raw.c

linux 内核源代码

			if (!daddr)
				goto done;
			daddr = ipc.opt->faddr;
		}
	}
	tos = RT_CONN_FLAGS(sk);
	if (msg->msg_flags & MSG_DONTROUTE)
		tos |= RTO_ONLINK;

	if (MULTICAST(daddr)) {
		if (!ipc.oif)
			ipc.oif = inet->mc_index;
		if (!saddr)
			saddr = inet->mc_addr;
	}

	{
		struct flowi fl = { .oif = ipc.oif,
				    .nl_u = { .ip4_u =
					      { .daddr = daddr,
						.saddr = saddr,
						.tos = tos } },
				    .proto = inet->hdrincl ? IPPROTO_RAW :
							     sk->sk_protocol,
				  };
		if (!inet->hdrincl) {
			err = raw_probe_proto_opt(&fl, msg);
			if (err)
				goto done;
		}

		security_sk_classify_flow(sk, &fl);
		err = ip_route_output_flow(&rt, &fl, sk, 1);
	}
	if (err)
		goto done;

	err = -EACCES;
	if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
		goto done;

	if (msg->msg_flags & MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	if (inet->hdrincl)
		err = raw_send_hdrinc(sk, msg->msg_iov, len,
					rt, msg->msg_flags);

	 else {
		if (!ipc.addr)
			ipc.addr = rt->rt_dst;
		lock_sock(sk);
		err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,
					&ipc, rt, msg->msg_flags);
		if (err)
			ip_flush_pending_frames(sk);
		else if (!(msg->msg_flags & MSG_MORE))
			err = ip_push_pending_frames(sk);
		release_sock(sk);
	}
done:
	if (free)
		kfree(ipc.opt);
	ip_rt_put(rt);

out:
	if (err < 0)
		return err;
	return len;

do_confirm:
	dst_confirm(&rt->u.dst);
	if (!(msg->msg_flags & MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto done;
}

static void raw_close(struct sock *sk, long timeout)
{
	/*
	 * Raw sockets may have direct kernel refereneces. Kill them.
	 */
	ip_ra_control(sk, 0, NULL);

	sk_common_release(sk);
}

/* This gets rid of all the nasties in af_inet. -DaveM */
static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
	int ret = -EINVAL;
	int chk_addr_ret;

	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
		goto out;
	chk_addr_ret = inet_addr_type(addr->sin_addr.s_addr);
	ret = -EADDRNOTAVAIL;
	if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
		goto out;
	inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->saddr = 0;  /* Use device */
	sk_dst_reset(sk);
	ret = 0;
out:	return ret;
}

/*
 *	This should be easy, if there is something there
 *	we return it, otherwise we block.
 */

static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		       size_t len, int noblock, int flags, int *addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	size_t copied = 0;
	int err = -EOPNOTSUPP;
	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
	struct sk_buff *skb;

	if (flags & MSG_OOB)
		goto out;

	if (addr_len)
		*addr_len = sizeof(*sin);

	if (flags & MSG_ERRQUEUE) {
		err = ip_recv_error(sk, msg, len);
		goto out;
	}

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

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

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

	sock_recv_timestamp(msg, sk, skb);

	/* Copy the address. */
	if (sin) {
		sin->sin_family = AF_INET;
		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
		sin->sin_port = 0;
		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
	}
	if (inet->cmsg_flags)
		ip_cmsg_recv(msg, skb);
	if (flags & MSG_TRUNC)
		copied = skb->len;
done:
	skb_free_datagram(sk, skb);
out:
	if (err)
		return err;
	return copied;
}

static int raw_init(struct sock *sk)
{
	struct raw_sock *rp = raw_sk(sk);

	if (inet_sk(sk)->num == IPPROTO_ICMP)
		memset(&rp->filter, 0, sizeof(rp->filter));
	return 0;
}

static int raw_seticmpfilter(struct sock *sk, char __user *optval, int optlen)
{
	if (optlen > sizeof(struct icmp_filter))
		optlen = sizeof(struct icmp_filter);
	if (copy_from_user(&raw_sk(sk)->filter, optval, optlen))
		return -EFAULT;
	return 0;
}

static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *optlen)
{
	int len, ret = -EFAULT;

	if (get_user(len, optlen))
		goto out;
	ret = -EINVAL;
	if (len < 0)
		goto out;
	if (len > sizeof(struct icmp_filter))
		len = sizeof(struct icmp_filter);
	ret = -EFAULT;
	if (put_user(len, optlen) ||
	    copy_to_user(optval, &raw_sk(sk)->filter, len))
		goto out;
	ret = 0;
out:	return ret;
}

static int do_raw_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
{
	if (optname == ICMP_FILTER) {
		if (inet_sk(sk)->num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		else
			return raw_seticmpfilter(sk, optval, optlen);
	}
	return -ENOPROTOOPT;
}

static int raw_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
{
	if (level != SOL_RAW)
		return ip_setsockopt(sk, level, optname, optval, optlen);
	return do_raw_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_raw_setsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, int optlen)
{
	if (level != SOL_RAW)
		return compat_ip_setsockopt(sk, level, optname, optval, optlen);
	return do_raw_setsockopt(sk, level, optname, optval, optlen);
}
#endif

static int do_raw_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (optname == ICMP_FILTER) {
		if (inet_sk(sk)->num != IPPROTO_ICMP)
			return -EOPNOTSUPP;
		else
			return raw_geticmpfilter(sk, optval, optlen);
	}
	return -ENOPROTOOPT;
}

static int raw_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (level != SOL_RAW)
		return ip_getsockopt(sk, level, optname, optval, optlen);
	return do_raw_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_raw_getsockopt(struct sock *sk, int level, int optname,
				 char __user *optval, int __user *optlen)
{
	if (level != SOL_RAW)
		return compat_ip_getsockopt(sk, level, optname, optval, optlen);
	return do_raw_getsockopt(sk, level, optname, optval, optlen);
}
#endif

static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch (cmd) {
		case SIOCOUTQ: {
			int amount = atomic_read(&sk->sk_wmem_alloc);
			return put_user(amount, (int __user *)arg);
		}
		case SIOCINQ: {
			struct sk_buff *skb;
			int amount = 0;

			spin_lock_bh(&sk->sk_receive_queue.lock);
			skb = skb_peek(&sk->sk_receive_queue);
			if (skb != NULL)
				amount = skb->len;
			spin_unlock_bh(&sk->sk_receive_queue.lock);
			return put_user(amount, (int __user *)arg);
		}

		default:
#ifdef CONFIG_IP_MROUTE
			return ipmr_ioctl(sk, cmd, (void __user *)arg);
#else
			return -ENOIOCTLCMD;
#endif
	}
}

DEFINE_PROTO_INUSE(raw)

struct proto raw_prot = {
	.name		   = "RAW",
	.owner		   = THIS_MODULE,
	.close		   = raw_close,
	.connect	   = ip4_datagram_connect,
	.disconnect	   = udp_disconnect,
	.ioctl		   = raw_ioctl,
	.init		   = raw_init,
	.setsockopt	   = raw_setsockopt,
	.getsockopt	   = raw_getsockopt,
	.sendmsg	   = raw_sendmsg,
	.recvmsg	   = raw_recvmsg,
	.bind		   = raw_bind,
	.backlog_rcv	   = raw_rcv_skb,
	.hash		   = raw_v4_hash,
	.unhash		   = raw_v4_unhash,
	.obj_size	   = sizeof(struct raw_sock),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_raw_setsockopt,
	.compat_getsockopt = compat_raw_getsockopt,
#endif
	REF_PROTO_INUSE(raw)
};

#ifdef CONFIG_PROC_FS
struct raw_iter_state {
	int bucket;
};

#define raw_seq_private(seq) ((struct raw_iter_state *)(seq)->private)

static struct sock *raw_get_first(struct seq_file *seq)
{
	struct sock *sk;
	struct raw_iter_state* state = raw_seq_private(seq);

	for (state->bucket = 0; state->bucket < RAWV4_HTABLE_SIZE; ++state->bucket) {
		struct hlist_node *node;

		sk_for_each(sk, node, &raw_v4_htable[state->bucket])
			if (sk->sk_family == PF_INET)
				goto found;
	}
	sk = NULL;
found:
	return sk;
}

static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
{
	struct raw_iter_state* state = raw_seq_private(seq);

	do {
		sk = sk_next(sk);
try_again:
		;
	} while (sk && sk->sk_family != PF_INET);

	if (!sk && ++state->bucket < RAWV4_HTABLE_SIZE) {
		sk = sk_head(&raw_v4_htable[state->bucket]);
		goto try_again;
	}
	return sk;
}

static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
{
	struct sock *sk = raw_get_first(seq);

	if (sk)
		while (pos && (sk = raw_get_next(seq, sk)) != NULL)
			--pos;
	return pos ? NULL : sk;
}

static void *raw_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&raw_v4_lock);
	return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}

static void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *sk;

	if (v == SEQ_START_TOKEN)
		sk = raw_get_first(seq);
	else
		sk = raw_get_next(seq, v);
	++*pos;
	return sk;
}

static void raw_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&raw_v4_lock);
}

static __inline__ char *get_raw_sock(struct sock *sp, char *tmpbuf, int i)
{
	struct inet_sock *inet = inet_sk(sp);
	__be32 dest = inet->daddr,
	       src = inet->rcv_saddr;
	__u16 destp = 0,
	      srcp  = inet->num;

	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
		i, src, srcp, dest, destp, sp->sk_state,
		atomic_read(&sp->sk_wmem_alloc),
		atomic_read(&sp->sk_rmem_alloc),
		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
		atomic_read(&sp->sk_refcnt), sp);
	return tmpbuf;
}

static int raw_seq_show(struct seq_file *seq, void *v)
{
	char tmpbuf[129];

	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "%-127s\n",
			       "  sl  local_address rem_address   st tx_queue "
			       "rx_queue tr tm->when retrnsmt   uid  timeout "
			       "inode");
	else {
		struct raw_iter_state *state = raw_seq_private(seq);

		seq_printf(seq, "%-127s\n",
			   get_raw_sock(v, tmpbuf, state->bucket));
	}
	return 0;
}

static const struct seq_operations raw_seq_ops = {
	.start = raw_seq_start,
	.next  = raw_seq_next,
	.stop  = raw_seq_stop,
	.show  = raw_seq_show,
};

static int raw_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &raw_seq_ops,
			sizeof(struct raw_iter_state));
}

static const struct file_operations raw_seq_fops = {
	.owner	 = THIS_MODULE,
	.open	 = raw_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_private,
};

int __init raw_proc_init(void)
{
	if (!proc_net_fops_create(&init_net, "raw", S_IRUGO, &raw_seq_fops))
		return -ENOMEM;
	return 0;
}

void __init raw_proc_exit(void)
{
	proc_net_remove(&init_net, "raw");
}
#endif /* CONFIG_PROC_FS */