af_packet.c

linux 内核源代码

	sll->sll_pkttype = skb->pkt_type;
	if (unlikely(po->origdev))
		sll->sll_ifindex = orig_dev->ifindex;
	else
		sll->sll_ifindex = dev->ifindex;

	h->tp_status = status;
	smp_mb();

	{
		struct page *p_start, *p_end;
		u8 *h_end = (u8 *)h + macoff + snaplen - 1;

		p_start = virt_to_page(h);
		p_end = virt_to_page(h_end);
		while (p_start <= p_end) {
			flush_dcache_page(p_start);
			p_start++;
		}
	}

	sk->sk_data_ready(sk, 0);

drop_n_restore:
	if (skb_head != skb->data && skb_shared(skb)) {
		skb->data = skb_head;
		skb->len = skb_len;
	}
drop:
	kfree_skb(skb);
	return 0;

ring_is_full:
	po->stats.tp_drops++;
	spin_unlock(&sk->sk_receive_queue.lock);

	sk->sk_data_ready(sk, 0);
	if (copy_skb)
		kfree_skb(copy_skb);
	goto drop_n_restore;
}

#endif


static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
			  struct msghdr *msg, size_t len)
{
	struct sock *sk = sock->sk;
	struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name;
	struct sk_buff *skb;
	struct net_device *dev;
	__be16 proto;
	unsigned char *addr;
	int ifindex, err, reserve = 0;

	/*
	 *	Get and verify the address.
	 */

	if (saddr == NULL) {
		struct packet_sock *po = pkt_sk(sk);

		ifindex	= po->ifindex;
		proto	= po->num;
		addr	= NULL;
	} else {
		err = -EINVAL;
		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
			goto out;
		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
			goto out;
		ifindex	= saddr->sll_ifindex;
		proto	= saddr->sll_protocol;
		addr	= saddr->sll_addr;
	}


	dev = dev_get_by_index(&init_net, ifindex);
	err = -ENXIO;
	if (dev == NULL)
		goto out_unlock;
	if (sock->type == SOCK_RAW)
		reserve = dev->hard_header_len;

	err = -ENETDOWN;
	if (!(dev->flags & IFF_UP))
		goto out_unlock;

	err = -EMSGSIZE;
	if (len > dev->mtu+reserve)
		goto out_unlock;

	skb = sock_alloc_send_skb(sk, len + LL_RESERVED_SPACE(dev),
				msg->msg_flags & MSG_DONTWAIT, &err);
	if (skb==NULL)
		goto out_unlock;

	skb_reserve(skb, LL_RESERVED_SPACE(dev));
	skb_reset_network_header(skb);

	err = -EINVAL;
	if (sock->type == SOCK_DGRAM &&
	    dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len) < 0)
		goto out_free;

	/* Returns -EFAULT on error */
	err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len);
	if (err)
		goto out_free;

	skb->protocol = proto;
	skb->dev = dev;
	skb->priority = sk->sk_priority;

	/*
	 *	Now send it
	 */

	err = dev_queue_xmit(skb);
	if (err > 0 && (err = net_xmit_errno(err)) != 0)
		goto out_unlock;

	dev_put(dev);

	return(len);

out_free:
	kfree_skb(skb);
out_unlock:
	if (dev)
		dev_put(dev);
out:
	return err;
}

/*
 *	Close a PACKET socket. This is fairly simple. We immediately go
 *	to 'closed' state and remove our protocol entry in the device list.
 */

static int packet_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct packet_sock *po;

	if (!sk)
		return 0;

	po = pkt_sk(sk);

	write_lock_bh(&packet_sklist_lock);
	sk_del_node_init(sk);
	write_unlock_bh(&packet_sklist_lock);

	/*
	 *	Unhook packet receive handler.
	 */

	if (po->running) {
		/*
		 *	Remove the protocol hook
		 */
		dev_remove_pack(&po->prot_hook);
		po->running = 0;
		po->num = 0;
		__sock_put(sk);
	}

	packet_flush_mclist(sk);

#ifdef CONFIG_PACKET_MMAP
	if (po->pg_vec) {
		struct tpacket_req req;
		memset(&req, 0, sizeof(req));
		packet_set_ring(sk, &req, 1);
	}
#endif

	/*
	 *	Now the socket is dead. No more input will appear.
	 */

	sock_orphan(sk);
	sock->sk = NULL;

	/* Purge queues */

	skb_queue_purge(&sk->sk_receive_queue);
	sk_refcnt_debug_release(sk);

	sock_put(sk);
	return 0;
}

/*
 *	Attach a packet hook.
 */

static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol)
{
	struct packet_sock *po = pkt_sk(sk);
	/*
	 *	Detach an existing hook if present.
	 */

	lock_sock(sk);

	spin_lock(&po->bind_lock);
	if (po->running) {
		__sock_put(sk);
		po->running = 0;
		po->num = 0;
		spin_unlock(&po->bind_lock);
		dev_remove_pack(&po->prot_hook);
		spin_lock(&po->bind_lock);
	}

	po->num = protocol;
	po->prot_hook.type = protocol;
	po->prot_hook.dev = dev;

	po->ifindex = dev ? dev->ifindex : 0;

	if (protocol == 0)
		goto out_unlock;

	if (!dev || (dev->flags & IFF_UP)) {
		dev_add_pack(&po->prot_hook);
		sock_hold(sk);
		po->running = 1;
	} else {
		sk->sk_err = ENETDOWN;
		if (!sock_flag(sk, SOCK_DEAD))
			sk->sk_error_report(sk);
	}

out_unlock:
	spin_unlock(&po->bind_lock);
	release_sock(sk);
	return 0;
}

/*
 *	Bind a packet socket to a device
 */

static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sock *sk=sock->sk;
	char name[15];
	struct net_device *dev;
	int err = -ENODEV;

	/*
	 *	Check legality
	 */

	if (addr_len != sizeof(struct sockaddr))
		return -EINVAL;
	strlcpy(name,uaddr->sa_data,sizeof(name));

	dev = dev_get_by_name(&init_net, name);
	if (dev) {
		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
		dev_put(dev);
	}
	return err;
}

static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr;
	struct sock *sk=sock->sk;
	struct net_device *dev = NULL;
	int err;


	/*
	 *	Check legality
	 */

	if (addr_len < sizeof(struct sockaddr_ll))
		return -EINVAL;
	if (sll->sll_family != AF_PACKET)
		return -EINVAL;

	if (sll->sll_ifindex) {
		err = -ENODEV;
		dev = dev_get_by_index(&init_net, sll->sll_ifindex);
		if (dev == NULL)
			goto out;
	}
	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
	if (dev)
		dev_put(dev);

out:
	return err;
}

static struct proto packet_proto = {
	.name	  = "PACKET",
	.owner	  = THIS_MODULE,
	.obj_size = sizeof(struct packet_sock),
};

/*
 *	Create a packet of type SOCK_PACKET.
 */

static int packet_create(struct net *net, struct socket *sock, int protocol)
{
	struct sock *sk;
	struct packet_sock *po;
	__be16 proto = (__force __be16)protocol; /* weird, but documented */
	int err;

	if (net != &init_net)
		return -EAFNOSUPPORT;

	if (!capable(CAP_NET_RAW))
		return -EPERM;
	if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW &&
	    sock->type != SOCK_PACKET)
		return -ESOCKTNOSUPPORT;

	sock->state = SS_UNCONNECTED;

	err = -ENOBUFS;
	sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto);
	if (sk == NULL)
		goto out;

	sock->ops = &packet_ops;
	if (sock->type == SOCK_PACKET)
		sock->ops = &packet_ops_spkt;

	sock_init_data(sock, sk);

	po = pkt_sk(sk);
	sk->sk_family = PF_PACKET;
	po->num = proto;

	sk->sk_destruct = packet_sock_destruct;
	sk_refcnt_debug_inc(sk);

	/*
	 *	Attach a protocol block
	 */

	spin_lock_init(&po->bind_lock);
	po->prot_hook.func = packet_rcv;

	if (sock->type == SOCK_PACKET)
		po->prot_hook.func = packet_rcv_spkt;

	po->prot_hook.af_packet_priv = sk;

	if (proto) {
		po->prot_hook.type = proto;
		dev_add_pack(&po->prot_hook);
		sock_hold(sk);
		po->running = 1;
	}

	write_lock_bh(&packet_sklist_lock);
	sk_add_node(sk, &packet_sklist);
	write_unlock_bh(&packet_sklist_lock);
	return(0);
out:
	return err;
}

/*
 *	Pull a packet from our receive queue and hand it to the user.
 *	If necessary we block.
 */

static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
			  struct msghdr *msg, size_t len, int flags)
{
	struct sock *sk = sock->sk;
	struct sk_buff *skb;
	int copied, err;
	struct sockaddr_ll *sll;

	err = -EINVAL;
	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
		goto out;

#if 0
	/* What error should we return now? EUNATTACH? */
	if (pkt_sk(sk)->ifindex < 0)
		return -ENODEV;
#endif

	/*
	 *	Call the generic datagram receiver. This handles all sorts
	 *	of horrible races and re-entrancy so we can forget about it
	 *	in the protocol layers.
	 *
	 *	Now it will return ENETDOWN, if device have just gone down,
	 *	but then it will block.
	 */

	skb=skb_recv_datagram(sk,flags,flags&MSG_DONTWAIT,&err);

	/*
	 *	An error occurred so return it. Because skb_recv_datagram()
	 *	handles the blocking we don't see and worry about blocking
	 *	retries.
	 */

	if (skb == NULL)
		goto out;

	/*
	 *	If the address length field is there to be filled in, we fill
	 *	it in now.
	 */

	sll = &PACKET_SKB_CB(skb)->sa.ll;
	if (sock->type == SOCK_PACKET)
		msg->msg_namelen = sizeof(struct sockaddr_pkt);
	else
		msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);

	/*
	 *	You lose any data beyond the buffer you gave. If it worries a
	 *	user program they can ask the device for its MTU anyway.
	 */

	copied = skb->len;
	if (copied > len)
	{
		copied=len;
		msg->msg_flags|=MSG_TRUNC;
	}

	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
	if (err)
		goto out_free;

	sock_recv_timestamp(msg, sk, skb);

	if (msg->msg_name)
		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
		       msg->msg_namelen);

	if (pkt_sk(sk)->auxdata) {
		struct tpacket_auxdata aux;

		aux.tp_status = TP_STATUS_USER;
		if (skb->ip_summed == CHECKSUM_PARTIAL)
			aux.tp_status |= TP_STATUS_CSUMNOTREADY;
		aux.tp_len = PACKET_SKB_CB(skb)->origlen;
		aux.tp_snaplen = skb->len;
		aux.tp_mac = 0;
		aux.tp_net = skb_network_offset(skb);

		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
	}

	/*
	 *	Free or return the buffer as appropriate. Again this
	 *	hides all the races and re-entrancy issues from us.
	 */
	err = (flags&MSG_TRUNC) ? skb->len : copied;

out_free:
	skb_free_datagram(sk, skb);
out:
	return err;
}

static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
			       int *uaddr_len, int peer)
{
	struct net_device *dev;
	struct sock *sk	= sock->sk;

	if (peer)
		return -EOPNOTSUPP;

	uaddr->sa_family = AF_PACKET;
	dev = dev_get_by_index(&init_net, pkt_sk(sk)->ifindex);
	if (dev) {
		strlcpy(uaddr->sa_data, dev->name, 15);
		dev_put(dev);
	} else
		memset(uaddr->sa_data, 0, 14);
	*uaddr_len = sizeof(*uaddr);

	return 0;
}

static int packet_getname(struct socket *sock, struct sockaddr *uaddr,
			  int *uaddr_len, int peer)
{
	struct net_device *dev;
	struct sock *sk = sock->sk;
	struct packet_sock *po = pkt_sk(sk);
	struct sockaddr_ll *sll = (struct sockaddr_ll*)uaddr;

	if (peer)
		return -EOPNOTSUPP;

	sll->sll_family = AF_PACKET;
	sll->sll_ifindex = po->ifindex;
	sll->sll_protocol = po->num;
	dev = dev_get_by_index(&init_net, po->ifindex);
	if (dev) {
		sll->sll_hatype = dev->type;
		sll->sll_halen = dev->addr_len;
		memcpy(sll->sll_addr, dev->dev_addr, dev->addr_len);
		dev_put(dev);
	} else {
		sll->sll_hatype = 0;	/* Bad: we have no ARPHRD_UNSPEC */
		sll->sll_halen = 0;
	}
	*uaddr_len = offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen;

	return 0;
}

static void packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what)
{
	switch (i->type) {
	case PACKET_MR_MULTICAST:
		if (what > 0)
			dev_mc_add(dev, i->addr, i->alen, 0);
		else
			dev_mc_delete(dev, i->addr, i->alen, 0);
		break;
	case PACKET_MR_PROMISC:
		dev_set_promiscuity(dev, what);
		break;
	case PACKET_MR_ALLMULTI:
		dev_set_allmulti(dev, what);
		break;
	default:;
	}
}

static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what)
{
	for ( ; i; i=i->next) {
		if (i->ifindex == dev->ifindex)
			packet_dev_mc(dev, i, what);
	}
}

static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq)
{
	struct packet_sock *po = pkt_sk(sk);
	struct packet_mclist *ml, *i;
	struct net_device *dev;
	int err;

	rtnl_lock();

	err = -ENODEV;
	dev = __dev_get_by_index(&init_net, mreq->mr_ifindex);
	if (!dev)
		goto done;

	err = -EINVAL;
	if (mreq->mr_alen > dev->addr_len)
		goto done;

	err = -ENOBUFS;
	i = kmalloc(sizeof(*i), GFP_KERNEL);
	if (i == NULL)
		goto done;

	err = 0;
	for (ml = po->mclist; ml; ml = ml->next) {
		if (ml->ifindex == mreq->mr_ifindex &&
		    ml->type == mreq->mr_type &&
		    ml->alen == mreq->mr_alen &&
		    memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
			ml->count++;
			/* Free the new element ... */
			kfree(i);
			goto done;
		}
	}

	i->type = mreq->mr_type;
	i->ifindex = mreq->mr_ifindex;
	i->alen = mreq->mr_alen;
	memcpy(i->addr, mreq->mr_address, i->alen);
	i->count = 1;
	i->next = po->mclist;
	po->mclist = i;
	packet_dev_mc(dev, i, +1);

done:
	rtnl_unlock();
	return err;
}

static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq)
{
	struct packet_mclist *ml, **mlp;

	rtnl_lock();

	for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) {
		if (ml->ifindex == mreq->mr_ifindex &&
		    ml->type == mreq->mr_type &&
		    ml->alen == mreq->mr_alen &&
		    memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) {
			if (--ml->count == 0) {
				struct net_device *dev;
				*mlp = ml->next;
				dev = dev_get_by_index(&init_net, ml->ifindex);
				if (dev) {
					packet_dev_mc(dev, ml, -1);
					dev_put(dev);
				}
				kfree(ml);
			}
			rtnl_unlock();
			return 0;
		}
	}
	rtnl_unlock();
	return -EADDRNOTAVAIL;
}

static void packet_flush_mclist(struct sock *sk)
{
	struct packet_sock *po = pkt_sk(sk);
	struct packet_mclist *ml;

	if (!po->mclist)
		return;

	rtnl_lock();
	while ((ml = po->mclist) != NULL) {
		struct net_device *dev;

		po->mclist = ml->next;
		if ((dev = dev_get_by_index(&init_net, ml->ifindex)) != NULL) {
			packet_dev_mc(dev, ml, -1);
			dev_put(dev);
		}
		kfree(ml);
	}
	rtnl_unlock();
}

static int
packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen)