af_netlink.c

linux 内核源代码

	if (addr->sa_family == AF_UNSPEC) {
		sk->sk_state	= NETLINK_UNCONNECTED;
		nlk->dst_pid	= 0;
		nlk->dst_group  = 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_group  = ffs(nladdr->nl_groups);
	}

	return err;
}

static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr_len, int peer)
{
	struct sock *sk = sock->sk;
	struct netlink_sock *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 = netlink_group_mask(nlk->dst_group);
	} else {
		nladdr->nl_pid = nlk->pid;
		nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
	}
	return 0;
}

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);
	}
}

static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
{
	struct sock *sock;
	struct netlink_sock *nlk;

	sock = netlink_lookup(ssk->sk_net, ssk->sk_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 (sock->sk_state == NETLINK_CONNECTED &&
	    nlk->dst_pid != nlk_sk(ssk)->pid) {
		sock_put(sock);
		return ERR_PTR(-ECONNREFUSED);
	}
	return sock;
}

struct sock *netlink_getsockbyfilp(struct file *filp)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct sock *sock;

	if (!S_ISSOCK(inode->i_mode))
		return ERR_PTR(-ENOTSOCK);

	sock = SOCKET_I(inode)->sk;
	if (sock->sk_family != AF_NETLINK)
		return ERR_PTR(-EINVAL);

	sock_hold(sock);
	return sock;
}

/*
 * 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_sock *nlk;

	nlk = nlk_sk(sk);

	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
	    test_bit(0, &nlk->state)) {
		DECLARE_WAITQUEUE(wait, current);
		if (!*timeo) {
			if (!ssk || netlink_is_kernel(ssk))
				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_set_owner_r(skb, sk);
	return 0;
}

int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
	int len = skb->len;

	skb_queue_tail(&sk->sk_receive_queue, skb);
	sk->sk_data_ready(sk, len);
	sock_put(sk);
	return len;
}

void netlink_detachskb(struct sock *sk, struct sk_buff *skb)
{
	kfree_skb(skb);
	sock_put(sk);
}

static inline struct sk_buff *netlink_trim(struct sk_buff *skb,
					   gfp_t allocation)
{
	int delta;

	skb_orphan(skb);

	delta = skb->end - skb->tail;
	if (delta * 2 < skb->truesize)
		return skb;

	if (skb_shared(skb)) {
		struct sk_buff *nskb = skb_clone(skb, allocation);
		if (!nskb)
			return skb;
		kfree_skb(skb);
		skb = nskb;
	}

	if (!pskb_expand_head(skb, 0, -delta, allocation))
		skb->truesize -= delta;

	return skb;
}

static inline void netlink_rcv_wake(struct sock *sk)
{
	struct netlink_sock *nlk = nlk_sk(sk);

	if (skb_queue_empty(&sk->sk_receive_queue))
		clear_bit(0, &nlk->state);
	if (!test_bit(0, &nlk->state))
		wake_up_interruptible(&nlk->wait);
}

static inline int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb)
{
	int ret;
	struct netlink_sock *nlk = nlk_sk(sk);

	ret = -ECONNREFUSED;
	if (nlk->netlink_rcv != NULL) {
		ret = skb->len;
		skb_set_owner_r(skb, sk);
		nlk->netlink_rcv(skb);
	}
	kfree_skb(skb);
	sock_put(sk);
	return ret;
}

int netlink_unicast(struct sock *ssk, struct sk_buff *skb,
		    u32 pid, int nonblock)
{
	struct sock *sk;
	int err;
	long timeo;

	skb = netlink_trim(skb, gfp_any());

	timeo = sock_sndtimeo(ssk, nonblock);
retry:
	sk = netlink_getsockbypid(ssk, pid);
	if (IS_ERR(sk)) {
		kfree_skb(skb);
		return PTR_ERR(sk);
	}
	if (netlink_is_kernel(sk))
		return netlink_unicast_kernel(sk, skb);

	err = netlink_attachskb(sk, skb, nonblock, &timeo, ssk);
	if (err == 1)
		goto retry;
	if (err)
		return err;

	return netlink_sendskb(sk, skb);
}

int netlink_has_listeners(struct sock *sk, unsigned int group)
{
	int res = 0;
	unsigned long *listeners;

	BUG_ON(!netlink_is_kernel(sk));

	rcu_read_lock();
	listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);

	if (group - 1 < nl_table[sk->sk_protocol].groups)
		res = test_bit(group - 1, listeners);

	rcu_read_unlock();

	return res;
}
EXPORT_SYMBOL_GPL(netlink_has_listeners);

static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
{
	struct netlink_sock *nlk = nlk_sk(sk);

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
	    !test_bit(0, &nlk->state)) {
		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;
}

struct netlink_broadcast_data {
	struct sock *exclude_sk;
	struct net *net;
	u32 pid;
	u32 group;
	int failure;
	int congested;
	int delivered;
	gfp_t allocation;
	struct sk_buff *skb, *skb2;
};

static inline int do_one_broadcast(struct sock *sk,
				   struct netlink_broadcast_data *p)
{
	struct netlink_sock *nlk = nlk_sk(sk);
	int val;

	if (p->exclude_sk == sk)
		goto out;

	if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups ||
	    !test_bit(p->group - 1, nlk->groups))
		goto out;

	if ((sk->sk_net != p->net))
		goto out;

	if (p->failure) {
		netlink_overrun(sk);
		goto out;
	}

	sock_hold(sk);
	if (p->skb2 == NULL) {
		if (skb_shared(p->skb)) {
			p->skb2 = skb_clone(p->skb, p->allocation);
		} else {
			p->skb2 = skb_get(p->skb);
			/*
			 * skb ownership may have been set when
			 * delivered to a previous socket.
			 */
			skb_orphan(p->skb2);
		}
	}
	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;
}

int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
		      u32 group, gfp_t allocation)
{
	struct net *net = ssk->sk_net;
	struct netlink_broadcast_data info;
	struct hlist_node *node;
	struct sock *sk;

	skb = netlink_trim(skb, allocation);

	info.exclude_sk = ssk;
	info.net = net;
	info.pid = pid;
	info.group = group;
	info.failure = 0;
	info.congested = 0;
	info.delivered = 0;
	info.allocation = allocation;
	info.skb = skb;
	info.skb2 = NULL;

	/* While we sleep in clone, do not allow to change socket list */

	netlink_lock_table();

	sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list)
		do_one_broadcast(sk, &info);

	kfree_skb(skb);

	netlink_unlock_table();

	if (info.skb2)
		kfree_skb(info.skb2);

	if (info.delivered) {
		if (info.congested && (allocation & __GFP_WAIT))
			yield();
		return 0;
	}
	if (info.failure)
		return -ENOBUFS;
	return -ESRCH;
}

struct netlink_set_err_data {
	struct sock *exclude_sk;
	u32 pid;
	u32 group;
	int code;
};

static inline int do_one_set_err(struct sock *sk,
				 struct netlink_set_err_data *p)
{
	struct netlink_sock *nlk = nlk_sk(sk);

	if (sk == p->exclude_sk)
		goto out;

	if (sk->sk_net != p->exclude_sk->sk_net)
		goto out;

	if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups ||
	    !test_bit(p->group - 1, nlk->groups))
		goto out;

	sk->sk_err = p->code;
	sk->sk_error_report(sk);
out:
	return 0;
}

void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
{
	struct netlink_set_err_data info;
	struct hlist_node *node;
	struct sock *sk;

	info.exclude_sk = ssk;
	info.pid = pid;
	info.group = group;
	info.code = code;

	read_lock(&nl_table_lock);

	sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list)
		do_one_set_err(sk, &info);

	read_unlock(&nl_table_lock);
}

/* must be called with netlink table grabbed */
static void netlink_update_socket_mc(struct netlink_sock *nlk,
				     unsigned int group,
				     int is_new)
{
	int old, new = !!is_new, subscriptions;

	old = test_bit(group - 1, nlk->groups);
	subscriptions = nlk->subscriptions - old + new;
	if (new)
		__set_bit(group - 1, nlk->groups);
	else
		__clear_bit(group - 1, nlk->groups);
	netlink_update_subscriptions(&nlk->sk, subscriptions);
	netlink_update_listeners(&nlk->sk);
}

static int netlink_setsockopt(struct socket *sock, int level, int optname,
			      char __user *optval, int optlen)
{
	struct sock *sk = sock->sk;
	struct netlink_sock *nlk = nlk_sk(sk);
	unsigned int val = 0;
	int err;

	if (level != SOL_NETLINK)
		return -ENOPROTOOPT;

	if (optlen >= sizeof(int) &&
	    get_user(val, (unsigned int __user *)optval))
		return -EFAULT;

	switch (optname) {
	case NETLINK_PKTINFO:
		if (val)
			nlk->flags |= NETLINK_RECV_PKTINFO;
		else
			nlk->flags &= ~NETLINK_RECV_PKTINFO;
		err = 0;
		break;
	case NETLINK_ADD_MEMBERSHIP:
	case NETLINK_DROP_MEMBERSHIP: {
		if (!netlink_capable(sock, NL_NONROOT_RECV))
			return -EPERM;
		err = netlink_realloc_groups(sk);
		if (err)
			return err;
		if (!val || val - 1 >= nlk->ngroups)
			return -EINVAL;
		netlink_table_grab();
		netlink_update_socket_mc(nlk, val,
					 optname == NETLINK_ADD_MEMBERSHIP);
		netlink_table_ungrab();
		err = 0;
		break;
	}
	default:
		err = -ENOPROTOOPT;
	}
	return err;
}

static int netlink_getsockopt(struct socket *sock, int level, int optname,
			      char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;
	struct netlink_sock *nlk = nlk_sk(sk);
	int len, val, err;

	if (level != SOL_NETLINK)
		return -ENOPROTOOPT;

	if (get_user(len, optlen))
		return -EFAULT;
	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case NETLINK_PKTINFO:
		if (len < sizeof(int))
			return -EINVAL;
		len = sizeof(int);
		val = nlk->flags & NETLINK_RECV_PKTINFO ? 1 : 0;
		if (put_user(len, optlen) ||
		    put_user(val, optval))
			return -EFAULT;
		err = 0;
		break;
	default:
		err = -ENOPROTOOPT;
	}
	return err;
}

static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
{
	struct nl_pktinfo info;

	info.group = NETLINK_CB(skb).dst_group;
	put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info);
}

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_sock *nlk = nlk_sk(sk);
	struct sockaddr_nl *addr=msg->msg_name;
	u32 dst_pid;
	u32 dst_group;
	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_group = ffs(addr->nl_groups);
		if (dst_group && !netlink_capable(sock, NL_NONROOT_SEND))
			return -EPERM;
	} else {
		dst_pid = nlk->dst_pid;
		dst_group = nlk->dst_group;
	}

	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).dst_group = dst_group;
	NETLINK_CB(skb).loginuid = audit_get_loginuid(current->audit_context);
	selinux_get_task_sid(current, &(NETLINK_CB(skb).sid));
	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_group) {
		atomic_inc(&skb->users);
		netlink_broadcast(sk, skb, dst_pid, dst_group, GFP_KERNEL);
	}
	err = netlink_unicast(sk, skb, dst_pid, msg->msg_flags&MSG_DONTWAIT);

out:
	return err;
}

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_sock *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_reset_transport_header(skb);
	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_group_mask(NETLINK_CB(skb).dst_group);
		msg->msg_namelen = sizeof(*addr);
	}

	if (nlk->flags & NETLINK_RECV_PKTINFO)
		netlink_cmsg_recv_pktinfo(msg, skb);

	if (NULL == siocb->scm) {
		memset(&scm, 0, sizeof(scm));
		siocb->scm = &scm;