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

Pull kvm fixes from Paolo Bonzini:
 "ARM64:

   - Address a rather annoying bug w.r.t. guest timer offsetting. The
     synchronization of timer offsets between vCPUs was broken, leading
     to inconsistent timer reads within the VM.

  x86:

   - New tests for the slow path of the EVTCHNOP_send Xen hypercall

   - Add missing nVMX consistency checks for CR0 and CR4

   - Fix bug that broke AMD GATag on 512 vCPU machines

  Selftests:

   - Skip hugetlb tests if huge pages are not available

   - Sync KVM exit reasons"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: selftests: Sync KVM exit reasons in selftests
  KVM: selftests: Add macro to generate KVM exit reason strings
  KVM: selftests: Print expected and actual exit reason in KVM exit reason assert
  KVM: selftests: Make vCPU exit reason test assertion common
  KVM: selftests: Add EVTCHNOP_send slow path test to xen_shinfo_test
  KVM: selftests: Use enum for test numbers in xen_shinfo_test
  KVM: selftests: Add helpers to make Xen-style VMCALL/VMMCALL hypercalls
  KVM: selftests: Move the guts of kvm_hypercall() to a separate macro
  KVM: SVM: WARN if GATag generation drops VM or vCPU ID information
  KVM: SVM: Modify AVIC GATag to support max number of 512 vCPUs
  KVM: SVM: Fix a benign off-by-one bug in AVIC physical table mask
  selftests: KVM: skip hugetlb tests if huge pages are not available
  KVM: VMX: Use tabs instead of spaces for indentation
  KVM: VMX: Fix indentation coding style issue
  KVM: nVMX: remove unnecessary #ifdef
  KVM: nVMX: add missing consistency checks for CR0 and CR4
  KVM: arm64: timers: Convert per-vcpu virtual offset to a global value

Author: torvalds

arch/arm64/include/asm/kvm_host.h

@@ -193,6 +193,9 @@ struct kvm_arch {
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
+	/* Timers */
+	struct arch_timer_vm_data timer_data;
+
 	/* Mandated version of PSCI */
 	u32 psci_version;
 

arch/arm64/kvm/arch_timer.c

@@ -84,14 +84,10 @@ u64 timer_get_cval(struct arch_timer_context *ctxt)
 
 static u64 timer_get_offset(struct arch_timer_context *ctxt)
 {
-	struct kvm_vcpu *vcpu = ctxt->vcpu;
+	if (ctxt->offset.vm_offset)
+		return *ctxt->offset.vm_offset;
 
-	switch(arch_timer_ctx_index(ctxt)) {
-	case TIMER_VTIMER:
-		return __vcpu_sys_reg(vcpu, CNTVOFF_EL2);
-	default:
-		return 0;
-	}
+	return 0;
 }
 
 static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
@@ -128,15 +124,12 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
 
 static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset)
 {
-	struct kvm_vcpu *vcpu = ctxt->vcpu;
-
-	switch(arch_timer_ctx_index(ctxt)) {
-	case TIMER_VTIMER:
-		__vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset;
-		break;
-	default:
+	if (!ctxt->offset.vm_offset) {
 		WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt));
+		return;
 	}
+
+	WRITE_ONCE(*ctxt->offset.vm_offset, offset);
 }
 
 u64 kvm_phys_timer_read(void)
@@ -765,36 +758,18 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/* Make the updates of cntvoff for all vtimer contexts atomic */
-static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
-{
-	unsigned long i;
-	struct kvm *kvm = vcpu->kvm;
-	struct kvm_vcpu *tmp;
-
-	mutex_lock(&kvm->lock);
-	kvm_for_each_vcpu(i, tmp, kvm)
-		timer_set_offset(vcpu_vtimer(tmp), cntvoff);
-
-	/*
-	 * When called from the vcpu create path, the CPU being created is not
-	 * included in the loop above, so we just set it here as well.
-	 */
-	timer_set_offset(vcpu_vtimer(vcpu), cntvoff);
-	mutex_unlock(&kvm->lock);
-}
-
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = vcpu_timer(vcpu);
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
 	vtimer->vcpu = vcpu;
+	vtimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.voffset;
 	ptimer->vcpu = vcpu;
 
 	/* Synchronize cntvoff across all vtimers of a VM. */
-	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
+	timer_set_offset(vtimer, kvm_phys_timer_read());
 	timer_set_offset(ptimer, 0);
 
 	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
@@ -840,7 +815,7 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
 		break;
 	case KVM_REG_ARM_TIMER_CNT:
 		timer = vcpu_vtimer(vcpu);
-		update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value);
+		timer_set_offset(timer, kvm_phys_timer_read() - value);
 		break;
 	case KVM_REG_ARM_TIMER_CVAL:
 		timer = vcpu_vtimer(vcpu);

arch/arm64/kvm/hypercalls.c

@@ -44,7 +44,7 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val)
 	feature = smccc_get_arg1(vcpu);
 	switch (feature) {
 	case KVM_PTP_VIRT_COUNTER:
-		cycles = systime_snapshot.cycles - vcpu_read_sys_reg(vcpu, CNTVOFF_EL2);
+		cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset;
 		break;
 	case KVM_PTP_PHYS_COUNTER:
 		cycles = systime_snapshot.cycles;

arch/x86/include/asm/svm.h

@@ -261,20 +261,22 @@ enum avic_ipi_failure_cause {
 	AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
 };
 
-#define AVIC_PHYSICAL_MAX_INDEX_MASK	GENMASK_ULL(9, 0)
+#define AVIC_PHYSICAL_MAX_INDEX_MASK	GENMASK_ULL(8, 0)
 
 /*
- * For AVIC, the max index allowed for physical APIC ID
- * table is 0xff (255).
+ * For AVIC, the max index allowed for physical APIC ID table is 0xfe (254), as
+ * 0xff is a broadcast to all CPUs, i.e. can't be targeted individually.
  */
 #define AVIC_MAX_PHYSICAL_ID		0XFEULL
 
 /*
- * For x2AVIC, the max index allowed for physical APIC ID
- * table is 0x1ff (511).
+ * For x2AVIC, the max index allowed for physical APIC ID table is 0x1ff (511).
  */
 #define X2AVIC_MAX_PHYSICAL_ID		0x1FFUL
 
+static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_PHYSICAL_ID);
+static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID);
+
 #define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 

arch/x86/kvm/svm/avic.c

@@ -27,19 +27,38 @@
 #include "irq.h"
 #include "svm.h"
 
-/* AVIC GATAG is encoded using VM and VCPU IDs */
-#define AVIC_VCPU_ID_BITS		8
-#define AVIC_VCPU_ID_MASK		((1 << AVIC_VCPU_ID_BITS) - 1)
+/*
+ * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID,
+ * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry
+ * if an interrupt can't be delivered, e.g. because the vCPU isn't running.
+ *
+ * For the vCPU ID, use however many bits are currently allowed for the max
+ * guest physical APIC ID (limited by the size of the physical ID table), and
+ * use whatever bits remain to assign arbitrary AVIC IDs to VMs.  Note, the
+ * size of the GATag is defined by hardware (32 bits), but is an opaque value
+ * as far as hardware is concerned.
+ */
+#define AVIC_VCPU_ID_MASK		AVIC_PHYSICAL_MAX_INDEX_MASK
 
-#define AVIC_VM_ID_BITS			24
-#define AVIC_VM_ID_NR			(1 << AVIC_VM_ID_BITS)
-#define AVIC_VM_ID_MASK			((1 << AVIC_VM_ID_BITS) - 1)
+#define AVIC_VM_ID_SHIFT		HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK)
+#define AVIC_VM_ID_MASK			(GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT)
 
-#define AVIC_GATAG(x, y)		(((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \
-						(y & AVIC_VCPU_ID_MASK))
-#define AVIC_GATAG_TO_VMID(x)		((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
+#define AVIC_GATAG_TO_VMID(x)		((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK)
 #define AVIC_GATAG_TO_VCPUID(x)		(x & AVIC_VCPU_ID_MASK)
 
+#define __AVIC_GATAG(vm_id, vcpu_id)	((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
+					 ((vcpu_id) & AVIC_VCPU_ID_MASK))
+#define AVIC_GATAG(vm_id, vcpu_id)					\
+({									\
+	u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id);			\
+									\
+	WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id));	\
+	WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id));		\
+	ga_tag;								\
+})
+
+static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u);
+
 static bool force_avic;
 module_param_unsafe(force_avic, bool, 0444);
 

arch/x86/kvm/vmx/nested.c

@@ -2903,7 +2903,7 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
-	bool ia32e;
+	bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
 
 	if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
 	    CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
@@ -2923,12 +2923,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 					   vmcs12->host_ia32_perf_global_ctrl)))
 		return -EINVAL;
 
-#ifdef CONFIG_X86_64
-	ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
-#else
-	ia32e = false;
-#endif
-
 	if (ia32e) {
 		if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
 			return -EINVAL;
@@ -3022,7 +3016,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 					struct vmcs12 *vmcs12,
 					enum vm_entry_failure_code *entry_failure_code)
 {
-	bool ia32e;
+	bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);
 
 	*entry_failure_code = ENTRY_FAIL_DEFAULT;
 
@@ -3048,6 +3042,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 					   vmcs12->guest_ia32_perf_global_ctrl)))
 		return -EINVAL;
 
+	if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG))
+		return -EINVAL;
+
+	if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
+	    CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -3059,7 +3060,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	 */
 	if (to_vmx(vcpu)->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
-		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
 		if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
 		    CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
 		    CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&

arch/x86/kvm/vmx/vmenter.S

@@ -262,7 +262,7 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
 	 * eIBRS has its own protection against poisoned RSB, so it doesn't
 	 * need the RSB filling sequence.  But it does need to be enabled, and a
 	 * single call to retire, before the first unbalanced RET.
-         */
+	 */
 
 	FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
 			   X86_FEATURE_RSB_VMEXIT_LITE
@@ -311,7 +311,7 @@ SYM_FUNC_END(vmx_do_nmi_irqoff)
  * vmread_error_trampoline - Trampoline from inline asm to vmread_error()
  * @field:	VMCS field encoding that failed
  * @fault:	%true if the VMREAD faulted, %false if it failed
-
+ *
  * Save and restore volatile registers across a call to vmread_error().  Note,
  * all parameters are passed on the stack.
  */

arch/x86/kvm/vmx/vmx.c

@@ -874,7 +874,7 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
 	 */
 	if (is_guest_mode(vcpu))
 		eb |= get_vmcs12(vcpu)->exception_bitmap;
-        else {
+	else {
 		int mask = 0, match = 0;
 
 		if (enable_ept && (eb & (1u << PF_VECTOR))) {
@@ -1282,7 +1282,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		}
 	}
 
-    	if (vmx->nested.need_vmcs12_to_shadow_sync)
+	if (vmx->nested.need_vmcs12_to_shadow_sync)
 		nested_sync_vmcs12_to_shadow(vcpu);
 
 	if (vmx->guest_state_loaded)
@@ -5049,10 +5049,10 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 	if (to_vmx(vcpu)->nested.nested_run_pending)
 		return -EBUSY;
 
-       /*
-        * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
-        * e.g. if the IRQ arrived asynchronously after checking nested events.
-        */
+	/*
+	 * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
+	 * e.g. if the IRQ arrived asynchronously after checking nested events.
+	 */
 	if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
 		return -EBUSY;
 

include/kvm/arm_arch_timer.h

@@ -23,6 +23,19 @@ enum kvm_arch_timer_regs {
 	TIMER_REG_CTL,
 };
 
+struct arch_timer_offset {
+	/*
+	 * If set, pointer to one of the offsets in the kvm's offset
+	 * structure. If NULL, assume a zero offset.
+	 */
+	u64	*vm_offset;
+};
+
+struct arch_timer_vm_data {
+	/* Offset applied to the virtual timer/counter */
+	u64	voffset;
+};
+
 struct arch_timer_context {
 	struct kvm_vcpu			*vcpu;
 
@@ -32,6 +45,8 @@ struct arch_timer_context {
 	/* Emulated Timer (may be unused) */
 	struct hrtimer			hrtimer;
 
+	/* Offset for this counter/timer */
+	struct arch_timer_offset	offset;
 	/*
 	 * We have multiple paths which can save/restore the timer state onto
 	 * the hardware, so we need some way of keeping track of where the

tools/testing/selftests/kvm/aarch64/psci_test.c

@@ -180,9 +180,7 @@ static void host_test_system_suspend(void)
 
 	enter_guest(source);
 
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_SYSTEM_EVENT,
-		    "Unhandled exit reason: %u (%s)",
-		    run->exit_reason, exit_reason_str(run->exit_reason));
+	TEST_ASSERT_KVM_EXIT_REASON(source, KVM_EXIT_SYSTEM_EVENT);
 	TEST_ASSERT(run->system_event.type == KVM_SYSTEM_EVENT_SUSPEND,
 		    "Unhandled system event: %u (expected: %u)",
 		    run->system_event.type, KVM_SYSTEM_EVENT_SUSPEND);