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

Pull kvm fixes from Paolo Bonzini:
 "It's a bit larger than I (and probably you) would like by the time we
  get to -rc6, but perhaps not entirely unexpected since the changes in
  the last merge window were larger than usual.

  x86:
   - Fixes for missing TLB flushes with TDP MMU

   - Fixes for race conditions in nested SVM

   - Fixes for lockdep splat with Xen emulation

   - Fix for kvmclock underflow

   - Fix srcdir != builddir builds

   - Other small cleanups

  ARM:
   - Fix GICv3 MMIO compatibility probing

   - Prevent guests from using the ARMv8.4 self-hosted tracing
     extension"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  selftests: kvm: Check that TSC page value is small after KVM_SET_CLOCK(0)
  KVM: x86: Prevent 'hv_clock->system_time' from going negative in kvm_guest_time_update()
  KVM: x86: disable interrupts while pvclock_gtod_sync_lock is taken
  KVM: x86: reduce pvclock_gtod_sync_lock critical sections
  KVM: SVM: ensure that EFER.SVME is set when running nested guest or on nested vmexit
  KVM: SVM: load control fields from VMCB12 before checking them
  KVM: x86/mmu: Don't allow TDP MMU to yield when recovering NX pages
  KVM: x86/mmu: Ensure TLBs are flushed for TDP MMU during NX zapping
  KVM: x86/mmu: Ensure TLBs are flushed when yielding during GFN range zap
  KVM: make: Fix out-of-source module builds
  selftests: kvm: make hardware_disable_test less verbose
  KVM: x86/vPMU: Forbid writing to MSR_F15H_PERF MSRs when guest doesn't have X86_FEATURE_PERFCTR_CORE
  KVM: x86: remove unused declaration of kvm_write_tsc()
  KVM: clean up the unused argument
  tools/kvm_stat: Add restart delay
  KVM: arm64: Fix CPU interface MMIO compatibility detection
  KVM: arm64: Disable guest access to trace filter controls
  KVM: arm64: Hide system instruction access to Trace registers

2 files changed, 31 insertions, 5 deletions

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 35891d9a1099..fb204eaa8bb3 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 	return true;
 }
 
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
+static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	bool vmcb12_lma;
 
+	/*
+	 * FIXME: these should be done after copying the fields,
+	 * to avoid TOC/TOU races.  For these save area checks
+	 * the possible damage is limited since kvm_set_cr0 and
+	 * kvm_set_cr4 handle failure; EFER_SVME is an exception
+	 * so it is force-set later in nested_prepare_vmcb_save.
+	 */
 	if ((vmcb12->save.efer & EFER_SVME) == 0)
 		return false;
 
@@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
 		return false;
 
-	return nested_vmcb_check_controls(&vmcb12->control);
+	return true;
 }
 
 static void load_nested_vmcb_control(struct vcpu_svm *svm,
@@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
 	svm->vmcb->save.idtr = vmcb12->save.idtr;
 	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
-	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+
+	/*
+	 * Force-set EFER_SVME even though it is checked earlier on the
+	 * VMCB12, because the guest can flip the bit between the check
+	 * and now.  Clearing EFER_SVME would call svm_free_nested.
+	 */
+	svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+
 	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
 	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
@@ -468,7 +482,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
 
 
 	svm->nested.vmcb12_gpa = vmcb12_gpa;
-	load_nested_vmcb_control(svm, &vmcb12->control);
 	nested_prepare_vmcb_control(svm);
 	nested_prepare_vmcb_save(svm, vmcb12);
 
@@ -515,7 +528,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 	if (WARN_ON_ONCE(!svm->nested.initialized))
 		return -EINVAL;
 
-	if (!nested_vmcb_checks(svm, vmcb12)) {
+	load_nested_vmcb_control(svm, &vmcb12->control);
+
+	if (!nested_vmcb_check_save(svm, vmcb12) ||
+	    !nested_vmcb_check_controls(&svm->nested.ctl)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_code_hi = 0;
 		vmcb12->control.exit_info_1  = 0;
@@ -1209,6 +1225,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 */
 	if (!(save->cr0 & X86_CR0_PG))
 		goto out_free;
+	if (!(save->efer & EFER_SVME))
+		goto out_free;
 
 	/*
 	 * All checks done, we can enter guest mode.  L1 control fields
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 035da07500e8..fdf587f19c5f 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr)
 static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 					     enum pmu_type type)
 {
+	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+
 	switch (msr) {
 	case MSR_F15H_PERF_CTL0:
 	case MSR_F15H_PERF_CTL1:
@@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	case MSR_F15H_PERF_CTL3:
 	case MSR_F15H_PERF_CTL4:
 	case MSR_F15H_PERF_CTL5:
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		fallthrough;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 		if (type != PMU_TYPE_EVNTSEL)
 			return NULL;
@@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	case MSR_F15H_PERF_CTR3:
 	case MSR_F15H_PERF_CTR4:
 	case MSR_F15H_PERF_CTR5:
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		fallthrough;
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 		if (type != PMU_TYPE_COUNTER)
 			return NULL;