1 files changed, 63 insertions, 174 deletions

diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index ae1b42775ef9..77ae87f36e84 100644
--- a/kernel/sched/syscalls.c
+++ b/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 (!rt_or_dl_prio(p->prio))
 		return p->normal_prio;
 	return p->prio;
 }
@@ -91,7 +91,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	}
 
 	queued = task_on_rq_queued(p);
-	running = task_current(rq, p);
+	running = task_current_donor(rq, p);
 	if (queued)
 		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	if (running)
@@ -174,7 +174,7 @@ SYSCALL_DEFINE1(nice, int, increment)
 	return 0;
 }
 
-#endif
+#endif /* __ARCH_WANT_SYS_NICE */
 
 /**
  * task_prio - return the priority value of a given task.
@@ -209,10 +209,8 @@ int idle_cpu(int cpu)
 	if (rq->nr_running)
 		return 0;
 
-#ifdef CONFIG_SMP
 	if (rq->ttwu_pending)
 		return 0;
-#endif
 
 	return 1;
 }
@@ -255,109 +253,7 @@ int sched_core_idle_cpu(int cpu)
 
 	return idle_cpu(cpu);
 }
-
-#endif
-
-#ifdef CONFIG_SMP
-/*
- * 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 */
+#endif /* CONFIG_SCHED_CORE */
 
 /**
  * find_process_by_pid - find a process with a matching PID value.
@@ -404,7 +300,15 @@ static void __setscheduler_params(struct task_struct *p,
 	if (dl_policy(policy))
 		__setparam_dl(p, attr);
 	else if (fair_policy(policy))
-		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+		__setparam_fair(p, attr);
+
+	/* rt-policy tasks do not have a timerslack */
+	if (rt_or_dl_task_policy(p)) {
+		p->timer_slack_ns = 0;
+	} else if (p->timer_slack_ns == 0) {
+		/* when switching back to non-rt policy, restore timerslack */
+		p->timer_slack_ns = p->default_timer_slack_ns;
+	}
 
 	/*
 	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
@@ -461,7 +365,7 @@ static int uclamp_validate(struct task_struct *p,
 	 * blocking operation which obviously cannot be done while holding
 	 * scheduler locks.
 	 */
-	static_branch_enable(&sched_uclamp_used);
+	sched_uclamp_enable();
 
 	return 0;
 }
@@ -541,7 +445,7 @@ static inline int uclamp_validate(struct task_struct *p,
 }
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr) { }
-#endif
+#endif /* !CONFIG_UCLAMP_TASK */
 
 /*
  * Allow unprivileged RT tasks to decrease priority.
@@ -612,7 +516,7 @@ int __sched_setscheduler(struct task_struct *p,
 {
 	int oldpolicy = -1, policy = attr->sched_policy;
 	int retval, oldprio, newprio, queued, running;
-	const struct sched_class *prev_class;
+	const struct sched_class *prev_class, *next_class;
 	struct balance_callback *head;
 	struct rq_flags rf;
 	int reset_on_fork;
@@ -695,12 +599,18 @@ recheck:
 		goto unlock;
 	}
 
+	retval = scx_check_setscheduler(p, policy);
+	if (retval)
+		goto unlock;
+
 	/*
 	 * If not changing anything there's no need to proceed further,
 	 * but store a possible modification of reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy)) {
-		if (fair_policy(policy) && attr->sched_nice != task_nice(p))
+		if (fair_policy(policy) &&
+		    (attr->sched_nice != task_nice(p) ||
+		     (attr->sched_runtime != p->se.slice)))
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
@@ -721,14 +631,14 @@ change:
 		 * Do not allow real-time tasks into groups that have no runtime
 		 * assigned.
 		 */
-		if (rt_bandwidth_enabled() && rt_policy(policy) &&
+		if (rt_group_sched_enabled() &&
+				rt_bandwidth_enabled() && rt_policy(policy) &&
 				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
 				!task_group_is_autogroup(task_group(p))) {
 			retval = -EPERM;
 			goto unlock;
 		}
-#endif
-#ifdef CONFIG_SMP
+#endif /* CONFIG_RT_GROUP_SCHED */
 		if (dl_bandwidth_enabled() && dl_policy(policy) &&
 				!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
 			cpumask_t *span = rq->rd->span;
@@ -744,7 +654,6 @@ change:
 				goto unlock;
 			}
 		}
-#endif
 	}
 
 	/* Re-check policy now with rq lock held: */
@@ -783,20 +692,26 @@ change:
 			queue_flags &= ~DEQUEUE_MOVE;
 	}
 
+	prev_class = p->sched_class;
+	next_class = __setscheduler_class(policy, newprio);
+
+	if (prev_class != next_class && p->se.sched_delayed)
+		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
+
 	queued = task_on_rq_queued(p);
-	running = task_current(rq, p);
+	running = task_current_donor(rq, p);
 	if (queued)
 		dequeue_task(rq, p, queue_flags);
 	if (running)
 		put_prev_task(rq, p);
 
-	prev_class = p->sched_class;
-
 	if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
 		__setscheduler_params(p, attr);
-		__setscheduler_prio(p, newprio);
+		p->sched_class = next_class;
+		p->prio = newprio;
 	}
 	__setscheduler_uclamp(p, attr);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued) {
 		/*
@@ -846,6 +761,9 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 
+	if (p->se.custom_slice)
+		attr.sched_runtime = p->se.slice;
+
 	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
 	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
@@ -953,7 +871,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	struct sched_param lparam;
 
-	if (!param || pid < 0)
+	if (unlikely(!param || pid < 0))
 		return -EINVAL;
 	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
 		return -EFAULT;
@@ -1012,12 +930,14 @@ err_size:
 
 static void get_params(struct task_struct *p, struct sched_attr *attr)
 {
-	if (task_has_dl_policy(p))
+	if (task_has_dl_policy(p)) {
 		__getparam_dl(p, attr);
-	else if (task_has_rt_policy(p))
+	} else if (task_has_rt_policy(p)) {
 		attr->sched_priority = p->rt_priority;
-	else
+	} else {
 		attr->sched_nice = task_nice(p);
+		attr->sched_runtime = p->se.slice;
+	}
 }
 
 /**
@@ -1060,7 +980,7 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	struct sched_attr attr;
 	int retval;
 
-	if (!uattr || pid < 0 || flags)
+	if (unlikely(!uattr || pid < 0 || flags))
 		return -EINVAL;
 
 	retval = sched_copy_attr(uattr, &attr);
@@ -1125,7 +1045,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	struct task_struct *p;
 	int retval;
 
-	if (!param || pid < 0)
+	if (unlikely(!param || pid < 0))
 		return -EINVAL;
 
 	scoped_guard (rcu) {
@@ -1147,45 +1067,6 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
 }
 
-/*
- * Copy the kernel size attribute structure (which might be larger
- * than what user-space knows about) to user-space.
- *
- * Note that all cases are valid: user-space buffer can be larger or
- * smaller than the kernel-space buffer. The usual case is that both
- * have the same size.
- */
-static int
-sched_attr_copy_to_user(struct sched_attr __user *uattr,
-			struct sched_attr *kattr,
-			unsigned int usize)
-{
-	unsigned int ksize = sizeof(*kattr);
-
-	if (!access_ok(uattr, usize))
-		return -EFAULT;
-
-	/*
-	 * sched_getattr() ABI forwards and backwards compatibility:
-	 *
-	 * If usize == ksize then we just copy everything to user-space and all is good.
-	 *
-	 * If usize < ksize then we only copy as much as user-space has space for,
-	 * this keeps ABI compatibility as well. We skip the rest.
-	 *
-	 * If usize > ksize then user-space is using a newer version of the ABI,
-	 * which part the kernel doesn't know about. Just ignore it - tooling can
-	 * detect the kernel's knowledge of attributes from the attr->size value
-	 * which is set to ksize in this case.
-	 */
-	kattr->size = min(usize, ksize);
-
-	if (copy_to_user(uattr, kattr, kattr->size))
-		return -EFAULT;
-
-	return 0;
-}
-
 /**
  * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
@@ -1200,8 +1081,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0 || usize > PAGE_SIZE ||
-	    usize < SCHED_ATTR_SIZE_VER0 || flags)
+	if (unlikely(!uattr || pid < 0 || usize > PAGE_SIZE ||
+		      usize < SCHED_ATTR_SIZE_VER0 || flags))
 		return -EINVAL;
 
 	scoped_guard (rcu) {
@@ -1230,10 +1111,10 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 #endif
 	}
 
-	return sched_attr_copy_to_user(uattr, &kattr, usize);
+	kattr.size = min(usize, sizeof(kattr));
+	return copy_struct_to_user(uattr, usize, &kattr, sizeof(kattr), NULL);
 }
 
-#ifdef CONFIG_SMP
 int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 {
 	/*
@@ -1244,6 +1125,13 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 		return 0;
 
 	/*
+	 * The special/sugov task isn't part of regular bandwidth/admission
+	 * control so let userspace change affinities.
+	 */
+	if (dl_entity_is_special(&p->dl))
+		return 0;
+
+	/*
 	 * Since bandwidth control happens on root_domain basis,
 	 * if admission test is enabled, we only admit -deadline
 	 * tasks allowed to run on all the CPUs in the task's
@@ -1255,7 +1143,6 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 
 	return 0;
 }
-#endif /* CONFIG_SMP */
 
 int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
 {
@@ -1304,7 +1191,7 @@ 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);
@@ -1348,7 +1235,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
 	if (user_mask) {
 		cpumask_copy(user_mask, in_mask);
-	} else if (IS_ENABLED(CONFIG_SMP)) {
+	} else {
 		return -ENOMEM;
 	}
 
@@ -1537,7 +1424,7 @@ int __sched yield_to(struct task_struct *p, bool preempt)
 	struct rq *rq, *p_rq;
 	int yielded = 0;
 
-	scoped_guard (irqsave) {
+	scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
 		rq = this_rq();
 
 again:
@@ -1602,6 +1489,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
+	case SCHED_EXT:
 		ret = 0;
 		break;
 	}
@@ -1629,6 +1517,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
+	case SCHED_EXT:
 		ret = 0;
 	}
 	return ret;