1 files changed, 132 insertions, 108 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 223f78d5c111..102dfcf0a29a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -24,7 +24,7 @@
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
 /*
  * Debugging: various feature bits
  *
@@ -107,11 +107,12 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 *					[L] ->on_rq
 		 *	RELEASE (rq->lock)
 		 *
-		 * If we observe the old CPU in task_rq_lock, the acquire of
+		 * If we observe the old CPU in task_rq_lock(), the acquire of
 		 * the old rq->lock will fully serialize against the stores.
 		 *
-		 * If we observe the new CPU in task_rq_lock, the acquire will
-		 * pair with the WMB to ensure we must then also see migrating.
+		 * If we observe the new CPU in task_rq_lock(), the address
+		 * dependency headed by '[L] rq = task_rq()' and the acquire
+		 * will pair with the WMB to ensure we then also see migrating.
 		 */
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
 			rq_pin_lock(rq, rf);
@@ -180,6 +181,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
+	update_rq_clock_pelt(rq, delta);
 }
 
 void update_rq_clock(struct rq *rq)
@@ -396,7 +398,7 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
-void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
 	struct wake_q_node *node = &task->wake_q;
 
@@ -405,19 +407,60 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() executes a full barrier, which pairs with the full
-	 * barrier executed by the wakeup in wake_up_q().
+	 * In order to ensure that a pending wakeup will observe our pending
+	 * state, even in the failed case, an explicit smp_mb() must be used.
 	 */
-	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
-		return;
-
-	get_task_struct(task);
+	smp_mb__before_atomic();
+	if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
+		return false;
 
 	/*
 	 * The head is context local, there can be no concurrency.
 	 */
 	*head->lastp = node;
 	head->lastp = &node->next;
+	return true;
+}
+
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+	if (__wake_q_add(head, task))
+		get_task_struct(task);
+}
+
+/**
+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ *
+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
+ * that already hold reference to @task can call the 'safe' version and trust
+ * wake_q to do the right thing depending whether or not the @task is already
+ * queued for wakeup.
+ */
+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
+{
+	if (!__wake_q_add(head, task))
+		put_task_struct(task);
 }
 
 void wake_up_q(struct wake_q_head *head)
@@ -749,10 +792,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
+
+	p->on_rq = TASK_ON_RQ_QUEUED;
 }
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
@@ -877,7 +924,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 
 /*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
@@ -915,7 +962,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	p->on_rq = TASK_ON_RQ_MIGRATING;
+	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
@@ -1108,7 +1155,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-		tlb_migrate_finish(p->mm);
 		return 0;
 	} else if (task_on_rq_queued(p)) {
 		/*
@@ -1194,11 +1240,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		rq_pin_lock(src_rq, &srf);
 		rq_pin_lock(dst_rq, &drf);
 
-		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
-		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 
 		rq_unpin_lock(dst_rq, &drf);
@@ -1638,16 +1682,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
-	activate_task(rq, p, en_flags);
-	p->on_rq = TASK_ON_RQ_QUEUED;
-
-	/* If a worker is waking up, notify the workqueue: */
-	if (p->flags & PF_WQ_WORKER)
-		wq_worker_waking_up(p, cpu_of(rq));
-}
-
 /*
  * Mark the task runnable and perform wakeup-preemption.
  */
@@ -1699,7 +1733,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
 
-	ttwu_activate(rq, p, en_flags);
+	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
@@ -2064,56 +2098,6 @@ out:
 }
 
 /**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
-	struct rq *rq = task_rq(p);
-
-	if (WARN_ON_ONCE(rq != this_rq()) ||
-	    WARN_ON_ONCE(p == current))
-		return;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (!raw_spin_trylock(&p->pi_lock)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet picked a replacement task.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&p->pi_lock);
-		rq_relock(rq, rf);
-	}
-
-	if (!(p->state & TASK_NORMAL))
-		goto out;
-
-	trace_sched_waking(p);
-
-	if (!task_on_rq_queued(p)) {
-		if (p->in_iowait) {
-			delayacct_blkio_end(p);
-			atomic_dec(&rq->nr_iowait);
-		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
-	}
-
-	ttwu_do_wakeup(rq, p, 0, rf);
-	ttwu_stat(p, smp_processor_id(), 0);
-out:
-	raw_spin_unlock(&p->pi_lock);
-}
-
-/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2177,6 +2161,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
+#ifdef CONFIG_COMPACTION
+	p->capture_control = NULL;
+#endif
 	init_numa_balancing(clone_flags, p);
 }
 
@@ -2418,10 +2405,9 @@ void wake_up_new_task(struct task_struct *p)
 #endif
 	rq = __task_rq_lock(p, &rf);
 	update_rq_clock(rq);
-	post_init_entity_util_avg(&p->se);
+	post_init_entity_util_avg(p);
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -3420,25 +3406,11 @@ static void __sched notrace __schedule(bool preempt)
 			prev->state = TASK_RUNNING;
 		} else {
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
 				atomic_inc(&rq->nr_iowait);
 				delayacct_blkio_start();
 			}
-
-			/*
-			 * If a worker went to sleep, notify and ask workqueue
-			 * whether it wants to wake up a task to maintain
-			 * concurrency.
-			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
-				to_wakeup = wq_worker_sleeping(prev);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, &rf);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -3498,6 +3470,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))
 		return;
+
+	/*
+	 * If a worker went to sleep, notify and ask workqueue whether
+	 * it wants to wake up a task to maintain concurrency.
+	 * As this function is called inside the schedule() context,
+	 * we disable preemption to avoid it calling schedule() again
+	 * in the possible wakeup of a kworker.
+	 */
+	if (tsk->flags & PF_WQ_WORKER) {
+		preempt_disable();
+		wq_worker_sleeping(tsk);
+		preempt_enable_no_resched();
+	}
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -3506,6 +3492,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
+static void sched_update_worker(struct task_struct *tsk)
+{
+	if (tsk->flags & PF_WQ_WORKER)
+		wq_worker_running(tsk);
+}
+
 asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
@@ -3516,6 +3508,7 @@ asmlinkage __visible void __sched schedule(void)
 		__schedule(false);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
@@ -5252,9 +5245,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 }
 
 #ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
-		       compat_pid_t, pid,
-		       struct old_timespec32 __user *, interval)
+SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
+		struct old_timespec32 __user *, interval)
 {
 	struct timespec64 t;
 	int retval = sched_rr_get_interval(pid, &t);
@@ -5854,14 +5846,11 @@ void __init sched_init_smp(void)
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
-	 * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
-	 * but there won't be any contention on it.
+	 * happen.
 	 */
-	cpus_read_lock();
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
 	mutex_unlock(&sched_domains_mutex);
-	cpus_read_unlock();
 
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
@@ -5876,7 +5865,7 @@ void __init sched_init_smp(void)
 
 static int __init migration_init(void)
 {
-	sched_rq_cpu_starting(smp_processor_id());
+	sched_cpu_starting(smp_processor_id());
 	return 0;
 }
 early_initcall(migration_init);
@@ -6149,6 +6138,34 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
 EXPORT_SYMBOL(___might_sleep);
+
+void __cant_sleep(const char *file, int line, int preempt_offset)
+{
+	static unsigned long prev_jiffy;
+
+	if (irqs_disabled())
+		return;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
+		return;
+
+	if (preempt_count() > preempt_offset)
+		return;
+
+	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+		return;
+	prev_jiffy = jiffies;
+
+	printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
+	printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+			in_atomic(), irqs_disabled(),
+			current->pid, current->comm);
+
+	debug_show_held_locks(current);
+	dump_stack();
+	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+}
+EXPORT_SYMBOL_GPL(__cant_sleep);
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
@@ -6489,6 +6506,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
 {
+	if (shareval > scale_load_down(ULONG_MAX))
+		shareval = MAX_SHARES;
 	return sched_group_set_shares(css_tg(css), scale_load(shareval));
 }
 
@@ -6504,7 +6523,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
 static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -6584,20 +6603,22 @@ out_unlock:
 	return ret;
 }
 
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 {
 	u64 quota, period;
 
 	period = ktime_to_ns(tg->cfs_bandwidth.period);
 	if (cfs_quota_us < 0)
 		quota = RUNTIME_INF;
-	else
+	else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
 		quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+	else
+		return -EINVAL;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
 {
 	u64 quota_us;
 
@@ -6610,17 +6631,20 @@ long tg_get_cfs_quota(struct task_group *tg)
 	return quota_us;
 }
 
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
 {
 	u64 quota, period;
 
+	if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	period = (u64)cfs_period_us * NSEC_PER_USEC;
 	quota = tg->cfs_bandwidth.quota;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
 {
 	u64 cfs_period_us;
 
@@ -6928,7 +6952,7 @@ static int __maybe_unused cpu_period_quota_parse(char *buf,
 {
 	char tok[21];	/* U64_MAX */
 
-	if (!sscanf(buf, "%s %llu", tok, periodp))
+	if (sscanf(buf, "%20s %llu", tok, periodp) < 1)
 		return -EINVAL;
 
 	*periodp *= NSEC_PER_USEC;