Commit Message
Isaku Yamahata
Feb. 26, 2024, 8:26 a.m. UTC
From: Isaku Yamahata <isaku.yamahata@intel.com> On EPT violation, call a common function, __vmx_handle_ept_violation() to trigger x86 MMU code. On EPT misconfiguration, exit to ring 3 with KVM_EXIT_UNKNOWN. because EPT misconfiguration can't happen as MMIO is trigged by TDG.VP.VMCALL. No point to set a misconfiguration value for the fast path. Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com> --- v14 -> v15: - use PFERR_GUEST_ENC_MASK to tell the fault is private Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com> --- arch/x86/kvm/vmx/common.h | 3 +++ arch/x86/kvm/vmx/tdx.c | 49 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+)
Comments
On 2/26/2024 4:26 PM, isaku.yamahata@intel.com wrote: > From: Isaku Yamahata <isaku.yamahata@intel.com> > > On EPT violation, call a common function, __vmx_handle_ept_violation() to > trigger x86 MMU code. On EPT misconfiguration, exit to ring 3 with > KVM_EXIT_UNKNOWN. because EPT misconfiguration can't happen as MMIO is > trigged by TDG.VP.VMCALL. No point to set a misconfiguration value for the s/trigged/triggered > fast path. > > Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com> > > --- > v14 -> v15: > - use PFERR_GUEST_ENC_MASK to tell the fault is private > > Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com> duplicated SOB > --- > arch/x86/kvm/vmx/common.h | 3 +++ > arch/x86/kvm/vmx/tdx.c | 49 +++++++++++++++++++++++++++++++++++++++ > 2 files changed, 52 insertions(+) > > diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h > index 632af7a76d0a..027aa4175d2c 100644 > --- a/arch/x86/kvm/vmx/common.h > +++ b/arch/x86/kvm/vmx/common.h > @@ -87,6 +87,9 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa, > error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? > PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; > > + if (kvm_is_private_gpa(vcpu->kvm, gpa)) > + error_code |= PFERR_GUEST_ENC_MASK; > + > return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); > } > > diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c > index 2f68e6f2b53a..0db80fa020d2 100644 > --- a/arch/x86/kvm/vmx/tdx.c > +++ b/arch/x86/kvm/vmx/tdx.c > @@ -1285,6 +1285,51 @@ void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, > __vmx_deliver_posted_interrupt(vcpu, &tdx->pi_desc, vector); > } > > +static int tdx_handle_ept_violation(struct kvm_vcpu *vcpu) > +{ > + unsigned long exit_qual; > + > + if (kvm_is_private_gpa(vcpu->kvm, tdexit_gpa(vcpu))) { > + /* > + * Always treat SEPT violations as write faults. Ignore the > + * EXIT_QUALIFICATION reported by TDX-SEAM for SEPT violations. > + * TD private pages are always RWX in the SEPT tables, > + * i.e. they're always mapped writable. Just as importantly, > + * treating SEPT violations as write faults is necessary to > + * avoid COW allocations, which will cause TDAUGPAGE failures > + * due to aliasing a single HPA to multiple GPAs. > + */ > +#define TDX_SEPT_VIOLATION_EXIT_QUAL EPT_VIOLATION_ACC_WRITE > + exit_qual = TDX_SEPT_VIOLATION_EXIT_QUAL; > + } else { > + exit_qual = tdexit_exit_qual(vcpu); > + if (exit_qual & EPT_VIOLATION_ACC_INSTR) { > + pr_warn("kvm: TDX instr fetch to shared GPA = 0x%lx @ RIP = 0x%lx\n", > + tdexit_gpa(vcpu), kvm_rip_read(vcpu)); > + vcpu->run->exit_reason = KVM_EXIT_EXCEPTION; > + vcpu->run->ex.exception = PF_VECTOR; > + vcpu->run->ex.error_code = exit_qual; > + return 0; > + } > + } > + > + trace_kvm_page_fault(vcpu, tdexit_gpa(vcpu), exit_qual); > + return __vmx_handle_ept_violation(vcpu, tdexit_gpa(vcpu), exit_qual); > +} > + > +static int tdx_handle_ept_misconfig(struct kvm_vcpu *vcpu) > +{ > + WARN_ON_ONCE(1); > + > + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; > + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; > + vcpu->run->internal.ndata = 2; > + vcpu->run->internal.data[0] = EXIT_REASON_EPT_MISCONFIG; > + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; > + > + return 0; > +} > + > int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) > { > union tdx_exit_reason exit_reason = to_tdx(vcpu)->exit_reason; > @@ -1345,6 +1390,10 @@ int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) > WARN_ON_ONCE(fastpath != EXIT_FASTPATH_NONE); > > switch (exit_reason.basic) { > + case EXIT_REASON_EPT_VIOLATION: > + return tdx_handle_ept_violation(vcpu); > + case EXIT_REASON_EPT_MISCONFIG: > + return tdx_handle_ept_misconfig(vcpu); > case EXIT_REASON_OTHER_SMI: > /* > * If reach here, it's not a Machine Check System Management
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h index 632af7a76d0a..027aa4175d2c 100644 --- a/arch/x86/kvm/vmx/common.h +++ b/arch/x86/kvm/vmx/common.h @@ -87,6 +87,9 @@ static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa, error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; + if (kvm_is_private_gpa(vcpu->kvm, gpa)) + error_code |= PFERR_GUEST_ENC_MASK; + return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 2f68e6f2b53a..0db80fa020d2 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -1285,6 +1285,51 @@ void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, __vmx_deliver_posted_interrupt(vcpu, &tdx->pi_desc, vector); } +static int tdx_handle_ept_violation(struct kvm_vcpu *vcpu) +{ + unsigned long exit_qual; + + if (kvm_is_private_gpa(vcpu->kvm, tdexit_gpa(vcpu))) { + /* + * Always treat SEPT violations as write faults. Ignore the + * EXIT_QUALIFICATION reported by TDX-SEAM for SEPT violations. + * TD private pages are always RWX in the SEPT tables, + * i.e. they're always mapped writable. Just as importantly, + * treating SEPT violations as write faults is necessary to + * avoid COW allocations, which will cause TDAUGPAGE failures + * due to aliasing a single HPA to multiple GPAs. + */ +#define TDX_SEPT_VIOLATION_EXIT_QUAL EPT_VIOLATION_ACC_WRITE + exit_qual = TDX_SEPT_VIOLATION_EXIT_QUAL; + } else { + exit_qual = tdexit_exit_qual(vcpu); + if (exit_qual & EPT_VIOLATION_ACC_INSTR) { + pr_warn("kvm: TDX instr fetch to shared GPA = 0x%lx @ RIP = 0x%lx\n", + tdexit_gpa(vcpu), kvm_rip_read(vcpu)); + vcpu->run->exit_reason = KVM_EXIT_EXCEPTION; + vcpu->run->ex.exception = PF_VECTOR; + vcpu->run->ex.error_code = exit_qual; + return 0; + } + } + + trace_kvm_page_fault(vcpu, tdexit_gpa(vcpu), exit_qual); + return __vmx_handle_ept_violation(vcpu, tdexit_gpa(vcpu), exit_qual); +} + +static int tdx_handle_ept_misconfig(struct kvm_vcpu *vcpu) +{ + WARN_ON_ONCE(1); + + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = EXIT_REASON_EPT_MISCONFIG; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + + return 0; +} + int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) { union tdx_exit_reason exit_reason = to_tdx(vcpu)->exit_reason; @@ -1345,6 +1390,10 @@ int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath) WARN_ON_ONCE(fastpath != EXIT_FASTPATH_NONE); switch (exit_reason.basic) { + case EXIT_REASON_EPT_VIOLATION: + return tdx_handle_ept_violation(vcpu); + case EXIT_REASON_EPT_MISCONFIG: + return tdx_handle_ept_misconfig(vcpu); case EXIT_REASON_OTHER_SMI: /* * If reach here, it's not a Machine Check System Management