On 3/13/2023 1:55 AM, isaku.yamahata@xxxxxxxxx wrote:
> From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
>
> As the first step to create TDX guest, create/destroy VM struct. Assign
> TDX private Host Key ID (HKID) to the TDX guest for memory encryption and
> allocate extra pages for the TDX guest. On destruction, free allocated
> pages, and HKID.
>
> Before tearing down private page tables, TDX requires some resources of the
> guest TD to be destroyed (i.e. HKID must have been reclaimed, etc). Add
> flush_shadow_all_private callback before tearing down private page tables
> for it.
>
> Add vm_free() of kvm_x86_ops hook at the end of kvm_arch_destroy_vm()
> because some per-VM TDX resources, e.g. TDR, need to be freed after other
> TDX resources, e.g. HKID, were freed.
>
> Co-developed-by: Kai Huang <kai.huang@xxxxxxxxx>
> Signed-off-by: Kai Huang <kai.huang@xxxxxxxxx>
> Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
>
> ---
> Changes v11 -> v12:
> - use cpu_feature_enabled().
>
> Changes v10 -> v11:
> - Fix doule free in tdx_vm_free() by setting NULL.
> - replace struct tdx_td_page tdr and tdcs from struct kvm_tdx with
> unsigned long
> ---
> arch/x86/include/asm/kvm-x86-ops.h | 2 +
> arch/x86/include/asm/kvm_host.h | 2 +
> arch/x86/kvm/vmx/main.c | 35 ++-
> arch/x86/kvm/vmx/tdx.c | 442 ++++++++++++++++++++++++++++-
> arch/x86/kvm/vmx/tdx.h | 6 +-
> arch/x86/kvm/vmx/x86_ops.h | 9 +
> arch/x86/kvm/x86.c | 8 +
> 7 files changed, 498 insertions(+), 6 deletions(-)
...
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index 8118647aa8ca..8f87eeeab97c 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -139,19 +139,28 @@ void vmx_setup_mce(struct kvm_vcpu *vcpu);
>
> #ifdef CONFIG_INTEL_TDX_HOST
> int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops);
> +void tdx_hardware_unsetup(void);
> int tdx_hardware_enable(void);
> bool tdx_is_vm_type_supported(unsigned long type);
> int tdx_dev_ioctl(void __user *argp);
>
> int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap);
> +int tdx_vm_init(struct kvm *kvm);
> +void tdx_mmu_release_hkid(struct kvm *kvm);
> +void tdx_vm_free(struct kvm *kvm);
> int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
> #else
> static inline int tdx_hardware_setup(struct kvm_x86_ops *x86_ops) { return -ENOSYS; }
> +static inline void tdx_hardware_unsetup(void) {}
> static inline int tdx_hardware_enable(void) { return -EOPNOTSUPP; }
> static inline bool tdx_is_vm_type_supported(unsigned long type) { return false; }
> static inline int tdx_dev_ioctl(void __user *argp) { return -EOPNOTSUPP; };
>
> static inline int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { return -EINVAL; };
> +static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; }
> +static inline void tdx_mmu_release_hkid(struct kvm *kvm) {}
> +static inline void tdx_flush_shadow_all_private(struct kvm *kvm) {}
typo? This function tdx_flush_shadow_all_private is not used anywhere.
> +static inline void tdx_vm_free(struct kvm *kvm) {}
> static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
> #endif
>
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 7b02dd40ef21..89fd8074c20c 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -12398,6 +12398,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
> kvm_page_track_cleanup(kvm);
> kvm_xen_destroy_vm(kvm);
> kvm_hv_destroy_vm(kvm);
> + static_call_cond(kvm_x86_vm_free)(kvm);
> }
>
> static void memslot_rmap_free(struct kvm_memory_slot *slot)
> @@ -12710,6 +12711,13 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
>
> void kvm_arch_flush_shadow_all(struct kvm *kvm)
> {
> + /*
> + * kvm_mmu_zap_all() zaps both private and shared page tables. Before
> + * tearing down private page tables, TDX requires some TD resources to
> + * be destroyed (i.e. keyID must have been reclaimed, etc). Invoke
> + * kvm_x86_flush_shadow_all_private() for this.
> + */
> + static_call_cond(kvm_x86_flush_shadow_all_private)(kvm);
> kvm_mmu_zap_all(kvm);
> }
>
