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

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

1 files changed, 46 insertions, 19 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 9c941535f78c..f235f77cbc03 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -245,7 +245,8 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 	src = &prev->host_state;
 	dest = &vmx->loaded_vmcs->host_state;
 
-	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
+	vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel,
+				src->fs_base, src->gs_base);
 	dest->ldt_sel = src->ldt_sel;
 #ifdef CONFIG_X86_64
 	dest->ds_sel = src->ds_sel;
@@ -269,7 +270,13 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	vmx_sync_vmcs_host_state(vmx, prev);
 	put_cpu();
 
-	vmx_register_cache_reset(vcpu);
+	vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET;
+
+	/*
+	 * All lazily updated registers will be reloaded from VMCS12 on both
+	 * vmentry and vmexit.
+	 */
+	vcpu->arch.regs_dirty = 0;
 }
 
 /*
@@ -391,9 +398,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 
 static void nested_ept_new_eptp(struct kvm_vcpu *vcpu)
 {
-	kvm_init_shadow_ept_mmu(vcpu,
-				to_vmx(vcpu)->nested.msrs.ept_caps &
-				VMX_EPT_EXECUTE_ONLY_BIT,
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT;
+	int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps);
+
+	kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level,
 				nested_ept_ad_enabled(vcpu),
 				nested_ept_get_eptp(vcpu));
 }
@@ -591,6 +600,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	int msr;
 	unsigned long *msr_bitmap_l1;
 	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
+	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
 	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
@@ -598,6 +608,19 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	    !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
 		return false;
 
+	/*
+	 * MSR bitmap update can be skipped when:
+	 * - MSR bitmap for L1 hasn't changed.
+	 * - Nested hypervisor (L1) is attempting to launch the same L2 as
+	 *   before.
+	 * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature
+	 *   and tells KVM (L0) there were no changes in MSR bitmap for L2.
+	 */
+	if (!vmx->nested.force_msr_bitmap_recalc && evmcs &&
+	    evmcs->hv_enlightenments_control.msr_bitmap &&
+	    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
+		return true;
+
 	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
 		return false;
 
@@ -664,6 +687,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 
 	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
 
+	vmx->nested.force_msr_bitmap_recalc = false;
+
 	return true;
 }
 
@@ -1095,7 +1120,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 	 * must not be dereferenced.
 	 */
 	if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) &&
-	    CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
+	    CC(!load_pdptrs(vcpu, cr3))) {
 		*entry_failure_code = ENTRY_FAIL_PDPTE;
 		return -EINVAL;
 	}
@@ -1104,7 +1129,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 		kvm_mmu_new_pgd(vcpu, cr3);
 
 	vcpu->arch.cr3 = cr3;
-	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
 
 	/* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */
 	kvm_init_mmu(vcpu);
@@ -2021,10 +2046,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	 * Clean fields data can't be used on VMLAUNCH and when we switch
 	 * between different L2 guests as KVM keeps a single VMCS12 per L1.
 	 */
-	if (from_launch || evmcs_gpa_changed)
+	if (from_launch || evmcs_gpa_changed) {
 		vmx->nested.hv_evmcs->hv_clean_fields &=
 			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
+		vmx->nested.force_msr_bitmap_recalc = true;
+	}
+
 	return EVMPTRLD_SUCCEEDED;
 }
 
@@ -3027,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr3, cr4;
+	unsigned long cr4;
 	bool vm_fail;
 
 	if (!nested_early_check)
@@ -3050,12 +3078,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	 */
 	vmcs_writel(GUEST_RFLAGS, 0);
 
-	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		vmx->loaded_vmcs->host_state.cr3 = cr3;
-	}
-
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
@@ -3145,7 +3167,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		 * the guest CR3 might be restored prior to setting the nested
 		 * state which can lead to a load of wrong PDPTRs.
 		 */
-		if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3)))
+		if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
 			return false;
 	}
 
@@ -3504,10 +3526,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (evmptrld_status == EVMPTRLD_ERROR) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
-	} else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) {
-		return nested_vmx_failInvalid(vcpu);
 	}
 
+	kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+
+	if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
+		return nested_vmx_failInvalid(vcpu);
+
 	if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) &&
 	       vmx->nested.current_vmptr == INVALID_GPA))
 		return nested_vmx_failInvalid(vcpu);
@@ -3603,7 +3628,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		    !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) &&
 		      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
 			vmx->nested.nested_run_pending = 0;
-			return kvm_vcpu_halt(vcpu);
+			return kvm_emulate_halt_noskip(vcpu);
 		}
 		break;
 	case GUEST_ACTIVITY_WAIT_SIPI:
@@ -5258,6 +5283,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 	}
 	vmx->nested.dirty_vmcs12 = true;
+	vmx->nested.force_msr_bitmap_recalc = true;
 }
 
 /* Emulate the VMPTRLD instruction */
@@ -6393,6 +6419,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		goto error_guest_mode;
 
 	vmx->nested.dirty_vmcs12 = true;
+	vmx->nested.force_msr_bitmap_recalc = true;
 	ret = nested_vmx_enter_non_root_mode(vcpu, false);
 	if (ret)
 		goto error_guest_mode;