Merge branch 'kvm-updates/2.6.28' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'kvm-updates/2.6.28' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (134 commits)
  KVM: ia64: Add intel iommu support for guests.
  KVM: ia64: add directed mmio range support for kvm guests
  KVM: ia64: Make pmt table be able to hold physical mmio entries.
  KVM: Move irqchip_in_kernel() from ioapic.h to irq.h
  KVM: Separate irq ack notification out of arch/x86/kvm/irq.c
  KVM: Change is_mmio_pfn to kvm_is_mmio_pfn, and make it common for all archs
  KVM: Move device assignment logic to common code
  KVM: Device Assignment: Move vtd.c from arch/x86/kvm/ to virt/kvm/
  KVM: VMX: enable invlpg exiting if EPT is disabled
  KVM: x86: Silence various LAPIC-related host kernel messages
  KVM: Device Assignment: Map mmio pages into VT-d page table
  KVM: PIC: enhance IPI avoidance
  KVM: MMU: add "oos_shadow" parameter to disable oos
  KVM: MMU: speed up mmu_unsync_walk
  KVM: MMU: out of sync shadow core
  KVM: MMU: mmu_convert_notrap helper
  KVM: MMU: awareness of new kvm_mmu_zap_page behaviour
  KVM: MMU: mmu_parent_walk
  KVM: x86: trap invlpg
  KVM: MMU: sync roots on mmu reload
  ...

6 files changed, 620 insertions, 75 deletions

diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index c0d22870ee9c..53772bb46320 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -39,6 +39,7 @@
 
 #include "ioapic.h"
 #include "lapic.h"
+#include "irq.h"
 
 #if 0
 #define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
@@ -285,26 +286,31 @@ void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	}
 }
 
-static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int gsi)
+static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int gsi,
+				    int trigger_mode)
 {
 	union ioapic_redir_entry *ent;
 
 	ent = &ioapic->redirtbl[gsi];
-	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);
+	kvm_notify_acked_irq(ioapic->kvm, gsi);
+
+	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);
+	}
 }
 
-void kvm_ioapic_update_eoi(struct kvm *kvm, int vector)
+void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 	int i;
 
 	for (i = 0; i < IOAPIC_NUM_PINS; i++)
 		if (ioapic->redirtbl[i].fields.vector == vector)
-			__kvm_ioapic_update_eoi(ioapic, i);
+			__kvm_ioapic_update_eoi(ioapic, i, trigger_mode);
 }
 
 static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr,
@@ -380,7 +386,7 @@ static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 		break;
 #ifdef	CONFIG_IA64
 	case IOAPIC_REG_EOI:
-		kvm_ioapic_update_eoi(ioapic->kvm, data);
+		kvm_ioapic_update_eoi(ioapic->kvm, data, IOAPIC_LEVEL_TRIG);
 		break;
 #endif
 
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 7f16675fe783..cd7ae7691c9d 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -58,6 +58,7 @@ struct kvm_ioapic {
 	} redirtbl[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
+	void (*ack_notifier)(void *opaque, int irq);
 };
 
 #ifdef DEBUG
@@ -78,16 +79,9 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
 	return kvm->arch.vioapic;
 }
 
-#ifdef CONFIG_IA64
-static inline int irqchip_in_kernel(struct kvm *kvm)
-{
-	return 1;
-}
-#endif
-
 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);
+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);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
new file mode 100644
index 000000000000..d0169f5e6047
--- /dev/null
+++ b/virt/kvm/irq_comm.c
@@ -0,0 +1,60 @@
+/*
+ * irq_comm.c: Common API for in kernel interrupt controller
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ * Authors:
+ *   Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *
+ */
+
+#include <linux/kvm_host.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, int level)
+{
+	/* 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, level);
+#ifdef CONFIG_X86
+	kvm_pic_set_irq(pic_irqchip(kvm), irq, level);
+#endif
+}
+
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi)
+{
+	struct kvm_irq_ack_notifier *kian;
+	struct hlist_node *n;
+
+	hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link)
+		if (kian->gsi == gsi)
+			kian->irq_acked(kian);
+}
+
+void kvm_register_irq_ack_notifier(struct kvm *kvm,
+				   struct kvm_irq_ack_notifier *kian)
+{
+	hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list);
+}
+
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+				     struct kvm_irq_ack_notifier *kian)
+{
+	hlist_del(&kian->link);
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7dd9b0b85e4e..cf0ab8ed3845 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -51,6 +51,12 @@
 #include "coalesced_mmio.h"
 #endif
 
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include "irq.h"
+#endif
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
@@ -71,11 +77,253 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 
 bool kvm_rebooting;
 
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
+						      int assigned_dev_id)
+{
+	struct list_head *ptr;
+	struct kvm_assigned_dev_kernel *match;
+
+	list_for_each(ptr, head) {
+		match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
+		if (match->assigned_dev_id == assigned_dev_id)
+			return match;
+	}
+	return NULL;
+}
+
+static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev;
+
+	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
+				    interrupt_work);
+
+	/* 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->guest_irq, 1);
+	mutex_unlock(&assigned_dev->kvm->lock);
+	kvm_put_kvm(assigned_dev->kvm);
+}
+
+/* FIXME: Implement the OR logic needed to make shared interrupts on
+ * this line behave properly
+ */
+static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
+{
+	struct kvm_assigned_dev_kernel *assigned_dev =
+		(struct kvm_assigned_dev_kernel *) dev_id;
+
+	kvm_get_kvm(assigned_dev->kvm);
+	schedule_work(&assigned_dev->interrupt_work);
+	disable_irq_nosync(irq);
+	return IRQ_HANDLED;
+}
+
+/* Ack the irq line for an assigned device */
+static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
+{
+	struct kvm_assigned_dev_kernel *dev;
+
+	if (kian->gsi == -1)
+		return;
+
+	dev = container_of(kian, struct kvm_assigned_dev_kernel,
+			   ack_notifier);
+	kvm_set_irq(dev->kvm, dev->guest_irq, 0);
+	enable_irq(dev->host_irq);
+}
+
+static void kvm_free_assigned_device(struct kvm *kvm,
+				     struct kvm_assigned_dev_kernel
+				     *assigned_dev)
+{
+	if (irqchip_in_kernel(kvm) && assigned_dev->irq_requested)
+		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
+
+	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
+
+	if (cancel_work_sync(&assigned_dev->interrupt_work))
+		/* We had pending work. That means we will have to take
+		 * care of kvm_put_kvm.
+		 */
+		kvm_put_kvm(kvm);
+
+	pci_release_regions(assigned_dev->dev);
+	pci_disable_device(assigned_dev->dev);
+	pci_dev_put(assigned_dev->dev);
+
+	list_del(&assigned_dev->list);
+	kfree(assigned_dev);
+}
+
+void kvm_free_all_assigned_devices(struct kvm *kvm)
+{
+	struct list_head *ptr, *ptr2;
+	struct kvm_assigned_dev_kernel *assigned_dev;
+
+	list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
+		assigned_dev = list_entry(ptr,
+					  struct kvm_assigned_dev_kernel,
+					  list);
+
+		kvm_free_assigned_device(kvm, assigned_dev);
+	}
+}
+
+static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
+				   struct kvm_assigned_irq
+				   *assigned_irq)
+{
+	int r = 0;
+	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) {
+		mutex_unlock(&kvm->lock);
+		return -EINVAL;
+	}
+
+	if (match->irq_requested) {
+		match->guest_irq = assigned_irq->guest_irq;
+		match->ack_notifier.gsi = assigned_irq->guest_irq;
+		mutex_unlock(&kvm->lock);
+		return 0;
+	}
+
+	INIT_WORK(&match->interrupt_work,
+		  kvm_assigned_dev_interrupt_work_handler);
+
+	if (irqchip_in_kernel(kvm)) {
+		if (!capable(CAP_SYS_RAWIO)) {
+			r = -EPERM;
+			goto out_release;
+		}
+
+		if (assigned_irq->host_irq)
+			match->host_irq = assigned_irq->host_irq;
+		else
+			match->host_irq = match->dev->irq;
+		match->guest_irq = assigned_irq->guest_irq;
+		match->ack_notifier.gsi = assigned_irq->guest_irq;
+		match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+		kvm_register_irq_ack_notifier(kvm, &match->ack_notifier);
+
+		/* 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(match->host_irq, kvm_assigned_dev_intr, 0,
+				"kvm_assigned_device", (void *)match)) {
+			r = -EIO;
+			goto out_release;
+		}
+	}
+
+	match->irq_requested = true;
+	mutex_unlock(&kvm->lock);
+	return r;
+out_release:
+	mutex_unlock(&kvm->lock);
+	kvm_free_assigned_device(kvm, match);
+	return r;
+}
+
+static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
+				      struct kvm_assigned_pci_dev *assigned_dev)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *match;
+	struct pci_dev *dev;
+
+	mutex_lock(&kvm->lock);
+
+	match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      assigned_dev->assigned_dev_id);
+	if (match) {
+		/* device already assigned */
+		r = -EINVAL;
+		goto out;
+	}
+
+	match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
+	if (match == NULL) {
+		printk(KERN_INFO "%s: Couldn't allocate memory\n",
+		       __func__);
+		r = -ENOMEM;
+		goto out;
+	}
+	dev = pci_get_bus_and_slot(assigned_dev->busnr,
+				   assigned_dev->devfn);
+	if (!dev) {
+		printk(KERN_INFO "%s: host device not found\n", __func__);
+		r = -EINVAL;
+		goto out_free;
+	}
+	if (pci_enable_device(dev)) {
+		printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
+		r = -EBUSY;
+		goto out_put;
+	}
+	r = pci_request_regions(dev, "kvm_assigned_device");
+	if (r) {
+		printk(KERN_INFO "%s: Could not get access to device regions\n",
+		       __func__);
+		goto out_disable;
+	}
+	match->assigned_dev_id = assigned_dev->assigned_dev_id;
+	match->host_busnr = assigned_dev->busnr;
+	match->host_devfn = assigned_dev->devfn;
+	match->dev = dev;
+
+	match->kvm = kvm;
+
+	list_add(&match->list, &kvm->arch.assigned_dev_head);
+
+	if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) {
+		r = kvm_iommu_map_guest(kvm, match);
+		if (r)
+			goto out_list_del;
+	}
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+out_list_del:
+	list_del(&match->list);
+	pci_release_regions(dev);
+out_disable:
+	pci_disable_device(dev);
+out_put:
+	pci_dev_put(dev);
+out_free:
+	kfree(match);
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+#endif
+
 static inline int valid_vcpu(int n)
 {
 	return likely(n >= 0 && n < KVM_MAX_VCPUS);
 }
 
+inline int kvm_is_mmio_pfn(pfn_t pfn)
+{
+	if (pfn_valid(pfn))
+		return PageReserved(pfn_to_page(pfn));
+
+	return true;
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */
@@ -570,6 +818,12 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	}
 
 	kvm_free_physmem_slot(&old, &new);
+#ifdef CONFIG_DMAR
+	/* map the pages in iommu page table */
+	r = kvm_iommu_map_pages(kvm, base_gfn, npages);
+	if (r)
+		goto out;
+#endif
 	return 0;
 
 out_free:
@@ -708,9 +962,6 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-/*
- * Requires current->mm->mmap_sem to be held
- */
 pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct page *page[1];
@@ -726,21 +977,24 @@ pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 		return page_to_pfn(bad_page);
 	}
 
-	npages = get_user_pages(current, current->mm, addr, 1, 1, 1, page,
-				NULL);
+	npages = get_user_pages_fast(addr, 1, 1, page);
 
 	if (unlikely(npages != 1)) {
 		struct vm_area_struct *vma;
 
+		down_read(&current->mm->mmap_sem);
 		vma = find_vma(current->mm, addr);
+
 		if (vma == NULL || addr < vma->vm_start ||
 		    !(vma->vm_flags & VM_PFNMAP)) {
+			up_read(&current->mm->mmap_sem);
 			get_page(bad_page);
 			return page_to_pfn(bad_page);
 		}
 
 		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
-		BUG_ON(pfn_valid(pfn));
+		up_read(&current->mm->mmap_sem);
+		BUG_ON(!kvm_is_mmio_pfn(pfn));
 	} else
 		pfn = page_to_pfn(page[0]);
 
@@ -754,10 +1008,10 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 	pfn_t pfn;
 
 	pfn = gfn_to_pfn(kvm, gfn);
-	if (pfn_valid(pfn))
+	if (!kvm_is_mmio_pfn(pfn))
 		return pfn_to_page(pfn);
 
-	WARN_ON(!pfn_valid(pfn));
+	WARN_ON(kvm_is_mmio_pfn(pfn));
 
 	get_page(bad_page);
 	return bad_page;
@@ -773,7 +1027,7 @@ EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
-	if (pfn_valid(pfn))
+	if (!kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
@@ -799,7 +1053,7 @@ EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
 
 void kvm_set_pfn_dirty(pfn_t pfn)
 {
-	if (pfn_valid(pfn)) {
+	if (!kvm_is_mmio_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
 		if (!PageReserved(page))
 			SetPageDirty(page);
@@ -809,14 +1063,14 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(pfn_t pfn)
 {
-	if (pfn_valid(pfn))
+	if (!kvm_is_mmio_pfn(pfn))
 		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
 
 void kvm_get_pfn(pfn_t pfn)
 {
-	if (pfn_valid(pfn))
+	if (!kvm_is_mmio_pfn(pfn))
 		get_page(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_get_pfn);
@@ -972,12 +1226,12 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-		if (kvm_cpu_has_interrupt(vcpu))
-			break;
-		if (kvm_cpu_has_pending_timer(vcpu))
-			break;
-		if (kvm_arch_vcpu_runnable(vcpu))
+		if (kvm_cpu_has_interrupt(vcpu) ||
+		    kvm_cpu_has_pending_timer(vcpu) ||
+		    kvm_arch_vcpu_runnable(vcpu)) {
+			set_bit(KVM_REQ_UNHALT, &vcpu->requests);
 			break;
+		}
 		if (signal_pending(current))
 			break;
 
@@ -1074,12 +1328,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 
 	r = kvm_arch_vcpu_setup(vcpu);
 	if (r)
-		goto vcpu_destroy;
+		return r;
 
 	mutex_lock(&kvm->lock);
 	if (kvm->vcpus[n]) {
 		r = -EEXIST;
-		mutex_unlock(&kvm->lock);
 		goto vcpu_destroy;
 	}
 	kvm->vcpus[n] = vcpu;
@@ -1095,8 +1348,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 unlink:
 	mutex_lock(&kvm->lock);
 	kvm->vcpus[n] = NULL;
-	mutex_unlock(&kvm->lock);
 vcpu_destroy:
+	mutex_unlock(&kvm->lock);
 	kvm_arch_vcpu_destroy(vcpu);
 	return r;
 }
@@ -1118,6 +1371,8 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
 	int r;
+	struct kvm_fpu *fpu = NULL;
+	struct kvm_sregs *kvm_sregs = NULL;
 
 	if (vcpu->kvm->mm != current->mm)
 		return -EIO;
@@ -1165,25 +1420,28 @@ out_free2:
 		break;
 	}
 	case KVM_GET_SREGS: {
-		struct kvm_sregs kvm_sregs;
-
-		memset(&kvm_sregs, 0, sizeof kvm_sregs);
-		r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs);
+		kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!kvm_sregs)
+			goto out;
+		r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs);
 		if (r)
 			goto out;
 		r = -EFAULT;
-		if (copy_to_user(argp, &kvm_sregs, sizeof kvm_sregs))
+		if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs)))
 			goto out;
 		r = 0;
 		break;
 	}
 	case KVM_SET_SREGS: {
-		struct kvm_sregs kvm_sregs;
-
+		kvm_sregs = kmalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!kvm_sregs)
+			goto out;
 		r = -EFAULT;
-		if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs))
+		if (copy_from_user(kvm_sregs, argp, sizeof(struct kvm_sregs)))
 			goto out;
-		r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs);
+		r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs);
 		if (r)
 			goto out;
 		r = 0;
@@ -1264,25 +1522,28 @@ out_free2:
 		break;
 	}
 	case KVM_GET_FPU: {
-		struct kvm_fpu fpu;
-
-		memset(&fpu, 0, sizeof fpu);
-		r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, &fpu);
+		fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!fpu)
+			goto out;
+		r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu);
 		if (r)
 			goto out;
 		r = -EFAULT;
-		if (copy_to_user(argp, &fpu, sizeof fpu))
+		if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu)))
 			goto out;
 		r = 0;
 		break;
 	}
 	case KVM_SET_FPU: {
-		struct kvm_fpu fpu;
-
+		fpu = kmalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
+		r = -ENOMEM;
+		if (!fpu)
+			goto out;
 		r = -EFAULT;
-		if (copy_from_user(&fpu, argp, sizeof fpu))
+		if (copy_from_user(fpu, argp, sizeof(struct kvm_fpu)))
 			goto out;
-		r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, &fpu);
+		r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
 		if (r)
 			goto out;
 		r = 0;
@@ -1292,6 +1553,8 @@ out_free2:
 		r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
 	}
 out:
+	kfree(fpu);
+	kfree(kvm_sregs);
 	return r;
 }
 
@@ -1360,6 +1623,30 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef KVM_CAP_DEVICE_ASSIGNMENT
+	case KVM_ASSIGN_PCI_DEVICE: {
+		struct kvm_assigned_pci_dev assigned_dev;
+
+		r = -EFAULT;
+		if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+			goto out;
+		r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
+		if (r)
+			goto out;
+		break;
+	}
+	case KVM_ASSIGN_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_assign_irq(kvm, &assigned_irq);
+		if (r)
+			goto out;
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -1369,17 +1656,22 @@ out:
 
 static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
+	struct page *page[1];
+	unsigned long addr;
+	int npages;
+	gfn_t gfn = vmf->pgoff;
 	struct kvm *kvm = vma->vm_file->private_data;
-	struct page *page;
 
-	if (!kvm_is_visible_gfn(kvm, vmf->pgoff))
+	addr = gfn_to_hva(kvm, gfn);
+	if (kvm_is_error_hva(addr))
 		return VM_FAULT_SIGBUS;
-	page = gfn_to_page(kvm, vmf->pgoff);
-	if (is_error_page(page)) {
-		kvm_release_page_clean(page);
+
+	npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page,
+				NULL);
+	if (unlikely(npages != 1))
 		return VM_FAULT_SIGBUS;
-	}
-	vmf->page = page;
+
+	vmf->page = page[0];
 	return 0;
 }
 
diff --git a/virt/kvm/kvm_trace.c b/virt/kvm/kvm_trace.c
index 58141f31ea8f..41dcc845f78c 100644
--- a/virt/kvm/kvm_trace.c
+++ b/virt/kvm/kvm_trace.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/relay.h>
 #include <linux/debugfs.h>
+#include <linux/ktime.h>
 
 #include <linux/kvm_host.h>
 
@@ -35,16 +36,16 @@ static struct kvm_trace *kvm_trace;
 struct kvm_trace_probe {
 	const char *name;
 	const char *format;
-	u32 cycle_in;
+	u32 timestamp_in;
 	marker_probe_func *probe_func;
 };
 
-static inline int calc_rec_size(int cycle, int extra)
+static inline int calc_rec_size(int timestamp, int extra)
 {
 	int rec_size = KVM_TRC_HEAD_SIZE;
 
 	rec_size += extra;
-	return cycle ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size;
+	return timestamp ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size;
 }
 
 static void kvm_add_trace(void *probe_private, void *call_data,
@@ -54,12 +55,13 @@ static void kvm_add_trace(void *probe_private, void *call_data,
 	struct kvm_trace *kt = kvm_trace;
 	struct kvm_trace_rec rec;
 	struct kvm_vcpu *vcpu;
-	int    i, extra, size;
+	int    i, size;
+	u32    extra;
 
 	if (unlikely(kt->trace_state != KVM_TRACE_STATE_RUNNING))
 		return;
 
-	rec.event	= va_arg(*args, u32);
+	rec.rec_val	= TRACE_REC_EVENT_ID(va_arg(*args, u32));
 	vcpu		= va_arg(*args, struct kvm_vcpu *);
 	rec.pid		= current->tgid;
 	rec.vcpu_id	= vcpu->vcpu_id;
@@ -67,21 +69,21 @@ static void kvm_add_trace(void *probe_private, void *call_data,
 	extra   	= va_arg(*args, u32);
 	WARN_ON(!(extra <= KVM_TRC_EXTRA_MAX));
 	extra 		= min_t(u32, extra, KVM_TRC_EXTRA_MAX);
-	rec.extra_u32   = extra;
 
-	rec.cycle_in 	= p->cycle_in;
+	rec.rec_val |= TRACE_REC_TCS(p->timestamp_in)
+			| TRACE_REC_NUM_DATA_ARGS(extra);
 
-	if (rec.cycle_in) {
-		rec.u.cycle.cycle_u64 = get_cycles();
+	if (p->timestamp_in) {
+		rec.u.timestamp.timestamp = ktime_to_ns(ktime_get());
 
-		for (i = 0; i < rec.extra_u32; i++)
-			rec.u.cycle.extra_u32[i] = va_arg(*args, u32);
+		for (i = 0; i < extra; i++)
+			rec.u.timestamp.extra_u32[i] = va_arg(*args, u32);
 	} else {
-		for (i = 0; i < rec.extra_u32; i++)
-			rec.u.nocycle.extra_u32[i] = va_arg(*args, u32);
+		for (i = 0; i < extra; i++)
+			rec.u.notimestamp.extra_u32[i] = va_arg(*args, u32);
 	}
 
-	size = calc_rec_size(rec.cycle_in, rec.extra_u32 * sizeof(u32));
+	size = calc_rec_size(p->timestamp_in, extra * sizeof(u32));
 	relay_write(kt->rchan, &rec, size);
 }
 
diff --git a/virt/kvm/vtd.c b/virt/kvm/vtd.c
new file mode 100644
index 000000000000..a770874f3a3a
--- /dev/null
+++ b/virt/kvm/vtd.c
@@ -0,0 +1,191 @@
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2006-2008 Intel Corporation
+ * Copyright IBM Corporation, 2008
+ * Author: Allen M. Kay <allen.m.kay@intel.com>
+ * Author: Weidong Han <weidong.han@intel.com>
+ * Author: Ben-Ami Yassour <benami@il.ibm.com>
+ */
+
+#include <linux/list.h>
+#include <linux/kvm_host.h>
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/intel-iommu.h>
+
+static int kvm_iommu_unmap_memslots(struct kvm *kvm);
+static void kvm_iommu_put_pages(struct kvm *kvm,
+				gfn_t base_gfn, unsigned long npages);
+
+int kvm_iommu_map_pages(struct kvm *kvm,
+			gfn_t base_gfn, unsigned long npages)
+{
+	gfn_t gfn = base_gfn;
+	pfn_t pfn;
+	int i, r = 0;
+	struct dmar_domain *domain = kvm->arch.intel_iommu_domain;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return 0;
+
+	for (i = 0; i < npages; i++) {
+		/* check if already mapped */
+		pfn = (pfn_t)intel_iommu_iova_to_pfn(domain,
+						     gfn_to_gpa(gfn));
+		if (pfn)
+			continue;
+
+		pfn = gfn_to_pfn(kvm, gfn);
+		r = intel_iommu_page_mapping(domain,
+					     gfn_to_gpa(gfn),
+					     pfn_to_hpa(pfn),
+					     PAGE_SIZE,
+					     DMA_PTE_READ |
+					     DMA_PTE_WRITE);
+		if (r) {
+			printk(KERN_ERR "kvm_iommu_map_pages:"
+			       "iommu failed to map pfn=%lx\n", pfn);
+			goto unmap_pages;
+		}
+		gfn++;
+	}
+	return 0;
+
+unmap_pages:
+	kvm_iommu_put_pages(kvm, base_gfn, i);
+	return r;
+}
+
+static int kvm_iommu_map_memslots(struct kvm *kvm)
+{
+	int i, r;
+
+	down_read(&kvm->slots_lock);
+	for (i = 0; i < kvm->nmemslots; i++) {
+		r = kvm_iommu_map_pages(kvm, kvm->memslots[i].base_gfn,
+					kvm->memslots[i].npages);
+		if (r)
+			break;
+	}
+	up_read(&kvm->slots_lock);
+	return r;
+}
+
+int kvm_iommu_map_guest(struct kvm *kvm,
+			struct kvm_assigned_dev_kernel *assigned_dev)
+{
+	struct pci_dev *pdev = NULL;
+	int r;
+
+	if (!intel_iommu_found()) {
+		printk(KERN_ERR "%s: intel iommu not found\n", __func__);
+		return -ENODEV;
+	}
+
+	printk(KERN_DEBUG "VT-d direct map: host bdf = %x:%x:%x\n",
+	       assigned_dev->host_busnr,
+	       PCI_SLOT(assigned_dev->host_devfn),
+	       PCI_FUNC(assigned_dev->host_devfn));
+
+	pdev = assigned_dev->dev;
+
+	if (pdev == NULL) {
+		if (kvm->arch.intel_iommu_domain) {
+			intel_iommu_domain_exit(kvm->arch.intel_iommu_domain);
+			kvm->arch.intel_iommu_domain = NULL;
+		}
+		return -ENODEV;
+	}
+
+	kvm->arch.intel_iommu_domain = intel_iommu_domain_alloc(pdev);
+	if (!kvm->arch.intel_iommu_domain)
+		return -ENODEV;
+
+	r = kvm_iommu_map_memslots(kvm);
+	if (r)
+		goto out_unmap;
+
+	intel_iommu_detach_dev(kvm->arch.intel_iommu_domain,
+			       pdev->bus->number, pdev->devfn);
+
+	r = intel_iommu_context_mapping(kvm->arch.intel_iommu_domain,
+					pdev);
+	if (r) {
+		printk(KERN_ERR "Domain context map for %s failed",
+		       pci_name(pdev));
+		goto out_unmap;
+	}
+	return 0;
+
+out_unmap:
+	kvm_iommu_unmap_memslots(kvm);
+	return r;
+}
+
+static void kvm_iommu_put_pages(struct kvm *kvm,
+			       gfn_t base_gfn, unsigned long npages)
+{
+	gfn_t gfn = base_gfn;
+	pfn_t pfn;
+	struct dmar_domain *domain = kvm->arch.intel_iommu_domain;
+	int i;
+
+	for (i = 0; i < npages; i++) {
+		pfn = (pfn_t)intel_iommu_iova_to_pfn(domain,
+						     gfn_to_gpa(gfn));
+		kvm_release_pfn_clean(pfn);
+		gfn++;
+	}
+}
+
+static int kvm_iommu_unmap_memslots(struct kvm *kvm)
+{
+	int i;
+	down_read(&kvm->slots_lock);
+	for (i = 0; i < kvm->nmemslots; i++) {
+		kvm_iommu_put_pages(kvm, kvm->memslots[i].base_gfn,
+				    kvm->memslots[i].npages);
+	}
+	up_read(&kvm->slots_lock);
+
+	return 0;
+}
+
+int kvm_iommu_unmap_guest(struct kvm *kvm)
+{
+	struct kvm_assigned_dev_kernel *entry;
+	struct dmar_domain *domain = kvm->arch.intel_iommu_domain;
+
+	/* check if iommu exists and in use */
+	if (!domain)
+		return 0;
+
+	list_for_each_entry(entry, &kvm->arch.assigned_dev_head, list) {
+		printk(KERN_DEBUG "VT-d unmap: host bdf = %x:%x:%x\n",
+		       entry->host_busnr,
+		       PCI_SLOT(entry->host_devfn),
+		       PCI_FUNC(entry->host_devfn));
+
+		/* detach kvm dmar domain */
+		intel_iommu_detach_dev(domain, entry->host_busnr,
+				       entry->host_devfn);
+	}
+	kvm_iommu_unmap_memslots(kvm);
+	intel_iommu_domain_exit(domain);
+	return 0;
+}