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

Pull kvm fixes from Paolo Bonzini:
"The main change here is a revert of reverts. We recently simplified
some code that was thought unnecessary; however, since then KVM has
grown quite a few cond_resched()s and for that reason the simplified
code is prone to livelocks---one CPUs tries to empty a list of guest
page tables while the others keep adding to them. This adds back the
generation-based zapping of guest page tables, which was not
unnecessary after all.

On top of this, there is a fix for a kernel memory leak and a couple
of s390 fixlets as well"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86/mmu: Reintroduce fast invalidate/zap for flushing memslot
KVM: x86: work around leak of uninitialized stack contents
KVM: nVMX: handle page fault in vmread
KVM: s390: Do not leak kernel stack data in the KVM_S390_INTERRUPT ioctl
KVM: s390: kvm_s390_vm_start_migration: check dirty_bitmap before using it as target for memset()

arch/s390/kvm/interrupt.c

···
 	case KVM_S390_MCHK:
 		irq->u.mchk.mcic = s390int->parm64;
 		break;
+	case KVM_S390_INT_PFAULT_INIT:
+		irq->u.ext.ext_params = s390int->parm;
+		irq->u.ext.ext_params2 = s390int->parm64;
+		break;
+	case KVM_S390_RESTART:
+	case KVM_S390_INT_CLOCK_COMP:
+	case KVM_S390_INT_CPU_TIMER:
+		break;
+	default:
+		return -EINVAL;
 	}
 	return 0;
 }

arch/s390/kvm/kvm-s390.c

···
 	/* mark all the pages in active slots as dirty */
 	for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
 		ms = slots->memslots + slotnr;
+		if (!ms->dirty_bitmap)
+			return -EINVAL;
 		/*
 		 * The second half of the bitmap is only used on x86,
 		 * and would be wasted otherwise, so we put it to good
···
 	}
 	case KVM_S390_INTERRUPT: {
 		struct kvm_s390_interrupt s390int;
-		struct kvm_s390_irq s390irq;
+		struct kvm_s390_irq s390irq = {};
 
 		if (copy_from_user(&s390int, argp, sizeof(s390int)))
 			return -EFAULT;

arch/x86/include/asm/kvm_host.h

···
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
 	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
+	unsigned long mmu_valid_gen;
 	DECLARE_BITMAP(unsync_child_bitmap, 512);
 
 #ifdef CONFIG_X86_32
···
 	unsigned long n_requested_mmu_pages;
 	unsigned long n_max_mmu_pages;
 	unsigned int indirect_shadow_pages;
+	unsigned long mmu_valid_gen;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
 	 * Hash table of struct kvm_mmu_page.

arch/x86/kvm/mmu.c

···
 	if (!direct)
 		sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+
+	/*
+	 * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
+	 * depends on valid pages being added to the head of the list.  See
+	 * comments in kvm_zap_obsolete_pages().
+	 */
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
 	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
 	return sp;
···
 #define for_each_valid_sp(_kvm, _sp, _gfn)				\
 	hlist_for_each_entry(_sp,					\
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
-		if ((_sp)->role.invalid) {    \
+		if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) {    \
 		} else
 
 #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)			\
···
 static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { }
 static void mmu_audit_disable(void) { }
 #endif
+
+static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+}
 
 static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			 struct list_head *invalid_list)
···
 		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
 			flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
 	}
+	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
 	clear_page(sp->spt);
 	trace_kvm_mmu_get_page(sp, true);
 
···
 			return false;
 
 		if (cached_root_available(vcpu, new_cr3, new_role)) {
+			/*
+			 * It is possible that the cached previous root page is
+			 * obsolete because of a change in the MMU generation
+			 * number. However, changing the generation number is
+			 * accompanied by KVM_REQ_MMU_RELOAD, which will free
+			 * the root set here and allocate a new one.
+			 */
 			kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
 			if (!skip_tlb_flush) {
 				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
···
 	return alloc_mmu_pages(vcpu);
 }
 
+
+static void kvm_zap_obsolete_pages(struct kvm *kvm)
+{
+	struct kvm_mmu_page *sp, *node;
+	LIST_HEAD(invalid_list);
+	int ign;
+
+restart:
+	list_for_each_entry_safe_reverse(sp, node,
+	      &kvm->arch.active_mmu_pages, link) {
+		/*
+		 * No obsolete valid page exists before a newly created page
+		 * since active_mmu_pages is a FIFO list.
+		 */
+		if (!is_obsolete_sp(kvm, sp))
+			break;
+
+		/*
+		 * Do not repeatedly zap a root page to avoid unnecessary
+		 * KVM_REQ_MMU_RELOAD, otherwise we may not be able to
+		 * progress:
+		 *    vcpu 0                        vcpu 1
+		 *                         call vcpu_enter_guest():
+		 *                            1): handle KVM_REQ_MMU_RELOAD
+		 *                                and require mmu-lock to
+		 *                                load mmu
+		 * repeat:
+		 *    1): zap root page and
+		 *        send KVM_REQ_MMU_RELOAD
+		 *
+		 *    2): if (cond_resched_lock(mmu-lock))
+		 *
+		 *                            2): hold mmu-lock and load mmu
+		 *
+		 *                            3): see KVM_REQ_MMU_RELOAD bit
+		 *                                on vcpu->requests is set
+		 *                                then return 1 to call
+		 *                                vcpu_enter_guest() again.
+		 *            goto repeat;
+		 *
+		 * Since we are reversely walking the list and the invalid
+		 * list will be moved to the head, skip the invalid page
+		 * can help us to avoid the infinity list walking.
+		 */
+		if (sp->role.invalid)
+			continue;
+
+		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			cond_resched_lock(&kvm->mmu_lock);
+			goto restart;
+		}
+
+		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
+			goto restart;
+	}
+
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+}
+
+/*
+ * Fast invalidate all shadow pages and use lock-break technique
+ * to zap obsolete pages.
+ *
+ * It's required when memslot is being deleted or VM is being
+ * destroyed, in these cases, we should ensure that KVM MMU does
+ * not use any resource of the being-deleted slot or all slots
+ * after calling the function.
+ */
+static void kvm_mmu_zap_all_fast(struct kvm *kvm)
+{
+	spin_lock(&kvm->mmu_lock);
+	kvm->arch.mmu_valid_gen++;
+
+	kvm_zap_obsolete_pages(kvm);
+	spin_unlock(&kvm->mmu_lock);
+}
+
 static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
 			struct kvm_memory_slot *slot,
 			struct kvm_page_track_notifier_node *node)
 {
-	kvm_mmu_zap_all(kvm);
+	kvm_mmu_zap_all_fast(kvm);
 }
 
 void kvm_mmu_init_vm(struct kvm *kvm)

arch/x86/kvm/vmx/nested.c

···
 	int len;
 	gva_t gva = 0;
 	struct vmcs12 *vmcs12;
+	struct x86_exception e;
 	short offset;
 
 	if (!nested_vmx_check_permission(vcpu))
···
 				vmx_instruction_info, true, len, &gva))
 			return 1;
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
-		kvm_write_guest_virt_system(vcpu, gva, &field_value, len, NULL);
+		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+			kvm_inject_page_fault(vcpu, &e);
 	}
 
 	return nested_vmx_succeed(vcpu);

arch/x86/kvm/x86.c

···
 	/* kvm_write_guest_virt_system can pull in tons of pages. */
 	vcpu->arch.l1tf_flush_l1d = true;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }