Re: [PATCH v10 024/108] KVM: TDX: allocate/free TDX vcpu structure

[Isaku Yamahata]

On Mon, Nov 14, 2022 at 02:46:22PM +0800,
Yuan Yao <yuan.yao@xxxxxxxxxxxxxxx> wrote:

> On Sat, Oct 29, 2022 at 11:22:25PM -0700, isaku.yamahata@xxxxxxxxx wrote:
> > From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> >
> > The next step of TDX guest creation is to create vcpu.  Allocate TDX vcpu
> > structures, initialize it.  Allocate pages of TDX vcpu for the TDX module.
> >
> > In the case of the conventional case, cpuid is empty at the initialization.
> > and cpuid is configured after the vcpu initialization.  Because TDX
> > supports only X2APIC mode, cpuid is forcibly initialized to support X2APIC
> > on the vcpu initialization.
> >
> > Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> > ---
> >  arch/x86/kvm/vmx/main.c    |  40 +++++++++--
> >  arch/x86/kvm/vmx/tdx.c     | 138 +++++++++++++++++++++++++++++++++++++
> >  arch/x86/kvm/vmx/x86_ops.h |   8 +++
> >  3 files changed, 182 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> > index b4e4c6c677f6..c125b2e3e8b4 100644
> > --- a/arch/x86/kvm/vmx/main.c
> > +++ b/arch/x86/kvm/vmx/main.c
> > @@ -63,6 +63,38 @@ static void vt_vm_free(struct kvm *kvm)
> >  		return tdx_vm_free(kvm);
> >  }
> >
> > +static int vt_vcpu_precreate(struct kvm *kvm)
> > +{
> > +	if (is_td(kvm))
> > +		return 0;
> > +
> > +	return vmx_vcpu_precreate(kvm);
> > +}
> > +
> > +static int vt_vcpu_create(struct kvm_vcpu *vcpu)
> > +{
> > +	if (is_td_vcpu(vcpu))
> > +		return tdx_vcpu_create(vcpu);
> > +
> > +	return vmx_vcpu_create(vcpu);
> > +}
> > +
> > +static void vt_vcpu_free(struct kvm_vcpu *vcpu)
> > +{
> > +	if (is_td_vcpu(vcpu))
> > +		return tdx_vcpu_free(vcpu);
> > +
> > +	return vmx_vcpu_free(vcpu);
> > +}
> > +
> > +static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
> > +{
> > +	if (is_td_vcpu(vcpu))
> > +		return tdx_vcpu_reset(vcpu, init_event);
> > +
> > +	return vmx_vcpu_reset(vcpu, init_event);
> > +}
> > +
> >  static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
> >  {
> >  	if (!is_td(kvm))
> > @@ -89,10 +121,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
> >  	.vm_destroy = vt_vm_destroy,
> >  	.vm_free = vt_vm_free,
> >
> > -	.vcpu_precreate = vmx_vcpu_precreate,
> > -	.vcpu_create = vmx_vcpu_create,
> > -	.vcpu_free = vmx_vcpu_free,
> > -	.vcpu_reset = vmx_vcpu_reset,
> > +	.vcpu_precreate = vt_vcpu_precreate,
> > +	.vcpu_create = vt_vcpu_create,
> > +	.vcpu_free = vt_vcpu_free,
> > +	.vcpu_reset = vt_vcpu_reset,
> >
> >  	.prepare_switch_to_guest = vmx_prepare_switch_to_guest,
> >  	.vcpu_load = vmx_vcpu_load,
> > diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> > index 54045e0576e7..0625c354b341 100644
> > --- a/arch/x86/kvm/vmx/tdx.c
> > +++ b/arch/x86/kvm/vmx/tdx.c
> > @@ -49,6 +49,11 @@ static __always_inline hpa_t set_hkid_to_hpa(hpa_t pa, u16 hkid)
> >  	return pa | ((hpa_t)hkid << boot_cpu_data.x86_phys_bits);
> >  }
> >
> > +static inline bool is_td_vcpu_created(struct vcpu_tdx *tdx)
> > +{
> > +	return tdx->tdvpr.added;
> > +}
> > +
> >  static inline bool is_td_created(struct kvm_tdx *kvm_tdx)
> >  {
> >  	return kvm_tdx->tdr.added;
> > @@ -296,6 +301,139 @@ int tdx_vm_init(struct kvm *kvm)
> >  	return 0;
> >  }
> >
> > +int tdx_vcpu_create(struct kvm_vcpu *vcpu)
> > +{
> > +	struct vcpu_tdx *tdx = to_tdx(vcpu);
> > +	int ret, i;
> > +
> > +	/* TDX only supports x2APIC, which requires an in-kernel local APIC. */
> > +	if (!vcpu->arch.apic)
> > +		return -EINVAL;
> > +
> > +	fpstate_set_confidential(&vcpu->arch.guest_fpu);
> > +
> > +	ret = tdx_alloc_td_page(&tdx->tdvpr);
> > +	if (ret)
> > +		return ret;
> > +
> > +	tdx->tdvpx = kcalloc(tdx_caps.tdvpx_nr_pages, sizeof(*tdx->tdvpx),
> > +			GFP_KERNEL_ACCOUNT);
> > +	if (!tdx->tdvpx) {
> > +		ret = -ENOMEM;
> > +		goto free_tdvpr;
> > +	}
> > +	for (i = 0; i < tdx_caps.tdvpx_nr_pages; i++) {
> > +		ret = tdx_alloc_td_page(&tdx->tdvpx[i]);
> > +		if (ret)
> > +			goto free_tdvpx;
> > +	}
> > +
> > +	vcpu->arch.efer = EFER_SCE | EFER_LME | EFER_LMA | EFER_NX;
> > +
> > +	vcpu->arch.cr0_guest_owned_bits = -1ul;
> > +	vcpu->arch.cr4_guest_owned_bits = -1ul;
> > +
> > +	vcpu->arch.tsc_offset = to_kvm_tdx(vcpu->kvm)->tsc_offset;
> > +	vcpu->arch.l1_tsc_offset = vcpu->arch.tsc_offset;
> > +	vcpu->arch.guest_state_protected =
> > +		!(to_kvm_tdx(vcpu->kvm)->attributes & TDX_TD_ATTRIBUTE_DEBUG);
> > +
> > +	return 0;
> > +
> > +free_tdvpx:
> > +	/* @i points at the TDVPX page that failed allocation. */
> > +	for (--i; i >= 0; i--)
> > +		free_page(tdx->tdvpx[i].va);
> > +	kfree(tdx->tdvpx);
> > +	tdx->tdvpx = NULL;
> > +free_tdvpr:
> > +	free_page(tdx->tdvpr.va);
> > +
> > +	return ret;
> > +}
> > +
> > +void tdx_vcpu_free(struct kvm_vcpu *vcpu)
> > +{
> > +	struct vcpu_tdx *tdx = to_tdx(vcpu);
> > +	int i;
> > +
> > +	/* Can't reclaim or free pages if teardown failed. */
> > +	if (is_hkid_assigned(to_kvm_tdx(vcpu->kvm)))
> > +		return;
> > +
> > +	if (tdx->tdvpx) {
> > +		for (i = 0; i < tdx_caps.tdvpx_nr_pages; i++)
> > +			tdx_reclaim_td_page(&tdx->tdvpx[i]);
> > +		kfree(tdx->tdvpx);
> > +		tdx->tdvpx = NULL;
> > +	}
> > +	tdx_reclaim_td_page(&tdx->tdvpr);
> > +}
> > +
> > +void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
> > +{
> > +	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
> > +	struct vcpu_tdx *tdx = to_tdx(vcpu);
> > +	struct msr_data apic_base_msr;
> > +	u64 err;
> > +	int i;
> > +
> > +	/* TDX doesn't support INIT event. */
> > +	if (WARN_ON_ONCE(init_event))
> > +		goto td_bugged;
> > +	if (WARN_ON_ONCE(is_td_vcpu_created(tdx)))
> > +		goto td_bugged;
> > +
> > +	err = tdh_vp_create(kvm_tdx->tdr.pa, tdx->tdvpr.pa);
> > +	if (WARN_ON_ONCE(err)) {
> > +		pr_tdx_error(TDH_VP_CREATE, err, NULL);
> > +		goto td_bugged;
> > +	}
> > +	tdx_mark_td_page_added(&tdx->tdvpr);
> > +
> > +	for (i = 0; i < tdx_caps.tdvpx_nr_pages; i++) {
> > +		err = tdh_vp_addcx(tdx->tdvpr.pa, tdx->tdvpx[i].pa);
> > +		if (WARN_ON_ONCE(err)) {
> > +			pr_tdx_error(TDH_VP_ADDCX, err, NULL);
> > +			goto td_bugged;
> > +		}
> > +		tdx_mark_td_page_added(&tdx->tdvpx[i]);
> > +	}
> > +
> > +	if (!vcpu->arch.cpuid_entries) {
> > +		/*
> > +		 * On cpu creation, cpuid entry is blank.  Forcibly enable
> > +		 * X2APIC feature to allow X2APIC.
> > +		 */
> > +		struct kvm_cpuid_entry2 *e;
> > +
> > +		e = kvmalloc_array(1, sizeof(*e), GFP_KERNEL_ACCOUNT);
> 
> NULL checking is necessary for kvmalloc_array.

Fixed. Because vcpu_reset() function doesn't return error, this logic is
moved to tdx_vcpu_create().

Thanks,
-- 
Isaku Yamahata <isaku.yamahata@xxxxxxxxx>