1 files changed, 77 insertions, 67 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3e5a6bf587f91..9aecd914ac691 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -740,39 +740,43 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 	s64 __maybe_unused steal = 0, irq_delta = 0;
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
-	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+	if (irqtime_enabled()) {
+		irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
 
-	/*
-	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
-	 * this case when a previous update_rq_clock() happened inside a
-	 * {soft,}IRQ region.
-	 *
-	 * When this happens, we stop ->clock_task and only update the
-	 * prev_irq_time stamp to account for the part that fit, so that a next
-	 * update will consume the rest. This ensures ->clock_task is
-	 * monotonic.
-	 *
-	 * It does however cause some slight miss-attribution of {soft,}IRQ
-	 * time, a more accurate solution would be to update the irq_time using
-	 * the current rq->clock timestamp, except that would require using
-	 * atomic ops.
-	 */
-	if (irq_delta > delta)
-		irq_delta = delta;
+		/*
+		 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+		 * this case when a previous update_rq_clock() happened inside a
+		 * {soft,}IRQ region.
+		 *
+		 * When this happens, we stop ->clock_task and only update the
+		 * prev_irq_time stamp to account for the part that fit, so that a next
+		 * update will consume the rest. This ensures ->clock_task is
+		 * monotonic.
+		 *
+		 * It does however cause some slight miss-attribution of {soft,}IRQ
+		 * time, a more accurate solution would be to update the irq_time using
+		 * the current rq->clock timestamp, except that would require using
+		 * atomic ops.
+		 */
+		if (irq_delta > delta)
+			irq_delta = delta;
 
-	rq->prev_irq_time += irq_delta;
-	delta -= irq_delta;
-	delayacct_irq(rq->curr, irq_delta);
+		rq->prev_irq_time += irq_delta;
+		delta -= irq_delta;
+		delayacct_irq(rq->curr, irq_delta);
+	}
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 	if (static_key_false((&paravirt_steal_rq_enabled))) {
-		steal = paravirt_steal_clock(cpu_of(rq));
+		u64 prev_steal;
+
+		steal = prev_steal = paravirt_steal_clock(cpu_of(rq));
 		steal -= rq->prev_steal_time_rq;
 
 		if (unlikely(steal > delta))
 			steal = delta;
 
-		rq->prev_steal_time_rq += steal;
+		rq->prev_steal_time_rq = prev_steal;
 		delta -= steal;
 	}
 #endif
@@ -789,6 +793,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 void update_rq_clock(struct rq *rq)
 {
 	s64 delta;
+	u64 clock;
 
 	lockdep_assert_rq_held(rq);
 
@@ -800,11 +805,14 @@ void update_rq_clock(struct rq *rq)
 		SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
 	rq->clock_update_flags |= RQCF_UPDATED;
 #endif
+	clock = sched_clock_cpu(cpu_of(rq));
+	scx_rq_clock_update(rq, clock);
 
-	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	delta = clock - rq->clock;
 	if (delta < 0)
 		return;
 	rq->clock += delta;
+
 	update_rq_clock_task(rq, delta);
 }
 
@@ -1055,9 +1063,10 @@ void wake_up_q(struct wake_q_head *head)
 		struct task_struct *task;
 
 		task = container_of(node, struct task_struct, wake_q);
-		/* Task can safely be re-inserted now: */
 		node = node->next;
-		task->wake_q.next = NULL;
+		/* pairs with cmpxchg_relaxed() in __wake_q_add() */
+		WRITE_ONCE(task->wake_q.next, NULL);
+		/* Task can safely be re-inserted now. */
 
 		/*
 		 * wake_up_process() executes a full barrier, which pairs with
@@ -1168,13 +1177,13 @@ int get_nohz_timer_target(void)
 	struct sched_domain *sd;
 	const struct cpumask *hk_mask;
 
-	if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
+	if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) {
 		if (!idle_cpu(cpu))
 			return cpu;
 		default_cpu = cpu;
 	}
 
-	hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
+	hk_mask = housekeeping_cpumask(HK_TYPE_KERNEL_NOISE);
 
 	guard(rcu)();
 
@@ -1189,7 +1198,7 @@ int get_nohz_timer_target(void)
 	}
 
 	if (default_cpu == -1)
-		default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
+		default_cpu = housekeeping_any_cpu(HK_TYPE_KERNEL_NOISE);
 
 	return default_cpu;
 }
@@ -1341,7 +1350,7 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (scx_enabled() && !scx_can_stop_tick(rq))
 		return false;
 
-	if (rq->cfs.h_nr_running > 1)
+	if (rq->cfs.h_nr_queued > 1)
 		return false;
 
 	/*
@@ -3534,7 +3543,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			 *
 			 * More yuck to audit.
 			 */
-			do_set_cpus_allowed(p, task_cpu_possible_mask(p));
+			do_set_cpus_allowed(p, task_cpu_fallback_mask(p));
 			state = fail;
 			break;
 		case fail:
@@ -4646,7 +4655,7 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf
 #endif /* CONFIG_SCHEDSTATS */
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_core_sysctls[] = {
+static const struct ctl_table sched_core_sysctls[] = {
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname       = "sched_schedstats",
@@ -5632,7 +5641,7 @@ void sched_tick(void)
 	unsigned long hw_pressure;
 	u64 resched_latency;
 
-	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
 		arch_scale_freq_tick();
 
 	sched_clock_tick();
@@ -5771,7 +5780,7 @@ static void sched_tick_start(int cpu)
 	int os;
 	struct tick_work *twork;
 
-	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
 		return;
 
 	WARN_ON_ONCE(!tick_work_cpu);
@@ -5792,7 +5801,7 @@ static void sched_tick_stop(int cpu)
 	struct tick_work *twork;
 	int os;
 
-	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
 		return;
 
 	WARN_ON_ONCE(!tick_work_cpu);
@@ -6018,7 +6027,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * opportunity to pull in more work from other CPUs.
 	 */
 	if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) &&
-		   rq->nr_running == rq->cfs.h_nr_running)) {
+		   rq->nr_running == rq->cfs.h_nr_queued)) {
 
 		p = pick_next_task_fair(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
@@ -6641,7 +6650,6 @@ static void __sched notrace __schedule(int sched_mode)
 	 * as a preemption by schedule_debug() and RCU.
 	 */
 	bool preempt = sched_mode > SM_NONE;
-	bool block = false;
 	unsigned long *switch_count;
 	unsigned long prev_state;
 	struct rq_flags rf;
@@ -6702,7 +6710,7 @@ static void __sched notrace __schedule(int sched_mode)
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
-		block = try_to_block_task(rq, prev, prev_state);
+		try_to_block_task(rq, prev, prev_state);
 		switch_count = &prev->nvcsw;
 	}
 
@@ -6748,7 +6756,8 @@ picked:
 
 		migrate_disable_switch(rq, prev);
 		psi_account_irqtime(rq, prev, next);
-		psi_sched_switch(prev, next, block);
+		psi_sched_switch(prev, next, !task_on_rq_queued(prev) ||
+					     prev->se.sched_delayed);
 
 		trace_sched_switch(preempt, prev, next, prev_state);
 
@@ -7701,9 +7710,9 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
+	pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d task_flags:0x%04x flags:0x%08lx\n",
 		free, task_pid_nr(p), task_tgid_nr(p),
-		ppid, read_task_thread_flags(p));
+		ppid, p->flags, read_task_thread_flags(p));
 
 	print_worker_info(KERN_INFO, p);
 	print_stop_info(KERN_INFO, p);
@@ -7930,19 +7939,26 @@ void sched_setnuma(struct task_struct *p, int nid)
 
 #ifdef CONFIG_HOTPLUG_CPU
 /*
- * Ensure that the idle task is using init_mm right before its CPU goes
- * offline.
+ * Invoked on the outgoing CPU in context of the CPU hotplug thread
+ * after ensuring that there are no user space tasks left on the CPU.
+ *
+ * If there is a lazy mm in use on the hotplug thread, drop it and
+ * switch to init_mm.
+ *
+ * The reference count on init_mm is dropped in finish_cpu().
  */
-void idle_task_exit(void)
+static void sched_force_init_mm(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	BUG_ON(cpu_online(smp_processor_id()));
-	BUG_ON(current != this_rq()->idle);
-
 	if (mm != &init_mm) {
-		switch_mm(mm, &init_mm, current);
+		mmgrab_lazy_tlb(&init_mm);
+		local_irq_disable();
+		current->active_mm = &init_mm;
+		switch_mm_irqs_off(mm, &init_mm, current);
+		local_irq_enable();
 		finish_arch_post_lock_switch();
+		mmdrop_lazy_tlb(mm);
 	}
 
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
@@ -8180,19 +8196,14 @@ static void cpuset_cpu_active(void)
 	cpuset_update_active_cpus();
 }
 
-static int cpuset_cpu_inactive(unsigned int cpu)
+static void cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		int ret = dl_bw_check_overflow(cpu);
-
-		if (ret)
-			return ret;
 		cpuset_update_active_cpus();
 	} else {
 		num_cpus_frozen++;
 		partition_sched_domains(1, NULL, NULL);
 	}
-	return 0;
 }
 
 static inline void sched_smt_present_inc(int cpu)
@@ -8254,6 +8265,11 @@ int sched_cpu_deactivate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	int ret;
 
+	ret = dl_bw_deactivate(cpu);
+
+	if (ret)
+		return ret;
+
 	/*
 	 * Remove CPU from nohz.idle_cpus_mask to prevent participating in
 	 * load balancing when not active
@@ -8299,15 +8315,7 @@ int sched_cpu_deactivate(unsigned int cpu)
 		return 0;
 
 	sched_update_numa(cpu, false);
-	ret = cpuset_cpu_inactive(cpu);
-	if (ret) {
-		sched_smt_present_inc(cpu);
-		sched_set_rq_online(rq, cpu);
-		balance_push_set(cpu, false);
-		set_cpu_active(cpu, true);
-		sched_update_numa(cpu, true);
-		return ret;
-	}
+	cpuset_cpu_inactive(cpu);
 	sched_domains_numa_masks_clear(cpu);
 	return 0;
 }
@@ -8344,6 +8352,7 @@ int sched_cpu_starting(unsigned int cpu)
 int sched_cpu_wait_empty(unsigned int cpu)
 {
 	balance_hotplug_wait();
+	sched_force_init_mm();
 	return 0;
 }
 
@@ -9042,7 +9051,7 @@ static void sched_change_group(struct task_struct *tsk, struct task_group *group
  * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
  * its new group.
  */
-void sched_move_task(struct task_struct *tsk)
+void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 {
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
@@ -9071,7 +9080,8 @@ void sched_move_task(struct task_struct *tsk)
 		put_prev_task(rq, tsk);
 
 	sched_change_group(tsk, group);
-	scx_move_task(tsk);
+	if (!for_autogroup)
+		scx_cgroup_move_task(tsk);
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
@@ -9172,7 +9182,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 	struct cgroup_subsys_state *css;
 
 	cgroup_taskset_for_each(task, css, tset)
-		sched_move_task(task);
+		sched_move_task(task, false);
 
 	scx_cgroup_finish_attach();
 }
@@ -10590,7 +10600,7 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
 		return;
 
 	/* No page allocation under rq lock */
-	task_work_add(curr, work, TWA_RESUME | TWAF_NO_ALLOC);
+	task_work_add(curr, work, TWA_RESUME);
 }
 
 void sched_mm_cid_exit_signals(struct task_struct *t)