Re: [PATCH v3 07/10] KVM: TDX: restore user ret MSRs

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

On 3/8/2025 5:20 AM, Paolo Bonzini wrote:
> From: Isaku Yamahata <isaku.yamahata@intel.com>
> 
> Several user ret MSRs are clobbered on TD exit.  Ensure the MSR cache is
> updated on vcpu_put, and the MSRs themselves before returning to ring 3.

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

> Co-developed-by: Tony Lindgren <tony.lindgren@linux.intel.com>
> Signed-off-by: Tony Lindgren <tony.lindgren@linux.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: <20250129095902.16391-10-adrian.hunter@intel.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>   arch/x86/kvm/vmx/tdx.c | 51 +++++++++++++++++++++++++++++++++++++++++-
>   arch/x86/kvm/vmx/tdx.h |  1 +
>   2 files changed, 51 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index b2948318cd8b..5819ed926166 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -646,9 +646,32 @@ void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
>   	vt->guest_state_loaded = true;
>   }
>   
> +struct tdx_uret_msr {
> +	u32 msr;
> +	unsigned int slot;
> +	u64 defval;
> +};
> +
> +static struct tdx_uret_msr tdx_uret_msrs[] = {
> +	{.msr = MSR_SYSCALL_MASK, .defval = 0x20200 },
> +	{.msr = MSR_STAR,},
> +	{.msr = MSR_LSTAR,},
> +	{.msr = MSR_TSC_AUX,},
> +};
> +
> +static void tdx_user_return_msr_update_cache(void)
> +{
> +	int i;
> +
> +	for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++)
> +		kvm_user_return_msr_update_cache(tdx_uret_msrs[i].slot,
> +						 tdx_uret_msrs[i].defval);
> +}
> +
>   static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
>   {
>   	struct vcpu_vt *vt = to_vt(vcpu);
> +	struct vcpu_tdx *tdx = to_tdx(vcpu);
>   
>   	if (!vt->guest_state_loaded)
>   		return;
> @@ -656,6 +679,11 @@ static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
>   	++vcpu->stat.host_state_reload;
>   	wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base);
>   
> +	if (tdx->guest_entered) {
> +		tdx_user_return_msr_update_cache();
> +		tdx->guest_entered = false;
> +	}
> +
>   	vt->guest_state_loaded = false;
>   }
>   
> @@ -762,6 +790,8 @@ EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
>   
>   fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
>   {
> +	struct vcpu_tdx *tdx = to_tdx(vcpu);
> +
>   	/*
>   	 * force_immediate_exit requires vCPU entering for events injection with
>   	 * an immediately exit followed. But The TDX module doesn't guarantee
> @@ -777,6 +807,7 @@ fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
>   	tdx_vcpu_enter_exit(vcpu);
>   
>   	tdx_load_host_xsave_state(vcpu);
> +	tdx->guest_entered = true;
>   
>   	vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET;
>   
> @@ -2236,7 +2267,25 @@ static int __init __do_tdx_bringup(void)
>   static int __init __tdx_bringup(void)
>   {
>   	const struct tdx_sys_info_td_conf *td_conf;
> -	int r;
> +	int r, i;
> +
> +	for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) {
> +		/*
> +		 * Check if MSRs (tdx_uret_msrs) can be saved/restored
> +		 * before returning to user space.
> +		 *
> +		 * this_cpu_ptr(user_return_msrs)->registered isn't checked
> +		 * because the registration is done at vcpu runtime by
> +		 * tdx_user_return_msr_update_cache().
> +		 */
> +		tdx_uret_msrs[i].slot = kvm_find_user_return_msr(tdx_uret_msrs[i].msr);
> +		if (tdx_uret_msrs[i].slot == -1) {
> +			/* If any MSR isn't supported, it is a KVM bug */
> +			pr_err("MSR %x isn't included by kvm_find_user_return_msr\n",
> +				tdx_uret_msrs[i].msr);
> +			return -EIO;
> +		}
> +	}
>   
>   	/*
>   	 * Enabling TDX requires enabling hardware virtualization first,
> diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
> index 6eb24bbacccc..55af3d866ff6 100644
> --- a/arch/x86/kvm/vmx/tdx.h
> +++ b/arch/x86/kvm/vmx/tdx.h
> @@ -56,6 +56,7 @@ struct vcpu_tdx {
>   	u64 vp_enter_ret;
>   
>   	enum vcpu_tdx_state state;
> +	bool guest_entered;
>   };
>   
>   void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err);