1 files changed, 76 insertions, 22 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 75554f366fd3..3da7a2444a91 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -508,7 +508,8 @@ void resched_cpu(int cpu)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
-	resched_curr(rq);
+	if (cpu_online(cpu) || cpu == smp_processor_id())
+		resched_curr(rq);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
@@ -2045,7 +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.
@@ -2056,7 +2057,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	p->state = TASK_WAKING;
 
 	if (p->in_iowait) {
-		delayacct_blkio_end();
+		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
 	}
 
@@ -2069,7 +2070,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 #else /* CONFIG_SMP */
 
 	if (p->in_iowait) {
-		delayacct_blkio_end();
+		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
 	}
 
@@ -2122,7 +2123,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 
 	if (!task_on_rq_queued(p)) {
 		if (p->in_iowait) {
-			delayacct_blkio_end();
+			delayacct_blkio_end(p);
 			atomic_dec(&rq->nr_iowait);
 		}
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
@@ -2571,6 +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
@@ -2591,7 +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);
 }
 
@@ -2646,7 +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.
 	 */
@@ -2663,7 +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);
@@ -4040,8 +4086,7 @@ recheck:
 			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;
 
 	/*
@@ -4108,6 +4153,9 @@ recheck:
 	}
 
 	if (user) {
+		if (attr->sched_flags & SCHED_FLAG_SUGOV)
+			return -EINVAL;
+
 		retval = security_task_setscheduler(p);
 		if (retval)
 			return retval;
@@ -4163,7 +4211,8 @@ change:
 		}
 #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;
 
 			/*
@@ -4293,6 +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.
@@ -5097,17 +5151,6 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 	return ret;
 }
 
-/**
- * sys_sched_rr_get_interval - return the default timeslice of a process.
- * @pid: pid of the process.
- * @interval: userspace pointer to the timeslice value.
- *
- * this syscall writes the default timeslice value of a given process
- * into the user-space timespec buffer. A value of '0' means infinity.
- *
- * Return: On success, 0 and the timeslice is in @interval. Otherwise,
- * an error code.
- */
 static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
 {
 	struct task_struct *p;
@@ -5144,6 +5187,17 @@ out_unlock:
 	return retval;
 }
 
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ *
+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
+ * an error code.
+ */
 SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 		struct timespec __user *, interval)
 {