Merge tag 'sched_urgent_for_v6.13_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Remove wrong enqueueing of a task for a later wakeup when a task
   blocks on a RT mutex

 - Do not setup a new deadline entity on a boosted task as that has
   happened already

 - Update preempt= kernel command line param

 - Prevent needless softirqd wakeups in the idle task's context

 - Detect the case where the idle load balancer CPU becomes busy and
   avoid unnecessary load balancing invocation

 - Remove an unnecessary load balancing need_resched() call in
   nohz_csd_func()

 - Allow for raising of SCHED_SOFTIRQ softirq type on RT but retain the
   warning to catch any other cases

 - Remove a wrong warning when a cpuset update makes the task affinity
   no longer a subset of the cpuset

* tag 'sched_urgent_for_v6.13_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking: rtmutex: Fix wake_q logic in task_blocks_on_rt_mutex
  sched/deadline: Fix warning in migrate_enable for boosted tasks
  sched/core: Update kernel boot parameters for LAZY preempt.
  sched/core: Prevent wakeup of ksoftirqd during idle load balance
  sched/fair: Check idle_cpu() before need_resched() to detect ilb CPU turning busy
  sched/core: Remove the unnecessary need_resched() check in nohz_csd_func()
  softirq: Allow raising SCHED_SOFTIRQ from SMP-call-function on RT kernel
  sched: fix warning in sched_setaffinity
  sched/deadline: Fix replenish_dl_new_period dl_server condition

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -4822,6 +4822,11 @@
 			       can be preempted anytime.  Tasks will also yield
 			       contended spinlocks (if the critical section isn't
 			       explicitly preempt disabled beyond the lock itself).
+			lazy - Scheduler controlled. Similar to full but instead
+			       of preempting the task immediately, the task gets
+			       one HZ tick time to yield itself before the
+			       preemption will be forced. One preemption is when the
+			       task returns to user space.
 
 	print-fatal-signals=
 			[KNL] debug: print fatal signals

kernel/locking/rtmutex.c

@@ -1248,10 +1248,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 
 		/* Check whether the waiter should back out immediately */
 		rtm = container_of(lock, struct rt_mutex, rtmutex);
-		preempt_disable();
 		res = __ww_mutex_add_waiter(waiter, rtm, ww_ctx, wake_q);
-		wake_up_q(wake_q);
-		preempt_enable();
 		if (res) {
 			raw_spin_lock(&task->pi_lock);
 			rt_mutex_dequeue(lock, waiter);

kernel/sched/core.c

@@ -1283,9 +1283,9 @@ static void nohz_csd_func(void *info)
 	WARN_ON(!(flags & NOHZ_KICK_MASK));
 
 	rq->idle_balance = idle_cpu(cpu);
-	if (rq->idle_balance && !need_resched()) {
+	if (rq->idle_balance) {
 		rq->nohz_idle_balance = flags;
-		raise_softirq_irqoff(SCHED_SOFTIRQ);
+		__raise_softirq_irqoff(SCHED_SOFTIRQ);
 	}
 }
 

kernel/sched/deadline.c

@@ -781,7 +781,7 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
 	 * If it is a deferred reservation, and the server
 	 * is not handling an starvation case, defer it.
 	 */
-	if (dl_se->dl_defer & !dl_se->dl_defer_running) {
+	if (dl_se->dl_defer && !dl_se->dl_defer_running) {
 		dl_se->dl_throttled = 1;
 		dl_se->dl_defer_armed = 1;
 	}
@@ -2042,6 +2042,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
+		   !is_dl_boosted(dl_se) &&
 		   dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) {
 		setup_new_dl_entity(dl_se);
 	}

kernel/sched/fair.c

@@ -12574,7 +12574,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
 		 * work being done for other CPUs. Next load
 		 * balancing owner will pick it up.
 		 */
-		if (need_resched()) {
+		if (!idle_cpu(this_cpu) && need_resched()) {
 			if (flags & NOHZ_STATS_KICK)
 				has_blocked_load = true;
 			if (flags & NOHZ_NEXT_KICK)

kernel/sched/syscalls.c

@@ -1200,7 +1200,7 @@ int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
 			bool empty = !cpumask_and(new_mask, new_mask,
 						  ctx->user_mask);
 
-			if (WARN_ON_ONCE(empty))
+			if (empty)
 				cpumask_copy(new_mask, cpus_allowed);
 		}
 		__set_cpus_allowed_ptr(p, ctx);

kernel/softirq.c

@@ -280,17 +280,24 @@ static inline void invoke_softirq(void)
 		wakeup_softirqd();
 }
 
+#define SCHED_SOFTIRQ_MASK	BIT(SCHED_SOFTIRQ)
+
 /*
  * flush_smp_call_function_queue() can raise a soft interrupt in a function
- * call. On RT kernels this is undesired and the only known functionality
- * in the block layer which does this is disabled on RT. If soft interrupts
- * get raised which haven't been raised before the flush, warn so it can be
+ * call. On RT kernels this is undesired and the only known functionalities
+ * are in the block layer which is disabled on RT, and in the scheduler for
+ * idle load balancing. If soft interrupts get raised which haven't been
+ * raised before the flush, warn if it is not a SCHED_SOFTIRQ so it can be
  * investigated.
  */
 void do_softirq_post_smp_call_flush(unsigned int was_pending)
 {
-	if (WARN_ON_ONCE(was_pending != local_softirq_pending()))
+	unsigned int is_pending = local_softirq_pending();
+
+	if (unlikely(was_pending != is_pending)) {
+		WARN_ON_ONCE(was_pending != (is_pending & ~SCHED_SOFTIRQ_MASK));
 		invoke_softirq();
+	}
 }
 
 #else /* CONFIG_PREEMPT_RT */