[v19,043/130] KVM: TDX: create/free TDX vcpu structure

Commit Message

Isaku Yamahata Feb. 26, 2024, 8:25 a.m. UTC

From: Isaku Yamahata <[e-mail]>

The next step of TDX guest creation is to create vcpu.  Create TDX vcpu
structures, initialize it that doesn't require TDX SEAMCALL.  TDX specific
vcpu initialization will be implemented as independent KVM_TDX_INIT_VCPU
so that when error occurs it's easy to determine which component has the
issue, KVM or TDX.

Signed-off-by: Isaku Yamahata <[e-mail]>
---
v19:
- removed stale comment in tdx_vcpu_create().

v18:
- update commit log to use create instead of allocate because the patch
  doesn't newly allocate memory for TDX vcpu.

v15 -> v16:
- Add AMX support as the KVM upstream supports it.

Signed-off-by: Isaku Yamahata <[e-mail]>
---
 arch/x86/kvm/vmx/main.c    | 44 ++++++++++++++++++++++++++++++++++----
 arch/x86/kvm/vmx/tdx.c     | 44 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h | 10 +++++++++
 arch/x86/kvm/x86.c         |  2 ++
 4 files changed, 96 insertions(+), 4 deletions(-)

Comments

Chao Gao March 21, 2024, 1:30 a.m. UTC | #1

>+int tdx_vcpu_create(struct kvm_vcpu *vcpu)
>+{
>+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
>+
>+	WARN_ON_ONCE(vcpu->arch.cpuid_entries);
>+	WARN_ON_ONCE(vcpu->arch.cpuid_nent);
>+
>+	/* TDX only supports x2APIC, which requires an in-kernel local APIC. */

Cannot QEMU emulate x2APIC? In my understanding, the reason is TDX module always
enables APICv for TDs. So, KVM cannot intercept every access to APIC and forward
them to QEMU for emulation.

>+	if (!vcpu->arch.apic)

will "if (!irqchip_in_kernel(vcpu->kvm))" work? looks this is the custome for such
a check.

>+		return -EINVAL;
>+
>+	fpstate_set_confidential(&vcpu->arch.guest_fpu);
>+
>+	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;

kvm_tdx->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);

!(kvm_tdx->attributes & TDX_TD_ATTRIBUTE_DEBUG);

>+
>+	if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE)
>+		vcpu->arch.xfd_no_write_intercept = true;
>+
>+	return 0;
>+}

Isaku Yamahata March 21, 2024, 8:21 p.m. UTC | #2

On Thu, Mar 21, 2024 at 09:30:12AM +0800,
Chao Gao <[e-mail]> wrote:

> >+int tdx_vcpu_create(struct kvm_vcpu *vcpu)
> >+{
> >+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
> >+
> >+	WARN_ON_ONCE(vcpu->arch.cpuid_entries);
> >+	WARN_ON_ONCE(vcpu->arch.cpuid_nent);
> >+
> >+	/* TDX only supports x2APIC, which requires an in-kernel local APIC. */
> 
> Cannot QEMU emulate x2APIC? In my understanding, the reason is TDX module always
> enables APICv for TDs. So, KVM cannot intercept every access to APIC and forward
> them to QEMU for emulation.

You're right. Let me update it as follows.

  /*
   * TDX module always enables APICv for TDs. So, KVM cannot intercept every
   * access to APIC and forward them to user space VMM.
   */



> >+	if (!vcpu->arch.apic)
> 
> will "if (!irqchip_in_kernel(vcpu->kvm))" work? looks this is the custome for such
> a check.


It should work because kvm_arch_vcpu_create().  Will update it.

Patch

diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index d69dd474775b..5796fb45433f 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -87,6 +87,42 @@  static void vt_vm_free(struct kvm *kvm)
 		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)) {
+		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)) {
+		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))
@@ -126,10 +162,10 @@  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 f2ee5abac14e..51283d2cd011 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -368,6 +368,50 @@  int tdx_vm_init(struct kvm *kvm)
 	return 0;
 }
 
+int tdx_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+
+	WARN_ON_ONCE(vcpu->arch.cpuid_entries);
+	WARN_ON_ONCE(vcpu->arch.cpuid_nent);
+
+	/* TDX only supports x2APIC, which requires an in-kernel local APIC. */
+	if (!vcpu->arch.apic)
+		return -EINVAL;
+
+	fpstate_set_confidential(&vcpu->arch.guest_fpu);
+
+	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);
+
+	if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE)
+		vcpu->arch.xfd_no_write_intercept = true;
+
+	return 0;
+}
+
+void tdx_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	/* This is stub for now.  More logic will come. */
+}
+
+void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
+{
+
+	/* Ignore INIT silently because TDX doesn't support INIT event. */
+	if (init_event)
+		return;
+
+	/* This is stub for now. More logic will come here. */
+}
+
 static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
 {
 	struct kvm_tdx_capabilities __user *user_caps;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 33ab6800eab8..bb73a9b5b354 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -144,7 +144,12 @@  int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap);
 int tdx_vm_init(struct kvm *kvm);
 void tdx_mmu_release_hkid(struct kvm *kvm);
 void tdx_vm_free(struct kvm *kvm);
+
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
+
+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);
 #else
 static inline int tdx_hardware_setup(struct kvm_x86_ops *x86_ops) { return -EOPNOTSUPP; }
 static inline void tdx_hardware_unsetup(void) {}
@@ -158,7 +163,12 @@  static inline int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 static inline int tdx_vm_init(struct kvm *kvm) { return -EOPNOTSUPP; }
 static inline void tdx_mmu_release_hkid(struct kvm *kvm) {}
 static inline void tdx_vm_free(struct kvm *kvm) {}
+
 static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
+
+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) {}
 #endif
 
 #endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e27ea5ed2968..c002761bb662 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -502,6 +502,7 @@  int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	kvm_recalculate_apic_map(vcpu->kvm);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 
 /*
  * Handle a fault on a hardware virtualization (VMX or SVM) instruction.
@@ -12517,6 +12518,7 @@  bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
 
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 {