Merge branch 'tip/sched/core' into sched_ext/for-6.12

Pull in tip/sched/core to resolve two merge conflicts:

- 96fd6c65efc6 ("sched: Factor out update_other_load_avgs() from __update_blocked_others()")
5d871a63997f ("sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c")

A simple context conflict. The former added __update_blocked_others() in
the same #ifdef CONFIG_SMP block that effective_cpu_util() and
sched_cpu_util() are in and the latter moved those functions to fair.c.
This makes __update_blocked_others() more out of place. Will follow up
with a patch to relocate.

- 96fd6c65efc6 ("sched: Factor out update_other_load_avgs() from __update_blocked_others()")
84d265281d6c ("sched/pelt: Use rq_clock_task() for hw_pressure")

The former factored out the body of __update_blocked_others() into
update_other_load_avgs(). The latter changed how update_hw_load_avg() is
called in the body. Resolved by applying the change to
update_other_load_avgs() instead.

Signed-off-by: Tejun Heo <[e-mail]>

Documentation/scheduler/sched-deadline.rst

···
  of the command line options. Please refer to rt-app documentation for more
  details (`<rt-app-sources>/doc/*.json`).
 
- The second testing application is a modification of schedtool, called
- schedtool-dl, which can be used to setup SCHED_DEADLINE parameters for a
- certain pid/application. schedtool-dl is available at:
- https://github.com/scheduler-tools/schedtool-dl.git.
+ The second testing application is done using chrt which has support
+ for SCHED_DEADLINE.
 
  The usage is straightforward::
 
-  # schedtool -E -t 10000000:100000000 -e ./my_cpuhog_app
+  # chrt -d -T 10000000 -D 100000000 0 ./my_cpuhog_app
 
  With this, my_cpuhog_app is put to run inside a SCHED_DEADLINE reservation
- of 10ms every 100ms (note that parameters are expressed in microseconds).
- You can also use schedtool to create a reservation for an already running
+ of 10ms every 100ms (note that parameters are expressed in nanoseconds).
+ You can also use chrt to create a reservation for an already running
  application, given that you know its pid::
 
-  # schedtool -E -t 10000000:100000000 my_app_pid
+  # chrt -d -T 10000000 -D 100000000 -p 0 my_app_pid
 
 Appendix B. Minimal main()
 ==========================

drivers/cpufreq/cppc_cpufreq.c

···
 		 * Fake (unused) bandwidth; workaround to "fix"
 		 * priority inheritance.
 		 */
-		.sched_runtime	= 1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
+		.sched_runtime	= NSEC_PER_MSEC,
+		.sched_deadline = 10 * NSEC_PER_MSEC,
+		.sched_period	= 10 * NSEC_PER_MSEC,
 	};
 	int ret;
 

include/uapi/linux/sched/types.h

···
  *
  * This is reflected by the following fields of the sched_attr structure:
  *
- *  @sched_deadline	representative of the task's deadline
- *  @sched_runtime	representative of the task's runtime
- *  @sched_period	representative of the task's period
+ *  @sched_deadline	representative of the task's deadline in nanoseconds
+ *  @sched_runtime	representative of the task's runtime in nanoseconds
+ *  @sched_period	representative of the task's period in nanoseconds
  *
  * Given this task model, there are a multiplicity of scheduling algorithms
  * and policies, that can be used to ensure all the tasks will make their

kernel/kthread.c

···
 		 * event only cares about the address.
 		 */
 		trace_sched_kthread_work_execute_end(work, func);
-	} else if (!freezing(current))
+	} else if (!freezing(current)) {
 		schedule();
+	} else {
+		/*
+		 * Handle the case where the current remains
+		 * TASK_INTERRUPTIBLE. try_to_freeze() expects
+		 * the current to be TASK_RUNNING.
+		 */
+		__set_current_state(TASK_RUNNING);
+	}
 
 	try_to_freeze();
 	cond_resched();

kernel/sched/core.c

···
 
 void sched_core_enqueue(struct rq *rq, struct task_struct *p)
 {
+	if (p->se.sched_delayed)
+		return;
+
 	rq->core->core_task_seq++;
 
 	if (!p->core_cookie)
···
 
 void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
 {
+	if (p->se.sched_delayed)
+		return;
+
 	rq->core->core_task_seq++;
 
 	if (sched_core_enqueued(p)) {
···
  * Constants for the sched_mode argument of __schedule().
  *
  * The mode argument allows RT enabled kernels to differentiate a
- * preemption from blocking on an 'sleeping' spin/rwlock. Note that
- * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
- * optimize the AND operation out and just check for zero.
+ * preemption from blocking on an 'sleeping' spin/rwlock.
  */
-#define SM_NONE			0x0
-#define SM_PREEMPT		0x1
-#define SM_RTLOCK_WAIT		0x2
-
-#ifndef CONFIG_PREEMPT_RT
-# define SM_MASK_PREEMPT	(~0U)
-#else
-# define SM_MASK_PREEMPT	SM_PREEMPT
-#endif
+#define SM_IDLE			(-1)
+#define SM_NONE			0
+#define SM_PREEMPT		1
+#define SM_RTLOCK_WAIT		2
 
 /*
  * __schedule() is the main scheduler function.
···
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(unsigned int sched_mode)
+static void __sched notrace __schedule(int sched_mode)
 {
 	struct task_struct *prev, *next;
+	/*
+	 * On PREEMPT_RT kernel, SM_RTLOCK_WAIT is noted
+	 * as a preemption by schedule_debug() and RCU.
+	 */
+	bool preempt = sched_mode > SM_NONE;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
···
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, !!sched_mode);
+	schedule_debug(prev, preempt);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(!!sched_mode);
+	rcu_note_context_switch(preempt);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
···
 
 	switch_count = &prev->nivcsw;
 
+	/* Task state changes only considers SM_PREEMPT as preemption */
+	preempt = sched_mode == SM_PREEMPT;
+
 	/*
 	 * We must load prev->state once (task_struct::state is volatile), such
 	 * that we form a control dependency vs deactivate_task() below.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
+	if (sched_mode == SM_IDLE) {
+		if (!rq->nr_running) {
+			next = prev;
+			goto picked;
+		}
+	} else if (!preempt && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
···
 	}
 
 	next = pick_next_task(rq, prev, &rf);
+picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
 #ifdef CONFIG_SCHED_DEBUG
···
 		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
+		trace_sched_switch(preempt, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
···
 	}
 }
 
-static __always_inline void __schedule_loop(unsigned int sched_mode)
+static __always_inline void __schedule_loop(int sched_mode)
 {
 	do {
 		preempt_disable();
···
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(SM_NONE);
+		__schedule(SM_IDLE);
 	} while (need_resched());
 }
 

kernel/sched/cpufreq_schedutil.c

···
 		 * Fake (unused) bandwidth; workaround to "fix"
 		 * priority inheritance.
 		 */
-		.sched_runtime	=  1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
+		.sched_runtime	= NSEC_PER_MSEC,
+		.sched_deadline = 10 * NSEC_PER_MSEC,
+		.sched_period	= 10 * NSEC_PER_MSEC,
 	};
 	struct cpufreq_policy *policy = sg_policy->policy;
 	int ret;

kernel/sched/debug.c

···
 	else
 		SEQ_printf(m, " %c", task_state_to_char(p));
 
-	SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, " %15s %5d %9Ld.%06ld   %c   %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld   %5d ",
 		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
 		entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N',
···
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 
-	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld",
+	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld",
 		SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
-		SPLIT_NS(p->se.sum_exec_runtime),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
+	SEQ_printf(m, "   %d      %d", task_node(p), task_numa_group_id(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
-	SEQ_printf_task_group_path(m, task_group(p), " %s")
+	SEQ_printf_task_group_path(m, task_group(p), "        %s")
 #endif
 
 	SEQ_printf(m, "\n");
···
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "runnable tasks:\n");
-	SEQ_printf(m, " S            task   PID         tree-key  switches  prio"
-		   "     wait-time             sum-exec        sum-sleep\n");
+	SEQ_printf(m, " S            task   PID       vruntime   eligible    "
+		   "deadline             slice          sum-exec      switches  "
+		   "prio         wait-time        sum-sleep       sum-block"
+#ifdef CONFIG_NUMA_BALANCING
+		   "  node   group-id"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "  group-path"
+#endif
+		   "\n");
 	SEQ_printf(m, "-------------------------------------------------------"
-		   "------------------------------------------------------\n");
+		   "------------------------------------------------------"
+		   "------------------------------------------------------"
+#ifdef CONFIG_NUMA_BALANCING
+		   "--------------"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "--------------"
+#endif
+		   "\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {

kernel/sched/fair.c

···
 	int rq_h_nr_running = rq->cfs.h_nr_running;
 	u64 slice = 0;
 
-	if (flags & ENQUEUE_DELAYED) {
-		requeue_delayed_entity(se);
-		return;
-	}
-
 	/*
 	 * The code below (indirectly) updates schedutil which looks at
 	 * the cfs_rq utilization to select a frequency.
 	 * Let's add the task's estimated utilization to the cfs_rq's
 	 * estimated utilization, before we update schedutil.
 	 */
-	util_est_enqueue(&rq->cfs, p);
+	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & ENQUEUE_RESTORE))))
+		util_est_enqueue(&rq->cfs, p);
+
+	if (flags & ENQUEUE_DELAYED) {
+		requeue_delayed_entity(se);
+		return;
+	}
 
 	/*
 	 * If in_iowait is set, the code below may not trigger any cpufreq
···
  */
 static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
-	util_est_dequeue(&rq->cfs, p);
+	if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE))))
+		util_est_dequeue(&rq->cfs, p);
 
 	if (dequeue_entities(rq, &p->se, flags) < 0) {
 		util_est_update(&rq->cfs, p, DEQUEUE_SLEEP);
···
 		p = NULL;
 
 	return cpu_util(cpu, p, -1, 0);
+}
+
+/*
+ * 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);
 }
 
 /*

kernel/sched/syscalls.c

···
 
 	lockdep_assert_rq_held(rq);
 
+	/* hw_pressure doesn't care about invariance */
 	return update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
 		update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-		update_hw_load_avg(now, rq, hw_pressure) |
+		update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure) |
 		update_irq_load_avg(rq, 0);
-}
-
-/*
- * 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 */