[RFC PATCH v6 029/104] KVM: TDX: allocate/free TDX vcpu structure

[isaku . yamahata]

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/tdx.c | 133 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 133 insertions(+)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 095ca7952114..eb4fd31bc369 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -6,6 +6,7 @@
 #include "capabilities.h"
 #include "x86_ops.h"
 #include "tdx.h"
+#include "x86.h"
 
 #undef pr_fmt
 #define pr_fmt(fmt) "tdx: " fmt
@@ -61,6 +62,11 @@ static __always_inline hpa_t set_hkid_to_hpa(hpa_t pa, u16 hkid)
 	return pa;
 }
 
+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;
@@ -392,6 +398,133 @@ int tdx_vm_init(struct kvm *kvm)
 	return ret;
 }
 
+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;
+
+	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);
+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;
+
+	for (i = 0; i < tdx_caps.tdvpx_nr_pages; i++)
+		tdx_reclaim_td_page(&tdx->tdvpx[i]);
+	kfree(tdx->tdvpx);
+	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(init_event))
+		goto td_bugged;
+	if (WARN_ON(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);
+		*e  = (struct kvm_cpuid_entry2) {
+			.function = 1,	/* Features for X2APIC */
+			.index = 0,
+			.eax = 0,
+			.ebx = 0,
+			.ecx = 1ULL << 21,	/* X2APIC */
+			.edx = 0,
+		};
+		vcpu->arch.cpuid_entries = e;
+		vcpu->arch.cpuid_nent = 1;
+	}
+	apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | LAPIC_MODE_X2APIC;
+	if (kvm_vcpu_is_reset_bsp(vcpu))
+		apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
+	apic_base_msr.host_initiated = true;
+	if (WARN_ON(kvm_set_apic_base(vcpu, &apic_base_msr)))
+		goto td_bugged;
+
+	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+	return;
+
+td_bugged:
+	vcpu->kvm->vm_bugged = true;
+}
+
 int tdx_dev_ioctl(void __user *argp)
 {
 	struct kvm_tdx_capabilities __user *user_caps;
-- 
2.25.1