The SCHED_DEADLINE scheduler allows reading the statically configured
run-time, deadline, and period parameters through the sched_getattr()
system call. However, there is no immediate way to access, from user space,
the current parameters used within the scheduler: the instantaneous runtime
left in the current cycle, as well as the current absolute deadline.

The `flags' sched_getattr() parameter, so far mandated to contain zero,
now supports the SCHED_GETATTR_FLAG_DL_DYNAMIC=1 flag, to request
retrieval of the leftover runtime and absolute deadline, converted to a
CLOCK_MONOTONIC reference, instead of the statically configured parameters.

This feature is useful for adaptive SCHED_DEADLINE tasks that need to
modify their behavior depending on whether or not there is enough runtime
left in the current period, and/or what is the current absolute deadline.

Notes:
- before returning the instantaneous parameters, the runtime is updated;
- the abs deadline is returned shifted from rq_clock() to ktime_get_ns(),
  in CLOCK_MONOTONIC reference; this causes multiple invocations from the
  same period to return values that may differ for a few ns (showing some
  small drift), albeit the deadline doesn't move, in rq_clock() reference;
- the abs deadline value returned to user-space, as unsigned 64-bit value,
  can represent nearly 585 years since boot time;
- setting flags=0 provides the old behavior (retrieve static parameters).

See also the notes from discussion held at OSPM 2025 on the topic
"Making user space aware of current deadline-scheduler parameters":
https://lwn.net/Articles/1022054/

Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it>
---
 include/uapi/linux/sched.h |  3 +++
 kernel/sched/deadline.c    | 18 +++++++++++++++---
 kernel/sched/sched.h       |  2 +-
 kernel/sched/syscalls.c    | 16 +++++++++++-----
 4 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 359a14cc..52b69ce8 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -146,4 +146,7 @@ struct clone_args {
 			 SCHED_FLAG_KEEP_ALL		| \
 			 SCHED_FLAG_UTIL_CLAMP)
 
+/* Only for sched_getattr() own flag param, if task is SCHED_DEADLINE */
+#define SCHED_GETATTR_FLAG_DL_DYNAMIC	0x01
+
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9c7d9528..1b5cd7fa 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3290,13 +3290,25 @@ void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
 }
 
-void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
+void __getparam_dl(struct task_struct *p, struct sched_attr *attr, unsigned int flags)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
+	struct rq *rq = task_rq(p);
+	u64 adj_deadline;
 
 	attr->sched_priority = p->rt_priority;
-	attr->sched_runtime = dl_se->dl_runtime;
-	attr->sched_deadline = dl_se->dl_deadline;
+	if (flags & SCHED_GETATTR_FLAG_DL_DYNAMIC) {
+		guard(raw_spinlock_irq)(&rq->__lock);
+		update_rq_clock(rq);
+		update_curr_dl(rq);
+
+		attr->sched_runtime = dl_se->runtime;
+		adj_deadline = dl_se->deadline - rq_clock(rq) + ktime_get_ns();
+		attr->sched_deadline = adj_deadline;
+	} else {
+		attr->sched_runtime = dl_se->dl_runtime;
+		attr->sched_deadline = dl_se->dl_deadline;
+	}
 	attr->sched_period = dl_se->dl_period;
 	attr->sched_flags &= ~SCHED_DL_FLAGS;
 	attr->sched_flags |= dl_se->flags;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3058fb62..f69bf019 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -353,7 +353,7 @@ extern int  sched_dl_global_validate(void);
 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);
+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 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);
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 77ae87f3..c80b3568 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -928,10 +928,10 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	return -E2BIG;
 }
 
-static void get_params(struct task_struct *p, struct sched_attr *attr)
+static void get_params(struct task_struct *p, struct sched_attr *attr, unsigned int flags)
 {
 	if (task_has_dl_policy(p)) {
-		__getparam_dl(p, attr);
+		__getparam_dl(p, attr, flags);
 	} else if (task_has_rt_policy(p)) {
 		attr->sched_priority = p->rt_priority;
 	} else {
@@ -997,7 +997,7 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 		return -ESRCH;
 
 	if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
-		get_params(p, &attr);
+		get_params(p, &attr, 0);
 
 	return sched_setattr(p, &attr);
 }
@@ -1082,7 +1082,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	int retval;
 
 	if (unlikely(!uattr || pid < 0 || usize > PAGE_SIZE ||
-		      usize < SCHED_ATTR_SIZE_VER0 || flags))
+		     usize < SCHED_ATTR_SIZE_VER0))
 		return -EINVAL;
 
 	scoped_guard (rcu) {
@@ -1090,6 +1090,12 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		if (!p)
 			return -ESRCH;
 
+		if (flags) {
+			if (!task_has_dl_policy(p)
+			    || flags != SCHED_GETATTR_FLAG_DL_DYNAMIC)
+				return -EINVAL;
+		}
+
 		retval = security_task_getscheduler(p);
 		if (retval)
 			return retval;
@@ -1097,7 +1103,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		kattr.sched_policy = p->policy;
 		if (p->sched_reset_on_fork)
 			kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-		get_params(p, &kattr);
+		get_params(p, &kattr, flags);
 		kattr.sched_flags &= SCHED_FLAG_ALL;
 
 #ifdef CONFIG_UCLAMP_TASK
-- 
2.45.2

Hi Tommaso,

On 15/07/25 18:39, Tommaso Cucinotta wrote:
> The SCHED_DEADLINE scheduler allows reading the statically configured
> run-time, deadline, and period parameters through the sched_getattr()
> system call. However, there is no immediate way to access, from user space,
> the current parameters used within the scheduler: the instantaneous runtime
> left in the current cycle, as well as the current absolute deadline.
> 
> The `flags' sched_getattr() parameter, so far mandated to contain zero,
> now supports the SCHED_GETATTR_FLAG_DL_DYNAMIC=1 flag, to request
> retrieval of the leftover runtime and absolute deadline, converted to a
> CLOCK_MONOTONIC reference, instead of the statically configured parameters.
> 
> This feature is useful for adaptive SCHED_DEADLINE tasks that need to
> modify their behavior depending on whether or not there is enough runtime
> left in the current period, and/or what is the current absolute deadline.
> 
> Notes:
> - before returning the instantaneous parameters, the runtime is updated;
> - the abs deadline is returned shifted from rq_clock() to ktime_get_ns(),
>   in CLOCK_MONOTONIC reference; this causes multiple invocations from the
>   same period to return values that may differ for a few ns (showing some
>   small drift), albeit the deadline doesn't move, in rq_clock() reference;
> - the abs deadline value returned to user-space, as unsigned 64-bit value,
>   can represent nearly 585 years since boot time;
> - setting flags=0 provides the old behavior (retrieve static parameters).

As we discussed this offline before your submission you know that I was
already on board with the idea, so I would really like to hear what
Peter and others think about this.

Still a few comments below.

$SUBJECT can maybe simply be "sched/deadline: Add reporting of remaining
time/abs deadline to sched_getattr".

> See also the notes from discussion held at OSPM 2025 on the topic
> "Making user space aware of current deadline-scheduler parameters":
> https://lwn.net/Articles/1022054/

I would probably remove the link from the changelog as it might
disappear/change in the future.

> Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it>
> ---
>  include/uapi/linux/sched.h |  3 +++
>  kernel/sched/deadline.c    | 18 +++++++++++++++---
>  kernel/sched/sched.h       |  2 +-
>  kernel/sched/syscalls.c    | 16 +++++++++++-----
>  4 files changed, 30 insertions(+), 9 deletions(-)
> 
> diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
> index 359a14cc..52b69ce8 100644
> --- a/include/uapi/linux/sched.h
> +++ b/include/uapi/linux/sched.h
> @@ -146,4 +146,7 @@ struct clone_args {
>  			 SCHED_FLAG_KEEP_ALL		| \
>  			 SCHED_FLAG_UTIL_CLAMP)
>  
> +/* Only for sched_getattr() own flag param, if task is SCHED_DEADLINE */
> +#define SCHED_GETATTR_FLAG_DL_DYNAMIC	0x01
> +
>  #endif /* _UAPI_LINUX_SCHED_H */
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 9c7d9528..1b5cd7fa 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -3290,13 +3290,25 @@ void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
>  	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
>  }
>  
> -void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
> +void __getparam_dl(struct task_struct *p, struct sched_attr *attr, unsigned int flags)
>  {
>  	struct sched_dl_entity *dl_se = &p->dl;
> +	struct rq *rq = task_rq(p);
> +	u64 adj_deadline;
>  
>  	attr->sched_priority = p->rt_priority;
> -	attr->sched_runtime = dl_se->dl_runtime;
> -	attr->sched_deadline = dl_se->dl_deadline;
> +	if (flags & SCHED_GETATTR_FLAG_DL_DYNAMIC) {
> +		guard(raw_spinlock_irq)(&rq->__lock);
> +		update_rq_clock(rq);
> +		update_curr_dl(rq);

I p is not current maybe we don't need to call update_curr_dl() as p
will still have sensible dynamic parameters updated last time it
blocked?

Also, even though this is superuser stuff and all, mildly fear this
could be used as a DOS attack vector? Do we want to be super defensive
and add some kind of rate limiting?

> +
> +		attr->sched_runtime = dl_se->runtime;
> +		adj_deadline = dl_se->deadline - rq_clock(rq) + ktime_get_ns();
> +		attr->sched_deadline = adj_deadline;
> +	} else {
> +		attr->sched_runtime = dl_se->dl_runtime;
> +		attr->sched_deadline = dl_se->dl_deadline;
> +	}
>  	attr->sched_period = dl_se->dl_period;
>  	attr->sched_flags &= ~SCHED_DL_FLAGS;
>  	attr->sched_flags |= dl_se->flags;
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 3058fb62..f69bf019 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -353,7 +353,7 @@ extern int  sched_dl_global_validate(void);
>  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);
> +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 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);
> diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
> index 77ae87f3..c80b3568 100644
> --- a/kernel/sched/syscalls.c
> +++ b/kernel/sched/syscalls.c
> @@ -928,10 +928,10 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
>  	return -E2BIG;
>  }
>  
> -static void get_params(struct task_struct *p, struct sched_attr *attr)
> +static void get_params(struct task_struct *p, struct sched_attr *attr, unsigned int flags)
>  {
>  	if (task_has_dl_policy(p)) {
> -		__getparam_dl(p, attr);
> +		__getparam_dl(p, attr, flags);
>  	} else if (task_has_rt_policy(p)) {
>  		attr->sched_priority = p->rt_priority;
>  	} else {
> @@ -997,7 +997,7 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
>  		return -ESRCH;
>  
>  	if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
> -		get_params(p, &attr);
> +		get_params(p, &attr, 0);
>  
>  	return sched_setattr(p, &attr);
>  }
> @@ -1082,7 +1082,7 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
>  	int retval;
>  
>  	if (unlikely(!uattr || pid < 0 || usize > PAGE_SIZE ||
> -		      usize < SCHED_ATTR_SIZE_VER0 || flags))
> +		     usize < SCHED_ATTR_SIZE_VER0))
>  		return -EINVAL;
>  
>  	scoped_guard (rcu) {
> @@ -1090,6 +1090,12 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
>  		if (!p)
>  			return -ESRCH;
>  
> +		if (flags) {
> +			if (!task_has_dl_policy(p)
> +			    || flags != SCHED_GETATTR_FLAG_DL_DYNAMIC)

Nit pick. Formatting usually has line break after '||'.

> +				return -EINVAL;
> +		}
> +

Thanks!
Juri