Merge branch 'sched/urgent' into sched/core

Pick up fixes before queueing up new changes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 53 insertions, 33 deletions

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 43c2bcc35761..b30a2924ef14 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu)
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
-	preempt_disable();
+	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return clock;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cde573d3f12e..dd89c27bb56f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1954,7 +1954,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 {
 
 	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	u64 period = attr->sched_period;
+	u64 period = attr->sched_period ?: attr->sched_deadline;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
 	int cpus, err = -1;
@@ -3328,6 +3328,15 @@ recheck:
 				return -EPERM;
 		}
 
+		 /*
+		  * Can't set/change SCHED_DEADLINE policy at all for now
+		  * (safest behavior); in the future we would like to allow
+		  * unprivileged DL tasks to increase their relative deadline
+		  * or reduce their runtime (both ways reducing utilization)
+		  */
+		if (dl_policy(policy))
+			return -EPERM;
+
 		/*
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
@@ -3673,13 +3682,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  */
-SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
+			       unsigned int, flags)
 {
 	struct sched_attr attr;
 	struct task_struct *p;
 	int retval;
 
-	if (!uattr || pid < 0)
+	if (!uattr || pid < 0 || flags)
 		return -EINVAL;
 
 	if (sched_copy_attr(uattr, &attr))
@@ -3798,7 +3808,7 @@ static int sched_read_attr(struct sched_attr __user *uattr,
 		attr->size = usize;
 	}
 
-	ret = copy_to_user(uattr, attr, usize);
+	ret = copy_to_user(uattr, attr, attr->size);
 	if (ret)
 		return -EFAULT;
 
@@ -3816,8 +3826,8 @@ err_size:
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
  */
-SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-		unsigned int, size)
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+		unsigned int, size, unsigned int, flags)
 {
 	struct sched_attr attr = {
 		.size = sizeof(struct sched_attr),
@@ -3826,7 +3836,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	int retval;
 
 	if (!uattr || pid < 0 || size > PAGE_SIZE ||
-	    size < SCHED_ATTR_SIZE_VER0)
+	    size < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
 	rcu_read_lock();
@@ -7461,6 +7471,7 @@ static int sched_dl_global_constraints(void)
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
 	int cpu, ret = 0;
+	unsigned long flags;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
@@ -7474,10 +7485,10 @@ static int sched_dl_global_constraints(void)
 	for_each_possible_cpu(cpu) {
 		struct dl_bw *dl_b = dl_bw_of(cpu);
 
-		raw_spin_lock(&dl_b->lock);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		if (new_bw < dl_b->total_bw)
 			ret = -EBUSY;
-		raw_spin_unlock(&dl_b->lock);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
 		if (ret)
 			break;
@@ -7490,6 +7501,7 @@ static void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
 	int cpu;
+	unsigned long flags;
 
 	def_dl_bandwidth.dl_period = global_rt_period();
 	def_dl_bandwidth.dl_runtime = global_rt_runtime();
@@ -7503,9 +7515,9 @@ static void sched_dl_do_global(void)
 	for_each_possible_cpu(cpu) {
 		struct dl_bw *dl_b = dl_bw_of(cpu);
 
-		raw_spin_lock(&dl_b->lock);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		dl_b->bw = new_bw;
-		raw_spin_unlock(&dl_b->lock);
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	}
 }
 
@@ -7514,7 +7526,8 @@ static int sched_rt_global_validate(void)
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
-	if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 045fc74e3f09..5b9bb42b2d47 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx)
 
 static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
-	WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
 
 	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
 		cp->elements[idx].dl = new_dl;
@@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	}
 
 out:
-	WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
 	return best_cpu;
 }
@@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
 	int old_idx, new_cpu;
 	unsigned long flags;
 
-	WARN_ON(cpu > num_present_cpus());
+	WARN_ON(!cpu_present(cpu));
 
 	raw_spin_lock_irqsave(&cp->lock, flags);
 	old_idx = cp->cpu_to_idx[cpu];
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3185b775dbf7..e4f3ac3b8514 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq)
 
 static void update_dl_migration(struct dl_rq *dl_rq)
 {
-	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
 		if (!dl_rq->overloaded) {
 			dl_set_overload(rq_of_dl_rq(dl_rq));
 			dl_rq->overloaded = 1;
@@ -135,9 +135,7 @@ static void update_dl_migration(struct dl_rq *dl_rq)
 static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
-	dl_rq->dl_nr_total++;
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory++;
 
@@ -147,9 +145,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	struct task_struct *p = dl_task_of(dl_se);
-	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
 
-	dl_rq->dl_nr_total--;
 	if (p->nr_cpus_allowed > 1)
 		dl_rq->dl_nr_migratory--;
 
@@ -589,6 +585,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 	return 1;
 }
 
+extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
+
 /*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
@@ -652,11 +650,13 @@ static void update_curr_dl(struct rq *rq)
 		struct rt_rq *rt_rq = &rq->rt;
 
 		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_time += delta_exec;
 		/*
 		 * We'll let actual RT tasks worry about the overflow here, we
-		 * have our own CBS to keep us inline -- see above.
+		 * have our own CBS to keep us inline; only account when RT
+		 * bandwidth is relevant.
 		 */
+		if (sched_rt_bandwidth_account(rt_rq))
+			rt_rq->rt_time += delta_exec;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 }
@@ -740,6 +740,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 
 	WARN_ON(!dl_prio(prio));
 	dl_rq->dl_nr_running++;
+	inc_nr_running(rq_of_dl_rq(dl_rq));
 
 	inc_dl_deadline(dl_rq, deadline);
 	inc_dl_migration(dl_se, dl_rq);
@@ -753,6 +754,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	WARN_ON(!dl_prio(prio));
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
+	dec_nr_running(rq_of_dl_rq(dl_rq));
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 	dec_dl_migration(dl_se, dl_rq);
@@ -859,8 +861,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
-
-	inc_nr_running(rq);
 }
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -873,8 +873,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
 	__dequeue_task_dl(rq, p, flags);
-
-	dec_nr_running(rq);
 }
 
 /*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 16042b58a32f..d8482e1c575e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1914,6 +1914,8 @@ void task_numa_work(struct callback_head *work)
 			start = end;
 			if (pages <= 0)
 				goto out;
+
+			cond_resched();
 		} while (end != vma->vm_end);
 	}
 
@@ -7316,15 +7318,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	/*
-	 * Ensure the task's vruntime is normalized, so that when its
+	 * Ensure the task's vruntime is normalized, so that when it's
 	 * switched back to the fair class the enqueue_entity(.flags=0) will
 	 * do the right thing.
 	 *
-	 * If it was on_rq, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it was !on_rq, then only when
+	 * If it's on_rq, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it's !on_rq, then only when
 	 * the task is sleeping will it still have non-normalized vruntime.
 	 */
-	if (!se->on_rq && p->state != TASK_RUNNING) {
+	if (!p->on_rq && p->state != TASK_RUNNING) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 398b3f990823..facc824334fb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -568,6 +568,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+bool sched_rt_bandwidth_account(struct rt_rq *rt_rq)
+{
+	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+	return (hrtimer_active(&rt_b->rt_period_timer) ||
+		rt_rq->rt_time < rt_b->rt_runtime);
+}
+
 #ifdef CONFIG_SMP
 /*
  * We ran out of runtime, see if we can borrow some from our neighbours.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1929deb3f29d..378bff76267f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -444,7 +444,6 @@ struct dl_rq {
 	} earliest_dl;
 
 	unsigned long dl_nr_migratory;
-	unsigned long dl_nr_total;
 	int overloaded;
 
 	/*