static void netlink_sock_destruct(struct sock *sk)
{
skb_queue_purge(&sk->sk_receive_queue);
if (!sock_flag(sk, SOCK_DEAD)) {
printk("Freeing alive netlink socket %p\n", sk);
return;
}
BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
BUG_TRAP(!nlk_sk(sk)->cb);
kfree(nlk_sk(sk));
}
static void netlink_overrun(struct sock *sk)
{
if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
sk->sk_err = ENOBUFS;
sk->sk_error_report(sk);
}
}
struct sock *
netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len))
{
struct socket *sock;
struct sock *sk;
if (!nl_table)
return NULL;
if (unit<0 || unit>=MAX_LINKS)
return NULL;
if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
return NULL;
if (netlink_create(sock, unit) < 0) {
sock_release(sock);
return NULL;
}
sk = sock->sk;
sk->sk_data_ready = netlink_data_ready;
if (input)
nlk_sk(sk)->data_ready = input;
if (netlink_insert(sk, 0)) {
sock_release(sock);
return NULL;
}
return sk;
}
static void netlink_data_ready(struct sock *sk, int len)
{
struct netlink_opt *nlk = nlk_sk(sk);
if (nlk->data_ready)
nlk->data_ready(sk, len);
netlink_rcv_wake(sk);
}
static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
struct msghdr *msg, size_t len,
int flags)
{
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct scm_cookie scm;
struct sock *sk = sock->sk;
struct netlink_opt *nlk = nlk_sk(sk);
int noblock = flags&MSG_DONTWAIT;
size_t copied;
struct sk_buff *skb;
int err;
if (flags&MSG_OOB)
return -EOPNOTSUPP;
copied = 0;
skb = skb_recv_datagram(sk,flags,noblock,&err);
if (skb==NULL)
goto out;
msg->msg_namelen = 0;
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
skb->h.raw = skb->data;
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
if (msg->msg_name) {
struct sockaddr_nl *addr = (struct sockaddr_nl*)msg->msg_name;
addr->nl_family = AF_NETLINK;
addr->nl_pad = 0;
addr->nl_pid = NETLINK_CB(skb).pid;
addr->nl_groups = NETLINK_CB(skb).dst_groups;
msg->msg_namelen = sizeof(*addr);
}
if (NULL == siocb->scm) {
memset(&scm, 0, sizeof(scm));
siocb->scm = &scm;
}
siocb->scm->creds = *NETLINK_CREDS(skb);
skb_free_datagram(sk, skb);
if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2)
netlink_dump(sk);
scm_recv(sock, msg, siocb->scm, flags);
out:
netlink_rcv_wake(sk);
return err ? : copied;
}
static inline void netlink_rcv_wake(struct sock *sk)
{
struct netlink_opt *nlk = nlk_sk(sk);
if (!skb_queue_len(&sk->sk_receive_queue))
clear_bit(0, &nlk->state);
if (!test_bit(0, &nlk->state))
wake_up_interruptible(&nlk->wait);
}
static void netlink_remove(struct sock *sk)
{
netlink_table_grab();
nl_table[sk->sk_protocol].hash.entries--;
sk_del_node_init(sk);
if (nlk_sk(sk)->groups)
__sk_del_bind_node(sk);
netlink_table_ungrab();
}
/*
* Attach a skb to a netlink socket.
* The caller must hold a reference to the destination socket. On error, the
* reference is dropped. The skb is not send to the destination, just all
* all error checks are performed and memory in the queue is reserved.
* Return values:
* < 0: error. skb freed, reference to sock dropped.
* 0: continue
* 1: repeat lookup - reference dropped while waiting for socket memory.
*/
int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock,
long timeo, struct sock *ssk)
{
struct netlink_opt *nlk;
nlk = nlk_sk(sk);
#ifdef NL_EMULATE_DEV
if (nlk->handler)
return 0;
#endif
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) {
DECLARE_WAITQUEUE(wait, current);
if (!timeo) {
if (!ssk || nlk_sk(ssk)->pid == 0)
netlink_overrun(sk);
sock_put(sk);
kfree_skb(skb);
return -EAGAIN;
}
__set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&nlk->wait, &wait);
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
test_bit(0, &nlk->state)) &&
!sock_flag(sk, SOCK_DEAD))
timeo = schedule_timeout(timeo);
__set_current_state(TASK_RUNNING);
remove_wait_queue(&nlk->wait, &wait);
sock_put(sk);
if (signal_pending(current)) {
kfree_skb(skb);
return sock_intr_errno(timeo);
}
return 1;
}
skb_orphan(skb);
skb_set_owner_r(skb, sk);
return 0;
}
static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
{
struct netlink_sock *nlk = nlk_sk(sk);
if (nlk->groups == NULL)
return 0;
return nla_put(nlskb, NETLINK_DIAG_GROUPS, NLGRPSZ(nlk->ngroups),
nlk->groups);
}
int netlink_attach(int unit, int (*function)(int, struct sk_buff *skb))
{
struct sock *sk = netlink_kernel_create(unit, NULL);
if (sk == NULL)
return -ENOBUFS;
nlk_sk(sk)->handler = function;
write_lock_bh(&nl_emu_lock);
netlink_kernel[unit] = sk->sk_socket;
write_unlock_bh(&nl_emu_lock);
return 0;
}
struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
{
int protocol = ssk->sk_protocol;
struct sock *sock;
struct netlink_opt *nlk;
sock = netlink_lookup(protocol, pid);
if (!sock)
return ERR_PTR(-ECONNREFUSED);
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
if ((nlk->pid == 0 && !nlk->data_ready) ||
(sock->sk_state == NETLINK_CONNECTED &&
nlk->dst_pid != nlk_sk(ssk)->pid)) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
return sock;
}
static int netlink_insert(struct sock *sk, u32 pid)
{
struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
struct hlist_head *head;
int err = -EADDRINUSE;
struct sock *osk;
struct hlist_node *node;
int len;
netlink_table_grab();
head = nl_pid_hashfn(hash, pid);
len = 0;
sk_for_each(osk, node, head) {
if (nlk_sk(osk)->pid == pid)
break;
len++;
}
if (node)
goto err;
err = -EBUSY;
if (nlk_sk(sk)->pid)
goto err;
err = -ENOMEM;
if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX))
goto err;
if (len && nl_pid_hash_dilute(hash, len))
head = nl_pid_hashfn(hash, pid);
hash->entries++;
nlk_sk(sk)->pid = pid;
sk_add_node(sk, head);
err = 0;
err:
netlink_table_ungrab();
return err;
}
static inline int do_one_set_err(struct sock *sk,
struct netlink_set_err_data *p)
{
struct netlink_opt *nlk = nlk_sk(sk);
if (sk == p->exclude_sk)
goto out;
if (nlk->pid == p->pid || !(nlk->groups & p->group))
goto out;
sk->sk_err = p->code;
sk->sk_error_report(sk);
out:
return 0;
}
static int netlink_dump(struct sock *sk)
{
struct netlink_opt *nlk = nlk_sk(sk);
struct netlink_callback *cb;
struct sk_buff *skb;
struct nlmsghdr *nlh;
int len;
skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
spin_lock(&nlk->cb_lock);
cb = nlk->cb;
if (cb == NULL) {
spin_unlock(&nlk->cb_lock);
kfree_skb(skb);
return -EINVAL;
}
len = cb->dump(skb, cb);
if (len > 0) {
spin_unlock(&nlk->cb_lock);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, len);
return 0;
}
nlh = __nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLMSG_DONE, sizeof(int));
nlh->nlmsg_flags |= NLM_F_MULTI;
memcpy(NLMSG_DATA(nlh), &len, sizeof(len));
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, skb->len);
cb->done(cb);
nlk->cb = NULL;
spin_unlock(&nlk->cb_lock);
netlink_destroy_callback(cb);
sock_put(sk);
return 0;
}
static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr_len, int peer)
{
struct sock *sk = sock->sk;
struct netlink_opt *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr=(struct sockaddr_nl *)addr;
nladdr->nl_family = AF_NETLINK;
nladdr->nl_pad = 0;
*addr_len = sizeof(*nladdr);
if (peer) {
nladdr->nl_pid = nlk->dst_pid;
nladdr->nl_groups = nlk->dst_groups;
} else {
nladdr->nl_pid = nlk->pid;
nladdr->nl_groups = nlk->groups;
}
return 0;
}
static inline int do_one_broadcast(struct sock *sk,
struct netlink_broadcast_data *p)
{
struct netlink_opt *nlk = nlk_sk(sk);
int val;
if (p->exclude_sk == sk)
goto out;
if (nlk->pid == p->pid || !(nlk->groups & p->group))
goto out;
if (p->failure) {
netlink_overrun(sk);
goto out;
}
sock_hold(sk);
if (p->skb2 == NULL) {
if (atomic_read(&p->skb->users) != 1) {
p->skb2 = skb_clone(p->skb, p->allocation);
} else {
p->skb2 = p->skb;
atomic_inc(&p->skb->users);
}
}
if (p->skb2 == NULL) {
netlink_overrun(sk);
/* Clone failed. Notify ALL listeners. */
p->failure = 1;
} else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
netlink_overrun(sk);
} else {
p->congested |= val;
p->delivered = 1;
p->skb2 = NULL;
}
sock_put(sk);
out:
return 0;
}
static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
struct netlink_opt *nlk = nlk_sk(sk);
#ifdef NL_EMULATE_DEV
if (nlk->handler) {
skb_orphan(skb);
nlk->handler(sk->sk_protocol, skb);
return 0;
} else
#endif
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
!test_bit(0, &nlk->state)) {
skb_orphan(skb);
skb_set_owner_r(skb, sk);
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, skb->len);
return atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf;
}
return -1;
}
int netlink_sendskb(struct sock *sk, struct sk_buff *skb, int protocol)
{
struct netlink_opt *nlk;
int len = skb->len;
nlk = nlk_sk(sk);
#ifdef NL_EMULATE_DEV
if (nlk->handler) {
skb_orphan(skb);
len = nlk->handler(protocol, skb);
sock_put(sk);
return len;
}
#endif
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_data_ready(sk, len);
sock_put(sk);
return len;
}
static __inline__ struct sock *netlink_lookup(int protocol, u32 pid)
{
struct nl_pid_hash *hash = &nl_table[protocol].hash;
struct hlist_head *head;
struct sock *sk;
struct hlist_node *node;
read_lock(&nl_table_lock);
head = nl_pid_hashfn(hash, pid);
sk_for_each(sk, node, head) {
if (nlk_sk(sk)->pid == pid) {
sock_hold(sk);
goto found;
}
}
sk = NULL;
found:
read_unlock(&nl_table_lock);
return sk;
}
static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow)
{
unsigned int omask, mask, shift;
size_t osize, size;
struct hlist_head *otable, *table;
int i;
omask = mask = hash->mask;
osize = size = (mask + 1) * sizeof(*table);
shift = hash->shift;
if (grow) {
if (++shift > hash->max_shift)
return 0;
mask = mask * 2 + 1;
size *= 2;
}
table = nl_pid_hash_alloc(size);
if (!table)
return 0;
memset(table, 0, size);
otable = hash->table;
hash->table = table;
hash->mask = mask;
hash->shift = shift;
get_random_bytes(&hash->rnd, sizeof(hash->rnd));
for (i = 0; i <= omask; i++) {
struct sock *sk;
struct hlist_node *node, *tmp;
sk_for_each_safe(sk, node, tmp, &otable[i])
__sk_add_node(sk, nl_pid_hashfn(hash, nlk_sk(sk)->pid));
}
nl_pid_hash_free(otable, osize);
hash->rehash_time = jiffies + 10 * 60 * HZ;
return 1;
}
int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
struct nlmsghdr *nlh,
int (*dump)(struct sk_buff *skb, struct netlink_callback*),
int (*done)(struct netlink_callback*))
{
struct netlink_callback *cb;
struct sock *sk;
struct netlink_opt *nlk;
cb = kmalloc(sizeof(*cb), GFP_KERNEL);
if (cb == NULL)
return -ENOBUFS;
memset(cb, 0, sizeof(*cb));
cb->dump = dump;
cb->done = done;
cb->nlh = nlh;
atomic_inc(&skb->users);
cb->skb = skb;
sk = netlink_lookup(ssk->sk_protocol, NETLINK_CB(skb).pid);
if (sk == NULL) {
netlink_destroy_callback(cb);
return -ECONNREFUSED;
}
nlk = nlk_sk(sk);
/* A dump is in progress... */
spin_lock(&nlk->cb_lock);
if (nlk->cb) {
spin_unlock(&nlk->cb_lock);
netlink_destroy_callback(cb);
sock_put(sk);
return -EBUSY;
}
nlk->cb = cb;
spin_unlock(&nlk->cb_lock);
netlink_dump(sk);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
struct netlink_diag_req *req,
u32 portid, u32 seq, u32 flags, int sk_ino)
{
struct nlmsghdr *nlh;
struct netlink_diag_msg *rep;
struct netlink_sock *nlk = nlk_sk(sk);
nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
flags);
if (!nlh)
return -EMSGSIZE;
rep = nlmsg_data(nlh);
rep->ndiag_family = AF_NETLINK;
rep->ndiag_type = sk->sk_type;
rep->ndiag_protocol = sk->sk_protocol;
rep->ndiag_state = sk->sk_state;
rep->ndiag_ino = sk_ino;
rep->ndiag_portid = nlk->portid;
rep->ndiag_dst_portid = nlk->dst_portid;
rep->ndiag_dst_group = nlk->dst_group;
sock_diag_save_cookie(sk, rep->ndiag_cookie);
if ((req->ndiag_show & NDIAG_SHOW_GROUPS) &&
sk_diag_dump_groups(sk, skb))
goto out_nlmsg_trim;
if ((req->ndiag_show & NDIAG_SHOW_MEMINFO) &&
sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
goto out_nlmsg_trim;
nlmsg_end(skb, nlh);
return 0;
out_nlmsg_trim:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int netlink_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct netlink_opt *nlk;
if (!sk)
return 0;
netlink_remove(sk);
nlk = nlk_sk(sk);
spin_lock(&nlk->cb_lock);
if (nlk->cb) {
nlk->cb->done(nlk->cb);
netlink_destroy_callback(nlk->cb);
nlk->cb = NULL;
__sock_put(sk);
}
spin_unlock(&nlk->cb_lock);
/* OK. Socket is unlinked, and, therefore,
no new packets will arrive */
sock_orphan(sk);
sock->sk = NULL;
wake_up_interruptible_all(&nlk->wait);
skb_queue_purge(&sk->sk_write_queue);
if (nlk->pid && !nlk->groups) {
struct netlink_notify n = {
.protocol = sk->sk_protocol,
.pid = nlk->pid,
};
notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n);
}
sock_put(sk);
return 0;
}
static int netlink_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
struct hlist_head *head;
struct sock *osk;
struct hlist_node *node;
s32 pid = current->pid;
int err;
static s32 rover = -4097;
retry:
cond_resched();
netlink_table_grab();
head = nl_pid_hashfn(hash, pid);
sk_for_each(osk, node, head) {
if (nlk_sk(osk)->pid == pid) {
/* Bind collision, search negative pid values. */
pid = rover--;
if (rover > -4097)
rover = -4097;
netlink_table_ungrab();
goto retry;
}
}
netlink_table_ungrab();
err = netlink_insert(sk, pid);
if (err == -EADDRINUSE)
goto retry;
nlk_sk(sk)->groups = 0;
return 0;
}
static inline int netlink_capable(struct socket *sock, unsigned int flag)
{
return (nl_nonroot[sock->sk->sk_protocol] & flag) ||
capable(CAP_NET_ADMIN);
}
static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
struct sock *sk = sock->sk;
struct netlink_opt *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err;
if (nladdr->nl_family != AF_NETLINK)
return -EINVAL;
/* Only superuser is allowed to listen multicasts */
if (nladdr->nl_groups && !netlink_capable(sock, NL_NONROOT_RECV))
return -EPERM;
if (nlk->pid) {
if (nladdr->nl_pid != nlk->pid)
return -EINVAL;
} else {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
netlink_autobind(sock);
if (err)
return err;
}
if (!nladdr->nl_groups && !nlk->groups)
return 0;
netlink_table_grab();
if (nlk->groups && !nladdr->nl_groups)
__sk_del_bind_node(sk);
else if (!nlk->groups && nladdr->nl_groups)
sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list);
nlk->groups = nladdr->nl_groups;
netlink_table_ungrab();
return 0;
}
static int netlink_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
int err = 0;
struct sock *sk = sock->sk;
struct netlink_opt *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr=(struct sockaddr_nl*)addr;
if (addr->sa_family == AF_UNSPEC) {
sk->sk_state = NETLINK_UNCONNECTED;
nlk->dst_pid = 0;
nlk->dst_groups = 0;
return 0;
}
if (addr->sa_family != AF_NETLINK)
return -EINVAL;
/* Only superuser is allowed to send multicasts */
if (nladdr->nl_groups && !netlink_capable(sock, NL_NONROOT_SEND))
return -EPERM;
if (!nlk->pid)
err = netlink_autobind(sock);
if (err == 0) {
sk->sk_state = NETLINK_CONNECTED;
nlk->dst_pid = nladdr->nl_pid;
nlk->dst_groups = nladdr->nl_groups;
}
return err;
}
static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct msghdr *msg, size_t len)
{
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct sock *sk = sock->sk;
struct netlink_opt *nlk = nlk_sk(sk);
struct sockaddr_nl *addr=msg->msg_name;
u32 dst_pid;
u32 dst_groups;
struct sk_buff *skb;
int err;
struct scm_cookie scm;
if (msg->msg_flags&MSG_OOB)
return -EOPNOTSUPP;
if (NULL == siocb->scm)
siocb->scm = &scm;
err = scm_send(sock, msg, siocb->scm);
if (err < 0)
return err;
if (msg->msg_namelen) {
if (addr->nl_family != AF_NETLINK)
return -EINVAL;
dst_pid = addr->nl_pid;
dst_groups = addr->nl_groups;
if (dst_groups && !netlink_capable(sock, NL_NONROOT_SEND))
return -EPERM;
} else {
dst_pid = nlk->dst_pid;
dst_groups = nlk->dst_groups;
}
if (!nlk->pid) {
err = netlink_autobind(sock);
if (err)
goto out;
}
err = -EMSGSIZE;
if (len > sk->sk_sndbuf - 32)
goto out;
err = -ENOBUFS;
skb = alloc_skb(len, GFP_KERNEL);
if (skb==NULL)
goto out;
NETLINK_CB(skb).pid = nlk->pid;
NETLINK_CB(skb).groups = nlk->groups;
NETLINK_CB(skb).dst_pid = dst_pid;
NETLINK_CB(skb).dst_groups = dst_groups;
memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
/* What can I do? Netlink is asynchronous, so that
we will have to save current capabilities to
check them, when this message will be delivered
to corresponding kernel module. --ANK (980802)
*/
err = -EFAULT;
if (memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len)) {
kfree_skb(skb);
goto out;
}
err = security_netlink_send(sk, skb);
if (err) {
kfree_skb(skb);
goto out;
}
if (dst_groups) {
atomic_inc(&skb->users);
netlink_broadcast(sk, skb, dst_pid, dst_groups, GFP_KERNEL);
}
err = netlink_unicast(sk, skb, dst_pid, msg->msg_flags&MSG_DONTWAIT);
out:
return err;
}
