&rq->rt).
Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
---
kernel/sched/rt.c | 174 +++++++++++++++++++++++++++-------------------
1 file changed, 104 insertions(+), 70 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1535046a23ff..2b1c3ab5d6a4 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -370,9 +370,9 @@ static inline void rt_clear_overload(struct rq *rq)
cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
}
-static inline int has_pushable_tasks(struct rq *rq)
+static inline int has_pushable_tasks(struct rt_rq *rt_rq)
{
- return !plist_head_empty(&rq->rt.pushable_tasks);
+ return !plist_head_empty(&rt_rq->pushable_tasks);
}
static DEFINE_PER_CPU(struct balance_callback, rt_push_head);
@@ -381,50 +381,66 @@ static DEFINE_PER_CPU(struct balance_callback, rt_pull_head);
static void push_rt_tasks(struct rq *);
static void pull_rt_task(struct rq *);
-static inline void rt_queue_push_tasks(struct rq *rq)
+static inline void rt_queue_push_tasks(struct rt_rq *rt_rq)
{
- if (!has_pushable_tasks(rq))
+ struct rq *rq = container_of_const(rt_rq, struct rq, rt);
+
+ if (!has_pushable_tasks(rt_rq))
return;
queue_balance_callback(rq, &per_cpu(rt_push_head, rq->cpu), push_rt_tasks);
}
-static inline void rt_queue_pull_task(struct rq *rq)
+static inline void rt_queue_pull_task(struct rt_rq *rt_rq)
{
+ struct rq *rq = container_of_const(rt_rq, struct rq, rt);
+
queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task);
}
-static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
+static void push_rt_rq_tasks(struct rt_rq *rt_rq);
+
+static void push_rt_tasks(struct rq *global_rq) {
+ push_rt_rq_tasks(&global_rq->rt);
+}
+
+static void pull_rt_rq_task(struct rt_rq *this_rt_rq);
+
+static void pull_rt_task(struct rq *global_rq) {
+ pull_rt_rq_task(&global_rq->rt);
+}
+
+static void enqueue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
{
- plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+ plist_del(&p->pushable_tasks, &rt_rq->pushable_tasks);
plist_node_init(&p->pushable_tasks, p->prio);
- plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
+ plist_add(&p->pushable_tasks, &rt_rq->pushable_tasks);
/* Update the highest prio pushable task */
- if (p->prio < rq->rt.highest_prio.next)
- rq->rt.highest_prio.next = p->prio;
+ if (p->prio < rt_rq->highest_prio.next)
+ rt_rq->highest_prio.next = p->prio;
- if (!rq->rt.overloaded) {
- rt_set_overload(rq);
- rq->rt.overloaded = 1;
+ if (!rt_rq->overloaded) {
+ rt_set_overload(rq_of_rt_rq(rt_rq));
+ rt_rq->overloaded = 1;
}
}
-static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
+static void dequeue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
{
- plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+ plist_del(&p->pushable_tasks, &rt_rq->pushable_tasks);
/* Update the new highest prio pushable task */
- if (has_pushable_tasks(rq)) {
- p = plist_first_entry(&rq->rt.pushable_tasks,
+ if (has_pushable_tasks(rt_rq)) {
+ p = plist_first_entry(&rt_rq->pushable_tasks,
struct task_struct, pushable_tasks);
- rq->rt.highest_prio.next = p->prio;
+ rt_rq->highest_prio.next = p->prio;
} else {
- rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+ rt_rq->highest_prio.next = MAX_RT_PRIO-1;
- if (rq->rt.overloaded) {
- rt_clear_overload(rq);
- rq->rt.overloaded = 0;
+ if (rt_rq->overloaded) {
+ rt_clear_overload(rq_of_rt_rq(rt_rq));
+ rt_rq->overloaded = 0;
}
}
}
@@ -1436,6 +1452,7 @@ static void
enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
struct sched_rt_entity *rt_se = &p->rt;
+ struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
if (flags & ENQUEUE_WAKEUP)
rt_se->timeout = 0;
@@ -1449,17 +1466,18 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
return;
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
- enqueue_pushable_task(rq, p);
+ enqueue_pushable_task(rt_rq, p);
}
static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
struct sched_rt_entity *rt_se = &p->rt;
+ struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
update_curr_rt(rq);
dequeue_rt_entity(rt_se, flags);
- dequeue_pushable_task(rq, p);
+ dequeue_pushable_task(rt_rq, p);
return true;
}
@@ -1498,7 +1516,7 @@ static void yield_task_rt(struct rq *rq)
requeue_task_rt(rq, rq->donor, 0);
}
-static int find_lowest_rq(struct task_struct *task);
+static int find_lowest_rt_rq(struct task_struct *task);
static int
select_task_rq_rt(struct task_struct *p, int cpu, int flags)
@@ -1548,7 +1566,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)
(curr->nr_cpus_allowed < 2 || donor->prio <= p->prio);
if (test || !rt_task_fits_capacity(p, cpu)) {
- int target = find_lowest_rq(p);
+ int target = find_lowest_rt_rq(p);
/*
* Bail out if we were forcing a migration to find a better
@@ -1612,7 +1630,7 @@ static int balance_rt(struct rq *rq, struct rq_flags *rf)
* not yet started the picking loop.
*/
rq_unpin_lock(rq, rf);
- pull_rt_task(rq);
+ pull_rt_rq_task(&rq->rt);
rq_repin_lock(rq, rf);
}
@@ -1657,7 +1675,7 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum snt_e type)
{
struct sched_rt_entity *rt_se = &p->rt;
- struct rt_rq *rt_rq = &rq->rt;
+ struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);
if (type == SNT_REPICK)
return;
@@ -1667,7 +1685,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum s
update_stats_wait_end_rt(rt_rq, rt_se);
/* The running task is never eligible for pushing */
- dequeue_pushable_task(rq, p);
+ dequeue_pushable_task(rt_rq, p);
if (type != SNT_PICK)
return;
@@ -1680,7 +1698,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum s
if (rq->donor->sched_class != &rt_sched_class)
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
- rt_queue_push_tasks(rq);
+ rt_queue_push_tasks(rt_rq);
}
static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
@@ -1731,7 +1749,7 @@ static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_struct *next)
{
struct sched_rt_entity *rt_se = &p->rt;
- struct rt_rq *rt_rq = &rq->rt;
+ struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);
if (on_rt_rq(&p->rt))
update_stats_wait_start_rt(rt_rq, rt_se);
@@ -1747,7 +1765,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_s
* if it is still active
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
- enqueue_pushable_task(rq, p);
+ enqueue_pushable_task(rt_rq, p);
}
/* Only try algorithms three times */
@@ -1757,16 +1775,16 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_s
* Return the highest pushable rq's task, which is suitable to be executed
* on the CPU, NULL otherwise
*/
-static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu)
+static struct task_struct *pick_highest_pushable_task(struct rt_rq *rt_rq, int cpu)
{
- struct plist_head *head = &rq->rt.pushable_tasks;
+ struct plist_head *head = &rt_rq->pushable_tasks;
struct task_struct *p;
- if (!has_pushable_tasks(rq))
+ if (!has_pushable_tasks(rt_rq))
return NULL;
plist_for_each_entry(p, head, pushable_tasks) {
- if (task_is_pushable(rq, p, cpu))
+ if (task_is_pushable(rq_of_rt_rq(rt_rq), p, cpu))
return p;
}
@@ -1775,7 +1793,7 @@ static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu)
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
-static int find_lowest_rq(struct task_struct *task)
+static int find_lowest_rt_rq(struct task_struct *task)
{
struct sched_domain *sd;
struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
@@ -1866,12 +1884,13 @@ static int find_lowest_rq(struct task_struct *task)
return -1;
}
-static struct task_struct *pick_next_pushable_task(struct rq *rq)
+static struct task_struct *pick_next_pushable_task(struct rt_rq *rt_rq)
{
- struct plist_head *head = &rq->rt.pushable_tasks;
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+ struct plist_head *head = &rt_rq->pushable_tasks;
struct task_struct *i, *p = NULL;
- if (!has_pushable_tasks(rq))
+ if (!has_pushable_tasks(rt_rq))
return NULL;
plist_for_each_entry(i, head, pushable_tasks) {
@@ -1897,14 +1916,15 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
}
/* Will lock the rq it finds */
-static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
+static struct rt_rq *find_lock_lowest_rt_rq(struct task_struct *task, struct rt_rq *rt_rq)
{
+ struct rq *rq = rq_of_rt_rq(rt_rq);
struct rq *lowest_rq = NULL;
int tries;
int cpu;
for (tries = 0; tries < RT_MAX_TRIES; tries++) {
- cpu = find_lowest_rq(task);
+ cpu = find_lowest_rt_rq(task);
if ((cpu == -1) || (cpu == rq->cpu))
break;
@@ -1935,7 +1955,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
*/
if (unlikely(is_migration_disabled(task) ||
!cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
- task != pick_next_pushable_task(rq))) {
+ task != pick_next_pushable_task(rt_rq))) {
double_unlock_balance(rq, lowest_rq);
lowest_rq = NULL;
@@ -1952,7 +1972,16 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
lowest_rq = NULL;
}
- return lowest_rq;
+ return &lowest_rq->rt;
+}
+
+static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) {
+ struct rt_rq *rt_rq = find_lock_lowest_rt_rq(task, &rq->rt);
+
+ if (!rt_rq)
+ return NULL;
+
+ return rq_of_rt_rq(rt_rq);
}
/*
@@ -1960,16 +1989,17 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
* running task can migrate over to a CPU that is running a task
* of lesser priority.
*/
-static int push_rt_task(struct rq *rq, bool pull)
+static int push_rt_rq_task(struct rt_rq *rt_rq, bool pull)
{
struct task_struct *next_task;
- struct rq *lowest_rq;
+ struct rq *lowest_rq, *rq = rq_of_rt_rq(rt_rq);
+ struct rt_rq *lowest_rt_rq;
int ret = 0;
- if (!rq->rt.overloaded)
+ if (!rt_rq->overloaded)
return 0;
- next_task = pick_next_pushable_task(rq);
+ next_task = pick_next_pushable_task(rt_rq);
if (!next_task)
return 0;
@@ -1992,7 +2022,7 @@ static int push_rt_task(struct rq *rq, bool pull)
return 0;
/*
- * Invoking find_lowest_rq() on anything but an RT task doesn't
+ * Invoking find_lowest_rt_rq() on anything but an RT task doesn't
* make sense. Per the above priority check, curr has to
* be of higher priority than next_task, so no need to
* reschedule when bailing out.
@@ -2003,7 +2033,7 @@ static int push_rt_task(struct rq *rq, bool pull)
if (rq->donor->sched_class != &rt_sched_class)
return 0;
- cpu = find_lowest_rq(rq->curr);
+ cpu = find_lowest_rt_rq(rq->curr);
if (cpu == -1 || cpu == rq->cpu)
return 0;
@@ -2032,19 +2062,19 @@ static int push_rt_task(struct rq *rq, bool pull)
/* We might release rq lock */
get_task_struct(next_task);
- /* find_lock_lowest_rq locks the rq if found */
- lowest_rq = find_lock_lowest_rq(next_task, rq);
- if (!lowest_rq) {
+ /* find_lock_lowest_rt_rq locks the rq if found */
+ lowest_rt_rq = find_lock_lowest_rt_rq(next_task, rt_rq);
+ if (!lowest_rt_rq) {
struct task_struct *task;
/*
- * find_lock_lowest_rq releases rq->lock
+ * find_lock_lowest_rt_rq releases rq->lock
* so it is possible that next_task has migrated.
*
* We need to make sure that the task is still on the same
* run-queue and is also still the next task eligible for
* pushing.
*/
- task = pick_next_pushable_task(rq);
+ task = pick_next_pushable_task(rt_rq);
if (task == next_task) {
/*
* The task hasn't migrated, and is still the next
@@ -2067,6 +2097,7 @@ static int push_rt_task(struct rq *rq, bool pull)
goto retry;
}
+ lowest_rq = rq_of_rt_rq(lowest_rt_rq);
move_queued_task_locked(rq, lowest_rq, next_task);
resched_curr(lowest_rq);
ret = 1;
@@ -2078,10 +2109,10 @@ static int push_rt_task(struct rq *rq, bool pull)
return ret;
}
-static void push_rt_tasks(struct rq *rq)
+static void push_rt_rq_tasks(struct rt_rq *rt_rq)
{
- /* push_rt_task will return true if it moved an RT */
- while (push_rt_task(rq, false))
+ /* push_rt_rq_task will return true if it moved an RT */
+ while (push_rt_rq_task(rt_rq, false))
;
}
@@ -2237,9 +2268,9 @@ void rto_push_irq_work_func(struct irq_work *work)
* We do not need to grab the lock to check for has_pushable_tasks.
* When it gets updated, a check is made if a push is possible.
*/
- if (has_pushable_tasks(rq)) {
+ if (has_pushable_tasks(&rq->rt)) {
raw_spin_rq_lock(rq);
- while (push_rt_task(rq, true))
+ while (push_rt_rq_task(&rq->rt, true))
;
raw_spin_rq_unlock(rq);
}
@@ -2261,11 +2292,13 @@ void rto_push_irq_work_func(struct irq_work *work)
}
#endif /* HAVE_RT_PUSH_IPI */
-static void pull_rt_task(struct rq *this_rq)
+static void pull_rt_rq_task(struct rt_rq *this_rt_rq)
{
+ struct rq *this_rq = rq_of_rt_rq(this_rt_rq);
int this_cpu = this_rq->cpu, cpu;
bool resched = false;
struct task_struct *p, *push_task;
+ struct rt_rq *src_rt_rq;
struct rq *src_rq;
int rt_overload_count = rt_overloaded(this_rq);
@@ -2295,6 +2328,7 @@ static void pull_rt_task(struct rq *this_rq)
continue;
src_rq = cpu_rq(cpu);
+ src_rt_rq = &src_rq->rt;
/*
* Don't bother taking the src_rq->lock if the next highest
@@ -2303,8 +2337,8 @@ static void pull_rt_task(struct rq *this_rq)
* logically higher, the src_rq will push this task away.
* And if its going logically lower, we do not care
*/
- if (src_rq->rt.highest_prio.next >=
- this_rq->rt.highest_prio.curr)
+ if (src_rt_rq->highest_prio.next >=
+ this_rt_rq->highest_prio.curr)
continue;
/*
@@ -2319,13 +2353,13 @@ static void pull_rt_task(struct rq *this_rq)
* We can pull only a task, which is pushable
* on its rq, and no others.
*/
- p = pick_highest_pushable_task(src_rq, this_cpu);
+ p = pick_highest_pushable_task(src_rt_rq, this_cpu);
/*
* Do we have an RT task that preempts
* the to-be-scheduled task?
*/
- if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
+ if (p && (p->prio < this_rt_rq->highest_prio.curr)) {
WARN_ON(p == src_rq->curr);
WARN_ON(!task_on_rq_queued(p));
@@ -2384,7 +2418,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
rq->donor->prio <= p->prio);
if (need_to_push)
- push_rt_tasks(rq);
+ push_rt_rq_tasks(rt_rq_of_se(&p->rt));
}
/* Assumes rq->lock is held */
@@ -2425,7 +2459,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
return;
- rt_queue_pull_task(rq);
+ rt_queue_pull_task(rt_rq_of_se(&p->rt));
}
void __init init_sched_rt_class(void)
@@ -2460,8 +2494,8 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
* then see if we can move to another run queue.
*/
if (task_on_rq_queued(p)) {
- if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
- rt_queue_push_tasks(rq);
+ if (p->nr_cpus_allowed > 1 && rt_rq_of_se(&p->rt)->overloaded)
+ rt_queue_push_tasks(rt_rq_of_se(&p->rt));
if (p->prio < rq->donor->prio && cpu_online(cpu_of(rq)))
resched_curr(rq);
}
@@ -2486,7 +2520,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, u64 oldprio)
* may need to pull tasks to this runqueue.
*/
if (oldprio < p->prio)
- rt_queue_pull_task(rq);
+ rt_queue_pull_task(rt_rq_of_se(&p->rt));
/*
* If there's a higher priority task waiting to run
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 05/29] sched/rt: Move functions from rt.c to sched.h
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (3 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 04/29] sched/rt: Pass an rt_rq instead of an rq where needed Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 06/29] sched/rt: Disable RT_GROUP_SCHED Yuri Andriaccio
` (23 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Make the following functions/macros be non-static and move them in
sched.h, so that they can be also used in other source files:
- rt_entity_is_task()
- rt_task_of()
- rq_of_rt_rq()
- rt_rq_of_se()
- rq_of_rt_se()
There are no functional changes, apart from the use of container_of_const()
instead of container_of() where applicable. This is needed by future patches.
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/rt.c | 56 ------------------------------------------
kernel/sched/sched.h | 58 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 58 insertions(+), 56 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2b1c3ab5d6a4..0862ee8b088d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -166,36 +166,6 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
hrtimer_cancel(&rt_b->rt_period_timer);
}
-#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
-
-static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
-{
- WARN_ON_ONCE(!rt_entity_is_task(rt_se));
-
- return container_of(rt_se, struct task_struct, rt);
-}
-
-static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
-{
- /* Cannot fold with non-CONFIG_RT_GROUP_SCHED version, layout */
- WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
- return rt_rq->rq;
-}
-
-static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
-{
- WARN_ON(!rt_group_sched_enabled() && rt_se->rt_rq->tg != &root_task_group);
- return rt_se->rt_rq;
-}
-
-static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
-{
- struct rt_rq *rt_rq = rt_se->rt_rq;
-
- WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
- return rt_rq->rq;
-}
-
void unregister_rt_sched_group(struct task_group *tg)
{
if (!rt_group_sched_enabled())
@@ -294,32 +264,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
#else /* !CONFIG_RT_GROUP_SCHED: */
-#define rt_entity_is_task(rt_se) (1)
-
-static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
-{
- return container_of(rt_se, struct task_struct, rt);
-}
-
-static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
-{
- return container_of(rt_rq, struct rq, rt);
-}
-
-static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
-{
- struct task_struct *p = rt_task_of(rt_se);
-
- return task_rq(p);
-}
-
-static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
-{
- struct rq *rq = rq_of_rt_se(rt_se);
-
- return &rq->rt;
-}
-
void unregister_rt_sched_group(struct task_group *tg) { }
void free_rt_sched_group(struct task_group *tg) { }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1b04b4c40ae9..e7e4da78340c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3495,6 +3495,64 @@ extern void set_rq_offline(struct rq *rq);
extern bool sched_smp_initialized;
+#ifdef CONFIG_RT_GROUP_SCHED
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
+static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+{
+ WARN_ON_ONCE(!rt_entity_is_task(rt_se));
+
+ return container_of(rt_se, struct task_struct, rt);
+}
+
+static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
+{
+ /* Cannot fold with non-CONFIG_RT_GROUP_SCHED version, layout */
+ WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
+ return rt_rq->rq;
+}
+
+static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+{
+ WARN_ON(!rt_group_sched_enabled() && rt_se->rt_rq->tg != &root_task_group);
+ return rt_se->rt_rq;
+}
+
+static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
+{
+ struct rt_rq *rt_rq = rt_se->rt_rq;
+
+ WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
+ return rt_rq->rq;
+}
+#else
+#define rt_entity_is_task(rt_se) (1)
+
+static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+{
+ return container_of(rt_se, struct task_struct, rt);
+}
+
+static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
+{
+ return container_of(rt_rq, struct rq, rt);
+}
+
+static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
+{
+ struct task_struct *p = rt_task_of(rt_se);
+
+ return task_rq(p);
+}
+
+static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
+{
+ struct rq *rq = rq_of_rt_se(rt_se);
+
+ return &rq->rt;
+}
+#endif
+
DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
double_rq_lock(_T->lock, _T->lock2),
double_rq_unlock(_T->lock, _T->lock2))
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 06/29] sched/rt: Disable RT_GROUP_SCHED
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (4 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 05/29] sched/rt: Move functions from rt.c to sched.h Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 07/29] sched/rt: Remove unnecessary runqueue pointer in struct rt_rq Yuri Andriaccio
` (22 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Disable the old RT_GROUP_SCHED scheduler. Note that this does not
completely remove all the RT_GROUP_SCHED functionality, just unhooks it
and removes most of the relevant functions. Some of the RT_GROUP_SCHED
functions are kept because they will be adapted for the HCBS scheduling.
Most notably:
- Disable the initialization of the rt_bandwidth for group scheduling.
- Unhook any functionality for RT_GROUP_SCHED in normal rt.c code, leaving
only non-group functionality.
- Remove group related field initialization in init_rt_rq().
- Remove all the unhooked (and so unused) functions from RT_GROUP_SCHED.
- Remove all allocation/deallocation code for rt-groups, always returning
failure on allocation.
- Update inc/dec_rt_tasks active tasks' counters, as rt scheduling
entities now only represent a single task, and not a group of tasks
anymore.
- Remove unused rq_of_rt_se function.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 6 -
kernel/sched/deadline.c | 34 --
kernel/sched/debug.c | 6 -
kernel/sched/rt.c | 857 ++--------------------------------------
kernel/sched/sched.h | 32 +-
kernel/sched/syscalls.c | 13 -
6 files changed, 35 insertions(+), 913 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 04b62c16fa8c..f5817136c8dd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8948,11 +8948,6 @@ void __init sched_init(void)
init_defrootdomain();
-#ifdef CONFIG_RT_GROUP_SCHED
- init_rt_bandwidth(&root_task_group.rt_bandwidth,
- global_rt_period(), global_rt_runtime());
-#endif /* CONFIG_RT_GROUP_SCHED */
-
#ifdef CONFIG_CGROUP_SCHED
task_group_cache = KMEM_CACHE(task_group, 0);
@@ -9004,7 +8999,6 @@ void __init sched_init(void)
* starts working after scheduler_running, which is not the case
* yet.
*/
- rq->rt.rt_runtime = global_rt_runtime();
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
rq->next_class = &idle_sched_class;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d24a1e14dd21..bc3ac4be8382 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1534,40 +1534,6 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
} else {
trace_sched_dl_update_tp(dl_se, cpu_of(rq), dl_get_type(dl_se, rq));
}
-
- /*
- * The dl_server does not account for real-time workload because it
- * is running fair work.
- */
- if (dl_se->dl_server)
- return;
-
-#ifdef CONFIG_RT_GROUP_SCHED
- /*
- * Because -- for now -- we share the rt bandwidth, we need to
- * account our runtime there too, otherwise actual rt tasks
- * would be able to exceed the shared quota.
- *
- * Account to the root rt group for now.
- *
- * The solution we're working towards is having the RT groups scheduled
- * using deadline servers -- however there's a few nasties to figure
- * out before that can happen.
- */
- if (rt_bandwidth_enabled()) {
- struct rt_rq *rt_rq = &rq->rt;
-
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- /*
- * We'll let actual RT tasks worry about the overflow here, we
- * have our own CBS to keep us inline; only account when RT
- * bandwidth is relevant.
- */
- if (sched_rt_bandwidth_account(rt_rq))
- rt_rq->rt_time += delta_exec;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- }
-#endif /* CONFIG_RT_GROUP_SCHED */
}
/*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e6a3b516c703..1e48f421576d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1144,12 +1144,6 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
PU(rt_nr_running);
-#ifdef CONFIG_RT_GROUP_SCHED
- P(rt_throttled);
- PN(rt_time);
- PN(rt_runtime);
-#endif
-
#undef PN
#undef PU
#undef P
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0862ee8b088d..6b819adcab4a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -82,115 +82,19 @@ void init_rt_rq(struct rt_rq *rt_rq)
rt_rq->highest_prio.next = MAX_RT_PRIO-1;
rt_rq->overloaded = 0;
plist_head_init(&rt_rq->pushable_tasks);
- /* We start is dequeued state, because no RT tasks are queued */
- rt_rq->rt_queued = 0;
-
-#ifdef CONFIG_RT_GROUP_SCHED
- rt_rq->rt_time = 0;
- rt_rq->rt_throttled = 0;
- rt_rq->rt_runtime = 0;
- raw_spin_lock_init(&rt_rq->rt_runtime_lock);
- rt_rq->tg = &root_task_group;
-#endif
}
#ifdef CONFIG_RT_GROUP_SCHED
-static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
-
-static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
-{
- struct rt_bandwidth *rt_b =
- container_of(timer, struct rt_bandwidth, rt_period_timer);
- int idle = 0;
- int overrun;
-
- raw_spin_lock(&rt_b->rt_runtime_lock);
- for (;;) {
- overrun = hrtimer_forward_now(timer, rt_b->rt_period);
- if (!overrun)
- break;
-
- raw_spin_unlock(&rt_b->rt_runtime_lock);
- idle = do_sched_rt_period_timer(rt_b, overrun);
- raw_spin_lock(&rt_b->rt_runtime_lock);
- }
- if (idle)
- rt_b->rt_period_active = 0;
- raw_spin_unlock(&rt_b->rt_runtime_lock);
-
- return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
-}
-
-void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
-{
- rt_b->rt_period = ns_to_ktime(period);
- rt_b->rt_runtime = runtime;
-
- raw_spin_lock_init(&rt_b->rt_runtime_lock);
-
- hrtimer_setup(&rt_b->rt_period_timer, sched_rt_period_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_REL_HARD);
-}
-
-static inline void do_start_rt_bandwidth(struct rt_bandwidth *rt_b)
-{
- raw_spin_lock(&rt_b->rt_runtime_lock);
- if (!rt_b->rt_period_active) {
- rt_b->rt_period_active = 1;
- /*
- * SCHED_DEADLINE updates the bandwidth, as a run away
- * RT task with a DL task could hog a CPU. But DL does
- * not reset the period. If a deadline task was running
- * without an RT task running, it can cause RT tasks to
- * throttle when they start up. Kick the timer right away
- * to update the period.
- */
- hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
- hrtimer_start_expires(&rt_b->rt_period_timer,
- HRTIMER_MODE_ABS_PINNED_HARD);
- }
- raw_spin_unlock(&rt_b->rt_runtime_lock);
-}
-
-static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
-{
- if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
- return;
-
- do_start_rt_bandwidth(rt_b);
-}
-
-static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
-{
- hrtimer_cancel(&rt_b->rt_period_timer);
-}
-
void unregister_rt_sched_group(struct task_group *tg)
{
- if (!rt_group_sched_enabled())
- return;
- if (tg->rt_se)
- destroy_rt_bandwidth(&tg->rt_bandwidth);
}
void free_rt_sched_group(struct task_group *tg)
{
- int i;
-
if (!rt_group_sched_enabled())
return;
-
- for_each_possible_cpu(i) {
- if (tg->rt_rq)
- kfree(tg->rt_rq[i]);
- if (tg->rt_se)
- kfree(tg->rt_se[i]);
- }
-
- kfree(tg->rt_rq);
- kfree(tg->rt_se);
}
void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
@@ -200,66 +104,19 @@ void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
struct rq *rq = cpu_rq(cpu);
rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
- rt_rq->rt_nr_boosted = 0;
rt_rq->rq = rq;
rt_rq->tg = tg;
tg->rt_rq[cpu] = rt_rq;
tg->rt_se[cpu] = rt_se;
-
- if (!rt_se)
- return;
-
- if (!parent)
- rt_se->rt_rq = &rq->rt;
- else
- rt_se->rt_rq = parent->my_q;
-
- rt_se->my_q = rt_rq;
- rt_se->parent = parent;
- INIT_LIST_HEAD(&rt_se->run_list);
}
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
- struct rt_rq *rt_rq;
- struct sched_rt_entity *rt_se;
- int i;
-
if (!rt_group_sched_enabled())
return 1;
- tg->rt_rq = kzalloc_objs(rt_rq, nr_cpu_ids);
- if (!tg->rt_rq)
- goto err;
- tg->rt_se = kzalloc_objs(rt_se, nr_cpu_ids);
- if (!tg->rt_se)
- goto err;
-
- init_rt_bandwidth(&tg->rt_bandwidth, ktime_to_ns(global_rt_period()), 0);
-
- for_each_possible_cpu(i) {
- rt_rq = kzalloc_node(sizeof(struct rt_rq),
- GFP_KERNEL, cpu_to_node(i));
- if (!rt_rq)
- goto err;
-
- rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
- GFP_KERNEL, cpu_to_node(i));
- if (!rt_se)
- goto err_free_rq;
-
- init_rt_rq(rt_rq);
- rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
- init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
- }
-
return 1;
-
-err_free_rq:
- kfree(rt_rq);
-err:
- return 0;
}
#else /* !CONFIG_RT_GROUP_SCHED: */
@@ -389,9 +246,6 @@ static void dequeue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
}
}
-static void enqueue_top_rt_rq(struct rt_rq *rt_rq);
-static void dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count);
-
static inline int on_rt_rq(struct sched_rt_entity *rt_se)
{
return rt_se->on_rq;
@@ -438,16 +292,6 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
#ifdef CONFIG_RT_GROUP_SCHED
-static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_runtime;
-}
-
-static inline u64 sched_rt_period(struct rt_rq *rt_rq)
-{
- return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
-}
-
typedef struct task_group *rt_rq_iter_t;
static inline struct task_group *next_task_group(struct task_group *tg)
@@ -473,457 +317,20 @@ static inline struct task_group *next_task_group(struct task_group *tg)
iter && (rt_rq = iter->rt_rq[cpu_of(rq)]); \
iter = next_task_group(iter))
-#define for_each_sched_rt_entity(rt_se) \
- for (; rt_se; rt_se = rt_se->parent)
-
-static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
-{
- return rt_se->my_q;
-}
-
static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags);
-static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
-{
- struct task_struct *donor = rq_of_rt_rq(rt_rq)->donor;
- struct rq *rq = rq_of_rt_rq(rt_rq);
- struct sched_rt_entity *rt_se;
-
- int cpu = cpu_of(rq);
-
- rt_se = rt_rq->tg->rt_se[cpu];
-
- if (rt_rq->rt_nr_running) {
- if (!rt_se)
- enqueue_top_rt_rq(rt_rq);
- else if (!on_rt_rq(rt_se))
- enqueue_rt_entity(rt_se, 0);
-
- if (rt_rq->highest_prio.curr < donor->prio)
- resched_curr(rq);
- }
-}
-
-static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
-{
- struct sched_rt_entity *rt_se;
- int cpu = cpu_of(rq_of_rt_rq(rt_rq));
-
- rt_se = rt_rq->tg->rt_se[cpu];
-
- if (!rt_se) {
- dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
- /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
- }
- else if (on_rt_rq(rt_se))
- dequeue_rt_entity(rt_se, 0);
-}
-
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
-}
-
-static int rt_se_boosted(struct sched_rt_entity *rt_se)
-{
- struct rt_rq *rt_rq = group_rt_rq(rt_se);
- struct task_struct *p;
-
- if (rt_rq)
- return !!rt_rq->rt_nr_boosted;
-
- p = rt_task_of(rt_se);
- return p->prio != p->normal_prio;
-}
-
-static inline const struct cpumask *sched_rt_period_mask(void)
-{
- return this_rq()->rd->span;
-}
-
-static inline
-struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
-{
- return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu];
-}
-
-static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
-{
- return &rt_rq->tg->rt_bandwidth;
-}
-
-bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
-{
- struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
-
- return (hrtimer_active(&rt_b->rt_period_timer) ||
- rt_rq->rt_time < rt_b->rt_runtime);
-}
-
-/*
- * We ran out of runtime, see if we can borrow some from our neighbours.
- */
-static void do_balance_runtime(struct rt_rq *rt_rq)
-{
- struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
- struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd;
- int i, weight;
- u64 rt_period;
-
- weight = cpumask_weight(rd->span);
-
- raw_spin_lock(&rt_b->rt_runtime_lock);
- rt_period = ktime_to_ns(rt_b->rt_period);
- for_each_cpu(i, rd->span) {
- struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
- s64 diff;
-
- if (iter == rt_rq)
- continue;
-
- raw_spin_lock(&iter->rt_runtime_lock);
- /*
- * Either all rqs have inf runtime and there's nothing to steal
- * or __disable_runtime() below sets a specific rq to inf to
- * indicate its been disabled and disallow stealing.
- */
- if (iter->rt_runtime == RUNTIME_INF)
- goto next;
-
- /*
- * From runqueues with spare time, take 1/n part of their
- * spare time, but no more than our period.
- */
- diff = iter->rt_runtime - iter->rt_time;
- if (diff > 0) {
- diff = div_u64((u64)diff, weight);
- if (rt_rq->rt_runtime + diff > rt_period)
- diff = rt_period - rt_rq->rt_runtime;
- iter->rt_runtime -= diff;
- rt_rq->rt_runtime += diff;
- if (rt_rq->rt_runtime == rt_period) {
- raw_spin_unlock(&iter->rt_runtime_lock);
- break;
- }
- }
-next:
- raw_spin_unlock(&iter->rt_runtime_lock);
- }
- raw_spin_unlock(&rt_b->rt_runtime_lock);
-}
-
-/*
- * Ensure this RQ takes back all the runtime it lend to its neighbours.
- */
-static void __disable_runtime(struct rq *rq)
-{
- struct root_domain *rd = rq->rd;
- rt_rq_iter_t iter;
- struct rt_rq *rt_rq;
-
- if (unlikely(!scheduler_running))
- return;
-
- for_each_rt_rq(rt_rq, iter, rq) {
- struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
- s64 want;
- int i;
-
- raw_spin_lock(&rt_b->rt_runtime_lock);
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- /*
- * Either we're all inf and nobody needs to borrow, or we're
- * already disabled and thus have nothing to do, or we have
- * exactly the right amount of runtime to take out.
- */
- if (rt_rq->rt_runtime == RUNTIME_INF ||
- rt_rq->rt_runtime == rt_b->rt_runtime)
- goto balanced;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
-
- /*
- * Calculate the difference between what we started out with
- * and what we current have, that's the amount of runtime
- * we lend and now have to reclaim.
- */
- want = rt_b->rt_runtime - rt_rq->rt_runtime;
-
- /*
- * Greedy reclaim, take back as much as we can.
- */
- for_each_cpu(i, rd->span) {
- struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
- s64 diff;
-
- /*
- * Can't reclaim from ourselves or disabled runqueues.
- */
- if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
- continue;
-
- raw_spin_lock(&iter->rt_runtime_lock);
- if (want > 0) {
- diff = min_t(s64, iter->rt_runtime, want);
- iter->rt_runtime -= diff;
- want -= diff;
- } else {
- iter->rt_runtime -= want;
- want -= want;
- }
- raw_spin_unlock(&iter->rt_runtime_lock);
-
- if (!want)
- break;
- }
-
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- /*
- * We cannot be left wanting - that would mean some runtime
- * leaked out of the system.
- */
- WARN_ON_ONCE(want);
-balanced:
- /*
- * Disable all the borrow logic by pretending we have inf
- * runtime - in which case borrowing doesn't make sense.
- */
- rt_rq->rt_runtime = RUNTIME_INF;
- rt_rq->rt_throttled = 0;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- raw_spin_unlock(&rt_b->rt_runtime_lock);
-
- /* Make rt_rq available for pick_next_task() */
- sched_rt_rq_enqueue(rt_rq);
- }
-}
-
-static void __enable_runtime(struct rq *rq)
-{
- rt_rq_iter_t iter;
- struct rt_rq *rt_rq;
-
- if (unlikely(!scheduler_running))
- return;
-
- /*
- * Reset each runqueue's bandwidth settings
- */
- for_each_rt_rq(rt_rq, iter, rq) {
- struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
-
- raw_spin_lock(&rt_b->rt_runtime_lock);
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- rt_rq->rt_runtime = rt_b->rt_runtime;
- rt_rq->rt_time = 0;
- rt_rq->rt_throttled = 0;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- raw_spin_unlock(&rt_b->rt_runtime_lock);
- }
-}
-
-static void balance_runtime(struct rt_rq *rt_rq)
-{
- if (!sched_feat(RT_RUNTIME_SHARE))
- return;
-
- if (rt_rq->rt_time > rt_rq->rt_runtime) {
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- do_balance_runtime(rt_rq);
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- }
-}
-
-static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
-{
- int i, idle = 1, throttled = 0;
- const struct cpumask *span;
-
- span = sched_rt_period_mask();
-
- /*
- * FIXME: isolated CPUs should really leave the root task group,
- * whether they are isolcpus or were isolated via cpusets, lest
- * the timer run on a CPU which does not service all runqueues,
- * potentially leaving other CPUs indefinitely throttled. If
- * isolation is really required, the user will turn the throttle
- * off to kill the perturbations it causes anyway. Meanwhile,
- * this maintains functionality for boot and/or troubleshooting.
- */
- if (rt_b == &root_task_group.rt_bandwidth)
- span = cpu_online_mask;
-
- for_each_cpu(i, span) {
- int enqueue = 0;
- struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
- struct rq *rq = rq_of_rt_rq(rt_rq);
- struct rq_flags rf;
- int skip;
-
- /*
- * When span == cpu_online_mask, taking each rq->lock
- * can be time-consuming. Try to avoid it when possible.
- */
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF)
- rt_rq->rt_runtime = rt_b->rt_runtime;
- skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- if (skip)
- continue;
-
- rq_lock(rq, &rf);
- update_rq_clock(rq);
-
- if (rt_rq->rt_time) {
- u64 runtime;
-
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- if (rt_rq->rt_throttled)
- balance_runtime(rt_rq);
- runtime = rt_rq->rt_runtime;
- rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
- if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
- rt_rq->rt_throttled = 0;
- enqueue = 1;
-
- /*
- * When we're idle and a woken (rt) task is
- * throttled wakeup_preempt() will set
- * skip_update and the time between the wakeup
- * and this unthrottle will get accounted as
- * 'runtime'.
- */
- if (rt_rq->rt_nr_running && rq->curr == rq->idle)
- rq_clock_cancel_skipupdate(rq);
- }
- if (rt_rq->rt_time || rt_rq->rt_nr_running)
- idle = 0;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- } else if (rt_rq->rt_nr_running) {
- idle = 0;
- if (!rt_rq_throttled(rt_rq))
- enqueue = 1;
- }
- if (rt_rq->rt_throttled)
- throttled = 1;
-
- if (enqueue)
- sched_rt_rq_enqueue(rt_rq);
- rq_unlock(rq, &rf);
- }
-
- if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
- return 1;
-
- return idle;
-}
-
-static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
-{
- u64 runtime = sched_rt_runtime(rt_rq);
-
- if (rt_rq->rt_throttled)
- return rt_rq_throttled(rt_rq);
-
- if (runtime >= sched_rt_period(rt_rq))
- return 0;
-
- balance_runtime(rt_rq);
- runtime = sched_rt_runtime(rt_rq);
- if (runtime == RUNTIME_INF)
- return 0;
-
- if (rt_rq->rt_time > runtime) {
- struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
-
- /*
- * Don't actually throttle groups that have no runtime assigned
- * but accrue some time due to boosting.
- */
- if (likely(rt_b->rt_runtime)) {
- rt_rq->rt_throttled = 1;
- printk_deferred_once("sched: RT throttling activated\n");
- } else {
- /*
- * In case we did anyway, make it go away,
- * replenishment is a joke, since it will replenish us
- * with exactly 0 ns.
- */
- rt_rq->rt_time = 0;
- }
-
- if (rt_rq_throttled(rt_rq)) {
- sched_rt_rq_dequeue(rt_rq);
- return 1;
- }
- }
-
- return 0;
-}
-
-#else /* !CONFIG_RT_GROUP_SCHED: */
+#else /* !CONFIG_RT_GROUP_SCHED */
typedef struct rt_rq *rt_rq_iter_t;
#define for_each_rt_rq(rt_rq, iter, rq) \
for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
-#define for_each_sched_rt_entity(rt_se) \
- for (; rt_se; rt_se = NULL)
-
-static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
-{
- return NULL;
-}
-
-static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
-{
- struct rq *rq = rq_of_rt_rq(rt_rq);
-
- if (!rt_rq->rt_nr_running)
- return;
-
- enqueue_top_rt_rq(rt_rq);
- resched_curr(rq);
-}
-
-static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
-{
- dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running);
-}
-
-static inline int rt_rq_throttled(struct rt_rq *rt_rq)
-{
- return false;
-}
-
-static inline const struct cpumask *sched_rt_period_mask(void)
-{
- return cpu_online_mask;
-}
-
-static inline
-struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
-{
- return &cpu_rq(cpu)->rt;
-}
-
-static void __enable_runtime(struct rq *rq) { }
-static void __disable_runtime(struct rq *rq) { }
-
-#endif /* !CONFIG_RT_GROUP_SCHED */
+#endif /* CONFIG_RT_GROUP_SCHED */
static inline int rt_se_prio(struct sched_rt_entity *rt_se)
{
-#ifdef CONFIG_RT_GROUP_SCHED
- struct rt_rq *rt_rq = group_rt_rq(rt_se);
-
- if (rt_rq)
- return rt_rq->highest_prio.curr;
-#endif
-
return rt_task_of(rt_se)->prio;
}
@@ -943,67 +350,8 @@ static void update_curr_rt(struct rq *rq)
if (unlikely(delta_exec <= 0))
return;
-#ifdef CONFIG_RT_GROUP_SCHED
- struct sched_rt_entity *rt_se = &donor->rt;
-
if (!rt_bandwidth_enabled())
return;
-
- for_each_sched_rt_entity(rt_se) {
- struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
- int exceeded;
-
- if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- rt_rq->rt_time += delta_exec;
- exceeded = sched_rt_runtime_exceeded(rt_rq);
- if (exceeded)
- resched_curr(rq);
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
- if (exceeded)
- do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq));
- }
- }
-#endif /* CONFIG_RT_GROUP_SCHED */
-}
-
-static void
-dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count)
-{
- struct rq *rq = rq_of_rt_rq(rt_rq);
-
- BUG_ON(&rq->rt != rt_rq);
-
- if (!rt_rq->rt_queued)
- return;
-
- BUG_ON(!rq->nr_running);
-
- sub_nr_running(rq, count);
- rt_rq->rt_queued = 0;
-
-}
-
-static void
-enqueue_top_rt_rq(struct rt_rq *rt_rq)
-{
- struct rq *rq = rq_of_rt_rq(rt_rq);
-
- BUG_ON(&rq->rt != rt_rq);
-
- if (rt_rq->rt_queued)
- return;
-
- if (rt_rq_throttled(rt_rq))
- return;
-
- if (rt_rq->rt_nr_running) {
- add_nr_running(rq, rt_rq->rt_nr_running);
- rt_rq->rt_queued = 1;
- }
-
- /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_util(rq, 0);
}
static void
@@ -1074,58 +422,11 @@ dec_rt_prio(struct rt_rq *rt_rq, int prio)
dec_rt_prio_smp(rt_rq, prio, prev_prio);
}
-#ifdef CONFIG_RT_GROUP_SCHED
-
-static void
-inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
- if (rt_se_boosted(rt_se))
- rt_rq->rt_nr_boosted++;
-
- start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
-}
-
-static void
-dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
- if (rt_se_boosted(rt_se))
- rt_rq->rt_nr_boosted--;
-
- WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted);
-}
-
-#else /* !CONFIG_RT_GROUP_SCHED: */
-
-static void
-inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
-static inline
-void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {}
-
-#endif /* !CONFIG_RT_GROUP_SCHED */
-
static inline
-unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se)
+unsigned int is_rr_task(struct sched_rt_entity *rt_se)
{
- struct rt_rq *group_rq = group_rt_rq(rt_se);
-
- if (group_rq)
- return group_rq->rt_nr_running;
- else
- return 1;
-}
-
-static inline
-unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se)
-{
- struct rt_rq *group_rq = group_rt_rq(rt_se);
struct task_struct *tsk;
- if (group_rq)
- return group_rq->rr_nr_running;
-
tsk = rt_task_of(rt_se);
return (tsk->policy == SCHED_RR) ? 1 : 0;
@@ -1134,26 +435,21 @@ unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se)
static inline
void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
- int prio = rt_se_prio(rt_se);
-
- WARN_ON(!rt_prio(prio));
- rt_rq->rt_nr_running += rt_se_nr_running(rt_se);
- rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se);
+ WARN_ON(!rt_prio(rt_se_prio(rt_se)));
+ rt_rq->rt_nr_running += 1;
+ rt_rq->rr_nr_running += is_rr_task(rt_se);
- inc_rt_prio(rt_rq, prio);
- inc_rt_group(rt_se, rt_rq);
+ inc_rt_prio(rt_rq, rt_se_prio(rt_se));
}
static inline
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
WARN_ON(!rt_prio(rt_se_prio(rt_se)));
- WARN_ON(!rt_rq->rt_nr_running);
- rt_rq->rt_nr_running -= rt_se_nr_running(rt_se);
- rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se);
+ rt_rq->rt_nr_running -= 1;
+ rt_rq->rr_nr_running -= is_rr_task(rt_se);
dec_rt_prio(rt_rq, rt_se_prio(rt_se));
- dec_rt_group(rt_se, rt_rq);
}
/*
@@ -1182,10 +478,6 @@ static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_arr
static inline struct sched_statistics *
__schedstats_from_rt_se(struct sched_rt_entity *rt_se)
{
- /* schedstats is not supported for rt group. */
- if (!rt_entity_is_task(rt_se))
- return NULL;
-
return &rt_task_of(rt_se)->stats;
}
@@ -1198,9 +490,7 @@ update_stats_wait_start_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
if (!schedstat_enabled())
return;
- if (rt_entity_is_task(rt_se))
- p = rt_task_of(rt_se);
-
+ p = rt_task_of(rt_se);
stats = __schedstats_from_rt_se(rt_se);
if (!stats)
return;
@@ -1217,9 +507,7 @@ update_stats_enqueue_sleeper_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_
if (!schedstat_enabled())
return;
- if (rt_entity_is_task(rt_se))
- p = rt_task_of(rt_se);
-
+ p = rt_task_of(rt_se);
stats = __schedstats_from_rt_se(rt_se);
if (!stats)
return;
@@ -1247,9 +535,7 @@ update_stats_wait_end_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
if (!schedstat_enabled())
return;
- if (rt_entity_is_task(rt_se))
- p = rt_task_of(rt_se);
-
+ p = rt_task_of(rt_se);
stats = __schedstats_from_rt_se(rt_se);
if (!stats)
return;
@@ -1267,12 +553,10 @@ update_stats_dequeue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
if (!schedstat_enabled())
return;
- if (rt_entity_is_task(rt_se)) {
- p = rt_task_of(rt_se);
+ p = rt_task_of(rt_se);
- if (p != rq->curr)
- update_stats_wait_end_rt(rt_rq, rt_se);
- }
+ if (p != rq->curr)
+ update_stats_wait_end_rt(rt_rq, rt_se);
if ((flags & DEQUEUE_SLEEP) && p) {
unsigned int state;
@@ -1292,21 +576,8 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag
{
struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
struct rt_prio_array *array = &rt_rq->active;
- struct rt_rq *group_rq = group_rt_rq(rt_se);
struct list_head *queue = array->queue + rt_se_prio(rt_se);
- /*
- * Don't enqueue the group if its throttled, or when empty.
- * The latter is a consequence of the former when a child group
- * get throttled and the current group doesn't have any other
- * active members.
- */
- if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) {
- if (rt_se->on_list)
- __delist_rt_entity(rt_se, array);
- return;
- }
-
if (move_entity(flags)) {
WARN_ON_ONCE(rt_se->on_list);
if (flags & ENQUEUE_HEAD)
@@ -1336,57 +607,27 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag
dec_rt_tasks(rt_se, rt_rq);
}
-/*
- * Because the prio of an upper entry depends on the lower
- * entries, we must remove entries top - down.
- */
-static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
{
- struct sched_rt_entity *back = NULL;
- unsigned int rt_nr_running;
-
- for_each_sched_rt_entity(rt_se) {
- rt_se->back = back;
- back = rt_se;
- }
-
- rt_nr_running = rt_rq_of_se(back)->rt_nr_running;
-
- for (rt_se = back; rt_se; rt_se = rt_se->back) {
- if (on_rt_rq(rt_se))
- __dequeue_rt_entity(rt_se, flags);
- }
+ struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
- dequeue_top_rt_rq(rt_rq_of_se(back), rt_nr_running);
-}
+ update_stats_enqueue_rt(rt_rq, rt_se, flags);
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
-{
- struct rq *rq = rq_of_rt_se(rt_se);
+ __enqueue_rt_entity(rt_se, flags);
- update_stats_enqueue_rt(rt_rq_of_se(rt_se), rt_se, flags);
+ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
- dequeue_rt_stack(rt_se, flags);
- for_each_sched_rt_entity(rt_se)
- __enqueue_rt_entity(rt_se, flags);
- enqueue_top_rt_rq(&rq->rt);
}
static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
{
- struct rq *rq = rq_of_rt_se(rt_se);
-
- update_stats_dequeue_rt(rt_rq_of_se(rt_se), rt_se, flags);
+ struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
- dequeue_rt_stack(rt_se, flags);
+ update_stats_dequeue_rt(rt_rq, rt_se, flags);
- for_each_sched_rt_entity(rt_se) {
- struct rt_rq *rt_rq = group_rt_rq(rt_se);
+ __dequeue_rt_entity(rt_se, flags);
- if (rt_rq && rt_rq->rt_nr_running)
- __enqueue_rt_entity(rt_se, flags);
- }
- enqueue_top_rt_rq(&rq->rt);
+ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
}
/*
@@ -1446,13 +687,7 @@ requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
{
- struct sched_rt_entity *rt_se = &p->rt;
- struct rt_rq *rt_rq;
-
- for_each_sched_rt_entity(rt_se) {
- rt_rq = rt_rq_of_se(rt_se);
- requeue_rt_entity(rt_rq, rt_se, head);
- }
+ requeue_rt_entity(rt_rq_of_se(&p->rt), &p->rt, head);
}
static void yield_task_rt(struct rq *rq)
@@ -1663,21 +898,6 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
return next;
}
-static struct task_struct *_pick_next_task_rt(struct rq *rq)
-{
- struct sched_rt_entity *rt_se;
- struct rt_rq *rt_rq = &rq->rt;
-
- do {
- rt_se = pick_next_rt_entity(rt_rq);
- if (unlikely(!rt_se))
- return NULL;
- rt_rq = group_rt_rq(rt_se);
- } while (rt_rq);
-
- return rt_task_of(rt_se);
-}
-
static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
{
struct task_struct *p;
@@ -1685,7 +905,7 @@ static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
if (!sched_rt_runnable(rq))
return NULL;
- p = _pick_next_task_rt(rq);
+ p = rt_task_of(pick_next_rt_entity(&rq->rt));
return p;
}
@@ -2371,8 +1591,6 @@ static void rq_online_rt(struct rq *rq)
if (rq->rt.overloaded)
rt_set_overload(rq);
- __enable_runtime(rq);
-
cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
}
@@ -2382,8 +1600,6 @@ static void rq_offline_rt(struct rq *rq)
if (rq->rt.overloaded)
rt_clear_overload(rq);
- __disable_runtime(rq);
-
cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
}
@@ -2544,12 +1760,10 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
* Requeue to the end of queue if we (and all of our ancestors) are not
* the only element on the queue
*/
- for_each_sched_rt_entity(rt_se) {
- if (rt_se->run_list.prev != rt_se->run_list.next) {
- requeue_task_rt(rq, p, 0);
- resched_curr(rq);
- return;
- }
+ if (rt_se->run_list.prev != rt_se->run_list.next) {
+ requeue_task_rt(rq, p, 0);
+ resched_curr(rq);
+ return;
}
}
@@ -2567,16 +1781,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
#ifdef CONFIG_SCHED_CORE
static int task_is_throttled_rt(struct task_struct *p, int cpu)
{
- struct rt_rq *rt_rq;
-
-#ifdef CONFIG_RT_GROUP_SCHED // XXX maybe add task_rt_rq(), see also sched_rt_period_rt_rq
- rt_rq = task_group(p)->rt_rq[cpu];
- WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
-#else
- rt_rq = &cpu_rq(cpu)->rt;
-#endif
-
- return rt_rq_throttled(rt_rq);
+ return 0;
}
#endif /* CONFIG_SCHED_CORE */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e7e4da78340c..13eebde95ec0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -872,7 +872,7 @@ struct scx_rq {
static inline int rt_bandwidth_enabled(void)
{
- return sysctl_sched_rt_runtime >= 0;
+ return 0;
}
/* RT IPI pull logic requires IRQ_WORK */
@@ -912,7 +912,7 @@ struct rt_rq {
static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
{
- return rt_rq->rt_queued && rt_rq->rt_nr_running;
+ return rt_rq->rt_nr_running;
}
/* Deadline class' related fields in a runqueue */
@@ -2939,7 +2939,7 @@ static inline bool sched_dl_runnable(struct rq *rq)
static inline bool sched_rt_runnable(struct rq *rq)
{
- return rq->rt.rt_queued > 0;
+ return rq->rt.rt_nr_running > 0;
}
static inline bool sched_fair_runnable(struct rq *rq)
@@ -3050,9 +3050,6 @@ extern void resched_curr(struct rq *rq);
extern void resched_curr_lazy(struct rq *rq);
extern void resched_cpu(int cpu);
-extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
-extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
-
extern void init_dl_entity(struct sched_dl_entity *dl_se);
extern void init_cfs_throttle_work(struct task_struct *p);
@@ -3496,12 +3493,8 @@ extern void set_rq_offline(struct rq *rq);
extern bool sched_smp_initialized;
#ifdef CONFIG_RT_GROUP_SCHED
-#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
-
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
- WARN_ON_ONCE(!rt_entity_is_task(rt_se));
-
return container_of(rt_se, struct task_struct, rt);
}
@@ -3517,17 +3510,7 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
WARN_ON(!rt_group_sched_enabled() && rt_se->rt_rq->tg != &root_task_group);
return rt_se->rt_rq;
}
-
-static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
-{
- struct rt_rq *rt_rq = rt_se->rt_rq;
-
- WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
- return rt_rq->rq;
-}
#else
-#define rt_entity_is_task(rt_se) (1)
-
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
return container_of(rt_se, struct task_struct, rt);
@@ -3538,16 +3521,9 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
return container_of(rt_rq, struct rq, rt);
}
-static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
-{
- struct task_struct *p = rt_task_of(rt_se);
-
- return task_rq(p);
-}
-
static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
- struct rq *rq = rq_of_rt_se(rt_se);
+ struct rq *rq = task_rq(rt_task_of(rt_se));
return &rq->rt;
}
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 45a127deeadd..02688e75a8bd 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -606,19 +606,6 @@ int __sched_setscheduler(struct task_struct *p,
change:
if (user) {
-#ifdef CONFIG_RT_GROUP_SCHED
- /*
- * Do not allow real-time tasks into groups that have no runtime
- * assigned.
- */
- if (rt_group_sched_enabled() &&
- rt_bandwidth_enabled() && rt_policy(policy) &&
- task_group(p)->rt_bandwidth.rt_runtime == 0 &&
- !task_group_is_autogroup(task_group(p))) {
- retval = -EPERM;
- goto unlock;
- }
-#endif /* CONFIG_RT_GROUP_SCHED */
if (dl_bandwidth_enabled() && dl_policy(policy) &&
!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
cpumask_t *span = rq->rd->span;
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 07/29] sched/rt: Remove unnecessary runqueue pointer in struct rt_rq
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (5 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 06/29] sched/rt: Disable RT_GROUP_SCHED Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 08/29] sched/rt: Introduce HCBS specific structs in task_group Yuri Andriaccio
` (21 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Remove the rq field in struct rt_rq.
The rq field now is just caching the pointer to the global runqueue of the
given rt_rq, so it is unnecessary as the global runqueue can be retrieved
in other ways.
Introduce global_rq_of_rt_rq to retrieve the global runqueue which serves a
rt_rq's dl_server.
Rework rq_of_rt_rq to retrieve the runqueue a rt_rq is serving.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/rt.c | 21 +++++++++------------
kernel/sched/sched.h | 16 ++++++++++++----
2 files changed, 21 insertions(+), 16 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6b819adcab4a..16eb027d4bdd 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -101,10 +101,7 @@ void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
struct sched_rt_entity *rt_se, int cpu,
struct sched_rt_entity *parent)
{
- struct rq *rq = cpu_rq(cpu);
-
rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
- rt_rq->rq = rq;
rt_rq->tg = tg;
tg->rt_rq[cpu] = rt_rq;
@@ -184,7 +181,7 @@ static void pull_rt_task(struct rq *);
static inline void rt_queue_push_tasks(struct rt_rq *rt_rq)
{
- struct rq *rq = container_of_const(rt_rq, struct rq, rt);
+ struct rq *rq = global_rq_of_rt_rq(rt_rq);
if (!has_pushable_tasks(rt_rq))
return;
@@ -194,7 +191,7 @@ static inline void rt_queue_push_tasks(struct rt_rq *rt_rq)
static inline void rt_queue_pull_task(struct rt_rq *rt_rq)
{
- struct rq *rq = container_of_const(rt_rq, struct rq, rt);
+ struct rq *rq = global_rq_of_rt_rq(rt_rq);
queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task);
}
@@ -222,7 +219,7 @@ static void enqueue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
rt_rq->highest_prio.next = p->prio;
if (!rt_rq->overloaded) {
- rt_set_overload(rq_of_rt_rq(rt_rq));
+ rt_set_overload(global_rq_of_rt_rq(rt_rq));
rt_rq->overloaded = 1;
}
}
@@ -240,7 +237,7 @@ static void dequeue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
rt_rq->highest_prio.next = MAX_RT_PRIO-1;
if (rt_rq->overloaded) {
- rt_clear_overload(rq_of_rt_rq(rt_rq));
+ rt_clear_overload(global_rq_of_rt_rq(rt_rq));
rt_rq->overloaded = 0;
}
}
@@ -495,7 +492,7 @@ update_stats_wait_start_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
if (!stats)
return;
- __update_stats_wait_start(rq_of_rt_rq(rt_rq), p, stats);
+ __update_stats_wait_start(global_rq_of_rt_rq(rt_rq), p, stats);
}
static inline void
@@ -512,7 +509,7 @@ update_stats_enqueue_sleeper_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_
if (!stats)
return;
- __update_stats_enqueue_sleeper(rq_of_rt_rq(rt_rq), p, stats);
+ __update_stats_enqueue_sleeper(global_rq_of_rt_rq(rt_rq), p, stats);
}
static inline void
@@ -540,7 +537,7 @@ update_stats_wait_end_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
if (!stats)
return;
- __update_stats_wait_end(rq_of_rt_rq(rt_rq), p, stats);
+ __update_stats_wait_end(global_rq_of_rt_rq(rt_rq), p, stats);
}
static inline void
@@ -564,11 +561,11 @@ update_stats_dequeue_rt(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
state = READ_ONCE(p->__state);
if (state & TASK_INTERRUPTIBLE)
__schedstat_set(p->stats.sleep_start,
- rq_clock(rq_of_rt_rq(rt_rq)));
+ rq_clock(global_rq_of_rt_rq(rt_rq)));
if (state & TASK_UNINTERRUPTIBLE)
__schedstat_set(p->stats.block_start,
- rq_clock(rq_of_rt_rq(rt_rq)));
+ rq_clock(global_rq_of_rt_rq(rt_rq)));
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 13eebde95ec0..27cb594cdfe9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -902,8 +902,6 @@ struct rt_rq {
raw_spinlock_t rt_runtime_lock;
unsigned int rt_nr_boosted;
-
- struct rq *rq; /* this is always top-level rq, cache? */
#endif
#ifdef CONFIG_CGROUP_SCHED
struct task_group *tg; /* this tg has "this" rt_rq on given CPU for runnable entities */
@@ -3500,9 +3498,14 @@ static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
- /* Cannot fold with non-CONFIG_RT_GROUP_SCHED version, layout */
WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
- return rt_rq->rq;
+ return container_of_const(rt_rq, struct rq, rt);
+}
+
+static inline struct rq *global_rq_of_rt_rq(struct rt_rq *rt_rq)
+{
+ /* Cannot fold with non-CONFIG_RT_GROUP_SCHED version, layout */
+ return cpu_rq(rq_of_rt_rq(rt_rq)->cpu);
}
static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
@@ -3521,6 +3524,11 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
return container_of(rt_rq, struct rq, rt);
}
+static inline struct rq *global_rq_of_rt_rq(struct rt_rq *rt_rq)
+{
+ return container_of_const(rt_rq, struct rq, rt);
+}
+
static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
struct rq *rq = task_rq(rt_task_of(rt_se));
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 08/29] sched/rt: Introduce HCBS specific structs in task_group
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (6 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 07/29] sched/rt: Remove unnecessary runqueue pointer in struct rt_rq Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 09/29] sched/core: Initialize HCBS specific structures Yuri Andriaccio
` (20 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Add an array of sched_dl_entity objects in task_group.
Create the dl_bandwidth struct and add a field for it in task_group.
Add a rq pointer field in struct rt_rq.
---
For each CPU on the host system, the task_group manages a sched_dl_entity and
a rt_rq object, which in turn keeps a pointer to its locally managed runqueue.
The sched_dl_entity object manages the deadline server which will be scheduled
for execution on the CPU, while the rt_rq object is instead used to reference
the local runqueue's specific data and entities and it is used when an actual
task must be scheduled when the CPU is given to the dl_server.
The dl_bandwidth object keeps track of the currently allocated bandwidth for
the cgroup and the currently active context. RT-cgroups can either run tasks
themselves or can delegate the scheduling of their tasks to their parent, the
active_context field keeps track of which cgroup is serving the tasks.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
---
kernel/sched/sched.h | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 27cb594cdfe9..94c530d1ce0c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -322,6 +322,15 @@ struct rt_bandwidth {
unsigned int rt_period_active;
};
+struct dl_bandwidth {
+ raw_spinlock_t dl_runtime_lock;
+ u64 dl_runtime;
+ u64 dl_internal_runtime;
+ u64 dl_period;
+ struct task_group *active_context;
+};
+
+
static inline int dl_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
@@ -499,10 +508,17 @@ struct task_group {
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Each task group manages a different scheduling entity per CPU, i.e. a
+ * different deadline server, and a runqueue per CPU. All the dl-servers
+ * share the same dl_bandwidth object.
+ */
struct sched_rt_entity **rt_se;
+ struct sched_dl_entity **dl_se;
struct rt_rq **rt_rq;
struct rt_bandwidth rt_bandwidth;
+ struct dl_bandwidth dl_bandwidth;
#endif
struct scx_task_group scx;
@@ -906,6 +922,12 @@ struct rt_rq {
#ifdef CONFIG_CGROUP_SCHED
struct task_group *tg; /* this tg has "this" rt_rq on given CPU for runnable entities */
#endif
+
+ /*
+ * The cgroup's served runqueue if the rt_rq entity belongs to a cgroup,
+ * otherwise the top-level global runqueue.
+ */
+ struct rq *rq;
};
static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 09/29] sched/core: Initialize HCBS specific structures.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (7 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 08/29] sched/rt: Introduce HCBS specific structs in task_group Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 10/29] sched/deadline: Add dl_init_tg Yuri Andriaccio
` (19 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Update autogroups' creation/destruction to use the new data structures.
Initialize the default bandwidth for rt-cgroups (sched_init).
Initialize rt-scheduler's specific data structures for the root control
group (sched_init).
Remove init_tg_rt_entry in favour of manual setup of the necessary data
structures in sched_init.
Add utility functions to check (and get) if a rt_rq entity is connected
to a rt-cgroup.
Add read/write accessors for dl_bandwidth.
Add dl_bw_lock_of_tg macro to reference the a task group dl_bandwidth's
spinlock.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
---
kernel/sched/autogroup.c | 4 ++--
kernel/sched/core.c | 11 ++++++++--
kernel/sched/deadline.c | 11 ++++++++++
kernel/sched/rt.c | 45 ++++++++++++++++++++++++++++------------
kernel/sched/sched.h | 38 ++++++++++++++++++++++++++++++---
5 files changed, 89 insertions(+), 20 deletions(-)
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index e380cf9372bb..2122a0740a19 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -52,7 +52,7 @@ static inline void autogroup_destroy(struct kref *kref)
#ifdef CONFIG_RT_GROUP_SCHED
/* We've redirected RT tasks to the root task group... */
- ag->tg->rt_se = NULL;
+ ag->tg->dl_se = NULL;
ag->tg->rt_rq = NULL;
#endif
sched_release_group(ag->tg);
@@ -109,7 +109,7 @@ static inline struct autogroup *autogroup_create(void)
* the policy change to proceed.
*/
free_rt_sched_group(tg);
- tg->rt_se = root_task_group.rt_se;
+ tg->dl_se = root_task_group.dl_se;
tg->rt_rq = root_task_group.rt_rq;
#endif /* CONFIG_RT_GROUP_SCHED */
tg->autogroup = ag;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f5817136c8dd..f1d43e77c711 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8938,7 +8938,7 @@ void __init sched_init(void)
#ifdef CONFIG_RT_GROUP_SCHED
ptr += 2 * nr_cpu_ids * sizeof(void **);
ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
- root_task_group.rt_se = (struct sched_rt_entity **)ptr;
+ root_task_group.dl_se = (struct sched_dl_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.rt_rq = (struct rt_rq **)ptr;
@@ -8948,6 +8948,11 @@ void __init sched_init(void)
init_defrootdomain();
+#ifdef CONFIG_RT_GROUP_SCHED
+ init_dl_bandwidth(&root_task_group.dl_bandwidth,
+ global_rt_period(), 0, &root_task_group);
+#endif /* CONFIG_RT_GROUP_SCHED */
+
#ifdef CONFIG_CGROUP_SCHED
task_group_cache = KMEM_CACHE(task_group, 0);
@@ -8999,7 +9004,9 @@ void __init sched_init(void)
* starts working after scheduler_running, which is not the case
* yet.
*/
- init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
+ rq->rt.tg = &root_task_group;
+ root_task_group.rt_rq[i] = &rq->rt;
+ root_task_group.dl_se[i] = NULL;
#endif
rq->next_class = &idle_sched_class;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index bc3ac4be8382..aceeb28d4b2b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -508,6 +508,17 @@ static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq
static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
+void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime,
+ struct task_group *active_context)
+{
+ raw_spin_lock_init(&dl_b->dl_runtime_lock);
+ dl_b->dl_period = period;
+ dl_b->dl_runtime = runtime;
+ dl_b->dl_internal_runtime = 0;
+ dl_b->active_context = active_context;
+}
+
+
void init_dl_bw(struct dl_bw *dl_b)
{
raw_spin_lock_init(&dl_b->lock);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 16eb027d4bdd..3ca932ddcf75 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -86,26 +86,47 @@ void init_rt_rq(struct rt_rq *rt_rq)
#ifdef CONFIG_RT_GROUP_SCHED
-void unregister_rt_sched_group(struct task_group *tg)
+DEFINE_MUTEX(rt_constraints_mutex);
+
+const struct dl_bandwidth *dl_bandwidth_read(struct task_group *tg)
{
+ int held;
+
+ if (IS_ENABLED(CONFIG_LOCKDEP) && debug_locks) {
+ held = 0;
+ if (lockdep_is_held(&rt_constraints_mutex)) {
+ __assume_ctx_lock(&rt_constraints_mutex);
+ held = 1;
+ }
+
+ if (lockdep_is_held(dl_bw_lock_of_tg(tg))) {
+ __assume_ctx_lock(dl_bw_lock_of_tg(tg));
+ held = 1;
+ }
+ lockdep_assert(held);
+ }
+
+ return (const struct dl_bandwidth *)&tg->dl_bandwidth;
}
-void free_rt_sched_group(struct task_group *tg)
+struct dl_bandwidth *dl_bandwidth_write(struct task_group *tg)
{
- if (!rt_group_sched_enabled())
- return;
+ lockdep_assert_held(&rt_constraints_mutex);
+ lockdep_assert_held(dl_bw_lock_of_tg(tg));
+
+ return &tg->dl_bandwidth;
}
-void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
- struct sched_rt_entity *rt_se, int cpu,
- struct sched_rt_entity *parent)
+void unregister_rt_sched_group(struct task_group *tg)
{
- rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
- rt_rq->tg = tg;
- tg->rt_rq[cpu] = rt_rq;
- tg->rt_se[cpu] = rt_se;
+}
+
+void free_rt_sched_group(struct task_group *tg)
+{
+ if (!rt_group_sched_enabled())
+ return;
}
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
@@ -1824,8 +1845,6 @@ DEFINE_SCHED_CLASS(rt) = {
/*
* Ensure that the real time constraints are schedulable.
*/
-static DEFINE_MUTEX(rt_constraints_mutex);
-
static inline int tg_has_rt_tasks(struct task_group *tg)
{
struct task_struct *task;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 94c530d1ce0c..e8a62b37a72d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -598,9 +598,6 @@ extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern bool cfs_task_bw_constrained(struct task_struct *p);
-extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
- struct sched_rt_entity *rt_se, int cpu,
- struct sched_rt_entity *parent);
extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
extern long sched_group_rt_runtime(struct task_group *tg);
@@ -3070,6 +3067,8 @@ extern void resched_curr(struct rq *rq);
extern void resched_curr_lazy(struct rq *rq);
extern void resched_cpu(int cpu);
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime,
+ struct task_group *active_context);
extern void init_dl_entity(struct sched_dl_entity *dl_se);
extern void init_cfs_throttle_work(struct task_struct *p);
@@ -3512,6 +3511,9 @@ extern void set_rq_offline(struct rq *rq);
extern bool sched_smp_initialized;
+extern const struct dl_bandwidth *dl_bandwidth_read(struct task_group *tg);
+extern struct dl_bandwidth *dl_bandwidth_write(struct task_group *tg);
+
#ifdef CONFIG_RT_GROUP_SCHED
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
@@ -3535,6 +3537,24 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
WARN_ON(!rt_group_sched_enabled() && rt_se->rt_rq->tg != &root_task_group);
return rt_se->rt_rq;
}
+
+static inline int is_dl_group(struct rt_rq *rt_rq)
+{
+ return rt_rq->tg != &root_task_group;
+}
+
+/*
+ * Return the scheduling entity of this group of tasks.
+ */
+static inline struct sched_dl_entity *dl_group_of(struct rt_rq *rt_rq)
+{
+ if (WARN_ON_ONCE(!is_dl_group(rt_rq)))
+ return NULL;
+
+ return rt_rq->tg->dl_se[rq_of_rt_rq(rt_rq)->cpu];
+}
+
+#define dl_bw_lock_of_tg(tg) (&(tg)->dl_bandwidth.dl_runtime_lock)
#else
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
@@ -3557,6 +3577,18 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
return &rq->rt;
}
+
+static inline int is_dl_group(struct rt_rq *rt_rq)
+{
+ return 0;
+}
+
+static inline struct sched_dl_entity *dl_group_of(struct rt_rq *rt_rq)
+{
+ return NULL;
+}
+
+#define dl_bw_lock_of_tg(tg) ((raw_spinlock_t*)NULL)
#endif
DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 10/29] sched/deadline: Add dl_init_tg
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (8 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 09/29] sched/core: Initialize HCBS specific structures Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 11/29] sched/rt: Add {alloc/unregister/free}_rt_sched_group Yuri Andriaccio
` (18 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Add dl_init_tg to initialize and/or update a rt-cgroup dl_server and to
also account the allocated bandwidth. This function is currently unhooked
and will be later used to allocate bandwidth to rt-cgroups.
Add lock guard for raw_spin_rq_lock_irq for cleaner code.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
---
kernel/sched/deadline.c | 31 +++++++++++++++++++++++++++++++
kernel/sched/sched.h | 1 +
2 files changed, 32 insertions(+)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index aceeb28d4b2b..b6b5fcb15f43 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -335,6 +335,37 @@ void cancel_inactive_timer(struct sched_dl_entity *dl_se)
cancel_dl_timer(dl_se, &dl_se->inactive_timer);
}
+#ifdef CONFIG_RT_GROUP_SCHED
+void dl_init_tg(struct sched_dl_entity *dl_se, u64 rt_runtime, u64 rt_period)
+{
+ struct rq *rq = container_of_const(dl_se->dl_rq, struct rq, dl);
+ int is_active;
+ u64 new_bw;
+
+ guard(rq_lock_irq)(rq);
+ is_active = dl_se->my_q->rt.rt_nr_running > 0;
+
+ update_rq_clock(rq);
+ dl_server_stop(dl_se);
+
+ new_bw = to_ratio(rt_period, rt_runtime);
+ dl_rq_change_utilization(rq, dl_se, new_bw);
+
+ dl_se->dl_runtime = rt_runtime;
+ dl_se->dl_deadline = rt_period;
+ dl_se->dl_period = rt_period;
+
+ dl_se->runtime = 0;
+ dl_se->deadline = 0;
+
+ dl_se->dl_bw = new_bw;
+ dl_se->dl_density = new_bw;
+
+ if (is_active)
+ dl_server_start(dl_se);
+}
+#endif
+
static void dl_change_utilization(struct task_struct *p, u64 new_bw)
{
WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e8a62b37a72d..b55ce13412d6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -425,6 +425,7 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq,
struct rq *served_rq,
dl_server_pick_f pick_task);
extern void sched_init_dl_servers(void);
+extern void dl_init_tg(struct sched_dl_entity *dl_se, u64 rt_runtime, u64 rt_period);
extern void fair_server_init(struct rq *rq);
extern void ext_server_init(struct rq *rq);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 11/29] sched/rt: Add {alloc/unregister/free}_rt_sched_group
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (9 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 10/29] sched/deadline: Add dl_init_tg Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 12/29] sched/deadline: Account rt-cgroups bandwidth in deadline tasks schedulability tests Yuri Andriaccio
` (17 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Add allocation and deallocation code for rt-cgroups.
Declare dl_server specific functions (only skeleton, but no
implementation yet), needed by the deadline servers to be called when
trying to schedule.
Initialize a cgroup's active context to that of its parent.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/rt.c | 156 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 154 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3ca932ddcf75..e6f018db7579 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -120,24 +120,176 @@ struct dl_bandwidth *dl_bandwidth_write(struct task_group *tg)
void unregister_rt_sched_group(struct task_group *tg)
{
+ int i;
+
+ if (!rt_group_sched_enabled())
+ return;
+
+ if (!tg->dl_se || !tg->rt_rq)
+ return;
+ for_each_possible_cpu(i) {
+ if (!tg->dl_se[i] || !tg->rt_rq[i])
+ continue;
+
+ if (tg->dl_se[i]->dl_runtime)
+ dl_init_tg(tg->dl_se[i], 0, tg->dl_se[i]->dl_period);
+ }
}
void free_rt_sched_group(struct task_group *tg)
{
+ int i;
+
if (!rt_group_sched_enabled())
return;
+
+ if (!tg->dl_se || !tg->rt_rq)
+ return;
+
+ for_each_possible_cpu(i) {
+ if (!tg->dl_se[i] || !tg->rt_rq[i])
+ continue;
+
+ /*
+ * Shutdown the dl_server and free it
+ *
+ * Since the dl timer is going to be cancelled,
+ * we risk to never decrease the running bw...
+ * Fix this issue by changing the group runtime
+ * to 0 immediately before freeing it.
+ */
+ if (tg->dl_se[i]->dl_runtime)
+ dl_init_tg(tg->dl_se[i], 0, tg->dl_se[i]->dl_period);
+
+ hrtimer_cancel(&tg->dl_se[i]->dl_timer);
+ hrtimer_cancel(&tg->dl_se[i]->inactive_timer);
+ kfree(tg->dl_se[i]);
+
+ /* Free the local per-cpu runqueue */
+ kfree(rq_of_rt_rq(tg->rt_rq[i]));
+ }
+
+ kfree(tg->rt_rq);
+ kfree(tg->dl_se);
}
+static inline void __rt_rq_free(struct rt_rq **rt_rq)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ if (rt_rq[i])
+ kfree(rq_of_rt_rq(rt_rq[i]));
+ }
+
+ kfree(rt_rq);
+}
+
+DEFINE_FREE(rt_rq_free, struct rt_rq **, if (_T) __rt_rq_free(_T))
+
+static inline void __dl_se_free(struct sched_dl_entity **dl_se)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ kfree(dl_se[i]);
+ }
+
+ kfree(dl_se);
+}
+
+DEFINE_FREE(dl_se_free, struct sched_dl_entity **, if (_T) __dl_se_free(_T))
+
+static int __alloc_rt_sched_group_data(struct task_group *tg) {
+ /* Instantiate automatic cleanup in event of kalloc fail */
+ struct rt_rq **tg_rt_rq __free(rt_rq_free) = NULL;
+ struct sched_dl_entity **tg_dl_se __free(dl_se_free) = NULL;
+ struct sched_dl_entity *dl_se __free(kfree) = NULL;
+ struct rq *s_rq __free(kfree) = NULL;
+ int i;
+
+ tg_rt_rq = kcalloc(nr_cpu_ids, sizeof(struct rt_rq *), GFP_KERNEL);
+ if (!tg_rt_rq)
+ return 0;
+
+ tg_dl_se = kcalloc(nr_cpu_ids,
+ sizeof(struct sched_dl_entity *), GFP_KERNEL);
+ if (!tg_dl_se)
+ return 0;
+
+ for_each_possible_cpu(i) {
+ s_rq = kzalloc_node(sizeof(struct rq),
+ GFP_KERNEL, cpu_to_node(i));
+ if (!s_rq)
+ return 0;
+
+ dl_se = kzalloc_node(sizeof(struct sched_dl_entity),
+ GFP_KERNEL, cpu_to_node(i));
+ if (!dl_se)
+ return 0;
+
+ tg_rt_rq[i] = &no_free_ptr(s_rq)->rt;
+ tg_dl_se[i] = no_free_ptr(dl_se);
+ }
+
+ tg->rt_rq = no_free_ptr(tg_rt_rq);
+ tg->dl_se = no_free_ptr(tg_dl_se);
+
+ return 1;
+}
+
+static struct task_struct *rt_server_pick(struct sched_dl_entity *dl_se, struct rq_flags *rf);
+
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
+ struct sched_dl_entity *dl_se;
+ struct rq *s_rq;
+ int i;
+
if (!rt_group_sched_enabled())
return 1;
+ /* Allocate all necessary resources beforehand */
+ if (!__alloc_rt_sched_group_data(tg))
+ return 0;
+
+ /* Initialize the allocated resources now. */
+ scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(parent)) {
+ init_dl_bandwidth(&tg->dl_bandwidth, 0, RUNTIME_INF,
+ dl_bandwidth_read(parent)->active_context);
+ }
+
+ for_each_possible_cpu(i) {
+ s_rq = rq_of_rt_rq(tg->rt_rq[i]);
+ dl_se = tg->dl_se[i];
+
+ init_rt_rq(&s_rq->rt);
+ s_rq->cpu = i;
+ s_rq->rt.tg = tg;
+
+ init_dl_entity(dl_se);
+ dl_se->dl_runtime = 0;
+ dl_se->dl_deadline = 0;
+ dl_se->dl_period = 0;
+ dl_se->runtime = 0;
+ dl_se->deadline = 0;
+ dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
+ dl_se->dl_server = 1;
+ dl_se->dl_bw_attached = 1;
+ dl_server_init(dl_se, &cpu_rq(i)->dl, s_rq, rt_server_pick);
+ }
+
return 1;
}
-#else /* !CONFIG_RT_GROUP_SCHED: */
+static struct task_struct *rt_server_pick(struct sched_dl_entity *dl_se, struct rq_flags *rf)
+{
+ return NULL;
+}
+
+#else /* !CONFIG_RT_GROUP_SCHED */
void unregister_rt_sched_group(struct task_group *tg) { }
@@ -147,7 +299,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
return 1;
}
-#endif /* !CONFIG_RT_GROUP_SCHED */
+#endif /* CONFIG_RT_GROUP_SCHED */
static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
{
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 12/29] sched/deadline: Account rt-cgroups bandwidth in deadline tasks schedulability tests.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (10 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 11/29] sched/rt: Add {alloc/unregister/free}_rt_sched_group Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:35 ` [RFC PATCH v7 13/29] sched/rt: Implement dl-server operations for rt-cgroups Yuri Andriaccio
` (16 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Account the rt-cgroups hierarchy's reserved bandwidth in the
schedulability test of deadline entities. This mechanism allows to
completely reserve portion of the rt-bandwidth to rt-cgroups even if
they do not use all of it.
Account for the rt-cgroups' reserved bandwidth also when changing the
total dedicated bandwidth for real time tasks.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
---
kernel/sched/deadline.c | 58 +++++++++++++++++++++++++++++------------
1 file changed, 41 insertions(+), 17 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b6b5fcb15f43..7c2f4d2c9301 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -127,14 +127,17 @@ static inline struct dl_bw *dl_bw_of(int i)
return &cpu_rq(i)->rd->dl_bw;
}
-static inline int dl_bw_cpus(int i)
+static inline int __dl_bw_cpus(const struct cpumask *mask)
{
- struct root_domain *rd = cpu_rq(i)->rd;
+ return cpumask_weight_and(mask, cpu_active_mask);
+}
+static inline int dl_bw_cpus(int i)
+{
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
"sched RCU must be held");
- return cpumask_weight_and(rd->span, cpu_active_mask);
+ return __dl_bw_cpus(cpu_rq(i)->rd->span);
}
static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
@@ -205,11 +208,25 @@ void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
__dl_update(dl_b, -((s32)tsk_bw / cpus));
}
+static inline u64 get_dl_groups_bw(void)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+ const struct dl_bandwidth *dl_b;
+
+ guard(raw_spinlock_irqsave)(dl_bw_lock_of_tg(&root_task_group));
+ dl_b = dl_bandwidth_read(&root_task_group);
+ return to_ratio(dl_b->dl_period, dl_b->dl_runtime);
+#else
+ return 0;
+#endif
+}
+
static inline bool
-__dl_overflow(struct dl_bw *dl_b, unsigned long cap, u64 old_bw, u64 new_bw)
+__dl_overflow(struct dl_bw *dl_b, unsigned long cap, int cpus, u64 old_bw, u64 new_bw)
{
return dl_b->bw != -1 &&
- cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
+ cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw
+ + get_dl_groups_bw() * cpus;
}
static inline
@@ -1937,7 +1954,7 @@ 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);
- if (__dl_overflow(dl_b, cap, old_bw, new_bw))
+ if (__dl_overflow(dl_b, cap, cpus, old_bw, new_bw))
return -EBUSY;
if (init) {
@@ -1984,7 +2001,7 @@ static int __dl_server_attach_bw_locked(struct sched_dl_entity *dl_se,
*/
if (cpu_active(cpu_of(rq))) {
cap = dl_bw_capacity(cpu_of(rq));
- if (__dl_overflow(dl_b, cap, 0, dl_se->dl_bw))
+ if (__dl_overflow(dl_b, cap, cpus, 0, dl_se->dl_bw))
return -EBUSY;
__dl_add(dl_b, dl_se->dl_bw, cpus);
}
@@ -3710,8 +3727,9 @@ int sched_dl_global_validate(void)
u64 period = global_rt_period();
u64 new_bw = to_ratio(period, runtime);
u64 cookie = ++dl_cookie;
+ u64 dl_groups_root = get_dl_groups_bw();
struct dl_bw *dl_b;
- int cpu, cpus, ret = 0;
+ int cpu, cap, cpus, ret = 0;
unsigned long flags;
/*
@@ -3726,10 +3744,12 @@ int sched_dl_global_validate(void)
goto next;
dl_b = dl_bw_of(cpu);
+ cap = dl_bw_capacity(cpu);
cpus = dl_bw_cpus(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 +
+ dl_groups_root * cpus)
ret = -EBUSY;
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
@@ -3823,13 +3843,13 @@ int sched_dl_overflow(struct task_struct *p, int policy,
cap = dl_bw_capacity(cpu);
if (dl_policy(policy) && !task_has_dl_policy(p) &&
- !__dl_overflow(dl_b, cap, 0, new_bw)) {
+ !__dl_overflow(dl_b, cap, cpus, 0, new_bw)) {
if (hrtimer_active(&p->dl.inactive_timer))
__dl_sub(dl_b, p->dl.dl_bw, cpus);
__dl_add(dl_b, new_bw, cpus);
err = 0;
} else if (dl_policy(policy) && task_has_dl_policy(p) &&
- !__dl_overflow(dl_b, cap, p->dl.dl_bw, new_bw)) {
+ !__dl_overflow(dl_b, cap, cpus, p->dl.dl_bw, new_bw)) {
/*
* XXX this is slightly incorrect: when the task
* utilization decreases, we should delay the total
@@ -4007,13 +4027,14 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
{
unsigned long flags, cap;
struct dl_bw *cur_dl_b;
- int ret = 1;
+ int cpus, ret = 1;
rcu_read_lock_sched();
cur_dl_b = dl_bw_of(cpumask_any(cur));
cap = __dl_bw_capacity(trial);
+ cpus = __dl_bw_cpus(trial);
raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
- if (__dl_overflow(cur_dl_b, cap, 0, 0))
+ if (__dl_overflow(cur_dl_b, cap, cpus, 0, 0))
ret = 0;
raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
rcu_read_unlock_sched();
@@ -4030,6 +4051,7 @@ enum dl_bw_request {
static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
{
unsigned long flags, cap;
+ int cpus;
struct dl_bw *dl_b;
bool overflow = 0;
u64 dl_server_bw = 0;
@@ -4039,12 +4061,13 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
raw_spin_lock_irqsave(&dl_b->lock, flags);
cap = dl_bw_capacity(cpu);
+ cpus = dl_bw_cpus(cpu);
switch (req) {
case dl_bw_req_free:
__dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
break;
case dl_bw_req_alloc:
- overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
+ overflow = __dl_overflow(dl_b, cap, cpus, 0, dl_bw);
if (!overflow) {
/*
@@ -4053,7 +4076,7 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
* We will free resources in the source root_domain
* later on (see set_cpus_allowed_dl()).
*/
- __dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
+ __dl_add(dl_b, dl_bw, cpus);
}
break;
case dl_bw_req_deactivate:
@@ -4063,6 +4086,7 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
* turn cpu off?).
*/
cap -= arch_scale_cpu_capacity(cpu);
+ cpus -= 1;
/*
* cpu is going offline and NORMAL and EXT tasks will be
@@ -4083,8 +4107,8 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
* 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, dl_server_bw, 0);
+ if (cpus)
+ overflow = __dl_overflow(dl_b, cap, cpus, dl_server_bw, 0);
else
overflow = 1;
}
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 13/29] sched/rt: Implement dl-server operations for rt-cgroups.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (11 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 12/29] sched/deadline: Account rt-cgroups bandwidth in deadline tasks schedulability tests Yuri Andriaccio
@ 2026-11-09 16:35 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 14/29] sched/rt: Update task event callbacks for HCBS scheduling Yuri Andriaccio
` (15 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:35 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Implement rt_server_pick, the callback that deadline servers use to
pick a task to schedule.
rt_server_pick(): pick the next runnable rt task and tell the
scheduler that it is going to be scheduled next.
Let enqueue_task_rt function start the attached deadline server when the
first task is enqueued on a specific rq/server.
The server is not symmetrically stopped in dequeue_task_rt as it is
stopped when server_pick_task returns NULL (see deadline.c).
Change update_curr_rt to perform a deadline server update if the
updated task is served by non-root group.
Update {enqueue/dequeue}_pushable_task and rt_{set/clear}_overload to
only set the CPU-wise overload flag only if the root runqueues are
overloaded, but not for HCBS runqueues.
Update inc/dec_dl_tasks to account the number of active tasks in the
local runqueue for rt-cgroups servers, as their local runqueue is
different from the global runqueue, and thus when a rt-group server is
activated/deactivated, the number of served tasks' must be
added/removed. This uses nr_running to be compatible with future
dl-server interfaces. Account also the deadline server so that it is
picked for shutdown when its runqueue is empty (future patches will
try to pull tasks before stopping).
Update inc/dec_rt_prio_smp to change a rq's cpupri only if the rt_rq
is the global runqueue, since cgroups are scheduled via their
dl-server priority.
Update inc/dec_rt_tasks to account for waking/sleeping tasks on the
global runqueue, when the task runs on the root cgroup, or its local
dl server is active. The accounting is not done when servers are
throttled, as they will add/sub the number of tasks running when they
get enqueued/dequeued. For rt cgroups, account for the number of active
tasks in the nr_running field of the local runqueue (add/sub_nr_running),
as this number is used when a dl server is enqueued/dequeued.
Update set_task_rq to record the rt_rq of the cgroup's active_context,
tracking where to schedule the given task.
Update set_task_rq to record the dl_rq, tracking which deadline
server manages a task.
Update set_task_rq to not use the parent field anymore, as it is
unused by this patchset's code. Remove the unused parent field from
sched_rt_entity.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
include/linux/sched.h | 1 -
kernel/sched/deadline.c | 8 +++++
kernel/sched/rt.c | 70 ++++++++++++++++++++++++++++++++++++-----
kernel/sched/sched.h | 17 +++++-----
4 files changed, 80 insertions(+), 16 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index febc03b02fa4..8780ef5def7e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -629,7 +629,6 @@ struct sched_rt_entity {
struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
- struct sched_rt_entity *parent;
/* rq on which this entity is (to be) queued: */
struct rt_rq *rt_rq;
/* rq "owned" by this entity/group: */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7c2f4d2c9301..17f303294d6c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2293,6 +2293,10 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
if (!dl_server(dl_se))
add_nr_running(rq_of_dl_rq(dl_rq), 1);
+ else if (rq_of_dl_se(dl_se) != dl_se->my_q) {
+ WARN_ON(dl_se->my_q->rt.rt_nr_running != dl_se->my_q->nr_running);
+ add_nr_running(rq_of_dl_rq(dl_rq), dl_se->my_q->nr_running + 1);
+ }
inc_dl_deadline(dl_rq, deadline);
}
@@ -2305,6 +2309,10 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
if (!dl_server(dl_se))
sub_nr_running(rq_of_dl_rq(dl_rq), 1);
+ else if (rq_of_dl_se(dl_se) != dl_se->my_q) {
+ WARN_ON(dl_se->my_q->rt.rt_nr_running != dl_se->my_q->nr_running);
+ sub_nr_running(rq_of_dl_rq(dl_rq), dl_se->my_q->nr_running + 1);
+ }
dec_dl_deadline(dl_rq, dl_se->deadline);
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e6f018db7579..ec0198902b70 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -284,9 +284,19 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
return 1;
}
+static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq);
+
static struct task_struct *rt_server_pick(struct sched_dl_entity *dl_se, struct rq_flags *rf)
{
- return NULL;
+ struct rt_rq *rt_rq = &dl_se->my_q->rt;
+ struct task_struct *p;
+
+ if (!sched_rt_runnable(dl_se->my_q))
+ return NULL;
+
+ p = rt_task_of(pick_next_rt_entity(rt_rq));
+
+ return p;
}
#else /* !CONFIG_RT_GROUP_SCHED */
@@ -314,6 +324,9 @@ static inline int rt_overloaded(struct rq *rq)
static inline void rt_set_overload(struct rq *rq)
{
+ if (is_dl_group(&rq->rt))
+ return;
+
if (!rq->online)
return;
@@ -333,6 +346,9 @@ static inline void rt_set_overload(struct rq *rq)
static inline void rt_clear_overload(struct rq *rq)
{
+ if (is_dl_group(&rq->rt))
+ return;
+
if (!rq->online)
return;
@@ -392,7 +408,7 @@ static void enqueue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
rt_rq->highest_prio.next = p->prio;
if (!rt_rq->overloaded) {
- rt_set_overload(global_rq_of_rt_rq(rt_rq));
+ rt_set_overload(rq_of_rt_rq(rt_rq));
rt_rq->overloaded = 1;
}
}
@@ -410,7 +426,7 @@ static void dequeue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
rt_rq->highest_prio.next = MAX_RT_PRIO-1;
if (rt_rq->overloaded) {
- rt_clear_overload(global_rq_of_rt_rq(rt_rq));
+ rt_clear_overload(rq_of_rt_rq(rt_rq));
rt_rq->overloaded = 0;
}
}
@@ -511,6 +527,7 @@ static inline int rt_se_prio(struct sched_rt_entity *rt_se)
static void update_curr_rt(struct rq *rq)
{
struct task_struct *donor = rq->donor;
+ struct rt_rq *rt_rq;
s64 delta_exec;
if (donor->sched_class != &rt_sched_class)
@@ -520,21 +537,32 @@ static void update_curr_rt(struct rq *rq)
if (unlikely(delta_exec <= 0))
return;
- if (!rt_bandwidth_enabled())
+ if (!rt_group_sched_enabled())
+ return;
+
+ if (!dl_bandwidth_enabled())
return;
+
+ rt_rq = rt_rq_of_se(&donor->rt);
+ if (is_dl_group(rt_rq)) {
+ struct sched_dl_entity *dl_se = dl_group_of(rt_rq);
+
+ dl_server_update(dl_se, delta_exec);
+ }
}
static void
inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
- struct rq *rq = rq_of_rt_rq(rt_rq);
+ struct rq *rq;
/*
* Change rq's cpupri only if rt_rq is the top queue.
*/
- if (IS_ENABLED(CONFIG_RT_GROUP_SCHED) && &rq->rt != rt_rq)
+ if (is_dl_group(rt_rq))
return;
+ rq = rq_of_rt_rq(rt_rq);
if (rq->online && prio < prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
}
@@ -542,14 +570,15 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
static void
dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
- struct rq *rq = rq_of_rt_rq(rt_rq);
+ struct rq *rq;
/*
* Change rq's cpupri only if rt_rq is the top queue.
*/
- if (IS_ENABLED(CONFIG_RT_GROUP_SCHED) && &rq->rt != rt_rq)
+ if (is_dl_group(rt_rq))
return;
+ rq = rq_of_rt_rq(rt_rq);
if (rq->online && rt_rq->highest_prio.curr != prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
}
@@ -610,6 +639,15 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
rt_rq->rr_nr_running += is_rr_task(rt_se);
inc_rt_prio(rt_rq, rt_se_prio(rt_se));
+
+ if (is_dl_group(rt_rq)) {
+ struct sched_dl_entity *dl_se = dl_group_of(rt_rq);
+
+ if (!dl_se->dl_throttled)
+ add_nr_running(global_rq_of_rt_rq(rt_rq), 1);
+ }
+
+ add_nr_running(rq_of_rt_rq(rt_rq), 1);
}
static inline
@@ -620,6 +658,15 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
rt_rq->rr_nr_running -= is_rr_task(rt_se);
dec_rt_prio(rt_rq, rt_se_prio(rt_se));
+
+ if (is_dl_group(rt_rq)) {
+ struct sched_dl_entity *dl_se = dl_group_of(rt_rq);
+
+ if (!dl_se->dl_throttled)
+ sub_nr_running(global_rq_of_rt_rq(rt_rq), 1);
+ }
+
+ sub_nr_running(rq_of_rt_rq(rt_rq), 1);
}
/*
@@ -815,6 +862,13 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
check_schedstat_required();
update_stats_wait_start_rt(rt_rq_of_se(rt_se), rt_se);
+ /* Task arriving in an idle group of tasks. */
+ if (is_dl_group(rt_rq) && rt_rq->rt_nr_running == 0) {
+ struct sched_dl_entity *dl_se = dl_group_of(rt_rq);
+
+ dl_server_start(dl_se);
+ }
+
enqueue_rt_entity(rt_se, flags);
if (task_is_blocked(p))
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b55ce13412d6..0166e75c7733 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2427,15 +2427,12 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
#endif
#ifdef CONFIG_RT_GROUP_SCHED
- /*
- * p->rt.rt_rq is NULL initially and it is easier to assign
- * root_task_group's rt_rq than switching in rt_rq_of_se()
- * Clobbers tg(!)
- */
if (!rt_group_sched_enabled())
tg = &root_task_group;
- p->rt.rt_rq = tg->rt_rq[cpu];
- p->rt.parent = tg->rt_se[cpu];
+
+ guard(raw_spinlock_irqsave)(&tg->dl_bandwidth.dl_runtime_lock);
+ p->rt.rt_rq = tg->dl_bandwidth.active_context->rt_rq[cpu];
+ p->dl.dl_rq = &cpu_rq(cpu)->dl;
#endif /* CONFIG_RT_GROUP_SCHED */
}
@@ -3116,6 +3113,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
unsigned prev_nr = rq->nr_running;
rq->nr_running = prev_nr + count;
+ if (rq != cpu_rq(rq->cpu))
+ return;
+
if (trace_sched_update_nr_running_tp_enabled()) {
call_trace_sched_update_nr_running(rq, count);
}
@@ -3129,6 +3129,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
static inline void sub_nr_running(struct rq *rq, unsigned count)
{
rq->nr_running -= count;
+ if (rq != cpu_rq(rq->cpu))
+ return;
+
if (trace_sched_update_nr_running_tp_enabled()) {
call_trace_sched_update_nr_running(rq, -count);
}
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 14/29] sched/rt: Update task event callbacks for HCBS scheduling
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (12 preceding siblings ...)
2026-11-09 16:35 ` [RFC PATCH v7 13/29] sched/rt: Implement dl-server operations for rt-cgroups Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 15/29] sched/rt: Remove support for cgroups-v1 Yuri Andriaccio
` (14 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Update wakeup_preempt_rt, switched_{from/to}_rt and prio_changed_rt with
rt-cgroup's specific preemption rules:
- In wakeup_preempt_rt(), whenever a task wakes up, it must be checked if
it is served by a deadline server or it lives on the global runqueue.
Preemption rules (as documented in the function), change based on the
current task's donor and woken task runqueue:
- If both tasks are FIFO/RR tasks on the global runqueue, or the same
cgroup, run as normal.
- If woken is inside a cgroup, but donor is a FIFO task on the global
runqueue, always preempt. If donor is a DEADLINE task, check if the dl
server preempts donor.
- If both tasks are FIFO/RR tasks in served but different groups, check
whether the woken server preempts the donor server.
- In prio_changed_rt(), if the task is not running, only run preemption
checks if the running task resides on the same task group of the task
that changed priority.
Update sched_rt_can_attach() to check if a task can be attached to a given
cgroup. For now the check only consists in checking if the group has
non-zero bandwidth. Remove the tsk argument from sched_rt_can_attach, as
it is unused.
Change cpu_cgroup_can_attach() to check if the attachee is a FIFO/RR
task before attaching it to a cgroup.
Update __sched_setscheduler() to perform checks when trying to switch
to FIFO/RR for a task inside a cgroup, as the group needs to have
runtime allocated.
Update task_is_throttled_rt() for SCHED_CORE, returning the is_throttled
value of the server if present, while global rt-tasks are never throttled.
Update migration functions to ignore cgroups migration, to be implemented
in later patches.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 2 +-
kernel/sched/rt.c | 108 +++++++++++++++++++++++++++++++++++++---
kernel/sched/sched.h | 2 +-
kernel/sched/syscalls.c | 12 +++++
4 files changed, 115 insertions(+), 9 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f1d43e77c711..0425d2c98240 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9577,7 +9577,7 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
goto scx_check;
cgroup_taskset_for_each(task, css, tset) {
- if (!sched_rt_can_attach(css_tg(css), task))
+ if (rt_task(task) && !sched_rt_can_attach(css_tg(css)))
return -EINVAL;
}
scx_check:
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ec0198902b70..b7ea6b5da9e4 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -372,6 +372,9 @@ static inline void rt_queue_push_tasks(struct rt_rq *rt_rq)
{
struct rq *rq = global_rq_of_rt_rq(rt_rq);
+ if (is_dl_group(rt_rq))
+ return;
+
if (!has_pushable_tasks(rt_rq))
return;
@@ -382,6 +385,9 @@ static inline void rt_queue_pull_task(struct rt_rq *rt_rq)
{
struct rq *rq = global_rq_of_rt_rq(rt_rq);
+ if (is_dl_group(rt_rq))
+ return;
+
queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task);
}
@@ -832,6 +838,9 @@ static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
__enqueue_rt_entity(rt_se, flags);
+ if (is_dl_group((rt_rq)))
+ return;
+
cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
}
@@ -844,6 +853,9 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags)
__dequeue_rt_entity(rt_se, flags);
+ if (is_dl_group((rt_rq)))
+ return;
+
cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
}
@@ -1046,7 +1058,56 @@ static int balance_rt(struct rq *rq, struct rq_flags *rf)
static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
{
struct task_struct *donor = rq->donor;
+ struct sched_dl_entity *woken_dl_se = NULL;
+ struct sched_dl_entity *donor_dl_se = NULL;
+
+ if (!rt_group_sched_enabled())
+ goto same_group_sched;
+ /*
+ * Preemption checks are different if the waking task and the current donor
+ * are running on the global runqueue or in a cgroup. The following rules
+ * apply:
+ * - dl-tasks (and equally dl_servers) always preempt FIFO/RR tasks.
+ * - if donor is a FIFO/RR task inside a cgroup (i.e. run by a
+ * dl_server), or donor is a DEADLINE task and waking is a FIFO/RR
+ * task on the root cgroup, do nothing.
+ * - if waking is inside a cgroup but donor is a FIFO/RR task in the
+ * root cgroup, always reschedule.
+ * - if they are both on the global runqueue or in the same cgroup, run
+ * the standard code.
+ * - if they are both in a cgroup, but not the same one, check whether the
+ * woken task's dl_server preempts the donor's dl_server.
+ * - if donor is a DEADLINE task and waking is in a cgroup, check whether
+ * the woken task's server preempts donor.
+ */
+ if (is_dl_group(rt_rq_of_se(&p->rt)))
+ woken_dl_se = dl_group_of(rt_rq_of_se(&p->rt));
+
+ if (task_has_dl_policy(donor))
+ donor_dl_se = &donor->dl;
+ else if (is_dl_group(rt_rq_of_se(&donor->rt)))
+ donor_dl_se = dl_group_of(rt_rq_of_se(&donor->rt));
+
+ if (woken_dl_se != NULL && donor_dl_se != NULL) {
+ if (woken_dl_se == donor_dl_se) {
+ goto same_group_sched;
+ }
+
+ if (dl_entity_preempt(woken_dl_se, donor_dl_se))
+ resched_curr(rq);
+
+ return;
+
+ } else if (woken_dl_se != NULL) {
+ resched_curr(rq);
+ return;
+
+ } else if (donor_dl_se != NULL) {
+ return;
+ }
+
+same_group_sched:
/*
* XXX If we're preempted by DL, queue a push?
*/
@@ -1071,7 +1132,8 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
* to move current somewhere else, making room for our non-migratable
* task.
*/
- if (p->prio == donor->prio && !test_tsk_need_resched(rq->curr))
+ if (!is_dl_group(rt_rq_of_se(&p->rt)) &&
+ p->prio == donor->prio && !test_tsk_need_resched(rq->curr))
check_preempt_equal_prio(rq, p);
}
@@ -1384,6 +1446,9 @@ static int push_rt_rq_task(struct rt_rq *rt_rq, bool pull)
struct rt_rq *lowest_rt_rq;
int ret = 0;
+ if (is_dl_group(rt_rq))
+ return 0;
+
if (!rt_rq->overloaded)
return 0;
@@ -1690,6 +1755,9 @@ static void pull_rt_rq_task(struct rt_rq *this_rt_rq)
struct rq *src_rq;
int rt_overload_count = rt_overloaded(this_rq);
+ if (is_dl_group(&this_rq->rt))
+ return;
+
if (likely(!rt_overload_count))
return;
@@ -1833,6 +1901,8 @@ static void rq_offline_rt(struct rq *rq)
*/
static void switched_from_rt(struct rq *rq, struct task_struct *p)
{
+ struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);
+
/*
* If there are other RT tasks then we will reschedule
* and the scheduling of the other RT tasks will handle
@@ -1840,10 +1910,10 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
* we may need to handle the pulling of RT tasks
* now.
*/
- if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
+ if (!task_on_rq_queued(p) || rt_rq->rt_nr_running)
return;
- rt_queue_pull_task(rt_rq_of_se(&p->rt));
+ rt_queue_pull_task(rt_rq);
}
void __init init_sched_rt_class(void)
@@ -1880,6 +1950,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
if (task_on_rq_queued(p)) {
if (p->nr_cpus_allowed > 1 && rt_rq_of_se(&p->rt)->overloaded)
rt_queue_push_tasks(rt_rq_of_se(&p->rt));
+
if (p->prio < rq->donor->prio && cpu_online(cpu_of(rq)))
resched_curr(rq);
}
@@ -1892,6 +1963,8 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
static void
prio_changed_rt(struct rq *rq, struct task_struct *p, u64 oldprio)
{
+ struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);
+
if (!task_on_rq_queued(p))
return;
@@ -1904,15 +1977,24 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, u64 oldprio)
* may need to pull tasks to this runqueue.
*/
if (oldprio < p->prio)
- rt_queue_pull_task(rt_rq_of_se(&p->rt));
+ rt_queue_pull_task(rt_rq);
/*
* If there's a higher priority task waiting to run
* then reschedule.
*/
- if (p->prio > rq->rt.highest_prio.curr)
+ if (p->prio > rt_rq->highest_prio.curr)
resched_curr(rq);
} else {
+ /*
+ * This task is not running, thus we check against the currently
+ * running task for preemption. We can preempt only if both tasks are
+ * in the same cgroup or on the global runqueue.
+ */
+ if (rt_group_sched_enabled() &&
+ rt_rq->tg != rt_rq_of_se(&rq->curr->rt)->tg)
+ return;
+
/*
* This task is not running, but if it is
* greater than the current running task
@@ -2005,7 +2087,19 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
#ifdef CONFIG_SCHED_CORE
static int task_is_throttled_rt(struct task_struct *p, int cpu)
{
+#ifdef CONFIG_RT_GROUP_SCHED
+ struct rt_rq *rt_rq;
+
+ rt_rq = task_group(p)->rt_rq[cpu];
+ WARN_ON(!rt_group_sched_enabled() && rt_rq->tg != &root_task_group);
+
+ if (is_dl_group(rt_rq))
+ return dl_group_of(rt_rq)->dl_throttled;
+ else
+ return 0;
+#else
return 0;
+#endif
}
#endif /* CONFIG_SCHED_CORE */
@@ -2244,10 +2338,10 @@ long sched_group_rt_period(struct task_group *tg)
return rt_period_us;
}
-int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+int sched_rt_can_attach(struct task_group *tg)
{
/* Don't accept real-time tasks when there is no way for them to run */
- if (rt_group_sched_enabled() && rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+ if (rt_group_sched_enabled() && tg->dl_bandwidth.dl_runtime == 0)
return 0;
return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0166e75c7733..ef11619cfc30 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -603,7 +603,7 @@ extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
extern long sched_group_rt_runtime(struct task_group *tg);
extern long sched_group_rt_period(struct task_group *tg);
-extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
+extern int sched_rt_can_attach(struct task_group *tg);
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_online_group(struct task_group *tg,
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 02688e75a8bd..8ed4a948b14d 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -606,6 +606,18 @@ int __sched_setscheduler(struct task_struct *p,
change:
if (user) {
+ /*
+ * Do not allow real-time tasks into groups that have no runtime
+ * assigned.
+ */
+ if (rt_group_sched_enabled() &&
+ dl_bandwidth_enabled() && rt_policy(policy) &&
+ !sched_rt_can_attach(task_group(p)) &&
+ !task_group_is_autogroup(task_group(p))) {
+ retval = -EPERM;
+ goto unlock;
+ }
+
if (dl_bandwidth_enabled() && dl_policy(policy) &&
!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
cpumask_t *span = rq->rd->span;
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 15/29] sched/rt: Remove support for cgroups-v1
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (13 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 14/29] sched/rt: Update task event callbacks for HCBS scheduling Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 16/29] sched/rt: Update rt-cgroup schedulability checks Yuri Andriaccio
` (13 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Disable control files for cgroups-v1.
Remove cpu_rt_group_init function and functions related to the
cgroup-v1 control files 'rt_runtime_us' and 'rt_period_us'.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 50 --------------------------------------------
kernel/sched/rt.c | 49 +------------------------------------------
kernel/sched/sched.h | 4 ----
3 files changed, 1 insertion(+), 102 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0425d2c98240..20297c2123d2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10185,32 +10185,6 @@ static int cpu_burst_write_u64(struct cgroup_subsys_state *css,
}
#endif /* CONFIG_GROUP_SCHED_BANDWIDTH */
-#ifdef CONFIG_RT_GROUP_SCHED
-static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
- struct cftype *cft, s64 val)
-{
- return sched_group_set_rt_runtime(css_tg(css), val);
-}
-
-static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
- struct cftype *cft)
-{
- return sched_group_rt_runtime(css_tg(css));
-}
-
-static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
- struct cftype *cftype, u64 rt_period_us)
-{
- return sched_group_set_rt_period(css_tg(css), rt_period_us);
-}
-
-static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
- struct cftype *cft)
-{
- return sched_group_rt_period(css_tg(css));
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
#ifdef CONFIG_GROUP_SCHED_WEIGHT
static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
@@ -10288,20 +10262,6 @@ static struct cftype cpu_legacy_files[] = {
};
#ifdef CONFIG_RT_GROUP_SCHED
-static struct cftype rt_group_files[] = {
- {
- .name = "rt_runtime_us",
- .read_s64 = cpu_rt_runtime_read,
- .write_s64 = cpu_rt_runtime_write,
- },
- {
- .name = "rt_period_us",
- .read_u64 = cpu_rt_period_read_uint,
- .write_u64 = cpu_rt_period_write_uint,
- },
- { } /* Terminate */
-};
-
# ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED
DEFINE_STATIC_KEY_FALSE(rt_group_sched);
# else
@@ -10324,16 +10284,6 @@ static int __init setup_rt_group_sched(char *str)
return 1;
}
__setup("rt_group_sched=", setup_rt_group_sched);
-
-static int __init cpu_rt_group_init(void)
-{
- if (!rt_group_sched_enabled())
- return 0;
-
- WARN_ON(cgroup_add_legacy_cftypes(&cpu_cgrp_subsys, rt_group_files));
- return 0;
-}
-subsys_initcall(cpu_rt_group_init);
#endif /* CONFIG_RT_GROUP_SCHED */
static int cpu_extra_stat_show(struct seq_file *sf,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index b7ea6b5da9e4..1df87d25fda2 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1,3 +1,4 @@
+#pragma GCC diagnostic ignored "-Wunused-function"
// SPDX-License-Identifier: GPL-2.0
/*
* Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
@@ -2290,54 +2291,6 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
return err;
}
-int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
-{
- u64 rt_runtime, rt_period;
-
- rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
- rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
- if (rt_runtime_us < 0)
- rt_runtime = RUNTIME_INF;
- else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
- return -EINVAL;
-
- return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-long sched_group_rt_runtime(struct task_group *tg)
-{
- u64 rt_runtime_us;
-
- if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
- return -1;
-
- rt_runtime_us = tg->rt_bandwidth.rt_runtime;
- do_div(rt_runtime_us, NSEC_PER_USEC);
- return rt_runtime_us;
-}
-
-int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
-{
- u64 rt_runtime, rt_period;
-
- if (rt_period_us > U64_MAX / NSEC_PER_USEC)
- return -EINVAL;
-
- rt_period = rt_period_us * NSEC_PER_USEC;
- rt_runtime = tg->rt_bandwidth.rt_runtime;
-
- return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-long sched_group_rt_period(struct task_group *tg)
-{
- u64 rt_period_us;
-
- rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
- do_div(rt_period_us, NSEC_PER_USEC);
- return rt_period_us;
-}
-
int sched_rt_can_attach(struct task_group *tg)
{
/* Don't accept real-time tasks when there is no way for them to run */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ef11619cfc30..047d564e8f71 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -599,10 +599,6 @@ extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern bool cfs_task_bw_constrained(struct task_struct *p);
-extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
-extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
-extern long sched_group_rt_runtime(struct task_group *tg);
-extern long sched_group_rt_period(struct task_group *tg);
extern int sched_rt_can_attach(struct task_group *tg);
extern struct task_group *sched_create_group(struct task_group *parent);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 16/29] sched/rt: Update rt-cgroup schedulability checks
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (14 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 15/29] sched/rt: Remove support for cgroups-v1 Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 17/29] sched/rt: Update task's RT runqueue when switching scheduling class Yuri Andriaccio
` (12 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Introduce cgroup-v2 control files:
- cpu.rt.max:
Get/set the bandwidth of the given cgroup, or inherith from parent.
- cpu.rt.effective.local:
Get the actual remaning bandwidth for the group, removing the bw of the
group's children.
Introduce a number of functions to update the cgroup settings across the
whole hierarchy:
- tg_subtree_has_rt_tasks()
Checks if the active context rooted at tg is running rt workload.
Child groups which do not share the same active context are ignored.
- tg_compute_children_bw()
Computes the total bandwidth of the active context rooted at tg minus
the root of the context itself.
- tg_rt_schedulable()
Runs admission tests for the current cgroup tree and the given
bandwidth update.
- tg_update_active_context()
Updates the active context of a given subtree with a new one.
- tg_rt_bandwidth() / tg_rt_internal_bandwidth()
Read the max (internal) bandwidth set to the cgroup.
- tg_set_rt_bandwidth()
Set the bandwidth of the group.
Update sched_rt_can_attach to run only tasks in the root cgroup or HCBS
cgroups which have non-zero runtime.
Update and reuse __checkparam_dl to check for numerical issues regarding
the dl_server's parameters.
Add from_ratio function to convert from period and bw to runtime, inverse
of the to_ratio function.
Add dl_check_tg(), which performs an admission control test similar to
__dl_overflow, but this time we are updating the cgroup's total bandwidth
rather than scheduling a new DEADLINE task or updating a non-cgroup
deadline server.
Add rcu_sched lock guard for rcu_read_{lock/unlock}_sched.
Add sched_domains lock guard for sched_domains_mutex_{lock/unlock}.
Add lock/unlock methods for sched_rt_handler_mutex and its lock guard.
Add asserts for held sched_domains_mutex and sched_rt_handler_mutex.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
include/linux/rcupdate.h | 1 +
include/linux/sched.h | 2 +
kernel/sched/core.c | 47 +++++
kernel/sched/deadline.c | 61 ++++--
kernel/sched/rt.c | 403 ++++++++++++++++++++++++++++++++-------
kernel/sched/sched.h | 17 +-
kernel/sched/syscalls.c | 2 +-
7 files changed, 447 insertions(+), 86 deletions(-)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 3f74ae6d6e1f..196fb3b85c81 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1214,6 +1214,7 @@ extern int rcu_expedited;
extern int rcu_normal;
DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock())
+DEFINE_LOCK_GUARD_0(rcu_sched, rcu_read_lock_sched(), rcu_read_unlock_sched())
DECLARE_LOCK_GUARD_0_ATTRS(rcu, __acquires_shared(RCU), __releases_shared(RCU))
#endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8780ef5def7e..4816e408b332 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2531,4 +2531,6 @@ extern void migrate_enable(void);
DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
+DEFINE_LOCK_GUARD_0(sched_domains, sched_domains_mutex_lock(), sched_domains_mutex_unlock())
+
#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 20297c2123d2..62039972ded6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10450,6 +10450,41 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
}
#endif /* CONFIG_CFS_BANDWIDTH */
+#ifdef CONFIG_RT_GROUP_SCHED
+static int cpu_rt_max_show(struct seq_file *sf, void *v)
+{
+ struct task_group *tg = css_tg(seq_css(sf));
+ u64 period_us, runtime_us;
+
+ tg_rt_bandwidth(tg, &period_us, &runtime_us);
+ cpu_period_quota_print(sf, period_us, runtime_us);
+ return 0;
+}
+
+static int cpu_rt_internal_show(struct seq_file *sf, void *v)
+{
+ struct task_group *tg = css_tg(seq_css(sf));
+ u64 period_us, runtime_us;
+
+ tg_rt_internal_bandwidth(tg, &period_us, &runtime_us);
+ cpu_period_quota_print(sf, period_us, runtime_us);
+ return 0;
+}
+
+static ssize_t cpu_rt_max_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct task_group *tg = css_tg(of_css(of));
+ u64 period_us = 0, runtime_us;
+ int ret;
+
+ ret = cpu_period_quota_parse(buf, &period_us, &runtime_us);
+ if (!ret)
+ ret = tg_set_rt_bandwidth(tg, period_us, runtime_us);
+ return ret ?: nbytes;
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
static struct cftype cpu_files[] = {
#ifdef CONFIG_GROUP_SCHED_WEIGHT
{
@@ -10485,6 +10520,18 @@ static struct cftype cpu_files[] = {
.write_u64 = cpu_burst_write_u64,
},
#endif /* CONFIG_CFS_BANDWIDTH */
+#ifdef CONFIG_RT_GROUP_SCHED
+ {
+ .name = "rt.max",
+ .seq_show = cpu_rt_max_show,
+ .write = cpu_rt_max_write,
+ },
+ {
+ .name = "rt.effective.local",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_rt_internal_show,
+ },
+#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_UCLAMP_TASK_GROUP
{
.name = "uclamp.min",
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 17f303294d6c..64df71ab370d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -352,10 +352,46 @@ void cancel_inactive_timer(struct sched_dl_entity *dl_se)
cancel_dl_timer(dl_se, &dl_se->inactive_timer);
}
+/*
+ * Used for dl_bw check and update, used under sched_rt_handler()::mutex and
+ * sched_domains_mutex.
+ */
+u64 dl_cookie;
+
#ifdef CONFIG_RT_GROUP_SCHED
+int dl_check_tg(unsigned long total)
+{
+ int cpu, cpus, cap;
+ struct dl_bw *dl_b;
+ u64 gen = ++dl_cookie;
+
+ lockdep_assert_held(&sched_domains_mutex);
+ lockdep_assert_held(&sched_rt_handler_mutex);
+
+ for_each_possible_cpu(cpu) {
+ guard(rcu_sched)();
+
+ if (!dl_bw_visited(cpu, gen)) {
+ cap = dl_bw_capacity(cpu);
+ cpus = dl_bw_cpus(cpu);
+ dl_b = dl_bw_of(cpu);
+
+ guard(raw_spinlock_irqsave)(&dl_b->lock);
+
+ if (dl_b->bw != -1 &&
+ cap_scale(dl_b->bw, cap) < dl_b->total_bw +
+ total * cpus)
+ return 0;
+ }
+
+ }
+
+ return 1;
+}
+
void dl_init_tg(struct sched_dl_entity *dl_se, u64 rt_runtime, u64 rt_period)
{
- struct rq *rq = container_of_const(dl_se->dl_rq, struct rq, dl);
+ struct rq *rq = rq_of_dl_se(dl_se);
int is_active;
u64 new_bw;
@@ -3723,12 +3759,6 @@ DEFINE_SCHED_CLASS(dl) = {
#endif
};
-/*
- * Used for dl_bw check and update, used under sched_rt_handler()::mutex and
- * sched_domains_mutex.
- */
-u64 dl_cookie;
-
int sched_dl_global_validate(void)
{
u64 runtime = global_rt_runtime();
@@ -3740,6 +3770,9 @@ int sched_dl_global_validate(void)
int cpu, cap, cpus, ret = 0;
unsigned long flags;
+ lockdep_assert_held(&sched_domains_mutex);
+ lockdep_assert_held(&sched_rt_handler_mutex);
+
/*
* Here we want to check the bandwidth not being set to some
* value smaller than the currently allocated bandwidth in
@@ -3792,6 +3825,9 @@ void sched_dl_do_global(void)
int cpu;
unsigned long flags;
+ lockdep_assert_held(&sched_domains_mutex);
+ lockdep_assert_held(&sched_rt_handler_mutex);
+
if (global_rt_runtime() != RUNTIME_INF)
new_bw = to_ratio(global_rt_period(), global_rt_runtime());
@@ -3937,7 +3973,7 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr, unsigned int
* below 2^63 ns (we have to check both sched_deadline and
* sched_period, as the latter can be zero).
*/
-bool __checkparam_dl(const struct sched_attr *attr)
+bool __checkparam_dl(const struct sched_attr *attr, bool allow_zero_runtime)
{
u64 period, max, min;
@@ -3946,14 +3982,16 @@ bool __checkparam_dl(const struct sched_attr *attr)
return true;
/* deadline != 0 */
- if (attr->sched_deadline == 0)
+ if ((!allow_zero_runtime || attr->sched_runtime != 0) &&
+ attr->sched_deadline == 0)
return false;
/*
* Since we truncate DL_SCALE bits, make sure we're at least
* that big.
*/
- if (attr->sched_runtime < (1ULL << DL_SCALE))
+ if ((!allow_zero_runtime || attr->sched_runtime != 0) &&
+ attr->sched_runtime < (1ULL << DL_SCALE))
return false;
/*
@@ -3976,7 +4014,8 @@ bool __checkparam_dl(const struct sched_attr *attr)
max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
- if (period < min || period > max)
+ if ((!allow_zero_runtime || period != 0) &&
+ (period < min || period > max))
return false;
return true;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1df87d25fda2..cf756639d9e8 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1,4 +1,3 @@
-#pragma GCC diagnostic ignored "-Wunused-function"
// SPDX-License-Identifier: GPL-2.0
/*
* Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
@@ -2143,9 +2142,6 @@ DEFINE_SCHED_CLASS(rt) = {
};
#ifdef CONFIG_RT_GROUP_SCHED
-/*
- * Ensure that the real time constraints are schedulable.
- */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
struct task_struct *task;
@@ -2166,38 +2162,126 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
return ret;
}
-struct rt_schedulable_data {
+static int __tg_subtree_has_rt_tasks(struct task_group *tg, void *data) {
+ struct task_group *ctx = data;
+
+ if (dl_bandwidth_read(tg)->active_context == ctx && tg_has_rt_tasks(tg))
+ return 1;
+ else
+ return 0;
+}
+
+static int tg_subtree_has_rt_tasks(struct task_group *tg) {
+ lockdep_assert(rcu_read_lock_held());
+ return walk_tg_tree_from(tg, __tg_subtree_has_rt_tasks, tg_nop,
+ dl_bandwidth_read(tg)->active_context);
+}
+
+struct tg_update_data {
struct task_group *tg;
u64 rt_period;
u64 rt_runtime;
};
-static int tg_rt_schedulable(struct task_group *tg, void *data)
+struct tg_compute_children_bw_data {
+ struct tg_update_data update;
+ struct task_group *active_context;
+ u64 period;
+ u64 runtime_sum;
+};
+
+static int __tg_compute_children_runtime(struct task_group *tg, void *data) {
+ struct tg_compute_children_bw_data *d = data;
+ const struct task_group *parent_active_context;
+ const struct dl_bandwidth *dl_b_parent, *dl_b = dl_bandwidth_read(tg);
+ u64 period, runtime;
+
+ /* Skip the current task group from the sum. */
+ if (tg == d->active_context)
+ return 0;
+
+ period = dl_b->dl_period;
+ runtime = dl_b->dl_runtime;
+ if (tg == d->update.tg) {
+ period = d->update.rt_period;
+ runtime = d->update.rt_runtime;
+ }
+ if (runtime == RUNTIME_INF || period == 0)
+ return 0;
+
+ dl_b_parent = dl_bandwidth_read(tg->parent);
+ parent_active_context = dl_b_parent->active_context;
+ if (tg->parent == d->update.tg) {
+ if (dl_b_parent->dl_runtime != RUNTIME_INF &&
+ d->update.rt_runtime == RUNTIME_INF)
+ parent_active_context = dl_bandwidth_read(tg->parent->parent)->active_context;
+ else if (d->update.rt_runtime != RUNTIME_INF)
+ parent_active_context = tg->parent;
+ }
+
+ if (parent_active_context != d->active_context)
+ return 0;
+
+ d->runtime_sum += mul_u64_u64_div_u64(runtime, d->period, period);
+ return 0;
+}
+
+static u64
+tg_compute_children_runtime(struct task_group *tg,
+ u64 normalization_period,
+ struct tg_update_data *data)
+{
+ struct tg_compute_children_bw_data sum_data = {
+ .active_context = tg,
+ .period = normalization_period,
+ .runtime_sum = 0,
+ .update = *data,
+ };
+
+ lockdep_assert(rcu_read_lock_held());
+ walk_tg_tree_from(tg, __tg_compute_children_runtime, tg_nop, &sum_data);
+ return sum_data.runtime_sum;
+}
+
+struct rt_schedulable_data {
+ struct tg_update_data update;
+ u64 rt_runtime_remainder;
+};
+
+static int __tg_rt_schedulable(struct task_group *tg, void *data)
{
struct rt_schedulable_data *d = data;
- struct task_group *child;
+ const struct dl_bandwidth *dl_b;
u64 total, sum = 0;
u64 period, runtime;
- period = ktime_to_ns(tg->rt_bandwidth.rt_period);
- runtime = tg->rt_bandwidth.rt_runtime;
+ dl_b = dl_bandwidth_read(tg);
+ period = dl_b->dl_period;
+ runtime = dl_b->dl_runtime;
- if (tg == d->tg) {
- period = d->rt_period;
- runtime = d->rt_runtime;
+ if (tg == d->update.tg) {
+ period = d->update.rt_period;
+ runtime = d->update.rt_runtime;
}
+ /*
+ * "max" groups are always schedulable, as they defer their access
+ * control to their first non-max parent.
+ */
+ if (runtime == RUNTIME_INF)
+ return 0;
+
/*
* Cannot have more runtime than the period.
*/
- if (runtime > period && runtime != RUNTIME_INF)
+ if (runtime > period)
return -EINVAL;
/*
* Ensure we don't starve existing RT tasks if runtime turns zero.
*/
- if (rt_bandwidth_enabled() && !runtime &&
- tg->rt_bandwidth.rt_runtime && tg_has_rt_tasks(tg))
+ if (dl_bandwidth_enabled() && !runtime && tg != &root_task_group &&
+ tg_subtree_has_rt_tasks(tg))
return -EBUSY;
total = to_ratio(period, runtime);
@@ -2208,58 +2292,144 @@ static int tg_rt_schedulable(struct task_group *tg, void *data)
if (total > to_ratio(global_rt_period(), global_rt_runtime()))
return -EINVAL;
+ if (tg == &root_task_group) {
+ if (!dl_check_tg(total))
+ return -EBUSY;
+ }
+
/*
- * The sum of our children's runtime should not exceed our own.
+ * The sum of our children's runtime, plus our own bw, should not
+ * exceed our own max.
*/
- list_for_each_entry_rcu(child, &tg->children, siblings) {
- period = ktime_to_ns(child->rt_bandwidth.rt_period);
- runtime = child->rt_bandwidth.rt_runtime;
+ total = runtime;
+ sum = tg_compute_children_runtime(tg, period, &d->update);
+ if (sum > total)
+ return -EINVAL;
- if (child == d->tg) {
- period = d->rt_period;
- runtime = d->rt_runtime;
- }
+ /*
+ * Compute remaining runtime
+ */
+ if (tg == d->update.tg)
+ d->rt_runtime_remainder = total - sum;
- sum += to_ratio(period, runtime);
+ return 0;
+}
+
+static int tg_rt_schedulable(struct tg_update_data *data, u64 *remainder_runtime)
+{
+ int err;
+ struct rt_schedulable_data d = {
+ .update = (struct tg_update_data) {
+ .tg = data->tg,
+ .rt_period = data->rt_period,
+ .rt_runtime = data->rt_runtime,
+ },
+ .rt_runtime_remainder = 0,
+ };
+
+ /*
+ * Walk the cgroup tree and check schedulability constraints.
+ */
+ lockdep_assert(rcu_read_lock_held());
+ err = walk_tg_tree(__tg_rt_schedulable, tg_nop, &d);
+ if (err)
+ return err;
+
+ *remainder_runtime = d.rt_runtime_remainder;
+ return 0;
+}
+
+struct tg_update_active_context_data {
+ struct task_group *new_active_context;
+ struct task_group *old_active_context;
+};
+
+static int __tg_update_active_context(struct task_group *tg, void *data) {
+ struct tg_update_active_context_data *d = data;
+
+ if (dl_bandwidth_read(tg)->active_context == d->old_active_context) {
+ guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
+ dl_bandwidth_write(tg)->active_context = d->new_active_context;
}
- if (sum > total)
- return -EINVAL;
+ return 0;
+}
+
+static void tg_update_active_context(struct task_group *tg,
+ struct task_group *old_context,
+ struct task_group *new_context)
+{
+ struct tg_update_active_context_data data = {
+ .new_active_context = new_context,
+ .old_active_context = old_context,
+ };
+ lockdep_assert(rcu_read_lock_held());
+ walk_tg_tree_from(tg, __tg_update_active_context, tg_nop, &data);
+}
+
+int tg_rt_bandwidth(struct task_group *tg,
+ u64 *rt_period_us, u64 *rt_runtime_us)
+{
+ const struct dl_bandwidth *dl_b;
+
+ guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
+ dl_b = dl_bandwidth_read(tg);
+
+ *rt_runtime_us = -1;
+ if (dl_b->dl_runtime != RUNTIME_INF) {
+ *rt_runtime_us = div64_u64(dl_b->dl_runtime, NSEC_PER_USEC);
+ }
+
+ *rt_period_us = div64_u64(dl_b->dl_period, NSEC_PER_USEC);
return 0;
}
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+int tg_rt_internal_bandwidth(struct task_group *tg,
+ u64 *rt_period_us, u64 *rt_runtime_us)
{
- int ret;
+ const struct dl_bandwidth *dl_b;
- struct rt_schedulable_data data = {
- .tg = tg,
- .rt_period = period,
- .rt_runtime = runtime,
- };
+ guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
+ dl_b = dl_bandwidth_read(tg);
- rcu_read_lock();
- ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
- rcu_read_unlock();
+ *rt_runtime_us = dl_b->dl_internal_runtime;
+ *rt_runtime_us = DIV64_U64_ROUND_CLOSEST(*rt_runtime_us, NSEC_PER_USEC);
- return ret;
+ *rt_period_us = div64_u64(dl_b->dl_period, NSEC_PER_USEC);
+
+ return 0;
}
-static int tg_set_rt_bandwidth(struct task_group *tg,
- u64 rt_period, u64 rt_runtime)
+int tg_set_rt_bandwidth(struct task_group *tg,
+ u64 rt_period_us, u64 rt_runtime_us)
{
- int i, err = 0;
+ struct tg_update_data update;
+ struct task_group *parent_ctx;
+ struct dl_bandwidth *dl_b;
+ u64 rt_period, rt_runtime, old_rt_runtime;
+ u64 rt_actual_runtime = 0;
+ u64 runtime, children_runtime;
+ struct sched_attr attr;
+ int err, i;
- /*
- * Disallowing the root group RT runtime is BAD, it would disallow the
- * kernel creating (and or operating) RT threads.
- */
- if (tg == &root_task_group && rt_runtime == 0)
+ if (rt_runtime_us == RUNTIME_INF)
+ rt_runtime = RUNTIME_INF;
+ else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
return -EINVAL;
+ else
+ rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
- /* No period doesn't make any sense. */
- if (rt_period == 0)
+ if ((u64)rt_period_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+ else
+ rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+
+ /*
+ * The root_task_group bandwidth settings are only used to reserve bw
+ * for HCBS cgroups; runtime == "max" has no meaning there.
+ */
+ if (rt_runtime == RUNTIME_INF && tg == &root_task_group)
return -EINVAL;
/*
@@ -2268,34 +2438,119 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
return -EINVAL;
- mutex_lock(&rt_constraints_mutex);
- err = __rt_schedulable(tg, rt_period, rt_runtime);
+ /*
+ * Check if the runtime and period min and max values are admissible.
+ */
+ attr = (struct sched_attr){
+ .sched_flags = 0,
+ .sched_runtime = rt_runtime,
+ .sched_deadline = rt_period,
+ .sched_period = rt_period,
+ };
+
+ if (rt_runtime != RUNTIME_INF && !__checkparam_dl(&attr, true))
+ return -EINVAL;
+
+ update = (struct tg_update_data) {
+ .tg = tg,
+ .rt_period = rt_period,
+ .rt_runtime = rt_runtime,
+ };
+
+ guard(mutex)(&rt_constraints_mutex);
+ old_rt_runtime = dl_bandwidth_read(tg)->dl_runtime;
+
+ /*
+ * Disallow changing from/to "max" and a HCBS reservation if the group
+ * and all of its "max" children have active tasks.
+ */
+ guard(sched_rt_handler)();
+ guard(sched_domains)();
+ guard(rcu)();
+ if (((rt_runtime == RUNTIME_INF && old_rt_runtime != RUNTIME_INF) ||
+ (rt_runtime != RUNTIME_INF && old_rt_runtime == RUNTIME_INF)) &&
+ tg_subtree_has_rt_tasks(tg))
+ return -EINVAL;
+
+ err = tg_rt_schedulable(&update, &rt_actual_runtime);
if (err)
- goto unlock;
+ return err;
+
+ scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(tg)) {
+ dl_b = dl_bandwidth_write(tg);
+ dl_b->dl_period = rt_period;
+ dl_b->dl_runtime = rt_runtime;
+ dl_b->dl_internal_runtime = rt_actual_runtime;
+ }
+
+ if (tg == &root_task_group)
+ return 0;
+
+ parent_ctx = dl_bandwidth_read(tg->parent)->active_context;
+
+ /*
+ * If changing from/to "max" and a HCBS reservation, must update the
+ * active_context of self and all of its subtree.
+ */
+ if ((rt_runtime == RUNTIME_INF && old_rt_runtime != RUNTIME_INF) ||
+ (rt_runtime != RUNTIME_INF && old_rt_runtime == RUNTIME_INF))
+ {
+ if (rt_runtime == RUNTIME_INF)
+ tg_update_active_context(tg, dl_b->active_context, parent_ctx);
+ else
+ tg_update_active_context(tg, dl_b->active_context, tg);
- raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
- tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
- tg->rt_bandwidth.rt_runtime = rt_runtime;
+ }
+ WARN_ON(rt_runtime == RUNTIME_INF && rt_actual_runtime != 0);
for_each_possible_cpu(i) {
- struct rt_rq *rt_rq = tg->rt_rq[i];
+ dl_init_tg(tg->dl_se[i], rt_actual_runtime, rt_period);
+ }
+
+ /*
+ * Update the dl_servers of the parent's active context
+ */
+ if (parent_ctx == &root_task_group)
+ return 0;
+
+ scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(parent_ctx)) {
+ dl_b = dl_bandwidth_write(parent_ctx);
- raw_spin_lock(&rt_rq->rt_runtime_lock);
- rt_rq->rt_runtime = rt_runtime;
- raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ runtime = dl_b->dl_runtime;
+ children_runtime = tg_compute_children_runtime(parent_ctx, dl_b->dl_period, &update);
+
+ rt_period = dl_b->dl_period;
+ rt_actual_runtime = runtime - children_runtime;
+ dl_b->dl_internal_runtime = rt_actual_runtime;
}
- raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-unlock:
- mutex_unlock(&rt_constraints_mutex);
- return err;
+ for_each_possible_cpu(i) {
+ dl_init_tg(parent_ctx->dl_se[i], rt_actual_runtime, rt_period);
+ }
+
+ return 0;
}
int sched_rt_can_attach(struct task_group *tg)
{
+ struct task_group *ctx;
+
+ /* If rt group sched is disabled, tasks are always run in the root rq */
+ if (!rt_group_sched_enabled())
+ return 1;
+
+ /* Can always run on the root task group */
+ scoped_guard(raw_spinlock_irqsave, dl_bw_lock_of_tg(tg)) {
+ ctx = dl_bandwidth_read(tg)->active_context;
+ if (ctx == &root_task_group)
+ return 1;
+ }
+
/* Don't accept real-time tasks when there is no way for them to run */
- if (rt_group_sched_enabled() && tg->dl_bandwidth.dl_runtime == 0)
- return 0;
+ scoped_guard(raw_spinlock_irqsave, dl_bw_lock_of_tg(ctx)) {
+ if (dl_bandwidth_read(ctx)->dl_runtime == 0)
+ return 0;
+ }
return 1;
}
@@ -2311,24 +2566,26 @@ static int sched_rt_global_validate(void)
NSEC_PER_USEC > max_rt_runtime)))
return -EINVAL;
-#ifdef CONFIG_RT_GROUP_SCHED
- if (!rt_group_sched_enabled())
- return 0;
-
- scoped_guard(mutex, &rt_constraints_mutex)
- return __rt_schedulable(NULL, 0, 0);
-#endif
return 0;
}
+DEFINE_MUTEX(sched_rt_handler_mutex);
+
+void sched_rt_handler_mutex_lock() {
+ mutex_lock(&sched_rt_handler_mutex);
+}
+
+void sched_rt_handler_mutex_unlock() {
+ mutex_unlock(&sched_rt_handler_mutex);
+}
+
static int sched_rt_handler(const struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
int old_period, old_runtime;
- static DEFINE_MUTEX(mutex);
int ret;
- mutex_lock(&mutex);
+ sched_rt_handler_mutex_lock();
sched_domains_mutex_lock();
old_period = sysctl_sched_rt_period;
old_runtime = sysctl_sched_rt_runtime;
@@ -2352,7 +2609,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
sysctl_sched_rt_runtime = old_runtime;
}
sched_domains_mutex_unlock();
- mutex_unlock(&mutex);
+ sched_rt_handler_mutex_unlock();
/*
* After changing maximum available bandwidth for DEADLINE, we need to
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 047d564e8f71..10eb56aba3d4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -366,7 +366,7 @@ extern void sched_dl_do_global(void);
extern int sched_dl_overflow(struct task_struct *p, int policy, const struct sched_attr *attr);
extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr, unsigned int flags);
-extern bool __checkparam_dl(const struct sched_attr *attr);
+extern bool __checkparam_dl(const struct sched_attr *attr, bool allow_zero_runtime);
extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int dl_bw_deactivate(int cpu);
@@ -425,6 +425,7 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq,
struct rq *served_rq,
dl_server_pick_f pick_task);
extern void sched_init_dl_servers(void);
+extern int dl_check_tg(unsigned long total);
extern void dl_init_tg(struct sched_dl_entity *dl_se, u64 rt_runtime, u64 rt_period);
extern void fair_server_init(struct rq *rq);
@@ -599,6 +600,12 @@ extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
extern bool cfs_task_bw_constrained(struct task_struct *p);
+extern int tg_rt_bandwidth(struct task_group *tg,
+ u64 *rt_period_us, u64 *rt_runtime_us);
+extern int tg_rt_internal_bandwidth(struct task_group *tg,
+ u64 *rt_period_us, u64 *rt_runtime_us);
+extern int tg_set_rt_bandwidth(struct task_group *tg,
+ u64 rt_period_us, u64 rt_runtime_us);
extern int sched_rt_can_attach(struct task_group *tg);
extern struct task_group *sched_create_group(struct task_group *parent);
@@ -2123,6 +2130,14 @@ static inline struct rq *_this_rq_lock_irq(struct rq_flags *rf) __acquires_ret
return rq;
}
+extern struct mutex sched_rt_handler_mutex;
+extern void sched_rt_handler_mutex_lock(void);
+extern void sched_rt_handler_mutex_unlock(void);
+
+DEFINE_LOCK_GUARD_0(sched_rt_handler,
+ sched_rt_handler_mutex_lock(),
+ sched_rt_handler_mutex_unlock())
+
#ifdef CONFIG_NUMA
enum numa_topology_type {
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 8ed4a948b14d..f1e9de478e1d 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -528,7 +528,7 @@ int __sched_setscheduler(struct task_struct *p,
*/
if (attr->sched_priority > MAX_RT_PRIO-1)
return -EINVAL;
- if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
+ if ((dl_policy(policy) && !__checkparam_dl(attr, false)) ||
(rt_policy(policy) != (attr->sched_priority != 0)))
return -EINVAL;
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 17/29] sched/rt: Update task's RT runqueue when switching scheduling class
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (15 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 16/29] sched/rt: Update rt-cgroup schedulability checks Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 18/29] sched/rt: Remove old RT_GROUP_SCHED data structures Yuri Andriaccio
` (11 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/rt.c | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index cf756639d9e8..b16cc77d7015 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1926,6 +1926,27 @@ void __init init_sched_rt_class(void)
}
}
+#ifdef CONFIG_RT_GROUP_SCHED
+static void switching_to_rt(struct rq *rq, struct task_struct *p)
+{
+ struct task_group *tg = p->sched_task_group;
+ int cpu = rq->cpu;
+
+ if (!rt_group_sched_enabled())
+ return;
+
+ if (tg == &root_task_group) {
+ p->rt.rt_rq = root_task_group.rt_rq[cpu];
+ return;
+ }
+
+ guard(raw_spinlock_irqsave)(dl_bw_lock_of_tg(tg));
+ p->rt.rt_rq = dl_bandwidth_read(tg)->active_context->rt_rq[cpu];
+}
+#else
+static void switching_to_rt(struct rq *rq, struct task_struct *p) {}
+#endif
+
/*
* When switching a task to RT, we may overload the runqueue
* with RT tasks. In this case we try to push them off to
@@ -2127,6 +2148,7 @@ DEFINE_SCHED_CLASS(rt) = {
.get_rr_interval = get_rr_interval_rt,
+ .switching_to = switching_to_rt,
.switched_to = switched_to_rt,
.prio_changed = prio_changed_rt,
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 18/29] sched/rt: Remove old RT_GROUP_SCHED data structures
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (16 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 17/29] sched/rt: Update task's RT runqueue when switching scheduling class Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 19/29] sched/rt: Add HCBS migration code to related functions Yuri Andriaccio
` (10 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Completely remove the old RT_GROUP_SCHED's functions and data structures:
- Remove the fields back and my_q from sched_rt_entity.
- Remove the rt_bandwidth data structure.
- Remove the field rt_bandwidth from task_group.
- Remove the rt_bandwidth_enabled function.
- Remove the fields rt_queued, rt_throttled, rt_time, rt_runtime,
rt_runtime_lock and rt_nr_boosted from rt_rq.
All of the removed fields and data are similarly represented in previously
added fields in rq, rt_rq, dl_bandwidth and in the dl server themselves.
Co-developed-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
---
include/linux/sched.h | 3 ---
kernel/sched/sched.h | 33 ---------------------------------
2 files changed, 36 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4816e408b332..112e6a450a16 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -627,12 +627,9 @@ struct sched_rt_entity {
unsigned short on_rq;
unsigned short on_list;
- struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
/* rq on which this entity is (to be) queued: */
struct rt_rq *rt_rq;
- /* rq "owned" by this entity/group: */
- struct rt_rq *my_q;
#endif
} __randomize_layout;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10eb56aba3d4..1242d297532f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -313,15 +313,6 @@ struct rt_prio_array {
struct list_head queue[MAX_RT_PRIO];
};
-struct rt_bandwidth {
- /* nests inside the rq lock: */
- raw_spinlock_t rt_runtime_lock;
- ktime_t rt_period;
- u64 rt_runtime;
- struct hrtimer rt_period_timer;
- unsigned int rt_period_active;
-};
-
struct dl_bandwidth {
raw_spinlock_t dl_runtime_lock;
u64 dl_runtime;
@@ -343,12 +334,6 @@ static inline int dl_bandwidth_enabled(void)
* - cache the fraction of bandwidth that is currently allocated in
* each root domain;
*
- * This is all done in the data structure below. It is similar to the
- * one used for RT-throttling (rt_bandwidth), with the main difference
- * that, since here we are only interested in admission control, we
- * do not decrease any runtime while the group "executes", neither we
- * need a timer to replenish it.
- *
* With respect to SMP, bandwidth is given on a per root domain basis,
* meaning that:
* - bw (< 100%) is the deadline bandwidth of each CPU;
@@ -515,11 +500,9 @@ struct task_group {
* different deadline server, and a runqueue per CPU. All the dl-servers
* share the same dl_bandwidth object.
*/
- struct sched_rt_entity **rt_se;
struct sched_dl_entity **dl_se;
struct rt_rq **rt_rq;
- struct rt_bandwidth rt_bandwidth;
struct dl_bandwidth dl_bandwidth;
#endif
@@ -887,11 +870,6 @@ struct scx_rq {
};
#endif /* CONFIG_SCHED_CLASS_EXT */
-static inline int rt_bandwidth_enabled(void)
-{
- return 0;
-}
-
/* RT IPI pull logic requires IRQ_WORK */
#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_SMP)
# define HAVE_RT_PUSH_IPI
@@ -909,17 +887,6 @@ struct rt_rq {
bool overloaded;
struct plist_head pushable_tasks;
- int rt_queued;
-
-#ifdef CONFIG_RT_GROUP_SCHED
- int rt_throttled;
- u64 rt_time; /* consumed RT time, goes up in update_curr_rt */
- u64 rt_runtime; /* allotted RT time, "slice" from rt_bandwidth, RT sharing/balancing */
- /* Nests inside the rq lock: */
- raw_spinlock_t rt_runtime_lock;
-
- unsigned int rt_nr_boosted;
-#endif
#ifdef CONFIG_CGROUP_SCHED
struct task_group *tg; /* this tg has "this" rt_rq on given CPU for runnable entities */
#endif
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 19/29] sched/rt: Add HCBS migration code to related functions
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (17 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 18/29] sched/rt: Remove old RT_GROUP_SCHED data structures Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 20/29] sched/rt: Hook HCBS migration functions Yuri Andriaccio
` (9 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Update rt_queue_{push/pull}_task{s} to differentiate between cgroup and
global runqueue balancing.
Introduce new balance callbacks for cgroup migration.
Add rq_to_push_from and rq_to_push_to fields for cgroup related migration.
Balance callbacks are only called on the root runqueues, thus it is
necessary to store which non-root runqueues need to be balanced. The rqs to
balance are stored as a forward-linked list/stack, with the top pointers
accessible on root runqueues.
Update migration functions to specialize for cgroup migration:
- find_lowest_rt_rq():
Scan all the cpus to get the cgroup specific lowest_mask.
- find_lock_lowest_rt_rq():
Use appropriate rt_rqs to differentiate the cgroup being checked.
Prevent migration for throttled cgroups.
- push_rt_rq_task():
Allow pushing away for migration disabled tasks only if the tasks
belong to the same cgroup.
- pull_rt_rq_task():
Use appropriate rt_rqs and push away for migration disabled only
if the task to pull and curr are in the same runqueue.
Add tg_of_se to get the task group a scheduling entity is assigned to.
This is different from the active context of the group.
Add new macros for field access and non-CONFIG_RT_GROUP_SCHED code.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/rt.c | 292 +++++++++++++++++++++++++++++++++----------
kernel/sched/sched.h | 24 ++++
2 files changed, 248 insertions(+), 68 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index b16cc77d7015..0b7c36f8acdc 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -364,31 +364,83 @@ static inline int has_pushable_tasks(struct rt_rq *rt_rq)
static DEFINE_PER_CPU(struct balance_callback, rt_push_head);
static DEFINE_PER_CPU(struct balance_callback, rt_pull_head);
+static DEFINE_PER_CPU(struct balance_callback, rt_group_push_head);
+static DEFINE_PER_CPU(struct balance_callback, rt_group_pull_head);
static void push_rt_tasks(struct rq *);
static void pull_rt_task(struct rq *);
+static void push_group_rt_tasks(struct rq *);
+static void pull_group_rt_task(struct rq *);
+
+#define rq_queue_field_push(global_rq, new_rq, field) \
+ do { \
+ struct rq *__rq = (global_rq); \
+ struct rq *__new_rq = (new_rq); \
+ __new_rq->field = __rq->field; \
+ __rq->field = __new_rq; \
+ } while (0)
+
+#define rq_queue_field_pop(global_rq, field) \
+ ({ \
+ struct rq *__rq = (global_rq); \
+ struct rq *__head = __rq->field; \
+ if (__head) { \
+ __rq->field = __head->field; \
+ __head->field = NULL; \
+ } \
+ __head; \
+ })
+
+#define push_rq_to_push_from(global_rq, new_rq) rq_queue_field_push((global_rq), (new_rq), rq_to_push_from)
+#define pop_rq_to_push_from(global_rq) rq_queue_field_pop((global_rq), rq_to_push_from)
+
+#define push_rq_to_pull_to(global_rq, new_rq) rq_queue_field_push((global_rq), (new_rq), rq_to_pull_to)
+#define pop_rq_to_pull_to(global_rq) rq_queue_field_pop((global_rq), rq_to_pull_to)
static inline void rt_queue_push_tasks(struct rt_rq *rt_rq)
{
- struct rq *rq = global_rq_of_rt_rq(rt_rq);
-
- if (is_dl_group(rt_rq))
- return;
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+ struct rq *global_rq = global_rq_of_rt_rq(rt_rq);
if (!has_pushable_tasks(rt_rq))
return;
- queue_balance_callback(rq, &per_cpu(rt_push_head, rq->cpu), push_rt_tasks);
+ if (!rt_group_sched_enabled() || !is_dl_group(rt_rq)) {
+
+ queue_balance_callback(global_rq,
+ &per_cpu(rt_push_head, rq->cpu),
+ push_rt_tasks);
+ } else {
+
+ push_rq_to_push_from(global_rq, rq);
+ queue_balance_callback(global_rq,
+ &per_cpu(rt_group_push_head, global_rq->cpu),
+ push_group_rt_tasks);
+ }
}
static inline void rt_queue_pull_task(struct rt_rq *rt_rq)
{
- struct rq *rq = global_rq_of_rt_rq(rt_rq);
+ struct rq *rq = rq_of_rt_rq(rt_rq);
+ struct rq *global_rq = global_rq_of_rt_rq(rt_rq);
+ struct sched_dl_entity *dl_se;
- if (is_dl_group(rt_rq))
- return;
+ if (!rt_group_sched_enabled() || !is_dl_group(rt_rq)) {
+
+ queue_balance_callback(global_rq,
+ &per_cpu(rt_pull_head, rq->cpu),
+ pull_rt_task);
+ } else {
+
+ dl_se = dl_group_of(rt_rq);
+ if (dl_se->dl_throttled)
+ return;
- queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task);
+ push_rq_to_pull_to(global_rq, rq);
+ queue_balance_callback(global_rq,
+ &per_cpu(rt_group_pull_head, global_rq->cpu),
+ pull_group_rt_task);
+ }
}
static void push_rt_rq_tasks(struct rt_rq *rt_rq);
@@ -403,6 +455,31 @@ static void pull_rt_task(struct rq *global_rq) {
pull_rt_rq_task(&global_rq->rt);
}
+static void push_group_rt_tasks(struct rq *global_rq)
+{
+ struct rq *rq;
+
+ while ((rq = pop_rq_to_push_from(global_rq))) {
+ struct rt_rq *rt_rq = &rq->rt;
+
+ if (rt_rq->rt_nr_running <= 1 && !dl_group_of(rt_rq)->dl_throttled)
+ continue;
+
+ push_rt_rq_tasks(rt_rq);
+ }
+}
+
+static void pull_group_rt_task(struct rq *global_rq)
+{
+ struct rq *rq;
+
+ while ((rq = pop_rq_to_pull_to(global_rq))) {
+ struct rt_rq *rt_rq = &rq->rt;
+
+ pull_rt_rq_task(rt_rq);
+ }
+}
+
static void enqueue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
{
plist_del(&p->pushable_tasks, &rt_rq->pushable_tasks);
@@ -1246,35 +1323,74 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
static int find_lowest_rt_rq(struct task_struct *task)
{
struct sched_domain *sd;
- struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
- int this_cpu = smp_processor_id();
- int cpu = task_cpu(task);
- int ret;
-
- /* Make sure the mask is initialized first */
- if (unlikely(!lowest_mask))
- return -1;
+ cpumask_var_t mask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+ struct cpumask *lowest_mask;
+ struct sched_dl_entity *dl_se;
+ struct rt_rq *rt_rq, *task_rt_rq = rt_rq_of_se(&task->rt);
+ int cpu, this_cpu = smp_processor_id();
+ int ret, prio, lowest_prio;
if (task->nr_cpus_allowed == 1)
return -1; /* No other targets possible */
- /*
- * If we're on asym system ensure we consider the different capacities
- * of the CPUs when searching for the lowest_mask.
- */
- if (sched_asym_cpucap_active()) {
+ if (!rt_group_sched_enabled() || !is_dl_group(task_rt_rq)) {
+
+ lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
+
+ /* Make sure the mask is initialized first */
+ if (unlikely(!lowest_mask))
+ return -1;
+
+ /*
+ * If we're on asym system ensure we consider the different
+ * capacities of the CPUs when searching for the lowest_mask.
+ */
+ if (sched_asym_cpucap_active()) {
+
+ ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
+ task, lowest_mask,
+ rt_task_fits_capacity);
+ } else {
+
+ ret = cpupri_find(&task_rq(task)->rd->cpupri,
+ task, lowest_mask);
+ }
- ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
- task, lowest_mask,
- rt_task_fits_capacity);
+ if (!ret)
+ return -1; /* No targets found */
} else {
+ if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ lowest_prio = task->prio - 1;
+ lowest_mask = mask;
+ cpumask_clear(lowest_mask);
+ for_each_cpu_and(cpu, cpu_online_mask, task->cpus_ptr) {
+ dl_se = dl_se_of_tg(task_rt_rq->tg, cpu);
+ rt_rq = &dl_se->my_q->rt;
+ prio = rt_rq->highest_prio.curr;
- ret = cpupri_find(&task_rq(task)->rd->cpupri,
- task, lowest_mask);
+ /*
+ * If we're on asym system ensure we consider the
+ * different capacities of the CPUs when searching for
+ * the lowest_mask.
+ */
+ if (dl_se->dl_throttled || !rt_task_fits_capacity(task, cpu))
+ continue;
+
+ if (prio >= lowest_prio) {
+ if (prio > lowest_prio) {
+ cpumask_clear(lowest_mask);
+ lowest_prio = prio;
+ }
+
+ cpumask_set_cpu(cpu, lowest_mask);
+ }
+ }
}
- if (!ret)
- return -1; /* No targets found */
+ if (cpumask_empty(lowest_mask))
+ return -1;
/*
* At this point we have built a mask of CPUs representing the
@@ -1284,6 +1400,7 @@ static int find_lowest_rt_rq(struct task_struct *task)
* We prioritize the last CPU that the task executed on since
* it is most likely cache-hot in that location.
*/
+ cpu = task_cpu(task);
if (cpumask_test_cpu(cpu, lowest_mask))
return cpu;
@@ -1294,30 +1411,27 @@ static int find_lowest_rt_rq(struct task_struct *task)
if (!cpumask_test_cpu(this_cpu, lowest_mask))
this_cpu = -1; /* Skip this_cpu opt if not among lowest */
- rcu_read_lock();
- for_each_domain(cpu, sd) {
- if (sd->flags & SD_WAKE_AFFINE) {
+ scoped_guard(rcu) {
+ for_each_domain(cpu, sd) {
int best_cpu;
+ if (!(sd->flags & SD_WAKE_AFFINE))
+ continue;
+
/*
* "this_cpu" is cheaper to preempt than a
* remote processor.
*/
if (this_cpu != -1 &&
- cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
- rcu_read_unlock();
+ cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
return this_cpu;
- }
best_cpu = cpumask_any_and_distribute(lowest_mask,
sched_domain_span(sd));
- if (best_cpu < nr_cpu_ids) {
- rcu_read_unlock();
+ if (best_cpu < nr_cpu_ids)
return best_cpu;
- }
}
}
- rcu_read_unlock();
/*
* And finally, if there were no matches within the domains
@@ -1368,27 +1482,35 @@ static struct task_struct *pick_next_pushable_task(struct rt_rq *rt_rq)
/* Will lock the rq it finds */
static struct rt_rq *find_lock_lowest_rt_rq(struct task_struct *task, struct rt_rq *rt_rq)
{
- struct rq *rq = rq_of_rt_rq(rt_rq);
- struct rq *lowest_rq = NULL;
- int tries;
- int cpu;
+ struct rq *lowest_rq, *rq = global_rq_of_rt_rq(rt_rq);
+ struct rt_rq *lowest_rt_rq;
+ struct sched_dl_entity *lowest_dl_se;
+ int tries, cpu;
+ bool dl_group;
+
+ dl_group = rt_group_sched_enabled() && is_dl_group(rt_rq);
for (tries = 0; tries < RT_MAX_TRIES; tries++) {
cpu = find_lowest_rt_rq(task);
if ((cpu == -1) || (cpu == rq->cpu))
- break;
+ return NULL;
lowest_rq = cpu_rq(cpu);
+ if (dl_group) {
+ lowest_dl_se = dl_se_of_tg(rt_rq->tg, cpu);
+ lowest_rt_rq = &lowest_dl_se->my_q->rt;
+ } else {
+ lowest_rt_rq = &lowest_rq->rt;
+ }
- if (lowest_rq->rt.highest_prio.curr <= task->prio) {
+ if (lowest_rt_rq->highest_prio.curr <= task->prio) {
/*
* Target rq has tasks of equal or higher priority,
* retrying does not release any lock and is unlikely
* to yield a different result.
*/
- lowest_rq = NULL;
- break;
+ return NULL;
}
/* if the prio of this runqueue changed, try again */
@@ -1404,25 +1526,24 @@ static struct rt_rq *find_lock_lowest_rt_rq(struct task_struct *task, struct rt_
* check the task migration disable flag here too.
*/
if (unlikely(is_migration_disabled(task) ||
+ (dl_group && lowest_dl_se->dl_throttled) ||
!cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
task != pick_next_pushable_task(rt_rq))) {
double_unlock_balance(rq, lowest_rq);
- lowest_rq = NULL;
- break;
+ return NULL;
}
}
/* If this rq is still suitable use it. */
- if (lowest_rq->rt.highest_prio.curr > task->prio)
- break;
+ if (lowest_rt_rq->highest_prio.curr > task->prio)
+ return lowest_rt_rq;
/* try again */
double_unlock_balance(rq, lowest_rq);
- lowest_rq = NULL;
}
- return &lowest_rq->rt;
+ return NULL;
}
static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) {
@@ -1442,12 +1563,10 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) {
static int push_rt_rq_task(struct rt_rq *rt_rq, bool pull)
{
struct task_struct *next_task;
- struct rq *lowest_rq, *rq = rq_of_rt_rq(rt_rq);
+ struct rq *lowest_rq, *rq = global_rq_of_rt_rq(rt_rq);
struct rt_rq *lowest_rt_rq;
int ret = 0;
-
- if (is_dl_group(rt_rq))
- return 0;
+ bool dl_group;
if (!rt_rq->overloaded)
return 0;
@@ -1462,7 +1581,8 @@ static int push_rt_rq_task(struct rt_rq *rt_rq, bool pull)
* higher priority than current. If that's the case
* just reschedule current.
*/
- if (unlikely(next_task->prio < rq->donor->prio)) {
+ dl_group = rt_group_sched_enabled() && is_dl_group(rt_rq);
+ if (!dl_group && unlikely(next_task->prio < rq->donor->prio)) {
resched_curr(rq);
return 0;
}
@@ -1474,6 +1594,13 @@ static int push_rt_rq_task(struct rt_rq *rt_rq, bool pull)
if (!pull || rq->push_busy)
return 0;
+ /*
+ * If the current task does not belong to the same task group
+ * we cannot push it away.
+ */
+ if (dl_group && rq->donor->sched_task_group != rt_rq->tg)
+ return 0;
+
/*
* Invoking find_lowest_rt_rq() on anything but an RT task doesn't
* make sense. Per the above priority check, curr has to
@@ -1550,7 +1677,7 @@ static int push_rt_rq_task(struct rt_rq *rt_rq, bool pull)
goto retry;
}
- lowest_rq = rq_of_rt_rq(lowest_rt_rq);
+ lowest_rq = global_rq_of_rt_rq(lowest_rt_rq);
move_queued_task_locked(rq, lowest_rq, next_task);
resched_curr(lowest_rq);
ret = 1;
@@ -1747,16 +1874,22 @@ void rto_push_irq_work_func(struct irq_work *work)
static void pull_rt_rq_task(struct rt_rq *this_rt_rq)
{
- struct rq *this_rq = rq_of_rt_rq(this_rt_rq);
+ struct rq* this_rq = global_rq_of_rt_rq(this_rt_rq);
int this_cpu = this_rq->cpu, cpu;
bool resched = false;
- struct task_struct *p, *push_task;
+ struct task_struct *p, *push_task = NULL;
+ struct sched_dl_entity *src_dl_se;
struct rt_rq *src_rt_rq;
struct rq *src_rq;
- int rt_overload_count = rt_overloaded(this_rq);
+ int rt_overload_count;
+ const struct cpumask *cpu_mask;
+ bool dl_group;
- if (is_dl_group(&this_rq->rt))
- return;
+ dl_group = rt_group_sched_enabled() && is_dl_group(this_rt_rq);
+ if (dl_group)
+ goto group_sched;
+
+ rt_overload_count = rt_overloaded(this_rq);
if (likely(!rt_overload_count))
return;
@@ -1779,12 +1912,26 @@ static void pull_rt_rq_task(struct rt_rq *this_rt_rq)
}
#endif
- for_each_cpu(cpu, this_rq->rd->rto_mask) {
+group_sched:
+ if (!dl_group)
+ cpu_mask = this_rq->rd->rto_mask;
+ else
+ cpu_mask = cpu_online_mask;
+
+ for_each_cpu(cpu, cpu_mask) {
if (this_cpu == cpu)
continue;
src_rq = cpu_rq(cpu);
- src_rt_rq = &src_rq->rt;
+ if (!dl_group) {
+ src_rt_rq = &src_rq->rt;
+ } else {
+ src_dl_se = dl_se_of_tg(this_rt_rq->tg, cpu);
+ src_rt_rq = &src_dl_se->my_q->rt;
+
+ if (src_rt_rq->rt_nr_running <= 1 && !src_dl_se->dl_throttled)
+ continue;
+ }
/*
* Don't bother taking the src_rq->lock if the next highest
@@ -1825,12 +1972,21 @@ static void pull_rt_rq_task(struct rt_rq *this_rt_rq)
* This is just that p is waking up and hasn't
* had a chance to schedule. We only pull
* p if it is lower in priority than the
- * current task on the run queue
+ * current task on the run queue and p is
+ * in the same runqueue as donor.
*/
- if (p->prio < src_rq->donor->prio)
+ if (tg_of_se(&src_rq->donor->rt) == this_rt_rq->tg &&
+ p->prio < src_rq->donor->prio)
goto skip;
if (is_migration_disabled(p)) {
+ /*
+ * If the current task does not belong to the
+ * same task group we cannot push it away.
+ */
+ if (tg_of_se(&src_rq->donor->rt) != this_rt_rq->tg)
+ goto skip;
+
push_task = get_push_task(src_rq);
} else {
move_queued_task_locked(src_rq, this_rq, p);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1242d297532f..835af319b78d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1403,6 +1403,16 @@ struct rq {
struct list_head cfsb_csd_list;
#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Balance callbacks operate only on global runqueues.
+ * These pointers allow referencing cgroup specific runqueues
+ * for balancing operations.
+ */
+ struct rq *rq_to_push_from;
+ struct rq *rq_to_pull_to;
+#endif
+
atomic_t nr_iowait;
} __no_randomize_layout;
@@ -3520,6 +3530,11 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
return rt_se->rt_rq;
}
+static inline struct task_group *tg_of_se(struct sched_rt_entity *rt_se)
+{
+ return rt_rq_of_se(rt_se)->tg;
+}
+
static inline int is_dl_group(struct rt_rq *rt_rq)
{
return rt_rq->tg != &root_task_group;
@@ -3536,6 +3551,7 @@ static inline struct sched_dl_entity *dl_group_of(struct rt_rq *rt_rq)
return rt_rq->tg->dl_se[rq_of_rt_rq(rt_rq)->cpu];
}
+#define dl_se_of_tg(tg, cpu) ((tg)->dl_se[(cpu)])
#define dl_bw_lock_of_tg(tg) (&(tg)->dl_bandwidth.dl_runtime_lock)
#else
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
@@ -3560,6 +3576,11 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
return &rq->rt;
}
+static inline struct task_group *tg_of_se(struct sched_rt_entity *rt_se)
+{
+ return &root_task_group;
+}
+
static inline int is_dl_group(struct rt_rq *rt_rq)
{
return 0;
@@ -3570,6 +3591,9 @@ static inline struct sched_dl_entity *dl_group_of(struct rt_rq *rt_rq)
return NULL;
}
+#define rq_to_push_from(rq) (rq)
+#define rq_to_pull_to(rq) (rq)
+#define dl_se_of_tg(tg, cpu) ((struct sched_dl_entity*)NULL)
#define dl_bw_lock_of_tg(tg) ((raw_spinlock_t*)NULL)
#endif
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 20/29] sched/rt: Hook HCBS migration functions
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (18 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 19/29] sched/rt: Add HCBS migration code to related functions Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 21/29] sched/core: Execute enqueued balance callbacks when changing allowed CPUs Yuri Andriaccio
` (8 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Hook rt-cgroup migration functions:
- select_task_rt_rq
Always return the cpu where the task is scheduled.
- balance_rt
- put_prev_task_rt
If a server is throttled, put_prev_task_rt is invoked and a push is
necessary so that the task can keep running on another server if possible.
- switched_to_rt
Keep track of the deadline server that is assigned to the task switching
to FIFO/RR priority.
Set rt-cgroups runqueues to online to allow balancing in balance_rt.
Co-developed-by: Alessio Balsini <a.balsini@sssup.it>
Signed-off-by: Alessio Balsini <a.balsini@sssup.it>
Co-developed-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Co-developed-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/rt.c | 42 +++++++++++++++++++++++++++++++++---------
1 file changed, 33 insertions(+), 9 deletions(-)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0b7c36f8acdc..9d95cf5fd520 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -266,6 +266,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
init_rt_rq(&s_rq->rt);
s_rq->cpu = i;
+ s_rq->online = 1;
s_rq->rt.tg = tg;
init_dl_entity(dl_se);
@@ -1017,6 +1018,10 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)
struct rq *rq;
bool test;
+ /* Just return the task_cpu for processes inside task groups */
+ if (is_dl_group(rt_rq_of_se(&p->rt)))
+ goto out;
+
/* For anything but wake ups, just return the task_cpu */
if (!(flags & (WF_TTWU | WF_FORK)))
goto out;
@@ -1106,27 +1111,30 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
resched_curr(rq);
}
-static int balance_rt(struct rq *rq, struct rq_flags *rf)
+static int balance_rt(struct rq *global_rq, struct rq_flags *rf)
{
/*
* Note, rq->donor may change during rq lock drops,
* so don't re-use p across lock drops
*/
- struct task_struct *p = rq->donor;
+ struct task_struct *p = global_rq->donor;
+ struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);
- if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+ if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq_of_rt_rq(rt_rq), p)) {
/*
* This is OK, because current is on_cpu, which avoids it being
* picked for load-balance and preemption/IRQs are still
* disabled avoiding further scheduler activity on it and we've
* not yet started the picking loop.
*/
- rq_unpin_lock(rq, rf);
- pull_rt_rq_task(&rq->rt);
- rq_repin_lock(rq, rf);
+ rq_unpin_lock(global_rq, rf);
+ pull_rt_rq_task(rt_rq);
+ rq_repin_lock(global_rq, rf);
}
- return sched_stop_runnable(rq) || sched_dl_runnable(rq) || sched_rt_runnable(rq);
+ return sched_stop_runnable(global_rq) ||
+ sched_dl_runnable(global_rq) ||
+ sched_rt_runnable(global_rq);
}
/*
@@ -1293,6 +1301,13 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_s
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rt_rq, p);
+
+ if (is_dl_group(rt_rq)) {
+ struct sched_dl_entity *dl_se = dl_group_of(rt_rq);
+
+ if (dl_se->dl_throttled)
+ rt_queue_push_tasks(rt_rq);
+ }
}
/* Only try algorithms three times */
@@ -2110,12 +2125,21 @@ static void switching_to_rt(struct rq *rq, struct task_struct *p) {}
*/
static void switched_to_rt(struct rq *rq, struct task_struct *p)
{
+ struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);
+
/*
* If we are running, update the avg_rt tracking, as the running time
* will now on be accounted into the latter.
*/
if (task_current(rq, p)) {
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+ if (is_dl_group(rt_rq)) {
+ struct sched_dl_entity *dl_se = dl_group_of(rt_rq);
+
+ p->dl_server = dl_se;
+ }
+
return;
}
@@ -2125,8 +2149,8 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
* then see if we can move to another run queue.
*/
if (task_on_rq_queued(p)) {
- if (p->nr_cpus_allowed > 1 && rt_rq_of_se(&p->rt)->overloaded)
- rt_queue_push_tasks(rt_rq_of_se(&p->rt));
+ if (p->nr_cpus_allowed > 1 && rt_rq->overloaded)
+ rt_queue_push_tasks(rt_rq);
if (p->prio < rq->donor->prio && cpu_online(cpu_of(rq)))
resched_curr(rq);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 21/29] sched/core: Execute enqueued balance callbacks when changing allowed CPUs
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (19 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 20/29] sched/rt: Hook HCBS migration functions Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 22/29] sched/rt: Try pull task on empty server pick Yuri Andriaccio
` (7 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
From: luca abeni <luca.abeni@santannapisa.it>
Execute balancing callbacks when setting the affinity of a task, since
the HCBS scheduler may request balancing of throttled dl_servers to fully
utilize the server's bandwidth.
Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 62039972ded6..aef019cef859 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3019,6 +3019,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask) ||
(task_current_donor(rq, p) && !task_current(rq, p))) {
struct task_struct *push_task = NULL;
+ struct balance_callback *head;
if ((flags & SCA_MIGRATE_ENABLE) &&
(p->migration_flags & MDF_PUSH) && !rq->push_busy) {
@@ -3037,11 +3038,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
}
preempt_disable();
+ head = splice_balance_callbacks(rq);
task_rq_unlock(rq, p, rf);
if (push_task) {
stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
p, &rq->push_work);
}
+ balance_callbacks(rq, head);
preempt_enable();
if (complete)
@@ -3096,6 +3099,8 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
}
if (task_on_cpu(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
+ struct balance_callback *head;
+
/*
* MIGRATE_ENABLE gets here because 'p == current', but for
* anything else we cannot do is_migration_disabled(), punt
@@ -3109,16 +3114,19 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
p->migration_flags &= ~MDF_PUSH;
preempt_disable();
+ head = splice_balance_callbacks(rq);
task_rq_unlock(rq, p, rf);
if (!stop_pending) {
stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
&pending->arg, &pending->stop_work);
}
+ balance_callbacks(rq, head);
preempt_enable();
if (flags & SCA_MIGRATE_ENABLE)
return 0;
} else {
+ struct balance_callback *head;
if (!is_migration_disabled(p)) {
if (task_on_rq_queued(p))
@@ -3129,7 +3137,12 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
complete = true;
}
}
+
+ preempt_disable();
+ head = splice_balance_callbacks(rq);
task_rq_unlock(rq, p, rf);
+ balance_callbacks(rq, head);
+ preempt_enable();
if (complete)
complete_all(&pending->done);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 22/29] sched/rt: Try pull task on empty server pick.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (20 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 21/29] sched/core: Execute enqueued balance callbacks when changing allowed CPUs Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 23/29] sched/core: Execute enqueued balance callbacks after migrate_disable_switch Yuri Andriaccio
` (6 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Try to pull task on a server with an empty runqueue before returning NULL (and
thus shutting down).
---
When all the servers of a cgroup are throttled, work is pending, and any one of
the servers is replenished, it may happen that the runqueue is empty and thus
the replenished server is immediately shut down.
The server may try to pull a task so that the cgroup could consume its
allocated runtime as soon as it is replenished.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/deadline.c | 8 ++++++++
kernel/sched/rt.c | 13 +++++++++++--
2 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 64df71ab370d..219493427e0b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2910,6 +2910,14 @@ static struct task_struct *__pick_task_dl(struct rq *rq, struct rq_flags *rf)
if (dl_server(dl_se)) {
p = dl_se->server_pick_task(dl_se, rf);
+
+ /*
+ * server_pick_task may drop the runqueue lock, so check if
+ * something has shifted.
+ */
+ if (pick_next_dl_entity(dl_rq) != dl_se)
+ goto again;
+
if (!p) {
dl_server_stop(dl_se);
goto again;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 9d95cf5fd520..839977b05d53 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -286,14 +286,23 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
}
static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq);
+static void pull_rt_task(struct rq *);
static struct task_struct *rt_server_pick(struct sched_dl_entity *dl_se, struct rq_flags *rf)
{
struct rt_rq *rt_rq = &dl_se->my_q->rt;
+ struct rq *global_rq = global_rq_of_rt_rq(rt_rq);
struct task_struct *p;
- if (!sched_rt_runnable(dl_se->my_q))
- return NULL;
+ if (!sched_rt_runnable(dl_se->my_q)) {
+ rq_unpin_lock(global_rq, rf);
+ pull_rt_task(rq_of_rt_rq(rt_rq));
+ update_rq_clock(global_rq);
+ rq_repin_lock(global_rq, rf);
+
+ if (!sched_rt_runnable(dl_se->my_q))
+ return NULL;
+ }
p = rt_task_of(pick_next_rt_entity(rt_rq));
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 23/29] sched/core: Execute enqueued balance callbacks after migrate_disable_switch
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (21 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 22/29] sched/rt: Try pull task on empty server pick Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 24/29] sched/syscalls: Allow unpriviledged tasks to set RT priority inside cgroups Yuri Andriaccio
` (5 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Execute balance callbacks after migrate_disable_switch.
Balancing may be requested on the __schedule path, in migrate_disable_switch,
when the running task is throttled and then pushed away from its runqueue.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index aef019cef859..e4e50202896d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2470,6 +2470,9 @@ do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
{
+ struct rq_flags rf;
+ struct balance_callback *head;
+
struct affinity_context ac = {
.new_mask = cpumask_of(rq->cpu),
.flags = SCA_MIGRATE_DISABLE,
@@ -2481,8 +2484,13 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
if (p->cpus_ptr != &p->cpus_mask)
return;
- scoped_guard (task_rq_lock, p)
- do_set_cpus_allowed(p, &ac);
+ rq = task_rq_lock(p, &rf);
+
+ do_set_cpus_allowed(p, &ac);
+
+ head = splice_balance_callbacks(rq);
+ task_rq_unlock(rq, p, &rf);
+ balance_callbacks(rq, head);
}
void ___migrate_enable(void)
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 24/29] sched/syscalls: Allow unpriviledged tasks to set RT priority inside cgroups.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (22 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 23/29] sched/core: Execute enqueued balance callbacks after migrate_disable_switch Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 25/29] sched/rt: Enable HRTICK_DL for HCBS servers Yuri Andriaccio
` (4 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/syscalls.c | 26 +++++++++++++++++++-------
1 file changed, 19 insertions(+), 7 deletions(-)
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index f1e9de478e1d..36bb07b10d41 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -444,15 +444,27 @@ static int user_check_sched_setscheduler(struct task_struct *p,
if (rt_policy(policy)) {
unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
+ struct task_group *active_context;
- /* Can't set/change the rt policy: */
- if (policy != p->policy && !rlim_rtprio)
- goto req_priv;
+ if (!rt_group_sched_enabled())
+ goto root_cgroup_checks;
- /* Can't increase priority: */
- if (attr->sched_priority > p->rt_priority &&
- attr->sched_priority > rlim_rtprio)
- goto req_priv;
+ scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(p->sched_task_group)) {
+ active_context = dl_bandwidth_read(p->sched_task_group)->active_context;
+ }
+
+ /* Allow changing to the rt policy when not in the root cgroup */
+ if (active_context == &root_task_group) {
+root_cgroup_checks:
+ /* Can't set/change the rt policy: */
+ if (policy != p->policy && !rlim_rtprio)
+ goto req_priv;
+
+ /* Can't increase priority: */
+ if (attr->sched_priority > p->rt_priority &&
+ attr->sched_priority > rlim_rtprio)
+ goto req_priv;
+ }
}
/*
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 25/29] sched/rt: Enable HRTICK_DL for HCBS servers.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (23 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 24/29] sched/syscalls: Allow unpriviledged tasks to set RT priority inside cgroups Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 26/29] Documentation: Update documentation for real-time cgroups Yuri Andriaccio
` (3 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
If HRTICK_DL is enabled, start hrtick timers whenever a rt-task that is served
by a rt-cgroup is ticked or enqueued for execution.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/deadline.c | 13 +++++++++++--
kernel/sched/rt.c | 30 ++++++++++++++++++++++++++++++
kernel/sched/sched.h | 1 +
3 files changed, 42 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 219493427e0b..6220d793ae91 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2841,10 +2841,20 @@ static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
{
hrtick_start(rq, dl_se->runtime);
}
+
+int dl_can_start_hrtick(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+ return dl_se->runtime > 0 && is_leftmost(dl_se, &rq->dl);
+}
#else /* !CONFIG_SCHED_HRTICK: */
static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
{
}
+
+int dl_can_start_hrtick(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+ return 0;
+}
#endif /* !CONFIG_SCHED_HRTICK */
/*
@@ -2975,8 +2985,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
* not being the leftmost task anymore. In that case NEED_RESCHED will
* be set and schedule() will start a new hrtick for the next task.
*/
- if (hrtick_enabled_dl(rq) && queued && p->dl.runtime > 0 &&
- is_leftmost(&p->dl, &rq->dl))
+ if (hrtick_enabled_dl(rq) && queued && dl_can_start_hrtick(rq, &p->dl))
start_hrtick_dl(rq, &p->dl);
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 839977b05d53..fffb6ec30e68 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1231,6 +1231,17 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
check_preempt_equal_prio(rq, p);
}
+#ifdef CONFIG_SCHED_HRTICK
+static void start_hrtick_rt(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+ hrtick_start(rq, dl_se->runtime);
+}
+#else /* !CONFIG_SCHED_HRTICK: */
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+}
+#endif /* !CONFIG_SCHED_HRTICK */
+
static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum snt_e type)
{
struct sched_rt_entity *rt_se = &p->rt;
@@ -1258,6 +1269,12 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum s
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
rt_queue_push_tasks(rt_rq);
+
+ if (!is_dl_group(rt_rq))
+ return;
+
+ if (hrtick_enabled_dl(rq))
+ start_hrtick_rt(rq, dl_group_of(rt_rq));
}
static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
@@ -2254,6 +2271,8 @@ static inline void watchdog(struct rq *rq, struct task_struct *p) { }
static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
struct sched_rt_entity *rt_se = &p->rt;
+ struct sched_dl_entity *dl_se;
+ struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
update_curr_rt(rq);
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1);
@@ -2281,6 +2300,17 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
resched_curr(rq);
return;
}
+
+ if (!is_dl_group(rt_rq))
+ return;
+
+ /*
+ * update_curr_rt() might have resulted our dl_server to not be anymore
+ * the leftmost deadline entity, similarly to task_tick_dl.
+ */
+ dl_se = dl_group_of(rt_rq);
+ if (hrtick_enabled_dl(rq) && queued && dl_can_start_hrtick(rq, dl_se))
+ start_hrtick_rt(rq, dl_se);
}
static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 835af319b78d..323befba5609 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -356,6 +356,7 @@ extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *att
extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
extern int dl_bw_deactivate(int cpu);
extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec);
+extern int dl_can_start_hrtick(struct rq *rq, struct sched_dl_entity *dl_se);
/*
* SCHED_DEADLINE supports servers (nested scheduling) with the following
* interface:
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 26/29] Documentation: Update documentation for real-time cgroups
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (24 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 25/29] sched/rt: Enable HRTICK_DL for HCBS servers Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 27/29] sched/rt: Integrate cpuset and cpu controllers Yuri Andriaccio
` (2 subsequent siblings)
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Update the RT_GROUP_SCHED specific documentation. Give a brief theoretical
background for Hierarchical Constant Bandwidth Server (HCBS). Document how
the HCBS is implemented in the kernel and how the RT_GROUP_SCHED behaves
now compared to the version which this patchset replaces.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
Documentation/scheduler/sched-rt-group.rst | 471 +++++++++++++++++----
1 file changed, 394 insertions(+), 77 deletions(-)
diff --git a/Documentation/scheduler/sched-rt-group.rst b/Documentation/scheduler/sched-rt-group.rst
index ab464335d320..9776cf4509cc 100644
--- a/Documentation/scheduler/sched-rt-group.rst
+++ b/Documentation/scheduler/sched-rt-group.rst
@@ -53,9 +53,12 @@ CPU time is divided by means of specifying how much time can be spent running
in a given period. We allocate this "run time" for each real-time group which
the other real-time groups will not be permitted to use.
-Any time not allocated to a real-time group will be used to run normal priority
-tasks (SCHED_OTHER). Any allocated run time not used will also be picked up by
-SCHED_OTHER.
+Each real-time group runs at the same priority as SCHED_DEADLINE, thus they
+share and contend the SCHED_DEADLINE allowed bandwidth. Any time not allocated
+to a real-time group (and SCHED_DEADLINE tasks) will be used to run both
+SCHED_FIFO/SCHED_RR, normal priority tasks (SCHED_OTHER), and SCHED_EXT tasks,
+following the usual priorities. Any allocated run time not used will also be
+picked up by the other scheduling classes, in the same order as before.
Let's consider an example: a frame fixed real-time renderer must deliver 25
frames a second, which yields a period of 0.04s per frame. Now say it will also
@@ -73,10 +76,6 @@ The remaining CPU time will be used for user input and other tasks. Because
real-time tasks have explicitly allocated the CPU time they need to perform
their tasks, buffer underruns in the graphics or audio can be eliminated.
-NOTE: the above example is not fully implemented yet. We still
-lack an EDF scheduler to make non-uniform periods usable.
-
-
2. The Interface
================
@@ -86,105 +85,423 @@ lack an EDF scheduler to make non-uniform periods usable.
The system wide settings are configured under the /proc virtual file system:
-/proc/sys/kernel/sched_rt_period_us:
+``/proc/sys/kernel/sched_rt_period_us``:
The scheduling period that is equivalent to 100% CPU bandwidth.
-/proc/sys/kernel/sched_rt_runtime_us:
- A global limit on how much time real-time scheduling may use. This is always
- less or equal to the period_us, as it denotes the time allocated from the
- period_us for the real-time tasks. Without CONFIG_RT_GROUP_SCHED enabled,
- this only serves for admission control of deadline tasks. With
- CONFIG_RT_GROUP_SCHED=y it also signifies the total bandwidth available to
- all real-time groups.
+``/proc/sys/kernel/sched_rt_runtime_us``:
+ A global limit on how much time real-time scheduling may use (SCHED_DEADLINE
+ tasks + real-time groups). This is always less or equal to the period_us, as
+ it denotes the time allocated from the period_us for the real-time tasks.
+ Without **CONFIG_RT_GROUP_SCHED** enabled, this only serves for admission
+ control of deadline tasks. With **CONFIG_RT_GROUP_SCHED=y** it also signifies
+ the total bandwidth available to both real-time groups and deadline tasks.
* Time is specified in us because the interface is s32. This gives an
operating range from 1us to about 35 minutes.
- * sched_rt_period_us takes values from 1 to INT_MAX.
- * sched_rt_runtime_us takes values from -1 to sched_rt_period_us.
- * A run time of -1 specifies runtime == period, ie. no limit.
- * sched_rt_runtime_us/sched_rt_period_us > 0.05 inorder to preserve
- bandwidth for fair dl_server. For accurate value check average of
- runtime/period in /sys/kernel/debug/sched/fair_server/cpuX/
+ * ``sched_rt_period_us`` takes values from 1 to INT_MAX.
+ * ``sched_rt_runtime_us`` takes values from -1 to ``sched_rt_period_us``.
+ * A run time of -1 specifies runtime == period, i.e., no limit, but also
+ disables admission tests for SCHED_DEADLINE.
+
+The default value for both ``sched_rt_period_us`` and ``sched_rt_runtime_us`` is
+1000000 (or 1s), while fair-servers and ext-servers have a default runtime of
+50ms and default period of 1s, giving a minimum of 0.05s to be used by
+SCHED_FIFO/SCHED_RR and non-RT tasks (SCHED_OTHER, SCHED_EXT), while 0.95s are
+the maximum to be used by SCHED_DEADLINE, and rt-cgroups if enabled.
+
+2.2 Cgroup settings
+-------------------
+
+Enabling **CONFIG_RT_GROUP_SCHED** lets you explicitly allocate real CPU
+bandwidth to task groups.
+
+ .. warning::
+ Real Time Cgroups are only available for cgroups-v2.
+ ..
+
+This uses the cgroup virtual file system and the CPU controller for cgroups.
+Enabling the controller for the hierarchy creates two files:
+
+* ``<cgroup>/cpu.rt.max``, which specifies the runtime and period of the group.
+ The file also accepts a runtime of 'max', specifying that its tasks must be
+ scheduled using the nearest configured ancestor (or the root cgroup if it is
+ the nearest non-max ancestor).
+* ``<cgroup>/cpu.rt.effective.local``, read-only, returns the runtime and period
+ actually allocated to the group, excluding that of its children.
+
+ .. tip::
+ For more information on working with control groups, you should read
+ *Documentation/admin-guide/cgroup-v2.rst*.
+ ..
+
+By default the root cgroup has the same period of
+``/proc/sys/kernel/sched_rt_period_us``, which is 1s, and a runtime of zero, so
+that rt-cgroup is *soft-disabled* by default, and all the runtime is available
+for SCHED_DEADLINE tasks only. New groups instead get a period of zero and
+runtime of 'max' (essentially delegating their tasks' scheduling to the nearest
+configured ancestor).
+
+3. Theoretical Background
+=========================
+
+
+ .. BIG FAT WARNING ******************************************************
+
+ .. warning::
+
+ This section contains a (not-thorough) summary on deadline/hierarchical
+ scheduling theory, and how it applies to real-time control groups.
+ The reader can "safely" skip to Section 4 if only interested in seeing
+ how the scheduling policy can be used. Anyway, we strongly recommend
+ to come back here and continue reading (once the urge for testing is
+ satisfied :P) to be sure of fully understanding all technical details.
+
+ .. ************************************************************************
+
+The real-time cgroup scheduler is based upon the **Hierarchical Constant
+Bandwidth Server** (HCBS) [1] *Compositional Scheduling Framework* (CSF). A
+**CSF** is a framework where global (system-level) timing properties can be
+established by composing independently (specified and) analyzed local
+(component-level) timing properties [5].
+
+For HCBS (related to the Linux kernel), the compositional framework consists of
+two parts:
+
+* The *scheduling components*, which are the basic units of the scheduling. In
+ the kernel these are the single cgroups along with the tasks that must be run
+ inside.
+
+* The *scheduling resources*, which are the CPUs of the machine.
+
+HCBS is a *hierarchical scheduling framework*, where the scheduling components
+form a hierarchy and resources are allocated from parent components to its child
+components in the hierarchy.
+
+The Chapter is organized as follows: **Section 3.1** gives basic real-time
+theory definitions that are used throughout the whole section. **Section 3.2**
+talks about the HCBS framework, giving a general idea on how this is structured.
+**Section 3.3** introduces the MPR model, one of the many models which may be
+used for the analysis of the scheduling components and the computation of the
+minimum required scheduling resources for a given component. **Section 3.4**
+shows the schedulability test for MPR on the HCBS framework. **Section 3.5**
+shows how to convert a MPR interface to a HCBS compatible resource reservation
+for a component. Finally, **Section 3.6** lists other interesting models which
+could be used for the component analysis in HCBS.
+
+3.1 Basic Definitions
+---------------------
+*We borrow the same definitions given in the* ``sched_deadline`` *document,
+which are very briefly summarized here, and new ones, needed by the following
+content, are added.*
+
+A typical real-time task is composed of a repetition of computation phases (task
+instances, or jobs) which are activated on a periodic or sporadic fashion. For
+our purposes, real-time tasks are characterized by three parameters:
+
+* Worst Case Execution Time (WCET): the maximum execution time among all jobs.
+* Relative Deadline (D): the maximum time each job must be completed, relative
+ to the release time of the job.
+* Inter-Arrival Period (P): the exact/minimum (for periodic/sporadic tasks) time
+ between each consecutive job.
+
+3.2 Hierarchical Constant Bandwidth Server (HCBS) [1]
+-----------------------------------------------------
+
+As mentioned, HCBS is a *hierarchical scheduling framework*:
+
+* The framework hierarchy follows the same hierarchy of cgroups. Cgroups may
+ have two roles, either bandwidth reservation for children cgroups, or they may
+ be *live*, i.e. run tasks (but not both). The root cgroup, for the kernel's
+ implementation of HCBS, acts only as bandwidth reservation (but as written in
+ this document it has also different uses outside of the hierarchical
+ framework).
+* The cgroup tree is internally flattened, for ease of scheduling, to a
+ two-level hierarchy, since only the *live* groups are of interest and all the
+ necessary information for their scheduling lies in their interface (there is
+ no need for the reservation components).
+* The hierarchical framework, now on two levels, consists then of a first level
+ of cgroups, and a second level of tasks that are run inside these groups.
+* The scheduling of components is performed using global Earliest Deadline First
+ (gEDF), SCHED_DEADLINE in the kernel, following the bandwidth reservation of
+ each group.
+* Whenever a component is scheduled, a local scheduler picks which of the tasks
+ of the cgroup to run. The scheduling policy is global Fixed Priority (gFP),
+ SCHED_FIFO/SCHED_RR in the kernel.
-2.2 Default behaviour
----------------------
+3.3 Multiprocessor Periodic Resource (MPR) model
+------------------------------------------------
+
+A Multiprocessor Periodic Resource (MPR) model [2] **u = <Pi, Theta, m'>**
+specifies that an identical, unit-capacity multiprocessor platform collectively
+provides **Theta** units of resource every **Pi** time units, where the
+**Theta** time units are supplied with concurrency at most **m'**.
+
+This theoretical model is one of the many models that can abstract the
+interface of our real-time cgroups: let **m'** be the number of CPUs of the
+machine, let **Theta** be **m' * <cgroup>/cpu.rt_runtime_us** and **Pi** be
+**<cgroup>/cpu.rt_period_us**.
+
+Let's introduce the concept of Supply Bound Function (SBF). A SBF is a function
+which outputs a lower bound for the processor supply provided in a given time
+interval, given a resource supply model. For a completely dedicated CPU, the SBF
+function is simply the identity function, as it will always provide **t** units
+of computation for an interval of length **t**. The situation gets slightly more
+complicated for the MPR model or any of the other model listed in section 3.6.
+
+The **SBF(t)** for a MPR model **u = <Pi, Theta, m'>** is::
+
+ | 0 if t' < 0
+ |
+ SBF_u(t) = | floor(t' / Pi) * Theta
+ | + max(0, m' * x - (m' * Pi - Theta)) if t' >= 0 and 1 <= x <= y
+ |
+ | floor(t' / Pi) * Theta
+ | + max(0, m' * x - (m' * Pi - Theta)) else
+ | - (m' - beta)
+
+where::
+
+ alpha = floor(Theta / m')
+ beta = Theta - m' * alpha
+ t' = t - (Pi - ceil(Theta / m'))
+ x = t' - (Pi * floor(t' / Pi))
+ y = Pi - floor(Theta / m')
+
+Briefly, this function models that the server's bandwidth is given as late as
+possible, so describing the worst case possible for the supplied bandwidth.
+
+3.4 Schedulability for MPR on global Fixed-Priority
+---------------------------------------------------
+
+Let's introduce the concept of Demand Bound Function (DBF). A DBF is a function
+that, given a taskset, a scheduling algorithm and an interval of time, outputs
+the worst resource demand for that interval of time.
+
+It is easy to see that, given a DBF and a SBF, we can deem a component/taskset
+schedulable if, for every time interval t >= 0, it is possible to demonstrate
+that:
+
+ DBF(t) <= SBF(t)
+
+We have the Supply Bound Function for our given MPR model, so we are missing the
+Demand Bound Function for a given taskset that is being scheduled using global
+Fixed Priority.
+
+3.4.1 Schedulability Analysis for global Fixed Priority
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Bertogna, Cirinei and Lipari [6] have derived a schedulability test for global
+Fixed Priority (gFP) on multi-processor platforms. In this test (called
+*BCL_gFP* test) we can consider all the CPUs to be dedicated to the scheduling.
+
+ A taskset **Tau** is schedulable with gFP on a multiprocessor platform
+ composed of **m'** identical processors if for each task **tau_k in Tau**:
+
+ Sum(for i < k)( min(W_i(D_k), D_k - C_k + 1) ) < m' * (D_k - C_k + 1)
+
+ where **W_i(t)** is the workload of task **tau_i** over a time interval **t**:
+
+ W_i(t) = N_i(t) * C_i + min(C_i, t + D_i - C_i - N_i(t) * P_i)
+
+ and **N_i(t)** is the number of activations of task **tau_i** that complete in
+ a time interval **t**:
-The default values for sched_rt_period_us (1000000 or 1s) and
-sched_rt_runtime_us (950000 or 0.95s). This gives 0.05s to be used by
-SCHED_OTHER (non-RT tasks). These defaults were chosen so that a run-away
-real-time tasks will not lock up the machine but leave a little time to recover
-it. By setting runtime to -1 you'd get the old behaviour back.
+ N_i(t) = floor( (t + D_i - C_i) / P_i )
-By default all bandwidth is assigned to the root group and new groups get the
-period from /proc/sys/kernel/sched_rt_period_us and a run time of 0. If you
-want to assign bandwidth to another group, reduce the root group's bandwidth
-and assign some or all of the difference to another group.
+ while the **min** term is the contribution of the carried-out job in the
+ interval **t**, i.e. that job that does not completely fit in the interval
+ **t**, but starts inside the interval after all the jobs that complete.
+
+3.4.2 From BCL_gFP to the Demand Bound Function
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+We can then derive the DBF from this test:
+
+ DBF_gFP(tau_k) = Sum(for i < k)( min(W_i(D_k), D_k - C_k + 1) ) + m' * (C_k - 1)
+
+Briefly, the first sum component, the same in the BCL_gFP test, describes the
+maximum interference that higher priority task give to the analysed task. The
+workload is upperbounded by ``(D_k - C_K + 1)`` because we are only interested
+in the interference in the slack time, while for the ``C_k`` time we are
+requiring that all the CPUs are fully available, as the single job needs `C_k`
+(non overlapping) time units to run.
+
+The demand bound function from Bertogna et al. is only defined on a single time
+(i.e. the deadline of the task in analysis) instead of all possible times as
+this is the minimum argument to demonstrate schedulability on global Fixed
+Priority.
+
+3.4.3 Putting it all together
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+A component **C**, on **m'** processors, running a taskset **Tau = { tau_1 =
+(C_1, D_1, P_1), ..., tau_n = (C_n, D_n, P_n) }** of **n** sporadic tasks, is
+schedulable under gFP using an MPR model **u = <Pi, Theta, m'>**, if for all
+tasks **tau_k in Tau**:
+
+ DBF_gFP(tau_k) <= SBF_u(D_k)
+
+3.5 From MPR to deadline servers
+--------------------------------
+
+Since there exist no algorithm to schedule MPR interfaces, a tecnique was
+developed to transform MPR interfaces into periodic tasks, so that a
+number of periodic servers which respect the tasks requirements can be used for
+the scheduling of the MPR interface and associated tasks.
+
+Let **u = <Pi, Theta, m>** be a MPR interface, let **a = Theta - m * floor(Theta
+/ m)**, let **k = floor(a)**. Define a transformation from **u** to a periodic
+taskset **Tau_u = { tau_1 = (C_1, D_1, P_1), ..., tau_m' = (C_m', D_m', P_m')
+}**, where:
+
+ **tau_1 = ... = tau_k = (floor(Theta / m') + 1, Pi, Pi)**
+
+ **tau_k+1 = (floor(Theta / m') + a - k * floor(a/k), Pi, Pi)**
+
+ **tau_k+2 = ... = tau_m' = (floor(Theta / m'), Pi, Pi)**
+
+This periodic taskset of servers **Tau_u** can be scheduled on any number of
+processors with concurrency at most **m'**.
+
+For real-time control groups, it is possible to just consider a slightly more
+demanding taskset **Tau_u'**, where each task **tau_i** is defined as follows:
+
+ **tau_i = (ceil(Theta / m'), Pi, Pi)**
+
+3.6 Other models
+----------------
+
+There exist many other theoretical models in literature which are used to
+describe a hierarchical scheduling framework on multi-core architectures.
+Notable examples are the Multi Supply Function (MSF) abstraction [3], the
+Parallel Supply Function (PSF) abstraction [4] and the Bounded Delay
+Multipartition (BDM) [7].
+
+3.7 References
+--------------
+ 1 - L. Abeni, A. Balsini, and T. Cucinotta, “Container-based real-time
+ scheduling in the Linux kernel,” SIGBED Rev., vol. 16, no. 3, pp. 33-38,
+ Nov. 2019, doi: 10.1145/3373400.3373405.
+ 2 - A. Easwaran, I. Shin, and I. Lee, “Optimal virtual cluster-based
+ multiprocessor scheduling,” Real-Time Syst, vol. 43, no. 1, pp. 25-59,
+ Sept. 2009, doi: 10.1007/s11241-009-9073-x.
+ 3 - E. Bini, G. Buttazzo, and M. Bertogna, “The Multi Supply Function
+ Abstraction for Multiprocessors,” in 2009 15th IEEE International
+ Conference on Embedded and Real-Time Computing Systems and Applications,
+ Aug. 2009, pp. 294-302. doi: 10.1109/RTCSA.2009.39.
+ 4 - E. Bini, B. Marko, and S. K. Baruah, “The Parallel Supply Function
+ Abstraction for a Virtual Multiprocessor,” in Scheduling, S. Albers, S. K.
+ Baruah, R. H. Möhring, and K. Pruhs, Eds., in Dagstuhl Seminar Proceedings
+ (DagSemProc), vol. 10071. Dagstuhl, Germany: Schloss Dagstuhl -
+ Leibniz-Zentrum für Informatik, 2010, pp. 1-14. doi:
+ 10.4230/DagSemProc.10071.14.
+ 5 - I. Shin and I. Lee, “Compositional real-time scheduling framework,” in
+ 25th IEEE International Real-Time Systems Symposium, Dec. 2004, pp. 57-67.
+ doi: 10.1109/REAL.2004.15.
+ 6 - M. Bertogna, M. Cirinei, and G. Lipari, “Schedulability Analysis of Global
+ Scheduling Algorithms on Multiprocessor Platforms,” IEEE Transactions on
+ Parallel and Distributed Systems, vol. 20, no. 4, pp. 553-566, Apr. 2009,
+ doi: 10.1109/TPDS.2008.129.
+ 7 - G. Lipari and E. Bini, “A Framework for Hierarchical Scheduling on
+ Multiprocessors: From Application Requirements to Run-Time Allocation,” in
+ 2010 31st IEEE Real-Time Systems Symposium, Nov. 2010, pp. 249-258. doi:
+ 10.1109/RTSS.2010.12.
+
+
+4. Using Real-Time cgroups
+==========================
+
+4.1 CGroup Setup
+----------------
-Real-time group scheduling means you have to assign a portion of total CPU
-bandwidth to the group before it will accept real-time tasks. Therefore you will
-not be able to run real-time tasks as any user other than root until you have
-done that, even if the user has the rights to run processes with real-time
-priority!
+The following is a brief guide to the use of Real-Time Control Groups.
+Of course, real-time control groups require mounting of the cgroup file system.
+We have decided to only support cgroups v2, so make sure you mount the v2
+controller for the cgroup hierarchy.
-2.3 Basis for grouping tasks
-----------------------------
+Additionally the real-time cgroups require the CPU controller for the cgroups to
+be enabled::
-Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
-CPU bandwidth to task groups.
+ # Assume the cgroup file system is mounted at /sys/fs/cgroup
+ > echo "+cpu" > /sys/fs/cgroup/cgroup.subtree_control
-This uses the cgroup virtual file system and "<cgroup>/cpu.rt_runtime_us"
-to control the CPU time reserved for each control group.
+The CPU controller can only be mounted if there is no SCHED_FIFO/SCHED_RR task
+scheduled in any cgroup other than the root control group.
-For more information on working with control groups, you should read
-Documentation/admin-guide/cgroup-v1/cgroups.rst as well.
+The root control group has no bandwidth allocated by default, so make sure to
+allocate some bandwidth so that it can be used by the other cgroups. More on
+that in the following section...
-Group settings are checked against the following limits in order to keep the
-configuration schedulable:
+4.2 Bandwidth Allocation for groups
+-----------------------------------
- \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period
+Allocating bandwidth to a cgroup is a fundamental step to run real-time
+workload. The cgroup filesystem exposes two files:
-For now, this can be simplified to just the following (but see Future plans):
+* ``<cgroup>/cpu.rt.max``: which specifies the cgroups' runtime and period in
+ microseconds.
+* ``<cgroup>/cpu.rt.effective.local``: read-only, get the cgroups' actualy
+ runtime and period in microseconds, without its children's bandwidth.
- \Sum_{i} runtime_{i} <= global_runtime
+By definition, the specified runtime must be always less than or equal to the
+period. Additionally, an admission test checks if the bandwidth invariant is
+respected (i.e. sum of children's bandwidth <= parent's bandwidth).
+The root control group files instead control and reserve the SCHED_DEADLINE
+bandwidth allocated to real-time cgroups, since real-time groups compete and
+share the same bandwidth allocated to SCHED_DEADLINE tasks.
-3. Future plans
-===============
+4.3 Running real-time tasks in groups
+-------------------------------------
-There is work in progress to make the scheduling period for each group
-("<cgroup>/cpu.rt_period_us") configurable as well.
+To run tasks in real-time groups it is just necessary to change a task's
+scheduling policy to SCHED_FIFO/SCHED_RR and migrate it into the group. If the
+group is not allowed to run real-time tasks because of incorrect configuration,
+either migrating a SCHED_FIFO/SCHED_RR task into the group or changing
+scheduling policy to a task already inside the group will fail::
-The constraint on the period is that a subgroup must have a smaller or
-equal period to its parent. But realistically its not very useful _yet_
-as its prone to starvation without deadline scheduling.
+ # assume there is a task of PID 42 running
+ # change its scheduling policy to SCHED_FIFO, priority 99
+ > chrt -f -p 99 42
-Consider two sibling groups A and B; both have 50% bandwidth, but A's
-period is twice the length of B's.
+ # migrate the task to a cgroup
+ > echo 42 > /sys/fs/cgroup/<my-cgroup>/cgroup.procs
-* group A: period=100000us, runtime=50000us
+4.4 Special case: the root control group
+----------------------------------------
- - this runs for 0.05s once every 0.1s
+The root cgroup is special, compared to the other cgroups, as its tasks are not
+managed by the HCBS algorithm, rather they just use the original
+SCHED_FIFO/SCHED_RR policies (as if CONFIG_RT_GROUP_SCHED was disabled). As
+mentioned, its bandwidth files are just used to control how much of the
+SCHED_DEADLINE bandwidth is allocated to cgroups.
-* group B: period= 50000us, runtime=25000us
+Any non-root cgroup configured as 'max' that has the root cgroup as its nearest
+non-max ancestor will run its tasks in the root runqueue.
- - this runs for 0.025s twice every 0.1s (or once every 0.05 sec).
+4.5 Guarantees and Special Behaviours
+-------------------------------------
-This means that currently a while (1) loop in A will run for the full period of
-B and can starve B's tasks (assuming they are of lower priority) for a whole
-period.
+Real-time cgroups are run at the same priority level of SCHED_DEADLINE tasks.
+Since this is the highest priority scheduling policy, and since the Constant
+Bandwidth Server (CBS) enforces that the specified bandwidth requirements for
+both groups and tasks cannot be overrun, real-time groups have the same
+guarantees that SCHED_DEADLINE tasks have, i.e. they will be necessarily
+supplied by the amount of bandwidth requested (whenever the admission tests
+pass).
-The next project will be SCHED_EDF (Earliest Deadline First scheduling) to bring
-full deadline scheduling to the linux kernel. Deadline scheduling the above
-groups and treating end of the period as a deadline will ensure that they both
-get their allocated time.
+This means that, since SCHED_FIFO/SCHED_RR tasks (scheduled in the root control
+group) are not subject to bandwidth controls, they are run at a lower priority
+than the cgroups' counterparts. Nonetheless, a minimum amount of bandwidth, if
+reserved, will always be available to run SCHED_FIFO/SCHED_RR workloads in the
+root cgroup, while they will be able to use more runtime if any of the
+SCHED_DEADLINE tasks or servers use less than their specified amount of
+bandwidth. SCHED_OTHER tasks are instead scheduled as normal, at lower priority
+than real-time workloads.
-Implementing SCHED_EDF might take a while to complete. Priority Inheritance is
-the biggest challenge as the current linux PI infrastructure is geared towards
-the limited static priority levels 0-99. With deadline scheduling you need to
-do deadline inheritance (since priority is inversely proportional to the
-deadline delta (deadline - now)).
+The aforementioned behaviour differs from the preceding RT_GROUP_SCHED
+implementation, but this is necessary to give actual guarantees to the amount of
+bandwidth given to rt-cgroups.
-This means the whole PI machinery will have to be reworked - and that is one of
-the most complex pieces of code we have.
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 27/29] sched/rt: Integrate cpuset and cpu controllers
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (25 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 26/29] Documentation: Update documentation for real-time cgroups Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 28/29] sched/rt: Prevent CPU offline operation on active rt-cgroups Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 29/29] sched/rt: Introduce multi-cpu support Yuri Andriaccio
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Integrate the cpuset and cpu controllers:
- cpuset cannot be changed if the HCBS cgroup is active (non-max)
or any of the group's children is active (cpuset_can_change function).
- introduce cpuset_effective_cpus to read the cpuset's effective mask.
- update struct dl_bandwidth to store the effective mask of the cgroup.
- remove the dl_internal_runtime in dl_bandwidth as this value is now
per-cpu/server and equal to dl_se->dl_runtime.
- update schedulability checks to account for cpumasks.
- update cpu.rt.effective.local interface to show per-cpu internal
values.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
include/linux/cpuset.h | 2 +
kernel/cgroup/cpuset.c | 31 +++++
kernel/sched/core.c | 22 +++-
kernel/sched/deadline.c | 13 ++-
kernel/sched/rt.c | 249 ++++++++++++++++++++++++++--------------
kernel/sched/sched.h | 9 +-
6 files changed, 237 insertions(+), 89 deletions(-)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 914983387e95..6487bdbbdeb3 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -81,6 +81,8 @@ extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *ma
extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
extern int cpuset_num_cpus(struct cgroup *cgroup);
+extern void cpuset_effective_cpus(struct cgroup *cgroup, struct cpumask *mask);
+extern int cpuset_can_change(struct cgroup *cgroup);
extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
#define cpuset_current_mems_allowed (current->mems_allowed)
void cpuset_init_current_mems_allowed(void);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 3219f927c35e..c7fd878154c6 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2572,6 +2572,10 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
return 0;
+ /* Disallow change if subtree has any allocated rt-cgroup */
+ if (!cpuset_can_change(cs->css.cgroup))
+ return -EINVAL;
+
compute_trialcs_excpus(trialcs, cs);
trialcs->prs_err = PERR_NONE;
@@ -2632,6 +2636,10 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus))
return 0;
+ /* Disallow change if subtree has any allocated rt-cgroup */
+ if (!cpuset_can_change(cs->css.cgroup))
+ return -EINVAL;
+
/*
* Reject the change if there is exclusive CPUs conflict with
* the siblings.
@@ -3585,6 +3593,10 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
else
return -EINVAL;
+ /* Disallow change if subtree has any allocated rt-cgroup */
+ if (!cpuset_can_change(cs->css.cgroup))
+ return -EINVAL;
+
mutex_lock(&cpuset_top_mutex);
cpus_read_lock();
wait_attach_done_lock();
@@ -4354,6 +4366,25 @@ int cpuset_num_cpus(struct cgroup *cgrp)
return nr;
}
+void cpuset_effective_cpus(struct cgroup *cgrp, struct cpumask *mask)
+{
+ struct cpuset *cs;
+
+ if (!is_in_v2_mode()) {
+ cpumask_copy(mask, cpu_online_mask);
+ return;
+ }
+
+ guard(rcu)();
+ cs = css_cs(cgroup_e_css(cgrp, &cpuset_cgrp_subsys));
+ if (!cs) {
+ cpumask_copy(mask, cpu_online_mask);
+ return;
+ }
+
+ cpumask_copy(mask, cs->effective_cpus);
+}
+
void __init cpuset_init_current_mems_allowed(void)
{
nodes_setall(current->mems_allowed);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e4e50202896d..59bd9599c509 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8970,6 +8970,8 @@ void __init sched_init(void)
init_defrootdomain();
#ifdef CONFIG_RT_GROUP_SCHED
+ BUG_ON(!alloc_dl_bandwidth(&root_task_group.dl_bandwidth, GFP_NOWAIT));
+
init_dl_bandwidth(&root_task_group.dl_bandwidth,
global_rt_period(), 0, &root_task_group);
#endif /* CONFIG_RT_GROUP_SCHED */
@@ -10426,6 +10428,19 @@ static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
seq_printf(sf, " %ld\n", period);
}
+static void __maybe_unused cpu_period_quota_single_print(struct seq_file *sf, int cpu,
+ long period, long quota)
+{
+ seq_printf(sf, "%d ", cpu);
+
+ if (quota < 0)
+ seq_puts(sf, "runtime=max");
+ else
+ seq_printf(sf, "runtime=%ld", quota);
+
+ seq_printf(sf, " period=%ld\n", period);
+}
+
/* caller should put the current value in *@periodp before calling */
static int __maybe_unused cpu_period_quota_parse(char *buf, u64 *period_us_p,
u64 *quota_us_p)
@@ -10486,9 +10501,12 @@ static int cpu_rt_internal_show(struct seq_file *sf, void *v)
{
struct task_group *tg = css_tg(seq_css(sf));
u64 period_us, runtime_us;
+ int cpu;
- tg_rt_internal_bandwidth(tg, &period_us, &runtime_us);
- cpu_period_quota_print(sf, period_us, runtime_us);
+ for_each_possible_cpu(cpu) {
+ tg_rt_internal_bandwidth(tg, cpu, &period_us, &runtime_us);
+ cpu_period_quota_single_print(sf, cpu, period_us, runtime_us);
+ }
return 0;
}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6220d793ae91..0282258db3e9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -592,14 +592,25 @@ static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq
static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
+struct dl_bandwidth *alloc_dl_bandwidth(struct dl_bandwidth *dl_b, gfp_t gfp_flags) {
+ if (!alloc_cpumask_var(&dl_b->active_mask, gfp_flags))
+ return NULL;
+
+ return dl_b;
+}
+
+void free_dl_bandwidth(struct dl_bandwidth *dl_b) {
+ free_cpumask_var(dl_b->active_mask);
+}
+
void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime,
struct task_group *active_context)
{
raw_spin_lock_init(&dl_b->dl_runtime_lock);
dl_b->dl_period = period;
dl_b->dl_runtime = runtime;
- dl_b->dl_internal_runtime = 0;
dl_b->active_context = active_context;
+ cpumask_clear(dl_b->active_mask);
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index fffb6ec30e68..37e4b24183ab 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -172,6 +172,7 @@ void free_rt_sched_group(struct task_group *tg)
kfree(tg->rt_rq);
kfree(tg->dl_se);
+ free_dl_bandwidth(&tg->dl_bandwidth);
}
static inline void __rt_rq_free(struct rt_rq **rt_rq)
@@ -206,6 +207,7 @@ static int __alloc_rt_sched_group_data(struct task_group *tg) {
struct rt_rq **tg_rt_rq __free(rt_rq_free) = NULL;
struct sched_dl_entity **tg_dl_se __free(dl_se_free) = NULL;
struct sched_dl_entity *dl_se __free(kfree) = NULL;
+ struct dl_bandwidth *dl_b __free(dl_bandwidth_free) = NULL;
struct rq *s_rq __free(kfree) = NULL;
int i;
@@ -218,6 +220,10 @@ static int __alloc_rt_sched_group_data(struct task_group *tg) {
if (!tg_dl_se)
return 0;
+ dl_b = alloc_dl_bandwidth(&tg->dl_bandwidth, GFP_KERNEL);
+ if(!dl_b)
+ return 0;
+
for_each_possible_cpu(i) {
s_rq = kzalloc_node(sizeof(struct rq),
GFP_KERNEL, cpu_to_node(i));
@@ -235,6 +241,7 @@ static int __alloc_rt_sched_group_data(struct task_group *tg) {
tg->rt_rq = no_free_ptr(tg_rt_rq);
tg->dl_se = no_free_ptr(tg_dl_se);
+ retain_and_null_ptr(dl_b);
return 1;
}
@@ -1416,7 +1423,8 @@ static int find_lowest_rt_rq(struct task_struct *task)
* different capacities of the CPUs when searching for
* the lowest_mask.
*/
- if (dl_se->dl_throttled || !rt_task_fits_capacity(task, cpu))
+ if (!dl_se->dl_runtime || dl_se->dl_throttled ||
+ !rt_task_fits_capacity(task, cpu))
continue;
if (prio >= lowest_prio) {
@@ -1567,7 +1575,8 @@ static struct rt_rq *find_lock_lowest_rt_rq(struct task_struct *task, struct rt_
* check the task migration disable flag here too.
*/
if (unlikely(is_migration_disabled(task) ||
- (dl_group && lowest_dl_se->dl_throttled) ||
+ (dl_group && lowest_dl_se->dl_throttled &&
+ !lowest_dl_se->dl_runtime) ||
!cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
task != pick_next_pushable_task(rt_rq))) {
@@ -2418,114 +2427,132 @@ static int tg_subtree_has_rt_tasks(struct task_group *tg) {
dl_bandwidth_read(tg)->active_context);
}
+static inline u64 tg_cpu_period(const struct dl_bandwidth *dl_b, int cpu) {
+ return cpumask_test_cpu(cpu, dl_b->active_mask) ? dl_b->dl_period : 0;
+}
+
+static inline u64 tg_cpu_runtime(const struct dl_bandwidth *dl_b, int cpu) {
+ return cpumask_test_cpu(cpu, dl_b->active_mask) ? dl_b->dl_runtime : 0;
+}
+
struct tg_update_data {
struct task_group *tg;
- u64 rt_period;
- u64 rt_runtime;
+ struct dl_bandwidth dl_b;
};
struct tg_compute_children_bw_data {
struct tg_update_data update;
struct task_group *active_context;
- u64 period;
- u64 runtime_sum;
+ const struct cpumask *mask;
+ u64 *rt_runtime_sum;
};
static int __tg_compute_children_runtime(struct task_group *tg, void *data) {
struct tg_compute_children_bw_data *d = data;
const struct task_group *parent_active_context;
- const struct dl_bandwidth *dl_b_parent, *dl_b = dl_bandwidth_read(tg);
- u64 period, runtime;
+ const struct dl_bandwidth *reference_dl_b, *dl_b_parent, *dl_b;
+ u64 reference_period, period, runtime;
+ int cpu;
/* Skip the current task group from the sum. */
if (tg == d->active_context)
return 0;
- period = dl_b->dl_period;
- runtime = dl_b->dl_runtime;
+ reference_dl_b = dl_bandwidth_read(d->active_context);
+ dl_b = dl_bandwidth_read(tg);
if (tg == d->update.tg) {
- period = d->update.rt_period;
- runtime = d->update.rt_runtime;
+ dl_b = &d->update.dl_b;
}
- if (runtime == RUNTIME_INF || period == 0)
+
+ /* Skip the task group if runtime = `max` */
+ if (dl_b->dl_runtime == RUNTIME_INF)
return 0;
+ /* Skip the task group if it's parent active context is not current */
dl_b_parent = dl_bandwidth_read(tg->parent);
parent_active_context = dl_b_parent->active_context;
if (tg->parent == d->update.tg) {
if (dl_b_parent->dl_runtime != RUNTIME_INF &&
- d->update.rt_runtime == RUNTIME_INF)
+ d->update.dl_b.dl_runtime == RUNTIME_INF)
parent_active_context = dl_bandwidth_read(tg->parent->parent)->active_context;
- else if (d->update.rt_runtime != RUNTIME_INF)
+ else if (d->update.dl_b.dl_runtime != RUNTIME_INF)
parent_active_context = tg->parent;
}
if (parent_active_context != d->active_context)
return 0;
- d->runtime_sum += mul_u64_u64_div_u64(runtime, d->period, period);
+ for_each_cpu(cpu, d->mask) {
+ reference_period = tg_cpu_period(reference_dl_b, cpu);
+ period = tg_cpu_period(dl_b, cpu);
+ runtime = tg_cpu_runtime(dl_b, cpu);
+
+ if (period)
+ d->rt_runtime_sum[cpu] += mul_u64_u64_div_u64(runtime, reference_period, period);
+ }
+
return 0;
}
-static u64
-tg_compute_children_runtime(struct task_group *tg,
- u64 normalization_period,
- struct tg_update_data *data)
+static void tg_compute_children_runtime(struct task_group *tg,
+ struct tg_update_data *data,
+ const struct cpumask *mask,
+ u64 *sum_runtime)
{
+ int cpu;
struct tg_compute_children_bw_data sum_data = {
.active_context = tg,
- .period = normalization_period,
- .runtime_sum = 0,
+ .rt_runtime_sum = sum_runtime,
+ .mask = mask,
.update = *data,
};
+ for_each_cpu(cpu, mask)
+ sum_runtime[cpu] = 0;
+
lockdep_assert(rcu_read_lock_held());
walk_tg_tree_from(tg, __tg_compute_children_runtime, tg_nop, &sum_data);
- return sum_data.runtime_sum;
}
struct rt_schedulable_data {
struct tg_update_data update;
- u64 rt_runtime_remainder;
+ u64 *children_runtime;
+ u64 *rt_runtime_remainder;
};
static int __tg_rt_schedulable(struct task_group *tg, void *data)
{
struct rt_schedulable_data *d = data;
const struct dl_bandwidth *dl_b;
- u64 total, sum = 0;
- u64 period, runtime;
+ u64 total, runtime;
+ int cpu;
dl_b = dl_bandwidth_read(tg);
- period = dl_b->dl_period;
- runtime = dl_b->dl_runtime;
-
if (tg == d->update.tg) {
- period = d->update.rt_period;
- runtime = d->update.rt_runtime;
+ dl_b = &d->update.dl_b;
}
/*
* "max" groups are always schedulable, as they defer their access
* control to their first non-max parent.
*/
- if (runtime == RUNTIME_INF)
+ if (dl_b->dl_runtime == RUNTIME_INF)
return 0;
/*
* Cannot have more runtime than the period.
*/
- if (runtime > period)
+ if (dl_b->dl_runtime > dl_b->dl_period)
return -EINVAL;
/*
* Ensure we don't starve existing RT tasks if runtime turns zero.
*/
- if (dl_bandwidth_enabled() && !runtime && tg != &root_task_group &&
+ if (dl_bandwidth_enabled() && !dl_b->dl_runtime && tg != &root_task_group &&
tg_subtree_has_rt_tasks(tg))
return -EBUSY;
- total = to_ratio(period, runtime);
+ total = to_ratio(dl_b->dl_period, dl_b->dl_runtime);
/*
* Nobody can have more than the global setting allows.
@@ -2542,16 +2569,18 @@ static int __tg_rt_schedulable(struct task_group *tg, void *data)
* The sum of our children's runtime, plus our own bw, should not
* exceed our own max.
*/
- total = runtime;
- sum = tg_compute_children_runtime(tg, period, &d->update);
- if (sum > total)
- return -EINVAL;
+ tg_compute_children_runtime(tg, &d->update, cpu_possible_mask, d->children_runtime);
+ for_each_possible_cpu(cpu) {
+ runtime = tg_cpu_runtime(dl_b, cpu);
+ if (d->children_runtime[cpu] > runtime)
+ return -EINVAL;
- /*
- * Compute remaining runtime
- */
- if (tg == d->update.tg)
- d->rt_runtime_remainder = total - sum;
+ /*
+ * Compute remaining runtime
+ */
+ if (tg == d->update.tg)
+ d->rt_runtime_remainder[cpu] = runtime - d->children_runtime[cpu];
+ }
return 0;
}
@@ -2559,15 +2588,25 @@ static int __tg_rt_schedulable(struct task_group *tg, void *data)
static int tg_rt_schedulable(struct tg_update_data *data, u64 *remainder_runtime)
{
int err;
+ u64 *children_runtime __free(kfree) = NULL;
+ u64 *rt_runtime_remainder __free(kfree) = NULL;
struct rt_schedulable_data d = {
- .update = (struct tg_update_data) {
- .tg = data->tg,
- .rt_period = data->rt_period,
- .rt_runtime = data->rt_runtime,
- },
- .rt_runtime_remainder = 0,
+ .update = *data,
+ .children_runtime = NULL,
+ .rt_runtime_remainder = NULL,
};
+ children_runtime = kcalloc(nr_cpu_ids, sizeof(u64), GFP_NOWAIT);
+ if (!children_runtime)
+ return -ENOMEM;
+
+ rt_runtime_remainder = kcalloc(nr_cpu_ids, sizeof(u64), GFP_NOWAIT);
+ if (!rt_runtime_remainder)
+ return -ENOMEM;
+
+ d.children_runtime = children_runtime;
+ d.rt_runtime_remainder = rt_runtime_remainder;
+
/*
* Walk the cgroup tree and check schedulability constraints.
*/
@@ -2576,7 +2615,7 @@ static int tg_rt_schedulable(struct tg_update_data *data, u64 *remainder_runtime
if (err)
return err;
- *remainder_runtime = d.rt_runtime_remainder;
+ memcpy(remainder_runtime, rt_runtime_remainder, array_size(nr_cpu_ids, sizeof(u64)));
return 0;
}
@@ -2626,16 +2665,25 @@ int tg_rt_bandwidth(struct task_group *tg,
return 0;
}
-int tg_rt_internal_bandwidth(struct task_group *tg,
+int tg_rt_internal_bandwidth(struct task_group *tg, int cpu,
u64 *rt_period_us, u64 *rt_runtime_us)
{
const struct dl_bandwidth *dl_b;
+ cpumask_var_t mask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+
+ if (!alloc_cpumask_var(&mask, GFP_NOWAIT))
+ return 0;
+
+ cpuset_effective_cpus(tg->css.cgroup, mask);
guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
dl_b = dl_bandwidth_read(tg);
- *rt_runtime_us = dl_b->dl_internal_runtime;
- *rt_runtime_us = DIV64_U64_ROUND_CLOSEST(*rt_runtime_us, NSEC_PER_USEC);
+ *rt_runtime_us = -1;
+ if (dl_b->dl_runtime != RUNTIME_INF || !cpumask_test_cpu(cpu, mask)) {
+ *rt_runtime_us = tg->dl_se[cpu]->dl_runtime;
+ *rt_runtime_us = DIV64_U64_ROUND_CLOSEST(*rt_runtime_us, NSEC_PER_USEC);
+ }
*rt_period_us = div64_u64(dl_b->dl_period, NSEC_PER_USEC);
@@ -2646,11 +2694,13 @@ int tg_set_rt_bandwidth(struct task_group *tg,
u64 rt_period_us, u64 rt_runtime_us)
{
struct tg_update_data update;
+ struct dl_bandwidth *__update_dl_b __free(dl_bandwidth_free) = NULL;
struct task_group *parent_ctx;
- struct dl_bandwidth *dl_b;
+ struct dl_bandwidth *dl_b_write;
+ const struct dl_bandwidth *dl_b;
u64 rt_period, rt_runtime, old_rt_runtime;
- u64 rt_actual_runtime = 0;
- u64 runtime, children_runtime;
+ u64 *rt_actual_runtime __free(kfree) = NULL;
+ u64 period, runtime;
struct sched_attr attr;
int err, i;
@@ -2692,14 +2742,9 @@ int tg_set_rt_bandwidth(struct task_group *tg,
if (rt_runtime != RUNTIME_INF && !__checkparam_dl(&attr, true))
return -EINVAL;
- update = (struct tg_update_data) {
- .tg = tg,
- .rt_period = rt_period,
- .rt_runtime = rt_runtime,
- };
-
guard(mutex)(&rt_constraints_mutex);
- old_rt_runtime = dl_bandwidth_read(tg)->dl_runtime;
+ dl_b = dl_bandwidth_read(tg);
+ old_rt_runtime = dl_b->dl_runtime;
/*
* Disallow changing from/to "max" and a HCBS reservation if the group
@@ -2713,15 +2758,28 @@ int tg_set_rt_bandwidth(struct task_group *tg,
tg_subtree_has_rt_tasks(tg))
return -EINVAL;
- err = tg_rt_schedulable(&update, &rt_actual_runtime);
+ rt_actual_runtime = kcalloc(nr_cpu_ids, sizeof(u64), GFP_NOWAIT);
+ if (!rt_actual_runtime)
+ return -ENOMEM;
+
+ __update_dl_b = alloc_dl_bandwidth(&update.dl_b, GFP_NOWAIT);
+ if(!__update_dl_b)
+ return -ENOMEM;
+
+ init_dl_bandwidth(&update.dl_b, rt_period, rt_runtime, dl_b->active_context);
+ update.tg = tg;
+
+ cpuset_effective_cpus(tg->css.cgroup, update.dl_b.active_mask);
+
+ err = tg_rt_schedulable(&update, rt_actual_runtime);
if (err)
return err;
scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(tg)) {
- dl_b = dl_bandwidth_write(tg);
- dl_b->dl_period = rt_period;
- dl_b->dl_runtime = rt_runtime;
- dl_b->dl_internal_runtime = rt_actual_runtime;
+ dl_b_write = dl_bandwidth_write(tg);
+ dl_b_write->dl_period = rt_period;
+ dl_b_write->dl_runtime = rt_runtime;
+ cpumask_copy(dl_b_write->active_mask, update.dl_b.active_mask);
}
if (tg == &root_task_group)
@@ -2737,15 +2795,13 @@ int tg_set_rt_bandwidth(struct task_group *tg,
(rt_runtime != RUNTIME_INF && old_rt_runtime == RUNTIME_INF))
{
if (rt_runtime == RUNTIME_INF)
- tg_update_active_context(tg, dl_b->active_context, parent_ctx);
+ tg_update_active_context(tg, update.dl_b.active_context, parent_ctx);
else
- tg_update_active_context(tg, dl_b->active_context, tg);
-
+ tg_update_active_context(tg, update.dl_b.active_context, tg);
}
- WARN_ON(rt_runtime == RUNTIME_INF && rt_actual_runtime != 0);
for_each_possible_cpu(i) {
- dl_init_tg(tg->dl_se[i], rt_actual_runtime, rt_period);
+ dl_init_tg(tg->dl_se[i], rt_actual_runtime[i], tg_cpu_period(dl_b, i));
}
/*
@@ -2754,24 +2810,49 @@ int tg_set_rt_bandwidth(struct task_group *tg,
if (parent_ctx == &root_task_group)
return 0;
- scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(parent_ctx)) {
- dl_b = dl_bandwidth_write(parent_ctx);
+ dl_b = dl_bandwidth_read(parent_ctx);
- runtime = dl_b->dl_runtime;
- children_runtime = tg_compute_children_runtime(parent_ctx, dl_b->dl_period, &update);
+ tg_compute_children_runtime(parent_ctx, &update, update.dl_b.active_mask, rt_actual_runtime);
+ for_each_cpu(i, update.dl_b.active_mask) {
+ period = tg_cpu_period(dl_b, i);
+ runtime = tg_cpu_runtime(dl_b, i) - rt_actual_runtime[i];
- rt_period = dl_b->dl_period;
- rt_actual_runtime = runtime - children_runtime;
- dl_b->dl_internal_runtime = rt_actual_runtime;
+ dl_init_tg(parent_ctx->dl_se[i], runtime, period);
}
- for_each_possible_cpu(i) {
- dl_init_tg(parent_ctx->dl_se[i], rt_actual_runtime, rt_period);
- }
+ return 0;
+}
+
+static int __tg_subtree_is_max(struct task_group *tg, void *data) {
+ const struct dl_bandwidth *dl_b;
+
+ guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
+ dl_b = dl_bandwidth_read(tg);
+ if (dl_b->dl_runtime != RUNTIME_INF)
+ return 1;
return 0;
}
+int cpuset_can_change(struct cgroup *cgroup) {
+ struct task_group *tg;
+ int err;
+
+ if (!rt_group_sched_enabled())
+ return 1;
+
+ guard(rcu)();
+ tg = css_tg(cgroup_e_css(cgroup, &cpu_cgrp_subsys));
+ if (!tg)
+ return 0;
+
+ err = walk_tg_tree_from(tg, __tg_subtree_is_max, tg_nop, NULL);
+ if (err)
+ return 0;
+
+ return 1;
+}
+
int sched_rt_can_attach(struct task_group *tg)
{
struct task_group *ctx;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 323befba5609..9410d1909729 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -316,8 +316,8 @@ struct rt_prio_array {
struct dl_bandwidth {
raw_spinlock_t dl_runtime_lock;
u64 dl_runtime;
- u64 dl_internal_runtime;
u64 dl_period;
+ cpumask_var_t active_mask;
struct task_group *active_context;
};
@@ -586,7 +586,7 @@ extern bool cfs_task_bw_constrained(struct task_struct *p);
extern int tg_rt_bandwidth(struct task_group *tg,
u64 *rt_period_us, u64 *rt_runtime_us);
-extern int tg_rt_internal_bandwidth(struct task_group *tg,
+extern int tg_rt_internal_bandwidth(struct task_group *tg, int cpu,
u64 *rt_period_us, u64 *rt_runtime_us);
extern int tg_set_rt_bandwidth(struct task_group *tg,
u64 rt_period_us, u64 rt_runtime_us);
@@ -3054,6 +3054,11 @@ extern void resched_curr(struct rq *rq);
extern void resched_curr_lazy(struct rq *rq);
extern void resched_cpu(int cpu);
+extern struct dl_bandwidth *alloc_dl_bandwidth(struct dl_bandwidth *dl_b, gfp_t gfp_flags);
+extern void free_dl_bandwidth(struct dl_bandwidth *dl_b);
+
+DEFINE_FREE(dl_bandwidth_free, struct dl_bandwidth *, if (_T) free_dl_bandwidth(_T))
+
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime,
struct task_group *active_context);
extern void init_dl_entity(struct sched_dl_entity *dl_se);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 28/29] sched/rt: Prevent CPU offline operation on active rt-cgroups.
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (26 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 27/29] sched/rt: Integrate cpuset and cpu controllers Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
2026-11-09 16:36 ` [RFC PATCH v7 29/29] sched/rt: Introduce multi-cpu support Yuri Andriaccio
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Introduce tg_can_offline_cpu and prevent CPU offlining if any rt-cgroup has
requested bandwidth on the offlining core.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 3 +++
kernel/sched/rt.c | 27 +++++++++++++++++++++++++++
kernel/sched/sched.h | 1 +
3 files changed, 31 insertions(+)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 59bd9599c509..4321be11c6c7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8717,6 +8717,9 @@ int sched_cpu_deactivate(unsigned int cpu)
struct rq *rq = cpu_rq(cpu);
int ret;
+ if (!tg_can_offline_cpu(cpu))
+ return -EBUSY;
+
ret = dl_bw_deactivate(cpu);
if (ret)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 37e4b24183ab..e5f05aeabd5c 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2853,6 +2853,33 @@ int cpuset_can_change(struct cgroup *cgroup) {
return 1;
}
+static int __tg_can_offline_cpu(struct task_group *tg, void *data) {
+ const struct dl_bandwidth *dl_b;
+ int *d = data;
+ int cpu = *d;
+
+ if (tg == &root_task_group)
+ return 0;
+
+ guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
+ dl_b = dl_bandwidth_read(tg);
+ if (dl_b->dl_runtime == RUNTIME_INF)
+ return 0;
+
+ return cpumask_test_cpu(cpu, dl_b->active_mask);
+}
+
+int tg_can_offline_cpu(int cpu) {
+ if (!rt_group_sched_enabled())
+ return 1;
+
+ guard(rcu)();
+ if (walk_tg_tree(__tg_can_offline_cpu, tg_nop, &cpu))
+ return 0;
+
+ return 1;
+}
+
int sched_rt_can_attach(struct task_group *tg)
{
struct task_group *ctx;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9410d1909729..a6aae4375a31 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -590,6 +590,7 @@ extern int tg_rt_internal_bandwidth(struct task_group *tg, int cpu,
u64 *rt_period_us, u64 *rt_runtime_us);
extern int tg_set_rt_bandwidth(struct task_group *tg,
u64 rt_period_us, u64 rt_runtime_us);
+extern int tg_can_offline_cpu(int cpu);
extern int sched_rt_can_attach(struct task_group *tg);
extern struct task_group *sched_create_group(struct task_group *parent);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread* [RFC PATCH v7 29/29] sched/rt: Introduce multi-cpu support
2026-11-09 16:35 [RFC PATCH v7 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
` (27 preceding siblings ...)
2026-11-09 16:36 ` [RFC PATCH v7 28/29] sched/rt: Prevent CPU offline operation on active rt-cgroups Yuri Andriaccio
@ 2026-11-09 16:36 ` Yuri Andriaccio
28 siblings, 0 replies; 30+ messages in thread
From: Yuri Andriaccio @ 2026-11-09 16:36 UTC (permalink / raw)
To: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
Valentin Schneider, K Prateek Nayak, Tejun Heo, Johannes Weiner,
Michal Koutný
Cc: cgroups, linux-kernel, Luca Abeni, Yuri Andriaccio
Introduce per-cpu overrides to server's runtime and period: it is now possible
to override a subset of cpus HCBS setup by writing to the cpu.rt.max file.
The new syntax is as follows:
max [<period_us>] - Set whole cgroup to `max`.
Remove any overrides.
default runtime=max - As above.
<runtime_us> <period_us> - Set default runtime/period.
Keeps overrides.
default runtime=<runtime_us> period=<period_us> - As above.
<cpumask> default - Remove override for the
given cpumask. Resets to
the default runtime and
period.
<cpumask> runtime=<runtime_us> period=<period_us> - Set override for the
given cpumask.
To keep consistency between the cpumask and the overrides, it is not possible
to override a cpu to zero runtime. Shrink the cpuset controller cpumask
instead.
If the cgroup defaults to zero runtime, defaulting an override will reset the
cpus to zero runtime. A zero runtime cgroup which has all of its cpus
overriden to non-zero can be scheduled onto (but for consistency, if not all
cpus are overriden, running tasks is disallowed).
Details:
- update struct dl_bandwidth to store per-cpu runtime and period overrides.
- introduce tg_set_rt_bandwidth_override to set a cpuset's override.
- update schedulability/admission checks.
- update cpu.rt.max interface to support per-cpu overrides.
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
kernel/sched/core.c | 89 ++++++++++++++-
kernel/sched/deadline.c | 23 ++++
kernel/sched/rt.c | 237 ++++++++++++++++++++++++++++++++++++----
kernel/sched/sched.h | 7 ++
4 files changed, 331 insertions(+), 25 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4321be11c6c7..bf57da4f59d9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10494,9 +10494,20 @@ static int cpu_rt_max_show(struct seq_file *sf, void *v)
{
struct task_group *tg = css_tg(seq_css(sf));
u64 period_us, runtime_us;
+ int cpu;
tg_rt_bandwidth(tg, &period_us, &runtime_us);
cpu_period_quota_print(sf, period_us, runtime_us);
+
+ if (tg == &root_task_group)
+ return 0;
+
+ for_each_possible_cpu(cpu) {
+ tg_rt_single_bandwidth(tg, cpu, &period_us, &runtime_us);
+ if (runtime_us != RUNTIME_INF)
+ cpu_period_quota_single_print(sf, cpu, period_us, runtime_us);
+ }
+
return 0;
}
@@ -10510,19 +10521,91 @@ static int cpu_rt_internal_show(struct seq_file *sf, void *v)
tg_rt_internal_bandwidth(tg, cpu, &period_us, &runtime_us);
cpu_period_quota_single_print(sf, cpu, period_us, runtime_us);
}
+
return 0;
}
+static int __cpu_rt_max_parse(char *buf, struct cpumask *mask,
+ u64 *period_us_p, u64 *quota_us_p)
+{
+ char *tok, *runtime_key, *period_key;
+
+ tok = strsep(&buf, " ");
+ if (!tok)
+ return -EINVAL;
+
+ if (strncmp(tok, "max", sizeof("max")) == 0) {
+ *quota_us_p = RUNTIME_INF;
+ return 0;
+ }
+
+ if (strncmp(tok, "default", sizeof("default")) == 0) {
+ if (strncmp(buf, "runtime=max", sizeof("runtime=max")) == 0) {
+ *quota_us_p = RUNTIME_INF;
+ *period_us_p = 0;
+ return 0;
+ }
+
+ if (!buf)
+ return -EINVAL;
+
+ goto parse_keys;
+ }
+
+ if (buf && sscanf(buf, "%llu", period_us_p) == 0) {
+ if (cpulist_parse(tok, mask) != 0)
+ return -EINVAL;
+
+ goto parse_cpumask;
+ }
+
+ if (sscanf(tok, "%llu", quota_us_p) < 1)
+ return -EINVAL;
+
+ return 0;
+
+parse_cpumask:
+ if (strncmp(buf, "default", sizeof("default")) == 0) {
+ *quota_us_p = RUNTIME_INF;
+ *period_us_p = RUNTIME_INF;
+ return 0;
+ }
+
+parse_keys:
+ runtime_key = strstr(buf, "runtime=");
+ period_key = strstr(buf, "period=");
+
+ if (runtime_key &&
+ period_key &&
+ sscanf(runtime_key, "runtime=%llu", quota_us_p) == 1 &&
+ sscanf(period_key, "period=%llu", period_us_p) == 1)
+ return 0;
+
+ return -EINVAL;
+}
+
static ssize_t cpu_rt_max_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct task_group *tg = css_tg(of_css(of));
- u64 period_us = 0, runtime_us;
+ cpumask_var_t mask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+ u64 period_us, runtime_us;
int ret;
- ret = cpu_period_quota_parse(buf, &period_us, &runtime_us);
- if (!ret)
+ if (!alloc_cpumask_var(&mask, GFP_NOWAIT))
+ return -ENOMEM;
+
+ cpumask_clear(mask);
+
+ ret = __cpu_rt_max_parse(buf, mask, &period_us, &runtime_us);
+ if (ret)
+ return ret;
+
+ if (cpumask_empty(mask))
ret = tg_set_rt_bandwidth(tg, period_us, runtime_us);
+ else
+ ret = tg_set_rt_bandwidth_override(tg, mask, period_us, runtime_us);
+
return ret ?: nbytes;
}
#endif /* CONFIG_RT_GROUP_SCHED */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0282258db3e9..392e48b63698 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -593,24 +593,47 @@ static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq
static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
struct dl_bandwidth *alloc_dl_bandwidth(struct dl_bandwidth *dl_b, gfp_t gfp_flags) {
+ u64 *period_overrides __free(kfree) = NULL;
+ u64 *runtime_overrides __free(kfree) = NULL;
+
+ period_overrides = kcalloc(nr_cpu_ids, sizeof(u64), gfp_flags);
+ if (!period_overrides)
+ return NULL;
+
+ runtime_overrides = kcalloc(nr_cpu_ids, sizeof(u64), gfp_flags);
+ if (!runtime_overrides)
+ return NULL;
+
if (!alloc_cpumask_var(&dl_b->active_mask, gfp_flags))
return NULL;
+ dl_b->dl_period_overrides = no_free_ptr(period_overrides);
+ dl_b->dl_runtime_overrides = no_free_ptr(runtime_overrides);
+
return dl_b;
}
void free_dl_bandwidth(struct dl_bandwidth *dl_b) {
free_cpumask_var(dl_b->active_mask);
+ kfree(dl_b->dl_period_overrides);
+ kfree(dl_b->dl_runtime_overrides);
}
void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime,
struct task_group *active_context)
{
+ int cpu;
+
raw_spin_lock_init(&dl_b->dl_runtime_lock);
dl_b->dl_period = period;
dl_b->dl_runtime = runtime;
dl_b->active_context = active_context;
cpumask_clear(dl_b->active_mask);
+
+ for_each_possible_cpu(cpu) {
+ dl_b->dl_period_overrides[cpu] = RUNTIME_INF;
+ dl_b->dl_runtime_overrides[cpu] = RUNTIME_INF;
+ }
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e5f05aeabd5c..8702d0e0c4e3 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2428,11 +2428,25 @@ static int tg_subtree_has_rt_tasks(struct task_group *tg) {
}
static inline u64 tg_cpu_period(const struct dl_bandwidth *dl_b, int cpu) {
- return cpumask_test_cpu(cpu, dl_b->active_mask) ? dl_b->dl_period : 0;
+ u64 period;
+
+ if (dl_b->dl_period_overrides[cpu] == RUNTIME_INF)
+ period = dl_b->dl_period;
+ else
+ period = dl_b->dl_period_overrides[cpu];
+
+ return cpumask_test_cpu(cpu, dl_b->active_mask) ? period : 0;
}
static inline u64 tg_cpu_runtime(const struct dl_bandwidth *dl_b, int cpu) {
- return cpumask_test_cpu(cpu, dl_b->active_mask) ? dl_b->dl_runtime : 0;
+ u64 runtime;
+
+ if (dl_b->dl_runtime_overrides[cpu] == RUNTIME_INF)
+ runtime = dl_b->dl_runtime;
+ else
+ runtime = dl_b->dl_runtime_overrides[cpu];
+
+ return cpumask_test_cpu(cpu, dl_b->active_mask) ? runtime : 0;
}
struct tg_update_data {
@@ -2542,8 +2556,9 @@ static int __tg_rt_schedulable(struct task_group *tg, void *data)
/*
* Cannot have more runtime than the period.
*/
- if (dl_b->dl_runtime > dl_b->dl_period)
- return -EINVAL;
+ for_each_possible_cpu(cpu)
+ if (tg_cpu_runtime(dl_b, cpu) > tg_cpu_period(dl_b, cpu))
+ return -EINVAL;
/*
* Ensure we don't starve existing RT tasks if runtime turns zero.
@@ -2551,16 +2566,21 @@ static int __tg_rt_schedulable(struct task_group *tg, void *data)
if (dl_bandwidth_enabled() && !dl_b->dl_runtime && tg != &root_task_group &&
tg_subtree_has_rt_tasks(tg))
return -EBUSY;
-
- total = to_ratio(dl_b->dl_period, dl_b->dl_runtime);
-
/*
* Nobody can have more than the global setting allows.
*/
- if (total > to_ratio(global_rt_period(), global_rt_runtime()))
- return -EINVAL;
+ for_each_possible_cpu(cpu) {
+ total = to_ratio(tg_cpu_period(dl_b, cpu), tg_cpu_runtime(dl_b, cpu));
+ if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+ return -EINVAL;
+ }
+ /*
+ * By definition the root_task_group has the same settings for all cpus,
+ * and the overrides are always disabled.
+ */
if (tg == &root_task_group) {
+ total = to_ratio(dl_b->dl_period, dl_b->dl_runtime);
if (!dl_check_tg(total))
return -EBUSY;
}
@@ -2665,6 +2685,34 @@ int tg_rt_bandwidth(struct task_group *tg,
return 0;
}
+int tg_rt_single_bandwidth(struct task_group *tg, int cpu,
+ u64 *rt_period_us, u64 *rt_runtime_us)
+{
+ const struct dl_bandwidth *dl_b;
+ cpumask_var_t mask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
+
+ if (!alloc_cpumask_var(&mask, GFP_NOWAIT))
+ return 0;
+
+ cpuset_effective_cpus(tg->css.cgroup, mask);
+
+ guard(raw_spinlock_irq)(dl_bw_lock_of_tg(tg));
+ dl_b = dl_bandwidth_read(tg);
+
+ if (dl_b->dl_runtime_overrides[cpu] == RUNTIME_INF) {
+ *rt_runtime_us = RUNTIME_INF;
+ return 0;
+ }
+
+ *rt_runtime_us = tg_cpu_runtime(dl_b, cpu);
+ *rt_runtime_us = div64_u64(*rt_runtime_us, NSEC_PER_USEC);
+
+ *rt_period_us = tg_cpu_period(dl_b, cpu);
+ *rt_period_us = div64_u64(*rt_period_us, NSEC_PER_USEC);
+
+ return 0;
+}
+
int tg_rt_internal_bandwidth(struct task_group *tg, int cpu,
u64 *rt_period_us, u64 *rt_runtime_us)
{
@@ -2680,16 +2728,40 @@ int tg_rt_internal_bandwidth(struct task_group *tg, int cpu,
dl_b = dl_bandwidth_read(tg);
*rt_runtime_us = -1;
+ *rt_period_us = 0;
if (dl_b->dl_runtime != RUNTIME_INF || !cpumask_test_cpu(cpu, mask)) {
*rt_runtime_us = tg->dl_se[cpu]->dl_runtime;
*rt_runtime_us = DIV64_U64_ROUND_CLOSEST(*rt_runtime_us, NSEC_PER_USEC);
- }
- *rt_period_us = div64_u64(dl_b->dl_period, NSEC_PER_USEC);
+ *rt_period_us = div64_u64(tg->dl_se[cpu]->dl_period, NSEC_PER_USEC);
+ }
return 0;
}
+static void __update_parent_runtime(struct tg_update_data *update,
+ struct task_group *parent_ctx,
+ const struct cpumask *mask,
+ u64 *children_runtime)
+{
+ const struct dl_bandwidth *dl_b;
+ u64 period, runtime;
+ int cpu;
+
+ if (parent_ctx == &root_task_group)
+ return;
+
+ dl_b = dl_bandwidth_read(parent_ctx);
+
+ tg_compute_children_runtime(parent_ctx, update, mask, children_runtime);
+ for_each_cpu(cpu, mask) {
+ period = tg_cpu_period(dl_b, cpu);
+ runtime = tg_cpu_runtime(dl_b, cpu) - children_runtime[cpu];
+
+ dl_init_tg(parent_ctx->dl_se[cpu], runtime, period);
+ }
+}
+
int tg_set_rt_bandwidth(struct task_group *tg,
u64 rt_period_us, u64 rt_runtime_us)
{
@@ -2700,7 +2772,6 @@ int tg_set_rt_bandwidth(struct task_group *tg,
const struct dl_bandwidth *dl_b;
u64 rt_period, rt_runtime, old_rt_runtime;
u64 *rt_actual_runtime __free(kfree) = NULL;
- u64 period, runtime;
struct sched_attr attr;
int err, i;
@@ -2768,6 +2839,10 @@ int tg_set_rt_bandwidth(struct task_group *tg,
init_dl_bandwidth(&update.dl_b, rt_period, rt_runtime, dl_b->active_context);
update.tg = tg;
+ for_each_possible_cpu(i) {
+ update.dl_b.dl_period_overrides[i] = dl_b->dl_period_overrides[i];
+ update.dl_b.dl_runtime_overrides[i] = dl_b->dl_runtime_overrides[i];
+ }
cpuset_effective_cpus(tg->css.cgroup, update.dl_b.active_mask);
@@ -2807,19 +2882,128 @@ int tg_set_rt_bandwidth(struct task_group *tg,
/*
* Update the dl_servers of the parent's active context
*/
- if (parent_ctx == &root_task_group)
- return 0;
+ __update_parent_runtime(&update, parent_ctx, update.dl_b.active_mask, rt_actual_runtime);
- dl_b = dl_bandwidth_read(parent_ctx);
+ return 0;
+}
- tg_compute_children_runtime(parent_ctx, &update, update.dl_b.active_mask, rt_actual_runtime);
- for_each_cpu(i, update.dl_b.active_mask) {
- period = tg_cpu_period(dl_b, i);
- runtime = tg_cpu_runtime(dl_b, i) - rt_actual_runtime[i];
+int tg_set_rt_bandwidth_override(struct task_group *tg,
+ const struct cpumask *rt_mask,
+ u64 rt_period_us,u64 rt_runtime_us)
+{
+ struct tg_update_data update;
+ struct dl_bandwidth *__update_dl_b __free(dl_bandwidth_free) = NULL;
+ struct task_group *parent_ctx;
+ struct dl_bandwidth *dl_b_write;
+ const struct dl_bandwidth *dl_b;
+ u64 rt_period, rt_runtime;
+ u64 *rt_actual_runtime __free(kfree) = NULL;
+ struct sched_attr attr;
+ int err, i;
- dl_init_tg(parent_ctx->dl_se[i], runtime, period);
+ if (rt_runtime_us == RUNTIME_INF)
+ rt_runtime = RUNTIME_INF;
+ else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+ else
+ rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
+
+ if (rt_runtime == RUNTIME_INF)
+ rt_period = RUNTIME_INF;
+ else if ((u64)rt_period_us > U64_MAX / NSEC_PER_USEC)
+ return -EINVAL;
+ else
+ rt_period = (u64)rt_period_us * NSEC_PER_USEC;
+
+ /*
+ * The root_task_group bandwidth settings are only used to reserve bw
+ * for HCBS cgroups; changing a subset of cpus has no meaning there.
+ */
+ if (tg == &root_task_group)
+ return -EINVAL;
+
+ /*
+ * Bound quota to defend quota against overflow during bandwidth shift.
+ */
+ if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
+ return -EINVAL;
+
+ /*
+ * Check if the runtime and period min and max values are admissible.
+ */
+ attr = (struct sched_attr){
+ .sched_flags = 0,
+ .sched_runtime = rt_runtime,
+ .sched_deadline = rt_period,
+ .sched_period = rt_period,
+ };
+
+ if (rt_runtime != RUNTIME_INF && !__checkparam_dl(&attr, false))
+ return -EINVAL;
+
+ guard(mutex)(&rt_constraints_mutex);
+ dl_b = dl_bandwidth_read(tg);
+
+ guard(sched_rt_handler)();
+ guard(sched_domains)();
+ guard(rcu)();
+ /*
+ * Disallow resetting overrides to active default-zero cgroups
+ */
+ if (rt_runtime == RUNTIME_INF && dl_b->dl_runtime == 0 &&
+ tg_subtree_has_rt_tasks(tg))
+ return -EINVAL;
+
+ rt_actual_runtime = kcalloc(nr_cpu_ids, sizeof(u64), GFP_NOWAIT);
+ if (!rt_actual_runtime)
+ return -ENOMEM;
+
+ __update_dl_b = alloc_dl_bandwidth(&update.dl_b, GFP_NOWAIT);
+ if(!__update_dl_b)
+ return -ENOMEM;
+
+ init_dl_bandwidth(&update.dl_b, dl_b->dl_period, dl_b->dl_runtime, dl_bandwidth_read(tg)->active_context);
+
+ update.tg = tg;
+ cpuset_effective_cpus(tg->css.cgroup, update.dl_b.active_mask);
+
+ /* Check if the input mask is a subset of the cpuset mask */
+ if (!cpumask_subset(rt_mask, update.dl_b.active_mask))
+ return -EINVAL;
+
+ for_each_cpu_andnot(i, update.dl_b.active_mask, rt_mask) {
+ update.dl_b.dl_period_overrides[i] = dl_b->dl_period_overrides[i];
+ update.dl_b.dl_runtime_overrides[i] = dl_b->dl_runtime_overrides[i];
+ }
+
+ for_each_cpu_and(i, update.dl_b.active_mask, rt_mask) {
+ update.dl_b.dl_period_overrides[i] = rt_period;
+ update.dl_b.dl_runtime_overrides[i] = rt_runtime;
}
+ err = tg_rt_schedulable(&update, rt_actual_runtime);
+ if (err)
+ return err;
+
+ scoped_guard(raw_spinlock_irq, dl_bw_lock_of_tg(tg)) {
+ dl_b_write = dl_bandwidth_write(tg);
+ for_each_cpu(i, rt_mask) {
+ dl_b_write->dl_period_overrides[i] = rt_period;
+ dl_b_write->dl_runtime_overrides[i] = rt_runtime;
+ }
+ }
+
+ parent_ctx = dl_bandwidth_read(tg->parent)->active_context;
+
+ for_each_cpu(i, rt_mask) {
+ dl_init_tg(tg->dl_se[i], rt_actual_runtime[i], tg_cpu_period(dl_b, i));
+ }
+
+ /*
+ * Update the dl_servers of the parent's active context
+ */
+ __update_parent_runtime(&update, parent_ctx, rt_mask, rt_actual_runtime);
+
return 0;
}
@@ -2883,6 +3067,8 @@ int tg_can_offline_cpu(int cpu) {
int sched_rt_can_attach(struct task_group *tg)
{
struct task_group *ctx;
+ const struct dl_bandwidth *dl_b;
+ int cpu;
/* If rt group sched is disabled, tasks are always run in the root rq */
if (!rt_group_sched_enabled())
@@ -2897,8 +3083,15 @@ int sched_rt_can_attach(struct task_group *tg)
/* Don't accept real-time tasks when there is no way for them to run */
scoped_guard(raw_spinlock_irqsave, dl_bw_lock_of_tg(ctx)) {
- if (dl_bandwidth_read(ctx)->dl_runtime == 0)
- return 0;
+ dl_b = dl_bandwidth_read(ctx);
+
+ if (dl_b->dl_runtime)
+ return 1;
+
+ /* Allow default-zero but fully overridden cgroups to be attached to */
+ for_each_cpu(cpu, dl_b->active_mask)
+ if (tg_cpu_runtime(dl_b, cpu) == 0)
+ return 0;
}
return 1;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a6aae4375a31..5ea5fd420305 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -317,6 +317,8 @@ struct dl_bandwidth {
raw_spinlock_t dl_runtime_lock;
u64 dl_runtime;
u64 dl_period;
+ u64 *dl_runtime_overrides;
+ u64 *dl_period_overrides;
cpumask_var_t active_mask;
struct task_group *active_context;
};
@@ -586,10 +588,15 @@ extern bool cfs_task_bw_constrained(struct task_struct *p);
extern int tg_rt_bandwidth(struct task_group *tg,
u64 *rt_period_us, u64 *rt_runtime_us);
+extern int tg_rt_single_bandwidth(struct task_group *tg, int cpu,
+ u64 *rt_period_us, u64 *rt_runtime_us);
extern int tg_rt_internal_bandwidth(struct task_group *tg, int cpu,
u64 *rt_period_us, u64 *rt_runtime_us);
extern int tg_set_rt_bandwidth(struct task_group *tg,
u64 rt_period_us, u64 rt_runtime_us);
+extern int tg_set_rt_bandwidth_override(struct task_group *tg,
+ const struct cpumask *rt_mask,
+ u64 rt_period_us, u64 rt_runtime_us);
extern int tg_can_offline_cpu(int cpu);
extern int sched_rt_can_attach(struct task_group *tg);
--
2.56.0
^ permalink raw reply [flat|nested] 30+ messages in thread