Merge branch 'for-4.4/hotplug' into libnvdimm-for-next

6 files changed, 15 insertions, 18 deletions

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index de41a68fc038..e25a83b67cce 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -22,7 +22,6 @@
 
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
- * @irq:       the interrupt number
  * @desc:      description of the interrupt
  *
  * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
@@ -35,6 +34,7 @@ void handle_bad_irq(struct irq_desc *desc)
 	kstat_incr_irqs_this_cpu(desc);
 	ack_bad_irq(irq);
 }
+EXPORT_SYMBOL_GPL(handle_bad_irq);
 
 /*
  * Special, empty irq handler:
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 7e6512b9dc1f..be9149f62eb8 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -228,11 +228,7 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info)
 {
 	struct irq_chip *chip = info->chip;
 
-	BUG_ON(!chip);
-	if (!chip->irq_mask)
-		chip->irq_mask = pci_msi_mask_irq;
-	if (!chip->irq_unmask)
-		chip->irq_unmask = pci_msi_unmask_irq;
+	BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask);
 	if (!chip->irq_set_affinity)
 		chip->irq_set_affinity = msi_domain_set_affinity;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 615953141951..10a8faa1b0d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2517,11 +2517,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
 	 * schedule one last time. The schedule call will never return, and
 	 * the scheduled task must drop that reference.
-	 * The test for TASK_DEAD must occur while the runqueue locks are
-	 * still held, otherwise prev could be scheduled on another cpu, die
-	 * there before we look at prev->state, and then the reference would
-	 * be dropped twice.
-	 *		Manfred Spraul <manfred@colorfullife.com>
+	 *
+	 * We must observe prev->state before clearing prev->on_cpu (in
+	 * finish_lock_switch), 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);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 68cda117574c..6d2a119c7ad9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * 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.
+	 *
+	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
-	smp_wmb();
-	prev->on_cpu = 0;
+	smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3739ac6aa473..44d2cc0436f4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1251,7 +1251,7 @@ void __init timekeeping_init(void)
 	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
 	tk_set_wall_to_mono(tk, tmp);
 
-	timekeeping_update(tk, TK_MIRROR);
+	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ca71582fcfab..bcb14cafe007 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1458,13 +1458,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	timer_stats_timer_set_start_info(&dwork->timer);
 
 	dwork->wq = wq;
+	/* timer isn't guaranteed to run in this cpu, record earlier */
+	if (cpu == WORK_CPU_UNBOUND)
+		cpu = raw_smp_processor_id();
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	if (unlikely(cpu != WORK_CPU_UNBOUND))
-		add_timer_on(timer, cpu);
-	else
-		add_timer(timer);
+	add_timer_on(timer, cpu);
 }
 
 /**