1 files changed, 53 insertions, 46 deletions

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 87cfadd70d0d..91806dc1236d 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -84,22 +84,12 @@ const struct evtchn_ops *evtchn_ops;
 static DEFINE_MUTEX(irq_mapping_update_lock);
 
 /*
- * Lock protecting event handling loop against removing event channels.
- * Adding of event channels is no issue as the associated IRQ becomes active
- * only after everything is setup (before request_[threaded_]irq() the handler
- * can't be entered for an event, as the event channel will be unmasked only
- * then).
- */
-static DEFINE_RWLOCK(evtchn_rwlock);
-
-/*
  * Lock hierarchy:
  *
  * irq_mapping_update_lock
- *   evtchn_rwlock
- *     IRQ-desc lock
- *       percpu eoi_list_lock
- *         irq_info->lock
+ *   IRQ-desc lock
+ *     percpu eoi_list_lock
+ *       irq_info->lock
  */
 
 static LIST_HEAD(xen_irq_list_head);
@@ -214,6 +204,22 @@ static void set_info_for_irq(unsigned int irq, struct irq_info *info)
 		irq_set_chip_data(irq, info);
 }
 
+static void delayed_free_irq(struct work_struct *work)
+{
+	struct irq_info *info = container_of(to_rcu_work(work), struct irq_info,
+					     rwork);
+	unsigned int irq = info->irq;
+
+	/* Remove the info pointer only now, with no potential users left. */
+	set_info_for_irq(irq, NULL);
+
+	kfree(info);
+
+	/* Legacy IRQ descriptors are managed by the arch. */
+	if (irq >= nr_legacy_irqs())
+		irq_free_desc(irq);
+}
+
 /* Constructors for packed IRQ information. */
 static int xen_irq_info_common_setup(struct irq_info *info,
 				     unsigned irq,
@@ -485,7 +491,9 @@ static void lateeoi_list_add(struct irq_info *info)
 
 	spin_lock_irqsave(&eoi->eoi_list_lock, flags);
 
-	if (list_empty(&eoi->eoi_list)) {
+	elem = list_first_entry_or_null(&eoi->eoi_list, struct irq_info,
+					eoi_list);
+	if (!elem || info->eoi_time < elem->eoi_time) {
 		list_add(&info->eoi_list, &eoi->eoi_list);
 		mod_delayed_work_on(info->eoi_cpu, system_wq,
 				    &eoi->delayed, delay);
@@ -548,33 +556,36 @@ static void xen_irq_lateeoi_worker(struct work_struct *work)
 
 	eoi = container_of(to_delayed_work(work), struct lateeoi_work, delayed);
 
-	read_lock_irqsave(&evtchn_rwlock, flags);
+	rcu_read_lock();
 
 	while (true) {
-		spin_lock(&eoi->eoi_list_lock);
+		spin_lock_irqsave(&eoi->eoi_list_lock, flags);
 
 		info = list_first_entry_or_null(&eoi->eoi_list, struct irq_info,
 						eoi_list);
 
-		if (info == NULL || now < info->eoi_time) {
-			spin_unlock(&eoi->eoi_list_lock);
+		if (info == NULL)
+			break;
+
+		if (now < info->eoi_time) {
+			mod_delayed_work_on(info->eoi_cpu, system_wq,
+					    &eoi->delayed,
+					    info->eoi_time - now);
 			break;
 		}
 
 		list_del_init(&info->eoi_list);
 
-		spin_unlock(&eoi->eoi_list_lock);
+		spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);
 
 		info->eoi_time = 0;
 
 		xen_irq_lateeoi_locked(info, false);
 	}
 
-	if (info)
-		mod_delayed_work_on(info->eoi_cpu, system_wq,
-				    &eoi->delayed, info->eoi_time - now);
+	spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);
 
-	read_unlock_irqrestore(&evtchn_rwlock, flags);
+	rcu_read_unlock();
 }
 
 static void xen_cpu_init_eoi(unsigned int cpu)
@@ -589,16 +600,15 @@ static void xen_cpu_init_eoi(unsigned int cpu)
 void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
 {
 	struct irq_info *info;
-	unsigned long flags;
 
-	read_lock_irqsave(&evtchn_rwlock, flags);
+	rcu_read_lock();
 
 	info = info_for_irq(irq);
 
 	if (info)
 		xen_irq_lateeoi_locked(info, eoi_flags & XEN_EOI_FLAG_SPURIOUS);
 
-	read_unlock_irqrestore(&evtchn_rwlock, flags);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(xen_irq_lateeoi);
 
@@ -617,6 +627,7 @@ static void xen_irq_init(unsigned irq)
 
 	info->type = IRQT_UNBOUND;
 	info->refcnt = -1;
+	INIT_RCU_WORK(&info->rwork, delayed_free_irq);
 
 	set_info_for_irq(irq, info);
 
@@ -669,31 +680,18 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 static void xen_free_irq(unsigned irq)
 {
 	struct irq_info *info = info_for_irq(irq);
-	unsigned long flags;
 
 	if (WARN_ON(!info))
 		return;
 
-	write_lock_irqsave(&evtchn_rwlock, flags);
-
 	if (!list_empty(&info->eoi_list))
 		lateeoi_list_del(info);
 
 	list_del(&info->list);
 
-	set_info_for_irq(irq, NULL);
-
 	WARN_ON(info->refcnt > 0);
 
-	write_unlock_irqrestore(&evtchn_rwlock, flags);
-
-	kfree(info);
-
-	/* Legacy IRQ descriptors are managed by the arch. */
-	if (irq < nr_legacy_irqs())
-		return;
-
-	irq_free_desc(irq);
+	queue_rcu_work(system_wq, &info->rwork);
 }
 
 static void xen_evtchn_close(unsigned int port)
@@ -1604,7 +1602,14 @@ static void __xen_evtchn_do_upcall(void)
 	unsigned count;
 	struct evtchn_loop_ctrl ctrl = { 0 };
 
-	read_lock(&evtchn_rwlock);
+	/*
+	 * When closing an event channel the associated IRQ must not be freed
+	 * until all cpus have left the event handling loop. This is ensured
+	 * by taking the rcu_read_lock() while handling events, as freeing of
+	 * the IRQ is handled via queue_rcu_work() _after_ closing the event
+	 * channel.
+	 */
+	rcu_read_lock();
 
 	do {
 		vcpu_info->evtchn_upcall_pending = 0;
@@ -1621,7 +1626,7 @@ static void __xen_evtchn_do_upcall(void)
 	} while (count != 1 || vcpu_info->evtchn_upcall_pending);
 
 out:
-	read_unlock(&evtchn_rwlock);
+	rcu_read_unlock();
 
 	/*
 	 * Increment irq_epoch only now to defer EOIs only for
@@ -2101,8 +2106,8 @@ void xen_callback_vector(void)
 void xen_callback_vector(void) {}
 #endif
 
-static bool fifo_events = true;
-module_param(fifo_events, bool, 0);
+bool xen_fifo_events = true;
+module_param_named(fifo_events, xen_fifo_events, bool, 0);
 
 static int xen_evtchn_cpu_prepare(unsigned int cpu)
 {
@@ -2131,10 +2136,12 @@ void __init xen_init_IRQ(void)
 	int ret = -EINVAL;
 	unsigned int evtchn;
 
-	if (fifo_events)
+	if (xen_fifo_events)
 		ret = xen_evtchn_fifo_init();
-	if (ret < 0)
+	if (ret < 0) {
 		xen_evtchn_2l_init();
+		xen_fifo_events = false;
+	}
 
 	xen_cpu_init_eoi(smp_processor_id());