Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

4 files changed, 380 insertions, 99 deletions

diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 23b81cf242a..c3b99def9cb 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -83,24 +83,28 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 	return result;
 }
 
-static void ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
+static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
 {
 	union ioapic_redir_entry *pent;
+	int injected = -1;
 
 	pent = &ioapic->redirtbl[idx];
 
 	if (!pent->fields.mask) {
-		int injected = ioapic_deliver(ioapic, idx);
+		injected = ioapic_deliver(ioapic, idx);
 		if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG)
 			pent->fields.remote_irr = 1;
 	}
 	if (!pent->fields.trig_mode)
 		ioapic->irr &= ~(1 << idx);
+
+	return injected;
 }
 
 static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
+	bool mask_before, mask_after;
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -120,6 +124,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		ioapic_debug("change redir index %x val %x\n", index, val);
 		if (index >= IOAPIC_NUM_PINS)
 			return;
+		mask_before = ioapic->redirtbl[index].fields.mask;
 		if (ioapic->ioregsel & 1) {
 			ioapic->redirtbl[index].bits &= 0xffffffff;
 			ioapic->redirtbl[index].bits |= (u64) val << 32;
@@ -128,6 +133,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			ioapic->redirtbl[index].bits |= (u32) val;
 			ioapic->redirtbl[index].fields.remote_irr = 0;
 		}
+		mask_after = ioapic->redirtbl[index].fields.mask;
+		if (mask_before != mask_after)
+			kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after);
 		if (ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index);
 		break;
@@ -202,7 +210,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode;
 	u32 deliver_bitmask;
 	struct kvm_vcpu *vcpu;
-	int vcpu_id, r = 0;
+	int vcpu_id, r = -1;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
@@ -242,7 +250,9 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 			deliver_bitmask &= ~(1 << vcpu_id);
 			vcpu = ioapic->kvm->vcpus[vcpu_id];
 			if (vcpu) {
-				r = ioapic_inj_irq(ioapic, vcpu, vector,
+				if (r < 0)
+					r = 0;
+				r += ioapic_inj_irq(ioapic, vcpu, vector,
 					       trig_mode, delivery_mode);
 			}
 		}
@@ -253,8 +263,10 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 				continue;
 			deliver_bitmask &= ~(1 << vcpu_id);
 			vcpu = ioapic->kvm->vcpus[vcpu_id];
-			if (vcpu)
+			if (vcpu) {
 				ioapic_inj_nmi(vcpu);
+				r = 1;
+			}
 			else
 				ioapic_debug("NMI to vcpu %d failed\n",
 						vcpu->vcpu_id);
@@ -268,11 +280,12 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	return r;
 }
 
-void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 {
 	u32 old_irr = ioapic->irr;
 	u32 mask = 1 << irq;
 	union ioapic_redir_entry entry;
+	int ret = 1;
 
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
 		entry = ioapic->redirtbl[irq];
@@ -283,25 +296,26 @@ void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 			ioapic->irr |= mask;
 			if ((!entry.fields.trig_mode && old_irr != ioapic->irr)
 			    || !entry.fields.remote_irr)
-				ioapic_service(ioapic, irq);
+				ret = ioapic_service(ioapic, irq);
 		}
 	}
+	return ret;
 }
 
-static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int gsi,
+static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin,
 				    int trigger_mode)
 {
 	union ioapic_redir_entry *ent;
 
-	ent = &ioapic->redirtbl[gsi];
+	ent = &ioapic->redirtbl[pin];
 
-	kvm_notify_acked_irq(ioapic->kvm, gsi);
+	kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin);
 
 	if (trigger_mode == IOAPIC_LEVEL_TRIG) {
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 		ent->fields.remote_irr = 0;
-		if (!ent->fields.mask && (ioapic->irr & (1 << gsi)))
-			ioapic_service(ioapic, gsi);
+		if (!ent->fields.mask && (ioapic->irr & (1 << pin)))
+			ioapic_service(ioapic, pin);
 	}
 }
 
@@ -426,3 +440,4 @@ int kvm_ioapic_init(struct kvm *kvm)
 	kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev);
 	return 0;
 }
+
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 49c9581d258..a34bd5e6436 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -83,7 +83,7 @@ struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
 				       unsigned long bitmap);
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
 int kvm_ioapic_init(struct kvm *kvm);
-void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
 u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
 				u8 dest_mode);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index aa5d1e5c497..864ac5483ba 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -20,35 +20,132 @@
  */
 
 #include <linux/kvm_host.h>
+
+#include <asm/msidef.h>
+
 #include "irq.h"
 
 #include "ioapic.h"
 
-/* This should be called with the kvm->lock mutex held */
-void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
+static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
+			   struct kvm *kvm, int level)
+{
+#ifdef CONFIG_X86
+	return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level);
+#else
+	return -1;
+#endif
+}
+
+static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
+			      struct kvm *kvm, int level)
+{
+	return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level);
+}
+
+static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		       struct kvm *kvm, int level)
+{
+	int vcpu_id, r = -1;
+	struct kvm_vcpu *vcpu;
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	int dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK)
+			>> MSI_ADDR_DEST_ID_SHIFT;
+	int vector = (e->msi.data & MSI_DATA_VECTOR_MASK)
+			>> MSI_DATA_VECTOR_SHIFT;
+	int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT,
+				(unsigned long *)&e->msi.address_lo);
+	int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT,
+				(unsigned long *)&e->msi.data);
+	int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT,
+				(unsigned long *)&e->msi.data);
+	u32 deliver_bitmask;
+
+	BUG_ON(!ioapic);
+
+	deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic,
+				dest_id, dest_mode);
+	/* IOAPIC delivery mode value is the same as MSI here */
+	switch (delivery_mode) {
+	case IOAPIC_LOWEST_PRIORITY:
+		vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
+				deliver_bitmask);
+		if (vcpu != NULL)
+			r = kvm_apic_set_irq(vcpu, vector, trig_mode);
+		else
+			printk(KERN_INFO "kvm: null lowest priority vcpu!\n");
+		break;
+	case IOAPIC_FIXED:
+		for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
+			if (!(deliver_bitmask & (1 << vcpu_id)))
+				continue;
+			deliver_bitmask &= ~(1 << vcpu_id);
+			vcpu = ioapic->kvm->vcpus[vcpu_id];
+			if (vcpu) {
+				if (r < 0)
+					r = 0;
+				r += kvm_apic_set_irq(vcpu, vector, trig_mode);
+			}
+		}
+		break;
+	default:
+		break;
+	}
+	return r;
+}
+
+/* This should be called with the kvm->lock mutex held
+ * Return value:
+ *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
+ *  = 0   Interrupt was coalesced (previous irq is still pending)
+ *  > 0   Number of CPUs interrupt was delivered to
+ */
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
 {
-	unsigned long *irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
+	struct kvm_kernel_irq_routing_entry *e;
+	unsigned long *irq_state, sig_level;
+	int ret = -1;
+
+	if (irq < KVM_IOAPIC_NUM_PINS) {
+		irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
 
-	/* Logical OR for level trig interrupt */
-	if (level)
-		set_bit(irq_source_id, irq_state);
-	else
-		clear_bit(irq_source_id, irq_state);
+		/* Logical OR for level trig interrupt */
+		if (level)
+			set_bit(irq_source_id, irq_state);
+		else
+			clear_bit(irq_source_id, irq_state);
+		sig_level = !!(*irq_state);
+	} else /* Deal with MSI/MSI-X */
+		sig_level = 1;
 
 	/* Not possible to detect if the guest uses the PIC or the
 	 * IOAPIC.  So set the bit in both. The guest will ignore
 	 * writes to the unused one.
 	 */
-	kvm_ioapic_set_irq(kvm->arch.vioapic, irq, !!(*irq_state));
-#ifdef CONFIG_X86
-	kvm_pic_set_irq(pic_irqchip(kvm), irq, !!(*irq_state));
-#endif
+	list_for_each_entry(e, &kvm->irq_routing, link)
+		if (e->gsi == irq) {
+			int r = e->set(e, kvm, sig_level);
+			if (r < 0)
+				continue;
+
+			ret = r + ((ret < 0) ? 0 : ret);
+		}
+	return ret;
 }
 
-void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi)
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
+	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_ack_notifier *kian;
 	struct hlist_node *n;
+	unsigned gsi = pin;
+
+	list_for_each_entry(e, &kvm->irq_routing, link)
+		if (e->irqchip.irqchip == irqchip &&
+		    e->irqchip.pin == pin) {
+			gsi = e->gsi;
+			break;
+		}
 
 	hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link)
 		if (kian->gsi == gsi)
@@ -99,3 +196,177 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 		clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
 }
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+				    struct kvm_irq_mask_notifier *kimn)
+{
+	kimn->irq = irq;
+	hlist_add_head(&kimn->link, &kvm->mask_notifier_list);
+}
+
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+				      struct kvm_irq_mask_notifier *kimn)
+{
+	hlist_del(&kimn->link);
+}
+
+void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
+{
+	struct kvm_irq_mask_notifier *kimn;
+	struct hlist_node *n;
+
+	hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link)
+		if (kimn->irq == irq)
+			kimn->func(kimn, mask);
+}
+
+static void __kvm_free_irq_routing(struct list_head *irq_routing)
+{
+	struct kvm_kernel_irq_routing_entry *e, *n;
+
+	list_for_each_entry_safe(e, n, irq_routing, link)
+		kfree(e);
+}
+
+void kvm_free_irq_routing(struct kvm *kvm)
+{
+	__kvm_free_irq_routing(&kvm->irq_routing);
+}
+
+static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+			       const struct kvm_irq_routing_entry *ue)
+{
+	int r = -EINVAL;
+	int delta;
+
+	e->gsi = ue->gsi;
+	switch (ue->type) {
+	case KVM_IRQ_ROUTING_IRQCHIP:
+		delta = 0;
+		switch (ue->u.irqchip.irqchip) {
+		case KVM_IRQCHIP_PIC_MASTER:
+			e->set = kvm_set_pic_irq;
+			break;
+		case KVM_IRQCHIP_PIC_SLAVE:
+			e->set = kvm_set_pic_irq;
+			delta = 8;
+			break;
+		case KVM_IRQCHIP_IOAPIC:
+				e->set = kvm_set_ioapic_irq;
+			break;
+		default:
+			goto out;
+		}
+		e->irqchip.irqchip = ue->u.irqchip.irqchip;
+		e->irqchip.pin = ue->u.irqchip.pin + delta;
+		break;
+	case KVM_IRQ_ROUTING_MSI:
+		e->set = kvm_set_msi;
+		e->msi.address_lo = ue->u.msi.address_lo;
+		e->msi.address_hi = ue->u.msi.address_hi;
+		e->msi.data = ue->u.msi.data;
+		break;
+	default:
+		goto out;
+	}
+	r = 0;
+out:
+	return r;
+}
+
+
+int kvm_set_irq_routing(struct kvm *kvm,
+			const struct kvm_irq_routing_entry *ue,
+			unsigned nr,
+			unsigned flags)
+{
+	struct list_head irq_list = LIST_HEAD_INIT(irq_list);
+	struct list_head tmp = LIST_HEAD_INIT(tmp);
+	struct kvm_kernel_irq_routing_entry *e = NULL;
+	unsigned i;
+	int r;
+
+	for (i = 0; i < nr; ++i) {
+		r = -EINVAL;
+		if (ue->gsi >= KVM_MAX_IRQ_ROUTES)
+			goto out;
+		if (ue->flags)
+			goto out;
+		r = -ENOMEM;
+		e = kzalloc(sizeof(*e), GFP_KERNEL);
+		if (!e)
+			goto out;
+		r = setup_routing_entry(e, ue);
+		if (r)
+			goto out;
+		++ue;
+		list_add(&e->link, &irq_list);
+		e = NULL;
+	}
+
+	mutex_lock(&kvm->lock);
+	list_splice(&kvm->irq_routing, &tmp);
+	INIT_LIST_HEAD(&kvm->irq_routing);
+	list_splice(&irq_list, &kvm->irq_routing);
+	INIT_LIST_HEAD(&irq_list);
+	list_splice(&tmp, &irq_list);
+	mutex_unlock(&kvm->lock);
+
+	r = 0;
+
+out:
+	kfree(e);
+	__kvm_free_irq_routing(&irq_list);
+	return r;
+}
+
+#define IOAPIC_ROUTING_ENTRY(irq) \
+	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
+	  .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) }
+#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
+
+#ifdef CONFIG_X86
+#  define PIC_ROUTING_ENTRY(irq) \
+	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
+	  .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 }
+#  define ROUTING_ENTRY2(irq) \
+	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
+#else
+#  define ROUTING_ENTRY2(irq) \
+	IOAPIC_ROUTING_ENTRY(irq)
+#endif
+
+static const struct kvm_irq_routing_entry default_routing[] = {
+	ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
+	ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
+	ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
+	ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
+	ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
+	ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
+	ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
+	ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
+	ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
+	ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
+	ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
+	ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
+#ifdef CONFIG_IA64
+	ROUTING_ENTRY1(24), ROUTING_ENTRY1(25),
+	ROUTING_ENTRY1(26), ROUTING_ENTRY1(27),
+	ROUTING_ENTRY1(28), ROUTING_ENTRY1(29),
+	ROUTING_ENTRY1(30), ROUTING_ENTRY1(31),
+	ROUTING_ENTRY1(32), ROUTING_ENTRY1(33),
+	ROUTING_ENTRY1(34), ROUTING_ENTRY1(35),
+	ROUTING_ENTRY1(36), ROUTING_ENTRY1(37),
+	ROUTING_ENTRY1(38), ROUTING_ENTRY1(39),
+	ROUTING_ENTRY1(40), ROUTING_ENTRY1(41),
+	ROUTING_ENTRY1(42), ROUTING_ENTRY1(43),
+	ROUTING_ENTRY1(44), ROUTING_ENTRY1(45),
+	ROUTING_ENTRY1(46), ROUTING_ENTRY1(47),
+#endif
+};
+
+int kvm_setup_default_irq_routing(struct kvm *kvm)
+{
+	return kvm_set_irq_routing(kvm, default_routing,
+				   ARRAY_SIZE(default_routing), 0);
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29a667ce35b..605697e9c4d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -47,10 +47,6 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
-#ifdef CONFIG_X86
-#include <asm/msidef.h>
-#endif
-
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 #include "coalesced_mmio.h"
 #endif
@@ -85,57 +81,6 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 static bool kvm_rebooting;
 
 #ifdef KVM_CAP_DEVICE_ASSIGNMENT
-
-#ifdef CONFIG_X86
-static void assigned_device_msi_dispatch(struct kvm_assigned_dev_kernel *dev)
-{
-	int vcpu_id;
-	struct kvm_vcpu *vcpu;
-	struct kvm_ioapic *ioapic = ioapic_irqchip(dev->kvm);
-	int dest_id = (dev->guest_msi.address_lo & MSI_ADDR_DEST_ID_MASK)
-			>> MSI_ADDR_DEST_ID_SHIFT;
-	int vector = (dev->guest_msi.data & MSI_DATA_VECTOR_MASK)
-			>> MSI_DATA_VECTOR_SHIFT;
-	int dest_mode = test_bit(MSI_ADDR_DEST_MODE_SHIFT,
-				(unsigned long *)&dev->guest_msi.address_lo);
-	int trig_mode = test_bit(MSI_DATA_TRIGGER_SHIFT,
-				(unsigned long *)&dev->guest_msi.data);
-	int delivery_mode = test_bit(MSI_DATA_DELIVERY_MODE_SHIFT,
-				(unsigned long *)&dev->guest_msi.data);
-	u32 deliver_bitmask;
-
-	BUG_ON(!ioapic);
-
-	deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic,
-				dest_id, dest_mode);
-	/* IOAPIC delivery mode value is the same as MSI here */
-	switch (delivery_mode) {
-	case IOAPIC_LOWEST_PRIORITY:
-		vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
-				deliver_bitmask);
-		if (vcpu != NULL)
-			kvm_apic_set_irq(vcpu, vector, trig_mode);
-		else
-			printk(KERN_INFO "kvm: null lowest priority vcpu!\n");
-		break;
-	case IOAPIC_FIXED:
-		for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) {
-			if (!(deliver_bitmask & (1 << vcpu_id)))
-				continue;
-			deliver_bitmask &= ~(1 << vcpu_id);
-			vcpu = ioapic->kvm->vcpus[vcpu_id];
-			if (vcpu)
-				kvm_apic_set_irq(vcpu, vector, trig_mode);
-		}
-		break;
-	default:
-		printk(KERN_INFO "kvm: unsupported MSI delivery mode\n");
-	}
-}
-#else
-static void assigned_device_msi_dispatch(struct kvm_assigned_dev_kernel *dev) {}
-#endif
-
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
 						      int assigned_dev_id)
 {
@@ -162,13 +107,10 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 	 * finer-grained lock, update this
 	 */
 	mutex_lock(&assigned_dev->kvm->lock);
-	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_INTX)
-		kvm_set_irq(assigned_dev->kvm,
-			    assigned_dev->irq_source_id,
-			    assigned_dev->guest_irq, 1);
-	else if (assigned_dev->irq_requested_type &
-				KVM_ASSIGNED_DEV_GUEST_MSI) {
-		assigned_device_msi_dispatch(assigned_dev);
+	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+		    assigned_dev->guest_irq, 1);
+
+	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI) {
 		enable_irq(assigned_dev->host_irq);
 		assigned_dev->host_irq_disabled = false;
 	}
@@ -331,18 +273,24 @@ static int assigned_device_update_msi(struct kvm *kvm,
 {
 	int r;
 
+	adev->guest_irq = airq->guest_irq;
 	if (airq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) {
 		/* x86 don't care upper address of guest msi message addr */
 		adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_MSI;
 		adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_INTX;
-		adev->guest_msi.address_lo = airq->guest_msi.addr_lo;
-		adev->guest_msi.data = airq->guest_msi.data;
 		adev->ack_notifier.gsi = -1;
 	} else if (msi2intx) {
 		adev->irq_requested_type |= KVM_ASSIGNED_DEV_GUEST_INTX;
 		adev->irq_requested_type &= ~KVM_ASSIGNED_DEV_GUEST_MSI;
-		adev->guest_irq = airq->guest_irq;
 		adev->ack_notifier.gsi = airq->guest_irq;
+	} else {
+		/*
+		 * Guest require to disable device MSI, we disable MSI and
+		 * re-enable INTx by default again. Notice it's only for
+		 * non-msi2intx.
+		 */
+		assigned_device_update_intx(kvm, adev, airq);
+		return 0;
 	}
 
 	if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
@@ -379,6 +327,7 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
 {
 	int r = 0;
 	struct kvm_assigned_dev_kernel *match;
+	u32 current_flags = 0, changed_flags;
 
 	mutex_lock(&kvm->lock);
 
@@ -416,8 +365,13 @@ static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
 		}
 	}
 
-	if ((!msi2intx &&
-	     (assigned_irq->flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI)) ||
+	if ((match->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI) &&
+		 (match->irq_requested_type & KVM_ASSIGNED_DEV_GUEST_MSI))
+		current_flags |= KVM_DEV_IRQ_ASSIGN_ENABLE_MSI;
+
+	changed_flags = assigned_irq->flags ^ current_flags;
+
+	if ((changed_flags & KVM_DEV_IRQ_ASSIGN_MSI_ACTION) ||
 	    (msi2intx && match->dev->msi_enabled)) {
 #ifdef CONFIG_X86
 		r = assigned_device_update_msi(kvm, match, assigned_irq);
@@ -563,7 +517,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
 		goto out;
 	}
 
-	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
+	if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)
 		kvm_deassign_device(kvm, match);
 
 	kvm_free_assigned_device(kvm, match);
@@ -581,8 +535,10 @@ static inline int valid_vcpu(int n)
 
 inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
-	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn));
+	if (pfn_valid(pfn)) {
+		struct page *page = compound_head(pfn_to_page(pfn));
+		return PageReserved(page);
+	}
 
 	return true;
 }
@@ -828,6 +784,10 @@ static struct kvm *kvm_create_vm(void)
 
 	if (IS_ERR(kvm))
 		goto out;
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+	INIT_LIST_HEAD(&kvm->irq_routing);
+	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+#endif
 
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -909,6 +869,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
 	spin_unlock(&kvm_lock);
+	kvm_free_irq_routing(kvm);
 	kvm_io_bus_destroy(&kvm->pio_bus);
 	kvm_io_bus_destroy(&kvm->mmio_bus);
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
@@ -1755,13 +1716,13 @@ out_free2:
 		r = 0;
 		break;
 	}
-	case KVM_DEBUG_GUEST: {
-		struct kvm_debug_guest dbg;
+	case KVM_SET_GUEST_DEBUG: {
+		struct kvm_guest_debug dbg;
 
 		r = -EFAULT;
 		if (copy_from_user(&dbg, argp, sizeof dbg))
 			goto out;
-		r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg);
+		r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
 		if (r)
 			goto out;
 		r = 0;
@@ -1929,6 +1890,36 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef KVM_CAP_IRQ_ROUTING
+	case KVM_SET_GSI_ROUTING: {
+		struct kvm_irq_routing routing;
+		struct kvm_irq_routing __user *urouting;
+		struct kvm_irq_routing_entry *entries;
+
+		r = -EFAULT;
+		if (copy_from_user(&routing, argp, sizeof(routing)))
+			goto out;
+		r = -EINVAL;
+		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+			goto out;
+		if (routing.flags)
+			goto out;
+		r = -ENOMEM;
+		entries = vmalloc(routing.nr * sizeof(*entries));
+		if (!entries)
+			goto out;
+		r = -EFAULT;
+		urouting = argp;
+		if (copy_from_user(entries, urouting->entries,
+				   routing.nr * sizeof(*entries)))
+			goto out_free_irq_routing;
+		r = kvm_set_irq_routing(kvm, entries, routing.nr,
+					routing.flags);
+	out_free_irq_routing:
+		vfree(entries);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -1995,6 +1986,10 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 		return 1;
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+	case KVM_CAP_IRQ_ROUTING:
+		return KVM_MAX_IRQ_ROUTES;
+#endif
 	default:
 		break;
 	}