KVM: TDX: Convert INIT_MEM_REGION and INIT_VCPU to "unlocked" vCPU ioctl

Handle the KVM_TDX_INIT_MEM_REGION and KVM_TDX_INIT_VCPU vCPU sub-ioctls
in the unlocked variant, i.e. outside of vcpu->mutex, in anticipation of
taking kvm->lock along with all other vCPU mutexes, at which point the
sub-ioctls _must_ start without vcpu->mutex held.

No functional change intended.

Reviewed-by: Kai Huang <kai.huang@intel.com>
Co-developed-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Kai Huang <kai.huang@intel.com>
Link: https://patch.msgid.link/20251030200951.3402865-24-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

6 files changed, 55 insertions, 6 deletions

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index fdf178443f85..de709fb5bd76 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -128,6 +128,7 @@ KVM_X86_OP(enable_smi_window)
 KVM_X86_OP_OPTIONAL(dev_get_attr)
 KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
 KVM_X86_OP_OPTIONAL(vcpu_mem_enc_ioctl)
+KVM_X86_OP_OPTIONAL(vcpu_mem_enc_unlocked_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/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 87a5f5100b1d..2bfae1cfa514 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1914,6 +1914,7 @@ struct kvm_x86_ops {
 	int (*dev_get_attr)(u32 group, u64 attr, u64 *val);
 	int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
 	int (*vcpu_mem_enc_ioctl)(struct kvm_vcpu *vcpu, void __user *argp);
+	int (*vcpu_mem_enc_unlocked_ioctl)(struct kvm_vcpu *vcpu, void __user *argp);
 	int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 0eb2773b2ae2..a46ccd670785 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -831,6 +831,14 @@ static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 	return tdx_vcpu_ioctl(vcpu, argp);
 }
 
+static int vt_vcpu_mem_enc_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
+{
+	if (!is_td_vcpu(vcpu))
+		return -EINVAL;
+
+	return tdx_vcpu_unlocked_ioctl(vcpu, argp);
+}
+
 static int vt_gmem_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
 				     bool is_private)
 {
@@ -1005,6 +1013,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl),
 	.vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl),
+	.vcpu_mem_enc_unlocked_ioctl = vt_op_tdx_only(vcpu_mem_enc_unlocked_ioctl),
 
 	.gmem_max_mapping_level = vt_op_tdx_only(gmem_max_mapping_level)
 };
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index f42cc955d49c..3b4d62a3bf31 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -3181,6 +3181,42 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c
 	return ret;
 }
 
+int tdx_vcpu_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
+{
+	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+	struct kvm_tdx_cmd cmd;
+	int r;
+
+	r = tdx_get_cmd(argp, &cmd);
+	if (r)
+		return r;
+
+	if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE)
+		return -EINVAL;
+
+	if (mutex_lock_killable(&vcpu->mutex))
+		return -EINTR;
+
+	vcpu_load(vcpu);
+
+	switch (cmd.id) {
+	case KVM_TDX_INIT_MEM_REGION:
+		r = tdx_vcpu_init_mem_region(vcpu, &cmd);
+		break;
+	case KVM_TDX_INIT_VCPU:
+		r = tdx_vcpu_init(vcpu, &cmd);
+		break;
+	default:
+		r = -ENOIOCTLCMD;
+		break;
+	}
+
+	vcpu_put(vcpu);
+
+	mutex_unlock(&vcpu->mutex);
+	return r;
+}
+
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 {
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
@@ -3195,12 +3231,6 @@ int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
 		return ret;
 
 	switch (cmd.id) {
-	case KVM_TDX_INIT_VCPU:
-		ret = tdx_vcpu_init(vcpu, &cmd);
-		break;
-	case KVM_TDX_INIT_MEM_REGION:
-		ret = tdx_vcpu_init_mem_region(vcpu, &cmd);
-		break;
 	case KVM_TDX_GET_CPUID:
 		ret = tdx_vcpu_get_cpuid(vcpu, &cmd);
 		break;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 9697368d65b3..a7a870919580 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -149,6 +149,7 @@ int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
+int tdx_vcpu_unlocked_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
 
 void tdx_flush_tlb_current(struct kvm_vcpu *vcpu);
 void tdx_flush_tlb_all(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b85cb213a336..593fccc9cf1c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7243,6 +7243,13 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
 long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl,
 				  unsigned long arg)
 {
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+
+	if (ioctl == KVM_MEMORY_ENCRYPT_OP &&
+	    kvm_x86_ops.vcpu_mem_enc_unlocked_ioctl)
+		return kvm_x86_call(vcpu_mem_enc_unlocked_ioctl)(vcpu, argp);
+
 	return -ENOIOCTLCMD;
 }