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
  ...

Author: torvalds

Documentation/scheduler/sched-deadline.rst

@@ -749,21 +749,19 @@ Appendix A. Test suite
  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

@@ -224,9 +224,9 @@ static void __init cppc_freq_invariance_init(void)
 		 * 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;
 

fs/bcachefs/six.c

@@ -335,7 +335,7 @@ static inline bool six_owner_running(struct six_lock *lock)
 	 */
 	rcu_read_lock();
 	struct task_struct *owner = READ_ONCE(lock->owner);
-	bool ret = owner ? owner_on_cpu(owner) : !rt_task(current);
+	bool ret = owner ? owner_on_cpu(owner) : !rt_or_dl_task(current);
 	rcu_read_unlock();
 
 	return ret;

fs/proc/base.c

@@ -2626,7 +2626,7 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
 	}
 
 	task_lock(p);
-	if (task_is_realtime(p))
+	if (rt_or_dl_task_policy(p))
 		slack_ns = 0;
 	else if (slack_ns == 0)
 		slack_ns = p->default_timer_slack_ns;

include/linux/ioprio.h

@@ -40,7 +40,7 @@ static inline int task_nice_ioclass(struct task_struct *task)
 {
 	if (task->policy == SCHED_IDLE)
 		return IOPRIO_CLASS_IDLE;
-	else if (task_is_realtime(task))
+	else if (rt_or_dl_task_policy(task))
 		return IOPRIO_CLASS_RT;
 	else
 		return IOPRIO_CLASS_BE;

include/linux/sched.h

@@ -149,8 +149,9 @@ struct user_event_mm;
  * Special states are those that do not use the normal wait-loop pattern. See
  * the comment with set_special_state().
  */
-#define is_special_task_state(state)				\
-	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
+#define is_special_task_state(state)					\
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED |	\
+		    TASK_DEAD | TASK_FROZEN))
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 # define debug_normal_state_change(state_value)				\
@@ -541,9 +542,14 @@ struct sched_entity {
 	struct rb_node			run_node;
 	u64				deadline;
 	u64				min_vruntime;
+	u64				min_slice;
 
 	struct list_head		group_node;
-	unsigned int			on_rq;
+	unsigned char			on_rq;
+	unsigned char			sched_delayed;
+	unsigned char			rel_deadline;
+	unsigned char			custom_slice;
+					/* hole */
 
 	u64				exec_start;
 	u64				sum_exec_runtime;
@@ -639,12 +645,26 @@ struct sched_dl_entity {
 	 *
 	 * @dl_overrun tells if the task asked to be informed about runtime
 	 * overruns.
+	 *
+	 * @dl_server tells if this is a server entity.
+	 *
+	 * @dl_defer tells if this is a deferred or regular server. For
+	 * now only defer server exists.
+	 *
+	 * @dl_defer_armed tells if the deferrable server is waiting
+	 * for the replenishment timer to activate it.
+	 *
+	 * @dl_defer_running tells if the deferrable server is actually
+	 * running, skipping the defer phase.
 	 */
 	unsigned int			dl_throttled      : 1;
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
 	unsigned int			dl_server         : 1;
+	unsigned int			dl_defer	  : 1;
+	unsigned int			dl_defer_armed	  : 1;
+	unsigned int			dl_defer_running  : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -672,7 +692,7 @@ struct sched_dl_entity {
 	 */
 	struct rq			*rq;
 	dl_server_has_tasks_f		server_has_tasks;
-	dl_server_pick_f		server_pick;
+	dl_server_pick_f		server_pick_task;
 
 #ifdef CONFIG_RT_MUTEXES
 	/*

include/linux/sched/deadline.h

@@ -10,16 +10,16 @@
 
 #include <linux/sched.h>
 
-#define MAX_DL_PRIO		0
-
-static inline int dl_prio(int prio)
+static inline bool dl_prio(int prio)
 {
-	if (unlikely(prio < MAX_DL_PRIO))
-		return 1;
-	return 0;
+	return unlikely(prio < MAX_DL_PRIO);
 }
 
-static inline int dl_task(struct task_struct *p)
+/*
+ * Returns true if a task has a priority that belongs to DL class. PI-boosted
+ * tasks will return true. Use dl_policy() to ignore PI-boosted tasks.
+ */
+static inline bool dl_task(struct task_struct *p)
 {
 	return dl_prio(p->prio);
 }

include/linux/sched/prio.h

@@ -14,6 +14,7 @@
  */
 
 #define MAX_RT_PRIO		100
+#define MAX_DL_PRIO		0
 
 #define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
 #define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)

include/linux/sched/rt.h

@@ -6,19 +6,40 @@
 
 struct task_struct;
 
-static inline int rt_prio(int prio)
+static inline bool rt_prio(int prio)
 {
-	if (unlikely(prio < MAX_RT_PRIO))
-		return 1;
-	return 0;
+	return unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO);
 }
 
-static inline int rt_task(struct task_struct *p)
+static inline bool rt_or_dl_prio(int prio)
+{
+	return unlikely(prio < MAX_RT_PRIO);
+}
+
+/*
+ * Returns true if a task has a priority that belongs to RT class. PI-boosted
+ * tasks will return true. Use rt_policy() to ignore PI-boosted tasks.
+ */
+static inline bool rt_task(struct task_struct *p)
 {
 	return rt_prio(p->prio);
 }
 
-static inline bool task_is_realtime(struct task_struct *tsk)
+/*
+ * Returns true if a task has a priority that belongs to RT or DL classes.
+ * PI-boosted tasks will return true. Use rt_or_dl_task_policy() to ignore
+ * PI-boosted tasks.
+ */
+static inline bool rt_or_dl_task(struct task_struct *p)
+{
+	return rt_or_dl_prio(p->prio);
+}
+
+/*
+ * Returns true if a task has a policy that belongs to RT or DL classes.
+ * PI-boosted tasks will return false.
+ */
+static inline bool rt_or_dl_task_policy(struct task_struct *tsk)
 {
 	int policy = tsk->policy;
 

include/uapi/linux/sched/types.h

@@ -58,9 +58,9 @@
  *
  * 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