raw.c

linux 内核源代码

			if (!type) {
				type = iov->iov_base;
				/* check if code field is readable or not. */
				if (iov->iov_len > 1)
					code = type + 1;
			} else if (!code)
				code = iov->iov_base;

			if (type && code) {
				if (get_user(fl->fl_icmp_type, type) ||
				    get_user(fl->fl_icmp_code, code))
					return -EFAULT;
				probed = 1;
			}
			break;
		case IPPROTO_MH:
			if (iov->iov_base && iov->iov_len < 1)
				break;
			/* check if type field is readable or not. */
			if (iov->iov_len > 2 - len) {
				u8 __user *p = iov->iov_base;
				if (get_user(fl->fl_mh_type, &p[2 - len]))
					return -EFAULT;
				probed = 1;
			} else
				len += iov->iov_len;

			break;
		default:
			probed = 1;
			break;
		}
		if (probed)
			break;
	}
	return 0;
}

static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
		   struct msghdr *msg, size_t len)
{
	struct ipv6_txoptions opt_space;
	struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name;
	struct in6_addr *daddr, *final_p = NULL, final;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct raw6_sock *rp = raw6_sk(sk);
	struct ipv6_txoptions *opt = NULL;
	struct ip6_flowlabel *flowlabel = NULL;
	struct dst_entry *dst = NULL;
	struct flowi fl;
	int addr_len = msg->msg_namelen;
	int hlimit = -1;
	int tclass = -1;
	u16 proto;
	int err;

	/* Rough check on arithmetic overflow,
	   better check is made in ip6_append_data().
	 */
	if (len > INT_MAX)
		return -EMSGSIZE;

	/* Mirror BSD error message compatibility */
	if (msg->msg_flags & MSG_OOB)
		return -EOPNOTSUPP;

	/*
	 *	Get and verify the address.
	 */
	memset(&fl, 0, sizeof(fl));

	if (sin6) {
		if (addr_len < SIN6_LEN_RFC2133)
			return -EINVAL;

		if (sin6->sin6_family && sin6->sin6_family != AF_INET6)
			return(-EAFNOSUPPORT);

		/* port is the proto value [0..255] carried in nexthdr */
		proto = ntohs(sin6->sin6_port);

		if (!proto)
			proto = inet->num;
		else if (proto != inet->num)
			return(-EINVAL);

		if (proto > 255)
			return(-EINVAL);

		daddr = &sin6->sin6_addr;
		if (np->sndflow) {
			fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
			if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
				flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
				if (flowlabel == NULL)
					return -EINVAL;
				daddr = &flowlabel->dst;
			}
		}

		/*
		 * Otherwise it will be difficult to maintain
		 * sk->sk_dst_cache.
		 */
		if (sk->sk_state == TCP_ESTABLISHED &&
		    ipv6_addr_equal(daddr, &np->daddr))
			daddr = &np->daddr;

		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    sin6->sin6_scope_id &&
		    ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
			fl.oif = sin6->sin6_scope_id;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;

		proto = inet->num;
		daddr = &np->daddr;
		fl.fl6_flowlabel = np->flow_label;
	}

	if (ipv6_addr_any(daddr)) {
		/*
		 * unspecified destination address
		 * treated as error... is this correct ?
		 */
		fl6_sock_release(flowlabel);
		return(-EINVAL);
	}

	if (fl.oif == 0)
		fl.oif = sk->sk_bound_dev_if;

	if (msg->msg_controllen) {
		opt = &opt_space;
		memset(opt, 0, sizeof(struct ipv6_txoptions));
		opt->tot_len = sizeof(struct ipv6_txoptions);

		err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
		if (err < 0) {
			fl6_sock_release(flowlabel);
			return err;
		}
		if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
		}
		if (!(opt->opt_nflen|opt->opt_flen))
			opt = NULL;
	}
	if (opt == NULL)
		opt = np->opt;
	if (flowlabel)
		opt = fl6_merge_options(&opt_space, flowlabel, opt);
	opt = ipv6_fixup_options(&opt_space, opt);

	fl.proto = proto;
	err = rawv6_probe_proto_opt(&fl, msg);
	if (err)
		goto out;

	ipv6_addr_copy(&fl.fl6_dst, daddr);
	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
		ipv6_addr_copy(&fl.fl6_src, &np->saddr);

	/* merge ip6_build_xmit from ip6_output */
	if (opt && opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
		final_p = &final;
	}

	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
		fl.oif = np->mcast_oif;
	security_sk_classify_flow(sk, &fl);

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto out;
	if (final_p)
		ipv6_addr_copy(&fl.fl6_dst, final_p);

	if ((err = __xfrm_lookup(&dst, &fl, sk, 1)) < 0) {
		if (err == -EREMOTE)
			err = ip6_dst_blackhole(sk, &dst, &fl);
		if (err < 0)
			goto out;
	}

	if (hlimit < 0) {
		if (ipv6_addr_is_multicast(&fl.fl6_dst))
			hlimit = np->mcast_hops;
		else
			hlimit = np->hop_limit;
		if (hlimit < 0)
			hlimit = dst_metric(dst, RTAX_HOPLIMIT);
		if (hlimit < 0)
			hlimit = ipv6_get_hoplimit(dst->dev);
	}

	if (tclass < 0) {
		tclass = np->tclass;
		if (tclass < 0)
			tclass = 0;
	}

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

back_from_confirm:
	if (inet->hdrincl) {
		err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl, (struct rt6_info*)dst, msg->msg_flags);
	} else {
		lock_sock(sk);
		err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
			len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
			msg->msg_flags);

		if (err)
			ip6_flush_pending_frames(sk);
		else if (!(msg->msg_flags & MSG_MORE))
			err = rawv6_push_pending_frames(sk, &fl, rp);
		release_sock(sk);
	}
done:
	dst_release(dst);
out:
	fl6_sock_release(flowlabel);
	return err<0?err:len;
do_confirm:
	dst_confirm(dst);
	if (!(msg->msg_flags & MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto done;
}

static int rawv6_seticmpfilter(struct sock *sk, int level, int optname,
			       char __user *optval, int optlen)
{
	switch (optname) {
	case ICMPV6_FILTER:
		if (optlen > sizeof(struct icmp6_filter))
			optlen = sizeof(struct icmp6_filter);
		if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen))
			return -EFAULT;
		return 0;
	default:
		return -ENOPROTOOPT;
	}

	return 0;
}

static int rawv6_geticmpfilter(struct sock *sk, int level, int optname,
			       char __user *optval, int __user *optlen)
{
	int len;

	switch (optname) {
	case ICMPV6_FILTER:
		if (get_user(len, optlen))
			return -EFAULT;
		if (len < 0)
			return -EINVAL;
		if (len > sizeof(struct icmp6_filter))
			len = sizeof(struct icmp6_filter);
		if (put_user(len, optlen))
			return -EFAULT;
		if (copy_to_user(optval, &raw6_sk(sk)->filter, len))
			return -EFAULT;
		return 0;
	default:
		return -ENOPROTOOPT;
	}

	return 0;
}


static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int optlen)
{
	struct raw6_sock *rp = raw6_sk(sk);
	int val;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	switch (optname) {
		case IPV6_CHECKSUM:
			/* You may get strange result with a positive odd offset;
			   RFC2292bis agrees with me. */
			if (val > 0 && (val&1))
				return(-EINVAL);
			if (val < 0) {
				rp->checksum = 0;
			} else {
				rp->checksum = 1;
				rp->offset = val;
			}

			return 0;
			break;

		default:
			return(-ENOPROTOOPT);
	}
}

static int rawv6_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
{
	switch(level) {
		case SOL_RAW:
			break;

		case SOL_ICMPV6:
			if (inet_sk(sk)->num != IPPROTO_ICMPV6)
				return -EOPNOTSUPP;
			return rawv6_seticmpfilter(sk, level, optname, optval,
						   optlen);
		case SOL_IPV6:
			if (optname == IPV6_CHECKSUM)
				break;
		default:
			return ipv6_setsockopt(sk, level, optname, optval,
					       optlen);
	}

	return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname,
				   char __user *optval, int optlen)
{
	switch (level) {
	case SOL_RAW:
		break;
	case SOL_ICMPV6:
		if (inet_sk(sk)->num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		return rawv6_seticmpfilter(sk, level, optname, optval, optlen);
	case SOL_IPV6:
		if (optname == IPV6_CHECKSUM)
			break;
	default:
		return compat_ipv6_setsockopt(sk, level, optname,
					      optval, optlen);
	}
	return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
}
#endif

static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int __user *optlen)
{
	struct raw6_sock *rp = raw6_sk(sk);
	int val, len;

	if (get_user(len,optlen))
		return -EFAULT;

	switch (optname) {
	case IPV6_CHECKSUM:
		if (rp->checksum == 0)
			val = -1;
		else
			val = rp->offset;
		break;

	default:
		return -ENOPROTOOPT;
	}

	len = min_t(unsigned int, sizeof(int), len);

	if (put_user(len, optlen))
		return -EFAULT;
	if (copy_to_user(optval,&val,len))
		return -EFAULT;
	return 0;
}

static int rawv6_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	switch(level) {
		case SOL_RAW:
			break;

		case SOL_ICMPV6:
			if (inet_sk(sk)->num != IPPROTO_ICMPV6)
				return -EOPNOTSUPP;
			return rawv6_geticmpfilter(sk, level, optname, optval,
						   optlen);
		case SOL_IPV6:
			if (optname == IPV6_CHECKSUM)
				break;
		default:
			return ipv6_getsockopt(sk, level, optname, optval,
					       optlen);
	}

	return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname,
				   char __user *optval, int __user *optlen)
{
	switch (level) {
	case SOL_RAW:
		break;
	case SOL_ICMPV6:
		if (inet_sk(sk)->num != IPPROTO_ICMPV6)
			return -EOPNOTSUPP;
		return rawv6_geticmpfilter(sk, level, optname, optval, optlen);
	case SOL_IPV6:
		if (optname == IPV6_CHECKSUM)
			break;
	default:
		return compat_ipv6_getsockopt(sk, level, optname,
					      optval, optlen);
	}
	return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
}
#endif

static int rawv6_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->tail - skb->transport_header;
			spin_unlock_bh(&sk->sk_receive_queue.lock);
			return put_user(amount, (int __user *)arg);
		}

		default:
			return -ENOIOCTLCMD;
	}
}

static void rawv6_close(struct sock *sk, long timeout)
{
	if (inet_sk(sk)->num == IPPROTO_RAW)
		ip6_ra_control(sk, -1, NULL);

	sk_common_release(sk);
}

static int rawv6_init_sk(struct sock *sk)
{
	struct raw6_sock *rp = raw6_sk(sk);

	switch (inet_sk(sk)->num) {
	case IPPROTO_ICMPV6:
		rp->checksum = 1;
		rp->offset   = 2;
		break;
	case IPPROTO_MH:
		rp->checksum = 1;
		rp->offset   = 4;
		break;
	default:
		break;
	}
	return(0);
}

DEFINE_PROTO_INUSE(rawv6)

struct proto rawv6_prot = {
	.name		   = "RAWv6",
	.owner		   = THIS_MODULE,
	.close		   = rawv6_close,
	.connect	   = ip6_datagram_connect,
	.disconnect	   = udp_disconnect,
	.ioctl		   = rawv6_ioctl,
	.init		   = rawv6_init_sk,
	.destroy	   = inet6_destroy_sock,
	.setsockopt	   = rawv6_setsockopt,
	.getsockopt	   = rawv6_getsockopt,
	.sendmsg	   = rawv6_sendmsg,
	.recvmsg	   = rawv6_recvmsg,
	.bind		   = rawv6_bind,
	.backlog_rcv	   = rawv6_rcv_skb,
	.hash		   = raw_v6_hash,
	.unhash		   = raw_v6_unhash,
	.obj_size	   = sizeof(struct raw6_sock),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_rawv6_setsockopt,
	.compat_getsockopt = compat_rawv6_getsockopt,
#endif
	REF_PROTO_INUSE(rawv6)
};

#ifdef CONFIG_PROC_FS
struct raw6_iter_state {
	int bucket;
};

#define raw6_seq_private(seq) ((struct raw6_iter_state *)(seq)->private)

static struct sock *raw6_get_first(struct seq_file *seq)
{
	struct sock *sk;
	struct hlist_node *node;
	struct raw6_iter_state* state = raw6_seq_private(seq);

	for (state->bucket = 0; state->bucket < RAWV6_HTABLE_SIZE; ++state->bucket)
		sk_for_each(sk, node, &raw_v6_htable[state->bucket])
			if (sk->sk_family == PF_INET6)
				goto out;
	sk = NULL;
out:
	return sk;
}

static struct sock *raw6_get_next(struct seq_file *seq, struct sock *sk)
{
	struct raw6_iter_state* state = raw6_seq_private(seq);

	do {
		sk = sk_next(sk);
try_again:
		;
	} while (sk && sk->sk_family != PF_INET6);

	if (!sk && ++state->bucket < RAWV6_HTABLE_SIZE) {
		sk = sk_head(&raw_v6_htable[state->bucket]);
		goto try_again;
	}
	return sk;
}

static struct sock *raw6_get_idx(struct seq_file *seq, loff_t pos)
{
	struct sock *sk = raw6_get_first(seq);
	if (sk)
		while (pos && (sk = raw6_get_next(seq, sk)) != NULL)
			--pos;
	return pos ? NULL : sk;
}

static void *raw6_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&raw_v6_lock);
	return *pos ? raw6_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}

static void *raw6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *sk;

	if (v == SEQ_START_TOKEN)
		sk = raw6_get_first(seq);
	else
		sk = raw6_get_next(seq, v);
	++*pos;
	return sk;
}

static void raw6_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&raw_v6_lock);
}

static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
{
	struct ipv6_pinfo *np = inet6_sk(sp);
	struct in6_addr *dest, *src;
	__u16 destp, srcp;

	dest  = &np->daddr;
	src   = &np->rcv_saddr;
	destp = 0;
	srcp  = inet_sk(sp)->num;
	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3], srcp,
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3], 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);
}

static int raw6_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq,
			   "  sl  "
			   "local_address                         "
			   "remote_address                        "
			   "st tx_queue rx_queue tr tm->when retrnsmt"
			   "   uid  timeout inode\n");
	else
		raw6_sock_seq_show(seq, v, raw6_seq_private(seq)->bucket);
	return 0;
}

static const struct seq_operations raw6_seq_ops = {
	.start =	raw6_seq_start,
	.next =		raw6_seq_next,
	.stop =		raw6_seq_stop,
	.show =		raw6_seq_show,
};

static int raw6_seq_open(struct inode *inode, struct file *file)
{
	return seq_open_private(file, &raw6_seq_ops,
			sizeof(struct raw6_iter_state));
}

static const struct file_operations raw6_seq_fops = {
	.owner =	THIS_MODULE,
	.open =		raw6_seq_open,
	.read =		seq_read,
	.llseek =	seq_lseek,
	.release =	seq_release_private,
};

int __init raw6_proc_init(void)
{
	if (!proc_net_fops_create(&init_net, "raw6", S_IRUGO, &raw6_seq_fops))
		return -ENOMEM;
	return 0;
}

void raw6_proc_exit(void)
{
	proc_net_remove(&init_net, "raw6");
}
#endif	/* CONFIG_PROC_FS */