KVM: s390: add parameter for KVM_CREATE_VM

This patch introduces a new config option for user controlled kernel
virtual machines. It introduces a parameter to KVM_CREATE_VM that
allows to set bits that alter the capabilities of the newly created
virtual machine.
The parameter is passed to kvm_arch_init_vm for all architectures.
The only valid modifier bit for now is KVM_VM_S390_UCONTROL.
This requires CAP_SYS_ADMIN privileges and creates a user controlled
virtual machine on s390 architectures.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -95,7 +95,7 @@ described as 'basic' will be available.
 Capability: basic
 Architectures: all
 Type: system ioctl
-Parameters: none
+Parameters: machine type identifier (KVM_VM_*)
 Returns: a VM fd that can be used to control the new virtual machine.
 
 The new VM has no virtual cpus and no memory.  An mmap() of a VM fd
@@ -103,6 +103,11 @@ will access the virtual machine's physical address space; offset zero
 corresponds to guest physical address zero.  Use of mmap() on a VM fd
 is discouraged if userspace memory allocation (KVM_CAP_USER_MEMORY) is
 available.
+You most certainly want to use 0 as machine type.
+
+In order to create user controlled virtual machines on S390, check
+KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
+privileged user (CAP_SYS_ADMIN).
 
 4.3 KVM_GET_MSR_INDEX_LIST
 

arch/ia64/kvm/kvm-ia64.c

@@ -809,10 +809,13 @@ static void kvm_build_io_pmt(struct kvm *kvm)
 #define GUEST_PHYSICAL_RR4	0x2739
 #define VMM_INIT_RR		0x1660
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	BUG_ON(!kvm);
 
+	if (type)
+		return -EINVAL;
+
 	kvm->arch.is_sn2 = ia64_platform_is("sn2");
 
 	kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;

arch/powerpc/kvm/powerpc.c

@@ -171,8 +171,11 @@ void kvm_arch_check_processor_compat(void *rtn)
 	*(int *)rtn = kvmppc_core_check_processor_compat();
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	if (type)
+		return -EINVAL;
+
 	return kvmppc_core_init_vm(kvm);
 }
 

arch/s390/kvm/Kconfig

@@ -34,6 +34,15 @@ config KVM
 
 	  If unsure, say N.
 
+config KVM_S390_UCONTROL
+	bool "Userspace controlled virtual machines"
+	depends on KVM
+	---help---
+	  Allow CAP_SYS_ADMIN users to create KVM virtual machines that are
+	  controlled by userspace.
+
+	  If unsure, say N.
+
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/vhost/Kconfig

arch/s390/kvm/kvm-s390.c

@@ -171,11 +171,22 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	return r;
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	int rc;
 	char debug_name[16];
 
+	rc = -EINVAL;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (type & ~KVM_VM_S390_UCONTROL)
+		goto out_err;
+	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
+		goto out_err;
+#else
+	if (type)
+		goto out_err;
+#endif
+
 	rc = s390_enable_sie();
 	if (rc)
 		goto out_err;
@@ -198,10 +209,13 @@ int kvm_arch_init_vm(struct kvm *kvm)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
-	kvm->arch.gmap = gmap_alloc(current->mm);
+	if (type & KVM_VM_S390_UCONTROL) {
-	if (!kvm->arch.gmap)
+		kvm->arch.gmap = NULL;
-		goto out_nogmap;
+	} else {
-
+		kvm->arch.gmap = gmap_alloc(current->mm);
+		if (!kvm->arch.gmap)
+			goto out_nogmap;
+	}
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);

arch/s390/kvm/kvm-s390.h

@@ -47,6 +47,16 @@ static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
 	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
 }
 
+static inline int kvm_is_ucontrol(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (kvm->arch.gmap)
+		return 0;
+	return 1;
+#else
+	return 0;
+#endif
+}
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);

arch/x86/kvm/x86.c

@@ -6031,8 +6031,11 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)vcpu->arch.pio_data);
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	if (type)
+		return -EINVAL;
+
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 

include/linux/kvm.h

@@ -431,6 +431,9 @@ struct kvm_ppc_pvinfo {
 
 #define KVMIO 0xAE
 
+/* machine type bits, to be used as argument to KVM_CREATE_VM */
+#define KVM_VM_S390_UCONTROL	1
+
 /*
  * ioctls for /dev/kvm fds:
  */

include/linux/kvm_host.h

@@ -520,7 +520,7 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
-int kvm_arch_init_vm(struct kvm *kvm);
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
 void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_free_all_assigned_devices(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);

virt/kvm/kvm_main.c

@@ -449,7 +449,7 @@ static void kvm_init_memslots_id(struct kvm *kvm)
 		slots->id_to_index[i] = slots->memslots[i].id = i;
 }
 
-static struct kvm *kvm_create_vm(void)
+static struct kvm *kvm_create_vm(unsigned long type)
 {
 	int r, i;
 	struct kvm *kvm = kvm_arch_alloc_vm();
@@ -457,7 +457,7 @@ static struct kvm *kvm_create_vm(void)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
-	r = kvm_arch_init_vm(kvm);
+	r = kvm_arch_init_vm(kvm, type);
 	if (r)
 		goto out_err_nodisable;
 
@@ -2198,12 +2198,12 @@ static struct file_operations kvm_vm_fops = {
 	.llseek		= noop_llseek,
 };
 
-static int kvm_dev_ioctl_create_vm(void)
+static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;
 	struct kvm *kvm;
 
-	kvm = kvm_create_vm();
+	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
 		return PTR_ERR(kvm);
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
@@ -2254,10 +2254,7 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = KVM_API_VERSION;
 		break;
 	case KVM_CREATE_VM:
-		r = -EINVAL;
+		r = kvm_dev_ioctl_create_vm(arg);
-		if (arg)
-			goto out;
-		r = kvm_dev_ioctl_create_vm();
 		break;
 	case KVM_CHECK_EXTENSION:
 		r = kvm_dev_ioctl_check_extension_generic(arg);