[PATCH v2 15/25] KVM: TDX: Add place holder for TDX VM specific mem_enc_op ioctl

[Rick Edgecombe <rick.p.edgecombe@intel.com>]

From: Isaku Yamahata <isaku.yamahata@intel.com>

KVM_MEMORY_ENCRYPT_OP was introduced for VM-scoped operations specific for
guest state-protected VM.  It defined subcommands for technology-specific
operations under KVM_MEMORY_ENCRYPT_OP.  Despite its name, the subcommands
are not limited to memory encryption, but various technology-specific
operations are defined.  It's natural to repurpose KVM_MEMORY_ENCRYPT_OP
for TDX specific operations and define subcommands.

Add a place holder function for TDX specific VM-scoped ioctl as mem_enc_op.
TDX specific sub-commands will be added to retrieve/pass TDX specific
parameters.  Make mem_enc_ioctl non-optional as it's always filled.

Signed-off-by: Isaku Yamahata <isaku.yamahata@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: Rick Edgecombe <rick.p.edgecombe@intel.com>
---
uAPI breakout v2:
 - Correct comment to use hw_error naming (Isaku)
 - Drop KVM_TDX_CAPABILITIES, it's not needed yet (Binbin)

uAPI breakout v1:
 - rename error->hw_error (Kai)
 - Include "x86_ops.h" to tdx.c as the patch to initialize TDX module
   doesn't include it anymore.
 - Introduce tdx_vm_ioctl() as the first tdx func in x86_ops.h
 - Drop middle paragraph in the commit log (Tony)

v15:
  - change struct kvm_tdx_cmd to drop unused member.
---
 arch/x86/include/asm/kvm-x86-ops.h |  2 +-
 arch/x86/include/uapi/asm/kvm.h    | 24 ++++++++++++++++++++++
 arch/x86/kvm/vmx/main.c            | 10 ++++++++++
 arch/x86/kvm/vmx/tdx.c             | 32 ++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h         |  6 ++++++
 arch/x86/kvm/x86.c                 |  4 ----
 6 files changed, 73 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 53756a670f41..f250137c837a 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -123,7 +123,7 @@ KVM_X86_OP(leave_smm)
 KVM_X86_OP(enable_smi_window)
 #endif
 KVM_X86_OP_OPTIONAL(dev_get_attr)
-KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
+KVM_X86_OP(mem_enc_ioctl)
 KVM_X86_OP_OPTIONAL(mem_enc_register_region)
 KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
 KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from)
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index cba4351b3091..b6cb87f2b477 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -926,4 +926,28 @@ struct kvm_hyperv_eventfd {
 #define KVM_X86_SNP_VM		4
 #define KVM_X86_TDX_VM		5
 
+/* Trust Domain eXtension sub-ioctl() commands. */
+enum kvm_tdx_cmd_id {
+	KVM_TDX_CMD_NR_MAX,
+};
+
+struct kvm_tdx_cmd {
+	/* enum kvm_tdx_cmd_id */
+	__u32 id;
+	/* flags for sub-commend. If sub-command doesn't use this, set zero. */
+	__u32 flags;
+	/*
+	 * data for each sub-command. An immediate or a pointer to the actual
+	 * data in process virtual address.  If sub-command doesn't use it,
+	 * set zero.
+	 */
+	__u64 data;
+	/*
+	 * Auxiliary error code.  The sub-command may return TDX SEAMCALL
+	 * status code in addition to -Exxx.
+	 * Defined for consistency with struct kvm_sev_cmd.
+	 */
+	__u64 hw_error;
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 245f7d1f1bd4..6ed78deea543 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -41,6 +41,14 @@ static __init int vt_hardware_setup(void)
 	return 0;
 }
 
+static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
+{
+	if (!is_td(kvm))
+		return -ENOTTY;
+
+	return tdx_vm_ioctl(kvm, argp);
+}
+
 #define VMX_REQUIRED_APICV_INHIBITS				\
 	(BIT(APICV_INHIBIT_REASON_DISABLED) |			\
 	 BIT(APICV_INHIBIT_REASON_ABSENT) |			\
@@ -191,6 +199,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 
 	.get_untagged_addr = vmx_get_untagged_addr,
+
+	.mem_enc_ioctl = vt_mem_enc_ioctl,
 };
 
 struct kvm_x86_init_ops vt_init_ops __initdata = {
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 60b577379a9a..76655d82f749 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -2,6 +2,7 @@
 #include <linux/cpu.h>
 #include <asm/tdx.h>
 #include "capabilities.h"
+#include "x86_ops.h"
 #include "tdx.h"
 
 #undef pr_fmt
@@ -29,6 +30,37 @@ static enum cpuhp_state tdx_cpuhp_state;
 
 static const struct tdx_sys_info *tdx_sysinfo;
 
+int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_tdx_cmd tdx_cmd;
+	int r;
+
+	if (copy_from_user(&tdx_cmd, argp, sizeof(struct kvm_tdx_cmd)))
+		return -EFAULT;
+
+	/*
+	 * Userspace should never set hw_error. It is used to fill
+	 * hardware-defined error by the kernel.
+	 */
+	if (tdx_cmd.hw_error)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	switch (tdx_cmd.id) {
+	default:
+		r = -EINVAL;
+		goto out;
+	}
+
+	if (copy_to_user(argp, &tdx_cmd, sizeof(struct kvm_tdx_cmd)))
+		r = -EFAULT;
+
+out:
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
 static int tdx_online_cpu(unsigned int cpu)
 {
 	unsigned long flags;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index a55981c5216e..42901be70f9d 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -118,4 +118,10 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu);
 #endif
 void vmx_setup_mce(struct kvm_vcpu *vcpu);
 
+#ifdef CONFIG_INTEL_TDX_HOST
+int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
+#else
+static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
+#endif
+
 #endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9da7c728c391..d86a18a4195b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7308,10 +7308,6 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		goto out;
 	}
 	case KVM_MEMORY_ENCRYPT_OP: {
-		r = -ENOTTY;
-		if (!kvm_x86_ops.mem_enc_ioctl)
-			goto out;
-
 		r = kvm_x86_call(mem_enc_ioctl)(kvm, argp);
 		break;
 	}
-- 
2.47.0