1 files changed, 107 insertions, 39 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a7bf32aabfda..bf724c1952ea 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);
 }
 
@@ -1629,16 +1630,16 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 
 #ifdef CONFIG_SMP
 	if (cpu == rq->cpu) {
-		schedstat_inc(rq->ttwu_local);
-		schedstat_inc(p->se.statistics.nr_wakeups_local);
+		__schedstat_inc(rq->ttwu_local);
+		__schedstat_inc(p->se.statistics.nr_wakeups_local);
 	} else {
 		struct sched_domain *sd;
 
-		schedstat_inc(p->se.statistics.nr_wakeups_remote);
+		__schedstat_inc(p->se.statistics.nr_wakeups_remote);
 		rcu_read_lock();
 		for_each_domain(rq->cpu, sd) {
 			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-				schedstat_inc(sd->ttwu_wake_remote);
+				__schedstat_inc(sd->ttwu_wake_remote);
 				break;
 			}
 		}
@@ -1646,14 +1647,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	}
 
 	if (wake_flags & WF_MIGRATED)
-		schedstat_inc(p->se.statistics.nr_wakeups_migrate);
+		__schedstat_inc(p->se.statistics.nr_wakeups_migrate);
 #endif /* CONFIG_SMP */
 
-	schedstat_inc(rq->ttwu_count);
-	schedstat_inc(p->se.statistics.nr_wakeups);
+	__schedstat_inc(rq->ttwu_count);
+	__schedstat_inc(p->se.statistics.nr_wakeups);
 
 	if (wake_flags & WF_SYNC)
-		schedstat_inc(p->se.statistics.nr_wakeups_sync);
+		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
 static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_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.
@@ -2460,6 +2461,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
 	 * as we're not fully set-up yet.
 	 */
+	p->recent_used_cpu = task_cpu(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -2571,6 +2573,50 @@ 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 +2637,7 @@ 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);
 }
 
@@ -2646,29 +2692,34 @@ 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.
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
 	perf_event_task_sched_in(prev, current);
-	/*
-	 * The membarrier system call requires a full memory barrier
-	 * after storing to rq->curr, before going back to user-space.
-	 *
-	 * TODO: This smp_mb__after_unlock_lock can go away if PPC end
-	 * up adding a full barrier to switch_mm(), or we should figure
-	 * out if a smp_mb__after_unlock_lock is really the proper API
-	 * 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);
-	if (mm)
+	/*
+	 * When switching through a kernel thread, the loop in
+	 * membarrier_{private,global}_expedited() may have observed that
+	 * kernel thread and not issued an IPI. It is therefore possible to
+	 * schedule between user->kernel->user threads without passing though
+	 * switch_mm(). Membarrier requires a barrier after storing to
+	 * rq->curr, before returning to userspace, so provide them here:
+	 *
+	 * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
+	 *   provided by mmdrop(),
+	 * - a sync_core for SYNC_CORE.
+	 */
+	if (mm) {
+		membarrier_mm_sync_core_before_usermode(mm);
 		mmdrop(mm);
+	}
 	if (unlikely(prev_state == TASK_DEAD)) {
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
@@ -2772,6 +2823,13 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 */
 	arch_start_context_switch(prev);
 
+	/*
+	 * If mm is non-NULL, we pass through switch_mm(). If mm is
+	 * NULL, we will pass through mmdrop() in finish_task_switch().
+	 * Both of these contain the full memory barrier required by
+	 * membarrier after storing to rq->curr, before returning to
+	 * user-space.
+	 */
 	if (!mm) {
 		next->active_mm = oldmm;
 		mmgrab(oldmm);
@@ -3308,6 +3366,9 @@ static void __sched notrace __schedule(bool preempt)
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
 	 * done by the caller to avoid the race with signal_wake_up().
+	 *
+	 * The membarrier system call requires a full memory barrier
+	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
 	smp_mb__after_spinlock();
@@ -3355,17 +3416,16 @@ static void __sched notrace __schedule(bool preempt)
 		/*
 		 * The membarrier system call requires each architecture
 		 * to have a full memory barrier after updating
-		 * rq->curr, before returning to user-space. For TSO
-		 * (e.g. x86), the architecture must provide its own
-		 * barrier in switch_mm(). For weakly ordered machines
-		 * for which spin_unlock() acts as a full memory
-		 * barrier, finish_lock_switch() in common code takes
-		 * care of this barrier. For weakly ordered machines for
-		 * which spin_unlock() acts as a RELEASE barrier (only
-		 * arm64 and PowerPC), arm64 has a full barrier in
-		 * switch_to(), and PowerPC has
-		 * smp_mb__after_unlock_lock() before
-		 * finish_lock_switch().
+		 * rq->curr, before returning to user-space.
+		 *
+		 * Here are the schemes providing that barrier on the
+		 * various architectures:
+		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
+		 *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+		 * - finish_lock_switch() for weakly-ordered
+		 *   architectures where spin_unlock is a full barrier,
+		 * - switch_to() for arm64 (weakly-ordered, spin_unlock
+		 *   is a RELEASE barrier),
 		 */
 		++*switch_count;
 
@@ -4040,8 +4100,7 @@ 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 +4167,9 @@ recheck:
 	}
 
 	if (user) {
+		if (attr->sched_flags & SCHED_FLAG_SUGOV)
+			return -EINVAL;
+
 		retval = security_task_setscheduler(p);
 		if (retval)
 			return retval;
@@ -4163,7 +4225,8 @@ 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 +4356,11 @@ 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.
@@ -4799,7 +4867,7 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 
 	ret = sched_getaffinity(pid, mask);
 	if (ret == 0) {
-		size_t retlen = min_t(size_t, len, cpumask_size());
+		unsigned int retlen = min(len, cpumask_size());
 
 		if (copy_to_user(user_mask_ptr, mask, retlen))
 			ret = -EFAULT;