1 files changed, 558 insertions, 256 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1cd693a76a5..4b6c01b477f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -70,7 +70,8 @@ MODULE_LICENSE("GPL");
  * 		kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_RAW_SPINLOCK(kvm_lock);
+DEFINE_SPINLOCK(kvm_lock);
+static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
 static cpumask_var_t cpus_hardware_enabled;
@@ -94,36 +95,22 @@ static int hardware_enable_all(void);
 static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
+static void update_memslots(struct kvm_memslots *slots,
+			    struct kvm_memory_slot *new, u64 last_generation);
 
-bool kvm_rebooting;
+static void kvm_release_pfn_dirty(pfn_t pfn);
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot, gfn_t gfn);
+
+__visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
 
 bool kvm_is_mmio_pfn(pfn_t pfn)
 {
-	if (pfn_valid(pfn)) {
-		int reserved;
-		struct page *tail = pfn_to_page(pfn);
-		struct page *head = compound_trans_head(tail);
-		reserved = PageReserved(head);
-		if (head != tail) {
-			/*
-			 * "head" is not a dangling pointer
-			 * (compound_trans_head takes care of that)
-			 * but the hugepage may have been splitted
-			 * from under us (and we may not hold a
-			 * reference count on the head page so it can
-			 * be reused before we run PageReferenced), so
-			 * we've to check PageTail before returning
-			 * what we just read.
-			 */
-			smp_rmb();
-			if (PageTail(tail))
-				return reserved;
-		}
-		return PageReserved(tail);
-	}
+	if (pfn_valid(pfn))
+		return PageReserved(pfn_to_page(pfn));
 
 	return true;
 }
@@ -206,6 +193,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 		++kvm->stat.remote_tlb_flush;
 	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
+EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
 void kvm_reload_remote_mmus(struct kvm *kvm)
 {
@@ -217,6 +205,11 @@ void kvm_make_mclock_inprogress_request(struct kvm *kvm)
 	make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
 }
 
+void kvm_make_scan_ioapic_request(struct kvm *kvm)
+{
+	make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
+}
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
@@ -239,6 +232,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 
 	kvm_vcpu_set_in_spin_loop(vcpu, false);
 	kvm_vcpu_set_dy_eligible(vcpu, false);
+	vcpu->preempted = false;
 
 	r = kvm_arch_vcpu_init(vcpu);
 	if (r < 0)
@@ -463,24 +457,28 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 	r = hardware_enable_all();
 	if (r)
-		goto out_err_nodisable;
+		goto out_err_no_disable;
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->mask_notifier_list);
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
+	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
+
 	r = -ENOMEM;
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
 	kvm_init_memslots_id(kvm);
 	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_nosrcu;
+		goto out_err_no_srcu;
+	if (init_srcu_struct(&kvm->irq_srcu))
+		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
 					GFP_KERNEL);
@@ -496,22 +494,25 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);
+	INIT_LIST_HEAD(&kvm->devices);
 
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
 		goto out_err;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	return kvm;
 
 out_err:
+	cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
 	hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
 	kfree(kvm->memslots);
@@ -551,37 +552,50 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /*
  * Free any memory in @free but not in @dont.
  */
-static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
+static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
-	kvm_arch_free_memslot(free, dont);
+	kvm_arch_free_memslot(kvm, free, dont);
 
 	free->npages = 0;
 }
 
-void kvm_free_physmem(struct kvm *kvm)
+static void kvm_free_physmem(struct kvm *kvm)
 {
 	struct kvm_memslots *slots = kvm->memslots;
 	struct kvm_memory_slot *memslot;
 
 	kvm_for_each_memslot(memslot, slots)
-		kvm_free_physmem_slot(memslot, NULL);
+		kvm_free_physmem_slot(kvm, memslot, NULL);
 
 	kfree(kvm->memslots);
 }
 
+static void kvm_destroy_devices(struct kvm *kvm)
+{
+	struct list_head *node, *tmp;
+
+	list_for_each_safe(node, tmp, &kvm->devices) {
+		struct kvm_device *dev =
+			list_entry(node, struct kvm_device, vm_node);
+
+		list_del(node);
+		dev->ops->destroy(dev);
+	}
+}
+
 static void kvm_destroy_vm(struct kvm *kvm)
 {
 	int i;
 	struct mm_struct *mm = kvm->mm;
 
 	kvm_arch_sync_events(kvm);
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kvm_io_bus_destroy(kvm->buses[i]);
@@ -592,7 +606,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	kvm_arch_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
+	kvm_destroy_devices(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
 	hardware_disable_all();
@@ -629,14 +645,12 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
  */
 static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
-#ifndef CONFIG_S390
 	unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
 	memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
 	if (!memslot->dirty_bitmap)
 		return -ENOMEM;
 
-#endif /* !CONFIG_S390 */
 	return 0;
 }
 
@@ -670,7 +684,9 @@ static void sort_memslots(struct kvm_memslots *slots)
 		slots->id_to_index[slots->memslots[i].id] = i;
 }
 
-void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
+static void update_memslots(struct kvm_memslots *slots,
+			    struct kvm_memory_slot *new,
+			    u64 last_generation)
 {
 	if (new) {
 		int id = new->id;
@@ -682,7 +698,7 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
 			sort_memslots(slots);
 	}
 
-	slots->generation++;
+	slots->generation = last_generation + 1;
 }
 
 static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
@@ -699,6 +715,20 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
 	return 0;
 }
 
+static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
+		struct kvm_memslots *slots, struct kvm_memory_slot *new)
+{
+	struct kvm_memslots *old_memslots = kvm->memslots;
+
+	update_memslots(slots, new, kvm->memslots->generation);
+	rcu_assign_pointer(kvm->memslots, slots);
+	synchronize_srcu_expedited(&kvm->srcu);
+
+	kvm_arch_memslots_updated(kvm);
+
+	return old_memslots;
+}
+
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -708,15 +738,15 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
  * Must be called holding mmap_sem for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    struct kvm_userspace_memory_region *mem,
-			    int user_alloc)
+			    struct kvm_userspace_memory_region *mem)
 {
 	int r;
 	gfn_t base_gfn;
 	unsigned long npages;
-	struct kvm_memory_slot *memslot, *slot;
+	struct kvm_memory_slot *slot;
 	struct kvm_memory_slot old, new;
-	struct kvm_memslots *slots, *old_memslots;
+	struct kvm_memslots *slots = NULL, *old_memslots;
+	enum kvm_mr_change change;
 
 	r = check_memory_region_flags(mem);
 	if (r)
@@ -729,7 +759,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		goto out;
 	/* We can read the guest memory with __xxx_user() later on. */
-	if (user_alloc &&
+	if ((mem->slot < KVM_USER_MEM_SLOTS) &&
 	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
 	     !access_ok(VERIFY_WRITE,
 			(void __user *)(unsigned long)mem->userspace_addr,
@@ -740,7 +770,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		goto out;
 
-	memslot = id_to_memslot(kvm->memslots, mem->slot);
+	slot = id_to_memslot(kvm->memslots, mem->slot);
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -751,26 +781,48 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!npages)
 		mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
-	new = old = *memslot;
+	new = old = *slot;
 
 	new.id = mem->slot;
 	new.base_gfn = base_gfn;
 	new.npages = npages;
 	new.flags = mem->flags;
 
-	/* Disallow changing a memory slot's size. */
 	r = -EINVAL;
-	if (npages && old.npages && npages != old.npages)
-		goto out_free;
+	if (npages) {
+		if (!old.npages)
+			change = KVM_MR_CREATE;
+		else { /* Modify an existing slot. */
+			if ((mem->userspace_addr != old.userspace_addr) ||
+			    (npages != old.npages) ||
+			    ((new.flags ^ old.flags) & KVM_MEM_READONLY))
+				goto out;
 
-	/* Check for overlaps */
-	r = -EEXIST;
-	kvm_for_each_memslot(slot, kvm->memslots) {
-		if (slot->id >= KVM_MEMORY_SLOTS || slot == memslot)
-			continue;
-		if (!((base_gfn + npages <= slot->base_gfn) ||
-		      (base_gfn >= slot->base_gfn + slot->npages)))
-			goto out_free;
+			if (base_gfn != old.base_gfn)
+				change = KVM_MR_MOVE;
+			else if (new.flags != old.flags)
+				change = KVM_MR_FLAGS_ONLY;
+			else { /* Nothing to change. */
+				r = 0;
+				goto out;
+			}
+		}
+	} else if (old.npages) {
+		change = KVM_MR_DELETE;
+	} else /* Modify a non-existent slot: disallowed. */
+		goto out;
+
+	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+		/* Check for overlaps */
+		r = -EEXIST;
+		kvm_for_each_memslot(slot, kvm->memslots) {
+			if ((slot->id >= KVM_USER_MEM_SLOTS) ||
+			    (slot->id == mem->slot))
+				continue;
+			if (!((base_gfn + npages <= slot->base_gfn) ||
+			      (base_gfn >= slot->base_gfn + slot->npages)))
+				goto out;
+		}
 	}
 
 	/* Free page dirty bitmap if unneeded */
@@ -778,13 +830,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		new.dirty_bitmap = NULL;
 
 	r = -ENOMEM;
-
-	/* Allocate if a slot is being created */
-	if (npages && !old.npages) {
-		new.user_alloc = user_alloc;
+	if (change == KVM_MR_CREATE) {
 		new.userspace_addr = mem->userspace_addr;
 
-		if (kvm_arch_create_memslot(&new, npages))
+		if (kvm_arch_create_memslot(kvm, &new, npages))
 			goto out_free;
 	}
 
@@ -792,12 +841,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
 		if (kvm_create_dirty_bitmap(&new) < 0)
 			goto out_free;
-		/* destroy any largepage mappings for dirty tracking */
 	}
 
-	if (!npages || base_gfn != old.base_gfn) {
-		struct kvm_memory_slot *slot;
-
+	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
 		r = -ENOMEM;
 		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
 				GFP_KERNEL);
@@ -806,11 +852,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		slot = id_to_memslot(slots, mem->slot);
 		slot->flags |= KVM_MEMSLOT_INVALID;
 
-		update_memslots(slots, NULL);
+		old_memslots = install_new_memslots(kvm, slots, NULL);
 
-		old_memslots = kvm->memslots;
-		rcu_assign_pointer(kvm->memslots, slots);
-		synchronize_srcu_expedited(&kvm->srcu);
+		/* slot was deleted or moved, clear iommu mapping */
+		kvm_iommu_unmap_pages(kvm, &old);
 		/* From this point no new shadow pages pointing to a deleted,
 		 * or moved, memslot will be created.
 		 *
@@ -819,74 +864,82 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		 * 	- kvm_is_visible_gfn (mmu_check_roots)
 		 */
 		kvm_arch_flush_shadow_memslot(kvm, slot);
-		kfree(old_memslots);
+		slots = old_memslots;
 	}
 
-	r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc);
+	r = kvm_arch_prepare_memory_region(kvm, &new, mem, change);
 	if (r)
-		goto out_free;
-
-	/* map/unmap the pages in iommu page table */
-	if (npages) {
-		r = kvm_iommu_map_pages(kvm, &new);
-		if (r)
-			goto out_free;
-	} else
-		kvm_iommu_unmap_pages(kvm, &old);
+		goto out_slots;
 
 	r = -ENOMEM;
-	slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-			GFP_KERNEL);
-	if (!slots)
-		goto out_free;
+	/*
+	 * We can re-use the old_memslots from above, the only difference
+	 * from the currently installed memslots is the invalid flag.  This
+	 * will get overwritten by update_memslots anyway.
+	 */
+	if (!slots) {
+		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
+				GFP_KERNEL);
+		if (!slots)
+			goto out_free;
+	}
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
-	if (!npages) {
+	if (change == KVM_MR_DELETE) {
 		new.dirty_bitmap = NULL;
 		memset(&new.arch, 0, sizeof(new.arch));
 	}
 
-	update_memslots(slots, &new);
-	old_memslots = kvm->memslots;
-	rcu_assign_pointer(kvm->memslots, slots);
-	synchronize_srcu_expedited(&kvm->srcu);
+	old_memslots = install_new_memslots(kvm, slots, &new);
 
-	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
+	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
-	kvm_free_physmem_slot(&old, &new);
+	kvm_free_physmem_slot(kvm, &old, &new);
 	kfree(old_memslots);
 
+	/*
+	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
+	 * un-mapped and re-mapped if their base changes.  Since base change
+	 * unmapping is handled above with slot deletion, mapping alone is
+	 * needed here.  Anything else the iommu might care about for existing
+	 * slots (size changes, userspace addr changes and read-only flag
+	 * changes) is disallowed above, so any other attribute changes getting
+	 * here can be skipped.
+	 */
+	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+		r = kvm_iommu_map_pages(kvm, &new);
+		return r;
+	}
+
 	return 0;
 
+out_slots:
+	kfree(slots);
 out_free:
-	kvm_free_physmem_slot(&new, &old);
+	kvm_free_physmem_slot(kvm, &new, &old);
 out:
 	return r;
-
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  struct kvm_userspace_memory_region *mem,
-			  int user_alloc)
+			  struct kvm_userspace_memory_region *mem)
 {
 	int r;
 
 	mutex_lock(&kvm->slots_lock);
-	r = __kvm_set_memory_region(kvm, mem, user_alloc);
+	r = __kvm_set_memory_region(kvm, mem);
 	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
-int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-				   struct
-				   kvm_userspace_memory_region *mem,
-				   int user_alloc)
+static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+					  struct kvm_userspace_memory_region *mem)
 {
-	if (mem->slot >= KVM_MEMORY_SLOTS)
+	if (mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
-	return kvm_set_memory_region(kvm, mem, user_alloc);
+	return kvm_set_memory_region(kvm, mem);
 }
 
 int kvm_get_dirty_log(struct kvm *kvm,
@@ -898,7 +951,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
 	unsigned long any = 0;
 
 	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
+	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);
@@ -922,6 +975,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
 out:
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
 
 bool kvm_largepages_enabled(void)
 {
@@ -944,7 +998,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
 
-	if (!memslot || memslot->id >= KVM_MEMORY_SLOTS ||
+	if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS ||
 	      memslot->flags & KVM_MEMSLOT_INVALID)
 		return 0;
 
@@ -1003,7 +1057,7 @@ static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
 }
 
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
-				 gfn_t gfn)
+					gfn_t gfn)
 {
 	return gfn_to_hva_many(slot, gfn, NULL);
 }
@@ -1016,12 +1070,18 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
 /*
- * The hva returned by this function is only allowed to be read.
- * It should pair with kvm_read_hva() or kvm_read_hva_atomic().
+ * If writable is set to false, the hva returned by this function is only
+ * allowed to be read.
  */
-static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn)
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
 {
-	return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false);
+	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+	unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
+
+	if (!kvm_is_error_hva(hva) && writable)
+		*writable = !memslot_is_readonly(slot);
+
+	return hva;
 }
 
 static int kvm_read_hva(void *data, void __user *hva, int len)
@@ -1034,7 +1094,7 @@ static int kvm_read_hva_atomic(void *data, void __user *hva, int len)
 	return __copy_from_user_inatomic(data, hva, len);
 }
 
-int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
+static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
 	unsigned long start, int write, struct page **page)
 {
 	int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET;
@@ -1337,18 +1397,11 @@ void kvm_release_page_dirty(struct page *page)
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
 
-void kvm_release_pfn_dirty(pfn_t pfn)
+static void kvm_release_pfn_dirty(pfn_t pfn)
 {
 	kvm_set_pfn_dirty(pfn);
 	kvm_release_pfn_clean(pfn);
 }
-EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
-
-void kvm_set_page_dirty(struct page *page)
-{
-	kvm_set_pfn_dirty(page_to_pfn(page));
-}
-EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
 
 void kvm_set_pfn_dirty(pfn_t pfn)
 {
@@ -1388,7 +1441,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 	int r;
 	unsigned long addr;
 
-	addr = gfn_to_hva_read(kvm, gfn);
+	addr = gfn_to_hva_prot(kvm, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
 	r = kvm_read_hva(data, (void __user *)addr + offset, len);
@@ -1426,7 +1479,7 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int offset = offset_in_page(gpa);
 
-	addr = gfn_to_hva_read(kvm, gfn);
+	addr = gfn_to_hva_prot(kvm, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
 	pagefault_disable();
@@ -1476,21 +1529,38 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 }
 
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			      gpa_t gpa)
+			      gpa_t gpa, unsigned long len)
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int offset = offset_in_page(gpa);
-	gfn_t gfn = gpa >> PAGE_SHIFT;
+	gfn_t start_gfn = gpa >> PAGE_SHIFT;
+	gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
+	gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
+	gfn_t nr_pages_avail;
 
 	ghc->gpa = gpa;
 	ghc->generation = slots->generation;
-	ghc->memslot = gfn_to_memslot(kvm, gfn);
-	ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
-	if (!kvm_is_error_hva(ghc->hva))
+	ghc->len = len;
+	ghc->memslot = gfn_to_memslot(kvm, start_gfn);
+	ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
+	if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
 		ghc->hva += offset;
-	else
-		return -EFAULT;
-
+	} else {
+		/*
+		 * If the requested region crosses two memslots, we still
+		 * verify that the entire region is valid here.
+		 */
+		while (start_gfn <= end_gfn) {
+			ghc->memslot = gfn_to_memslot(kvm, start_gfn);
+			ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
+						   &nr_pages_avail);
+			if (kvm_is_error_hva(ghc->hva))
+				return -EFAULT;
+			start_gfn += nr_pages_avail;
+		}
+		/* Use the slow path for cross page reads and writes. */
+		ghc->memslot = NULL;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
@@ -1501,8 +1571,13 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
 
+	BUG_ON(len > ghc->len);
+
 	if (slots->generation != ghc->generation)
-		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+	if (unlikely(!ghc->memslot))
+		return kvm_write_guest(kvm, ghc->gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
@@ -1522,8 +1597,13 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
 
+	BUG_ON(len > ghc->len);
+
 	if (slots->generation != ghc->generation)
-		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+	if (unlikely(!ghc->memslot))
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
@@ -1538,8 +1618,9 @@ EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
 {
-	return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page,
-				    offset, len);
+	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+
+	return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
 
@@ -1562,8 +1643,9 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
-			     gfn_t gfn)
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot,
+				    gfn_t gfn)
 {
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
@@ -1579,6 +1661,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	memslot = gfn_to_memslot(kvm, gfn);
 	mark_page_dirty_in_slot(kvm, memslot, gfn);
 }
+EXPORT_SYMBOL_GPL(mark_page_dirty);
 
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
@@ -1604,6 +1687,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 
 	finish_wait(&vcpu->wq, &wait);
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_block);
 
 #ifndef CONFIG_S390
 /*
@@ -1627,20 +1711,14 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 			smp_send_reschedule(cpu);
 	put_cpu();
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
 #endif /* !CONFIG_S390 */
 
-void kvm_resched(struct kvm_vcpu *vcpu)
-{
-	if (!need_resched())
-		return;
-	cond_resched();
-}
-EXPORT_SYMBOL_GPL(kvm_resched);
-
-bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
+int kvm_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct pid *pid;
 	struct task_struct *task = NULL;
+	int ret = 0;
 
 	rcu_read_lock();
 	pid = rcu_dereference(target->pid);
@@ -1648,21 +1726,18 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 		task = get_pid_task(target->pid, PIDTYPE_PID);
 	rcu_read_unlock();
 	if (!task)
-		return false;
+		return ret;
 	if (task->flags & PF_VCPU) {
 		put_task_struct(task);
-		return false;
-	}
-	if (yield_to(task, 1)) {
-		put_task_struct(task);
-		return true;
+		return ret;
 	}
+	ret = yield_to(task, 1);
 	put_task_struct(task);
-	return false;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
 
-#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 /*
  * Helper that checks whether a VCPU is eligible for directed yield.
  * Most eligible candidate to yield is decided by following heuristics:
@@ -1685,8 +1760,9 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
  *  locking does not harm. It may result in trying to yield to  same VCPU, fail
  *  and continue with next VCPU and so on.
  */
-bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 {
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 	bool eligible;
 
 	eligible = !vcpu->spin_loop.in_spin_loop ||
@@ -1697,14 +1773,18 @@ bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 		kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
 
 	return eligible;
-}
+#else
+	return true;
 #endif
+}
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
 	struct kvm_vcpu *vcpu;
 	int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
 	int yielded = 0;
+	int try = 3;
 	int pass;
 	int i;
 
@@ -1716,23 +1796,30 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	 * VCPU is holding the lock that we need and will release it.
 	 * We approximate round-robin by starting at the last boosted VCPU.
 	 */
-	for (pass = 0; pass < 2 && !yielded; pass++) {
+	for (pass = 0; pass < 2 && !yielded && try; pass++) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (!pass && i <= last_boosted_vcpu) {
 				i = last_boosted_vcpu;
 				continue;
 			} else if (pass && i > last_boosted_vcpu)
 				break;
+			if (!ACCESS_ONCE(vcpu->preempted))
+				continue;
 			if (vcpu == me)
 				continue;
-			if (waitqueue_active(&vcpu->wq))
+			if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;
-			if (kvm_vcpu_yield_to(vcpu)) {
+
+			yielded = kvm_vcpu_yield_to(vcpu);
+			if (yielded > 0) {
 				kvm->last_boosted_vcpu = i;
-				yielded = 1;
 				break;
+			} else if (yielded < 0) {
+				try--;
+				if (!try)
+					break;
 			}
 		}
 	}
@@ -1798,7 +1885,7 @@ static struct file_operations kvm_vcpu_fops = {
  */
 static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 {
-	return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR);
+	return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
 }
 
 /*
@@ -1809,6 +1896,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	int r;
 	struct kvm_vcpu *vcpu, *v;
 
+	if (id >= KVM_MAX_VCPUS)
+		return -EINVAL;
+
 	vcpu = kvm_arch_vcpu_create(kvm, id);
 	if (IS_ERR(vcpu))
 		return PTR_ERR(vcpu);
@@ -1883,7 +1973,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	if (vcpu->kvm->mm != current->mm)
 		return -EIO;
 
-#if defined(CONFIG_S390) || defined(CONFIG_PPC)
+#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
 	/*
 	 * Special cases: vcpu ioctls that are asynchronous to vcpu execution,
 	 * so vcpu_load() would break it.
@@ -2106,6 +2196,134 @@ out:
 }
 #endif
 
+static int kvm_device_ioctl_attr(struct kvm_device *dev,
+				 int (*accessor)(struct kvm_device *dev,
+						 struct kvm_device_attr *attr),
+				 unsigned long arg)
+{
+	struct kvm_device_attr attr;
+
+	if (!accessor)
+		return -EPERM;
+
+	if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
+		return -EFAULT;
+
+	return accessor(dev, &attr);
+}
+
+static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
+			     unsigned long arg)
+{
+	struct kvm_device *dev = filp->private_data;
+
+	switch (ioctl) {
+	case KVM_SET_DEVICE_ATTR:
+		return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
+	case KVM_GET_DEVICE_ATTR:
+		return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg);
+	case KVM_HAS_DEVICE_ATTR:
+		return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg);
+	default:
+		if (dev->ops->ioctl)
+			return dev->ops->ioctl(dev, ioctl, arg);
+
+		return -ENOTTY;
+	}
+}
+
+static int kvm_device_release(struct inode *inode, struct file *filp)
+{
+	struct kvm_device *dev = filp->private_data;
+	struct kvm *kvm = dev->kvm;
+
+	kvm_put_kvm(kvm);
+	return 0;
+}
+
+static const struct file_operations kvm_device_fops = {
+	.unlocked_ioctl = kvm_device_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = kvm_device_ioctl,
+#endif
+	.release = kvm_device_release,
+};
+
+struct kvm_device *kvm_device_from_filp(struct file *filp)
+{
+	if (filp->f_op != &kvm_device_fops)
+		return NULL;
+
+	return filp->private_data;
+}
+
+static int kvm_ioctl_create_device(struct kvm *kvm,
+				   struct kvm_create_device *cd)
+{
+	struct kvm_device_ops *ops = NULL;
+	struct kvm_device *dev;
+	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+	int ret;
+
+	switch (cd->type) {
+#ifdef CONFIG_KVM_MPIC
+	case KVM_DEV_TYPE_FSL_MPIC_20:
+	case KVM_DEV_TYPE_FSL_MPIC_42:
+		ops = &kvm_mpic_ops;
+		break;
+#endif
+#ifdef CONFIG_KVM_XICS
+	case KVM_DEV_TYPE_XICS:
+		ops = &kvm_xics_ops;
+		break;
+#endif
+#ifdef CONFIG_KVM_VFIO
+	case KVM_DEV_TYPE_VFIO:
+		ops = &kvm_vfio_ops;
+		break;
+#endif
+#ifdef CONFIG_KVM_ARM_VGIC
+	case KVM_DEV_TYPE_ARM_VGIC_V2:
+		ops = &kvm_arm_vgic_v2_ops;
+		break;
+#endif
+#ifdef CONFIG_S390
+	case KVM_DEV_TYPE_FLIC:
+		ops = &kvm_flic_ops;
+		break;
+#endif
+	default:
+		return -ENODEV;
+	}
+
+	if (test)
+		return 0;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->ops = ops;
+	dev->kvm = kvm;
+
+	ret = ops->create(dev, cd->type);
+	if (ret < 0) {
+		kfree(dev);
+		return ret;
+	}
+
+	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
+	if (ret < 0) {
+		ops->destroy(dev);
+		return ret;
+	}
+
+	list_add(&dev->vm_node, &kvm->devices);
+	kvm_get_kvm(kvm);
+	cd->fd = ret;
+	return 0;
+}
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -2127,7 +2345,7 @@ static long kvm_vm_ioctl(struct file *filp,
 						sizeof kvm_userspace_mem))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1);
+		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
@@ -2206,7 +2424,8 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
 
-		r = kvm_vm_ioctl_irq_line(kvm, &irq_event);
+		r = kvm_vm_ioctl_irq_line(kvm, &irq_event,
+					ioctl == KVM_IRQ_LINE_STATUS);
 		if (r)
 			goto out;
 
@@ -2220,6 +2439,54 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef CONFIG_HAVE_KVM_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 /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+	case KVM_CREATE_DEVICE: {
+		struct kvm_create_device cd;
+
+		r = -EFAULT;
+		if (copy_from_user(&cd, argp, sizeof(cd)))
+			goto out;
+
+		r = kvm_ioctl_create_device(kvm, &cd);
+		if (r)
+			goto out;
+
+		r = -EFAULT;
+		if (copy_to_user(argp, &cd, sizeof(cd)))
+			goto out;
+
+		r = 0;
+		break;
+	}
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)
@@ -2273,44 +2540,12 @@ out:
 }
 #endif
 
-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;
-
-	addr = gfn_to_hva(kvm, gfn);
-	if (kvm_is_error_hva(addr))
-		return VM_FAULT_SIGBUS;
-
-	npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page,
-				NULL);
-	if (unlikely(npages != 1))
-		return VM_FAULT_SIGBUS;
-
-	vmf->page = page[0];
-	return 0;
-}
-
-static const struct vm_operations_struct kvm_vm_vm_ops = {
-	.fault = kvm_vm_fault,
-};
-
-static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	vma->vm_ops = &kvm_vm_vm_ops;
-	return 0;
-}
-
 static struct file_operations kvm_vm_fops = {
 	.release        = kvm_vm_release,
 	.unlocked_ioctl = kvm_vm_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = kvm_vm_compat_ioctl,
 #endif
-	.mmap           = kvm_vm_mmap,
 	.llseek		= noop_llseek,
 };
 
@@ -2329,7 +2564,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		return r;
 	}
 #endif
-	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
 	if (r < 0)
 		kvm_put_kvm(kvm);
 
@@ -2349,8 +2584,11 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
 #endif
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+	case KVM_CAP_IRQFD_RESAMPLE:
+#endif
 		return 1;
-#ifdef KVM_CAP_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
@@ -2434,11 +2672,12 @@ static void hardware_enable_nolock(void *junk)
 	}
 }
 
-static void hardware_enable(void *junk)
+static void hardware_enable(void)
 {
-	raw_spin_lock(&kvm_lock);
-	hardware_enable_nolock(junk);
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
+	if (kvm_usage_count)
+		hardware_enable_nolock(NULL);
+	raw_spin_unlock(&kvm_count_lock);
 }
 
 static void hardware_disable_nolock(void *junk)
@@ -2451,11 +2690,12 @@ static void hardware_disable_nolock(void *junk)
 	kvm_arch_hardware_disable(NULL);
 }
 
-static void hardware_disable(void *junk)
+static void hardware_disable(void)
 {
-	raw_spin_lock(&kvm_lock);
-	hardware_disable_nolock(junk);
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
+	if (kvm_usage_count)
+		hardware_disable_nolock(NULL);
+	raw_spin_unlock(&kvm_count_lock);
 }
 
 static void hardware_disable_all_nolock(void)
@@ -2469,16 +2709,16 @@ static void hardware_disable_all_nolock(void)
 
 static void hardware_disable_all(void)
 {
-	raw_spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
 	hardware_disable_all_nolock();
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_count_lock);
 }
 
 static int hardware_enable_all(void)
 {
 	int r = 0;
 
-	raw_spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
 
 	kvm_usage_count++;
 	if (kvm_usage_count == 1) {
@@ -2491,7 +2731,7 @@ static int hardware_enable_all(void)
 		}
 	}
 
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_count_lock);
 
 	return r;
 }
@@ -2501,33 +2741,22 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 {
 	int cpu = (long)v;
 
-	if (!kvm_usage_count)
-		return NOTIFY_OK;
-
 	val &= ~CPU_TASKS_FROZEN;
 	switch (val) {
 	case CPU_DYING:
 		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
 		       cpu);
-		hardware_disable(NULL);
+		hardware_disable();
 		break;
 	case CPU_STARTING:
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
-		hardware_enable(NULL);
+		hardware_enable();
 		break;
 	}
 	return NOTIFY_OK;
 }
 
-
-asmlinkage void kvm_spurious_fault(void)
-{
-	/* Fault while not rebooting.  We want the trace. */
-	BUG();
-}
-EXPORT_SYMBOL_GPL(kvm_spurious_fault);
-
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
 {
@@ -2560,11 +2789,9 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 	kfree(bus);
 }
 
-int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
+                                 const struct kvm_io_range *r2)
 {
-	const struct kvm_io_range *r1 = p1;
-	const struct kvm_io_range *r2 = p2;
-
 	if (r1->addr < r2->addr)
 		return -1;
 	if (r1->addr + r1->len > r2->addr + r2->len)
@@ -2572,7 +2799,12 @@ int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
 	return 0;
 }
 
-int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
+static int kvm_io_bus_sort_cmp(const void *p1, const void *p2)
+{
+	return kvm_io_bus_cmp(p1, p2);
+}
+
+static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 			  gpa_t addr, int len)
 {
 	bus->range[bus->dev_count++] = (struct kvm_io_range) {
@@ -2587,7 +2819,7 @@ int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev,
 	return 0;
 }
 
-int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
+static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
 			     gpa_t addr, int len)
 {
 	struct kvm_io_range *range, key;
@@ -2605,19 +2837,39 @@ int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus,
 
 	off = range - bus->range;
 
-	while (off > 0 && kvm_io_bus_sort_cmp(&key, &bus->range[off-1]) == 0)
+	while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0)
 		off--;
 
 	return off;
 }
 
+static int __kvm_io_bus_write(struct kvm_io_bus *bus,
+			      struct kvm_io_range *range, const void *val)
+{
+	int idx;
+
+	idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len);
+	if (idx < 0)
+		return -EOPNOTSUPP;
+
+	while (idx < bus->dev_count &&
+		kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
+		if (!kvm_iodevice_write(bus->range[idx].dev, range->addr,
+					range->len, val))
+			return idx;
+		idx++;
+	}
+
+	return -EOPNOTSUPP;
+}
+
 /* kvm_io_bus_write - called under kvm->slots_lock */
 int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		     int len, const void *val)
 {
-	int idx;
 	struct kvm_io_bus *bus;
 	struct kvm_io_range range;
+	int r;
 
 	range = (struct kvm_io_range) {
 		.addr = addr,
@@ -2625,27 +2877,66 @@ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	idx = kvm_io_bus_get_first_dev(bus, addr, len);
+	r = __kvm_io_bus_write(bus, &range, val);
+	return r < 0 ? r : 0;
+}
+
+/* kvm_io_bus_write_cookie - called under kvm->slots_lock */
+int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
+			    int len, const void *val, long cookie)
+{
+	struct kvm_io_bus *bus;
+	struct kvm_io_range range;
+
+	range = (struct kvm_io_range) {
+		.addr = addr,
+		.len = len,
+	};
+
+	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
+
+	/* First try the device referenced by cookie. */
+	if ((cookie >= 0) && (cookie < bus->dev_count) &&
+	    (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0))
+		if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len,
+					val))
+			return cookie;
+
+	/*
+	 * cookie contained garbage; fall back to search and return the
+	 * correct cookie value.
+	 */
+	return __kvm_io_bus_write(bus, &range, val);
+}
+
+static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range,
+			     void *val)
+{
+	int idx;
+
+	idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len);
 	if (idx < 0)
 		return -EOPNOTSUPP;
 
 	while (idx < bus->dev_count &&
-		kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) {
-		if (!kvm_iodevice_write(bus->range[idx].dev, addr, len, val))
-			return 0;
+		kvm_io_bus_cmp(range, &bus->range[idx]) == 0) {
+		if (!kvm_iodevice_read(bus->range[idx].dev, range->addr,
+				       range->len, val))
+			return idx;
 		idx++;
 	}
 
 	return -EOPNOTSUPP;
 }
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
 
 /* kvm_io_bus_read - called under kvm->slots_lock */
 int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 		    int len, void *val)
 {
-	int idx;
 	struct kvm_io_bus *bus;
 	struct kvm_io_range range;
+	int r;
 
 	range = (struct kvm_io_range) {
 		.addr = addr,
@@ -2653,20 +2944,11 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	};
 
 	bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu);
-	idx = kvm_io_bus_get_first_dev(bus, addr, len);
-	if (idx < 0)
-		return -EOPNOTSUPP;
-
-	while (idx < bus->dev_count &&
-		kvm_io_bus_sort_cmp(&range, &bus->range[idx]) == 0) {
-		if (!kvm_iodevice_read(bus->range[idx].dev, addr, len, val))
-			return 0;
-		idx++;
-	}
-
-	return -EOPNOTSUPP;
+	r = __kvm_io_bus_read(bus, &range, val);
+	return r < 0 ? r : 0;
 }
 
+
 /* Caller must hold slots_lock. */
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 			    int len, struct kvm_io_device *dev)
@@ -2674,7 +2956,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm->buses[bus_idx];
-	if (bus->dev_count > NR_IOBUS_DEVS - 1)
+	/* exclude ioeventfd which is limited by maximum fd */
+	if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
 		return -ENOSPC;
 
 	new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) *
@@ -2735,10 +3018,10 @@ static int vm_stat_get(void *_offset, u64 *val)
 	struct kvm *kvm;
 
 	*val = 0;
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		*val += *(u32 *)((void *)kvm + offset);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -2752,12 +3035,12 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	int i;
 
 	*val = 0;
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			*val += *(u32 *)((void *)vcpu + offset);
 
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -2770,7 +3053,7 @@ static const struct file_operations *stat_fops[] = {
 
 static int kvm_init_debug(void)
 {
-	int r = -EFAULT;
+	int r = -EEXIST;
 	struct kvm_stats_debugfs_item *p;
 
 	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
@@ -2812,7 +3095,7 @@ static int kvm_suspend(void)
 static void kvm_resume(void)
 {
 	if (kvm_usage_count) {
-		WARN_ON(raw_spin_is_locked(&kvm_lock));
+		WARN_ON(raw_spin_is_locked(&kvm_count_lock));
 		hardware_enable_nolock(NULL);
 	}
 }
@@ -2831,6 +3114,8 @@ struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
 static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
+	if (vcpu->preempted)
+		vcpu->preempted = false;
 
 	kvm_arch_vcpu_load(vcpu, cpu);
 }
@@ -2840,6 +3125,8 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
+	if (current->state == TASK_RUNNING)
+		vcpu->preempted = true;
 	kvm_arch_vcpu_put(vcpu);
 }
 
@@ -2853,6 +3140,17 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	if (r)
 		goto out_fail;
 
+	/*
+	 * kvm_arch_init makes sure there's at most one caller
+	 * for architectures that support multiple implementations,
+	 * like intel and amd on x86.
+	 * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
+	 * conflicts in case kvm is already setup for another implementation.
+	 */
+	r = kvm_irqfd_init();
+	if (r)
+		goto out_irqfd;
+
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
 		goto out_free_0;
@@ -2914,6 +3212,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 out_undebugfs:
 	unregister_syscore_ops(&kvm_syscore_ops);
+	misc_deregister(&kvm_dev);
 out_unreg:
 	kvm_async_pf_deinit();
 out_free:
@@ -2927,6 +3226,8 @@ out_free_1:
 out_free_0a:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
+	kvm_irqfd_exit();
+out_irqfd:
 	kvm_arch_exit();
 out_fail:
 	return r;
@@ -2945,6 +3246,7 @@ void kvm_exit(void)
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
+	kvm_irqfd_exit();
 	free_cpumask_var(cpus_hardware_enabled);
 }
 EXPORT_SYMBOL_GPL(kvm_exit);