1 files changed, 49 insertions, 35 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 479802a892d4..dfbaafbe3a00 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -154,11 +154,6 @@ static unsigned long long kvm_active_vms;
 
 static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask);
 
-__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-						   unsigned long start, unsigned long end)
-{
-}
-
 __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
 {
 }
@@ -521,18 +516,6 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 	return container_of(mn, struct kvm, mmu_notifier);
 }
 
-static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
-					      struct mm_struct *mm,
-					      unsigned long start, unsigned long end)
-{
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int idx;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_mmu_notifier_invalidate_range(kvm, start, end);
-	srcu_read_unlock(&kvm->srcu, idx);
-}
-
 typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
 typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
@@ -686,6 +669,24 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 
 	return __kvm_handle_hva_range(kvm, &range);
 }
+
+static bool kvm_change_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	/*
+	 * Skipping invalid memslots is correct if and only change_pte() is
+	 * surrounded by invalidate_range_{start,end}(), which is currently
+	 * guaranteed by the primary MMU.  If that ever changes, KVM needs to
+	 * unmap the memslot instead of skipping the memslot to ensure that KVM
+	 * doesn't hold references to the old PFN.
+	 */
+	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
+
+	if (range->slot->flags & KVM_MEMSLOT_INVALID)
+		return false;
+
+	return kvm_set_spte_gfn(kvm, range);
+}
+
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
 					unsigned long address,
@@ -707,7 +708,7 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
-	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
+	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_change_spte_gfn);
 }
 
 void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
@@ -892,7 +893,6 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 }
 
 static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
-	.invalidate_range	= kvm_mmu_notifier_invalidate_range,
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
@@ -2477,7 +2477,7 @@ static inline int check_user_page_hwpoison(unsigned long addr)
 {
 	int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
 
-	rc = get_user_pages(addr, 1, flags, NULL, NULL);
+	rc = get_user_pages(addr, 1, flags, NULL);
 	return rc == -EHWPOISON;
 }
 
@@ -2578,6 +2578,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 {
 	kvm_pfn_t pfn;
 	pte_t *ptep;
+	pte_t pte;
 	spinlock_t *ptl;
 	int r;
 
@@ -2601,14 +2602,16 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 			return r;
 	}
 
-	if (write_fault && !pte_write(*ptep)) {
+	pte = ptep_get(ptep);
+
+	if (write_fault && !pte_write(pte)) {
 		pfn = KVM_PFN_ERR_RO_FAULT;
 		goto out;
 	}
 
 	if (writable)
-		*writable = pte_write(*ptep);
-	pfn = pte_pfn(*ptep);
+		*writable = pte_write(pte);
+	pfn = pte_pfn(pte);
 
 	/*
 	 * Get a reference here because callers of *hva_to_pfn* and
@@ -2626,7 +2629,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 	 * tail pages of non-compound higher order allocations, which
 	 * would then underflow the refcount when the caller does the
 	 * required put_page. Don't allow those pages here.
-	 */ 
+	 */
 	if (!kvm_try_get_pfn(pfn))
 		r = -EFAULT;
 
@@ -3870,7 +3873,10 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 static int vcpu_get_pid(void *data, u64 *val)
 {
 	struct kvm_vcpu *vcpu = data;
-	*val = pid_nr(rcu_access_pointer(vcpu->pid));
+
+	rcu_read_lock();
+	*val = pid_nr(rcu_dereference(vcpu->pid));
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -3972,7 +3978,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r < 0)
 		goto kvm_put_xa_release;
 
-	if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {
+	if (KVM_BUG_ON(xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) {
 		r = -EINVAL;
 		goto kvm_put_xa_release;
 	}
@@ -4602,7 +4608,7 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return -EINVAL;
 }
 
-static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+bool kvm_are_all_memslots_empty(struct kvm *kvm)
 {
 	int i;
 
@@ -4615,6 +4621,7 @@ static bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty);
 
 static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 					   struct kvm_enable_cap *cap)
@@ -5294,6 +5301,12 @@ static void hardware_disable_all(void)
 }
 #endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */
 
+static void kvm_iodevice_destructor(struct kvm_io_device *dev)
+{
+	if (dev->ops->destructor)
+		dev->ops->destructor(dev);
+}
+
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 {
 	int i;
@@ -5517,7 +5530,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			      struct kvm_io_device *dev)
 {
-	int i, j;
+	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
 	lockdep_assert_held(&kvm->slots_lock);
@@ -5547,18 +5560,19 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 
-	/* Destroy the old bus _after_ installing the (null) bus. */
+	/*
+	 * If NULL bus is installed, destroy the old bus, including all the
+	 * attached devices. Otherwise, destroy the caller's device only.
+	 */
 	if (!new_bus) {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		for (j = 0; j < bus->dev_count; j++) {
-			if (j == i)
-				continue;
-			kvm_iodevice_destructor(bus->range[j].dev);
-		}
+		kvm_io_bus_destroy(bus);
+		return -ENOMEM;
 	}
 
+	kvm_iodevice_destructor(dev);
 	kfree(bus);
-	return new_bus ? 0 : -ENOMEM;
+	return 0;
 }
 
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,