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

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Fix MTE shared page detection

   - Enable selftest's use of PMU registers when asked to

  s390:

   - restore 5.13 debugfs names

  x86:

   - fix sizes for vcpu-id indexed arrays

   - fixes for AMD virtualized LAPIC (AVIC)

   - other small bugfixes

  Generic:

   - access tracking performance test

   - dirty_log_perf_test command line parsing fix

   - Fix selftest use of obsolete pthread_yield() in favour of
     sched_yield()

   - use cpu_relax when halt polling

   - fixed missing KVM_CLEAR_DIRTY_LOG compat ioctl"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: add missing compat KVM_CLEAR_DIRTY_LOG
  KVM: use cpu_relax when halt polling
  KVM: SVM: use vmcb01 in svm_refresh_apicv_exec_ctrl
  KVM: SVM: tweak warning about enabled AVIC on nested entry
  KVM: SVM: svm_set_vintr don't warn if AVIC is active but is about to be deactivated
  KVM: s390: restore old debugfs names
  KVM: SVM: delay svm_vcpu_init_msrpm after svm->vmcb is initialized
  KVM: selftests: Introduce access_tracking_perf_test
  KVM: selftests: Fix missing break in dirty_log_perf_test arg parsing
  x86/kvm: fix vcpu-id indexed array sizes
  KVM: x86: Check the right feature bit for MSR_KVM_ASYNC_PF_ACK access
  docs: virt: kvm: api.rst: replace some characters
  KVM: Documentation: Fix KVM_CAP_ENFORCE_PV_FEATURE_CPUID name
  KVM: nSVM: Swap the parameter order for svm_copy_vmrun_state()/svm_copy_vmloadsave_state()
  KVM: nSVM: Rename nested_svm_vmloadsave() to svm_copy_vmloadsave_state()
  KVM: arm64: selftests: get-reg-list: actually enable pmu regs in pmu sublist
  KVM: selftests: change pthread_yield to sched_yield
  KVM: arm64: Fix detection of shared VMAs on guest fault

Documentation/virt/kvm/api.rst

@@ -855,7 +855,7 @@ in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
 use PPIs designated for specific cpus.  The irq field is interpreted
 like this::
 
-  bits:  |  31 ... 28  | 27 ... 24 | 23  ... 16 | 15 ... 0 |
+  bits:  |  31 ... 28  | 27 ... 24 | 23  ... 16 | 15 ... 0 |
   field: | vcpu2_index | irq_type  | vcpu_index |  irq_id  |
 
 The irq_type field has the following values:
@@ -2149,10 +2149,10 @@ prior to calling the KVM_RUN ioctl.
 Errors:
 
   ======   ============================================================
-  ENOENT   no such register
-  EINVAL   invalid register ID, or no such register or used with VMs in
+  ENOENT   no such register
+  EINVAL   invalid register ID, or no such register or used with VMs in
            protected virtualization mode on s390
-  EPERM    (arm64) register access not allowed before vcpu finalization
+  EPERM    (arm64) register access not allowed before vcpu finalization
   ======   ============================================================
 
 (These error codes are indicative only: do not rely on a specific error
@@ -2590,10 +2590,10 @@ following id bit patterns::
 Errors include:
 
   ======== ============================================================
-  ENOENT   no such register
-  EINVAL   invalid register ID, or no such register or used with VMs in
+  ENOENT   no such register
+  EINVAL   invalid register ID, or no such register or used with VMs in
            protected virtualization mode on s390
-  EPERM    (arm64) register access not allowed before vcpu finalization
+  EPERM    (arm64) register access not allowed before vcpu finalization
   ======== ============================================================
 
 (These error codes are indicative only: do not rely on a specific error
@@ -3112,13 +3112,13 @@ current state.  "addr" is ignored.
 Errors:
 
   ======     =================================================================
-  EINVAL     the target is unknown, or the combination of features is invalid.
-  ENOENT     a features bit specified is unknown.
+  EINVAL     the target is unknown, or the combination of features is invalid.
+  ENOENT     a features bit specified is unknown.
   ======     =================================================================
 
 This tells KVM what type of CPU to present to the guest, and what
-optional features it should have.  This will cause a reset of the cpu
-registers to their initial values.  If this is not called, KVM_RUN will
+optional features it should have.  This will cause a reset of the cpu
+registers to their initial values.  If this is not called, KVM_RUN will
 return ENOEXEC for that vcpu.
 
 The initial values are defined as:
@@ -3239,8 +3239,8 @@ VCPU matching underlying host.
 Errors:
 
   =====      ==============================================================
-  E2BIG      the reg index list is too big to fit in the array specified by
-             the user (the number required will be written into n).
+  E2BIG      the reg index list is too big to fit in the array specified by
+             the user (the number required will be written into n).
   =====      ==============================================================
 
 ::
@@ -3288,7 +3288,7 @@ specific device.
 ARM/arm64 divides the id field into two parts, a device id and an
 address type id specific to the individual device::
 
-  bits:  | 63        ...       32 | 31    ...    16 | 15    ...    0 |
+  bits:  | 63        ...       32 | 31    ...    16 | 15    ...    0 |
   field: |        0x00000000      |     device id   |  addr type id  |
 
 ARM/arm64 currently only require this when using the in-kernel GIC
@@ -7049,7 +7049,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
 trap and emulate MSRs that are outside of the scope of KVM as well as
 limit the attack surface on KVM's MSR emulation code.
 
-8.28 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
 -----------------------------
 
 Architectures: x86

arch/arm64/kvm/mmu.c

@@ -947,7 +947,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
 
-	shared = (vma->vm_flags & VM_PFNMAP);
+	shared = (vma->vm_flags & VM_SHARED);
 
 	switch (vma_shift) {
 #ifndef __PAGETABLE_PMD_FOLDED

arch/s390/include/asm/kvm_host.h

@@ -445,15 +445,15 @@ struct kvm_vcpu_stat {
 	u64 instruction_sigp_init_cpu_reset;
 	u64 instruction_sigp_cpu_reset;
 	u64 instruction_sigp_unknown;
-	u64 diagnose_10;
-	u64 diagnose_44;
-	u64 diagnose_9c;
-	u64 diagnose_9c_ignored;
-	u64 diagnose_9c_forward;
-	u64 diagnose_258;
-	u64 diagnose_308;
-	u64 diagnose_500;
-	u64 diagnose_other;
+	u64 instruction_diagnose_10;
+	u64 instruction_diagnose_44;
+	u64 instruction_diagnose_9c;
+	u64 diag_9c_ignored;
+	u64 diag_9c_forward;
+	u64 instruction_diagnose_258;
+	u64 instruction_diagnose_308;
+	u64 instruction_diagnose_500;
+	u64 instruction_diagnose_other;
 	u64 pfault_sync;
 };
 

arch/s390/kvm/diag.c

@@ -24,7 +24,7 @@ static int diag_release_pages(struct kvm_vcpu *vcpu)
 
 	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
 	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + PAGE_SIZE;
-	vcpu->stat.diagnose_10++;
+	vcpu->stat.instruction_diagnose_10++;
 
 	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
 	    || start < 2 * PAGE_SIZE)
@@ -74,7 +74,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 
 	VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx",
 		   vcpu->run->s.regs.gprs[rx]);
-	vcpu->stat.diagnose_258++;
+	vcpu->stat.instruction_diagnose_258++;
 	if (vcpu->run->s.regs.gprs[rx] & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
@@ -145,7 +145,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
 static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
-	vcpu->stat.diagnose_44++;
+	vcpu->stat.instruction_diagnose_44++;
 	kvm_vcpu_on_spin(vcpu, true);
 	return 0;
 }
@@ -169,7 +169,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 	int tid;
 
 	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
-	vcpu->stat.diagnose_9c++;
+	vcpu->stat.instruction_diagnose_9c++;
 
 	/* yield to self */
 	if (tid == vcpu->vcpu_id)
@@ -192,7 +192,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 		VCPU_EVENT(vcpu, 5,
 			   "diag time slice end directed to %d: yield forwarded",
 			   tid);
-		vcpu->stat.diagnose_9c_forward++;
+		vcpu->stat.diag_9c_forward++;
 		return 0;
 	}
 
@@ -203,7 +203,7 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
 	return 0;
 no_yield:
 	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid);
-	vcpu->stat.diagnose_9c_ignored++;
+	vcpu->stat.diag_9c_ignored++;
 	return 0;
 }
 
@@ -213,7 +213,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
 
 	VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode);
-	vcpu->stat.diagnose_308++;
+	vcpu->stat.instruction_diagnose_308++;
 	switch (subcode) {
 	case 3:
 		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
@@ -245,7 +245,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
 {
 	int ret;
 
-	vcpu->stat.diagnose_500++;
+	vcpu->stat.instruction_diagnose_500++;
 	/* No virtio-ccw notification? Get out quickly. */
 	if (!vcpu->kvm->arch.css_support ||
 	    (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
@@ -299,7 +299,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 	case 0x500:
 		return __diag_virtio_hypercall(vcpu);
 	default:
-		vcpu->stat.diagnose_other++;
+		vcpu->stat.instruction_diagnose_other++;
 		return -EOPNOTSUPP;
 	}
 }

arch/s390/kvm/kvm-s390.c

@@ -163,15 +163,15 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset),
 	STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset),
 	STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown),
-	STATS_DESC_COUNTER(VCPU, diagnose_10),
-	STATS_DESC_COUNTER(VCPU, diagnose_44),
-	STATS_DESC_COUNTER(VCPU, diagnose_9c),
-	STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored),
-	STATS_DESC_COUNTER(VCPU, diagnose_9c_forward),
-	STATS_DESC_COUNTER(VCPU, diagnose_258),
-	STATS_DESC_COUNTER(VCPU, diagnose_308),
-	STATS_DESC_COUNTER(VCPU, diagnose_500),
-	STATS_DESC_COUNTER(VCPU, diagnose_other),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_10),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_44),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_9c),
+	STATS_DESC_COUNTER(VCPU, diag_9c_ignored),
+	STATS_DESC_COUNTER(VCPU, diag_9c_forward),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_258),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_308),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_500),
+	STATS_DESC_COUNTER(VCPU, instruction_diagnose_other),
 	STATS_DESC_COUNTER(VCPU, pfault_sync)
 };
 static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) ==

arch/x86/kvm/ioapic.c

@@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);

arch/x86/kvm/ioapic.h

@@ -43,13 +43,13 @@ struct kvm_vcpu;
 
 struct dest_map {
 	/* vcpu bitmap where IRQ has been sent */
-	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
+	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);
 
 	/*
 	 * Vector sent to a given vcpu, only valid when
 	 * the vcpu's bit in map is set
 	 */
-	u8 vectors[KVM_MAX_VCPU_ID];
+	u8 vectors[KVM_MAX_VCPU_ID + 1];
 };
 
 

arch/x86/kvm/svm/avic.c

@@ -646,7 +646,7 @@ static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *vmcb = svm->vmcb;
+	struct vmcb *vmcb = svm->vmcb01.ptr;
 	bool activated = kvm_vcpu_apicv_active(vcpu);
 
 	if (!enable_apicv)

arch/x86/kvm/svm/nested.c

@@ -515,7 +515,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	 * Also covers avic_vapic_bar, avic_backing_page, avic_logical_id,
 	 * avic_physical_id.
 	 */
-	WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK);
+	WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
 
 	/* Copied from vmcb01.  msrpm_base can be overwritten later.  */
 	svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl;
@@ -702,8 +702,8 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 }
 
 /* Copy state save area fields which are handled by VMRUN */
-void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
-			  struct vmcb_save_area *to_save)
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+			  struct vmcb_save_area *from_save)
 {
 	to_save->es = from_save->es;
 	to_save->cs = from_save->cs;
@@ -722,7 +722,7 @@ void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
 	to_save->cpl = 0;
 }
 
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 {
 	to_vmcb->save.fs = from_vmcb->save.fs;
 	to_vmcb->save.gs = from_vmcb->save.gs;
@@ -1385,7 +1385,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 
 	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
 
-	svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save);
+	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
 	nested_load_control_from_vmcb12(svm, ctl);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);

arch/x86/kvm/svm/svm.c

@@ -1406,8 +1406,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		goto error_free_vmsa_page;
 	}
 
-	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
 	svm->vmcb01.ptr = page_address(vmcb01_page);
 	svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
 
@@ -1419,6 +1417,8 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	svm_switch_vmcb(svm, &svm->vmcb01);
 	init_vmcb(vcpu);
 
+	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
+
 	svm_init_osvw(vcpu);
 	vcpu->arch.microcode_version = 0x01000065;
 
@@ -1568,8 +1568,11 @@ static void svm_set_vintr(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control;
 
-	/* The following fields are ignored when AVIC is enabled */
-	WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu));
+	/*
+	 * The following fields are ignored when AVIC is enabled
+	 */
+	WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
+
 	svm_set_intercept(svm, INTERCEPT_VINTR);
 
 	/*
@@ -2147,11 +2150,12 @@ static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload)
 	ret = kvm_skip_emulated_instruction(vcpu);
 
 	if (vmload) {
-		nested_svm_vmloadsave(vmcb12, svm->vmcb);
+		svm_copy_vmloadsave_state(svm->vmcb, vmcb12);
 		svm->sysenter_eip_hi = 0;
 		svm->sysenter_esp_hi = 0;
-	} else
-		nested_svm_vmloadsave(svm->vmcb, vmcb12);
+	} else {
+		svm_copy_vmloadsave_state(vmcb12, svm->vmcb);
+	}
 
 	kvm_vcpu_unmap(vcpu, &map, true);
 
@@ -4344,8 +4348,8 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 
 		BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
 
-		svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
-				     map_save.hva + 0x400);
+		svm_copy_vmrun_state(map_save.hva + 0x400,
+				     &svm->vmcb01.ptr->save);
 
 		kvm_vcpu_unmap(vcpu, &map_save, true);
 	}
@@ -4393,8 +4397,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 					 &map_save) == -EINVAL)
 				return 1;
 
-			svm_copy_vmrun_state(map_save.hva + 0x400,
-					     &svm->vmcb01.ptr->save);
+			svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+					     map_save.hva + 0x400);
 
 			kvm_vcpu_unmap(vcpu, &map_save, true);
 		}

arch/x86/kvm/svm/svm.h

@@ -464,9 +464,9 @@ void svm_leave_nested(struct vcpu_svm *svm);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);
 int nested_svm_vmrun(struct kvm_vcpu *vcpu);
-void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
-			  struct vmcb_save_area *to_save);
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+			  struct vmcb_save_area *from_save);
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
 int nested_svm_vmexit(struct vcpu_svm *svm);
 
 static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)

arch/x86/kvm/svm/svm_onhyperv.h

@@ -89,7 +89,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments(
 	 * as we mark it dirty unconditionally towards end of vcpu
 	 * init phase.
 	 */
-	if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
+	if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
 	    hve->hv_enlightenments_control.msr_bitmap)
 		vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
 }