Merge tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Implement the SCHED_DEADLINE server infrastructure - Daniel Bristot
   de Oliveira's last major contribution to the kernel:

     "SCHED_DEADLINE servers can help fixing starvation issues of low
      priority tasks (e.g., SCHED_OTHER) when higher priority tasks
      monopolize CPU cycles. Today we have RT Throttling; DEADLINE
      servers should be able to replace and improve that."

   (Daniel Bristot de Oliveira, Peter Zijlstra, Joel Fernandes, Youssef
   Esmat, Huang Shijie)

 - Preparatory changes for sched_ext integration:
     - Use set_next_task(.first) where required
     - Fix up set_next_task() implementations
     - Clean up DL server vs. core sched
     - Split up put_prev_task_balance()
     - Rework pick_next_task()
     - Combine the last put_prev_task() and the first set_next_task()
     - Rework dl_server
     - Add put_prev_task(.next)

   (Peter Zijlstra, with a fix by Tejun Heo)

 - Complete the EEVDF transition and refine EEVDF scheduling:
     - Implement delayed dequeue
     - Allow shorter slices to wakeup-preempt
     - Use sched_attr::sched_runtime to set request/slice suggestion
     - Document the new feature flags
     - Remove unused and duplicate-functionality fields
     - Simplify & unify pick_next_task_fair()
     - Misc debuggability enhancements

   (Peter Zijlstra, with fixes/cleanups by Dietmar Eggemann, Valentin
   Schneider and Chuyi Zhou)

 - Initialize the vruntime of a new task when it is first enqueued,
   resulting in significant decrease in latency of newly woken tasks
   (Zhang Qiao)

 - Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
   (K Prateek Nayak, Peter Zijlstra)

 - Clean up and clarify the usage of Clean up usage of rt_task()
   (Qais Yousef)

 - Preempt SCHED_IDLE entities in strict cgroup hierarchies
   (Tianchen Ding)

 - Clarify the documentation of time units for deadline scheduler
   parameters (Christian Loehle)

 - Remove the HZ_BW chicken-bit feature flag introduced a year ago,
   the original change seems to be working fine (Phil Auld)

 - Misc fixes and cleanups (Chen Yu, Dan Carpenter, Huang Shijie,
   Peilin He, Qais Yousefm and Vincent Guittot)

* tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/cpufreq: Use NSEC_PER_MSEC for deadline task
  cpufreq/cppc: Use NSEC_PER_MSEC for deadline task
  sched/deadline: Clarify nanoseconds in uapi
  sched/deadline: Convert schedtool example to chrt
  sched/debug: Fix the runnable tasks output
  sched: Fix sched_delayed vs sched_core
  kernel/sched: Fix util_est accounting for DELAY_DEQUEUE
  kthread: Fix task state in kthread worker if being frozen
  sched/pelt: Use rq_clock_task() for hw_pressure
  sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c
  sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
  sched: Add put_prev_task(.next)
  sched: Rework dl_server
  sched: Combine the last put_prev_task() and the first set_next_task()
  sched: Rework pick_next_task()
  sched: Split up put_prev_task_balance()
  sched: Clean up DL server vs core sched
  sched: Fixup set_next_task() implementations
  sched: Use set_next_task(.first) where required
  sched/fair: Properly deactivate sched_delayed task upon class change
  ...

1 files changed, 25 insertions, 109 deletions

diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 195d2f2834a9..cb03c790c27a 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -57,7 +57,7 @@ static int effective_prio(struct task_struct *p)
 	 * keep the priority unchanged. Otherwise, update priority
 	 * to the normal priority:
 	 */
-	if (!rt_prio(p->prio))
+	if (!rt_or_dl_prio(p->prio))
 		return p->normal_prio;
 	return p->prio;
 }
@@ -258,107 +258,6 @@ int sched_core_idle_cpu(int cpu)
 
 #endif
 
-#ifdef CONFIG_SMP
-/*
- * This function computes an effective utilization for the given CPU, to be
- * used for frequency selection given the linear relation: f = u * f_max.
- *
- * The scheduler tracks the following metrics:
- *
- *   cpu_util_{cfs,rt,dl,irq}()
- *   cpu_bw_dl()
- *
- * Where the cfs,rt and dl util numbers are tracked with the same metric and
- * synchronized windows and are thus directly comparable.
- *
- * The cfs,rt,dl utilization are the running times measured with rq->clock_task
- * which excludes things like IRQ and steal-time. These latter are then accrued
- * in the IRQ utilization.
- *
- * The DL bandwidth number OTOH is not a measured metric but a value computed
- * based on the task model parameters and gives the minimal utilization
- * required to meet deadlines.
- */
-unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long *min,
-				 unsigned long *max)
-{
-	unsigned long util, irq, scale;
-	struct rq *rq = cpu_rq(cpu);
-
-	scale = arch_scale_cpu_capacity(cpu);
-
-	/*
-	 * Early check to see if IRQ/steal time saturates the CPU, can be
-	 * because of inaccuracies in how we track these -- see
-	 * update_irq_load_avg().
-	 */
-	irq = cpu_util_irq(rq);
-	if (unlikely(irq >= scale)) {
-		if (min)
-			*min = scale;
-		if (max)
-			*max = scale;
-		return scale;
-	}
-
-	if (min) {
-		/*
-		 * The minimum utilization returns the highest level between:
-		 * - the computed DL bandwidth needed with the IRQ pressure which
-		 *   steals time to the deadline task.
-		 * - The minimum performance requirement for CFS and/or RT.
-		 */
-		*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
-
-		/*
-		 * When an RT task is runnable and uclamp is not used, we must
-		 * ensure that the task will run at maximum compute capacity.
-		 */
-		if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
-			*min = max(*min, scale);
-	}
-
-	/*
-	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
-	 * CFS tasks and we use the same metric to track the effective
-	 * utilization (PELT windows are synchronized) we can directly add them
-	 * to obtain the CPU's actual utilization.
-	 */
-	util = util_cfs + cpu_util_rt(rq);
-	util += cpu_util_dl(rq);
-
-	/*
-	 * The maximum hint is a soft bandwidth requirement, which can be lower
-	 * than the actual utilization because of uclamp_max requirements.
-	 */
-	if (max)
-		*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
-
-	if (util >= scale)
-		return scale;
-
-	/*
-	 * There is still idle time; further improve the number by using the
-	 * IRQ metric. Because IRQ/steal time is hidden from the task clock we
-	 * need to scale the task numbers:
-	 *
-	 *              max - irq
-	 *   U' = irq + --------- * U
-	 *                 max
-	 */
-	util = scale_irq_capacity(util, irq, scale);
-	util += irq;
-
-	return min(scale, util);
-}
-
-unsigned long sched_cpu_util(int cpu)
-{
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
-}
-#endif /* CONFIG_SMP */
-
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
@@ -401,13 +300,23 @@ static void __setscheduler_params(struct task_struct *p,
 
 	p->policy = policy;
 
-	if (dl_policy(policy))
+	if (dl_policy(policy)) {
 		__setparam_dl(p, attr);
-	else if (fair_policy(policy))
+	} else if (fair_policy(policy)) {
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+		if (attr->sched_runtime) {
+			p->se.custom_slice = 1;
+			p->se.slice = clamp_t(u64, attr->sched_runtime,
+					      NSEC_PER_MSEC/10,   /* HZ=1000 * 10 */
+					      NSEC_PER_MSEC*100); /* HZ=100  / 10 */
+		} else {
+			p->se.custom_slice = 0;
+			p->se.slice = sysctl_sched_base_slice;
+		}
+	}
 
 	/* rt-policy tasks do not have a timerslack */
-	if (task_is_realtime(p)) {
+	if (rt_or_dl_task_policy(p)) {
 		p->timer_slack_ns = 0;
 	} else if (p->timer_slack_ns == 0) {
 		/* when switching back to non-rt policy, restore timerslack */
@@ -708,7 +617,9 @@ recheck:
 	 * but store a possible modification of reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
+		if (fair_policy(policy) &&
+		    (attr->sched_nice != task_nice(p) ||
+		     (attr->sched_runtime != p->se.slice)))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
@@ -854,6 +765,9 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 
+	if (p->se.custom_slice)
+		attr.sched_runtime = p->se.slice;
+
 	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
 	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
@@ -1020,12 +934,14 @@ err_size:
 
 static void get_params(struct task_struct *p, struct sched_attr *attr)
 {
-	if (task_has_dl_policy(p))
+	if (task_has_dl_policy(p)) {
 		__getparam_dl(p, attr);
-	else if (task_has_rt_policy(p))
+	} else if (task_has_rt_policy(p)) {
 		attr->sched_priority = p->rt_priority;
-	else
+	} else {
 		attr->sched_nice = task_nice(p);
+		attr->sched_runtime = p->se.slice;
+	}
 }
 
 /**