sched/deadline: Add reporting of runtime left & abs deadline to sched_getattr() for DEADLINE tasks

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".

Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@santannapisa.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matteo Martelli <matteo.martelli@codethink.co.uk>
Link: https://patch.msgid.link/20250912053937.31636-2-tommaso.cucinotta@santannapisa.it

4 files changed, 31 insertions, 9 deletions

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 359a14cc76a4..52b69ce89368 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 2de5727b94b4..9e253a825f39 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3617,13 +3617,26 @@ 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);
+		if (task_current(rq, p))
+			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 8bf2f7d524cd..fa2237e89bee 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -356,7 +356,7 @@ 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 6f10db3646e7..a288ac0a633d 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -881,10 +881,10 @@ err_size:
 	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 {
@@ -950,7 +950,7 @@ 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);
 }
@@ -1035,7 +1035,7 @@ 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) {
@@ -1043,6 +1043,12 @@ 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;
@@ -1050,7 +1056,7 @@ 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