Re: [PATCH 4/7] KVM: TDX: Handle TDG.VP.VMCALL<MapGPA>

[Chao Gao]

>+/*
>+ * Split into chunks and check interrupt pending between chunks.  This allows
>+ * for timely injection of interrupts to prevent issues with guest lockup
>+ * detection.

Would it cause any problems if an (intra-host or inter-host) migration happens
between chunks?

My understanding is that KVM would lose track of the progress if
map_gpa_next/end are not migrated. I'm not sure if KVM should expose the
state or prevent migration in the middle. Or, we can let the userspace VMM
cut the range into chunks, making it the userspace VMM's responsibility to
ensure necessary state is migrated.

I am not asking to fix this issue right now. I just want to ensure this issue
can be solved in a clean way when we start to support migration.

>+ */
>+#define TDX_MAP_GPA_MAX_LEN (2 * 1024 * 1024)
>+static void __tdx_map_gpa(struct vcpu_tdx * tdx);
>+
>+static int tdx_complete_vmcall_map_gpa(struct kvm_vcpu *vcpu)
>+{
>+	struct vcpu_tdx * tdx = to_tdx(vcpu);
>+
>+	if(vcpu->run->hypercall.ret) {
>+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
>+		kvm_r11_write(vcpu, tdx->map_gpa_next);

s/kvm_r11_write/tdvmcall_set_return_val

please fix other call sites in this patch.

>+		return 1;
>+	}
>+
>+	tdx->map_gpa_next += TDX_MAP_GPA_MAX_LEN;
>+	if (tdx->map_gpa_next >= tdx->map_gpa_end) {
>+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
>+		return 1;
>+	}
>+
>+	/*
>+	 * Stop processing the remaining part if there is pending interrupt.
>+	 * Skip checking pending virtual interrupt (reflected by
>+	 * TDX_VCPU_STATE_DETAILS_INTR_PENDING bit) to save a seamcall because
>+	 * if guest disabled interrupt, it's OK not returning back to guest
>+	 * due to non-NMI interrupt. Also it's rare to TDVMCALL_MAP_GPA
>+	 * immediately after STI or MOV/POP SS.
>+	 */
>+	if (pi_has_pending_interrupt(vcpu) ||
>+	    kvm_test_request(KVM_REQ_NMI, vcpu) || vcpu->arch.nmi_pending) {
>+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_RETRY);
>+		kvm_r11_write(vcpu, tdx->map_gpa_next);
>+		return 1;
>+	}
>+
>+	__tdx_map_gpa(tdx);
>+	/* Forward request to userspace. */
>+	return 0;
>+}
>+
>+static void __tdx_map_gpa(struct vcpu_tdx * tdx)
>+{
>+	u64 gpa = tdx->map_gpa_next;
>+	u64 size = tdx->map_gpa_end - tdx->map_gpa_next;
>+
>+	if(size > TDX_MAP_GPA_MAX_LEN)
>+		size = TDX_MAP_GPA_MAX_LEN;
>+
>+	tdx->vcpu.run->exit_reason       = KVM_EXIT_HYPERCALL;
>+	tdx->vcpu.run->hypercall.nr      = KVM_HC_MAP_GPA_RANGE;
>+	tdx->vcpu.run->hypercall.args[0] = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
>+	tdx->vcpu.run->hypercall.args[1] = size / PAGE_SIZE;
>+	tdx->vcpu.run->hypercall.args[2] = vt_is_tdx_private_gpa(tdx->vcpu.kvm, gpa) ?
>+					   KVM_MAP_GPA_RANGE_ENCRYPTED :
>+					   KVM_MAP_GPA_RANGE_DECRYPTED;
>+	tdx->vcpu.run->hypercall.flags   = KVM_EXIT_HYPERCALL_LONG_MODE;
>+
>+	tdx->vcpu.arch.complete_userspace_io = tdx_complete_vmcall_map_gpa;
>+}
>+
>+static int tdx_map_gpa(struct kvm_vcpu *vcpu)
>+{
>+	struct vcpu_tdx * tdx = to_tdx(vcpu);
>+	u64 gpa = tdvmcall_a0_read(vcpu);
>+	u64 size = tdvmcall_a1_read(vcpu);
>+	u64 ret;
>+
>+	/*
>+	 * Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires
>+	 * userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE
>+	 * bit set.  If not, the error code is not defined in GHCI for TDX, use
>+	 * TDVMCALL_STATUS_INVALID_OPERAND for this case.
>+	 */
>+	if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
>+		ret = TDVMCALL_STATUS_INVALID_OPERAND;
>+		goto error;
>+	}
>+
>+	if (gpa + size <= gpa || !kvm_vcpu_is_legal_gpa(vcpu, gpa) ||
>+	    !kvm_vcpu_is_legal_gpa(vcpu, gpa + size -1) ||
>+	    (vt_is_tdx_private_gpa(vcpu->kvm, gpa) !=
>+	     vt_is_tdx_private_gpa(vcpu->kvm, gpa + size -1))) {
>+		ret = TDVMCALL_STATUS_INVALID_OPERAND;
>+		goto error;
>+	}
>+
>+	if (!PAGE_ALIGNED(gpa) || !PAGE_ALIGNED(size)) {
>+		ret = TDVMCALL_STATUS_ALIGN_ERROR;
>+		goto error;
>+	}
>+
>+	tdx->map_gpa_end = gpa + size;
>+	tdx->map_gpa_next = gpa;
>+
>+	__tdx_map_gpa(tdx);
>+	/* Forward request to userspace. */
>+	return 0;
>+
>+error:
>+	tdvmcall_set_return_code(vcpu, ret);
>+	kvm_r11_write(vcpu, gpa);
>+	return 1;
>+}
>+
> static int handle_tdvmcall(struct kvm_vcpu *vcpu)
> {
> 	if (tdvmcall_exit_type(vcpu))
> 		return tdx_emulate_vmcall(vcpu);
> 
> 	switch (tdvmcall_leaf(vcpu)) {
>+	case TDVMCALL_MAP_GPA:
>+		return tdx_map_gpa(vcpu);
> 	default:
> 		break;
> 	}
>diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
>index 1abc94b046a0..bfae70887695 100644
>--- a/arch/x86/kvm/vmx/tdx.h
>+++ b/arch/x86/kvm/vmx/tdx.h
>@@ -71,6 +71,9 @@ struct vcpu_tdx {
> 
> 	enum tdx_prepare_switch_state prep_switch_state;
> 	u64 msr_host_kernel_gs_base;
>+
>+	u64 map_gpa_next;
>+	u64 map_gpa_end;
> };
> 
> void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err);
>-- 
>2.46.0
>