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

Pull kvm fixes from Paolo Bonzini:
 "x86:

   - Fixes for Xen emulation. While nobody should be enabling it in the
     kernel (the only public users of the feature are the selftests),
     the bug effectively allows userspace to read arbitrary memory.

   - Correctness fixes for nested hypervisors that do not intercept INIT
     or SHUTDOWN on AMD; the subsequent CPU reset can cause a
     use-after-free when it disables virtualization extensions. While
     downgrading the panic to a WARN is quite easy, the full fix is a
     bit more laborious; there are also tests. This is the bulk of the
     pull request.

   - Fix race condition due to incorrect mmu_lock use around
     make_mmu_pages_available().

  Generic:

   - Obey changes to the kvm.halt_poll_ns module parameter in VMs not
     using KVM_CAP_HALT_POLL, restoring behavior from before the
     introduction of the capability"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Update gfn_to_pfn_cache khva when it moves within the same page
  KVM: x86/xen: Only do in-kernel acceleration of hypercalls for guest CPL0
  KVM: x86/xen: Validate port number in SCHEDOP_poll
  KVM: x86/mmu: Fix race condition in direct_page_fault
  KVM: x86: remove exit_int_info warning in svm_handle_exit
  KVM: selftests: add svm part to triple_fault_test
  KVM: x86: allow L1 to not intercept triple fault
  kvm: selftests: add svm nested shutdown test
  KVM: selftests: move idt_entry to header
  KVM: x86: forcibly leave nested mode on vCPU reset
  KVM: x86: add kvm_leave_nested
  KVM: x86: nSVM: harden svm_free_nested against freeing vmcb02 while still in use
  KVM: x86: nSVM: leave nested mode on vCPU free
  KVM: Obey kvm.halt_poll_ns in VMs not using KVM_CAP_HALT_POLL
  KVM: Avoid re-reading kvm->max_halt_poll_ns during halt-polling
  KVM: Cap vcpu->halt_poll_ns before halting rather than after

arch/x86/kvm/mmu/mmu.c

@@ -2443,6 +2443,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 {
 	bool list_unstable, zapped_root = false;
 
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	trace_kvm_mmu_prepare_zap_page(sp);
 	++kvm->stat.mmu_shadow_zapped;
 	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
@@ -4262,14 +4263,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
-	r = make_mmu_pages_available(vcpu);
-	if (r)
-		goto out_unlock;
-
-	if (is_tdp_mmu_fault)
+	if (is_tdp_mmu_fault) {
 		r = kvm_tdp_mmu_map(vcpu, fault);
-	else
+	} else {
+		r = make_mmu_pages_available(vcpu);
+		if (r)
+			goto out_unlock;
 		r = __direct_map(vcpu, fault);
+	}
 
 out_unlock:
 	if (is_tdp_mmu_fault)

arch/x86/kvm/svm/nested.c

@@ -1091,6 +1091,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN))
+		return;
+
+	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN);
 }
 
@@ -1125,6 +1131,9 @@ void svm_free_nested(struct vcpu_svm *svm)
 	if (!svm->nested.initialized)
 		return;
 
+	if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr))
+		svm_switch_vmcb(svm, &svm->vmcb01);
+
 	svm_vcpu_free_msrpm(svm->nested.msrpm);
 	svm->nested.msrpm = NULL;
 
@@ -1143,9 +1152,6 @@ void svm_free_nested(struct vcpu_svm *svm)
 	svm->nested.initialized = false;
 }
 
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
 void svm_leave_nested(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);

arch/x86/kvm/svm/svm.c

@@ -346,12 +346,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	return 0;
 }
 
-static int is_external_interrupt(u32 info)
-{
-	info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
-	return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
-}
-
 static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1438,6 +1432,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	 */
 	svm_clear_current_vmcb(svm->vmcb);
 
+	svm_leave_nested(vcpu);
 	svm_free_nested(svm);
 
 	sev_free_vcpu(vcpu);
@@ -3425,15 +3420,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		return 0;
 	}
 
-	if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
-	    exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
-	    exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH &&
-	    exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI)
-		printk(KERN_ERR "%s: unexpected exit_int_info 0x%x "
-		       "exit_code 0x%x\n",
-		       __func__, svm->vmcb->control.exit_int_info,
-		       exit_code);
-
 	if (exit_fastpath != EXIT_FASTPATH_NONE)
 		return 1;
 

arch/x86/kvm/vmx/nested.c

@@ -4854,6 +4854,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu)
 {
+	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
 }
 
@@ -6440,9 +6441,6 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	return kvm_state.size;
 }
 
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
 void vmx_leave_nested(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu)) {

arch/x86/kvm/x86.c

@@ -628,6 +628,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
 	ex->payload = payload;
 }
 
+/* Forcibly leave the nested mode in cases like a vCPU reset */
+static void kvm_leave_nested(struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops.nested_ops->leave_nested(vcpu);
+}
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
 	        bool has_payload, unsigned long payload, bool reinject)
@@ -5195,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
 		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
-			kvm_x86_ops.nested_ops->leave_nested(vcpu);
+			kvm_leave_nested(vcpu);
 			kvm_smm_changed(vcpu, events->smi.smm);
 		}
 
@@ -9805,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 
 int kvm_check_nested_events(struct kvm_vcpu *vcpu)
 {
-	if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+	if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 		kvm_x86_ops.nested_ops->triple_fault(vcpu);
 		return 1;
 	}
@@ -10560,15 +10566,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
-		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
-			if (is_guest_mode(vcpu)) {
+		if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+			if (is_guest_mode(vcpu))
 				kvm_x86_ops.nested_ops->triple_fault(vcpu);
-			} else {
+
+			if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 				vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
 				vcpu->mmio_needed = 0;
 				r = 0;
-				goto out;
 			}
+			goto out;
 		}
 		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
 			/* Page is swapped out. Do synthetic halt */
@@ -11997,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	WARN_ON_ONCE(!init_event &&
 		     (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu)));
 
+	/*
+	 * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's
+	 * possible to INIT the vCPU while L2 is active.  Force the vCPU back
+	 * into L1 as EFER.SVME is cleared on INIT (along with all other EFER
+	 * bits), i.e. virtualization is disabled.
+	 */
+	if (is_guest_mode(vcpu))
+		kvm_leave_nested(vcpu);
+
 	kvm_lapic_reset(vcpu, init_event);
 
+	WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu));
 	vcpu->arch.hflags = 0;
 
 	vcpu->arch.smi_pending = 0;

arch/x86/kvm/xen.c

@@ -954,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
 	return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result);
 }
 
+static inline int max_evtchn_port(struct kvm *kvm)
+{
+	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
+		return EVTCHN_2L_NR_CHANNELS;
+	else
+		return COMPAT_EVTCHN_2L_NR_CHANNELS;
+}
+
 static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports,
 			       evtchn_port_t *ports)
 {
@@ -1042,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 			*r = -EFAULT;
 			goto out;
 		}
+		if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
+			*r = -EINVAL;
+			goto out;
+		}
 	}
 
 	if (sched_poll.nr_ports == 1)
@@ -1215,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	bool longmode;
 	u64 input, params[6], r = -ENOSYS;
 	bool handled = false;
+	u8 cpl;
 
 	input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX);
 
@@ -1242,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 		params[5] = (u64)kvm_r9_read(vcpu);
 	}
 #endif
+	cpl = static_call(kvm_x86_get_cpl)(vcpu);
 	trace_kvm_xen_hypercall(input, params[0], params[1], params[2],
 				params[3], params[4], params[5]);
 
+	/*
+	 * Only allow hypercall acceleration for CPL0. The rare hypercalls that
+	 * are permitted in guest userspace can be handled by the VMM.
+	 */
+	if (unlikely(cpl > 0))
+		goto handle_in_userspace;
+
 	switch (input) {
 	case __HYPERVISOR_xen_version:
 		if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) {
@@ -1279,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	if (handled)
 		return kvm_xen_hypercall_set_result(vcpu, r);
 
+handle_in_userspace:
 	vcpu->run->exit_reason = KVM_EXIT_XEN;
 	vcpu->run->xen.type = KVM_EXIT_XEN_HCALL;
 	vcpu->run->xen.u.hcall.longmode = longmode;
-	vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu);
+	vcpu->run->xen.u.hcall.cpl = cpl;
 	vcpu->run->xen.u.hcall.input = input;
 	vcpu->run->xen.u.hcall.params[0] = params[0];
 	vcpu->run->xen.u.hcall.params[1] = params[1];
@@ -1297,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static inline int max_evtchn_port(struct kvm *kvm)
-{
-	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
-		return EVTCHN_2L_NR_CHANNELS;
-	else
-		return COMPAT_EVTCHN_2L_NR_CHANNELS;
-}
-
 static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port)
 {
 	int poll_evtchn = vcpu->arch.xen.poll_evtchn;

include/linux/kvm_host.h

@@ -776,6 +776,7 @@ struct kvm {
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
 	pid_t userspace_pid;
+	bool override_halt_poll_ns;
 	unsigned int max_halt_poll_ns;
 	u32 dirty_ring_size;
 	bool vm_bugged;

tools/testing/selftests/kvm/.gitignore

@@ -41,6 +41,7 @@
 /x86_64/svm_vmcall_test
 /x86_64/svm_int_ctl_test
 /x86_64/svm_nested_soft_inject_test
+/x86_64/svm_nested_shutdown_test
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
 /x86_64/tsc_scaling_sync

tools/testing/selftests/kvm/Makefile

@@ -101,6 +101,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test

tools/testing/selftests/kvm/include/x86_64/processor.h

@@ -748,6 +748,19 @@ struct ex_regs {
 	uint64_t rflags;
 };
 
+struct idt_entry {
+	uint16_t offset0;
+	uint16_t selector;
+	uint16_t ist : 3;
+	uint16_t : 5;
+	uint16_t type : 4;
+	uint16_t : 1;
+	uint16_t dpl : 2;
+	uint16_t p : 1;
+	uint16_t offset1;
+	uint32_t offset2; uint32_t reserved;
+};
+
 void vm_init_descriptor_tables(struct kvm_vm *vm);
 void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
 void vm_install_exception_handler(struct kvm_vm *vm, int vector,

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -1074,19 +1074,6 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 	}
 }
 
-struct idt_entry {
-	uint16_t offset0;
-	uint16_t selector;
-	uint16_t ist : 3;
-	uint16_t : 5;
-	uint16_t type : 4;
-	uint16_t : 1;
-	uint16_t dpl : 2;
-	uint16_t p : 1;
-	uint16_t offset1;
-	uint32_t offset2; uint32_t reserved;
-};
-
 static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
 			  int dpl, unsigned short selector)
 {

tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c

@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_nested_shutdown_test
+ *
+ * Copyright (C) 2022, Red Hat, Inc.
+ *
+ * Nested SVM testing: test that unintercepted shutdown in L2 doesn't crash the host
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+	__asm__ __volatile__("ud2");
+}
+
+static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt)
+{
+	#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN));
+
+	idt[6].p   = 0; // #UD is intercepted but its injection will cause #NP
+	idt[11].p  = 0; // #NP is not intercepted and will cause another
+			// #NP that will be converted to #DF
+	idt[8].p   = 0; // #DF will cause #NP which will cause SHUTDOWN
+
+	run_guest(vmcb, svm->vmcb_gpa);
+
+	/* should not reach here */
+	GUEST_ASSERT(0);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
+	vm_vaddr_t svm_gva;
+	struct kvm_vm *vm;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vcpu);
+
+	vcpu_alloc_svm(vm, &svm_gva);
+
+	vcpu_args_set(vcpu, 2, svm_gva, vm->idt);
+	run = vcpu->run;
+
+	vcpu_run(vcpu);
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+		    "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	kvm_vm_free(vm);
+}