xen/evtchn: add IOCTL_EVTCHN_RESTRICT

IOCTL_EVTCHN_RESTRICT limits the file descriptor to being able to bind
to interdomain event channels from a specific domain.  Event channels
that are already bound continue to work for sending and receiving
notifications.

This is useful as part of deprivileging a user space PV backend or
device model (QEMU).  e.g., Once the device model as bound to the
ioreq server event channels it can restrict the file handle so an
exploited DM cannot use it to create or bind to arbitrary event
channels.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

drivers/xen/evtchn.c

@@ -73,8 +73,12 @@ struct per_user_data {
 	wait_queue_head_t evtchn_wait;
 	struct fasync_struct *evtchn_async_queue;
 	const char *name;
+
+	domid_t restrict_domid;
 };
 
+#define UNRESTRICTED_DOMID ((domid_t)-1)
+
 struct user_evtchn {
 	struct rb_node node;
 	struct per_user_data *user;
@@ -443,6 +447,10 @@ static long evtchn_ioctl(struct file *file,
 		struct ioctl_evtchn_bind_virq bind;
 		struct evtchn_bind_virq bind_virq;
 
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID)
+			break;
+
 		rc = -EFAULT;
 		if (copy_from_user(&bind, uarg, sizeof(bind)))
 			break;
@@ -468,6 +476,11 @@ static long evtchn_ioctl(struct file *file,
 		if (copy_from_user(&bind, uarg, sizeof(bind)))
 			break;
 
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID &&
+		    u->restrict_domid != bind.remote_domain)
+			break;
+
 		bind_interdomain.remote_dom  = bind.remote_domain;
 		bind_interdomain.remote_port = bind.remote_port;
 		rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
@@ -485,6 +498,10 @@ static long evtchn_ioctl(struct file *file,
 		struct ioctl_evtchn_bind_unbound_port bind;
 		struct evtchn_alloc_unbound alloc_unbound;
 
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID)
+			break;
+
 		rc = -EFAULT;
 		if (copy_from_user(&bind, uarg, sizeof(bind)))
 			break;
@@ -553,6 +570,27 @@ static long evtchn_ioctl(struct file *file,
 		break;
 	}
 
+	case IOCTL_EVTCHN_RESTRICT_DOMID: {
+		struct ioctl_evtchn_restrict_domid ierd;
+
+		rc = -EACCES;
+		if (u->restrict_domid != UNRESTRICTED_DOMID)
+			break;
+
+		rc = -EFAULT;
+		if (copy_from_user(&ierd, uarg, sizeof(ierd)))
+		    break;
+
+		rc = -EINVAL;
+		if (ierd.domid == 0 || ierd.domid >= DOMID_FIRST_RESERVED)
+			break;
+
+		u->restrict_domid = ierd.domid;
+		rc = 0;
+
+		break;
+	}
+
 	default:
 		rc = -ENOSYS;
 		break;
@@ -601,6 +639,8 @@ static int evtchn_open(struct inode *inode, struct file *filp)
 	mutex_init(&u->ring_cons_mutex);
 	spin_lock_init(&u->ring_prod_lock);
 
+	u->restrict_domid = UNRESTRICTED_DOMID;
+
 	filp->private_data = u;
 
 	return nonseekable_open(inode, filp);

include/uapi/xen/evtchn.h

@@ -85,4 +85,19 @@ struct ioctl_evtchn_notify {
 #define IOCTL_EVTCHN_RESET				\
 	_IOC(_IOC_NONE, 'E', 5, 0)
 
+/*
+ * Restrict this file descriptor so that it can only be used to bind
+ * new interdomain events from one domain.
+ *
+ * Once a file descriptor has been restricted it cannot be
+ * de-restricted, and must be closed and re-opened.  Event channels
+ * which were bound before restricting remain bound afterwards, and
+ * can be notified as usual.
+ */
+#define IOCTL_EVTCHN_RESTRICT_DOMID			\
+	_IOC(_IOC_NONE, 'E', 6, sizeof(struct ioctl_evtchn_restrict_domid))
+struct ioctl_evtchn_restrict_domid {
+	domid_t domid;
+};
+
 #endif /* __LINUX_PUBLIC_EVTCHN_H__ */