From: Sean Christopherson Date: Thu, 4 Feb 2021 00:01:12 +0000 (-0800) Subject: KVM: x86: SEV: Treat C-bit as legal GPA bit regardless of vCPU mode X-Git-Tag: accepted/tizen/unified/20230118.172025~7642^2~105 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=ca29e14506bd66d50733c1f3e4448aba54e70cc7;p=platform%2Fkernel%2Flinux-rpi.git KVM: x86: SEV: Treat C-bit as legal GPA bit regardless of vCPU mode Rename cr3_lm_rsvd_bits to reserved_gpa_bits, and use it for all GPA legality checks. AMD's APM states: If the C-bit is an address bit, this bit is masked from the guest physical address when it is translated through the nested page tables. Thus, any access that can conceivably be run through NPT should ignore the C-bit when checking for validity. For features that KVM emulates in software, e.g. MTRRs, there is no clear direction in the APM for how the C-bit should be handled. For such cases, follow the SME behavior inasmuch as possible, since SEV is is essentially a VM-specific variant of SME. For SME, the APM states: In this case the upper physical address bits are treated as reserved when the feature is enabled except where otherwise indicated. Collecting the various relavant SME snippets in the APM and cross- referencing the omissions with Linux kernel code, this leaves MTTRs and APIC_BASE as the only flows that KVM emulates that should _not_ ignore the C-bit. Note, this means the reserved bit checks in the page tables are technically broken. This will be remedied in a future patch. Although the page table checks are technically broken, in practice, it's all but guaranteed to be irrelevant. NPT is required for SEV, i.e. shadowing page tables isn't needed in the common case. Theoretically, the checks could be in play for nested NPT, but it's extremely unlikely that anyone is running nested VMs on SEV, as doing so would require L1 to expose sensitive data to L0, e.g. the entire VMCB. And if anyone is running nested VMs, L0 can't read the guest's encrypted memory, i.e. L1 would need to put its NPT in shared memory, in which case the C-bit will never be set. Or, L1 could use shadow paging, but again, if L0 needs to read page tables, e.g. to load PDPTRs, the memory can't be encrypted if L1 has any expectation of L0 doing the right thing. Cc: Tom Lendacky Cc: Brijesh Singh Signed-off-by: Sean Christopherson Message-Id: <20210204000117.3303214-8-seanjc@google.com> Signed-off-by: Paolo Bonzini --- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b37afd8..717940e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -660,7 +660,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - unsigned long cr3_lm_rsvd_bits; + u64 reserved_gpa_bits; int maxphyaddr; int max_tdp_level; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ff16734..8d75576e 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -179,7 +179,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); - vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + vcpu->arch.reserved_gpa_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); /* Invoke the vendor callback only after the above state is updated. */ static_call(kvm_x86_vcpu_after_set_cpuid)(vcpu); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index a9d55ab..f673f45 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -38,7 +38,7 @@ static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - return !(gpa >> cpuid_maxphyaddr(vcpu)); + return !(gpa & vcpu->arch.reserved_gpa_bits); } static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 1055b7d..cc91738 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -248,7 +248,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) if (vmcb12_lma) { if (!(vmcb12->save.cr4 & X86_CR4_PAE) || !(vmcb12->save.cr0 & X86_CR0_PE) || - (vmcb12->save.cr3 & vcpu->arch.cr3_lm_rsvd_bits)) + kvm_vcpu_is_illegal_gpa(vcpu, vmcb12->save.cr3)) return false; } if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index fdea099..4141cae 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4058,7 +4058,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (sev_guest(vcpu->kvm)) { best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); if (best) - vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f)); + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); } if (!kvm_vcpu_apicv_active(vcpu)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 10414a7..077e8b9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1074,8 +1074,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) return 0; } - if (is_long_mode(vcpu) && - (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) + if (is_long_mode(vcpu) && kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -9701,7 +9700,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits) + if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) return false; } else { /* @@ -10080,7 +10079,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) fx_init(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + vcpu->arch.reserved_gpa_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;