Received-SPF: pass (google.com: domain of linux-kernel+bounces-51989-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Message-ID: <9d024bfc-4b1d-4da5-81ba-36e60cf5e284@linux.intel.com>
Date: Mon, 5 Feb 2024 10:23:34 +0800
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v18 057/121] KVM: TDX: Add load_mmu_pgd method for TDX
To: isaku.yamahata@intel.com
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
 isaku.yamahata@gmail.com, Paolo Bonzini <pbonzini@redhat.com>,
 erdemaktas@google.com, Sean Christopherson <seanjc@google.com>,
 Sagi Shahar <sagis@google.com>, Kai Huang <kai.huang@intel.com>,
 chen.bo@intel.com, hang.yuan@intel.com, tina.zhang@intel.com,
 Sean Christopherson <sean.j.christopherson@intel.com>
References: <cover.1705965634.git.isaku.yamahata@intel.com>
 <bd5256f2f58c36c6e8712e8137525815eede3bc8.1705965635.git.isaku.yamahata@intel.com>
From: Binbin Wu <binbin.wu@linux.intel.com>
In-Reply-To: <bd5256f2f58c36c6e8712e8137525815eede3bc8.1705965635.git.isaku.yamahata@intel.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit


On 1/23/2024 7:53 AM, isaku.yamahata@intel.com wrote:
> From: Sean Christopherson <sean.j.christopherson@intel.com>
>
> For virtual IO, the guest TD shares guest pages with VMM without
> encryption.  Shared EPT is used to map guest pages in unprotected way.
>
> Add the VMCS field encoding for the shared EPTP, which will be used by
> TDX to have separate EPT walks for private GPAs (existing EPTP) versus
> shared GPAs (new shared EPTP).
>
> Set shared EPT pointer value for the TDX guest to initialize TDX MMU.
>
> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   arch/x86/include/asm/vmx.h |  1 +
>   arch/x86/kvm/vmx/main.c    | 13 ++++++++++++-
>   arch/x86/kvm/vmx/tdx.c     |  5 +++++
>   arch/x86/kvm/vmx/x86_ops.h |  4 ++++
>   4 files changed, 22 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
> index f703bae0c4ac..9deb663a42e3 100644
> --- a/arch/x86/include/asm/vmx.h
> +++ b/arch/x86/include/asm/vmx.h
> @@ -236,6 +236,7 @@ enum vmcs_field {
>   	TSC_MULTIPLIER_HIGH             = 0x00002033,
>   	TERTIARY_VM_EXEC_CONTROL	= 0x00002034,
>   	TERTIARY_VM_EXEC_CONTROL_HIGH	= 0x00002035,
> +	SHARED_EPT_POINTER		= 0x0000203C,
>   	PID_POINTER_TABLE		= 0x00002042,
>   	PID_POINTER_TABLE_HIGH		= 0x00002043,
>   	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
> diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> index 8059b44ed159..f55ac09edc60 100644
> --- a/arch/x86/kvm/vmx/main.c
> +++ b/arch/x86/kvm/vmx/main.c
> @@ -147,6 +147,17 @@ static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
>   	vmx_vcpu_reset(vcpu, init_event);
>   }
>   
> +static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
> +			int pgd_level)
> +{
> +	if (is_td_vcpu(vcpu)) {
> +		tdx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
> +		return;
> +	}
> +
> +	vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
> +}
> +
>   static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
>   {
>   	if (!is_td(kvm))
> @@ -279,7 +290,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
>   	.write_tsc_offset = vmx_write_tsc_offset,
>   	.write_tsc_multiplier = vmx_write_tsc_multiplier,
>   
> -	.load_mmu_pgd = vmx_load_mmu_pgd,
> +	.load_mmu_pgd = vt_load_mmu_pgd,
>   
>   	.check_intercept = vmx_check_intercept,
>   	.handle_exit_irqoff = vmx_handle_exit_irqoff,
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index 59d170709f82..25510b6740a3 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -501,6 +501,11 @@ void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
>   	 */
>   }
>   
> +void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
> +{
> +	td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa & PAGE_MASK);

If we have concern about the alignment of root_hpa, shouldn't we do some
check instead of masking the address quietly?

> +}
> +
>   static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
>   {
>   	struct kvm_tdx_capabilities __user *user_caps;
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index 5f8ee1c93cd1..a9e5caf880dd 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -152,6 +152,8 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu);
>   void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
>   
>   int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
> +
> +void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
>   #else
>   static inline int tdx_hardware_setup(struct kvm_x86_ops *x86_ops) { return -EOPNOTSUPP; }
>   static inline void tdx_hardware_unsetup(void) {}
> @@ -173,6 +175,8 @@ static inline void tdx_vcpu_free(struct kvm_vcpu *vcpu) {}
>   static inline void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) {}
>   
>   static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
> +
> +static inline void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level) {}
>   #endif
>   
>   #endif /* __KVM_X86_VMX_X86_OPS_H */