1 files changed, 532 insertions, 65 deletions

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index e4dd991e2888..56bf952de411 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -32,6 +32,10 @@
 #include <linux/slab.h>
 #include <linux/irqnr.h>
 #include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+#include <linux/atomic.h>
+#include <linux/ktime.h>
 
 #ifdef CONFIG_X86
 #include <asm/desc.h>
@@ -62,6 +66,15 @@
 
 #include "events_internal.h"
 
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "xen."
+
+static uint __read_mostly event_loop_timeout = 2;
+module_param(event_loop_timeout, uint, 0644);
+
+static uint __read_mostly event_eoi_delay = 10;
+module_param(event_eoi_delay, uint, 0644);
+
 const struct evtchn_ops *evtchn_ops;
 
 /*
@@ -70,6 +83,25 @@ 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
+ */
+
 static LIST_HEAD(xen_irq_list_head);
 
 /* IRQ <-> VIRQ mapping. */
@@ -91,18 +123,23 @@ static bool (*pirq_needs_eoi)(unsigned irq);
 /* Xen will never allocate port zero for any purpose. */
 #define VALID_EVTCHN(chn)	((chn) != 0)
 
+static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY];
+
 static struct irq_chip xen_dynamic_chip;
+static struct irq_chip xen_lateeoi_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
 static void enable_dynirq(struct irq_data *data);
 static void disable_dynirq(struct irq_data *data);
 
+static DEFINE_PER_CPU(unsigned int, irq_epoch);
+
 static void clear_evtchn_to_irq_row(unsigned row)
 {
 	unsigned col;
 
 	for (col = 0; col < EVTCHN_PER_ROW; col++)
-		evtchn_to_irq[row][col] = -1;
+		WRITE_ONCE(evtchn_to_irq[row][col], -1);
 }
 
 static void clear_evtchn_to_irq_all(void)
@@ -139,7 +176,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq)
 		clear_evtchn_to_irq_row(row);
 	}
 
-	evtchn_to_irq[row][col] = irq;
+	WRITE_ONCE(evtchn_to_irq[row][col], irq);
 	return 0;
 }
 
@@ -149,13 +186,24 @@ int get_evtchn_to_irq(unsigned evtchn)
 		return -1;
 	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
 		return -1;
-	return evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)];
+	return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);
 }
 
 /* Get info for IRQ */
 struct irq_info *info_for_irq(unsigned irq)
 {
-	return irq_get_chip_data(irq);
+	if (irq < nr_legacy_irqs())
+		return legacy_info_ptrs[irq];
+	else
+		return irq_get_chip_data(irq);
+}
+
+static void set_info_for_irq(unsigned int irq, struct irq_info *info)
+{
+	if (irq < nr_legacy_irqs())
+		legacy_info_ptrs[irq] = info;
+	else
+		irq_set_chip_data(irq, info);
 }
 
 /* Constructors for packed IRQ information. */
@@ -173,6 +221,8 @@ static int xen_irq_info_common_setup(struct irq_info *info,
 	info->irq = irq;
 	info->evtchn = evtchn;
 	info->cpu = cpu;
+	info->mask_reason = EVT_MASK_REASON_EXPLICIT;
+	raw_spin_lock_init(&info->lock);
 
 	ret = set_evtchn_to_irq(evtchn, irq);
 	if (ret < 0)
@@ -239,6 +289,7 @@ static int xen_irq_info_pirq_setup(unsigned irq,
 static void xen_irq_info_cleanup(struct irq_info *info)
 {
 	set_evtchn_to_irq(info->evtchn, -1);
+	xen_evtchn_port_remove(info->evtchn, info->cpu);
 	info->evtchn = 0;
 }
 
@@ -247,10 +298,14 @@ static void xen_irq_info_cleanup(struct irq_info *info)
  */
 unsigned int evtchn_from_irq(unsigned irq)
 {
-	if (unlikely(WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)))
+	const struct irq_info *info = NULL;
+
+	if (likely(irq < nr_irqs))
+		info = info_for_irq(irq);
+	if (!info)
 		return 0;
 
-	return info_for_irq(irq)->evtchn;
+	return info->evtchn;
 }
 
 unsigned irq_from_evtchn(unsigned int evtchn)
@@ -315,6 +370,34 @@ unsigned int cpu_from_evtchn(unsigned int evtchn)
 	return ret;
 }
 
+static void do_mask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&info->lock, flags);
+
+	if (!info->mask_reason)
+		mask_evtchn(info->evtchn);
+
+	info->mask_reason |= reason;
+
+	raw_spin_unlock_irqrestore(&info->lock, flags);
+}
+
+static void do_unmask(struct irq_info *info, u8 reason)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&info->lock, flags);
+
+	info->mask_reason &= ~reason;
+
+	if (!info->mask_reason)
+		unmask_evtchn(info->evtchn);
+
+	raw_spin_unlock_irqrestore(&info->lock, flags);
+}
+
 #ifdef CONFIG_X86
 static bool pirq_check_eoi_map(unsigned irq)
 {
@@ -369,9 +452,157 @@ void notify_remote_via_irq(int irq)
 }
 EXPORT_SYMBOL_GPL(notify_remote_via_irq);
 
+struct lateeoi_work {
+	struct delayed_work delayed;
+	spinlock_t eoi_list_lock;
+	struct list_head eoi_list;
+};
+
+static DEFINE_PER_CPU(struct lateeoi_work, lateeoi);
+
+static void lateeoi_list_del(struct irq_info *info)
+{
+	struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu);
+	unsigned long flags;
+
+	spin_lock_irqsave(&eoi->eoi_list_lock, flags);
+	list_del_init(&info->eoi_list);
+	spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);
+}
+
+static void lateeoi_list_add(struct irq_info *info)
+{
+	struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu);
+	struct irq_info *elem;
+	u64 now = get_jiffies_64();
+	unsigned long delay;
+	unsigned long flags;
+
+	if (now < info->eoi_time)
+		delay = info->eoi_time - now;
+	else
+		delay = 1;
+
+	spin_lock_irqsave(&eoi->eoi_list_lock, flags);
+
+	if (list_empty(&eoi->eoi_list)) {
+		list_add(&info->eoi_list, &eoi->eoi_list);
+		mod_delayed_work_on(info->eoi_cpu, system_wq,
+				    &eoi->delayed, delay);
+	} else {
+		list_for_each_entry_reverse(elem, &eoi->eoi_list, eoi_list) {
+			if (elem->eoi_time <= info->eoi_time)
+				break;
+		}
+		list_add(&info->eoi_list, &elem->eoi_list);
+	}
+
+	spin_unlock_irqrestore(&eoi->eoi_list_lock, flags);
+}
+
+static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
+{
+	evtchn_port_t evtchn;
+	unsigned int cpu;
+	unsigned int delay = 0;
+
+	evtchn = info->evtchn;
+	if (!VALID_EVTCHN(evtchn) || !list_empty(&info->eoi_list))
+		return;
+
+	if (spurious) {
+		if ((1 << info->spurious_cnt) < (HZ << 2))
+			info->spurious_cnt++;
+		if (info->spurious_cnt > 1) {
+			delay = 1 << (info->spurious_cnt - 2);
+			if (delay > HZ)
+				delay = HZ;
+			if (!info->eoi_time)
+				info->eoi_cpu = smp_processor_id();
+			info->eoi_time = get_jiffies_64() + delay;
+		}
+	} else {
+		info->spurious_cnt = 0;
+	}
+
+	cpu = info->eoi_cpu;
+	if (info->eoi_time &&
+	    (info->irq_epoch == per_cpu(irq_epoch, cpu) || delay)) {
+		lateeoi_list_add(info);
+		return;
+	}
+
+	info->eoi_time = 0;
+	do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
+}
+
+static void xen_irq_lateeoi_worker(struct work_struct *work)
+{
+	struct lateeoi_work *eoi;
+	struct irq_info *info;
+	u64 now = get_jiffies_64();
+	unsigned long flags;
+
+	eoi = container_of(to_delayed_work(work), struct lateeoi_work, delayed);
+
+	read_lock_irqsave(&evtchn_rwlock, flags);
+
+	while (true) {
+		spin_lock(&eoi->eoi_list_lock);
+
+		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);
+			break;
+		}
+
+		list_del_init(&info->eoi_list);
+
+		spin_unlock(&eoi->eoi_list_lock);
+
+		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);
+
+	read_unlock_irqrestore(&evtchn_rwlock, flags);
+}
+
+static void xen_cpu_init_eoi(unsigned int cpu)
+{
+	struct lateeoi_work *eoi = &per_cpu(lateeoi, cpu);
+
+	INIT_DELAYED_WORK(&eoi->delayed, xen_irq_lateeoi_worker);
+	spin_lock_init(&eoi->eoi_list_lock);
+	INIT_LIST_HEAD(&eoi->eoi_list);
+}
+
+void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
+{
+	struct irq_info *info;
+	unsigned long flags;
+
+	read_lock_irqsave(&evtchn_rwlock, flags);
+
+	info = info_for_irq(irq);
+
+	if (info)
+		xen_irq_lateeoi_locked(info, eoi_flags & XEN_EOI_FLAG_SPURIOUS);
+
+	read_unlock_irqrestore(&evtchn_rwlock, flags);
+}
+EXPORT_SYMBOL_GPL(xen_irq_lateeoi);
+
 static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;
+
 #ifdef CONFIG_SMP
 	/* By default all event channels notify CPU#0. */
 	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0));
@@ -384,8 +615,9 @@ static void xen_irq_init(unsigned irq)
 	info->type = IRQT_UNBOUND;
 	info->refcnt = -1;
 
-	irq_set_chip_data(irq, info);
+	set_info_for_irq(irq, info);
 
+	INIT_LIST_HEAD(&info->eoi_list);
 	list_add_tail(&info->list, &xen_irq_list_head);
 }
 
@@ -433,17 +665,25 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
 
 static void xen_free_irq(unsigned irq)
 {
-	struct irq_info *info = irq_get_chip_data(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);
 
-	irq_set_chip_data(irq, NULL);
+	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. */
@@ -462,6 +702,12 @@ static void xen_evtchn_close(unsigned int port)
 		BUG();
 }
 
+static void event_handler_exit(struct irq_info *info)
+{
+	smp_store_release(&info->is_active, 0);
+	clear_evtchn(info->evtchn);
+}
+
 static void pirq_query_unmask(int irq)
 {
 	struct physdev_irq_status_query irq_status;
@@ -480,7 +726,8 @@ static void pirq_query_unmask(int irq)
 
 static void eoi_pirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	int evtchn = info ? info->evtchn : 0;
 	struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
 	int rc = 0;
 
@@ -489,16 +736,15 @@ static void eoi_pirq(struct irq_data *data)
 
 	if (unlikely(irqd_is_setaffinity_pending(data)) &&
 	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
+		do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 
 		irq_move_masked_irq(data);
 
-		if (!masked)
-			unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 	} else
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 
 	if (pirq_needs_eoi(data->irq)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
@@ -549,7 +795,8 @@ static unsigned int __startup_pirq(unsigned int irq)
 		goto err;
 
 out:
-	unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_EXPLICIT);
+
 	eoi_pirq(irq_get_irq_data(irq));
 
 	return 0;
@@ -576,7 +823,7 @@ static void shutdown_pirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	mask_evtchn(evtchn);
+	do_mask(info, EVT_MASK_REASON_EXPLICIT);
 	xen_evtchn_close(evtchn);
 	xen_irq_info_cleanup(info);
 }
@@ -610,7 +857,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi);
 static void __unbind_from_irq(unsigned int irq)
 {
 	int evtchn = evtchn_from_irq(irq);
-	struct irq_info *info = irq_get_chip_data(irq);
+	struct irq_info *info = info_for_irq(irq);
 
 	if (info->refcnt > 0) {
 		info->refcnt--;
@@ -835,7 +1082,7 @@ int xen_pirq_from_irq(unsigned irq)
 }
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 
-int bind_evtchn_to_irq(unsigned int evtchn)
+static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip)
 {
 	int irq;
 	int ret;
@@ -852,7 +1099,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 		if (irq < 0)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+		irq_set_chip_and_handler_name(irq, chip,
 					      handle_edge_irq, "event");
 
 		ret = xen_irq_info_evtchn_setup(irq, evtchn);
@@ -873,8 +1120,19 @@ out:
 
 	return irq;
 }
+
+int bind_evtchn_to_irq(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
+
 static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
@@ -916,8 +1174,9 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 	return irq;
 }
 
-int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-				   unsigned int remote_port)
+static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain,
+					       evtchn_port_t remote_port,
+					       struct irq_chip *chip)
 {
 	struct evtchn_bind_interdomain bind_interdomain;
 	int err;
@@ -928,10 +1187,26 @@ int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
 	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
 					  &bind_interdomain);
 
-	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+	return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port,
+					       chip);
+}
+
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   evtchn_port_t remote_port)
+{
+	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						   &xen_dynamic_chip);
 }
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq);
 
+int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
+					   evtchn_port_t remote_port)
+{
+	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						   &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi);
+
 static int find_virq(unsigned int virq, unsigned int cpu)
 {
 	struct evtchn_status status;
@@ -1027,14 +1302,15 @@ static void unbind_from_irq(unsigned int irq)
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
-int bind_evtchn_to_irqhandler(unsigned int evtchn,
-			      irq_handler_t handler,
-			      unsigned long irqflags,
-			      const char *devname, void *dev_id)
+static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname, void *dev_id,
+					  struct irq_chip *chip)
 {
 	int irq, retval;
 
-	irq = bind_evtchn_to_irq(evtchn);
+	irq = bind_evtchn_to_irq_chip(evtchn, chip);
 	if (irq < 0)
 		return irq;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
@@ -1045,18 +1321,38 @@ int bind_evtchn_to_irqhandler(unsigned int evtchn,
 
 	return irq;
 }
+
+int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
+			      irq_handler_t handler,
+			      unsigned long irqflags,
+			      const char *devname, void *dev_id)
+{
+	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
+					      devname, dev_id,
+					      &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
 
-int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
-					  unsigned int remote_port,
-					  irq_handler_t handler,
-					  unsigned long irqflags,
-					  const char *devname,
-					  void *dev_id)
+int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn,
+				      irq_handler_t handler,
+				      unsigned long irqflags,
+				      const char *devname, void *dev_id)
+{
+	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
+					      devname, dev_id,
+					      &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler_lateeoi);
+
+static int bind_interdomain_evtchn_to_irqhandler_chip(
+		unsigned int remote_domain, evtchn_port_t remote_port,
+		irq_handler_t handler, unsigned long irqflags,
+		const char *devname, void *dev_id, struct irq_chip *chip)
 {
 	int irq, retval;
 
-	irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+	irq = bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						  chip);
 	if (irq < 0)
 		return irq;
 
@@ -1068,8 +1364,33 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
 
 	return irq;
 }
+
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+					  evtchn_port_t remote_port,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname,
+					  void *dev_id)
+{
+	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
+				remote_port, handler, irqflags, devname,
+				dev_id, &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
 
+int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
+						  evtchn_port_t remote_port,
+						  irq_handler_t handler,
+						  unsigned long irqflags,
+						  const char *devname,
+						  void *dev_id)
+{
+	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
+				remote_port, handler, irqflags, devname,
+				dev_id, &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler_lateeoi);
+
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
 			    unsigned long irqflags, const char *devname, void *dev_id)
@@ -1114,7 +1435,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 
 void unbind_from_irqhandler(unsigned int irq, void *dev_id)
 {
-	struct irq_info *info = irq_get_chip_data(irq);
+	struct irq_info *info = info_for_irq(irq);
 
 	if (WARN_ON(!info))
 		return;
@@ -1148,7 +1469,7 @@ int evtchn_make_refcounted(unsigned int evtchn)
 	if (irq == -1)
 		return -ENOENT;
 
-	info = irq_get_chip_data(irq);
+	info = info_for_irq(irq);
 
 	if (!info)
 		return -ENOENT;
@@ -1176,13 +1497,13 @@ int evtchn_get(unsigned int evtchn)
 	if (irq == -1)
 		goto done;
 
-	info = irq_get_chip_data(irq);
+	info = info_for_irq(irq);
 
 	if (!info)
 		goto done;
 
 	err = -EINVAL;
-	if (info->refcnt <= 0)
+	if (info->refcnt <= 0 || info->refcnt == SHRT_MAX)
 		goto done;
 
 	info->refcnt++;
@@ -1220,6 +1541,56 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
 	notify_remote_via_irq(irq);
 }
 
+struct evtchn_loop_ctrl {
+	ktime_t timeout;
+	unsigned count;
+	bool defer_eoi;
+};
+
+void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl)
+{
+	int irq;
+	struct irq_info *info;
+
+	irq = get_evtchn_to_irq(port);
+	if (irq == -1)
+		return;
+
+	/*
+	 * Check for timeout every 256 events.
+	 * We are setting the timeout value only after the first 256
+	 * events in order to not hurt the common case of few loop
+	 * iterations. The 256 is basically an arbitrary value.
+	 *
+	 * In case we are hitting the timeout we need to defer all further
+	 * EOIs in order to ensure to leave the event handling loop rather
+	 * sooner than later.
+	 */
+	if (!ctrl->defer_eoi && !(++ctrl->count & 0xff)) {
+		ktime_t kt = ktime_get();
+
+		if (!ctrl->timeout.tv64) {
+			kt = ktime_add_ms(kt,
+					  jiffies_to_msecs(event_loop_timeout));
+			ctrl->timeout = kt;
+		} else if (kt.tv64 > ctrl->timeout.tv64) {
+			ctrl->defer_eoi = true;
+		}
+	}
+
+	info = info_for_irq(irq);
+	if (xchg_acquire(&info->is_active, 1))
+		return;
+
+	if (ctrl->defer_eoi) {
+		info->eoi_cpu = smp_processor_id();
+		info->irq_epoch = __this_cpu_read(irq_epoch);
+		info->eoi_time = get_jiffies_64() + event_eoi_delay;
+	}
+
+	generic_handle_irq(irq);
+}
+
 static DEFINE_PER_CPU(unsigned, xed_nesting_count);
 
 static void __xen_evtchn_do_upcall(void)
@@ -1227,6 +1598,9 @@ static void __xen_evtchn_do_upcall(void)
 	struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu);
 	int cpu = get_cpu();
 	unsigned count;
+	struct evtchn_loop_ctrl ctrl = { 0 };
+
+	read_lock(&evtchn_rwlock);
 
 	do {
 		vcpu_info->evtchn_upcall_pending = 0;
@@ -1234,7 +1608,7 @@ static void __xen_evtchn_do_upcall(void)
 		if (__this_cpu_inc_return(xed_nesting_count) - 1)
 			goto out;
 
-		xen_evtchn_handle_events(cpu);
+		xen_evtchn_handle_events(cpu, &ctrl);
 
 		BUG_ON(!irqs_disabled());
 
@@ -1243,6 +1617,14 @@ static void __xen_evtchn_do_upcall(void)
 	} while (count != 1 || vcpu_info->evtchn_upcall_pending);
 
 out:
+	read_unlock(&evtchn_rwlock);
+
+	/*
+	 * Increment irq_epoch only now to defer EOIs only for
+	 * xen_irq_lateeoi() invocations occurring from inside the loop
+	 * above.
+	 */
+	__this_cpu_inc(irq_epoch);
 
 	put_cpu();
 }
@@ -1305,8 +1687,8 @@ void rebind_evtchn_irq(int evtchn, int irq)
 static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 {
 	struct evtchn_bind_vcpu bind_vcpu;
-	int evtchn = evtchn_from_irq(irq);
-	int masked;
+	struct irq_info *info = info_for_irq(irq);
+	int evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return -1;
@@ -1322,7 +1704,7 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	 * Mask the event while changing the VCPU binding to prevent
 	 * it being delivered on an unexpected VCPU.
 	 */
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
 	/*
 	 * If this fails, it usually just indicates that we're dealing with a
@@ -1332,8 +1714,7 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
 		bind_evtchn_to_cpu(evtchn, tcpu);
 
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 0;
 }
@@ -1348,39 +1729,41 @@ static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 
 static void enable_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void disable_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		mask_evtchn(evtchn);
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
 }
 
 static void ack_dynirq(struct irq_data *data)
 {
-	int evtchn = evtchn_from_irq(data->irq);
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
 	if (unlikely(irqd_is_setaffinity_pending(data)) &&
 	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
+		do_mask(info, EVT_MASK_REASON_TEMPORARY);
 
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 
 		irq_move_masked_irq(data);
 
-		if (!masked)
-			unmask_evtchn(evtchn);
+		do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 	} else
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
@@ -1389,18 +1772,39 @@ static void mask_ack_dynirq(struct irq_data *data)
 	ack_dynirq(data);
 }
 
+static void lateeoi_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
+		ack_dynirq(data);
+	}
+}
+
+static void lateeoi_mask_ack_dynirq(struct irq_data *data)
+{
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+	if (VALID_EVTCHN(evtchn)) {
+		do_mask(info, EVT_MASK_REASON_EXPLICIT);
+		ack_dynirq(data);
+	}
+}
+
 static int retrigger_dynirq(struct irq_data *data)
 {
-	unsigned int evtchn = evtchn_from_irq(data->irq);
-	int masked;
+	struct irq_info *info = info_for_irq(data->irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (!VALID_EVTCHN(evtchn))
 		return 0;
 
-	masked = test_and_set_mask(evtchn);
+	do_mask(info, EVT_MASK_REASON_TEMPORARY);
 	set_evtchn(evtchn);
-	if (!masked)
-		unmask_evtchn(evtchn);
+	do_unmask(info, EVT_MASK_REASON_TEMPORARY);
 
 	return 1;
 }
@@ -1495,10 +1899,11 @@ static void restore_cpu_ipis(unsigned int cpu)
 /* Clear an irq's pending state, in preparation for polling on it */
 void xen_clear_irq_pending(int irq)
 {
-	int evtchn = evtchn_from_irq(irq);
+	struct irq_info *info = info_for_irq(irq);
+	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
 	if (VALID_EVTCHN(evtchn))
-		clear_evtchn(evtchn);
+		event_handler_exit(info);
 }
 EXPORT_SYMBOL(xen_clear_irq_pending);
 void xen_set_irq_pending(int irq)
@@ -1599,6 +2004,21 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.irq_retrigger		= retrigger_dynirq,
 };
 
+static struct irq_chip xen_lateeoi_chip __read_mostly = {
+	/* The chip name needs to contain "xen-dyn" for irqbalance to work. */
+	.name			= "xen-dyn-lateeoi",
+
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= lateeoi_ack_dynirq,
+	.irq_mask_ack		= lateeoi_mask_ack_dynirq,
+
+	.irq_set_affinity	= set_affinity_irq,
+	.irq_retrigger		= retrigger_dynirq,
+};
+
 static struct irq_chip xen_pirq_chip __read_mostly = {
 	.name			= "xen-pirq",
 
@@ -1666,12 +2086,55 @@ void xen_callback_vector(void)
 void xen_callback_vector(void) {}
 #endif
 
-#undef MODULE_PARAM_PREFIX
-#define MODULE_PARAM_PREFIX "xen."
-
 static bool fifo_events = true;
 module_param(fifo_events, bool, 0);
 
+static int xen_evtchn_cpu_prepare(unsigned int cpu)
+{
+	int ret = 0;
+
+	xen_cpu_init_eoi(cpu);
+
+	if (evtchn_ops->percpu_init)
+		ret = evtchn_ops->percpu_init(cpu);
+
+	return ret;
+}
+
+static int xen_evtchn_cpu_dead(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (evtchn_ops->percpu_deinit)
+		ret = evtchn_ops->percpu_deinit(cpu);
+
+	return ret;
+}
+
+static int evtchn_cpu_notification(struct notifier_block *self,
+				   unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	int ret = 0;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+		ret = xen_evtchn_cpu_prepare(cpu);
+		break;
+	case CPU_DEAD:
+		ret = xen_evtchn_cpu_dead(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return ret < 0 ? NOTIFY_BAD : NOTIFY_OK;
+}
+
+static struct notifier_block evtchn_cpu_notifier = {
+	.notifier_call  = evtchn_cpu_notification,
+};
+
 void __init xen_init_IRQ(void)
 {
 	int ret = -EINVAL;
@@ -1681,6 +2144,10 @@ void __init xen_init_IRQ(void)
 	if (ret < 0)
 		xen_evtchn_2l_init();
 
+	xen_cpu_init_eoi(smp_processor_id());
+
+	register_cpu_notifier(&evtchn_cpu_notifier);
+
 	evtchn_to_irq = kcalloc(EVTCHN_ROW(xen_evtchn_max_channels()),
 				sizeof(*evtchn_to_irq), GFP_KERNEL);
 	BUG_ON(!evtchn_to_irq);