Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Implement frequency/CPU invariance and OPP selection for
     SCHED_DEADLINE (Juri Lelli)

   - Tweak the task migration logic for better multi-tasking
     workload scalability (Mel Gorman)

   - Misc cleanups, fixes and improvements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Make bandwidth enforcement scale-invariant
  sched/cpufreq: Move arch_scale_{freq,cpu}_capacity() outside of #ifdef CONFIG_SMP
  sched/cpufreq: Remove arch_scale_freq_capacity()'s 'sd' parameter
  sched/cpufreq: Always consider all CPUs when deciding next freq
  sched/cpufreq: Split utilization signals
  sched/cpufreq: Change the worker kthread to SCHED_DEADLINE
  sched/deadline: Move CPU frequency selection triggering points
  sched/cpufreq: Use the DEADLINE utilization signal
  sched/deadline: Implement "runtime overrun signal" support
  sched/fair: Only immediately migrate tasks due to interrupts if prev and target CPUs share cache
  sched/fair: Correct obsolete comment about cpufreq_update_util()
  sched/fair: Remove impossible condition from find_idlest_group_cpu()
  sched/cpufreq: Don't pass flags to sugov_set_iowait_boost()
  sched/cpufreq: Initialize sg_cpu->flags to 0
  sched/fair: Consider RT/IRQ pressure in capacity_spare_wake()
  sched/fair: Use 'unsigned long' for utilization, consistently
  sched/core: Rework and clarify prepare_lock_switch()
  sched/fair: Remove unused 'curr' parameter from wakeup_gran
  sched/headers: Constify object_is_on_stack()

Author: torvalds

include/linux/arch_topology.h

@@ -27,7 +27,7 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
 DECLARE_PER_CPU(unsigned long, freq_scale);
 
 static inline
-unsigned long topology_get_freq_scale(struct sched_domain *sd, int cpu)
+unsigned long topology_get_freq_scale(int cpu)
 {
 	return per_cpu(freq_scale, cpu);
 }

include/linux/sched.h

@@ -472,11 +472,15 @@ struct sched_dl_entity {
 	 * has not been executed yet. This flag is useful to avoid race
 	 * conditions between the inactive timer handler and the wakeup
 	 * code.
+	 *
+	 * @dl_overrun tells if the task asked to be informed about runtime
+	 * overruns.
 	 */
 	unsigned int			dl_throttled      : 1;
 	unsigned int			dl_boosted        : 1;
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
+	unsigned int			dl_overrun	  : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -1427,6 +1431,7 @@ extern int idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);
+extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *);
 extern struct task_struct *idle_task(int cpu);
 
 /**

include/linux/sched/cpufreq.h

@@ -12,8 +12,6 @@
 #define SCHED_CPUFREQ_DL	(1U << 1)
 #define SCHED_CPUFREQ_IOWAIT	(1U << 2)
 
-#define SCHED_CPUFREQ_RT_DL	(SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL)
-
 #ifdef CONFIG_CPU_FREQ
 struct update_util_data {
        void (*func)(struct update_util_data *data, u64 time, unsigned int flags);

include/linux/sched/task_stack.h

@@ -78,7 +78,7 @@ static inline void put_task_stack(struct task_struct *tsk) {}
 #define task_stack_end_corrupted(task) \
 		(*(end_of_stack(task)) != STACK_END_MAGIC)
 
-static inline int object_is_on_stack(void *obj)
+static inline int object_is_on_stack(const void *obj)
 {
 	void *stack = task_stack_page(current);
 

include/linux/sched/topology.h

@@ -6,6 +6,12 @@
 
 #include <linux/sched/idle.h>
 
+/*
+ * Increase resolution of cpu_capacity calculations
+ */
+#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
+#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
+
 /*
  * sched-domains (multiprocessor balancing) declarations:
  */
@@ -27,12 +33,6 @@
 #define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
 #define SD_NUMA			0x4000	/* cross-node balancing */
 
-/*
- * Increase resolution of cpu_capacity calculations
- */
-#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
-#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
-
 #ifdef CONFIG_SCHED_SMT
 static inline int cpu_smt_flags(void)
 {

include/uapi/linux/sched.h

@@ -49,5 +49,10 @@
  */
 #define SCHED_FLAG_RESET_ON_FORK	0x01
 #define SCHED_FLAG_RECLAIM		0x02
+#define SCHED_FLAG_DL_OVERRUN		0x04
+
+#define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
+			 SCHED_FLAG_RECLAIM		| \
+			 SCHED_FLAG_DL_OVERRUN)
 
 #endif /* _UAPI_LINUX_SCHED_H */

kernel/sched/core.c

@@ -2046,7 +2046,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * If the owning (remote) CPU is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
 	 *
-	 * Pairs with the smp_store_release() in finish_lock_switch().
+	 * Pairs with the smp_store_release() in finish_task().
 	 *
 	 * This ensures that tasks getting woken will be fully ordered against
 	 * their previous state and preserve Program Order.
@@ -2572,6 +2572,50 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 
 #endif /* CONFIG_PREEMPT_NOTIFIERS */
 
+static inline void prepare_task(struct task_struct *next)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Claim the task as running, we do this before switching to it
+	 * such that any running task will have this set.
+	 */
+	next->on_cpu = 1;
+#endif
+}
+
+static inline void finish_task(struct task_struct *prev)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
+	 * We must ensure this doesn't happen until the switch is completely
+	 * finished.
+	 *
+	 * In particular, the load of prev->state in finish_task_switch() must
+	 * happen before this.
+	 *
+	 * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
+	 */
+	smp_store_release(&prev->on_cpu, 0);
+#endif
+}
+
+static inline void finish_lock_switch(struct rq *rq)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/* this is a valid case when another task releases the spinlock */
+	rq->lock.owner = current;
+#endif
+	/*
+	 * If we are tracking spinlock dependencies then we have to
+	 * fix up the runqueue lock - which gets 'carried over' from
+	 * prev into current:
+	 */
+	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+
+	raw_spin_unlock_irq(&rq->lock);
+}
+
 /**
  * prepare_task_switch - prepare to switch tasks
  * @rq: the runqueue preparing to switch
@@ -2592,7 +2636,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 	sched_info_switch(rq, prev, next);
 	perf_event_task_sched_out(prev, next);
 	fire_sched_out_preempt_notifiers(prev, next);
-	prepare_lock_switch(rq, next);
+	prepare_task(next);
 	prepare_arch_switch(next);
 }
 
@@ -2647,7 +2691,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * the scheduled task must drop that reference.
 	 *
 	 * We must observe prev->state before clearing prev->on_cpu (in
-	 * finish_lock_switch), otherwise a concurrent wakeup can get prev
+	 * finish_task), otherwise a concurrent wakeup can get prev
 	 * running on another CPU and we could rave with its RUNNING -> DEAD
 	 * transition, resulting in a double drop.
 	 */
@@ -2664,7 +2708,8 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * to use.
 	 */
 	smp_mb__after_unlock_lock();
-	finish_lock_switch(rq, prev);
+	finish_task(prev);
+	finish_lock_switch(rq);
 	finish_arch_post_lock_switch();
 
 	fire_sched_in_preempt_notifiers(current);
@@ -4041,8 +4086,7 @@ static int __sched_setscheduler(struct task_struct *p,
 			return -EINVAL;
 	}
 
-	if (attr->sched_flags &
-		~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM))
+	if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV))
 		return -EINVAL;
 
 	/*
@@ -4109,6 +4153,9 @@ static int __sched_setscheduler(struct task_struct *p,
 	}
 
 	if (user) {
+		if (attr->sched_flags & SCHED_FLAG_SUGOV)
+			return -EINVAL;
+
 		retval = security_task_setscheduler(p);
 		if (retval)
 			return retval;
@@ -4164,7 +4211,8 @@ static int __sched_setscheduler(struct task_struct *p,
 		}
 #endif
 #ifdef CONFIG_SMP
-		if (dl_bandwidth_enabled() && dl_policy(policy)) {
+		if (dl_bandwidth_enabled() && dl_policy(policy) &&
+				!(attr->sched_flags & SCHED_FLAG_SUGOV)) {
 			cpumask_t *span = rq->rd->span;
 
 			/*
@@ -4294,6 +4342,11 @@ int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
 }
 EXPORT_SYMBOL_GPL(sched_setattr);
 
+int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
+{
+	return __sched_setscheduler(p, attr, false, true);
+}
+
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
  * @p: the task in question.