Re: [PATCH v3 04/10] KVM: TDX: vcpu_run: save/restore host state(host kernel gs)

[Xiaoyao Li <xiaoyao.li@intel.com>]

On 3/8/2025 5:20 AM, Paolo Bonzini wrote:
> From: Isaku Yamahata <isaku.yamahata@intel.com>
> 
> On entering/exiting TDX vcpu, preserved or clobbered CPU state is different
> from the VMX case. Add TDX hooks to save/restore host/guest CPU state.
> Save/restore kernel GS base MSR.


Reviewed-by: Xiayao Li <xiaoyao.li@intel.com>

> Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
> Message-ID: <20250129095902.16391-7-adrian.hunter@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   arch/x86/kvm/vmx/main.c    | 24 +++++++++++++++++++++--
>   arch/x86/kvm/vmx/tdx.c     | 40 ++++++++++++++++++++++++++++++++++++++
>   arch/x86/kvm/vmx/x86_ops.h |  4 ++++
>   3 files changed, 66 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> index 037590fc05e9..c0497ed0c9be 100644
> --- a/arch/x86/kvm/vmx/main.c
> +++ b/arch/x86/kvm/vmx/main.c
> @@ -145,6 +145,26 @@ static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
>   	vmx_update_cpu_dirty_logging(vcpu);
>   }
>   
> +static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
> +{
> +	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)) {
> +		tdx_vcpu_put(vcpu);
> +		return;
> +	}
> +
> +	vmx_vcpu_put(vcpu);
> +}
> +
>   static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
>   {
>   	if (is_td_vcpu(vcpu))
> @@ -265,9 +285,9 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
>   	.vcpu_free = vt_vcpu_free,
>   	.vcpu_reset = vt_vcpu_reset,
>   
> -	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
> +	.prepare_switch_to_guest = vt_prepare_switch_to_guest,
>   	.vcpu_load = vt_vcpu_load,
> -	.vcpu_put = vmx_vcpu_put,
> +	.vcpu_put = vt_vcpu_put,
>   
>   	.update_exception_bitmap = vmx_update_exception_bitmap,
>   	.get_feature_msr = vmx_get_feature_msr,
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index f50565f45b6a..94e08fdcb775 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -3,6 +3,7 @@
>   #include <linux/cpu.h>
>   #include <asm/cpufeature.h>
>   #include <linux/misc_cgroup.h>
> +#include <linux/mmu_context.h>
>   #include <asm/tdx.h>
>   #include "capabilities.h"
>   #include "mmu.h"
> @@ -12,6 +13,7 @@
>   #include "vmx.h"
>   #include "mmu/spte.h"
>   #include "common.h"
> +#include "posted_intr.h"
>   #include <trace/events/kvm.h>
>   #include "trace.h"
>   
> @@ -624,6 +626,44 @@ void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
>   	local_irq_enable();
>   }
>   
> +/*
> + * Compared to vmx_prepare_switch_to_guest(), there is not much to do
> + * as SEAMCALL/SEAMRET calls take care of most of save and restore.
> + */
> +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vt *vt = to_vt(vcpu);
> +
> +	if (vt->guest_state_loaded)
> +		return;
> +
> +	if (likely(is_64bit_mm(current->mm)))
> +		vt->msr_host_kernel_gs_base = current->thread.gsbase;
> +	else
> +		vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
> +
> +	vt->guest_state_loaded = true;
> +}
> +
> +static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
> +{
> +	struct vcpu_vt *vt = to_vt(vcpu);
> +
> +	if (!vt->guest_state_loaded)
> +		return;
> +
> +	++vcpu->stat.host_state_reload;
> +	wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base);
> +
> +	vt->guest_state_loaded = 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 kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index 578c26d3aec4..cd18e9b1e124 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -133,6 +133,8 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu);
>   void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
>   int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu);
>   fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
> +void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
> +void tdx_vcpu_put(struct kvm_vcpu *vcpu);
>   
>   int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
>   
> @@ -164,6 +166,8 @@ static inline fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediat
>   {
>   	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_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
>