sched/rt: Clean up usage of rt_task()

rt_task() checks if a task has RT priority. But depends on your
dictionary, this could mean it belongs to RT class, or is a 'realtime'
task, which includes RT and DL classes.

Since this has caused some confusion already on discussion [1], it
seemed a clean up is due.

I define the usage of rt_task() to be tasks that belong to RT class.
Make sure that it returns true only for RT class and audit the users and
replace the ones required the old behavior with the new realtime_task()
which returns true for RT and DL classes. Introduce similar
realtime_prio() to create similar distinction to rt_prio() and update
the users that required the old behavior to use the new function.

Move MAX_DL_PRIO to prio.h so it can be used in the new definitions.

Document the functions to make it more obvious what is the difference
between them. PI-boosted tasks is a factor that must be taken into
account when choosing which function to use.

Rename task_is_realtime() to realtime_task_policy() as the old name is
confusing against the new realtime_task().

No functional changes were intended.

[1] https://lore.kernel.org/lkml/20240506100509.GL40213@noisy.programming.kicks-ass.net/

Signed-off-by: Qais Yousef <qyousef@layalina.io>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Reviewed-by: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20240610192018.1567075-2-qyousef@layalina.io

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) : !realtime_task(current);
 	rcu_read_unlock();
 
 	return ret;

fs/select.c

@@ -82,7 +82,7 @@ u64 select_estimate_accuracy(struct timespec64 *tv)
 	 * Realtime tasks get a slack of 0 for obvious reasons.
 	 */
 
-	if (rt_task(current))
+	if (realtime_task(current))
 		return 0;
 
 	ktime_get_ts64(&now);

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 (realtime_task_policy(task))
 		return IOPRIO_CLASS_RT;
 	else
 		return IOPRIO_CLASS_BE;

include/linux/sched/deadline.h

@@ -10,8 +10,6 @@
 
 #include <linux/sched.h>
 
-#define MAX_DL_PRIO		0
-
 static inline int dl_prio(int prio)
 {
 	if (unlikely(prio < MAX_DL_PRIO))
@@ -19,6 +17,10 @@ static inline int dl_prio(int prio)
 	return 0;
 }
 
+/*
+ * 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 int 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

@@ -7,18 +7,43 @@
 struct task_struct;
 
 static inline int rt_prio(int prio)
+{
+	if (unlikely(prio < MAX_RT_PRIO && prio >= MAX_DL_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int realtime_prio(int prio)
 {
 	if (unlikely(prio < MAX_RT_PRIO))
 		return 1;
 	return 0;
 }
 
+/*
+ * 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 int 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 realtime_task_policy() to ignore
+ * PI-boosted tasks.
+ */
+static inline int realtime_task(struct task_struct *p)
+{
+	return realtime_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 realtime_task_policy(struct task_struct *tsk)
 {
 	int policy = tsk->policy;
 

kernel/locking/rtmutex.c

@@ -347,7 +347,7 @@ static __always_inline int __waiter_prio(struct task_struct *task)
 {
 	int prio = task->prio;
 
-	if (!rt_prio(prio))
+	if (!realtime_prio(prio))
 		return DEFAULT_PRIO;
 
 	return prio;
@@ -435,7 +435,7 @@ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
 	 * Note that RT tasks are excluded from same priority (lateral)
 	 * steals to prevent the introduction of an unbounded latency.
 	 */
-	if (rt_prio(waiter->tree.prio) || dl_prio(waiter->tree.prio))
+	if (realtime_prio(waiter->tree.prio))
 		return false;
 
 	return rt_waiter_node_equal(&waiter->tree, &top_waiter->tree);

kernel/locking/rwsem.c

@@ -631,7 +631,7 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 			 * if it is an RT task or wait in the wait queue
 			 * for too long.
 			 */
-			if (has_handoff || (!rt_task(waiter->task) &&
+			if (has_handoff || (!realtime_task(waiter->task) &&
 					    !time_after(jiffies, waiter->timeout)))
 				return false;
 
@@ -914,7 +914,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		if (owner_state != OWNER_WRITER) {
 			if (need_resched())
 				break;
-			if (rt_task(current) &&
+			if (realtime_task(current) &&
 			   (prev_owner_state != OWNER_WRITER))
 				break;
 		}

kernel/locking/ww_mutex.h

@@ -237,7 +237,7 @@ __ww_ctx_less(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
 	int a_prio = a->task->prio;
 	int b_prio = b->task->prio;
 
-	if (rt_prio(a_prio) || rt_prio(b_prio)) {
+	if (realtime_prio(a_prio) || realtime_prio(b_prio)) {
 
 		if (a_prio > b_prio)
 			return true;

kernel/sched/core.c

@@ -166,7 +166,7 @@ static inline int __task_prio(const struct task_struct *p)
 	if (p->dl_server)
 		return -1; /* deadline */
 
-	if (rt_prio(p->prio)) /* includes deadline */
+	if (realtime_prio(p->prio)) /* includes deadline */
 		return p->prio; /* [-1, 99] */
 
 	if (p->sched_class == &idle_sched_class)
@@ -8590,7 +8590,7 @@ void normalize_rt_tasks(void)
 		schedstat_set(p->stats.sleep_start, 0);
 		schedstat_set(p->stats.block_start, 0);
 
-		if (!dl_task(p) && !rt_task(p)) {
+		if (!realtime_task(p)) {
 			/*
 			 * Renice negative nice level userspace
 			 * tasks back to 0:

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 (!realtime_prio(p->prio))
 		return p->normal_prio;
 	return p->prio;
 }

kernel/time/hrtimer.c

@@ -1975,7 +1975,7 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 	 * expiry.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT))
+		if (realtime_task_policy(current) && !(mode & HRTIMER_MODE_SOFT))
 			mode |= HRTIMER_MODE_HARD;
 	}
 
@@ -2075,7 +2075,7 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	u64 slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (realtime_task(current))
 		slack = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
@@ -2280,7 +2280,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 	 * Override any slack passed by the user if under
 	 * rt contraints.
 	 */
-	if (rt_task(current))
+	if (realtime_task(current))
 		delta = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clock_id, mode);

kernel/trace/trace_sched_wakeup.c

@@ -547,7 +547,7 @@ probe_wakeup(void *ignore, struct task_struct *p)
 	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
 	 */
 	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
-	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (wakeup_rt && !realtime_task(p)) ||
 	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 

mm/page-writeback.c

@@ -418,7 +418,7 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 		bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
 
 	tsk = current;
-	if (rt_task(tsk)) {
+	if (realtime_task(tsk)) {
 		bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
 		thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
 	}
@@ -477,7 +477,7 @@ static unsigned long node_dirty_limit(struct pglist_data *pgdat)
 	else
 		dirty = vm_dirty_ratio * node_memory / 100;
 
-	if (rt_task(tsk))
+	if (realtime_task(tsk))
 		dirty += dirty / 4;
 
 	/*

mm/page_alloc.c

@@ -4002,7 +4002,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
 		 */
 		if (alloc_flags & ALLOC_MIN_RESERVE)
 			alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(current)) && in_task())
+	} else if (unlikely(realtime_task(current)) && in_task())
 		alloc_flags |= ALLOC_MIN_RESERVE;
 
 	alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags);