Merge branch 'sched/urgent' into sched/core, to pick up fixes before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/bpf/verifier.c

@@ -1374,6 +1374,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
 	}
 
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
+	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
 		verbose("BPF_LD_ABS uses reserved fields\n");
 		return -EINVAL;

kernel/cpu.c

@@ -36,6 +36,7 @@
  * @target:	The target state
  * @thread:	Pointer to the hotplug thread
  * @should_run:	Thread should execute
+ * @rollback:	Perform a rollback
  * @cb_stat:	The state for a single callback (install/uninstall)
  * @cb:		Single callback function (install/uninstall)
  * @result:	Result of the operation
@@ -47,6 +48,7 @@ struct cpuhp_cpu_state {
 #ifdef CONFIG_SMP
 	struct task_struct	*thread;
 	bool			should_run;
+	bool			rollback;
 	enum cpuhp_state	cb_state;
 	int			(*cb)(unsigned int cpu);
 	int			result;
@@ -301,6 +303,11 @@ static int cpu_notify(unsigned long val, unsigned int cpu)
 	return __cpu_notify(val, cpu, -1, NULL);
 }
 
+static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
+{
+	BUG_ON(cpu_notify(val, cpu));
+}
+
 /* Notifier wrappers for transitioning to state machine */
 static int notify_prepare(unsigned int cpu)
 {
@@ -477,6 +484,16 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		} else {
 			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
 		}
+	} else if (st->rollback) {
+		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
+
+		undo_cpu_down(cpu, st, cpuhp_ap_states);
+		/*
+		 * This is a momentary workaround to keep the notifier users
+		 * happy. Will go away once we got rid of the notifiers.
+		 */
+		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
+		st->rollback = false;
 	} else {
 		/* Cannot happen .... */
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
@@ -636,11 +653,6 @@ static inline void check_for_tasks(int dead_cpu)
 	read_unlock(&tasklist_lock);
 }
 
-static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
-{
-	BUG_ON(cpu_notify(val, cpu));
-}
-
 static int notify_down_prepare(unsigned int cpu)
 {
 	int err, nr_calls = 0;
@@ -721,9 +733,10 @@ static int takedown_cpu(unsigned int cpu)
 	 */
 	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
 	if (err) {
-		/* CPU didn't die: tell everyone.  Can't complain. */
-		cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
+		/* CPU refused to die */
 		irq_unlock_sparse();
+		/* Unpark the hotplug thread so we can rollback there */
+		kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread);
 		return err;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -832,6 +845,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	 * to do the further cleanups.
 	 */
 	ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
+	if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
+		st->target = prev_state;
+		st->rollback = true;
+		cpuhp_kick_ap_work(cpu);
+	}
 
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
@@ -1249,6 +1267,7 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.name			= "notify:online",
 		.startup		= notify_online,
 		.teardown		= notify_down_prepare,
+		.skip_onerr		= true,
 	},
 #endif
 	/*

kernel/futex.c

@@ -1295,10 +1295,20 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
-	else if (curval != uval)
-		ret = -EINVAL;
+	} else if (curval != uval) {
+		/*
+		 * If a unconditional UNLOCK_PI operation (user space did not
+		 * try the TID->0 transition) raced with a waiter setting the
+		 * FUTEX_WAITERS flag between get_user() and locking the hash
+		 * bucket lock, retry the operation.
+		 */
+		if ((FUTEX_TID_MASK & curval) == uval)
+			ret = -EAGAIN;
+		else
+			ret = -EINVAL;
+	}
 	if (ret) {
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
@@ -1525,8 +1535,8 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
 	if (likely(&hb1->chain != &hb2->chain)) {
 		plist_del(&q->list, &hb1->chain);
 		hb_waiters_dec(hb1);
-		plist_add(&q->list, &hb2->chain);
 		hb_waiters_inc(hb2);
+		plist_add(&q->list, &hb2->chain);
 		q->lock_ptr = &hb2->lock;
 	}
 	get_futex_key_refs(key2);
@@ -2622,6 +2632,15 @@ retry:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
+		/*
+		 * A unconditional UNLOCK_PI op raced against a waiter
+		 * setting the FUTEX_WAITERS bit. Try again.
+		 */
+		if (ret == -EAGAIN) {
+			spin_unlock(&hb->lock);
+			put_futex_key(&key);
+			goto retry;
+		}
 		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.

kernel/irq/ipi.c

@@ -94,6 +94,7 @@ unsigned int irq_reserve_ipi(struct irq_domain *domain,
 		data = irq_get_irq_data(virq + i);
 		cpumask_copy(data->common->affinity, dest);
 		data->common->ipi_offset = offset;
+		irq_set_status_flags(virq + i, IRQ_NO_BALANCING);
 	}
 	return virq;
 

kernel/locking/qspinlock_stat.h

@@ -136,10 +136,12 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf,
 	}
 
 	if (counter == qstat_pv_hash_hops) {
-		u64 frac;
+		u64 frac = 0;
 
-		frac = 100ULL * do_div(stat, kicks);
-		frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
+		if (kicks) {
+			frac = 100ULL * do_div(stat, kicks);
+			frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
+		}
 
 		/*
 		 * Return a X.XX decimal number

kernel/sched/core.c

@@ -596,17 +596,8 @@ bool sched_can_stop_tick(struct rq *rq)
 		return false;
 
 	/*
-	 * FIFO realtime policy runs the highest priority task (after DEADLINE).
-	 * Other runnable tasks are of a lower priority. The scheduler tick
-	 * isn't needed.
-	 */
-	fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
-	if (fifo_nr_running)
-		return true;
-
-	/*
-	 * Round-robin realtime tasks time slice with other tasks at the same
-	 * realtime priority.
+	 * If there are more than one RR tasks, we need the tick to effect the
+	 * actual RR behaviour.
 	 */
 	if (rq->rt.rr_nr_running) {
 		if (rq->rt.rr_nr_running == 1)
@@ -615,8 +606,20 @@ bool sched_can_stop_tick(struct rq *rq)
 			return false;
 	}
 
-	/* Normal multitasking need periodic preemption checks */
-	if (rq->cfs.nr_running > 1)
+	/*
+	 * If there's no RR tasks, but FIFO tasks, we can skip the tick, no
+	 * forced preemption between FIFO tasks.
+	 */
+	fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running;
+	if (fifo_nr_running)
+		return true;
+
+	/*
+	 * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
+	 * if there's more than one we need the tick for involuntary
+	 * preemption.
+	 */
+	if (rq->nr_running > 1)
 		return false;
 
 	return true;