| Message ID | 20240227232100.478238-22-pbonzini@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | TDX/SNP part 1 of n, for 6.9 | expand |
On 2/28/2024 7:21 AM, Paolo Bonzini wrote: > From: Michael Roth<michael.roth@amd.com> > > In the case of SEV-SNP, whether or not a 2MB page can be mapped via a > 2MB mapping in the guest's nested page table depends on whether or not > any subpages within the range have already been initialized as private > in the RMP table. The existing mixed-attribute tracking in KVM is > insufficient here, for instance: > > - gmem allocates 2MB page > - guest issues PVALIDATE on 2MB page > - guest later converts a subpage to shared > - SNP host code issues PSMASH to split 2MB RMP mapping to 4K > - KVM MMU splits NPT mapping to 4K Is here a sentence missing that "guest converts the shared subpage back to private"? Otherwise, it conflicts with the following statement "there are no mixed attributes". > At this point there are no mixed attributes, and KVM would normally > allow for 2MB NPT mappings again, but this is actually not allowed > because the RMP table mappings are 4K and cannot be promoted on the > hypervisor side, so the NPT mappings must still be limited to 4K to > match this. > > Add a hook to determine the max NPT mapping size in situations like > this. > > Signed-off-by: Michael Roth<michael.roth@amd.com> > Message-Id:<20231230172351.574091-31-michael.roth@amd.com> > Signed-off-by: Paolo Bonzini<pbonzini@redhat.com> > --- > arch/x86/include/asm/kvm-x86-ops.h | 1 + > arch/x86/include/asm/kvm_host.h | 1 + > arch/x86/kvm/mmu/mmu.c | 7 +++++++ > 3 files changed, 9 insertions(+) > > diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h > index 42474acb7375..436e3c157fae 100644 > --- a/arch/x86/include/asm/kvm-x86-ops.h > +++ b/arch/x86/include/asm/kvm-x86-ops.h > @@ -140,6 +140,7 @@ KVM_X86_OP(vcpu_deliver_sipi_vector) > KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); > KVM_X86_OP_OPTIONAL(get_untagged_addr) > KVM_X86_OP_OPTIONAL_RET0(gmem_prepare) > +KVM_X86_OP_OPTIONAL_RET0(gmem_validate_fault) > KVM_X86_OP_OPTIONAL(gmem_invalidate) > > #undef KVM_X86_OP > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index e523b204697d..259e6bb1e447 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -1806,6 +1806,7 @@ struct kvm_x86_ops { > gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); > int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); > void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); > + int (*gmem_validate_fault)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, u8 *max_level); > }; > > struct kvm_x86_nested_ops { > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c > index 6b4cb71668df..bcf12ac489f9 100644 > --- a/arch/x86/kvm/mmu/mmu.c > +++ b/arch/x86/kvm/mmu/mmu.c > @@ -4339,6 +4339,13 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, > fault->max_level); > fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); > > + r = static_call(kvm_x86_gmem_validate_fault)(vcpu->kvm, fault->pfn, > + fault->gfn, &fault->max_level); > + if (r) { > + kvm_release_pfn_clean(fault->pfn); > + return r; > + } > + > return RET_PF_CONTINUE; > } >
On 2/28/2024 7:21 AM, Paolo Bonzini wrote: > From: Michael Roth <michael.roth@amd.com> > > In the case of SEV-SNP, whether or not a 2MB page can be mapped via a > 2MB mapping in the guest's nested page table depends on whether or not > any subpages within the range have already been initialized as private > in the RMP table. The existing mixed-attribute tracking in KVM is > insufficient here, for instance: > > - gmem allocates 2MB page > - guest issues PVALIDATE on 2MB page > - guest later converts a subpage to shared > - SNP host code issues PSMASH to split 2MB RMP mapping to 4K > - KVM MMU splits NPT mapping to 4K > > At this point there are no mixed attributes, and KVM would normally > allow for 2MB NPT mappings again, but this is actually not allowed > because the RMP table mappings are 4K and cannot be promoted on the > hypervisor side, so the NPT mappings must still be limited to 4K to > match this. > > Add a hook to determine the max NPT mapping size in situations like > this. > > Signed-off-by: Michael Roth <michael.roth@amd.com> > Message-Id: <20231230172351.574091-31-michael.roth@amd.com> > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > arch/x86/include/asm/kvm-x86-ops.h | 1 + > arch/x86/include/asm/kvm_host.h | 1 + > arch/x86/kvm/mmu/mmu.c | 7 +++++++ > 3 files changed, 9 insertions(+) > > diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h > index 42474acb7375..436e3c157fae 100644 > --- a/arch/x86/include/asm/kvm-x86-ops.h > +++ b/arch/x86/include/asm/kvm-x86-ops.h > @@ -140,6 +140,7 @@ KVM_X86_OP(vcpu_deliver_sipi_vector) > KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); > KVM_X86_OP_OPTIONAL(get_untagged_addr) > KVM_X86_OP_OPTIONAL_RET0(gmem_prepare) > +KVM_X86_OP_OPTIONAL_RET0(gmem_validate_fault) > KVM_X86_OP_OPTIONAL(gmem_invalidate) > > #undef KVM_X86_OP > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index e523b204697d..259e6bb1e447 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -1806,6 +1806,7 @@ struct kvm_x86_ops { > gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); > int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); > void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); > + int (*gmem_validate_fault)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, u8 *max_level); Since it's named "gmem_validate_fault", can we just passed in the "fault" as an argument to avoid passing in pfn, gfn, max_level individually? I noticed in Isaku's TDX patch set, fault->private would also need to be passed in. > }; > > struct kvm_x86_nested_ops { > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c > index 6b4cb71668df..bcf12ac489f9 100644 > --- a/arch/x86/kvm/mmu/mmu.c > +++ b/arch/x86/kvm/mmu/mmu.c > @@ -4339,6 +4339,13 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, > fault->max_level); > fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); > > + r = static_call(kvm_x86_gmem_validate_fault)(vcpu->kvm, fault->pfn, > + fault->gfn, &fault->max_level); > + if (r) { > + kvm_release_pfn_clean(fault->pfn); > + return r; > + } > + > return RET_PF_CONTINUE; > } >
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 42474acb7375..436e3c157fae 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -140,6 +140,7 @@ KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); KVM_X86_OP_OPTIONAL(get_untagged_addr) KVM_X86_OP_OPTIONAL_RET0(gmem_prepare) +KVM_X86_OP_OPTIONAL_RET0(gmem_validate_fault) KVM_X86_OP_OPTIONAL(gmem_invalidate) #undef KVM_X86_OP diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e523b204697d..259e6bb1e447 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1806,6 +1806,7 @@ struct kvm_x86_ops { gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); + int (*gmem_validate_fault)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, u8 *max_level); }; struct kvm_x86_nested_ops { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6b4cb71668df..bcf12ac489f9 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4339,6 +4339,13 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, fault->max_level); fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + r = static_call(kvm_x86_gmem_validate_fault)(vcpu->kvm, fault->pfn, + fault->gfn, &fault->max_level); + if (r) { + kvm_release_pfn_clean(fault->pfn); + return r; + } + return RET_PF_CONTINUE; }