Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "Fix unwinding of KVM_CREATE_VM failure, VT-d posted interrupts,
  DAX/ZONE_DEVICE, and module unload/reload"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: MMU: Do not treat ZONE_DEVICE pages as being reserved
  KVM: VMX: Introduce pi_is_pir_empty() helper
  KVM: VMX: Do not change PID.NDST when loading a blocked vCPU
  KVM: VMX: Consider PID.PIR to determine if vCPU has pending interrupts
  KVM: VMX: Fix comment to specify PID.ON instead of PIR.ON
  KVM: X86: Fix initialization of MSR lists
  KVM: fix placement of refcount initialization
  KVM: Fix NULL-ptr deref after kvm_create_vm fails

1 files changed, 34 insertions, 14 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4aab3547a165..524cff24a68d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -150,10 +150,30 @@ __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 	return 0;
 }
 
+bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+{
+	/*
+	 * The metadata used by is_zone_device_page() to determine whether or
+	 * not a page is ZONE_DEVICE is guaranteed to be valid if and only if
+	 * the device has been pinned, e.g. by get_user_pages().  WARN if the
+	 * page_count() is zero to help detect bad usage of this helper.
+	 */
+	if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+		return false;
+
+	return is_zone_device_page(pfn_to_page(pfn));
+}
+
 bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 {
+	/*
+	 * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
+	 * perspective they are "normal" pages, albeit with slightly different
+	 * usage rules.
+	 */
 	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn));
+		return PageReserved(pfn_to_page(pfn)) &&
+		       !kvm_is_zone_device_pfn(pfn);
 
 	return true;
 }
@@ -663,6 +683,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
 
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
+	if (init_srcu_struct(&kvm->srcu))
+		goto out_err_no_srcu;
+	if (init_srcu_struct(&kvm->irq_srcu))
+		goto out_err_no_irq_srcu;
+
+	refcount_set(&kvm->users_count, 1);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		struct kvm_memslots *slots = kvm_alloc_memslots();
 
@@ -680,7 +706,6 @@ static struct kvm *kvm_create_vm(unsigned long type)
 			goto out_err_no_arch_destroy_vm;
 	}
 
-	refcount_set(&kvm->users_count, 1);
 	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_no_arch_destroy_vm;
@@ -693,11 +718,6 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
-	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_no_srcu;
-	if (init_srcu_struct(&kvm->irq_srcu))
-		goto out_err_no_irq_srcu;
-
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
 		goto out_err_no_mmu_notifier;
@@ -720,19 +740,19 @@ out_err:
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
 #endif
 out_err_no_mmu_notifier:
-	cleanup_srcu_struct(&kvm->irq_srcu);
-out_err_no_irq_srcu:
-	cleanup_srcu_struct(&kvm->srcu);
-out_err_no_srcu:
 	hardware_disable_all();
 out_err_no_disable:
 	kvm_arch_destroy_vm(kvm);
-	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
 out_err_no_arch_destroy_vm:
+	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm_get_bus(kvm, i));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
 		kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
+	cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
+	cleanup_srcu_struct(&kvm->srcu);
+out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
 	return ERR_PTR(r);
@@ -1886,7 +1906,7 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
 
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn)) {
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
 
 		SetPageDirty(page);
@@ -1896,7 +1916,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn))
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
 		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);