Merge branch 'next' into for-linus

5 files changed, 617 insertions, 399 deletions

diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index c3b99def9cb..1150c6d5c7b 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -85,7 +85,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 
 static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx)
 {
-	union ioapic_redir_entry *pent;
+	union kvm_ioapic_redirect_entry *pent;
 	int injected = -1;
 
 	pent = &ioapic->redirtbl[idx];
@@ -95,8 +95,6 @@ static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int 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;
 }
@@ -136,155 +134,47 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		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))
+		if (ioapic->redirtbl[index].fields.trig_mode == IOAPIC_LEVEL_TRIG
+		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index);
 		break;
 	}
 }
 
-static int ioapic_inj_irq(struct kvm_ioapic *ioapic,
-			   struct kvm_vcpu *vcpu,
-			   u8 vector, u8 trig_mode, u8 delivery_mode)
-{
-	ioapic_debug("irq %d trig %d deliv %d\n", vector, trig_mode,
-		     delivery_mode);
-
-	ASSERT((delivery_mode == IOAPIC_FIXED) ||
-	       (delivery_mode == IOAPIC_LOWEST_PRIORITY));
-
-	return kvm_apic_set_irq(vcpu, vector, trig_mode);
-}
-
-static void ioapic_inj_nmi(struct kvm_vcpu *vcpu)
-{
-	kvm_inject_nmi(vcpu);
-	kvm_vcpu_kick(vcpu);
-}
-
-u32 kvm_ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest,
-				    u8 dest_mode)
-{
-	u32 mask = 0;
-	int i;
-	struct kvm *kvm = ioapic->kvm;
-	struct kvm_vcpu *vcpu;
-
-	ioapic_debug("dest %d dest_mode %d\n", dest, dest_mode);
-
-	if (dest_mode == 0) {	/* Physical mode. */
-		if (dest == 0xFF) {	/* Broadcast. */
-			for (i = 0; i < KVM_MAX_VCPUS; ++i)
-				if (kvm->vcpus[i] && kvm->vcpus[i]->arch.apic)
-					mask |= 1 << i;
-			return mask;
-		}
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (!vcpu)
-				continue;
-			if (kvm_apic_match_physical_addr(vcpu->arch.apic, dest)) {
-				if (vcpu->arch.apic)
-					mask = 1 << i;
-				break;
-			}
-		}
-	} else if (dest != 0)	/* Logical mode, MDA non-zero. */
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (!vcpu)
-				continue;
-			if (vcpu->arch.apic &&
-			    kvm_apic_match_logical_addr(vcpu->arch.apic, dest))
-				mask |= 1 << vcpu->vcpu_id;
-		}
-	ioapic_debug("mask %x\n", mask);
-	return mask;
-}
-
 static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 {
-	u8 dest = ioapic->redirtbl[irq].fields.dest_id;
-	u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode;
-	u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode;
-	u8 vector = ioapic->redirtbl[irq].fields.vector;
-	u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode;
-	u32 deliver_bitmask;
-	struct kvm_vcpu *vcpu;
-	int vcpu_id, r = -1;
+	union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
+	struct kvm_lapic_irq irqe;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
-		     dest, dest_mode, delivery_mode, vector, trig_mode);
-
-	deliver_bitmask = kvm_ioapic_get_delivery_bitmask(ioapic, dest,
-							  dest_mode);
-	if (!deliver_bitmask) {
-		ioapic_debug("no target on destination\n");
-		return 0;
-	}
+		     entry->fields.dest, entry->fields.dest_mode,
+		     entry->fields.delivery_mode, entry->fields.vector,
+		     entry->fields.trig_mode);
+
+	irqe.dest_id = entry->fields.dest_id;
+	irqe.vector = entry->fields.vector;
+	irqe.dest_mode = entry->fields.dest_mode;
+	irqe.trig_mode = entry->fields.trig_mode;
+	irqe.delivery_mode = entry->fields.delivery_mode << 8;
+	irqe.level = 1;
+	irqe.shorthand = 0;
 
-	switch (delivery_mode) {
-	case IOAPIC_LOWEST_PRIORITY:
-		vcpu = kvm_get_lowest_prio_vcpu(ioapic->kvm, vector,
-				deliver_bitmask);
 #ifdef CONFIG_X86
-		if (irq == 0)
-			vcpu = ioapic->kvm->vcpus[0];
-#endif
-		if (vcpu != NULL)
-			r = ioapic_inj_irq(ioapic, vcpu, vector,
-				       trig_mode, delivery_mode);
-		else
-			ioapic_debug("null lowest prio vcpu: "
-				     "mask=%x vector=%x delivery_mode=%x\n",
-				     deliver_bitmask, vector, IOAPIC_LOWEST_PRIORITY);
-		break;
-	case IOAPIC_FIXED:
-#ifdef CONFIG_X86
-		if (irq == 0)
-			deliver_bitmask = 1;
-#endif
-		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 += ioapic_inj_irq(ioapic, vcpu, vector,
-					       trig_mode, delivery_mode);
-			}
-		}
-		break;
-	case IOAPIC_NMI:
-		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) {
-				ioapic_inj_nmi(vcpu);
-				r = 1;
-			}
-			else
-				ioapic_debug("NMI to vcpu %d failed\n",
-						vcpu->vcpu_id);
-		}
-		break;
-	default:
-		printk(KERN_WARNING "Unsupported delivery mode %d\n",
-		       delivery_mode);
-		break;
+	/* Always delivery PIT interrupt to vcpu 0 */
+	if (irq == 0) {
+		irqe.dest_mode = 0; /* Physical mode. */
+		irqe.dest_id = ioapic->kvm->vcpus[0]->vcpu_id;
 	}
-	return r;
+#endif
+	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
 }
 
 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;
+	union kvm_ioapic_redirect_entry entry;
 	int ret = 1;
 
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
@@ -293,9 +183,10 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 		if (!level)
 			ioapic->irr &= ~mask;
 		else {
+			int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
 			ioapic->irr |= mask;
-			if ((!entry.fields.trig_mode && old_irr != ioapic->irr)
-			    || !entry.fields.remote_irr)
+			if ((edge && old_irr != ioapic->irr) ||
+			    (!edge && !entry.fields.remote_irr))
 				ret = ioapic_service(ioapic, irq);
 		}
 	}
@@ -305,7 +196,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin,
 				    int trigger_mode)
 {
-	union ioapic_redir_entry *ent;
+	union kvm_ioapic_redirect_entry *ent;
 
 	ent = &ioapic->redirtbl[pin];
 
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index a34bd5e6436..7080b713c16 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -40,22 +40,7 @@ struct kvm_ioapic {
 	u32 id;
 	u32 irr;
 	u32 pad;
-	union ioapic_redir_entry {
-		u64 bits;
-		struct {
-			u8 vector;
-			u8 delivery_mode:3;
-			u8 dest_mode:1;
-			u8 delivery_status:1;
-			u8 polarity:1;
-			u8 remote_irr:1;
-			u8 trig_mode:1;
-			u8 mask:1;
-			u8 reserve:7;
-			u8 reserved[4];
-			u8 dest_id;
-		} fields;
-	} redirtbl[IOAPIC_NUM_PINS];
+	union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
@@ -79,13 +64,13 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
 	return kvm->arch.vioapic;
 }
 
-struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
-				       unsigned long bitmap);
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+		int short_hand, int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
 int kvm_ioapic_init(struct kvm *kvm);
 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);
-
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq);
 #endif
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 4c403750360..15147583abd 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -39,11 +39,16 @@ int kvm_iommu_map_pages(struct kvm *kvm,
 	pfn_t pfn;
 	int i, r = 0;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
+	int flags;
 
 	/* check if iommu exists and in use */
 	if (!domain)
 		return 0;
 
+	flags = IOMMU_READ | IOMMU_WRITE;
+	if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
+		flags |= IOMMU_CACHE;
+
 	for (i = 0; i < npages; i++) {
 		/* check if already mapped */
 		if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn)))
@@ -53,8 +58,7 @@ int kvm_iommu_map_pages(struct kvm *kvm,
 		r = iommu_map_range(domain,
 				    gfn_to_gpa(gfn),
 				    pfn_to_hpa(pfn),
-				    PAGE_SIZE,
-				    IOMMU_READ | IOMMU_WRITE);
+				    PAGE_SIZE, flags);
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%lx\n", pfn);
@@ -88,7 +92,7 @@ int kvm_assign_device(struct kvm *kvm,
 {
 	struct pci_dev *pdev = NULL;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
-	int r;
+	int r, last_flags;
 
 	/* check if iommu exists and in use */
 	if (!domain)
@@ -107,12 +111,29 @@ int kvm_assign_device(struct kvm *kvm,
 		return r;
 	}
 
+	last_flags = kvm->arch.iommu_flags;
+	if (iommu_domain_has_cap(kvm->arch.iommu_domain,
+				 IOMMU_CAP_CACHE_COHERENCY))
+		kvm->arch.iommu_flags |= KVM_IOMMU_CACHE_COHERENCY;
+
+	/* Check if need to update IOMMU page table for guest memory */
+	if ((last_flags ^ kvm->arch.iommu_flags) ==
+			KVM_IOMMU_CACHE_COHERENCY) {
+		kvm_iommu_unmap_memslots(kvm);
+		r = kvm_iommu_map_memslots(kvm);
+		if (r)
+			goto out_unmap;
+	}
+
 	printk(KERN_DEBUG "assign device: host bdf = %x:%x:%x\n",
 		assigned_dev->host_busnr,
 		PCI_SLOT(assigned_dev->host_devfn),
 		PCI_FUNC(assigned_dev->host_devfn));
 
 	return 0;
+out_unmap:
+	kvm_iommu_unmap_memslots(kvm);
+	return r;
 }
 
 int kvm_deassign_device(struct kvm *kvm,
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 864ac5483ba..ddc17f0e2f3 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -22,6 +22,9 @@
 #include <linux/kvm_host.h>
 
 #include <asm/msidef.h>
+#ifdef CONFIG_IA64
+#include <asm/iosapic.h>
+#endif
 
 #include "irq.h"
 
@@ -43,57 +46,73 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 	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)
+inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
 {
-	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);
-			}
+#ifdef CONFIG_IA64
+	return irq->delivery_mode ==
+		(IOSAPIC_LOWEST_PRIORITY << IOSAPIC_DELIVERY_SHIFT);
+#else
+	return irq->delivery_mode == APIC_DM_LOWEST;
+#endif
+}
+
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq)
+{
+	int i, r = -1;
+	struct kvm_vcpu *vcpu, *lowest = NULL;
+
+	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
+			kvm_is_dm_lowest_prio(irq))
+		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+
+	for (i = 0; i < KVM_MAX_VCPUS; i++) {
+		vcpu = kvm->vcpus[i];
+
+		if (!vcpu || !kvm_apic_present(vcpu))
+			continue;
+
+		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
+					irq->dest_id, irq->dest_mode))
+			continue;
+
+		if (!kvm_is_dm_lowest_prio(irq)) {
+			if (r < 0)
+				r = 0;
+			r += kvm_apic_set_irq(vcpu, irq);
+		} else {
+			if (!lowest)
+				lowest = vcpu;
+			else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+				lowest = vcpu;
 		}
-		break;
-	default:
-		break;
 	}
+
+	if (lowest)
+		r = kvm_apic_set_irq(lowest, irq);
+
 	return r;
 }
 
+static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		       struct kvm *kvm, int level)
+{
+	struct kvm_lapic_irq irq;
+
+	irq.dest_id = (e->msi.address_lo &
+			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	irq.vector = (e->msi.data &
+			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq.delivery_mode = e->msi.data & 0x700;
+	irq.level = 1;
+	irq.shorthand = 0;
+
+	/* TODO Deal with RH bit of MSI message address */
+	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
+}
+
 /* This should be called with the kvm->lock mutex held
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
@@ -141,7 +160,8 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 	unsigned gsi = pin;
 
 	list_for_each_entry(e, &kvm->irq_routing, link)
-		if (e->irqchip.irqchip == irqchip &&
+		if (e->type == KVM_IRQ_ROUTING_IRQCHIP &&
+		    e->irqchip.irqchip == irqchip &&
 		    e->irqchip.pin == pin) {
 			gsi = e->gsi;
 			break;
@@ -240,6 +260,7 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 	int delta;
 
 	e->gsi = ue->gsi;
+	e->type = ue->type;
 	switch (ue->type) {
 	case KVM_IRQ_ROUTING_IRQCHIP:
 		delta = 0;
@@ -252,7 +273,7 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			delta = 8;
 			break;
 		case KVM_IRQCHIP_IOAPIC:
-				e->set = kvm_set_ioapic_irq;
+			e->set = kvm_set_ioapic_irq;
 			break;
 		default:
 			goto out;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4d0dd390aa5..2884baf1d5f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -41,6 +41,8 @@
 #include <linux/pagemap.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
+#include <linux/bitops.h>
+#include <linux/spinlock.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -60,9 +62,6 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
-static int msi2intx = 1;
-module_param(msi2intx, bool, 0);
-
 DEFINE_SPINLOCK(kvm_lock);
 LIST_HEAD(vm_list);
 
@@ -95,38 +94,96 @@ static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *h
 	return NULL;
 }
 
+static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
+				    *assigned_dev, int irq)
+{
+	int i, index;
+	struct msix_entry *host_msix_entries;
+
+	host_msix_entries = assigned_dev->host_msix_entries;
+
+	index = -1;
+	for (i = 0; i < assigned_dev->entries_nr; i++)
+		if (irq == host_msix_entries[i].vector) {
+			index = i;
+			break;
+		}
+	if (index < 0) {
+		printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+		return 0;
+	}
+
+	return index;
+}
+
 static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev;
+	struct kvm *kvm;
+	int irq, i;
 
 	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
 				    interrupt_work);
+	kvm = assigned_dev->kvm;
 
 	/* This is taken to safely inject irq inside the guest. When
 	 * the interrupt injection (or the ioapic code) uses a
 	 * finer-grained lock, update this
 	 */
-	mutex_lock(&assigned_dev->kvm->lock);
-	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;
+	mutex_lock(&kvm->lock);
+	spin_lock_irq(&assigned_dev->assigned_dev_lock);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		struct kvm_guest_msix_entry *guest_entries =
+			assigned_dev->guest_msix_entries;
+		for (i = 0; i < assigned_dev->entries_nr; i++) {
+			if (!(guest_entries[i].flags &
+					KVM_ASSIGNED_MSIX_PENDING))
+				continue;
+			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
+			kvm_set_irq(assigned_dev->kvm,
+				    assigned_dev->irq_source_id,
+				    guest_entries[i].vector, 1);
+			irq = assigned_dev->host_msix_entries[i].vector;
+			if (irq != 0)
+				enable_irq(irq);
+			assigned_dev->host_irq_disabled = false;
+		}
+	} else {
+		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+			    assigned_dev->guest_irq, 1);
+		if (assigned_dev->irq_requested_type &
+				KVM_DEV_IRQ_GUEST_MSI) {
+			enable_irq(assigned_dev->host_irq);
+			assigned_dev->host_irq_disabled = false;
+		}
 	}
+
+	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
 	mutex_unlock(&assigned_dev->kvm->lock);
 }
 
 static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 {
+	unsigned long flags;
 	struct kvm_assigned_dev_kernel *assigned_dev =
 		(struct kvm_assigned_dev_kernel *) dev_id;
 
+	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int index = find_index_from_host_irq(assigned_dev, irq);
+		if (index < 0)
+			goto out;
+		assigned_dev->guest_msix_entries[index].flags |=
+			KVM_ASSIGNED_MSIX_PENDING;
+	}
+
 	schedule_work(&assigned_dev->interrupt_work);
 
 	disable_irq_nosync(irq);
 	assigned_dev->host_irq_disabled = true;
 
+out:
+	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -134,6 +191,7 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
 	struct kvm_assigned_dev_kernel *dev;
+	unsigned long flags;
 
 	if (kian->gsi == -1)
 		return;
@@ -146,28 +204,30 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 	/* The guest irq may be shared so this ack may be
 	 * from another device.
 	 */
+	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
 	if (dev->host_irq_disabled) {
 		enable_irq(dev->host_irq);
 		dev->host_irq_disabled = false;
 	}
+	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
 }
 
-/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
-static void kvm_free_assigned_irq(struct kvm *kvm,
-				  struct kvm_assigned_dev_kernel *assigned_dev)
+static void deassign_guest_irq(struct kvm *kvm,
+			       struct kvm_assigned_dev_kernel *assigned_dev)
 {
-	if (!irqchip_in_kernel(kvm))
-		return;
-
 	kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
+	assigned_dev->ack_notifier.gsi = -1;
 
 	if (assigned_dev->irq_source_id != -1)
 		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
 	assigned_dev->irq_source_id = -1;
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
+}
 
-	if (!assigned_dev->irq_requested_type)
-		return;
-
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void deassign_host_irq(struct kvm *kvm,
+			      struct kvm_assigned_dev_kernel *assigned_dev)
+{
 	/*
 	 * In kvm_free_device_irq, cancel_work_sync return true if:
 	 * 1. work is scheduled, and then cancelled.
@@ -184,17 +244,64 @@ static void kvm_free_assigned_irq(struct kvm *kvm,
 	 * now, the kvm state is still legal for probably we also have to wait
 	 * interrupt_work done.
 	 */
-	disable_irq_nosync(assigned_dev->host_irq);
-	cancel_work_sync(&assigned_dev->interrupt_work);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+		int i;
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			disable_irq_nosync(assigned_dev->
+					   host_msix_entries[i].vector);
+
+		cancel_work_sync(&assigned_dev->interrupt_work);
+
+		for (i = 0; i < assigned_dev->entries_nr; i++)
+			free_irq(assigned_dev->host_msix_entries[i].vector,
+				 (void *)assigned_dev);
+
+		assigned_dev->entries_nr = 0;
+		kfree(assigned_dev->host_msix_entries);
+		kfree(assigned_dev->guest_msix_entries);
+		pci_disable_msix(assigned_dev->dev);
+	} else {
+		/* Deal with MSI and INTx */
+		disable_irq_nosync(assigned_dev->host_irq);
+		cancel_work_sync(&assigned_dev->interrupt_work);
 
-	free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
 
-	if (assigned_dev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
-		pci_disable_msi(assigned_dev->dev);
+		if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
+			pci_disable_msi(assigned_dev->dev);
+	}
 
-	assigned_dev->irq_requested_type = 0;
+	assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
 }
 
+static int kvm_deassign_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *assigned_dev,
+			    unsigned long irq_requested_type)
+{
+	unsigned long guest_irq_type, host_irq_type;
+
+	if (!irqchip_in_kernel(kvm))
+		return -EINVAL;
+	/* no irq assignment to deassign */
+	if (!assigned_dev->irq_requested_type)
+		return -ENXIO;
+
+	host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
+	guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
+
+	if (host_irq_type)
+		deassign_host_irq(kvm, assigned_dev);
+	if (guest_irq_type)
+		deassign_guest_irq(kvm, assigned_dev);
+
+	return 0;
+}
+
+static void kvm_free_assigned_irq(struct kvm *kvm,
+				  struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
+}
 
 static void kvm_free_assigned_device(struct kvm *kvm,
 				     struct kvm_assigned_dev_kernel
@@ -226,190 +333,244 @@ void kvm_free_all_assigned_devices(struct kvm *kvm)
 	}
 }
 
-static int assigned_device_update_intx(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *adev,
-			struct kvm_assigned_irq *airq)
+static int assigned_device_enable_host_intx(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
 {
-	adev->guest_irq = airq->guest_irq;
-	adev->ack_notifier.gsi = airq->guest_irq;
+	dev->host_irq = dev->dev->irq;
+	/* Even though this is PCI, we don't want to use shared
+	 * interrupts. Sharing host devices with guest-assigned devices
+	 * on the same interrupt line is not a happy situation: there
+	 * are going to be long delays in accepting, acking, etc.
+	 */
+	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
+			0, "kvm_assigned_intx_device", (void *)dev))
+		return -EIO;
+	return 0;
+}
 
-	if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_INTX)
-		return 0;
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_host_msi(struct kvm *kvm,
+					   struct kvm_assigned_dev_kernel *dev)
+{
+	int r;
 
-	if (irqchip_in_kernel(kvm)) {
-		if (!msi2intx &&
-		    (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)) {
-			free_irq(adev->host_irq, (void *)adev);
-			pci_disable_msi(adev->dev);
-		}
+	if (!dev->dev->msi_enabled) {
+		r = pci_enable_msi(dev->dev);
+		if (r)
+			return r;
+	}
 
-		if (!capable(CAP_SYS_RAWIO))
-			return -EPERM;
+	dev->host_irq = dev->dev->irq;
+	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
+			"kvm_assigned_msi_device", (void *)dev)) {
+		pci_disable_msi(dev->dev);
+		return -EIO;
+	}
 
-		if (airq->host_irq)
-			adev->host_irq = airq->host_irq;
-		else
-			adev->host_irq = adev->dev->irq;
+	return 0;
+}
+#endif
 
-		/* Even though this is PCI, we don't want to use shared
-		 * interrupts. Sharing host devices with guest-assigned devices
-		 * on the same interrupt line is not a happy situation: there
-		 * are going to be long delays in accepting, acking, etc.
-		 */
-		if (request_irq(adev->host_irq, kvm_assigned_dev_intr,
-				0, "kvm_assigned_intx_device", (void *)adev))
-			return -EIO;
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_host_msix(struct kvm *kvm,
+					    struct kvm_assigned_dev_kernel *dev)
+{
+	int i, r = -EINVAL;
+
+	/* host_msix_entries and guest_msix_entries should have been
+	 * initialized */
+	if (dev->entries_nr == 0)
+		return r;
+
+	r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
+	if (r)
+		return r;
+
+	for (i = 0; i < dev->entries_nr; i++) {
+		r = request_irq(dev->host_msix_entries[i].vector,
+				kvm_assigned_dev_intr, 0,
+				"kvm_assigned_msix_device",
+				(void *)dev);
+		/* FIXME: free requested_irq's on failure */
+		if (r)
+			return r;
 	}
 
-	adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_INTX |
-				   KVM_ASSIGNED_DEV_HOST_INTX;
 	return 0;
 }
 
-#ifdef CONFIG_X86
-static int assigned_device_update_msi(struct kvm *kvm,
-			struct kvm_assigned_dev_kernel *adev,
-			struct kvm_assigned_irq *airq)
+#endif
+
+static int assigned_device_enable_guest_intx(struct kvm *kvm,
+				struct kvm_assigned_dev_kernel *dev,
+				struct kvm_assigned_irq *irq)
 {
-	int r;
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = irq->guest_irq;
+	return 0;
+}
 
-	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->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->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;
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_guest_msi(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	return 0;
+}
+#endif
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_guest_msix(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *dev,
+			struct kvm_assigned_irq *irq)
+{
+	dev->guest_irq = irq->guest_irq;
+	dev->ack_notifier.gsi = -1;
+	return 0;
+}
+#endif
+
+static int assign_host_irq(struct kvm *kvm,
+			   struct kvm_assigned_dev_kernel *dev,
+			   __u32 host_irq_type)
+{
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
+		return r;
+
+	switch (host_irq_type) {
+	case KVM_DEV_IRQ_HOST_INTX:
+		r = assigned_device_enable_host_intx(kvm, dev);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_HOST_MSI:
+		r = assigned_device_enable_host_msi(kvm, dev);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_HOST_MSIX:
+		r = assigned_device_enable_host_msix(kvm, dev);
+		break;
+#endif
+	default:
+		r = -EINVAL;
 	}
 
-	if (adev->irq_requested_type & KVM_ASSIGNED_DEV_HOST_MSI)
-		return 0;
+	if (!r)
+		dev->irq_requested_type |= host_irq_type;
 
-	if (irqchip_in_kernel(kvm)) {
-		if (!msi2intx) {
-			if (adev->irq_requested_type &
-					KVM_ASSIGNED_DEV_HOST_INTX)
-				free_irq(adev->host_irq, (void *)adev);
+	return r;
+}
 
-			r = pci_enable_msi(adev->dev);
-			if (r)
-				return r;
-		}
+static int assign_guest_irq(struct kvm *kvm,
+			    struct kvm_assigned_dev_kernel *dev,
+			    struct kvm_assigned_irq *irq,
+			    unsigned long guest_irq_type)
+{
+	int id;
+	int r = -EEXIST;
+
+	if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
+		return r;
 
-		adev->host_irq = adev->dev->irq;
-		if (request_irq(adev->host_irq, kvm_assigned_dev_intr, 0,
-				"kvm_assigned_msi_device", (void *)adev))
-			return -EIO;
+	id = kvm_request_irq_source_id(kvm);
+	if (id < 0)
+		return id;
+
+	dev->irq_source_id = id;
+
+	switch (guest_irq_type) {
+	case KVM_DEV_IRQ_GUEST_INTX:
+		r = assigned_device_enable_guest_intx(kvm, dev, irq);
+		break;
+#ifdef __KVM_HAVE_MSI
+	case KVM_DEV_IRQ_GUEST_MSI:
+		r = assigned_device_enable_guest_msi(kvm, dev, irq);
+		break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+	case KVM_DEV_IRQ_GUEST_MSIX:
+		r = assigned_device_enable_guest_msix(kvm, dev, irq);
+		break;
+#endif
+	default:
+		r = -EINVAL;
 	}
 
-	if (!msi2intx)
-		adev->irq_requested_type = KVM_ASSIGNED_DEV_GUEST_MSI;
+	if (!r) {
+		dev->irq_requested_type |= guest_irq_type;
+		kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+	} else
+		kvm_free_irq_source_id(kvm, dev->irq_source_id);
 
-	adev->irq_requested_type |= KVM_ASSIGNED_DEV_HOST_MSI;
-	return 0;
+	return r;
 }
-#endif
 
+/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
 static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
-				   struct kvm_assigned_irq
-				   *assigned_irq)
+				   struct kvm_assigned_irq *assigned_irq)
 {
-	int r = 0;
+	int r = -EINVAL;
 	struct kvm_assigned_dev_kernel *match;
-	u32 current_flags = 0, changed_flags;
+	unsigned long host_irq_type, guest_irq_type;
 
-	mutex_lock(&kvm->lock);
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
 
+	if (!irqchip_in_kernel(kvm))
+		return r;
+
+	mutex_lock(&kvm->lock);
+	r = -ENODEV;
 	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
 				      assigned_irq->assigned_dev_id);
-	if (!match) {
-		mutex_unlock(&kvm->lock);
-		return -EINVAL;
-	}
-
-	if (!match->irq_requested_type) {
-		INIT_WORK(&match->interrupt_work,
-				kvm_assigned_dev_interrupt_work_handler);
-		if (irqchip_in_kernel(kvm)) {
-			/* Register ack nofitier */
-			match->ack_notifier.gsi = -1;
-			match->ack_notifier.irq_acked =
-					kvm_assigned_dev_ack_irq;
-			kvm_register_irq_ack_notifier(kvm,
-					&match->ack_notifier);
-
-			/* Request IRQ source ID */
-			r = kvm_request_irq_source_id(kvm);
-			if (r < 0)
-				goto out_release;
-			else
-				match->irq_source_id = r;
-
-#ifdef CONFIG_X86
-			/* Determine host device irq type, we can know the
-			 * result from dev->msi_enabled */
-			if (msi2intx)
-				pci_enable_msi(match->dev);
-#endif
-		}
-	}
+	if (!match)
+		goto out;
 
-	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;
+	host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
+	guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
 
-	changed_flags = assigned_irq->flags ^ current_flags;
+	r = -EINVAL;
+	/* can only assign one type at a time */
+	if (hweight_long(host_irq_type) > 1)
+		goto out;
+	if (hweight_long(guest_irq_type) > 1)
+		goto out;
+	if (host_irq_type == 0 && guest_irq_type == 0)
+		goto out;
 
-	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);
-		if (r) {
-			printk(KERN_WARNING "kvm: failed to enable "
-					"MSI device!\n");
-			goto out_release;
-		}
-#else
-		r = -ENOTTY;
-#endif
-	} else if (assigned_irq->host_irq == 0 && match->dev->irq == 0) {
-		/* Host device IRQ 0 means don't support INTx */
-		if (!msi2intx) {
-			printk(KERN_WARNING
-			       "kvm: wait device to enable MSI!\n");
-			r = 0;
-		} else {
-			printk(KERN_WARNING
-			       "kvm: failed to enable MSI device!\n");
-			r = -ENOTTY;
-			goto out_release;
-		}
-	} else {
-		/* Non-sharing INTx mode */
-		r = assigned_device_update_intx(kvm, match, assigned_irq);
-		if (r) {
-			printk(KERN_WARNING "kvm: failed to enable "
-					"INTx device!\n");
-			goto out_release;
-		}
-	}
+	r = 0;
+	if (host_irq_type)
+		r = assign_host_irq(kvm, match, host_irq_type);
+	if (r)
+		goto out;
 
+	if (guest_irq_type)
+		r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
+out:
 	mutex_unlock(&kvm->lock);
 	return r;
-out_release:
+}
+
+static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
+					 struct kvm_assigned_irq
+					 *assigned_irq)
+{
+	int r = -ENODEV;
+	struct kvm_assigned_dev_kernel *match;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_irq->assigned_dev_id);
+	if (!match)
+		goto out;
+
+	r = kvm_deassign_irq(kvm, match, assigned_irq->flags);
+out:
 	mutex_unlock(&kvm->lock);
-	kvm_free_assigned_device(kvm, match);
 	return r;
 }
 
@@ -427,7 +588,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 				      assigned_dev->assigned_dev_id);
 	if (match) {
 		/* device already assigned */
-		r = -EINVAL;
+		r = -EEXIST;
 		goto out;
 	}
 
@@ -464,8 +625,12 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	match->host_devfn = assigned_dev->devfn;
 	match->flags = assigned_dev->flags;
 	match->dev = dev;
+	spin_lock_init(&match->assigned_dev_lock);
 	match->irq_source_id = -1;
 	match->kvm = kvm;
+	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+	INIT_WORK(&match->interrupt_work,
+		  kvm_assigned_dev_interrupt_work_handler);
 
 	list_add(&match->list, &kvm->arch.assigned_dev_head);
 
@@ -581,6 +746,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		cpumask_clear(cpus);
 
 	me = get_cpu();
+	spin_lock(&kvm->requests_lock);
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		vcpu = kvm->vcpus[i];
 		if (!vcpu)
@@ -597,6 +763,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		smp_call_function_many(cpus, ack_flush, NULL, 1);
 	else
 		called = false;
+	spin_unlock(&kvm->requests_lock);
 	put_cpu();
 	free_cpumask_var(cpus);
 	return called;
@@ -817,6 +984,7 @@ static struct kvm *kvm_create_vm(void)
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	spin_lock_init(&kvm->mmu_lock);
+	spin_lock_init(&kvm->requests_lock);
 	kvm_io_bus_init(&kvm->pio_bus);
 	mutex_init(&kvm->lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
@@ -878,6 +1046,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #endif
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
+#else
+	kvm_arch_flush_shadow(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	mmdrop(mm);
@@ -919,9 +1089,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 {
 	int r;
 	gfn_t base_gfn;
-	unsigned long npages;
-	int largepages;
-	unsigned long i;
+	unsigned long npages, ugfn;
+	unsigned long largepages, i;
 	struct kvm_memory_slot *memslot;
 	struct kvm_memory_slot old, new;
 
@@ -1010,6 +1179,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			new.lpage_info[0].write_count = 1;
 		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
 			new.lpage_info[largepages-1].write_count = 1;
+		ugfn = new.userspace_addr >> PAGE_SHIFT;
+		/*
+		 * If the gfn and userspace address are not aligned wrt each
+		 * other, disable large page support for this slot
+		 */
+		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1))
+			for (i = 0; i < largepages; ++i)
+				new.lpage_info[i].write_count = 1;
 	}
 
 	/* Allocate page dirty bitmap if needed */
@@ -1020,6 +1197,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if (!new.dirty_bitmap)
 			goto out_free;
 		memset(new.dirty_bitmap, 0, dirty_bytes);
+		if (old.npages)
+			kvm_arch_flush_shadow(kvm);
 	}
 #endif /* not defined CONFIG_S390 */
 
@@ -1043,8 +1222,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_free_physmem_slot(&old, npages ? &new : NULL);
 	/* Slot deletion case: we have to update the current slot */
+	spin_lock(&kvm->mmu_lock);
 	if (!npages)
 		*memslot = old;
+	spin_unlock(&kvm->mmu_lock);
 #ifdef CONFIG_DMAR
 	/* map the pages in iommu page table */
 	r = kvm_iommu_map_pages(kvm, base_gfn, npages);
@@ -1454,12 +1635,14 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-		if (kvm_cpu_has_interrupt(vcpu) ||
-		    kvm_cpu_has_pending_timer(vcpu) ||
-		    kvm_arch_vcpu_runnable(vcpu)) {
+		if ((kvm_arch_interrupt_allowed(vcpu) &&
+					kvm_cpu_has_interrupt(vcpu)) ||
+				kvm_arch_vcpu_runnable(vcpu)) {
 			set_bit(KVM_REQ_UNHALT, &vcpu->requests);
 			break;
 		}
+		if (kvm_cpu_has_pending_timer(vcpu))
+			break;
 		if (signal_pending(current))
 			break;
 
@@ -1593,6 +1776,88 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
 	return 0;
 }
 
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+				    struct kvm_assigned_msix_nr *entry_nr)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry_nr->assigned_dev_id);
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_nr_out;
+	}
+
+	if (adev->entries_nr == 0) {
+		adev->entries_nr = entry_nr->entry_nr;
+		if (adev->entries_nr == 0 ||
+		    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
+			r = -EINVAL;
+			goto msix_nr_out;
+		}
+
+		adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+						entry_nr->entry_nr,
+						GFP_KERNEL);
+		if (!adev->host_msix_entries) {
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+		adev->guest_msix_entries = kzalloc(
+				sizeof(struct kvm_guest_msix_entry) *
+				entry_nr->entry_nr, GFP_KERNEL);
+		if (!adev->guest_msix_entries) {
+			kfree(adev->host_msix_entries);
+			r = -ENOMEM;
+			goto msix_nr_out;
+		}
+	} else /* Not allowed set MSI-X number twice */
+		r = -EINVAL;
+msix_nr_out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+				       struct kvm_assigned_msix_entry *entry)
+{
+	int r = 0, i;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      entry->assigned_dev_id);
+
+	if (!adev) {
+		r = -EINVAL;
+		goto msix_entry_out;
+	}
+
+	for (i = 0; i < adev->entries_nr; i++)
+		if (adev->guest_msix_entries[i].vector == 0 ||
+		    adev->guest_msix_entries[i].entry == entry->entry) {
+			adev->guest_msix_entries[i].entry = entry->entry;
+			adev->guest_msix_entries[i].vector = entry->gsi;
+			adev->host_msix_entries[i].entry = entry->entry;
+			break;
+		}
+	if (i == adev->entries_nr) {
+		r = -ENOSPC;
+		goto msix_entry_out;
+	}
+
+msix_entry_out:
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+#endif
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -1864,6 +2129,11 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_ASSIGN_IRQ: {
+		r = -EOPNOTSUPP;
+		break;
+	}
+#ifdef KVM_CAP_ASSIGN_DEV_IRQ
+	case KVM_ASSIGN_DEV_IRQ: {
 		struct kvm_assigned_irq assigned_irq;
 
 		r = -EFAULT;
@@ -1874,6 +2144,18 @@ static long kvm_vm_ioctl(struct file *filp,
 			goto out;
 		break;
 	}
+	case KVM_DEASSIGN_DEV_IRQ: {
+		struct kvm_assigned_irq assigned_irq;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+			goto out;
+		r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
 #endif
 #ifdef KVM_CAP_DEVICE_DEASSIGNMENT
 	case KVM_DEASSIGN_PCI_DEVICE: {
@@ -1917,7 +2199,29 @@ static long kvm_vm_ioctl(struct file *filp,
 		vfree(entries);
 		break;
 	}
+#ifdef __KVM_HAVE_MSIX
+	case KVM_ASSIGN_SET_MSIX_NR: {
+		struct kvm_assigned_msix_nr entry_nr;
+		r = -EFAULT;
+		if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_SET_MSIX_ENTRY: {
+		struct kvm_assigned_msix_entry entry;
+		r = -EFAULT;
+		if (copy_from_user(&entry, argp, sizeof entry))
+			goto out;
+		r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+		if (r)
+			goto out;
+		break;
+	}
 #endif
+#endif /* KVM_CAP_IRQ_ROUTING */
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -2112,15 +2416,15 @@ EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot);
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
 {
-	if (val == SYS_RESTART) {
-		/*
-		 * Some (well, at least mine) BIOSes hang on reboot if
-		 * in vmx root mode.
-		 */
-		printk(KERN_INFO "kvm: exiting hardware virtualization\n");
-		kvm_rebooting = true;
-		on_each_cpu(hardware_disable, NULL, 1);
-	}
+	/*
+	 * Some (well, at least mine) BIOSes hang on reboot if
+	 * in vmx root mode.
+	 *
+	 * And Intel TXT required VMX off for all cpu when system shutdown.
+	 */
+	printk(KERN_INFO "kvm: exiting hardware virtualization\n");
+	kvm_rebooting = true;
+	on_each_cpu(hardware_disable, NULL, 1);
 	return NOTIFY_OK;
 }
 
@@ -2305,7 +2609,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		r = -ENOMEM;
 		goto out_free_0;
 	}
-	cpumask_clear(cpus_hardware_enabled);
 
 	r = kvm_arch_hardware_setup();
 	if (r < 0)
@@ -2354,9 +2657,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;
-#ifndef CONFIG_X86
-	msi2intx = 0;
-#endif
 
 	return 0;