static ssize_t store_group_addr(struct device *d,
struct device_attribute *attr,
const char *buf, size_t len)
{
struct net_bridge *br = to_bridge(d);
u8 new_addr[6];
int i;
if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
&new_addr[0], &new_addr[1], &new_addr[2],
&new_addr[3], &new_addr[4], &new_addr[5]) != 6)
return -EINVAL;
if (!is_link_local_ether_addr(new_addr))
return -EINVAL;
if (new_addr[5] == 1 || /* 802.3x Pause address */
new_addr[5] == 2 || /* 802.3ad Slow protocols */
new_addr[5] == 3) /* 802.1X PAE address */
return -EINVAL;
spin_lock_bh(&br->lock);
for (i = 0; i < 6; i++)
br->group_addr[i] = new_addr[i];
spin_unlock_bh(&br->lock);
return len;
}
SYSCALL_DEFINE1(chroot, const char __user *, filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
goto dput_and_out;
error = security_path_chroot(&path);
if (error)
goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
/*
* Common code for storing bridge parameters.
*/
static ssize_t store_bridge_parm(struct device *d,
const char *buf, size_t len,
int (*set)(struct net_bridge *, unsigned long))
{
struct net_bridge *br = to_bridge(d);
char *endp;
unsigned long val;
int err;
if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
val = simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EINVAL;
if (!rtnl_trylock())
return restart_syscall();
err = (*set)(br, val);
if (!err)
netdev_state_change(br->dev);
rtnl_unlock();
return err ? err : len;
}
/*
* called from clone. This now handles copy for nsproxy and all
* namespaces therein.
*/
int copy_namespaces(unsigned long flags, struct task_struct *tsk)
{
struct nsproxy *old_ns = tsk->nsproxy;
struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
struct nsproxy *new_ns;
if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWPID | CLONE_NEWNET |
CLONE_NEWCGROUP)))) {
get_nsproxy(old_ns);
return 0;
}
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
/*
* CLONE_NEWIPC must detach from the undolist: after switching
* to a new ipc namespace, the semaphore arrays from the old
* namespace are unreachable. In clone parlance, CLONE_SYSVSEM
* means share undolist with parent, so we must forbid using
* it along with CLONE_NEWIPC.
*/
if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
(CLONE_NEWIPC | CLONE_SYSVSEM))
return -EINVAL;
new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
if (IS_ERR(new_ns))
return PTR_ERR(new_ns);
tsk->nsproxy = new_ns;
return 0;
}
static ssize_t brport_store(struct kobject *kobj,
struct attribute *attr,
const char *buf, size_t count)
{
struct brport_attribute *brport_attr = to_brport_attr(attr);
struct net_bridge_port *p = to_brport(kobj);
ssize_t ret = -EINVAL;
char *endp;
unsigned long val;
if (!ns_capable(dev_net(p->dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
val = simple_strtoul(buf, &endp, 0);
if (endp != buf) {
if (!rtnl_trylock())
return restart_syscall();
if (p->dev && p->br && brport_attr->store) {
spin_lock_bh(&p->br->lock);
ret = brport_attr->store(p, val);
spin_unlock_bh(&p->br->lock);
if (!ret) {
br_ifinfo_notify(RTM_NEWLINK, p);
ret = count;
}
}
rtnl_unlock();
}
return ret;
}
/* use same locking and permission rules as SIF* ioctl's */
static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len,
int (*set)(struct net_device *, unsigned long))
{
struct net_device *netdev = to_net_dev(dev);
struct net *net = dev_net(netdev);
unsigned long new;
int ret = -EINVAL;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
ret = kstrtoul(buf, 0, &new);
if (ret)
goto err;
if (!rtnl_trylock())
return restart_syscall();
if (dev_isalive(netdev)) {
ret = (*set)(netdev, new);
if (ret == 0)
ret = len;
}
rtnl_unlock();
err:
return ret;
}
static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
struct net_device *netdev = to_net_dev(dev);
struct net *net = dev_net(netdev);
size_t count = len;
ssize_t ret = 0;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
/* ignore trailing newline */
if (len > 0 && buf[len - 1] == '\n')
--count;
if (!rtnl_trylock())
return restart_syscall();
if (dev_isalive(netdev)) {
ret = dev_set_alias(netdev, buf, count);
if (ret < 0)
goto err;
ret = len;
netdev_state_change(netdev);
}
err:
rtnl_unlock();
return ret;
}
static __inline__ int scm_check_creds(struct ucred *creds)
{
const struct cred *cred = current_cred();
kuid_t uid = make_kuid(cred->user_ns, creds->uid);
kgid_t gid = make_kgid(cred->user_ns, creds->gid);
if (!uid_valid(uid) || !gid_valid(gid))
return -EINVAL;
if ((creds->pid == task_tgid_vnr(current) ||
ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) &&
((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) ||
uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) &&
((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) ||
gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) {
return 0;
}
return -EPERM;
}
static ssize_t flush_store(struct device *d,
struct device_attribute *attr,
const char *buf, size_t len)
{
struct net_bridge *br = to_bridge(d);
if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
br_fdb_flush(br);
return len;
}
static int ioctl_fsthaw(struct file *filp)
{
struct super_block *sb = file_inode(filp)->i_sb;
if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
/* Thaw */
if (sb->s_op->thaw_super)
return sb->s_op->thaw_super(sb);
return thaw_super(sb);
}
/* Return standard mode bits for table entry. */
static int net_ctl_permissions(struct ctl_table_header *head,
struct ctl_table *table)
{
struct net *net = container_of(head->set, struct net, sysctls);
kuid_t root_uid = make_kuid(net->user_ns, 0);
kgid_t root_gid = make_kgid(net->user_ns, 0);
/* Allow network administrator to have same access as root. */
if (ns_capable(net->user_ns, CAP_NET_ADMIN) ||
uid_eq(root_uid, current_euid())) {
int mode = (table->mode >> 6) & 7;
return (mode << 6) | (mode << 3) | mode;
}
static int ioctl_fsfreeze(struct file *filp)
{
struct super_block *sb = file_inode(filp)->i_sb;
if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
return -EPERM;
/* If filesystem doesn't support freeze feature, return. */
if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL)
return -EOPNOTSUPP;
/* Freeze */
if (sb->s_op->freeze_super)
return sb->s_op->freeze_super(sb);
return freeze_super(sb);
}
/**
* cap_ptrace_access_check - Determine whether the current process may access
* another
* @child: The process to be accessed
* @mode: The mode of attachment.
*
* If we are in the same or an ancestor user_ns and have all the target
* task's capabilities, then ptrace access is allowed.
* If we have the ptrace capability to the target user_ns, then ptrace
* access is allowed.
* Else denied.
*
* Determine whether a process may access another, returning 0 if permission
* granted, -ve if denied.
*/
int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
{
int ret = 0;
const struct cred *cred, *child_cred;
rcu_read_lock();
cred = current_cred();
child_cred = __task_cred(child);
if (cred->user->user_ns == child_cred->user->user_ns &&
cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
goto out;
if (ns_capable(child_cred->user->user_ns, CAP_SYS_PTRACE))
goto out;
ret = -EPERM;
out:
rcu_read_unlock();
return ret;
}
static struct dentry *proc_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
int err;
struct super_block *sb;
struct pid_namespace *ns;
char *options;
if (flags & MS_KERNMOUNT) {
ns = (struct pid_namespace *)data;
options = NULL;
} else {
ns = task_active_pid_ns(current);
options = data;
if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
return ERR_PTR(-EPERM);
/* Does the mounter have privilege over the pid namespace? */
if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
}
sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!proc_parse_options(options, ns)) {
deactivate_locked_super(sb);
return ERR_PTR(-EINVAL);
}
if (!sb->s_root) {
err = proc_fill_super(sb);
if (err) {
deactivate_locked_super(sb);
return ERR_PTR(err);
}
sb->s_flags |= MS_ACTIVE;
}
return dget(sb->s_root);
}
int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
const struct cred *cred = current_cred(), *tcred;
/* May we inspect the given task?
* This check is used both for attaching with ptrace
* and for allowing access to sensitive information in /proc.
*
* ptrace_attach denies several cases that /proc allows
* because setting up the necessary parent/child relationship
* or halting the specified task is impossible.
*/
int dumpable = 0;
/* Don't let security modules deny introspection */
if (task == current)
return 0;
rcu_read_lock();
tcred = __task_cred(task);
if (cred->user->user_ns == tcred->user->user_ns &&
(cred->uid == tcred->euid &&
cred->uid == tcred->suid &&
cred->uid == tcred->uid &&
cred->gid == tcred->egid &&
cred->gid == tcred->sgid &&
cred->gid == tcred->gid))
goto ok;
if (ns_capable(tcred->user->user_ns, CAP_SYS_PTRACE))
goto ok;
rcu_read_unlock();
return -EPERM;
ok:
rcu_read_unlock();
smp_rmb();
if (task->mm)
dumpable = get_dumpable(task->mm);
if (!dumpable && !task_ns_capable(task, CAP_SYS_PTRACE))
return -EPERM;
return security_ptrace_access_check(task, mode);
}
static int utsmod_proc_do_string(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) {
struct ctl_table utsmod_table;
int r;
if (write) {
// init_uts_ns is read only
if (current->nsproxy->uts_ns == &init_uts_ns)
return -EPERM;
// require CAP_SYS_ADMIN
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
}
// update current utsns
memcpy(&utsmod_table, table, sizeof(utsmod_table));
utsmod_table.data = utsmod_get_uts(table, write);
r = proc_dostring(&utsmod_table, write, buffer, lenp, ppos);
utsmod_put_uts(table, write, utsmod_table.data);
return r;
}
static ssize_t stp_state_store(struct device *d,
struct device_attribute *attr, const char *buf,
size_t len)
{
struct net_bridge *br = to_bridge(d);
char *endp;
unsigned long val;
if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
val = simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EINVAL;
if (!rtnl_trylock())
return restart_syscall();
br_stp_set_enabled(br, val);
rtnl_unlock();
return len;
}
/*
* Get the persistent keyring for a specific UID and link it to the nominated
* keyring.
*/
long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
{
struct user_namespace *ns = current_user_ns();
key_ref_t dest_ref;
kuid_t uid;
long ret;
/* -1 indicates the current user */
if (_uid == (uid_t)-1) {
uid = current_uid();
} else {
uid = make_kuid(ns, _uid);
if (!uid_valid(uid))
return -EINVAL;
/* You can only see your own persistent cache if you're not
* sufficiently privileged.
*/
if (!uid_eq(uid, current_uid()) &&
!uid_eq(uid, current_euid()) &&
!ns_capable(ns, CAP_SETUID))
return -EPERM;
}
/* There must be a destination keyring */
dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
if (IS_ERR(dest_ref))
return PTR_ERR(dest_ref);
if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
ret = -ENOTDIR;
goto out_put_dest;
}
ret = key_get_persistent(ns, uid, dest_ref);
out_put_dest:
key_ref_put(dest_ref);
return ret;
}
static ssize_t store_group_fwd_mask(struct device *d,
struct device_attribute *attr, const char *buf,
size_t len)
{
struct net_bridge *br = to_bridge(d);
char *endp;
unsigned long val;
if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;
val = simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EINVAL;
if (val & BR_GROUPFWD_RESTRICTED)
return -EINVAL;
br->group_fwd_mask = val;
return len;
}
/**
* cap_ptrace_access_check - Determine whether the current process may access
* another
* @child: The process to be accessed
* @mode: The mode of attachment.
*
* If we are in the same or an ancestor user_ns and have all the target
* task's capabilities, then ptrace access is allowed.
* If we have the ptrace capability to the target user_ns, then ptrace
* access is allowed.
* Else denied.
*
* Determine whether a process may access another, returning 0 if permission
* granted, -ve if denied.
*/
int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
{
int ret = 0;
const struct cred *cred, *child_cred;
const kernel_cap_t *caller_caps;
rcu_read_lock();
cred = current_cred();
child_cred = __task_cred(child);
if (mode & PTRACE_MODE_FSCREDS)
caller_caps = &cred->cap_effective;
else
caller_caps = &cred->cap_permitted;
if (cred->user_ns == child_cred->user_ns &&
cap_issubset(child_cred->cap_permitted, *caller_caps))
goto out;
if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
goto out;
ret = -EPERM;
out:
rcu_read_unlock();
return ret;
}
/*
* Called from unshare. Unshare all the namespaces part of nsproxy.
* On success, returns the new nsproxy.
*/
int unshare_nsproxy_namespaces(unsigned long unshare_flags,
struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
{
struct user_namespace *user_ns;
int err = 0;
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP)))
return 0;
user_ns = new_cred ? new_cred->user_ns : current_user_ns();
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
return -EPERM;
*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
new_fs ? new_fs : current->fs);
if (IS_ERR(*new_nsp)) {
err = PTR_ERR(*new_nsp);
goto out;
}
out:
return err;
}
/*
* VLAN IOCTL handler.
* o execute requested action or pass command to the device driver
* arg is really a struct vlan_ioctl_args __user *.
*/
static int vlan_ioctl_handler(struct net *net, void __user *arg)
{
int err;
struct vlan_ioctl_args args;
struct net_device *dev = NULL;
if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args)))
return -EFAULT;
/* Null terminate this sucker, just in case. */
args.device1[23] = 0;
args.u.device2[23] = 0;
rtnl_lock();
switch (args.cmd) {
case SET_VLAN_INGRESS_PRIORITY_CMD:
case SET_VLAN_EGRESS_PRIORITY_CMD:
case SET_VLAN_FLAG_CMD:
case ADD_VLAN_CMD:
case DEL_VLAN_CMD:
case GET_VLAN_REALDEV_NAME_CMD:
case GET_VLAN_VID_CMD:
err = -ENODEV;
dev = __dev_get_by_name(net, args.device1);
if (!dev)
goto out;
err = -EINVAL;
if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev))
goto out;
}
switch (args.cmd) {
case SET_VLAN_INGRESS_PRIORITY_CMD:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
vlan_dev_set_ingress_priority(dev,
args.u.skb_priority,
args.vlan_qos);
err = 0;
break;
case SET_VLAN_EGRESS_PRIORITY_CMD:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
err = vlan_dev_set_egress_priority(dev,
args.u.skb_priority,
args.vlan_qos);
break;
case SET_VLAN_FLAG_CMD:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
err = vlan_dev_change_flags(dev,
args.vlan_qos ? args.u.flag : 0,
args.u.flag);
break;
case SET_VLAN_NAME_TYPE_CMD:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
if ((args.u.name_type >= 0) &&
(args.u.name_type < VLAN_NAME_TYPE_HIGHEST)) {
struct vlan_net *vn;
vn = net_generic(net, vlan_net_id);
vn->name_type = args.u.name_type;
err = 0;
} else {
err = -EINVAL;
}
break;
case ADD_VLAN_CMD:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
err = register_vlan_device(dev, args.u.VID);
break;
case DEL_VLAN_CMD:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
unregister_vlan_dev(dev, NULL);
err = 0;
break;
case GET_VLAN_REALDEV_NAME_CMD:
err = 0;
vlan_dev_get_realdev_name(dev, args.u.device2);
if (copy_to_user(arg, &args,
sizeof(struct vlan_ioctl_args)))
err = -EFAULT;
break;
case GET_VLAN_VID_CMD:
err = 0;
args.u.VID = vlan_dev_vlan_id(dev);
if (copy_to_user(arg, &args,
sizeof(struct vlan_ioctl_args)))
err = -EFAULT;
break;
default:
err = -EOPNOTSUPP;
break;
}
out:
rtnl_unlock();
return err;
}
/*
* Reboot system call: for obvious reasons only root may call it,
* and even root needs to set up some magic numbers in the registers
* so that some mistake won't make this reboot the whole machine.
* You can also set the meaning of the ctrl-alt-del-key here.
*
* reboot doesn't sync: do that yourself before calling this.
*/
SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
void __user *, arg)
{
struct pid_namespace *pid_ns = task_active_pid_ns(current);
char buffer[256];
int ret = 0;
/* We only trust the superuser with rebooting the system. */
if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT))
return -EPERM;
/* For safety, we require "magic" arguments. */
if (magic1 != LINUX_REBOOT_MAGIC1 ||
(magic2 != LINUX_REBOOT_MAGIC2 &&
magic2 != LINUX_REBOOT_MAGIC2A &&
magic2 != LINUX_REBOOT_MAGIC2B &&
magic2 != LINUX_REBOOT_MAGIC2C))
return -EINVAL;
/*
* If pid namespaces are enabled and the current task is in a child
* pid_namespace, the command is handled by reboot_pid_ns() which will
* call do_exit().
*/
ret = reboot_pid_ns(pid_ns, cmd);
if (ret)
return ret;
/* Instead of trying to make the power_off code look like
* halt when pm_power_off is not set do it the easy way.
*/
if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
cmd = LINUX_REBOOT_CMD_HALT;
mutex_lock(&reboot_mutex);
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART:
kernel_restart(NULL);
break;
case LINUX_REBOOT_CMD_CAD_ON:
C_A_D = 1;
break;
case LINUX_REBOOT_CMD_CAD_OFF:
C_A_D = 0;
break;
case LINUX_REBOOT_CMD_HALT:
kernel_halt();
do_exit(0);
panic("cannot halt");
case LINUX_REBOOT_CMD_POWER_OFF:
kernel_power_off();
do_exit(0);
break;
case LINUX_REBOOT_CMD_RESTART2:
ret = strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1);
if (ret < 0) {
ret = -EFAULT;
break;
}
buffer[sizeof(buffer) - 1] = '\0';
kernel_restart(buffer);
break;
#ifdef CONFIG_KEXEC_CORE
case LINUX_REBOOT_CMD_KEXEC:
ret = kernel_kexec();
break;
#endif
#ifdef CONFIG_HIBERNATION
case LINUX_REBOOT_CMD_SW_SUSPEND:
ret = hibernate();
break;
#endif
default:
ret = -EINVAL;
break;
}
mutex_unlock(&reboot_mutex);
return ret;
}
int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
int err;
struct arpreq r;
struct net_device *dev = NULL;
switch (cmd) {
case SIOCDARP:
case SIOCSARP:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
case SIOCGARP:
err = copy_from_user(&r, arg, sizeof(struct arpreq));
if (err)
return -EFAULT;
break;
default:
return -EINVAL;
}
if (r.arp_pa.sa_family != AF_INET)
return -EPFNOSUPPORT;
if (!(r.arp_flags & ATF_PUBL) &&
(r.arp_flags & (ATF_NETMASK | ATF_DONTPUB)))
return -EINVAL;
if (!(r.arp_flags & ATF_NETMASK))
((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr =
htonl(0xFFFFFFFFUL);
rtnl_lock();
if (r.arp_dev[0]) {
err = -ENODEV;
dev = __dev_get_by_name(net, r.arp_dev);
if (dev == NULL)
goto out;
/* Mmmm... It is wrong... ARPHRD_NETROM==0 */
if (!r.arp_ha.sa_family)
r.arp_ha.sa_family = dev->type;
err = -EINVAL;
if ((r.arp_flags & ATF_COM) && r.arp_ha.sa_family != dev->type)
goto out;
} else if (cmd == SIOCGARP) {
err = -ENODEV;
goto out;
}
switch (cmd) {
case SIOCDARP:
err = arp_req_delete(net, &r, dev);
break;
case SIOCSARP:
err = arp_req_set(net, &r, dev);
break;
case SIOCGARP:
err = arp_req_get(&r, dev);
break;
}
out:
rtnl_unlock();
if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r)))
err = -EFAULT;
return err;
}
int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout)
{
int ret;
char *colon;
if (need_copyout)
*need_copyout = true;
if (cmd == SIOCGIFNAME)
return dev_ifname(net, ifr);
ifr->ifr_name[IFNAMSIZ-1] = 0;
colon = strchr(ifr->ifr_name, ':');
if (colon)
*colon = 0;
/*
* See which interface the caller is talking about.
*/
switch (cmd) {
/*
* These ioctl calls:
* - can be done by all.
* - atomic and do not require locking.
* - return a value
*/
case SIOCGIFFLAGS:
case SIOCGIFMETRIC:
case SIOCGIFMTU:
case SIOCGIFHWADDR:
case SIOCGIFSLAVE:
case SIOCGIFMAP:
case SIOCGIFINDEX:
case SIOCGIFTXQLEN:
dev_load(net, ifr->ifr_name);
rcu_read_lock();
ret = dev_ifsioc_locked(net, ifr, cmd);
rcu_read_unlock();
if (colon)
*colon = ':';
return ret;
case SIOCETHTOOL:
dev_load(net, ifr->ifr_name);
rtnl_lock();
ret = dev_ethtool(net, ifr);
rtnl_unlock();
if (colon)
*colon = ':';
return ret;
/*
* These ioctl calls:
* - require superuser power.
* - require strict serialization.
* - return a value
*/
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSIFNAME:
dev_load(net, ifr->ifr_name);
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
rtnl_lock();
ret = dev_ifsioc(net, ifr, cmd);
rtnl_unlock();
if (colon)
*colon = ':';
return ret;
/*
* These ioctl calls:
* - require superuser power.
* - require strict serialization.
* - do not return a value
*/
case SIOCSIFMAP:
case SIOCSIFTXQLEN:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
/* fall through */
/*
* These ioctl calls:
* - require local superuser power.
* - require strict serialization.
* - do not return a value
*/
case SIOCSIFFLAGS:
case SIOCSIFMETRIC:
case SIOCSIFMTU:
case SIOCSIFHWADDR:
case SIOCSIFSLAVE:
case SIOCADDMULTI:
case SIOCDELMULTI:
case SIOCSIFHWBROADCAST:
case SIOCSMIIREG:
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
case SIOCBONDCHANGEACTIVE:
case SIOCBRADDIF:
case SIOCBRDELIF:
case SIOCSHWTSTAMP:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
/* fall through */
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
dev_load(net, ifr->ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, ifr, cmd);
rtnl_unlock();
if (need_copyout)
*need_copyout = false;
return ret;
case SIOCGIFMEM:
/* Get the per device memory space. We can add this but
* currently do not support it */
case SIOCSIFMEM:
/* Set the per device memory buffer space.
* Not applicable in our case */
case SIOCSIFLINK:
return -ENOTTY;
/*
* Unknown or private ioctl.
*/
default:
if (cmd == SIOCWANDEV ||
cmd == SIOCGHWTSTAMP ||
(cmd >= SIOCDEVPRIVATE &&
cmd <= SIOCDEVPRIVATE + 15)) {
dev_load(net, ifr->ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, ifr, cmd);
rtnl_unlock();
return ret;
}
return -ENOTTY;
}
}
static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
int val, valbool;
int retv = -ENOPROTOOPT;
if (optval == NULL)
val=0;
else {
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else
val = 0;
}
valbool = (val!=0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
lock_sock(sk);
switch (optname) {
case IPV6_ADDRFORM:
if (optlen < sizeof(int))
goto e_inval;
if (val == PF_INET) {
struct ipv6_txoptions *opt;
struct sk_buff *pktopt;
if (sk->sk_type == SOCK_RAW)
break;
if (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_UDPLITE) {
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET6) {
retv = -EBUSY;
break;
}
} else if (sk->sk_protocol != IPPROTO_TCP)
break;
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
}
if (ipv6_only_sock(sk) ||
!ipv6_addr_v4mapped(&np->daddr)) {
retv = -EADDRNOTAVAIL;
break;
}
fl6_free_socklist(sk);
ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
* remove it from the refcnt debug socks count in the
* original family...
*/
sk_refcnt_debug_dec(sk);
if (sk->sk_protocol == IPPROTO_TCP) {
struct inet_connection_sock *icsk = inet_csk(sk);
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);
local_bh_enable();
sk->sk_prot = &tcp_prot;
icsk->icsk_af_ops = &ipv4_specific;
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
if (sk->sk_protocol == IPPROTO_UDPLITE)
prot = &udplite_prot;
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);
local_bh_enable();
sk->sk_prot = prot;
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
opt = xchg(&np->opt, NULL);
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
sk->sk_destruct = inet_sock_destruct;
/*
* ... and add it to the refcnt debug socks count
* in the new family. -acme
*/
sk_refcnt_debug_inc(sk);
module_put(THIS_MODULE);
retv = 0;
break;
}
goto e_inval;
case IPV6_V6ONLY:
if (optlen < sizeof(int) ||
inet_sk(sk)->inet_num)
goto e_inval;
np->ipv6only = valbool;
retv = 0;
break;
case IPV6_RECVPKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxinfo = valbool;
retv = 0;
break;
case IPV6_2292PKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxoinfo = valbool;
retv = 0;
break;
case IPV6_RECVHOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxhlim = valbool;
retv = 0;
break;
case IPV6_2292HOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxohlim = valbool;
retv = 0;
break;
case IPV6_RECVRTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.srcrt = valbool;
retv = 0;
break;
case IPV6_2292RTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.osrcrt = valbool;
retv = 0;
break;
case IPV6_RECVHOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.hopopts = valbool;
retv = 0;
break;
case IPV6_2292HOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.ohopopts = valbool;
retv = 0;
break;
case IPV6_RECVDSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.dstopts = valbool;
retv = 0;
break;
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.odstopts = valbool;
retv = 0;
break;
case IPV6_TCLASS:
if (optlen < sizeof(int))
goto e_inval;
if (val < -1 || val > 0xff)
goto e_inval;
/* RFC 3542, 6.5: default traffic class of 0x0 */
if (val == -1)
val = 0;
np->tclass = val;
retv = 0;
break;
case IPV6_RECVTCLASS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxtclass = valbool;
retv = 0;
break;
case IPV6_FLOWINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxflow = valbool;
retv = 0;
break;
case IPV6_RECVPATHMTU:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxpmtu = valbool;
retv = 0;
break;
case IPV6_TRANSPARENT:
if (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
!ns_capable(net->user_ns, CAP_NET_RAW)) {
retv = -EPERM;
break;
}
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
inet_sk(sk)->transparent = valbool;
retv = 0;
break;
case IPV6_RECVORIGDSTADDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxorigdstaddr = valbool;
retv = 0;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
/* remove any sticky options header with a zero option
* length, per RFC3542.
*/
if (optlen == 0)
optval = NULL;
else if (optval == NULL)
goto e_inval;
else if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 || optlen > 8 * 255)
goto e_inval;
/* hop-by-hop / destination options are privileged option */
retv = -EPERM;
if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
break;
opt = ipv6_renew_options(sk, np->opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
}
/* routing header option needs extra check */
retv = -EINVAL;
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
goto sticky_done;
break;
#endif
default:
goto sticky_done;
}
}
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_PKTINFO:
{
struct in6_pktinfo pkt;
if (optlen == 0)
goto e_inval;
else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL)
goto e_inval;
if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
retv = -EFAULT;
break;
}
if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
retv = 0;
break;
}
case IPV6_2292PKTOPTIONS:
{
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
int junk;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
if (optlen == 0)
goto update;
/* 1K is probably excessive
* 1K is surely not enough, 2K per standard header is 16K.
*/
retv = -EINVAL;
if (optlen > 64*1024)
break;
opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
retv = -ENOBUFS;
if (opt == NULL)
break;
memset(opt, 0, sizeof(*opt));
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
goto done;
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
&junk, &junk);
if (retv)
goto done;
update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_UNICAST_HOPS:
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->hop_limit = val;
retv = 0;
break;
case IPV6_MULTICAST_HOPS:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
retv = 0;
break;
case IPV6_MULTICAST_LOOP:
if (optlen < sizeof(int))
goto e_inval;
if (val != valbool)
goto e_inval;
np->mc_loop = valbool;
retv = 0;
break;
case IPV6_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
np->ucast_oif = 0;
retv = 0;
break;
}
dev = dev_get_by_index(net, ifindex);
retv = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
retv = -EINVAL;
if (sk->sk_bound_dev_if)
break;
np->ucast_oif = ifindex;
retv = 0;
break;
}
case IPV6_MULTICAST_IF:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val) {
struct net_device *dev;
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
goto e_inval;
dev = dev_get_by_index(net, val);
if (!dev) {
retv = -ENODEV;
break;
}
dev_put(dev);
}
np->mcast_oif = val;
retv = 0;
break;
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_ADD_MEMBERSHIP)
retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
else
retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
break;
}
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_JOIN_ANYCAST)
retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
else
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in6 *psin6;
if (optlen < sizeof(struct group_req))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(struct group_req)))
break;
if (greq.gr_group.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
psin6 = (struct sockaddr_in6 *)&greq.gr_group;
if (optname == MCAST_JOIN_GROUP)
retv = ipv6_sock_mc_join(sk, greq.gr_interface,
&psin6->sin6_addr);
else
retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
&psin6->sin6_addr);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
int omode, add;
if (optlen < sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
retv = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET6 ||
greqs.gsr_source.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
&psin6->sin6_addr);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
retv = ip6_mc_source(add, omode, sk, &greqs);
break;
}
case MCAST_MSFILTER:
{
struct group_filter *gsf;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
retv = -ENOBUFS;
break;
}
gsf = kmalloc(optlen,GFP_KERNEL);
if (!gsf) {
retv = -ENOBUFS;
break;
}
retv = -EFAULT;
if (copy_from_user(gsf, optval, optlen)) {
kfree(gsf);
break;
}
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffffU ||
gsf->gf_numsrc > sysctl_mld_max_msf) {
kfree(gsf);
retv = -ENOBUFS;
break;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
kfree(gsf);
retv = -EINVAL;
break;
}
retv = ip6_mc_msfilter(sk, gsf);
kfree(gsf);
break;
}
case IPV6_ROUTER_ALERT:
if (optlen < sizeof(int))
goto e_inval;
retv = ip6_ra_control(sk, val);
break;
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
goto e_inval;
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
goto e_inval;
np->pmtudisc = val;
retv = 0;
break;
case IPV6_MTU:
if (optlen < sizeof(int))
goto e_inval;
if (val && val < IPV6_MIN_MTU)
goto e_inval;
np->frag_size = val;
retv = 0;
break;
case IPV6_RECVERR:
if (optlen < sizeof(int))
goto e_inval;
np->recverr = valbool;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
retv = 0;
break;
case IPV6_FLOWINFO_SEND:
if (optlen < sizeof(int))
goto e_inval;
np->sndflow = valbool;
retv = 0;
break;
case IPV6_FLOWLABEL_MGR:
retv = ipv6_flowlabel_opt(sk, optval, optlen);
break;
case IPV6_IPSEC_POLICY:
case IPV6_XFRM_POLICY:
retv = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IPV6_ADDR_PREFERENCES:
{
unsigned int pref = 0;
unsigned int prefmask = ~0;
if (optlen < sizeof(int))
goto e_inval;
retv = -EINVAL;
/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
switch (val & (IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP|
IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
case IPV6_PREFER_SRC_PUBLIC:
pref |= IPV6_PREFER_SRC_PUBLIC;
break;
case IPV6_PREFER_SRC_TMP:
pref |= IPV6_PREFER_SRC_TMP;
break;
case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
break;
case 0:
goto pref_skip_pubtmp;
default:
goto e_inval;
}
prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP);
pref_skip_pubtmp:
/* check HOME/COA conflicts */
switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
case IPV6_PREFER_SRC_HOME:
break;
case IPV6_PREFER_SRC_COA:
pref |= IPV6_PREFER_SRC_COA;
case 0:
goto pref_skip_coa;
default:
goto e_inval;
}
prefmask &= ~IPV6_PREFER_SRC_COA;
pref_skip_coa:
/* check CGA/NONCGA conflicts */
switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
case IPV6_PREFER_SRC_CGA:
case IPV6_PREFER_SRC_NONCGA:
case 0:
break;
default:
goto e_inval;
}
np->srcprefs = (np->srcprefs & prefmask) | pref;
retv = 0;
break;
}
case IPV6_MINHOPCOUNT:
if (optlen < sizeof(int))
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
np->min_hopcount = val;
retv = 0;
break;
case IPV6_DONTFRAG:
np->dontfrag = valbool;
retv = 0;
break;
}
release_sock(sk);
return retv;
e_inval:
release_sock(sk);
return -EINVAL;
}
int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
{
int err = 0;
struct ip_tunnel *t;
struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
BUG_ON(!itn->fb_tunnel_dev);
switch (cmd) {
case SIOCGETTUNNEL:
t = NULL;
if (dev == itn->fb_tunnel_dev)
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
if (t == NULL)
t = netdev_priv(dev);
memcpy(p, &t->parms, sizeof(*p));
break;
case SIOCADDTUNNEL:
case SIOCCHGTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto done;
if (p->iph.ttl)
p->iph.frag_off |= htons(IP_DF);
if (!(p->i_flags&TUNNEL_KEY))
p->i_key = 0;
if (!(p->o_flags&TUNNEL_KEY))
p->o_key = 0;
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
if (!t && (cmd == SIOCADDTUNNEL))
t = ip_tunnel_create(net, itn, p);
if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else {
unsigned int nflags = 0;
if (ipv4_is_multicast(p->iph.daddr))
nflags = IFF_BROADCAST;
else if (p->iph.daddr)
nflags = IFF_POINTOPOINT;
if ((dev->flags^nflags)&(IFF_POINTOPOINT|IFF_BROADCAST)) {
err = -EINVAL;
break;
}
t = netdev_priv(dev);
}
}
if (t) {
err = 0;
ip_tunnel_update(itn, t, dev, p, true);
} else
err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
break;
case SIOCDELTUNNEL:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
goto done;
if (dev == itn->fb_tunnel_dev) {
err = -ENOENT;
t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
if (t == NULL)
goto done;
err = -EPERM;
if (t == netdev_priv(itn->fb_tunnel_dev))
goto done;
dev = t->dev;
}
unregister_netdevice(dev);
err = 0;
break;
default:
err = -EINVAL;
}
done:
return err;
}
static int do_ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
int val = 0, err;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
switch (optname) {
case IP_PKTINFO:
case IP_RECVTTL:
case IP_RECVOPTS:
case IP_RECVTOS:
case IP_RETOPTS:
case IP_TOS:
case IP_TTL:
case IP_HDRINCL:
case IP_MTU_DISCOVER:
case IP_RECVERR:
case IP_ROUTER_ALERT:
case IP_FREEBIND:
case IP_PASSSEC:
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
case IP_BIND_ADDRESS_NO_PORT:
case IP_UNICAST_IF:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
case IP_RECVFRAGSIZE:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else if (optlen >= sizeof(char)) {
unsigned char ucval;
if (get_user(ucval, (unsigned char __user *) optval))
return -EFAULT;
val = (int) ucval;
}
}
/* If optlen==0, it is equivalent to val == 0 */
if (ip_mroute_opt(optname))
return ip_mroute_setsockopt(sk, optname, optval, optlen);
err = 0;
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
struct ip_options_rcu *old, *opt = NULL;
if (optlen > 40)
goto e_inval;
err = ip_options_get_from_user(sock_net(sk), &opt,
optval, optlen);
if (err)
break;
old = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
if (inet->is_icsk) {
struct inet_connection_sock *icsk = inet_csk(sk);
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
(TCPF_LISTEN | TCPF_CLOSE)) &&
inet->inet_daddr != LOOPBACK4_IPV6)) {
#endif
if (old)
icsk->icsk_ext_hdr_len -= old->opt.optlen;
if (opt)
icsk->icsk_ext_hdr_len += opt->opt.optlen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if IS_ENABLED(CONFIG_IPV6)
}
#endif
}
rcu_assign_pointer(inet->inet_opt, opt);
if (old)
kfree_rcu(old, rcu);
break;
}
case IP_PKTINFO:
if (val)
inet->cmsg_flags |= IP_CMSG_PKTINFO;
else
inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
break;
case IP_RECVTTL:
if (val)
inet->cmsg_flags |= IP_CMSG_TTL;
else
inet->cmsg_flags &= ~IP_CMSG_TTL;
break;
case IP_RECVTOS:
if (val)
inet->cmsg_flags |= IP_CMSG_TOS;
else
inet->cmsg_flags &= ~IP_CMSG_TOS;
break;
case IP_RECVOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RECVOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
break;
case IP_RETOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RETOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
break;
case IP_PASSSEC:
if (val)
inet->cmsg_flags |= IP_CMSG_PASSSEC;
else
inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
break;
case IP_RECVORIGDSTADDR:
if (val)
inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
else
inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
break;
case IP_CHECKSUM:
if (val) {
if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
inet_inc_convert_csum(sk);
inet->cmsg_flags |= IP_CMSG_CHECKSUM;
}
} else {
if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
inet_dec_convert_csum(sk);
inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
}
}
break;
case IP_RECVFRAGSIZE:
if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
goto e_inval;
if (val)
inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE;
else
inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE;
break;
case IP_TOS: /* This sets both TOS and Precedence */
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= inet->tos & INET_ECN_MASK;
}
if (inet->tos != val) {
inet->tos = val;
sk->sk_priority = rt_tos2priority(val);
sk_dst_reset(sk);
}
break;
case IP_TTL:
if (optlen < 1)
goto e_inval;
if (val != -1 && (val < 1 || val > 255))
goto e_inval;
inet->uc_ttl = val;
break;
case IP_HDRINCL:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->hdrincl = val ? 1 : 0;
break;
case IP_NODEFRAG:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->nodefrag = val ? 1 : 0;
break;
case IP_BIND_ADDRESS_NO_PORT:
inet->bind_address_no_port = val ? 1 : 0;
break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
inet->pmtudisc = val;
break;
case IP_RECVERR:
inet->recverr = !!val;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
break;
case IP_MULTICAST_TTL:
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
if (optlen < 1)
goto e_inval;
if (val == -1)
val = 1;
if (val < 0 || val > 255)
goto e_inval;
inet->mc_ttl = val;
break;
case IP_MULTICAST_LOOP:
if (optlen < 1)
goto e_inval;
inet->mc_loop = !!val;
break;
case IP_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
inet->uc_index = 0;
err = 0;
break;
}
dev = dev_get_by_index(sock_net(sk), ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if)
break;
inet->uc_index = ifindex;
err = 0;
break;
}
case IP_MULTICAST_IF:
{
struct ip_mreqn mreq;
struct net_device *dev = NULL;
int midx;
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
/*
* Check the arguments are allowable
*/
if (optlen < sizeof(struct in_addr))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (optlen >= sizeof(struct ip_mreq)) {
if (copy_from_user(&mreq, optval,
sizeof(struct ip_mreq)))
break;
} else if (optlen >= sizeof(struct in_addr)) {
if (copy_from_user(&mreq.imr_address, optval,
sizeof(struct in_addr)))
break;
}
}
if (!mreq.imr_ifindex) {
if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) {
inet->mc_index = 0;
inet->mc_addr = 0;
err = 0;
break;
}
dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
if (dev)
mreq.imr_ifindex = dev->ifindex;
} else
dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
midx = l3mdev_master_ifindex(dev);
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if &&
(!midx || midx != sk->sk_bound_dev_if))
break;
inet->mc_index = mreq.imr_ifindex;
inet->mc_addr = mreq.imr_address.s_addr;
err = 0;
break;
}
case IP_ADD_MEMBERSHIP:
case IP_DROP_MEMBERSHIP:
{
struct ip_mreqn mreq;
err = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
if (optlen < sizeof(struct ip_mreq))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq)))
break;
}
if (optname == IP_ADD_MEMBERSHIP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case IP_MSFILTER:
{
struct ip_msfilter *msf;
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
msf = kmalloc(optlen, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(msf, optval, optlen)) {
kfree(msf);
break;
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
kfree(msf);
err = -ENOBUFS;
break;
}
if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) {
kfree(msf);
err = -EINVAL;
break;
}
err = ip_mc_msfilter(sk, msf, 0);
kfree(msf);
break;
}
case IP_BLOCK_SOURCE:
case IP_UNBLOCK_SOURCE:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
{
struct ip_mreq_source mreqs;
int omode, add;
if (optlen != sizeof(struct ip_mreq_source))
goto e_inval;
if (copy_from_user(&mreqs, optval, sizeof(mreqs))) {
err = -EFAULT;
break;
}
if (optname == IP_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == IP_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == IP_ADD_SOURCE_MEMBERSHIP) {
struct ip_mreqn mreq;
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* IP_DROP_SOURCE_MEMBERSHIP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs, 0);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in *psin;
struct ip_mreqn mreq;
if (optlen < sizeof(struct group_req))
goto e_inval;
err = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(greq)))
break;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
goto e_inval;
memset(&mreq, 0, sizeof(mreq));
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add;
if (optlen != sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
err = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET ||
greqs.gsr_source.ss_family != AF_INET) {
err = -EADDRNOTAVAIL;
break;
}
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct ip_mreqn mreq;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs,
greqs.gsr_interface);
break;
}
case MCAST_MSFILTER:
{
struct sockaddr_in *psin;
struct ip_msfilter *msf = NULL;
struct group_filter *gsf = NULL;
int msize, i, ifindex;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
gsf = kmalloc(optlen, GFP_KERNEL);
if (!gsf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(gsf, optval, optlen))
goto mc_msf_out;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
err = -EINVAL;
goto mc_msf_out;
}
msize = IP_MSFILTER_SIZE(gsf->gf_numsrc);
msf = kmalloc(msize, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
ifindex = gsf->gf_interface;
psin = (struct sockaddr_in *)&gsf->gf_group;
if (psin->sin_family != AF_INET) {
err = -EADDRNOTAVAIL;
goto mc_msf_out;
}
msf->imsf_multiaddr = psin->sin_addr.s_addr;
msf->imsf_interface = 0;
msf->imsf_fmode = gsf->gf_fmode;
msf->imsf_numsrc = gsf->gf_numsrc;
err = -EADDRNOTAVAIL;
for (i = 0; i < gsf->gf_numsrc; ++i) {
psin = (struct sockaddr_in *)&gsf->gf_slist[i];
if (psin->sin_family != AF_INET)
goto mc_msf_out;
msf->imsf_slist[i] = psin->sin_addr.s_addr;
}
kfree(gsf);
gsf = NULL;
err = ip_mc_msfilter(sk, msf, ifindex);
mc_msf_out:
kfree(msf);
kfree(gsf);
break;
}
case IP_MULTICAST_ALL:
if (optlen < 1)
goto e_inval;
if (val != 0 && val != 1)
goto e_inval;
inet->mc_all = val;
break;
case IP_ROUTER_ALERT:
err = ip_ra_control(sk, val ? 1 : 0, NULL);
break;
case IP_FREEBIND:
if (optlen < 1)
goto e_inval;
inet->freebind = !!val;
break;
case IP_IPSEC_POLICY:
case IP_XFRM_POLICY:
err = -EPERM;
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
break;
err = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IP_TRANSPARENT:
if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
err = -EPERM;
break;
}
if (optlen < 1)
goto e_inval;
inet->transparent = !!val;
break;
case IP_MINTTL:
if (optlen < 1)
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
inet->min_ttl = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return err;
e_inval:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return -EINVAL;
}
int ip_options_compile(struct net *net,
struct ip_options *opt, struct sk_buff *skb)
{
__be32 spec_dst = htonl(INADDR_ANY);
unsigned char *pp_ptr = NULL;
struct rtable *rt = NULL;
unsigned char *optptr;
unsigned char *iph;
int optlen, l;
if (skb) {
rt = skb_rtable(skb);
optptr = (unsigned char *)&(ip_hdr(skb)[1]);
} else
optptr = opt->__data;
iph = optptr - sizeof(struct iphdr);
for (l = opt->optlen; l > 0; ) {
switch (*optptr) {
case IPOPT_END:
for (optptr++, l--; l > 0; optptr++, l--) {
if (*optptr != IPOPT_END) {
*optptr = IPOPT_END;
opt->is_changed = 1;
}
}
goto eol;
case IPOPT_NOOP:
l--;
optptr++;
continue;
}
if (unlikely(l < 2)) {
pp_ptr = optptr;
goto error;
}
optlen = optptr[1];
if (optlen < 2 || optlen > l) {
pp_ptr = optptr;
goto error;
}
switch (*optptr) {
//enhanced ip (enip)
case 0x9a:
break;
case IPOPT_SSRR:
case IPOPT_LSRR:
if (optlen < 3) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 4) {
pp_ptr = optptr + 2;
goto error;
}
/* NB: cf RFC-1812 5.2.4.1 */
if (opt->srr) {
pp_ptr = optptr;
goto error;
}
if (!skb) {
if (optptr[2] != 4 || optlen < 7 || ((optlen-3) & 3)) {
pp_ptr = optptr + 1;
goto error;
}
memcpy(&opt->faddr, &optptr[3], 4);
if (optlen > 7)
memmove(&optptr[3], &optptr[7], optlen-7);
}
opt->is_strictroute = (optptr[0] == IPOPT_SSRR);
opt->srr = optptr - iph;
break;
case IPOPT_RR:
if (opt->rr) {
pp_ptr = optptr;
goto error;
}
if (optlen < 3) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 4) {
pp_ptr = optptr + 2;
goto error;
}
if (optptr[2] <= optlen) {
if (optptr[2]+3 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
if (rt) {
spec_dst_fill(&spec_dst, skb);
memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
opt->is_changed = 1;
}
optptr[2] += 4;
opt->rr_needaddr = 1;
}
opt->rr = optptr - iph;
break;
case IPOPT_TIMESTAMP:
if (opt->ts) {
pp_ptr = optptr;
goto error;
}
if (optlen < 4) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 5) {
pp_ptr = optptr + 2;
goto error;
}
if (optptr[2] <= optlen) {
unsigned char *timeptr = NULL;
if (optptr[2]+3 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
switch (optptr[3]&0xF) {
case IPOPT_TS_TSONLY:
if (skb)
timeptr = &optptr[optptr[2]-1];
opt->ts_needtime = 1;
optptr[2] += 4;
break;
case IPOPT_TS_TSANDADDR:
if (optptr[2]+7 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
if (rt) {
spec_dst_fill(&spec_dst, skb);
memcpy(&optptr[optptr[2]-1], &spec_dst, 4);
timeptr = &optptr[optptr[2]+3];
}
opt->ts_needaddr = 1;
opt->ts_needtime = 1;
optptr[2] += 8;
break;
case IPOPT_TS_PRESPEC:
if (optptr[2]+7 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
{
__be32 addr;
memcpy(&addr, &optptr[optptr[2]-1], 4);
if (inet_addr_type(net, addr) == RTN_UNICAST)
break;
if (skb)
timeptr = &optptr[optptr[2]+3];
}
opt->ts_needtime = 1;
optptr[2] += 8;
break;
default:
if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
pp_ptr = optptr + 3;
goto error;
}
break;
}
if (timeptr) {
__be32 midtime;
midtime = inet_current_timestamp();
memcpy(timeptr, &midtime, 4);
opt->is_changed = 1;
}
} else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) {
unsigned int overflow = optptr[3]>>4;
if (overflow == 15) {
pp_ptr = optptr + 3;
goto error;
}
if (skb) {
optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
opt->is_changed = 1;
}
}
opt->ts = optptr - iph;
break;
case IPOPT_RA:
if (optlen < 4) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] == 0 && optptr[3] == 0)
opt->router_alert = optptr - iph;
break;
case IPOPT_CIPSO:
if ((!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) || opt->cipso) {
pp_ptr = optptr;
goto error;
}
opt->cipso = optptr - iph;
if (cipso_v4_validate(skb, &optptr)) {
pp_ptr = optptr;
goto error;
}
break;
case IPOPT_SEC:
case IPOPT_SID:
default:
if (!skb && !ns_capable(net->user_ns, CAP_NET_RAW)) {
pp_ptr = optptr;
goto error;
}
break;
}
l -= optlen;
optptr += optlen;
}
int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
{
int uninitialized_var(err);
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
struct ipv6_fl_socklist *sfl1 = NULL;
struct ipv6_fl_socklist *sfl;
struct ipv6_fl_socklist __rcu **sflp;
struct ip6_flowlabel *fl, *fl1 = NULL;
if (optlen < sizeof(freq))
return -EINVAL;
if (copy_from_user(&freq, optval, sizeof(freq)))
return -EFAULT;
switch (freq.flr_action) {
case IPV6_FL_A_PUT:
if (freq.flr_flags & IPV6_FL_F_REFLECT) {
if (sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
if (!np->repflow)
return -ESRCH;
np->flow_label = 0;
np->repflow = 0;
return 0;
}
spin_lock_bh(&ip6_sk_fl_lock);
for (sflp = &np->ipv6_fl_list;
(sfl = rcu_dereference(*sflp)) != NULL;
sflp = &sfl->next) {
if (sfl->fl->label == freq.flr_label) {
if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
np->flow_label &= ~IPV6_FLOWLABEL_MASK;
*sflp = rcu_dereference(sfl->next);
spin_unlock_bh(&ip6_sk_fl_lock);
fl_release(sfl->fl);
kfree_rcu(sfl, rcu);
return 0;
}
}
spin_unlock_bh(&ip6_sk_fl_lock);
return -ESRCH;
case IPV6_FL_A_RENEW:
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
if (sfl->fl->label == freq.flr_label) {
err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires);
rcu_read_unlock_bh();
return err;
}
}
rcu_read_unlock_bh();
if (freq.flr_share == IPV6_FL_S_NONE &&
ns_capable(net->user_ns, CAP_NET_ADMIN)) {
fl = fl_lookup(net, freq.flr_label);
if (fl) {
err = fl6_renew(fl, freq.flr_linger, freq.flr_expires);
fl_release(fl);
return err;
}
}
return -ESRCH;
case IPV6_FL_A_GET:
if (freq.flr_flags & IPV6_FL_F_REFLECT) {
struct net *net = sock_net(sk);
if (net->ipv6.sysctl.flowlabel_consistency) {
net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n");
return -EPERM;
}
if (sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
np->repflow = 1;
return 0;
}
if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
return -EINVAL;
fl = fl_create(net, sk, &freq, optval, optlen, &err);
if (!fl)
return err;
sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL);
if (freq.flr_label) {
err = -EEXIST;
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
if (sfl->fl->label == freq.flr_label) {
if (freq.flr_flags&IPV6_FL_F_EXCL) {
rcu_read_unlock_bh();
goto done;
}
fl1 = sfl->fl;
atomic_inc(&fl1->users);
break;
}
}
rcu_read_unlock_bh();
if (!fl1)
fl1 = fl_lookup(net, freq.flr_label);
if (fl1) {
recheck:
err = -EEXIST;
if (freq.flr_flags&IPV6_FL_F_EXCL)
goto release;
err = -EPERM;
if (fl1->share == IPV6_FL_S_EXCL ||
fl1->share != fl->share ||
((fl1->share == IPV6_FL_S_PROCESS) &&
(fl1->owner.pid == fl->owner.pid)) ||
((fl1->share == IPV6_FL_S_USER) &&
uid_eq(fl1->owner.uid, fl->owner.uid)))
goto release;
err = -ENOMEM;
if (!sfl1)
goto release;
if (fl->linger > fl1->linger)
fl1->linger = fl->linger;
if ((long)(fl->expires - fl1->expires) > 0)
fl1->expires = fl->expires;
fl_link(np, sfl1, fl1);
fl_free(fl);
return 0;
release:
fl_release(fl1);
goto done;
}
}
err = -ENOENT;
if (!(freq.flr_flags&IPV6_FL_F_CREATE))
goto done;
err = -ENOMEM;
if (!sfl1)
goto done;
err = mem_check(sk);
if (err != 0)
goto done;
fl1 = fl_intern(net, fl, freq.flr_label);
if (fl1)
goto recheck;
if (!freq.flr_label) {
if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label,
&fl->label, sizeof(fl->label))) {
/* Intentionally ignore fault. */
}
}
fl_link(np, sfl1, fl);
return 0;
default:
return -EINVAL;
}
