[PATCH v6 00/14] Add a deadline server for sched_ext tasks

[PATCH v6 00/14] Add a deadline server for sched_ext tasks

[Joel Fernandes]

sched_ext tasks currently are starved by RT hoggers especially since RT
throttling was replaced by deadline servers to boost only CFS tasks. Several
users in the community have reported issues with RT stalling sched_ext tasks.
Add a sched_ext deadline server as well so that sched_ext tasks are also
boosted and do not suffer starvation.

2 kselftest are provided to verify the starvation fixes and bandwidth
allocation is looking correct.

v5->v6: mostly no changes versus v5.
- Added Acks to few patches.
- Fixes to few nits suggested by Tejun. 

v4->v5:
-  Added a kselftest (total_bw) to sched_ext to verify bandwidth values
   from debugfs.
- Address comment from Andrea about redundant rq clock invalidation.

v3->v4:
 - Fixed issues with hotplugged CPUs having their DL server bandwidth
   altered due to loading SCX.
 - Fixed other issues.
 - Rebased on Linus master.
 - All sched_ext kselftests reliably pass now, also verified that
   the total_bw in debugfs (CONFIG_SCHED_DEBUG) is conserved with
   these patches.

v2->v3:
 - Removed code duplication in debugfs. Made ext interface separate.
 - Fixed issue where rq_lock_irqsave was not used in the relinquish patch.
 - Fixed running bw accounting issue in dl_server_remove_params.

Link to v1: https://lore.kernel.org/all/20250315022158.2354454-1-joelagnelf@nvidia.com/
Link to v2: https://lore.kernel.org/all/20250602180110.816225-1-joelagnelf@nvidia.com/
Link to v3: https://lore.kernel.org/all/20250613051734.4023260-1-joelagnelf@nvidia.com/
Link to v4: https://lore.kernel.org/all/20250617200523.1261231-1-joelagnelf@nvidia.com/
Link to v5: https://lore.kernel.org/all/20250620203234.3349930-1-joelagnelf@nvidia.com/

Andrea Righi (2):
  sched/deadline: Add support to remove DLserver's bandwidth
    contribution
  selftests/sched_ext: Add test for sched_ext dl_server

Joel Fernandes (12):
  sched/debug: Fix updating of ppos on server write ops
  sched/debug: Stop and start server based on if it was active
  sched/deadline: Clear the defer params
  sched/deadline: Prevent setting server as started if params couldn't
    be applied
  sched/deadline: Return EBUSY if dl_bw_cpus is zero
  sched: Add support to pick functions to take rf
  sched: Add a server arg to dl_server_update_idle_time()
  sched/ext: Add a DL server for sched_ext tasks
  sched/debug: Add support to change sched_ext server params
  sched/ext: Relinquish DL server reservations when not needed
  sched/deadline: Fix DL server crash in inactive_timer callback
  selftests/sched_ext: Add test for DL server total_bw consistency

 include/linux/sched.h                         |   2 +-
 kernel/sched/core.c                           |  19 +-
 kernel/sched/deadline.c                       |  86 ++++--
 kernel/sched/debug.c                          | 165 ++++++++--
 kernel/sched/ext.c                            | 120 +++++++-
 kernel/sched/fair.c                           |  15 +-
 kernel/sched/idle.c                           |   4 +-
 kernel/sched/rt.c                             |   2 +-
 kernel/sched/sched.h                          |  13 +-
 kernel/sched/stop_task.c                      |   2 +-
 tools/testing/selftests/sched_ext/Makefile    |   2 +
 .../selftests/sched_ext/rt_stall.bpf.c        |  23 ++
 tools/testing/selftests/sched_ext/rt_stall.c  | 213 +++++++++++++
 tools/testing/selftests/sched_ext/total_bw.c  | 286 ++++++++++++++++++
 14 files changed, 869 insertions(+), 83 deletions(-)
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c
 create mode 100644 tools/testing/selftests/sched_ext/total_bw.c

-- 
2.34.1

[PATCH v6 01/14] sched/debug: Fix updating of ppos on server write ops

[Joel Fernandes]

Updating "ppos" on error conditions does not make much sense. The pattern
is to return the error code directly without modifying the position, or
modify the position on success and return the number of bytes written.

Since on success, the return value of apply is 0, there is no point in
modifying ppos either. Fix it by removing all this and just returning
error code or number of bytes written on success.

Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>

Acked-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/debug.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9d71baf08075..9db3fcb4bc8b 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -350,8 +350,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
 	struct rq *rq = cpu_rq(cpu);
 	u64 runtime, period;
+	int retval = 0;
 	size_t err;
-	int retval;
 	u64 value;
 
 	err = kstrtoull_from_user(ubuf, cnt, 10, &value);
@@ -387,8 +387,6 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		}
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
-		if (retval)
-			cnt = retval;
 
 		if (!runtime)
 			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
@@ -396,6 +394,9 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 
 		if (rq->cfs.h_nr_queued)
 			dl_server_start(&rq->fair_server);
+
+		if (retval < 0)
+			return retval;
 	}
 
 	*ppos += cnt;
-- 
2.34.1

[PATCH v6 02/14] sched/debug: Stop and start server based on if it was active

[Joel Fernandes]

Currently the DL server interface for applying parameters checks
CFS-internals to identify if the server is active. This is error-prone
and makes it difficult when adding new servers in the future.

Fix it, by using dl_server_active() which is also used by the DL server
code to determine if the DL server was started.

Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>

Acked-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/debug.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9db3fcb4bc8b..dcb6b2b2ff59 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -359,6 +359,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		return err;
 
 	scoped_guard (rq_lock_irqsave, rq) {
+		bool is_active;
+		
 		runtime  = rq->fair_server.dl_runtime;
 		period = rq->fair_server.dl_period;
 
@@ -381,7 +383,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			return  -EINVAL;
 		}
 
-		if (rq->cfs.h_nr_queued) {
+		is_active = dl_server_active(&rq->fair_server);
+		if (is_active) {
 			update_rq_clock(rq);
 			dl_server_stop(&rq->fair_server);
 		}
@@ -392,7 +395,7 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
 					cpu_of(rq));
 
-		if (rq->cfs.h_nr_queued)
+		if (is_active)
 			dl_server_start(&rq->fair_server);
 
 		if (retval < 0)
-- 
2.34.1

[PATCH v6 03/14] sched/deadline: Clear the defer params

[Joel Fernandes]

The defer params were not cleared in __dl_clear_params. Clear them.

Without this is some of my test cases are flaking and the DL timer is
not starting correctly AFAICS.

Fixes: a110a81c52a9 ("sched/deadline: Deferrable dl server")
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/deadline.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ad45a8fea245..c6da2d51667b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3431,6 +3431,9 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se)
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
 	dl_se->dl_server		= 0;
+	dl_se->dl_defer			= 0;
+	dl_se->dl_defer_running		= 0;
+	dl_se->dl_defer_armed		= 0;
 
 #ifdef CONFIG_RT_MUTEXES
 	dl_se->pi_se			= dl_se;
-- 
2.34.1

[PATCH v6 04/14] sched/deadline: Prevent setting server as started if params couldn't be applied

[Joel Fernandes]

The following call trace fails to set dl_server_apply_params() as
dl_bw_cpus() is 0 during CPU onlining.

[   11.878356] ------------[ cut here ]------------
[   11.882592]  <TASK>
[   11.882685]  enqueue_task_scx+0x190/0x280
[   11.882802]  ttwu_do_activate+0xaa/0x2a0
[   11.882925]  try_to_wake_up+0x371/0x600
[   11.883047]  cpuhp_bringup_ap+0xd6/0x170
[   11.883172]  cpuhp_invoke_callback+0x142/0x540
[   11.883327]  _cpu_up+0x15b/0x270
[   11.883450]  cpu_up+0x52/0xb0
[   11.883576]  cpu_subsys_online+0x32/0x120
[   11.883704]  online_store+0x98/0x130
[   11.883824]  kernfs_fop_write_iter+0xeb/0x170
[   11.883972]  vfs_write+0x2c7/0x430
[   11.884091]  ksys_write+0x70/0xe0
[   11.884209]  do_syscall_64+0xd6/0x250
[   11.884327]  ? clear_bhb_loop+0x40/0x90
[   11.884443]  entry_SYSCALL_64_after_hwframe+0x77/0x7f

It is too early to start the server. Simply defer the starting of the
server to the next enqueue if dl_server_apply_params() returns an error.
In any case, we should not pretend like the server started and it does
seem to mess up with the sched_ext CPU hotplug test.

With this, the sched_ext hotplug test reliably passes.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/deadline.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index c6da2d51667b..7129b61d548b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1656,8 +1656,8 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 		u64 runtime =  50 * NSEC_PER_MSEC;
 		u64 period = 1000 * NSEC_PER_MSEC;
 
-		dl_server_apply_params(dl_se, runtime, period, 1);
-
+		if (WARN_ON_ONCE(dl_server_apply_params(dl_se, runtime, period, 1)))
+			return;
 		dl_se->dl_server = 1;
 		dl_se->dl_defer = 1;
 		setup_new_dl_entity(dl_se);
@@ -1674,7 +1674,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 
 void dl_server_stop(struct sched_dl_entity *dl_se)
 {
-	if (!dl_se->dl_runtime)
+	if (!dl_se->dl_runtime || !dl_se->dl_server_active)
 		return;
 
 	dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
-- 
2.34.1

[PATCH v6 05/14] sched/deadline: Return EBUSY if dl_bw_cpus is zero

[Joel Fernandes]

Hotplugged CPUs coming online do an enqueue but are not a part of any
root domain containing cpu_active() CPUs. So in this case, don't mess
with accounting and we can retry later. Without this patch, we see
crashes with sched_ext selftest's hotplug test due to divide by zero.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/deadline.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7129b61d548b..0e73577257ad 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1725,7 +1725,12 @@ 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))
+	/*
+	 * Hotplugged CPUs coming online do an enqueue but are not a part of any
+	 * root domain containing cpu_active() CPUs. So in this case, don't mess
+	 * with accounting and we can retry later.
+	 */
+	if (!cpus || __dl_overflow(dl_b, cap, old_bw, new_bw))
 		return -EBUSY;
 
 	if (init) {
-- 
2.34.1

Re: [PATCH v6 05/14] sched/deadline: Return EBUSY if dl_bw_cpus is zero

[Andrea Righi]

Hi Joel,

On Wed, Jul 02, 2025 at 07:29:30PM -0400, Joel Fernandes wrote:
> Hotplugged CPUs coming online do an enqueue but are not a part of any
> root domain containing cpu_active() CPUs. So in this case, don't mess
> with accounting and we can retry later. Without this patch, we see
> crashes with sched_ext selftest's hotplug test due to divide by zero.
> 
> Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
> ---
>  kernel/sched/deadline.c | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 7129b61d548b..0e73577257ad 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -1725,7 +1725,12 @@ 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))
> +	/*
> +	 * Hotplugged CPUs coming online do an enqueue but are not a part of any
> +	 * root domain containing cpu_active() CPUs. So in this case, don't mess
> +	 * with accounting and we can retry later.
> +	 */
> +	if (!cpus || __dl_overflow(dl_b, cap, old_bw, new_bw))
>  		return -EBUSY;

I can trigger the following with the hotplug sched_ext selftest:

[   61.731069] ------------[ cut here ]------------
[   61.731241] WARNING: CPU: 4 PID: 2191 at kernel/sched/deadline.c:1591 dl_server_start+0x9c/0xb0
...
[   61.731552] Sched_ext: hotplug_cbs (enabled+all), task: runnable_at=-1ms
[   61.731555] RIP: 0010:dl_server_start+0x9c/0xb0
...
[   61.732216] Call Trace:
[   61.732239]  <TASK>
[   61.732262]  enqueue_task_scx+0x2bb/0x350
[   61.732298]  enqueue_task+0x2e/0xd0
[   61.732333]  ttwu_do_activate+0xa4/0x2d0
[   61.732368]  try_to_wake_up+0x2a2/0x8e0
[   61.732406]  cpuhp_bringup_ap+0x72/0x250
[   61.732441]  ? __pfx_cpuhp_bringup_ap+0x10/0x10
[   61.732478]  cpuhp_invoke_callback+0x1b0/0x650
[   61.732523]  __cpuhp_invoke_callback_range+0x7e/0xf0
[   61.732566]  _cpu_up+0xea/0x1e0
[   61.732601]  cpu_up+0xc3/0xd0
[   61.732635]  cpu_subsys_online+0x4b/0xd0
[   61.732678]  device_online+0x49/0x80
[   61.732714]  online_store+0x9a/0xd0
[   61.732744]  ? sysfs_kf_write+0x2b/0x70
[   61.732780]  kernfs_fop_write_iter+0x137/0x200
[   61.732822]  vfs_write+0x264/0x5e0
[   61.732867]  ksys_write+0x79/0xf0
[   61.732901]  do_syscall_64+0xbb/0x370
[   61.732939]  entry_SYSCALL_64_after_hwframe+0x77/0x7f

I think we can simply ignore the !cpus case, as it's safe to skip
hotplugged CPUs that perform an enqueue when coming online, without
triggering a warning, and we can always retry applying the server params
later.

Maybe return -EAGAIN when !cpus and handle that gracefully in
dl_server_start()?

Something along these lines (on top of this patch). What do you think?

Thanks,
-Andrea

 kernel/sched/deadline.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5d5819d445fb9..78d2a3b0a4cde 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1587,9 +1587,14 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 	if (!dl_server(dl_se)) {
 		u64 runtime =  50 * NSEC_PER_MSEC;
 		u64 period = 1000 * NSEC_PER_MSEC;
+		int err;
 
-		if (WARN_ON_ONCE(dl_server_apply_params(dl_se, runtime, period, 1)))
+		err = dl_server_apply_params(dl_se, runtime, period, 1);
+		if (err == -EAGAIN)
 			return;
+
+		WARN_ON_ONCE(err);
+
 		dl_se->dl_server = 1;
 		dl_se->dl_defer = 1;
 		setup_new_dl_entity(dl_se);
@@ -1662,7 +1667,10 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio
 	 * root domain containing cpu_active() CPUs. So in this case, don't mess
 	 * with accounting and we can retry later.
 	 */
-	if (!cpus || __dl_overflow(dl_b, cap, old_bw, new_bw))
+	if (!cpus)
+		return -EAGAIN;
+
+	if (__dl_overflow(dl_b, cap, old_bw, new_bw))
 		return -EBUSY;
 
 	if (init) {

[PATCH v6 06/14] sched: Add support to pick functions to take rf

[Joel Fernandes]

Some pick functions like the internal pick_next_task_fair() already take
rf but some others dont. We need this for scx's server pick function.
Prepare for this by having pick functions accept it.

Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 include/linux/sched.h    |  2 +-
 kernel/sched/core.c      | 16 ++++++++--------
 kernel/sched/deadline.c  |  8 ++++----
 kernel/sched/ext.c       |  2 +-
 kernel/sched/fair.c      | 13 ++++++++-----
 kernel/sched/idle.c      |  2 +-
 kernel/sched/rt.c        |  2 +-
 kernel/sched/sched.h     |  7 ++++---
 kernel/sched/stop_task.c |  2 +-
 9 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..6799c14061b7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -634,7 +634,7 @@ struct sched_rt_entity {
 } __randomize_layout;
 
 typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
-typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
+typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, void *);
 
 struct sched_dl_entity {
 	struct rb_node			rb_node;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8988d38d46a3..7d856d8dcb94 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6049,7 +6049,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
-			p = pick_task_idle(rq);
+			p = pick_task_idle(rq, rf);
 			put_prev_set_next_task(rq, prev, p);
 		}
 
@@ -6061,11 +6061,11 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	for_each_active_class(class) {
 		if (class->pick_next_task) {
-			p = class->pick_next_task(rq, prev);
+			p = class->pick_next_task(rq, prev, rf);
 			if (p)
 				return p;
 		} else {
-			p = class->pick_task(rq);
+			p = class->pick_task(rq, rf);
 			if (p) {
 				put_prev_set_next_task(rq, prev, p);
 				return p;
@@ -6095,7 +6095,7 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
 	return a->core_cookie == b->core_cookie;
 }
 
-static inline struct task_struct *pick_task(struct rq *rq)
+static inline struct task_struct *pick_task(struct rq *rq, struct rq_flags *rf)
 {
 	const struct sched_class *class;
 	struct task_struct *p;
@@ -6103,7 +6103,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
 	rq->dl_server = NULL;
 
 	for_each_active_class(class) {
-		p = class->pick_task(rq);
+		p = class->pick_task(rq, rf);
 		if (p)
 			return p;
 	}
@@ -6203,7 +6203,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * and there are no cookied tasks running on siblings.
 	 */
 	if (!need_sync) {
-		next = pick_task(rq);
+		next = pick_task(rq, rf);
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
 			rq->core_dl_server = NULL;
@@ -6234,7 +6234,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		if (i != cpu && (rq_i != rq->core || !core_clock_updated))
 			update_rq_clock(rq_i);
 
-		rq_i->core_pick = p = pick_task(rq_i);
+		rq_i->core_pick = p = pick_task(rq_i, rf);
 		rq_i->core_dl_server = rq_i->dl_server;
 
 		if (!max || prio_less(max, p, fi_before))
@@ -6256,7 +6256,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			if (cookie)
 				p = sched_core_find(rq_i, cookie);
 			if (!p)
-				p = idle_sched_class.pick_task(rq_i);
+				p = idle_sched_class.pick_task(rq_i, rf);
 		}
 
 		rq_i->core_pick = p;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0e73577257ad..2889cfecf835 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2424,7 +2424,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
  * __pick_next_task_dl - Helper to pick the next -deadline task to run.
  * @rq: The runqueue to pick the next task from.
  */
-static struct task_struct *__pick_task_dl(struct rq *rq)
+static struct task_struct *__pick_task_dl(struct rq *rq, struct rq_flags *rf)
 {
 	struct sched_dl_entity *dl_se;
 	struct dl_rq *dl_rq = &rq->dl;
@@ -2438,7 +2438,7 @@ static struct task_struct *__pick_task_dl(struct rq *rq)
 	WARN_ON_ONCE(!dl_se);
 
 	if (dl_server(dl_se)) {
-		p = dl_se->server_pick_task(dl_se);
+		p = dl_se->server_pick_task(dl_se, rf);
 		if (!p) {
 			if (dl_server_active(dl_se)) {
 				dl_se->dl_yielded = 1;
@@ -2454,9 +2454,9 @@ static struct task_struct *__pick_task_dl(struct rq *rq)
 	return p;
 }
 
-static struct task_struct *pick_task_dl(struct rq *rq)
+static struct task_struct *pick_task_dl(struct rq *rq, struct rq_flags *rf)
 {
-	return __pick_task_dl(rq);
+	return __pick_task_dl(rq, rf);
 }
 
 static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_struct *next)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index b498d867ba21..f00bb75ad539 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3397,7 +3397,7 @@ static struct task_struct *first_local_task(struct rq *rq)
 					struct task_struct, scx.dsq_list.node);
 }
 
-static struct task_struct *pick_task_scx(struct rq *rq)
+static struct task_struct *pick_task_scx(struct rq *rq, struct rq_flags *rf)
 {
 	struct task_struct *prev = rq->curr;
 	struct task_struct *p;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7a14da5396fb..6bf097e39b4a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8852,7 +8852,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
 	resched_curr_lazy(rq);
 }
 
-static struct task_struct *pick_task_fair(struct rq *rq)
+static struct task_struct *pick_task_fair(struct rq *rq, struct rq_flags *rf)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
@@ -8890,7 +8890,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 	int new_tasks;
 
 again:
-	p = pick_task_fair(rq);
+	p = pick_task_fair(rq, rf);
 	if (!p)
 		goto idle;
 	se = &p->se;
@@ -8969,7 +8969,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 	return NULL;
 }
 
-static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_struct *prev)
+static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_struct *prev,
+												 struct rq_flags *rf)
 {
 	return pick_next_task_fair(rq, prev, NULL);
 }
@@ -8979,9 +8980,11 @@ static bool fair_server_has_tasks(struct sched_dl_entity *dl_se)
 	return !!dl_se->rq->cfs.nr_queued;
 }
 
-static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se)
+static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se, void *flags)
 {
-	return pick_task_fair(dl_se->rq);
+	struct rq_flags *rf = flags;
+
+	return pick_task_fair(dl_se->rq, rf);
 }
 
 void fair_server_init(struct rq *rq)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 2c85c86b455f..01e9612deefe 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -463,7 +463,7 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
 	next->se.exec_start = rq_clock_task(rq);
 }
 
-struct task_struct *pick_task_idle(struct rq *rq)
+struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf)
 {
 	scx_update_idle(rq, true, false);
 	return rq->idle;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e40422c37033..6e62fe531067 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1744,7 +1744,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 	return rt_task_of(rt_se);
 }
 
-static struct task_struct *pick_task_rt(struct rq *rq)
+static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
 {
 	struct task_struct *p;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 475bb5998295..35d7b328a9c7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2401,7 +2401,7 @@ struct sched_class {
 	void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
 
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-	struct task_struct *(*pick_task)(struct rq *rq);
+	struct task_struct *(*pick_task)(struct rq *rq, struct rq_flags *rf);
 	/*
 	 * Optional! When implemented pick_next_task() should be equivalent to:
 	 *
@@ -2411,7 +2411,8 @@ struct sched_class {
 	 *       set_next_task_first(next);
 	 *   }
 	 */
-	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev);
+	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev,
+										  struct rq_flags *rf);
 
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
@@ -2574,7 +2575,7 @@ static inline bool sched_fair_runnable(struct rq *rq)
 }
 
 extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-extern struct task_struct *pick_task_idle(struct rq *rq);
+extern struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf);
 
 #define SCA_CHECK		0x01
 #define SCA_MIGRATE_DISABLE	0x02
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 058dd42e3d9b..1c70123cb6a4 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -33,7 +33,7 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool fir
 	stop->se.exec_start = rq_clock_task(rq);
 }
 
-static struct task_struct *pick_task_stop(struct rq *rq)
+static struct task_struct *pick_task_stop(struct rq *rq, struct rq_flags *rf)
 {
 	if (!sched_stop_runnable(rq))
 		return NULL;
-- 
2.34.1

[PATCH v6 07/14] sched: Add a server arg to dl_server_update_idle_time()

[Joel Fernandes]

Since we are adding more servers, make dl_server_update_idle_time()
accept a server argument than a specific server.

Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/deadline.c | 17 +++++++++--------
 kernel/sched/fair.c     |  2 +-
 kernel/sched/idle.c     |  2 +-
 kernel/sched/sched.h    |  3 ++-
 4 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 2889cfecf835..b571d06c837c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1609,28 +1609,29 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
  * as time available for the fair server, avoiding a penalty for the
  * rt scheduler that did not consumed that time.
  */
-void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
+void dl_server_update_idle_time(struct rq *rq, struct task_struct *p,
+			       struct sched_dl_entity *rq_dl_server)
 {
 	s64 delta_exec, scaled_delta_exec;
 
-	if (!rq->fair_server.dl_defer)
+	if (!rq_dl_server->dl_defer)
 		return;
 
 	/* no need to discount more */
-	if (rq->fair_server.runtime < 0)
+	if (rq_dl_server->runtime < 0)
 		return;
 
 	delta_exec = rq_clock_task(rq) - p->se.exec_start;
 	if (delta_exec < 0)
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec);
+	scaled_delta_exec = dl_scaled_delta_exec(rq, rq_dl_server, delta_exec);
 
-	rq->fair_server.runtime -= scaled_delta_exec;
+	rq_dl_server->runtime -= scaled_delta_exec;
 
-	if (rq->fair_server.runtime < 0) {
-		rq->fair_server.dl_defer_running = 0;
-		rq->fair_server.runtime = 0;
+	if (rq_dl_server->runtime < 0) {
+		rq_dl_server->dl_defer_running = 0;
+		rq_dl_server->runtime = 0;
 	}
 
 	p->se.exec_start = rq_clock_task(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6bf097e39b4a..033f12ba7f2a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7026,7 +7026,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!rq_h_nr_queued && rq->cfs.h_nr_queued) {
 		/* Account for idle runtime */
 		if (!rq->nr_running)
-			dl_server_update_idle_time(rq, rq->curr);
+			dl_server_update_idle_time(rq, rq->curr, &rq->fair_server);
 		dl_server_start(&rq->fair_server);
 	}
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 01e9612deefe..13a3d20d35e2 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -451,7 +451,7 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
 {
-	dl_server_update_idle_time(rq, prev);
+	dl_server_update_idle_time(rq, prev, &rq->fair_server);
 	scx_update_idle(rq, false, true);
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 35d7b328a9c7..1ac2fb398982 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -386,7 +386,8 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_pick_f pick_task);
 
 extern void dl_server_update_idle_time(struct rq *rq,
-		    struct task_struct *p);
+		    struct task_struct *p,
+		    struct sched_dl_entity *rq_dl_server);
 extern void fair_server_init(struct rq *rq);
 extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
-- 
2.34.1

[PATCH v6 08/14] sched/ext: Add a DL server for sched_ext tasks

[Joel Fernandes]

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

A kselftest is also provided later to verify:

./runner -t rt_stall
===== START =====
TEST: rt_stall
DESCRIPTION: Verify that RT tasks cannot stall SCHED_EXT tasks
OUTPUT:
TAP version 13
1..1
ok 1 PASS: CFS task got more than 4.00% of runtime

Cc: Luigi De Matteis <ldematteis123@gmail.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/core.c     |  3 ++
 kernel/sched/deadline.c |  2 +-
 kernel/sched/ext.c      | 62 +++++++++++++++++++++++++++++++++++++++--
 kernel/sched/sched.h    |  2 ++
 4 files changed, 66 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7d856d8dcb94..a1ee241a63ce 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8650,6 +8650,9 @@ void __init sched_init(void)
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
 		fair_server_init(rq);
+#ifdef CONFIG_SCHED_CLASS_EXT
+		ext_server_init(rq);
+#endif
 
 #ifdef CONFIG_SCHED_CORE
 		rq->core = rq;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b571d06c837c..b7f1724c54a6 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1570,7 +1570,7 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 	 * The fair server (sole dl_server) does not account for real-time
 	 * workload because it is running fair work.
 	 */
-	if (dl_se == &rq->fair_server)
+	if (dl_se == &rq->fair_server || dl_se == &rq->ext_server)
 		return;
 
 #ifdef CONFIG_RT_GROUP_SCHED
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index f00bb75ad539..34c95100fbe5 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1909,6 +1909,9 @@ static void update_curr_scx(struct rq *rq)
 		if (!curr->scx.slice)
 			touch_core_sched(rq, curr);
 	}
+
+	if (dl_server_active(&rq->ext_server))
+		dl_server_update(&rq->ext_server, delta_exec);
 }
 
 static bool scx_dsq_priq_less(struct rb_node *node_a,
@@ -2396,6 +2399,15 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
 	if (enq_flags & SCX_ENQ_WAKEUP)
 		touch_core_sched(rq, p);
 
+	if (rq->scx.nr_running == 1) {
+		/* Account for idle runtime */
+		if (!rq->nr_running)
+			dl_server_update_idle_time(rq, rq->curr, &rq->ext_server);
+
+		/* Start dl_server if this is the first task being enqueued */
+		dl_server_start(&rq->ext_server);
+	}
+
 	do_enqueue_task(rq, p, enq_flags, sticky_cpu);
 out:
 	rq->scx.flags &= ~SCX_RQ_IN_WAKEUP;
@@ -2495,6 +2507,11 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 	sub_nr_running(rq, 1);
 
 	dispatch_dequeue(rq, p);
+
+	/* Stop the server if this was the last task */
+	if (rq->scx.nr_running == 0)
+		dl_server_stop(&rq->ext_server);
+
 	return true;
 }
 
@@ -4050,6 +4067,15 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p)
 static void switched_from_scx(struct rq *rq, struct task_struct *p)
 {
 	scx_disable_task(p);
+
+	/*
+	 * After class switch, if the DL server is still active, restart it so
+	 * that DL timers will be queued, in case SCX switched to higher class.
+	 */
+	if (dl_server_active(&rq->ext_server)) {
+		dl_server_stop(&rq->ext_server);
+		dl_server_start(&rq->ext_server);
+	}
 }
 
 static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
@@ -7310,8 +7336,8 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
  * relative scale between 0 and %SCX_CPUPERF_ONE. This determines how the
  * schedutil cpufreq governor chooses the target frequency.
  *
- * The actual performance level chosen, CPU grouping, and the overhead and
- * latency of the operations are dependent on the hardware and cpufreq driver in
+ * The actual performance level chosen, CPU grouping, and the overhead and latency
+ * of the operations are dependent on the hardware and cpufreq driver in
  * use. Consult hardware and cpufreq documentation for more information. The
  * current performance level can be monitored using scx_bpf_cpuperf_cur().
  */
@@ -7603,6 +7629,38 @@ BTF_ID_FLAGS(func, scx_bpf_now)
 BTF_ID_FLAGS(func, scx_bpf_events, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(scx_kfunc_ids_any)
 
+/*
+ * Check if ext scheduler has tasks ready to run.
+ */
+static bool ext_server_has_tasks(struct sched_dl_entity *dl_se)
+{
+	return !!dl_se->rq->scx.nr_running;
+}
+
+/*
+ * Select the next task to run from the ext scheduling class.
+ */
+static struct task_struct *ext_server_pick_task(struct sched_dl_entity *dl_se,
+						void *flags)
+{
+	struct rq_flags *rf = flags;
+
+	balance_scx(dl_se->rq, dl_se->rq->curr, rf);
+	return pick_task_scx(dl_se->rq, rf);
+}
+
+/*
+ * Initialize the ext server deadline entity.
+ */
+void ext_server_init(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se = &rq->ext_server;
+
+	init_dl_entity(dl_se);
+
+	dl_server_init(dl_se, rq, ext_server_has_tasks, ext_server_pick_task);
+}
+
 static const struct btf_kfunc_id_set scx_kfunc_set_any = {
 	.owner			= THIS_MODULE,
 	.set			= &scx_kfunc_ids_any,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1ac2fb398982..576b69cee6b1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -389,6 +389,7 @@ extern void dl_server_update_idle_time(struct rq *rq,
 		    struct task_struct *p,
 		    struct sched_dl_entity *rq_dl_server);
 extern void fair_server_init(struct rq *rq);
+extern void ext_server_init(struct rq *rq);
 extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
 		    u64 runtime, u64 period, bool init);
@@ -1137,6 +1138,7 @@ struct rq {
 #endif
 
 	struct sched_dl_entity	fair_server;
+	struct sched_dl_entity	ext_server;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this CPU: */
-- 
2.34.1

[PATCH v6 09/14] sched/debug: Add support to change sched_ext server params

[Joel Fernandes]

When a sched_ext server is loaded, tasks in CFS are converted to run in
sched_ext class. Add support to modify the ext server parameters similar
to how the fair server parameters are modified.

Re-use common code between ext and fair servers as needed.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/debug.c | 153 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 129 insertions(+), 24 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dcb6b2b2ff59..c3e0c02da07b 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -341,14 +341,16 @@ enum dl_param {
 	DL_PERIOD,
 };
 
-static unsigned long fair_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
-static unsigned long fair_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
+static unsigned long dl_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
+static unsigned long dl_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
 
-static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubuf,
-				       size_t cnt, loff_t *ppos, enum dl_param param)
+static ssize_t sched_server_write_common(struct file *filp, const char __user *ubuf,
+					 size_t cnt, loff_t *ppos, enum dl_param param,
+					 void *server)
 {
 	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
 	struct rq *rq = cpu_rq(cpu);
+	struct sched_dl_entity *dl_se = (struct sched_dl_entity *)server;
 	u64 runtime, period;
 	int retval = 0;
 	size_t err;
@@ -361,8 +363,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	scoped_guard (rq_lock_irqsave, rq) {
 		bool is_active;
 		
-		runtime  = rq->fair_server.dl_runtime;
-		period = rq->fair_server.dl_period;
+		runtime  = dl_se->dl_runtime;
+		period = dl_se->dl_period;
 
 		switch (param) {
 		case DL_RUNTIME:
@@ -378,25 +380,25 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		}
 
 		if (runtime > period ||
-		    period > fair_server_period_max ||
-		    period < fair_server_period_min) {
+		    period > dl_server_period_max ||
+		    period < dl_server_period_min) {
 			return  -EINVAL;
 		}
 
-		is_active = dl_server_active(&rq->fair_server);
+		is_active = dl_server_active(dl_se);
 		if (is_active) {
 			update_rq_clock(rq);
-			dl_server_stop(&rq->fair_server);
+			dl_server_stop(dl_se);
 		}
 
-		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
+		retval = dl_server_apply_params(dl_se, runtime, period, 0);
 
 		if (!runtime)
-			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
-					cpu_of(rq));
+			printk_deferred("%s server disabled on CPU %d, system may crash due to starvation.\n",
+					server == &rq->fair_server ? "Fair" : "Ext", cpu_of(rq));
 
 		if (is_active)
-			dl_server_start(&rq->fair_server);
+			dl_server_start(dl_se);
 
 		if (retval < 0)
 			return retval;
@@ -406,36 +408,46 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	return cnt;
 }
 
-static size_t sched_fair_server_show(struct seq_file *m, void *v, enum dl_param param)
+
+
+static size_t sched_server_show_common(struct seq_file *m, void *v, enum dl_param param,
+				       void *server)
 {
-	unsigned long cpu = (unsigned long) m->private;
-	struct rq *rq = cpu_rq(cpu);
+	struct sched_dl_entity *dl_se = (struct sched_dl_entity *)server;
 	u64 value;
 
 	switch (param) {
 	case DL_RUNTIME:
-		value = rq->fair_server.dl_runtime;
+		value = dl_se->dl_runtime;
 		break;
 	case DL_PERIOD:
-		value = rq->fair_server.dl_period;
+		value = dl_se->dl_period;
 		break;
 	}
 
 	seq_printf(m, "%llu\n", value);
 	return 0;
-
 }
 
+
+
 static ssize_t
 sched_fair_server_runtime_write(struct file *filp, const char __user *ubuf,
 				size_t cnt, loff_t *ppos)
 {
-	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_RUNTIME);
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_RUNTIME,
+					&rq->fair_server);
 }
 
 static int sched_fair_server_runtime_show(struct seq_file *m, void *v)
 {
-	return sched_fair_server_show(m, v, DL_RUNTIME);
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_RUNTIME, &rq->fair_server);
 }
 
 static int sched_fair_server_runtime_open(struct inode *inode, struct file *filp)
@@ -451,16 +463,55 @@ static const struct file_operations fair_server_runtime_fops = {
 	.release	= single_release,
 };
 
+static ssize_t
+sched_ext_server_runtime_write(struct file *filp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_RUNTIME,
+					&rq->ext_server);
+}
+
+static int sched_ext_server_runtime_show(struct seq_file *m, void *v)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_RUNTIME, &rq->ext_server);
+}
+
+static int sched_ext_server_runtime_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_ext_server_runtime_show, inode->i_private);
+}
+
+static const struct file_operations ext_server_runtime_fops = {
+	.open		= sched_ext_server_runtime_open,
+	.write		= sched_ext_server_runtime_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static ssize_t
 sched_fair_server_period_write(struct file *filp, const char __user *ubuf,
 			       size_t cnt, loff_t *ppos)
 {
-	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_PERIOD);
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_PERIOD,
+					&rq->fair_server);
 }
 
 static int sched_fair_server_period_show(struct seq_file *m, void *v)
 {
-	return sched_fair_server_show(m, v, DL_PERIOD);
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_PERIOD, &rq->fair_server);
 }
 
 static int sched_fair_server_period_open(struct inode *inode, struct file *filp)
@@ -476,6 +527,38 @@ static const struct file_operations fair_server_period_fops = {
 	.release	= single_release,
 };
 
+static ssize_t
+sched_ext_server_period_write(struct file *filp, const char __user *ubuf,
+			      size_t cnt, loff_t *ppos)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_PERIOD,
+					&rq->ext_server);
+}
+
+static int sched_ext_server_period_show(struct seq_file *m, void *v)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_PERIOD, &rq->ext_server);
+}
+
+static int sched_ext_server_period_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_ext_server_period_show, inode->i_private);
+}
+
+static const struct file_operations ext_server_period_fops = {
+	.open		= sched_ext_server_period_open,
+	.write		= sched_ext_server_period_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct dentry *debugfs_sched;
 
 static void debugfs_fair_server_init(void)
@@ -499,6 +582,27 @@ static void debugfs_fair_server_init(void)
 	}
 }
 
+static void debugfs_ext_server_init(void)
+{
+	struct dentry *d_ext;
+	unsigned long cpu;
+
+	d_ext = debugfs_create_dir("ext_server", debugfs_sched);
+	if (!d_ext)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct dentry *d_cpu;
+		char buf[32];
+
+		snprintf(buf, sizeof(buf), "cpu%lu", cpu);
+		d_cpu = debugfs_create_dir(buf, d_ext);
+
+		debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &ext_server_runtime_fops);
+		debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &ext_server_period_fops);
+	}
+}
+
 static __init int sched_init_debug(void)
 {
 	struct dentry __maybe_unused *numa;
@@ -539,6 +643,7 @@ static __init int sched_init_debug(void)
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
 	debugfs_fair_server_init();
+	debugfs_ext_server_init();
 
 	return 0;
 }
-- 
2.34.1

[PATCH v6 10/14] sched/deadline: Add support to remove DLserver's bandwidth contribution

[Joel Fernandes]

From: Andrea Righi <arighi@nvidia.com>

During switching from sched_ext to FAIR tasks and vice-versa, we need
support for removing the bandwidth contribution of either DL server. Add
support for the same.

Co-developed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 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 b7f1724c54a6..aee1aa6c74e8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1744,6 +1744,12 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio
 		dl_rq_change_utilization(rq, dl_se, new_bw);
 	}
 
+	/* Clear these so that the dl_server is reinitialized */
+	if (new_bw == 0) {
+		dl_se->dl_defer = 0;
+		dl_se->dl_server = 0;
+	}
+
 	dl_se->dl_runtime = runtime;
 	dl_se->dl_deadline = period;
 	dl_se->dl_period = period;
@@ -1757,6 +1763,31 @@ int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 perio
 	return retval;
 }
 
+/**
+ * dl_server_remove_params - Remove bandwidth reservation for a DL server
+ * @dl_se: The DL server entity to remove bandwidth for
+ *
+ * This function removes the bandwidth reservation for a DL server entity,
+ * cleaning up all bandwidth accounting and server state.
+ *
+ * Returns: 0 on success, negative error code on failure
+ */
+int dl_server_remove_params(struct sched_dl_entity *dl_se)
+{
+	if (!dl_se->dl_server)
+		return 0; /* Already disabled */
+
+	/*
+	 * First dequeue if still queued. It should not be queued since
+	 * we call this only after the last dl_server_stop().
+	 */
+	if (WARN_ON_ONCE(on_dl_rq(dl_se)))
+		dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
+
+	/* Remove bandwidth reservation */
+	return dl_server_apply_params(dl_se, 0, dl_se->dl_period, false);
+}
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 576b69cee6b1..13dc32a6346a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -393,6 +393,7 @@ extern void ext_server_init(struct rq *rq);
 extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
 		    u64 runtime, u64 period, bool init);
+extern int dl_server_remove_params(struct sched_dl_entity *dl_se);
 
 static inline bool dl_server_active(struct sched_dl_entity *dl_se)
 {
-- 
2.34.1

[PATCH v6 11/14] sched/ext: Relinquish DL server reservations when not needed

[Joel Fernandes]

I tested loading a test SCX program and verifying the bandwidth both
before and after applying the patch:

Without patch:
Before loading scx:
  .dl_bw->total_bw               : 1887408
After unloading scx:
  .dl_bw->total_bw               : 3774816

After patch:
Before loading scx:
  .dl_bw->total_bw               : 1887408
After unloading scx:
  .dl_bw->total_bw               : 1887408

Co-developed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/ext.c | 56 ++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 47 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 34c95100fbe5..6bc0ce358238 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4965,6 +4965,31 @@ static void scx_disable_workfn(struct kthread_work *work)
 
 	scx_init_task_enabled = false;
 
+	for_each_possible_cpu(cpu) {
+		struct rq *rq = cpu_rq(cpu);
+		struct rq_flags rf;
+
+		/*
+		 * Invalidate all the rq clocks to prevent getting outdated
+		 * rq clocks from a previous scx scheduler.
+		 */
+		scx_rq_clock_invalidate(rq);
+
+		/*
+		 * We are unloading the sched_ext scheduler, we do not need its
+		 * DL server bandwidth anymore, remove it for all CPUs. Whenever
+		 * the first SCX task is enqueued (when scx is re-loaded), its DL
+		 * server bandwidth will be re-initialized.
+		 */
+		rq_lock_irqsave(rq, &rf);
+		update_rq_clock(rq);
+		if (dl_server_active(&rq->ext_server))
+			dl_server_stop(&rq->ext_server);
+		dl_server_remove_params(&rq->ext_server);
+		rq_unlock_irqrestore(rq, &rf);
+	}
+
+
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		const struct sched_class *old_class = p->sched_class;
@@ -4988,15 +5013,6 @@ static void scx_disable_workfn(struct kthread_work *work)
 	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
 
-	/*
-	 * Invalidate all the rq clocks to prevent getting outdated
-	 * rq clocks from a previous scx scheduler.
-	 */
-	for_each_possible_cpu(cpu) {
-		struct rq *rq = cpu_rq(cpu);
-		scx_rq_clock_invalidate(rq);
-	}
-
 	/* no task is on scx, turn off all the switches and flush in-progress calls */
 	static_branch_disable(&__scx_enabled);
 	bitmap_zero(sch->has_op, SCX_OPI_END);
@@ -5730,6 +5746,28 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		check_class_changed(task_rq(p), p, old_class, p->prio);
 	}
 	scx_task_iter_stop(&sti);
+
+	if (scx_switching_all) {
+		for_each_possible_cpu(cpu) {
+			struct rq *rq = cpu_rq(cpu);
+			struct rq_flags rf;
+
+			/*
+			 * We are switching all fair tasks to the sched_ext scheduler,
+			 * we do not need fair server's DL bandwidth anymore, remove it
+			 * for all CPUs. Whenever the first CFS task is enqueued (when
+			 * scx is unloaded), the fair server's DL bandwidth will be
+			 * re-initialized.
+			 */
+			rq_lock_irqsave(rq, &rf);
+			update_rq_clock(rq);
+			if (dl_server_active(&rq->fair_server))
+				dl_server_stop(&rq->fair_server);
+			dl_server_remove_params(&rq->fair_server);
+			rq_unlock_irqrestore(rq, &rf);
+		}
+	}
+
 	percpu_up_write(&scx_fork_rwsem);
 
 	scx_bypass(false);
-- 
2.34.1

[PATCH v6 12/14] selftests/sched_ext: Add test for sched_ext dl_server

[Joel Fernandes]

From: Andrea Righi <arighi@nvidia.com>

Add a selftest to validate the correct behavior of the deadline server
for the ext_sched_class.

[ Joel: Replaced occurences of CFS in the test with EXT. ]

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 tools/testing/selftests/sched_ext/Makefile    |   1 +
 .../selftests/sched_ext/rt_stall.bpf.c        |  23 ++
 tools/testing/selftests/sched_ext/rt_stall.c  | 213 ++++++++++++++++++
 3 files changed, 237 insertions(+)
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 9d9d6b4c38b0..f0a8cba3a99f 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -182,6 +182,7 @@ auto-test-targets :=			\
 	select_cpu_dispatch_bad_dsq	\
 	select_cpu_dispatch_dbl_dsp	\
 	select_cpu_vtime		\
+	rt_stall			\
 	test_example			\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
new file mode 100644
index 000000000000..80086779dd1e
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that verified if RT tasks can stall SCHED_EXT tasks.
+ *
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops rt_stall_ops = {
+	.exit			= (void *)rt_stall_exit,
+	.name			= "rt_stall",
+};
diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
new file mode 100644
index 000000000000..d4cb545ebfd8
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/rt_stall.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sched.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <linux/sched.h>
+#include <signal.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "rt_stall.bpf.skel.h"
+#include "scx_test.h"
+#include "../kselftest.h"
+
+#define CORE_ID		0	/* CPU to pin tasks to */
+#define RUN_TIME        5	/* How long to run the test in seconds */
+
+/* Simple busy-wait function for test tasks */
+static void process_func(void)
+{
+	while (1) {
+		/* Busy wait */
+		for (volatile unsigned long i = 0; i < 10000000UL; i++);
+	}
+}
+
+/* Set CPU affinity to a specific core */
+static void set_affinity(int cpu)
+{
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+	if (sched_setaffinity(0, sizeof(mask), &mask) != 0) {
+		perror("sched_setaffinity");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Set task scheduling policy and priority */
+static void set_sched(int policy, int priority)
+{
+	struct sched_param param;
+
+	param.sched_priority = priority;
+	if (sched_setscheduler(0, policy, &param) != 0) {
+		perror("sched_setscheduler");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Get process runtime from /proc/<pid>/stat */
+static float get_process_runtime(int pid)
+{
+	char path[256];
+	FILE *file;
+	long utime, stime;
+	int fields;
+
+	snprintf(path, sizeof(path), "/proc/%d/stat", pid);
+	file = fopen(path, "r");
+	if (file == NULL) {
+		perror("Failed to open stat file");
+		return -1;
+	}
+
+	/* Skip the first 13 fields and read the 14th and 15th */
+	fields = fscanf(file,
+			"%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu",
+			&utime, &stime);
+	fclose(file);
+
+	if (fields != 2) {
+		fprintf(stderr, "Failed to read stat file\n");
+		return -1;
+	}
+
+	/* Calculate the total time spent in the process */
+	long total_time = utime + stime;
+	long ticks_per_second = sysconf(_SC_CLK_TCK);
+	float runtime_seconds = total_time * 1.0 / ticks_per_second;
+
+	return runtime_seconds;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct rt_stall *skel;
+
+	skel = rt_stall__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static bool sched_stress_test(void)
+{
+	float cfs_runtime, rt_runtime;
+	int cfs_pid, rt_pid;
+	float expected_min_ratio = 0.04; /* 4% */
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	/* Create and set up a EXT task */
+	cfs_pid = fork();
+	if (cfs_pid == 0) {
+		set_affinity(CORE_ID);
+		process_func();
+		exit(0);
+	} else if (cfs_pid < 0) {
+		perror("fork for EXT task");
+		ksft_exit_fail();
+	}
+
+	/* Create an RT task */
+	rt_pid = fork();
+	if (rt_pid == 0) {
+		set_affinity(CORE_ID);
+		set_sched(SCHED_FIFO, 50);
+		process_func();
+		exit(0);
+	} else if (rt_pid < 0) {
+		perror("fork for RT task");
+		ksft_exit_fail();
+	}
+
+	/* Let the processes run for the specified time */
+	sleep(RUN_TIME);
+
+	/* Get runtime for the EXT task */
+	cfs_runtime = get_process_runtime(cfs_pid);
+	if (cfs_runtime != -1)
+		ksft_print_msg("Runtime of EXT task (PID %d) is %f seconds\n", cfs_pid, cfs_runtime);
+	else
+		ksft_exit_fail_msg("Error getting runtime for EXT task (PID %d)\n", cfs_pid);
+
+	/* Get runtime for the RT task */
+	rt_runtime = get_process_runtime(rt_pid);
+	if (rt_runtime != -1)
+		ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime);
+	else
+		ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid);
+
+	/* Kill the processes */
+	kill(cfs_pid, SIGKILL);
+	kill(rt_pid, SIGKILL);
+	waitpid(cfs_pid, NULL, 0);
+	waitpid(rt_pid, NULL, 0);
+
+	/* Verify that the scx task got enough runtime */
+	float actual_ratio = cfs_runtime / (cfs_runtime + rt_runtime);
+	ksft_print_msg("EXT task got %.2f%% of total runtime\n", actual_ratio * 100);
+
+	if (actual_ratio >= expected_min_ratio) {
+		ksft_test_result_pass("PASS: EXT task got more than %.2f%% of runtime\n",
+				      expected_min_ratio * 100);
+		return true;
+	} else {
+		ksft_test_result_fail("FAIL: EXT task got less than %.2f%% of runtime\n",
+				      expected_min_ratio * 100);
+		return false;
+	}
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+	struct bpf_link *link;
+	bool res;
+
+	link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	res = sched_stress_test();
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+	bpf_link__destroy(link);
+
+	if (!res)
+		ksft_exit_fail();
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+
+	rt_stall__destroy(skel);
+}
+
+struct scx_test rt_stall = {
+	.name = "rt_stall",
+	.description = "Verify that RT tasks cannot stall SCHED_EXT tasks",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&rt_stall)
-- 
2.34.1

[PATCH v6 13/14] sched/deadline: Fix DL server crash in inactive_timer callback

[Joel Fernandes]

When sched_ext is rapidly disabled/enabled (the reload_loop selftest),
the following crash is observed. This happens because the timer handler
could not be cancelled and still fires even though the dl_server
bandwidth may have been removed via dl_server_remove_params().
hrtimer_try_to_cancel() does not guarantee timer cancellation. This
results in a NULL pointer dereference as 'p' is bogus for a dl_se.

I think this happens because the timer may be about to run, but its
softirq has not executed yet. Because of that hrtimer_try_to_cancel()
cannot prevent the timer from being canceled, however dl_server is still
set to 0 by dl_server_apply_params(). When the timer handler eventually
runs, it crashes.

[   24.771835] BUG: kernel NULL pointer dereference, address: 000000000000006c
[   24.772097] #PF: supervisor read access in kernel mode
[   24.772248] #PF: error_code(0x0000) - not-present page
[   24.772404] PGD 0 P4D 0
[   24.772499] Oops: Oops: 0000 [#1] SMP PTI
[   24.772614] CPU: 9 UID: 0 PID: 0 Comm: swapper/9 [..] #74 PREEMPT(voluntary)
[   24.772932] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), [...]
[   24.773149] Sched_ext: maximal (disabling)
[   24.773944] RSP: 0018:ffffb162c0348ee0 EFLAGS: 00010046
[   24.774100] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff88d4412f1800
[   24.774302] RDX: 0000000000000001 RSI: 0000000000000010 RDI: ffffffffac939240
[   24.774498] RBP: ffff88d47e65b940 R08: 0000000000000010 R09: 00000008bad3370a
[   24.774742] R10: 0000000000000000 R11: ffffffffa9f159d0 R12: ffff88d47e65b900
[   24.774962] R13: ffff88d47e65b960 R14: ffff88d47e66a340 R15: ffff88d47e66aed0
[   24.775182] FS:  0000000000000000(0000) GS:ffff88d4d1d56000(0000) knlGS:[...]
[   24.775392] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   24.775579] CR2: 000000000000006c CR3: 0000000002bb0003 CR4: 0000000000770ef0
[   24.775810] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   24.776023] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   24.776225] PKRU: 55555554
[   24.776292] Call Trace:
[   24.776373]  <IRQ>
[   24.776453]  ? __pfx_inactive_task_timer+0x10/0x10
[   24.776591]  __hrtimer_run_queues+0xf1/0x270
[   24.776744]  hrtimer_interrupt+0xfa/0x220
[   24.776847]  __sysvec_apic_timer_interrupt+0x4d/0x190
[   24.776988]  sysvec_apic_timer_interrupt+0x69/0x80
[   24.777132]  </IRQ>
[   24.777194]  <TASK>
[   24.777256]  asm_sysvec_apic_timer_interrupt+0x1a/0x20

Fix, by also checking the DL server's has_task pointer which only exists
for server tasks. This fixes the crash.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/sched/deadline.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index aee1aa6c74e8..aa200350f600 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1822,7 +1822,13 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	struct rq_flags rf;
 	struct rq *rq;
 
-	if (!dl_server(dl_se)) {
+	/*
+	 * It is possible that after dl_server_apply_params(), the dl_se->dl_server == 0,
+	 * but the inactive timer is still queued and could not get canceled. Double check
+	 * by looking at ->server_has_tasks to make sure we're dealing with a non-server
+	 * here. Otherwise p may be bogus and we'll crash.
+	 */
+	if (!dl_server(dl_se) && !dl_se->server_has_tasks) {
 		p = dl_task_of(dl_se);
 		rq = task_rq_lock(p, &rf);
 	} else {
@@ -1833,7 +1839,7 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	sched_clock_tick();
 	update_rq_clock(rq);
 
-	if (dl_server(dl_se))
+	if (dl_server(dl_se) || dl_se->server_has_tasks)
 		goto no_task;
 
 	if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
@@ -1861,7 +1867,7 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	dl_se->dl_non_contending = 0;
 unlock:
 
-	if (!dl_server(dl_se)) {
+	if (!dl_server(dl_se) && !dl_se->server_has_tasks) {
 		task_rq_unlock(rq, p, &rf);
 		put_task_struct(p);
 	} else {
-- 
2.34.1

[PATCH v6 14/14] selftests/sched_ext: Add test for DL server total_bw consistency

[Joel Fernandes]

Add a new kselftest to verify that the total_bw value in
/sys/kernel/debug/sched/debug remains consistent across all CPUs
under different sched_ext BPF program states:

1. Before a BPF scheduler is loaded
2. While a BPF scheduler is loaded and active
3. After a BPF scheduler is unloaded

The test runs CPU stress threads to ensure DL server bandwidth
values stabilize before checking consistency. This helps catch
potential issues with DL server bandwidth accounting during
sched_ext transitions.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 tools/testing/selftests/sched_ext/Makefile   |   1 +
 tools/testing/selftests/sched_ext/total_bw.c | 286 +++++++++++++++++++
 2 files changed, 287 insertions(+)
 create mode 100644 tools/testing/selftests/sched_ext/total_bw.c

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index f0a8cba3a99f..d48be158b0a1 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -184,6 +184,7 @@ auto-test-targets :=			\
 	select_cpu_vtime		\
 	rt_stall			\
 	test_example			\
+	total_bw			\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
 
diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c
new file mode 100644
index 000000000000..6b81d6c51054
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/total_bw.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test to verify that total_bw value remains consistent across all CPUs
+ * in different BPF program states.
+ *
+ * Copyright (C) 2025 Nvidia Corporation.
+ */
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <scx/common.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "minimal.bpf.skel.h"
+#include "scx_test.h"
+
+#define MAX_CPUS 512
+#define STABILIZATION_TIME_SEC 5
+#define STRESS_DURATION_SEC 5
+
+struct total_bw_ctx {
+	struct minimal *skel;
+	long baseline_bw[MAX_CPUS];
+	int nr_cpus;
+};
+
+static void *cpu_stress_thread(void *arg)
+{
+	volatile int i;
+	time_t end_time = time(NULL) + STRESS_DURATION_SEC;
+
+	while (time(NULL) < end_time) {
+		for (i = 0; i < 1000000; i++);
+	}
+
+	return NULL;
+}
+
+/*
+ * The first enqueue on a CPU causes the DL server to start, for that
+ * reason run stressor threads in the hopes it schedules on all CPUs.
+ */
+static int run_cpu_stress(int nr_cpus)
+{
+	pthread_t *threads;
+	int i, ret = 0;
+
+	threads = calloc(nr_cpus, sizeof(pthread_t));
+	if (!threads)
+		return -ENOMEM;
+
+	/* Create threads to run on each CPU */
+	for (i = 0; i < nr_cpus; i++) {
+		if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) {
+			ret = -errno;
+			fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret));
+			break;
+		}
+	}
+
+	/* Wait for all threads to complete */
+	for (i = 0; i < nr_cpus; i++) {
+		if (threads[i])
+			pthread_join(threads[i], NULL);
+	}
+
+	free(threads);
+	return ret;
+}
+
+static int read_total_bw_values(long *bw_values, int max_cpus)
+{
+	FILE *fp;
+	char line[256];
+	int cpu_count = 0;
+
+	fp = fopen("/sys/kernel/debug/sched/debug", "r");
+	if (!fp) {
+		SCX_ERR("Failed to open debug file");
+		return -1;
+	}
+
+	while (fgets(line, sizeof(line), fp)) {
+		char *bw_str = strstr(line, "total_bw");
+		if (bw_str) {
+			bw_str = strchr(bw_str, ':');
+			if (bw_str) {
+				/* Only store up to max_cpus values */
+				if (cpu_count < max_cpus) {
+					bw_values[cpu_count] = atol(bw_str + 1);
+				}
+				cpu_count++;
+			}
+		}
+	}
+
+	fclose(fp);
+	return cpu_count;
+}
+
+static bool verify_total_bw_consistency(long *bw_values, int count)
+{
+	int i;
+	long first_value;
+
+	if (count <= 0)
+		return false;
+
+	first_value = bw_values[0];
+
+	for (i = 1; i < count; i++) {
+		if (bw_values[i] != first_value) {
+			SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld",
+				first_value, i, bw_values[i]);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int fetch_verify_total_bw(long *bw_values, int nr_cpus)
+{
+	int attempts = 0;
+	int max_attempts = 10;
+	int count;
+
+	/*
+	 * The first enqueue on a CPU causes the DL server to start, for that
+	 * reason run stressor threads in the hopes it schedules on all CPUs.
+	 */
+	if (run_cpu_stress(nr_cpus) < 0) {
+		SCX_ERR("Failed to run CPU stress");
+		return -1;
+	}
+
+	/* Let things settle down */
+	sleep(STABILIZATION_TIME_SEC);
+
+	/* Try multiple times to get stable values */
+	while (attempts < max_attempts) {
+		count = read_total_bw_values(bw_values, nr_cpus);
+		fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus);
+		/* If system has more CPUs than we're testing, that's OK */
+		if (count < nr_cpus) {
+			SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count);
+			attempts++;
+			sleep(1);
+			continue;
+		}
+
+		/* Only verify the CPUs we're testing */
+		if (verify_total_bw_consistency(bw_values, nr_cpus)) {
+			fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]);
+			return 0;
+		}
+
+		attempts++;
+		sleep(1);
+	}
+
+	return -1;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct total_bw_ctx *test_ctx;
+
+	if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) {
+		fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n");
+		return SCX_TEST_SKIP;
+	}
+
+	test_ctx = calloc(1, sizeof(*test_ctx));
+	if (!test_ctx)
+		return SCX_TEST_FAIL;
+
+	test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (test_ctx->nr_cpus <= 0) {
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	/* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */
+	if (test_ctx->nr_cpus > MAX_CPUS) {
+		test_ctx->nr_cpus = MAX_CPUS;
+	}
+
+	/* Test scenario 1: BPF program not loaded */
+	/* Read and verify baseline total_bw before loading BPF program */
+	fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable baseline values");
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	/* Load the BPF skeleton */
+	test_ctx->skel = minimal__open();
+	if (!test_ctx->skel) {
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	SCX_ENUM_INIT(test_ctx->skel);
+	if (minimal__load(test_ctx->skel)) {
+		minimal__destroy(test_ctx->skel);
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	*ctx = test_ctx;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct total_bw_ctx *test_ctx = ctx;
+	struct bpf_link *link;
+	long loaded_bw[MAX_CPUS];
+	long unloaded_bw[MAX_CPUS];
+	int i;
+
+	/* Test scenario 2: BPF program loaded */
+	link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	fprintf(stderr, "BPF program loaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values with BPF loaded");
+		bpf_link__destroy(link);
+		return SCX_TEST_FAIL;
+	}
+	bpf_link__destroy(link);
+
+	/* Test scenario 3: BPF program unloaded */
+	fprintf(stderr, "BPF program unloaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values after BPF unload");
+		return SCX_TEST_FAIL;
+	}
+
+	/* Verify all three scenarios have the same total_bw values */
+	for (i = 0; i < test_ctx->nr_cpus; i++) {
+		if (test_ctx->baseline_bw[i] != loaded_bw[i]) {
+			SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld",
+				i, test_ctx->baseline_bw[i], loaded_bw[i]);
+			return SCX_TEST_FAIL;
+		}
+
+		if (test_ctx->baseline_bw[i] != unloaded_bw[i]) {
+			SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld",
+				i, test_ctx->baseline_bw[i], unloaded_bw[i]);
+			return SCX_TEST_FAIL;
+		}
+	}
+
+	fprintf(stderr, "All total_bw values are consistent across all scenarios\n");
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct total_bw_ctx *test_ctx = ctx;
+
+	if (test_ctx) {
+		if (test_ctx->skel)
+			minimal__destroy(test_ctx->skel);
+		free(test_ctx);
+	}
+}
+
+struct scx_test total_bw = {
+	.name = "total_bw",
+	.description = "Verify total_bw consistency across BPF program states",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&total_bw)
-- 
2.34.1