Merge tag 'sched-urgent-2020-07-19' of...

Merge tag 'sched-urgent-2020-07-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into master

Pull scheduler fixes from Thomas Gleixner:
 "A set of scheduler fixes:

   - Plug a load average accounting race which was introduced with a
     recent optimization casing load average to show bogus numbers.

   - Fix the rseq CPU id initialization for new tasks. sched_fork() does
     not update the rseq CPU id so the id is the stale id of the parent
     task, which can cause user space data corruption.

   - Handle a 0 return value of task_h_load() correctly in the load
     balancer, which does not decrease imbalance and therefore pulls
     until the maximum number of loops is reached, which might be all
     tasks just created by a fork bomb"

* tag 'sched-urgent-2020-07-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: handle case of task_h_load() returning 0
  sched: Fix unreliable rseq cpu_id for new tasks
  sched: Fix loadavg accounting race

include/linux/sched.h

@@ -114,10 +114,6 @@ struct task_group;
 
 #define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 
-#define task_contributes_to_load(task)	((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-					 (task->flags & PF_FROZEN) == 0 && \
-					 (task->state & TASK_NOLOAD) == 0)
-
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
 /*

kernel/sched/core.c

@@ -1311,9 +1311,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1323,9 +1320,6 @@ 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++;
-
 	dequeue_task(rq, p, flags);
 }
 
@@ -2236,10 +2230,10 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
@@ -2583,7 +2577,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -2592,9 +2586,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	}
 
 #ifdef CONFIG_SMP
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
 	 * possible to, falsely, observe p->on_cpu == 0.
@@ -2613,8 +2604,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -2962,6 +2965,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -3026,6 +3030,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -4097,6 +4102,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4113,12 +4119,22 @@ static void __sched notrace __schedule(bool preempt)
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
 
+	/* See deactivate_task() below. */
+	prev_state = prev->state;
+
 	/*
 	 * 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().
+	 * done by the caller to avoid the race with signal_wake_up():
+	 *
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4129,10 +4145,31 @@ static void __sched notrace __schedule(bool preempt)
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+	/*
+	 * We must re-load prev->state in case ttwu_remote() changed it
+	 * before we acquired rq->lock.
+	 */
+	if (!preempt && prev_state && prev_state == prev->state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;	  if (READ_ONCE(p->on_rq) && ...)
+			 *   LOCK rq->lock		    goto out;
+			 *   smp_mb__after_spinlock();	  smp_acquire__after_ctrl_dep();
+			 *   p->on_rq = 0;		  p->state = TASK_WAKING;
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {

kernel/sched/fair.c

@@ -4039,7 +4039,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 		return;
 	}
 
-	rq->misfit_task_load = task_h_load(p);
+	/*
+	 * Make sure that misfit_task_load will not be null even if
+	 * task_h_load() returns 0.
+	 */
+	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
 #else /* CONFIG_SMP */
@@ -7638,7 +7642,14 @@ static int detach_tasks(struct lb_env *env)
 
 		switch (env->migration_type) {
 		case migrate_load:
-			load = task_h_load(p);
+			/*
+			 * Depending of the number of CPUs and tasks and the
+			 * cgroup hierarchy, task_h_load() can return a null
+			 * value. Make sure that env->imbalance decreases
+			 * otherwise detach_tasks() will stop only after
+			 * detaching up to loop_max tasks.
+			 */
+			load = max_t(unsigned long, task_h_load(p), 1);
 
 			if (sched_feat(LB_MIN) &&
 			    load < 16 && !env->sd->nr_balance_failed)