Re: [RFC PATCH v5 065/104] KVM: TDX: vcpu_run: save/restore host state(host kernel gs)

[Paolo Bonzini]

On 3/4/22 20:49, isaku.yamahata@xxxxxxxxx wrote:
> From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
>
> On entering/exiting TDX vcpu, Preserved or clobbered CPU state is different
> from VMX case.  Add TDX hooks to save/restore host/guest CPU state.
> Save/restore kernel GS base MSR.
>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> ---
>   arch/x86/kvm/vmx/main.c    | 28 +++++++++++++++++++++++++--
>   arch/x86/kvm/vmx/tdx.c     | 39 ++++++++++++++++++++++++++++++++++++++
>   arch/x86/kvm/vmx/tdx.h     |  4 ++++
>   arch/x86/kvm/vmx/x86_ops.h |  4 ++++
>   4 files changed, 73 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> index 2e5a7a72d560..f9d43f2de145 100644
> --- a/arch/x86/kvm/vmx/main.c
> +++ b/arch/x86/kvm/vmx/main.c
> @@ -89,6 +89,30 @@ static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
>   	return vmx_vcpu_reset(vcpu, init_event);
>   }
>   
> +static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
> +{
> +	/*
> +	 * All host state is saved/restored across SEAMCALL/SEAMRET, and the
> +	 * guest state of a TD is obviously off limits.  Deferring MSRs and DRs
> +	 * is pointless because the TDX module needs to load *something* so as
> +	 * not to expose guest state.
> +	 */
> +	if (is_td_vcpu(vcpu)) {
> +		tdx_prepare_switch_to_guest(vcpu);
> +		return;
> +	}
> +
> +	vmx_prepare_switch_to_guest(vcpu);
> +}
> +
> +static void vt_vcpu_put(struct kvm_vcpu *vcpu)
> +{
> +	if (is_td_vcpu(vcpu))
> +		return tdx_vcpu_put(vcpu);
> +
> +	return vmx_vcpu_put(vcpu);
> +}
> +
>   static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu)
>   {
>   	if (is_td_vcpu(vcpu))
> @@ -174,9 +198,9 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
>   	.vcpu_free = vt_vcpu_free,
>   	.vcpu_reset = vt_vcpu_reset,
>   
> -	.prepare_guest_switch = vmx_prepare_switch_to_guest,
> +	.prepare_guest_switch = vt_prepare_switch_to_guest,
>   	.vcpu_load = vmx_vcpu_load,
> -	.vcpu_put = vmx_vcpu_put,
> +	.vcpu_put = vt_vcpu_put,
>   
>   	.update_exception_bitmap = vmx_update_exception_bitmap,
>   	.get_msr_feature = vmx_get_msr_feature,
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index ebe4f9bf19e7..7a288aae03ba 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -1,5 +1,6 @@
>   // SPDX-License-Identifier: GPL-2.0
>   #include <linux/cpu.h>
> +#include <linux/mmu_context.h>
>   
>   #include <asm/tdx.h>
>   
> @@ -407,6 +408,9 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
>   	vcpu->arch.guest_state_protected =
>   		!(to_kvm_tdx(vcpu->kvm)->attributes & TDX_TD_ATTRIBUTE_DEBUG);
>   
> +	tdx->host_state_need_save = true;
> +	tdx->host_state_need_restore = false;
> +
>   	return 0;
>   
>   free_tdvpx:
> @@ -420,6 +424,39 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu)
>   	return ret;
>   }
>   
> +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_tdx *tdx = to_tdx(vcpu);
> +
> +	if (!tdx->host_state_need_save)
> +		return;
> +
> +	if (likely(is_64bit_mm(current->mm)))
> +		tdx->msr_host_kernel_gs_base = current->thread.gsbase;
> +	else
> +		tdx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
> +
> +	tdx->host_state_need_save = false;
> +}
> +
> +static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_tdx *tdx = to_tdx(vcpu);
> +
> +	tdx->host_state_need_save = true;
> +	if (!tdx->host_state_need_restore)
> +		return;
> +
> +	wrmsrl(MSR_KERNEL_GS_BASE, tdx->msr_host_kernel_gs_base);
> +	tdx->host_state_need_restore = false;
> +}
> +
> +void tdx_vcpu_put(struct kvm_vcpu *vcpu)
> +{
> +	vmx_vcpu_pi_put(vcpu);
> +	tdx_prepare_switch_to_host(vcpu);
> +}
> +
>   void tdx_vcpu_free(struct kvm_vcpu *vcpu)
>   {
>   	struct vcpu_tdx *tdx = to_tdx(vcpu);
> @@ -535,6 +572,8 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu)
>   
>   	tdx_vcpu_enter_exit(vcpu, tdx);
>   
> +	tdx->host_state_need_restore = true;
> +
>   	vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
>   	trace_kvm_exit(vcpu, KVM_ISA_VMX);
>   
> diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
> index e950404ce5de..8b1cf9c158e3 100644
> --- a/arch/x86/kvm/vmx/tdx.h
> +++ b/arch/x86/kvm/vmx/tdx.h
> @@ -84,6 +84,10 @@ struct vcpu_tdx {
>   	union tdx_exit_reason exit_reason;
>   
>   	bool initialized;
> +
> +	bool host_state_need_save;
> +	bool host_state_need_restore;
> +	u64 msr_host_kernel_gs_base;
>   };
>   
>   static inline bool is_td(struct kvm *kvm)
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index 44404dd25737..8b871c5f52cf 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -141,6 +141,8 @@ int tdx_vcpu_create(struct kvm_vcpu *vcpu);
>   void tdx_vcpu_free(struct kvm_vcpu *vcpu);
>   void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
>   fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu);
> +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
> +void tdx_vcpu_put(struct kvm_vcpu *vcpu);
>   
>   int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
>   int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
> @@ -162,6 +164,8 @@ static inline int tdx_vcpu_create(struct kvm_vcpu *vcpu) { return -EOPNOTSUPP; }
>   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 fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu) { return EXIT_FASTPATH_NONE; }
> +static inline void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
> +static inline void tdx_vcpu_put(struct kvm_vcpu *vcpu) {}
>   
>   static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
>   static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }

Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>