int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, struct ipv6_txoptions *opt, struct flowi *fl, struct rt6_info *rt,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
unsigned int maxfraglen, fragheaderlen;
int exthdrlen;
int hh_len;
int mtu;
int copy;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
if (flags&MSG_PROBE)
return 0;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (np->cork.opt == NULL) {
np->cork.opt = kmalloc(opt->tot_len,
sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
} else if (np->cork.opt->tot_len < opt->tot_len) {
printk(KERN_DEBUG "ip6_append_data: invalid option length\n");
return -EINVAL;
}
memcpy(np->cork.opt, opt, opt->tot_len);
inet->cork.flags |= IPCORK_OPT;
/* need source address above miyazawa*/
}
dst_hold(&rt->u.dst);
np->cork.rt = rt;
inet->cork.fl = *fl;
np->cork.hop_limit = hlimit;
inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
if (dst_allfrag(rt->u.dst.path))
inet->cork.flags |= IPCORK_ALLFRAG;
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
rt = np->cork.rt;
fl = &inet->cork.fl;
if (inet->cork.flags & IPCORK_OPT)
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = inet->cork.fragsize;
}
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + (opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
inet->cork.length += length;
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
/* There's no room in the current skb */
if (skb_prev)
fraggap = skb_prev->len - maxfraglen;
else
fraggap = 0;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
if ((flags & MSG_MORE) &&
!(rt->u.dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
/*
* The last fragment gets additional space at tail.
* Note: we overallocate on fragments with MSG_MODE
* because we have no idea if we're the last one.
*/
if (datalen == length + fraggap)
alloclen += rt->u.dst.trailer_len;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation */
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb->nh.raw = data + exthdrlen;
data += fragheaderlen;
skb->h.raw = data + exthdrlen;
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
skb_trim(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = sk->sk_sndmsg_page;
int off = sk->sk_sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != frag->page) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
get_page(page);
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->sk_allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
skb->truesize += PAGE_SIZE;
atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
sk->sk_sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
}
offset += copy;
length -= copy;
}
return 0;
error:
inet->cork.length -= length;
IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
return err;
}
static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned flags)
{
struct ipv6_pinfo *np = inet6_sk(sk);
int len;
int val;
if (ip6_mroute_opt(optname))
return ip6_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
case IPV6_ADDRFORM:
if (sk->sk_protocol != IPPROTO_UDP &&
sk->sk_protocol != IPPROTO_UDPLITE &&
sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
if (sk->sk_state != TCP_ESTABLISHED)
return -ENOTCONN;
val = sk->sk_family;
break;
case MCAST_MSFILTER:
{
struct group_filter gsf;
int err;
if (len < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
return -EFAULT;
if (gsf.gf_group.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
lock_sock(sk);
err = ip6_mc_msfget(sk, &gsf,
(struct group_filter __user *)optval, optlen);
release_sock(sk);
return err;
}
case IPV6_2292PKTOPTIONS:
{
struct msghdr msg;
struct sk_buff *skb;
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
lock_sock(sk);
skb = np->pktoptions;
if (skb)
atomic_inc(&skb->users);
release_sock(sk);
if (skb) {
int err = datagram_recv_ctl(sk, &msg, skb);
kfree_skb(skb);
if (err)
return err;
} else {
if (np->rxopt.bits.rxinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxhlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxoinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
}
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IPV6_MTU:
{
struct dst_entry *dst;
val = 0;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = dst_mtu(dst);
rcu_read_unlock();
if (!val)
return -ENOTCONN;
break;
}
case IPV6_V6ONLY:
val = np->ipv6only;
break;
case IPV6_RECVPKTINFO:
val = np->rxopt.bits.rxinfo;
break;
case IPV6_2292PKTINFO:
val = np->rxopt.bits.rxoinfo;
break;
case IPV6_RECVHOPLIMIT:
val = np->rxopt.bits.rxhlim;
break;
case IPV6_2292HOPLIMIT:
val = np->rxopt.bits.rxohlim;
break;
case IPV6_RECVRTHDR:
val = np->rxopt.bits.srcrt;
break;
case IPV6_2292RTHDR:
val = np->rxopt.bits.osrcrt;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
lock_sock(sk);
len = ipv6_getsockopt_sticky(sk, np->opt,
optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
return len;
return put_user(len, optlen);
}
case IPV6_RECVHOPOPTS:
val = np->rxopt.bits.hopopts;
break;
case IPV6_2292HOPOPTS:
val = np->rxopt.bits.ohopopts;
break;
case IPV6_RECVDSTOPTS:
val = np->rxopt.bits.dstopts;
break;
case IPV6_2292DSTOPTS:
val = np->rxopt.bits.odstopts;
break;
case IPV6_TCLASS:
val = np->tclass;
break;
case IPV6_RECVTCLASS:
val = np->rxopt.bits.rxtclass;
break;
case IPV6_FLOWINFO:
val = np->rxopt.bits.rxflow;
break;
case IPV6_RECVPATHMTU:
val = np->rxopt.bits.rxpmtu;
break;
case IPV6_PATHMTU:
{
struct dst_entry *dst;
struct ip6_mtuinfo mtuinfo;
if (len < sizeof(mtuinfo))
return -EINVAL;
len = sizeof(mtuinfo);
memset(&mtuinfo, 0, sizeof(mtuinfo));
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
mtuinfo.ip6m_mtu = dst_mtu(dst);
rcu_read_unlock();
if (!mtuinfo.ip6m_mtu)
return -ENOTCONN;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &mtuinfo, len))
return -EFAULT;
return 0;
break;
}
case IPV6_TRANSPARENT:
val = inet_sk(sk)->transparent;
break;
case IPV6_RECVORIGDSTADDR:
val = np->rxopt.bits.rxorigdstaddr;
break;
case IPV6_UNICAST_HOPS:
case IPV6_MULTICAST_HOPS:
{
struct dst_entry *dst;
if (optname == IPV6_UNICAST_HOPS)
val = np->hop_limit;
else
val = np->mcast_hops;
if (val < 0) {
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = ip6_dst_hoplimit(dst);
rcu_read_unlock();
}
if (val < 0)
val = sock_net(sk)->ipv6.devconf_all->hop_limit;
break;
}
case IPV6_MULTICAST_LOOP:
val = np->mc_loop;
break;
case IPV6_MULTICAST_IF:
val = np->mcast_oif;
break;
case IPV6_MTU_DISCOVER:
val = np->pmtudisc;
break;
case IPV6_RECVERR:
val = np->recverr;
break;
case IPV6_FLOWINFO_SEND:
val = np->sndflow;
break;
case IPV6_ADDR_PREFERENCES:
val = 0;
if (np->srcprefs & IPV6_PREFER_SRC_TMP)
val |= IPV6_PREFER_SRC_TMP;
else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC)
val |= IPV6_PREFER_SRC_PUBLIC;
else {
/* XXX: should we return system default? */
val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT;
}
if (np->srcprefs & IPV6_PREFER_SRC_COA)
val |= IPV6_PREFER_SRC_COA;
else
val |= IPV6_PREFER_SRC_HOME;
break;
case IPV6_MINHOPCOUNT:
val = np->min_hopcount;
break;
case IPV6_DONTFRAG:
val = np->dontfrag;
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 dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
sk->sk_v6_daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
* DCCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &dccp_ipv6_mapped;
sk->sk_backlog_rcv = dccp_v4_do_rcv;
err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &dccp_ipv6_af_ops;
sk->sk_backlog_rcv = dccp_v6_do_rcv;
goto failure;
}
np->saddr = sk->sk_v6_rcv_saddr;
return err;
}
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
saddr = &sk->sk_v6_rcv_saddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
sk->sk_v6_rcv_saddr = *saddr;
}
/* set the source address */
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet6_hash_connect(&dccp_death_row, sk);
if (err)
goto late_failure;
dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
err = dccp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
/*
* This routine is called by the ICMP module when it gets some sort of error
* condition. If err < 0 then the socket should be closed and the error
* returned to the user. If err > 0 it's just the icmp type << 8 | icmp code.
* After adjustment header points to the first 8 bytes of the tcp header. We
* need to find the appropriate port.
*
* The locking strategy used here is very "optimistic". When someone else
* accesses the socket the ICMP is just dropped and for some paths there is no
* check at all. A more general error queue to queue errors for later handling
* is probably better.
*/
static void dccp_v4_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (struct iphdr *)skb->data;
const u8 offset = iph->ihl << 2;
const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
struct dccp_sock *dp;
struct inet_sock *inet;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct sock *sk;
__u64 seq;
int err;
struct net *net = dev_net(skb->dev);
if (skb->len < offset + sizeof(*dh) ||
skb->len < offset + __dccp_basic_hdr_len(dh)) {
ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return;
}
sk = inet_lookup(net, &dccp_hashinfo,
iph->daddr, dh->dccph_dport,
iph->saddr, dh->dccph_sport, inet_iif(skb));
if (sk == NULL) {
ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
* servers this needs to be solved differently.
*/
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
seq = dccp_hdr_seq(dh);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
switch (type) {
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
goto out;
case ICMP_PARAMETERPROB:
err = EPROTO;
break;
case ICMP_DEST_UNREACH:
if (code > NR_ICMP_UNREACH)
goto out;
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
if (!sock_owned_by_user(sk))
dccp_do_pmtu_discovery(sk, iph, info);
goto out;
}
err = icmp_err_convert[code].errno;
break;
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
default:
goto out;
}
switch (sk->sk_state) {
struct request_sock *req , **prev;
case DCCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet_csk_search_req(sk, &prev, dh->dccph_dport,
iph->daddr, iph->saddr);
if (!req)
goto out;
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
WARN_ON(req->sk);
if (seq != dccp_rsk(req)->dreq_iss) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
/*
* Still in RESPOND, just remove it silently.
* There is no good way to pass the error to the newly
* created socket, and POSIX does not want network
* errors returned from accept().
*/
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case DCCP_REQUESTING:
case DCCP_RESPOND:
if (!sock_owned_by_user(sk)) {
DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
/* If we've already connected we will keep trying
* until we time out, or the user gives up.
*
* rfc1122 4.2.3.9 allows to consider as hard errors
* only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
* but it is obsoleted by pmtu discovery).
*
* Note, that in modern internet, where routing is unreliable
* and in each dark corner broken firewalls sit, sending random
* errors ordered by their masters even this two messages finally lose
* their original sense (even Linux sends invalid PORT_UNREACHs)
*
* Now we are in compliance with RFCs.
* --ANK (980905)
*/
inet = inet_sk(sk);
if (!sock_owned_by_user(sk) && inet->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else /* Only an error on timeout */
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct icmp6hdr user_icmph;
int addr_type;
struct in6_addr *daddr;
int iif = 0;
struct flowi6 fl6;
int err;
int hlimit;
struct dst_entry *dst;
struct rt6_info *rt;
struct pingfakehdr pfh;
pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
err = ping_common_sendmsg(AF_INET6, msg, len, &user_icmph,
sizeof(user_icmph));
if (err)
return err;
if (msg->msg_name) {
struct sockaddr_in6 *u = (struct sockaddr_in6 *) msg->msg_name;
if (msg->msg_namelen < sizeof(struct sockaddr_in6) ||
u->sin6_family != AF_INET6) {
return -EINVAL;
}
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != u->sin6_scope_id) {
return -EINVAL;
}
daddr = &(u->sin6_addr);
iif = u->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &np->daddr;
}
if (!iif)
iif = sk->sk_bound_dev_if;
addr_type = ipv6_addr_type(daddr);
if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
return -EINVAL;
if (addr_type & IPV6_ADDR_MAPPED)
return -EINVAL;
/* TODO: use ip6_datagram_send_ctl to get options from cmsg */
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, 1);
if (IS_ERR(dst))
return PTR_ERR(dst);
rt = (struct rt6_info *) dst;
np = inet6_sk(sk);
if (!np)
return -EBADF;
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
else if (!fl6.flowi6_oif)
fl6.flowi6_oif = np->ucast_oif;
pfh.icmph.type = user_icmph.icmp6_type;
pfh.icmph.code = user_icmph.icmp6_code;
pfh.icmph.checksum = 0;
pfh.icmph.un.echo.id = inet->inet_sport;
pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
pfh.iov = msg->msg_iov;
pfh.wcheck = 0;
pfh.family = AF_INET6;
if (ipv6_addr_is_multicast(&fl6.daddr))
hlimit = np->mcast_hops;
else
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
lock_sock(sk);
err = ip6_append_data(sk, ping_getfrag, &pfh, len,
0, hlimit,
np->tclass, NULL, &fl6, rt,
MSG_DONTWAIT, np->dontfrag);
if (err) {
ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
err = icmpv6_push_pending_frames(sk, &fl6,
(struct icmp6hdr *) &pfh.icmph,
len);
}
release_sock(sk);
if (err)
return err;
return len;
}
static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
struct flowi4 fl4;
int free = 0;
__be32 daddr;
__be32 saddr;
u8 tos;
int err;
struct ip_options_data opt_copy;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB)
goto out;
if (msg->msg_namelen) {
struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
err = -EINVAL;
if (msg->msg_namelen < sizeof(*usin))
goto out;
if (usin->sin_family != AF_INET) {
pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n",
__func__, current->comm);
err = -EAFNOSUPPORT;
if (usin->sin_family)
goto out;
}
daddr = usin->sin_addr.s_addr;
} else {
err = -EDESTADDRREQ;
if (sk->sk_state != TCP_ESTABLISHED)
goto out;
daddr = inet->inet_daddr;
}
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc);
if (err)
goto out;
if (ipc.opt)
free = 1;
}
saddr = ipc.addr;
ipc.addr = daddr;
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt) {
memcpy(&opt_copy, inet_opt,
sizeof(*inet_opt) + inet_opt->opt.optlen);
ipc.opt = &opt_copy.opt;
}
rcu_read_unlock();
}
if (ipc.opt) {
err = -EINVAL;
if (inet->hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
goto done;
daddr = ipc.opt->opt.faddr;
}
}
tos = RT_CONN_FLAGS(sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
} else if (!ipc.oif)
ipc.oif = inet->uc_index;
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP,
daddr, saddr, 0, 0);
if (!inet->hdrincl) {
err = raw_probe_proto_opt(&fl4, msg);
if (err)
goto done;
}
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
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, &fl4, msg->msg_iov, len,
&rt, msg->msg_flags);
else {
if (!ipc.addr)
ipc.addr = fl4.daddr;
lock_sock(sk);
err = ip_append_data(sk, &fl4, 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, &fl4);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
}
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->dst);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data;
const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
if (skb->len < offset + sizeof(*dh) ||
skb->len < offset + __dccp_basic_hdr_len(dh)) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
sk = inet6_lookup(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
seq = dccp_hdr_seq(dh);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
goto out;
/* icmp should have updated the destination cache entry */
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi fl;
/* BUGGG_FUTURE: Again, it is not clear how
to handle rthdr case. Ignore this complexity
for now.
*/
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
security_sk_classify_flow(sk, &fl);
err = ip6_dst_lookup(sk, &dst, &fl);
if (err) {
sk->sk_err_soft = -err;
goto out;
}
err = xfrm_lookup(net, &dst, &fl, sk, 0);
if (err < 0) {
sk->sk_err_soft = -err;
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
dccp_sync_mss(sk, dst_mtu(dst));
} /* else let the usual retransmit timer handle it */
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case DCCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
&hdr->daddr, &hdr->saddr,
inet6_iif(skb));
if (req == NULL)
goto out;
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
WARN_ON(req->sk != NULL);
if (seq != dccp_rsk(req)->dreq_iss) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
/*
* Wake people up to see the error
* (see connect in sock.c)
*/
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
int offset)
{
struct inet_sock *inet = inet_sk(skb->sk);
unsigned int flags = inet->cmsg_flags;
/* Ordered by supposed usage frequency */
if (flags & IP_CMSG_PKTINFO) {
ip_cmsg_recv_pktinfo(msg, skb);
flags &= ~IP_CMSG_PKTINFO;
if (!flags)
return;
}
if (flags & IP_CMSG_TTL) {
ip_cmsg_recv_ttl(msg, skb);
flags &= ~IP_CMSG_TTL;
if (!flags)
return;
}
if (flags & IP_CMSG_TOS) {
ip_cmsg_recv_tos(msg, skb);
flags &= ~IP_CMSG_TOS;
if (!flags)
return;
}
if (flags & IP_CMSG_RECVOPTS) {
ip_cmsg_recv_opts(msg, skb);
flags &= ~IP_CMSG_RECVOPTS;
if (!flags)
return;
}
if (flags & IP_CMSG_RETOPTS) {
ip_cmsg_recv_retopts(msg, skb);
flags &= ~IP_CMSG_RETOPTS;
if (!flags)
return;
}
if (flags & IP_CMSG_PASSSEC) {
ip_cmsg_recv_security(msg, skb);
flags &= ~IP_CMSG_PASSSEC;
if (!flags)
return;
}
if (flags & IP_CMSG_ORIGDSTADDR) {
ip_cmsg_recv_dstaddr(msg, skb);
flags &= ~IP_CMSG_ORIGDSTADDR;
if (!flags)
return;
}
if (flags & IP_CMSG_CHECKSUM)
ip_cmsg_recv_checksum(msg, skb, offset);
}
/*
* Handle MSG_ERRQUEUE
*/
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb;
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct {
struct sock_extended_err ee;
struct sockaddr_in offender;
} errhdr;
int err;
int copied;
WARN_ON_ONCE(sk->sk_family == AF_INET6);
err = -EAGAIN;
skb = sock_dequeue_err_skb(sk);
if (!skb)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto out_free_skb;
sock_recv_timestamp(msg, sk, skb);
serr = SKB_EXT_ERR(skb);
if (sin && ipv4_datagram_support_addr(serr)) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
sin = &errhdr.offender;
memset(sin, 0, sizeof(*sin));
if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
if (inet_sk(sk)->cmsg_flags)
ip_cmsg_recv(msg, skb);
}
put_cmsg(msg, SOL_IP, IP_RECVERR, sizeof(errhdr), &errhdr);
/* Now we could try to dump offended packet options */
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
out_free_skb:
kfree_skb(skb);
out:
return err;
}
int ip6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb, *tmp_skb;
struct sk_buff **tail_skb;
struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
struct ipv6hdr *hdr;
struct ipv6_txoptions *opt = np->cork.opt;
struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
unsigned char proto = fl6->flowi6_proto;
int err = 0;
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
goto out;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
if (skb->data < skb_network_header(skb))
__skb_pull(skb, skb_network_offset(skb));
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
__skb_pull(tmp_skb, skb_network_header_len(skb));
*tail_skb = tmp_skb;
tail_skb = &(tmp_skb->next);
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
}
/* Allow local fragmentation. */
if (np->pmtudisc < IPV6_PMTUDISC_DO)
skb->local_df = 1;
*final_dst = fl6->daddr;
__skb_pull(skb, skb_network_header_len(skb));
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel);
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
hdr->daddr = *final_dst;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, dst_clone(&rt->dst));
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
err = ip6_local_out(skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
}
out:
ip6_cork_release(inet, np);
return err;
error:
IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
goto out;
}
static int do_ip_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
int val;
int len;
if (level != SOL_IP)
return -EOPNOTSUPP;
if (ip_mroute_opt(optname))
return ip_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
unsigned char optbuf[sizeof(struct ip_options)+40];
struct ip_options *opt = (struct ip_options *)optbuf;
struct ip_options_rcu *inet_opt;
inet_opt = rcu_dereference_protected(inet->inet_opt,
sock_owned_by_user(sk));
opt->optlen = 0;
if (inet_opt)
memcpy(optbuf, &inet_opt->opt,
sizeof(struct ip_options) +
inet_opt->opt.optlen);
release_sock(sk);
if (opt->optlen == 0)
return put_user(0, optlen);
ip_options_undo(opt);
len = min_t(unsigned int, len, opt->optlen);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, opt->__data, len))
return -EFAULT;
return 0;
}
case IP_PKTINFO:
val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0;
break;
case IP_RECVTTL:
val = (inet->cmsg_flags & IP_CMSG_TTL) != 0;
break;
case IP_RECVTOS:
val = (inet->cmsg_flags & IP_CMSG_TOS) != 0;
break;
case IP_RECVOPTS:
val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
break;
case IP_RETOPTS:
val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
break;
case IP_PASSSEC:
val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0;
break;
case IP_RECVORIGDSTADDR:
val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
break;
case IP_CHECKSUM:
val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
break;
case IP_TOS:
val = inet->tos;
break;
case IP_TTL:
val = (inet->uc_ttl == -1 ?
sysctl_ip_default_ttl :
inet->uc_ttl);
break;
case IP_HDRINCL:
val = inet->hdrincl;
break;
case IP_NODEFRAG:
val = inet->nodefrag;
break;
case IP_BIND_ADDRESS_NO_PORT:
val = inet->bind_address_no_port;
break;
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;
case IP_MTU:
{
struct dst_entry *dst;
val = 0;
dst = sk_dst_get(sk);
if (dst) {
val = dst_mtu(dst);
dst_release(dst);
}
if (!val) {
release_sock(sk);
return -ENOTCONN;
}
break;
}
case IP_RECVERR:
val = inet->recverr;
break;
case IP_MULTICAST_TTL:
val = inet->mc_ttl;
break;
case IP_MULTICAST_LOOP:
val = inet->mc_loop;
break;
case IP_UNICAST_IF:
val = (__force int)htonl((__u32) inet->uc_index);
break;
case IP_MULTICAST_IF:
{
struct in_addr addr;
len = min_t(unsigned int, len, sizeof(struct in_addr));
addr.s_addr = inet->mc_addr;
release_sock(sk);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &addr, len))
return -EFAULT;
return 0;
}
case IP_MSFILTER:
{
struct ip_msfilter msf;
int err;
if (len < IP_MSFILTER_SIZE(0)) {
release_sock(sk);
return -EINVAL;
}
if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
release_sock(sk);
return -EFAULT;
}
err = ip_mc_msfget(sk, &msf,
(struct ip_msfilter __user *)optval, optlen);
release_sock(sk);
return err;
}
case MCAST_MSFILTER:
{
struct group_filter gsf;
int err;
if (len < GROUP_FILTER_SIZE(0)) {
release_sock(sk);
return -EINVAL;
}
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) {
release_sock(sk);
return -EFAULT;
}
err = ip_mc_gsfget(sk, &gsf,
(struct group_filter __user *)optval,
optlen);
release_sock(sk);
return err;
}
case IP_MULTICAST_ALL:
val = inet->mc_all;
break;
case IP_PKTOPTIONS:
{
struct msghdr msg;
release_sock(sk);
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = (__force void *) optval;
msg.msg_controllen = len;
msg.msg_flags = flags;
if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
struct in_pktinfo info;
info.ipi_addr.s_addr = inet->inet_rcv_saddr;
info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr;
info.ipi_ifindex = inet->mc_index;
put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
if (inet->cmsg_flags & IP_CMSG_TTL) {
int hlim = inet->mc_ttl;
put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
}
if (inet->cmsg_flags & IP_CMSG_TOS) {
int tos = inet->rcv_tos;
put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos);
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IP_FREEBIND:
val = inet->freebind;
break;
case IP_TRANSPARENT:
val = inet->transparent;
break;
case IP_MINTTL:
val = inet->min_ttl;
break;
default:
release_sock(sk);
return -ENOPROTOOPT;
}
release_sock(sk);
if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) {
unsigned char ucval = (unsigned char)val;
len = 1;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &ucval, 1))
return -EFAULT;
} else {
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;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
int copy;
int err;
int offset = 0;
__u8 tx_flags = 0;
if (flags&MSG_PROBE)
return 0;
cork = &inet->cork.base;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (WARN_ON(np->cork.opt))
return -EINVAL;
np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
np->cork.opt->tot_len = opt->tot_len;
np->cork.opt->opt_flen = opt->opt_flen;
np->cork.opt->opt_nflen = opt->opt_nflen;
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
sk->sk_allocation);
if (opt->dst0opt && !np->cork.opt->dst0opt)
return -ENOBUFS;
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
sk->sk_allocation);
if (opt->dst1opt && !np->cork.opt->dst1opt)
return -ENOBUFS;
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
sk->sk_allocation);
if (opt->hopopt && !np->cork.opt->hopopt)
return -ENOBUFS;
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
sk->sk_allocation);
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
dst_hold(&rt->dst);
cork->dst = &rt->dst;
inet->cork.fl.u.ip6 = *fl6;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
cork->fragsize = mtu;
if (dst_allfrag(rt->dst.path))
cork->flags |= IPCORK_ALLFRAG;
cork->length = 0;
exthdrlen = (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
} else {
rt = (struct rt6_info *)cork->dst;
fl6 = &inet->cork.fl.u.ip6;
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/* For UDP, check if TX timestamp is enabled */
if (sk->sk_type == SOCK_DGRAM)
sock_tx_timestamp(sk, &tx_flags);
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_RAW)) {
ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
skb = skb_peek_tail(&sk->sk_write_queue);
cork->length += length;
if (((length > mtu) ||
(skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
hh_len, fragheaderlen,
transhdrlen, mtu, flags, rt);
if (err)
goto error;
return 0;
}
if (!skb)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
fraggap = skb->len - maxfraglen;
else
fraggap = 0;
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt,
orig_mtu);
skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
alloclen += dst_exthdrlen;
if (datalen != length + fraggap) {
/*
* this is not the last fragment, the trailer
* space is regarded as data space.
*/
datalen += rt->dst.trailer_len;
}
alloclen += rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
else {
/* Only the initial fragment
* is time stamped.
*/
tx_flags = 0;
}
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = CHECKSUM_NONE;
skb->csum = 0;
/* reserve for fragmentation and ipsec header */
skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
dst_exthdrlen);
if (sk->sk_type == SOCK_DGRAM)
skb_shinfo(skb)->tx_flags = tx_flags;
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
struct page_frag *pfrag = sk_page_frag(sk);
err = -ENOMEM;
if (!sk_page_frag_refill(sk, pfrag))
goto error;
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
err = -EMSGSIZE;
if (i == MAX_SKB_FRAGS)
goto error;
__skb_fill_page_desc(skb, i, pfrag->page,
pfrag->offset, 0);
skb_shinfo(skb)->nr_frags = ++i;
get_page(pfrag->page);
}
copy = min_t(int, copy, pfrag->size - pfrag->offset);
if (getfrag(from,
page_address(pfrag->page) + pfrag->offset,
offset, copy, skb->len, skb) < 0)
goto error_efault;
pfrag->offset += copy;
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error_efault:
err = -EFAULT;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
struct inet_opt *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
int free = 0;
u32 daddr;
u32 saddr;
u8 tos;
int err;
err = -EMSGSIZE;
if (len < 0 || len > 0xFFFF)
goto out;
/*
* Check the flags.
*/
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message */
goto out; /* compatibility */
/*
* Get and verify the address.
*/
if (msg->msg_namelen) {
struct sockaddr_in *usin = (struct sockaddr_in*)msg->msg_name;
err = -EINVAL;
if (msg->msg_namelen < sizeof(*usin))
goto out;
if (usin->sin_family != AF_INET) {
static int complained;
if (!complained++)
printk(KERN_INFO "%s forgot to set AF_INET in "
"raw sendmsg. Fix it!\n",
current->comm);
err = -EINVAL;
if (usin->sin_family)
goto out;
}
daddr = usin->sin_addr.s_addr;
/* ANK: I did not forget to get protocol from port field.
* I just do not know, who uses this weirdness.
* IP_HDRINCL is much more convenient.
*/
} else {
err = -EDESTADDRREQ;
if (sk->sk_state != TCP_ESTABLISHED)
goto out;
daddr = inet->daddr;
}
ipc.addr = inet->saddr;
ipc.opt = NULL;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
err = ip_cmsg_send(msg, &ipc);
if (err)
goto out;
if (ipc.opt)
free = 1;
}
saddr = ipc.addr;
ipc.addr = daddr;
if (!ipc.opt)
ipc.opt = inet->opt;
if (ipc.opt) {
err = -EINVAL;
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
if (inet->hdrincl)
goto done;
if (ipc.opt->srr) {
if (!daddr)
goto done;
daddr = ipc.opt->faddr;
}
}
tos = RT_TOS(inet->tos) | sk->sk_localroute;
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,
};
err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT));
}
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: return err < 0 ? err : len;
do_confirm:
dst_confirm(&rt->u.dst);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
static int raw_send_hdrinc(struct sock *sk, void *from, int length,
struct rtable *rt,
unsigned int flags)
{
struct inet_opt *inet = inet_sk(sk);
int hh_len;
struct iphdr *iph;
struct sk_buff *skb;
int err;
if (length > rt->u.dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport,
rt->u.dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
skb = sock_alloc_send_skb(sk, length+hh_len+15,
flags&MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, hh_len);
skb->priority = sk->sk_priority;
skb->dst = dst_clone(&rt->u.dst);
skb->nh.iph = iph = (struct iphdr *)skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->h.raw = skb->nh.raw;
err = memcpy_fromiovecend((void *)iph, from, 0, length);
if (err)
goto error_fault;
/* We don't modify invalid header */
if (length >= sizeof(*iph) && iph->ihl * 4 <= length) {
if (!iph->saddr)
iph->saddr = rt->rt_src;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(iph, &rt->u.dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
dst_output);
if (err > 0)
err = inet->recverr ? net_xmit_errno(err) : 0;
if (err)
goto error;
out:
return 0;
error_fault:
err = -EFAULT;
kfree_skb(skb);
error:
IP_INC_STATS(OutDiscards);
return err;
}
/*
* This routine is called by the ICMP module when it gets some sort of error
* condition. If err < 0 then the socket should be closed and the error
* returned to the user. If err > 0 it's just the icmp type << 8 | icmp code.
* After adjustment header points to the first 8 bytes of the tcp header. We
* need to find the appropriate port.
*
* The locking strategy used here is very "optimistic". When someone else
* accesses the socket the ICMP is just dropped and for some paths there is no
* check at all. A more general error queue to queue errors for later handling
* is probably better.
*/
static void dccp_v4_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (struct iphdr *)skb->data;
const u8 offset = iph->ihl << 2;
const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct inet_sock *inet;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct sock *sk;
__u64 seq;
int err;
struct net *net = dev_net(skb->dev);
/* Only need dccph_dport & dccph_sport which are the first
* 4 bytes in dccp header.
* Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
*/
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet_lookup_established(net, &dccp_hashinfo,
iph->daddr, dh->dccph_dport,
iph->saddr, ntohs(dh->dccph_sport),
inet_iif(skb));
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
seq = dccp_hdr_seq(dh);
if (sk->sk_state == DCCP_NEW_SYN_RECV)
return dccp_req_err(sk, seq);
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
* servers this needs to be solved differently.
*/
if (sock_owned_by_user(sk))
__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
switch (type) {
case ICMP_REDIRECT:
dccp_do_redirect(skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
goto out;
case ICMP_PARAMETERPROB:
err = EPROTO;
break;
case ICMP_DEST_UNREACH:
if (code > NR_ICMP_UNREACH)
goto out;
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
if (!sock_owned_by_user(sk))
dccp_do_pmtu_discovery(sk, iph, info);
goto out;
}
err = icmp_err_convert[code].errno;
break;
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
default:
goto out;
}
switch (sk->sk_state) {
case DCCP_REQUESTING:
case DCCP_RESPOND:
if (!sock_owned_by_user(sk)) {
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
/* If we've already connected we will keep trying
* until we time out, or the user gives up.
*
* rfc1122 4.2.3.9 allows to consider as hard errors
* only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
* but it is obsoleted by pmtu discovery).
*
* Note, that in modern internet, where routing is unreliable
* and in each dark corner broken firewalls sit, sending random
* errors ordered by their masters even this two messages finally lose
* their original sense (even Linux sends invalid PORT_UNREACHs)
*
* Now we are in compliance with RFCs.
* --ANK (980905)
*/
inet = inet_sk(sk);
if (!sock_owned_by_user(sk) && inet->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else /* Only an error on timeout */
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static int do_ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
struct inet_sock *inet = inet_sk(sk);
int val = 0, err;
bool needs_rtnl = setsockopt_needs_rtnl(optname);
switch (optname) {
case IP_PKTINFO:
case IP_RECVTTL:
case IP_RECVOPTS:
case IP_RECVTOS:
case IP_RETOPTS:
case IP_TOS:
case IP_TTL:
case IP_HDRINCL:
case IP_MTU_DISCOVER:
case IP_RECVERR:
case IP_ROUTER_ALERT:
case IP_FREEBIND:
case IP_PASSSEC:
case IP_TRANSPARENT:
case IP_MINTTL:
case IP_NODEFRAG:
case IP_BIND_ADDRESS_NO_PORT:
case IP_UNICAST_IF:
case IP_MULTICAST_TTL:
case IP_MULTICAST_ALL:
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else if (optlen >= sizeof(char)) {
unsigned char ucval;
if (get_user(ucval, (unsigned char __user *) optval))
return -EFAULT;
val = (int) ucval;
}
}
/* If optlen==0, it is equivalent to val == 0 */
if (ip_mroute_opt(optname))
return ip_mroute_setsockopt(sk, optname, optval, optlen);
err = 0;
if (needs_rtnl)
rtnl_lock();
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
struct ip_options_rcu *old, *opt = NULL;
if (optlen > 40)
goto e_inval;
err = ip_options_get_from_user(sock_net(sk), &opt,
optval, optlen);
if (err)
break;
old = rcu_dereference_protected(inet->inet_opt,
sock_owned_by_user(sk));
if (inet->is_icsk) {
struct inet_connection_sock *icsk = inet_csk(sk);
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == PF_INET ||
(!((1 << sk->sk_state) &
(TCPF_LISTEN | TCPF_CLOSE)) &&
inet->inet_daddr != LOOPBACK4_IPV6)) {
#endif
if (old)
icsk->icsk_ext_hdr_len -= old->opt.optlen;
if (opt)
icsk->icsk_ext_hdr_len += opt->opt.optlen;
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
#if IS_ENABLED(CONFIG_IPV6)
}
#endif
}
rcu_assign_pointer(inet->inet_opt, opt);
if (old)
kfree_rcu(old, rcu);
break;
}
case IP_PKTINFO:
if (val)
inet->cmsg_flags |= IP_CMSG_PKTINFO;
else
inet->cmsg_flags &= ~IP_CMSG_PKTINFO;
break;
case IP_RECVTTL:
if (val)
inet->cmsg_flags |= IP_CMSG_TTL;
else
inet->cmsg_flags &= ~IP_CMSG_TTL;
break;
case IP_RECVTOS:
if (val)
inet->cmsg_flags |= IP_CMSG_TOS;
else
inet->cmsg_flags &= ~IP_CMSG_TOS;
break;
case IP_RECVOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RECVOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RECVOPTS;
break;
case IP_RETOPTS:
if (val)
inet->cmsg_flags |= IP_CMSG_RETOPTS;
else
inet->cmsg_flags &= ~IP_CMSG_RETOPTS;
break;
case IP_PASSSEC:
if (val)
inet->cmsg_flags |= IP_CMSG_PASSSEC;
else
inet->cmsg_flags &= ~IP_CMSG_PASSSEC;
break;
case IP_RECVORIGDSTADDR:
if (val)
inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR;
else
inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
break;
case IP_CHECKSUM:
if (val) {
if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
inet_inc_convert_csum(sk);
inet->cmsg_flags |= IP_CMSG_CHECKSUM;
}
} else {
if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
inet_dec_convert_csum(sk);
inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
}
}
break;
case IP_TOS: /* This sets both TOS and Precedence */
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
val |= inet->tos & INET_ECN_MASK;
}
if (inet->tos != val) {
inet->tos = val;
sk->sk_priority = rt_tos2priority(val);
sk_dst_reset(sk);
}
break;
case IP_TTL:
if (optlen < 1)
goto e_inval;
if (val != -1 && (val < 1 || val > 255))
goto e_inval;
inet->uc_ttl = val;
break;
case IP_HDRINCL:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->hdrincl = val ? 1 : 0;
break;
case IP_NODEFRAG:
if (sk->sk_type != SOCK_RAW) {
err = -ENOPROTOOPT;
break;
}
inet->nodefrag = val ? 1 : 0;
break;
case IP_BIND_ADDRESS_NO_PORT:
inet->bind_address_no_port = val ? 1 : 0;
break;
case IP_MTU_DISCOVER:
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT)
goto e_inval;
inet->pmtudisc = val;
break;
case IP_RECVERR:
inet->recverr = !!val;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
break;
case IP_MULTICAST_TTL:
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
if (optlen < 1)
goto e_inval;
if (val == -1)
val = 1;
if (val < 0 || val > 255)
goto e_inval;
inet->mc_ttl = val;
break;
case IP_MULTICAST_LOOP:
if (optlen < 1)
goto e_inval;
inet->mc_loop = !!val;
break;
case IP_UNICAST_IF:
{
struct net_device *dev = NULL;
int ifindex;
if (optlen != sizeof(int))
goto e_inval;
ifindex = (__force int)ntohl((__force __be32)val);
if (ifindex == 0) {
inet->uc_index = 0;
err = 0;
break;
}
dev = dev_get_by_index(sock_net(sk), ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if)
break;
inet->uc_index = ifindex;
err = 0;
break;
}
case IP_MULTICAST_IF:
{
struct ip_mreqn mreq;
struct net_device *dev = NULL;
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
/*
* Check the arguments are allowable
*/
if (optlen < sizeof(struct in_addr))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (optlen >= sizeof(struct ip_mreq)) {
if (copy_from_user(&mreq, optval,
sizeof(struct ip_mreq)))
break;
} else if (optlen >= sizeof(struct in_addr)) {
if (copy_from_user(&mreq.imr_address, optval,
sizeof(struct in_addr)))
break;
}
}
if (!mreq.imr_ifindex) {
if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) {
inet->mc_index = 0;
inet->mc_addr = 0;
err = 0;
break;
}
dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
if (dev)
mreq.imr_ifindex = dev->ifindex;
} else
dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
err = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
err = -EINVAL;
if (sk->sk_bound_dev_if &&
mreq.imr_ifindex != sk->sk_bound_dev_if)
break;
inet->mc_index = mreq.imr_ifindex;
inet->mc_addr = mreq.imr_address.s_addr;
err = 0;
break;
}
case IP_ADD_MEMBERSHIP:
case IP_DROP_MEMBERSHIP:
{
struct ip_mreqn mreq;
err = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
if (optlen < sizeof(struct ip_mreq))
goto e_inval;
err = -EFAULT;
if (optlen >= sizeof(struct ip_mreqn)) {
if (copy_from_user(&mreq, optval, sizeof(mreq)))
break;
} else {
memset(&mreq, 0, sizeof(mreq));
if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq)))
break;
}
if (optname == IP_ADD_MEMBERSHIP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case IP_MSFILTER:
{
struct ip_msfilter *msf;
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
msf = kmalloc(optlen, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(msf, optval, optlen)) {
kfree(msf);
break;
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
msf->imsf_numsrc > sysctl_igmp_max_msf) {
kfree(msf);
err = -ENOBUFS;
break;
}
if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) {
kfree(msf);
err = -EINVAL;
break;
}
err = ip_mc_msfilter(sk, msf, 0);
kfree(msf);
break;
}
case IP_BLOCK_SOURCE:
case IP_UNBLOCK_SOURCE:
case IP_ADD_SOURCE_MEMBERSHIP:
case IP_DROP_SOURCE_MEMBERSHIP:
{
struct ip_mreq_source mreqs;
int omode, add;
if (optlen != sizeof(struct ip_mreq_source))
goto e_inval;
if (copy_from_user(&mreqs, optval, sizeof(mreqs))) {
err = -EFAULT;
break;
}
if (optname == IP_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == IP_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == IP_ADD_SOURCE_MEMBERSHIP) {
struct ip_mreqn mreq;
mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
mreq.imr_address.s_addr = mreqs.imr_interface;
mreq.imr_ifindex = 0;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* IP_DROP_SOURCE_MEMBERSHIP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs, 0);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in *psin;
struct ip_mreqn mreq;
if (optlen < sizeof(struct group_req))
goto e_inval;
err = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(greq)))
break;
psin = (struct sockaddr_in *)&greq.gr_group;
if (psin->sin_family != AF_INET)
goto e_inval;
memset(&mreq, 0, sizeof(mreq));
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_ifindex = greq.gr_interface;
if (optname == MCAST_JOIN_GROUP)
err = ip_mc_join_group(sk, &mreq);
else
err = ip_mc_leave_group(sk, &mreq);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add;
if (optlen != sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
err = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET ||
greqs.gsr_source.ss_family != AF_INET) {
err = -EADDRNOTAVAIL;
break;
}
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct ip_mreqn mreq;
psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group(sk, &mreq);
if (err && err != -EADDRINUSE)
break;
greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
err = ip_mc_source(add, omode, sk, &mreqs,
greqs.gsr_interface);
break;
}
case MCAST_MSFILTER:
{
struct sockaddr_in *psin;
struct ip_msfilter *msf = NULL;
struct group_filter *gsf = NULL;
int msize, i, ifindex;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
err = -ENOBUFS;
break;
}
gsf = kmalloc(optlen, GFP_KERNEL);
if (!gsf) {
err = -ENOBUFS;
break;
}
err = -EFAULT;
if (copy_from_user(gsf, optval, optlen))
goto mc_msf_out;
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > sysctl_igmp_max_msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
err = -EINVAL;
goto mc_msf_out;
}
msize = IP_MSFILTER_SIZE(gsf->gf_numsrc);
msf = kmalloc(msize, GFP_KERNEL);
if (!msf) {
err = -ENOBUFS;
goto mc_msf_out;
}
ifindex = gsf->gf_interface;
psin = (struct sockaddr_in *)&gsf->gf_group;
if (psin->sin_family != AF_INET) {
err = -EADDRNOTAVAIL;
goto mc_msf_out;
}
msf->imsf_multiaddr = psin->sin_addr.s_addr;
msf->imsf_interface = 0;
msf->imsf_fmode = gsf->gf_fmode;
msf->imsf_numsrc = gsf->gf_numsrc;
err = -EADDRNOTAVAIL;
for (i = 0; i < gsf->gf_numsrc; ++i) {
psin = (struct sockaddr_in *)&gsf->gf_slist[i];
if (psin->sin_family != AF_INET)
goto mc_msf_out;
msf->imsf_slist[i] = psin->sin_addr.s_addr;
}
kfree(gsf);
gsf = NULL;
err = ip_mc_msfilter(sk, msf, ifindex);
mc_msf_out:
kfree(msf);
kfree(gsf);
break;
}
case IP_MULTICAST_ALL:
if (optlen < 1)
goto e_inval;
if (val != 0 && val != 1)
goto e_inval;
inet->mc_all = val;
break;
case IP_ROUTER_ALERT:
err = ip_ra_control(sk, val ? 1 : 0, NULL);
break;
case IP_FREEBIND:
if (optlen < 1)
goto e_inval;
inet->freebind = !!val;
break;
case IP_IPSEC_POLICY:
case IP_XFRM_POLICY:
err = -EPERM;
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
break;
err = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IP_TRANSPARENT:
if (!!val && !ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
err = -EPERM;
break;
}
if (optlen < 1)
goto e_inval;
inet->transparent = !!val;
break;
case IP_MINTTL:
if (optlen < 1)
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
inet->min_ttl = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return err;
e_inval:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
return -EINVAL;
}
static int print_request_stats (threadinfo_t *ti, char *page, unsigned int skip_count, unsigned int max_count)
{
struct list_head *head, *curr;
tux_req_t *req;
unsigned int count = 0, size, line_off, len;
char stat_line [LINE_SIZE];
if (!max_count)
BUG();
head = &ti->all_requests;
curr = head->next;
while (curr != head) {
req = list_entry(curr, tux_req_t, all);
curr = curr->next;
count++;
if (count <= skip_count)
continue;
line_off = 0;
#define SP(x...) \
line_off += sprintf(stat_line + line_off, x)
if (req->proto == &tux_proto_http)
SP("0 ");
else
SP("1 ");
SP("%p ", req);
SP("%d ", req->atom_idx);
if (req->atom_idx >= 1)
SP("%p ", req->atoms[0]);
else
SP("........ ");
if (req->atom_idx >= 2)
SP("%p ", req->atoms[1]);
else
SP("........ ");
if (!list_empty(&req->work)) SP("W"); else SP(".");
if (!list_empty(&req->free)) SP("F"); else SP(".");
if (!list_empty(&req->lru)) SP("L"); else SP(".");
if (req->keep_alive) SP("K"); else SP(".");
if (req->idle_input) SP("I"); else SP(".");
if (timer_pending(&req->keepalive_timer))
SP("T(%lu/%lu)",jiffies,req->keepalive_timer.expires); else SP(".");
if (req->wait_output_space) SP("O"); else SP(".");
if (timer_pending(&req->output_timer))
SP("T"); else SP(".");
SP(" %d ", req->error);
SP(" %d ", req->status);
#define SP_HOST(ip,port) \
SP("%d.%d.%d.%d:%d ",NIPQUAD(ip),port)
if (req->sock) {
if (req->sock->sk)
SP("%d:", req->sock->sk->sk_state);
else
SP("-2:");
} else
SP("-1:");
SP_HOST(req->client_addr, req->client_port);
SP("%Ld ", req->total_file_len);
SP("%Ld ", req->in_file ? req->in_file->f_pos : -1);
if (req->proto == &tux_proto_http) {
SP("%d ", req->method);
SP("%d ", req->version);
}
if (req->proto == &tux_proto_ftp) {
SP("%d ", req->ftp_command);
if (req->data_sock) {
if (req->data_sock->sk)
SP("%d:",req->data_sock->sk->sk_state);
else
SP("-2:");
if (req->data_sock->sk)
SP_HOST(inet_sk(req->data_sock->sk)->daddr,
inet_sk(req->data_sock->sk)->dport);
else
SP("-1:-1 ");
} else
SP("-1 ");
}
SP("%p/%p %p/%p ", req->sock, req->sock ? req->sock->sk : (void *)-1, req->data_sock, req->data_sock ? req->data_sock->sk : (void *)-1);
SP("%d\n", req->parsed_len);
len = req->headers_len;
if (len > 500)
len = 500;
SP("\n%d\n", len);
memcpy(stat_line + line_off, req->headers, len);
line_off += len;
len = req->objectname_len;
if (len > 100)
len = 100;
SP("\n%d\n", len);
memcpy(stat_line + line_off, req->objectname, len);
line_off += len;
SP("\n\n<END>");
if (line_off >= LINE_SIZE)
BUG();
Dprintk("printing req %p, count %d, page %p: {%s}.\n", req, count, page, stat_line);
size = sprintf(page, "%-*s\n", LINE_SIZE-1, stat_line);
if (size != LINE_SIZE)
BUG();
page += LINE_SIZE;
if (count-skip_count >= max_count)
break;
}
Dprintk("count: %d.\n", count-skip_count);
return count - skip_count;
}
//--------------------------------------------------------------------------------
static int tuxguardian_socket_listen(struct socket *listen_sock, int backlog)
{
int retval;
struct tg_query answer;
struct socket *sock;
// local communication is always allowed
// (notice that since we are creating local sockets to
// communicate w/ userspace this function SHOULD NOT
// analyse local sockets or it'll loop)
if (! is_internet_socket(listen_sock->sk->sk_family)) {
// printk("local communication always allowed\n");
return 0;
}
/* else { */
/* printk("\nAsking if '%s' may be a server - ", current->comm); */
/* print_socket_info(listen_sock->sk->sk_family, listen_sock->sk->sk_type); */
/* printk("\n protocol %s at port %d\n", listen_sock->sk->sk_prot->name, */
/* htons(((struct inet_opt *)inet_sk(listen_sock->sk))->sport)); */
/* } */
retval = send_question_permit(&sock, current->pid, TG_PERMIT_SERVER);
if (retval < 0)
return -EPERM;
// TODO: timeout
// /usr/src/linux269/fs/ncpfs/sock.c
// /usr/src/linux269/net/bluetooth/rfcomm/sock.c
// sock_rcvtimeo
retval = read_answer_from_daemon(sock, &answer);
if (retval < 0)
return -EPERM;
switch (answer.query_data) {
case YES:
return 0;
case NO_ACCESS_IS_DENIED:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (ACCESS IS DENIED)\n", current->pid, current->comm,
htons(((struct inet_sock *)inet_sk(listen_sock->sk))->sport));
return -EPERM;
case NO_WRONG_HASH:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (WRONG MD5HASH)\n", current->pid, current->comm,
htons(((struct inet_sock*)inet_sk(listen_sock->sk))->sport));
return -EPERM;
case NO_NOT_IN_HASHTABLE:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (APP NOT PERMITTED)\n", current->pid, current->comm,
htons(((struct inet_sock *)inet_sk(listen_sock->sk))->sport));
return -EPERM;
case NO_ERROR_IN_DAEMON:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (ERR IN DAEMON)\n", current->pid, current->comm,
htons(((struct inet_sock *)inet_sk(listen_sock->sk))->sport));
return -EPERM;
case NO_USER_FORBID:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (USER FORBID)\n", current->pid, current->comm,
htons(((struct inet_sock *)inet_sk(listen_sock->sk))->sport));
return -EPERM;
case NO_ERROR_IN_FRONTEND:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (ERR IN FRONTEND)\n", current->pid, current->comm,
htons(((struct inet_sock *)inet_sk(listen_sock->sk))->sport));
return -EPERM;
default:
printk(KERN_INFO "TuxGuardian: process #%d (%s@%d) will not be allowed to act like a server"
" (UNKNOWN ANSWER %d)\n", current->pid, current->comm, answer.query_data,
htons(((struct inet_sock *)inet_sk(listen_sock->sk))->sport));
return -EPERM;
}
/* printk("resposta -> sender: %d seqno: %d query_type: %d query_data: %d\n", */
/* (int)answer.sender, answer.seqno, (int)answer.query_type, answer.query_data); */
// connection is closed by the daemon
// sock_release(sock);
}
static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct inet_sock *newinet;
struct dccp_sock *newdp;
struct dccp6_sock *newdp6;
struct sock *newsk;
struct ipv6_txoptions *opt;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newdp = dccp_sk(newsk);
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF),
newinet->daddr);
ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF),
newinet->saddr);
ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, dccp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
opt = np->opt;
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (dst == NULL) {
struct in6_addr *final_p = NULL, final;
struct flowi fl;
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
if (opt != NULL && opt->srcrt != NULL) {
const 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;
}
ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet_rsk(req)->rmt_port;
fl.fl_ip_sport = inet_rsk(req)->loc_port;
security_sk_classify_flow(sk, &fl);
if (ip6_dst_lookup(sk, &dst, &fl))
goto out;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
goto out;
}
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, dccp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
__ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
if (!sysctl_tcp_use_sg)
newsk->sk_route_caps &= ~NETIF_F_SG;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newdp = dccp_sk(newsk);
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr);
ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr);
ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr);
newsk->sk_bound_dev_if = ireq6->iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
if (ireq6->pktopts != NULL) {
newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
kfree_skb(ireq6->pktopts);
ireq6->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* Clone native IPv6 options from listening socket (if any)
*
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
if (opt != NULL) {
newnp->opt = ipv6_dup_options(newsk, opt);
if (opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newnp->opt != NULL)
inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
newnp->opt->opt_flen);
dccp_sync_mss(newsk, dst_mtu(dst));
newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;
__inet6_hash(newsk);
__inet_inherit_port(sk, newsk);
return newsk;
out_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
if (opt != NULL && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
dst_release(dst);
return NULL;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
u32 daddr, nexthop;
int tmp;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (dccp_service_not_initialized(sk))
return -EPROTO;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
if (inet->opt != NULL && inet->opt->srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet->opt->faddr;
}
tmp = ip_route_connect(&rt, nexthop, inet->saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
inet->sport, usin->sin_port, sk);
if (tmp < 0)
return tmp;
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet->opt == NULL || !inet->opt->srr)
daddr = rt->rt_dst;
if (inet->saddr == 0)
inet->saddr = rt->rt_src;
inet->rcv_saddr = inet->saddr;
inet->dport = usin->sin_port;
inet->daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt != NULL)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
err = ip_route_newports(&rt, IPPROTO_DCCP, inet->sport, inet->dport,
sk);
if (err != 0)
goto failure;
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->u.dst);
dp->dccps_gar =
dp->dccps_iss = secure_dccp_sequence_number(inet->saddr,
inet->daddr,
inet->sport,
usin->sin_port);
dccp_update_gss(sk, dp->dccps_iss);
inet->id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->dport = 0;
goto out;
}
static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p = NULL, final;
struct flowi fl;
struct dst_entry *dst;
int addr_type;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl, 0, sizeof(fl));
if (np->sndflow) {
fl.fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl.fl6_flowlabel);
if (fl.fl6_flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
if (flowlabel == NULL)
return -EINVAL;
ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
np->flow_label = fl.fl6_flowlabel;
/*
* DCCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &dccp_ipv6_mapped;
sk->sk_backlog_rcv = dccp_v4_do_rcv;
err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &dccp_ipv6_af_ops;
sk->sk_backlog_rcv = dccp_v6_do_rcv;
goto failure;
} else {
ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF),
inet->saddr);
ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF),
inet->rcv_saddr);
}
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl.proto = IPPROTO_DCCP;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = usin->sin6_port;
fl.fl_ip_sport = inet->sport;
security_sk_classify_flow(sk, &fl);
if (np->opt != NULL && np->opt->srcrt != NULL) {
const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
goto failure;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
if (err < 0) {
if (err == -EREMOTE)
err = ip6_dst_blackhole(sk, &dst, &fl);
if (err < 0)
goto failure;
}
if (saddr == NULL) {
saddr = &fl.fl6_src;
ipv6_addr_copy(&np->rcv_saddr, saddr);
}
/* set the source address */
ipv6_addr_copy(&np->saddr, saddr);
inet->rcv_saddr = LOOPBACK4_IPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (np->opt != NULL)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->opt->opt_nflen);
inet->dport = usin->sin6_port;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet6_hash_connect(&dccp_death_row, sk);
if (err)
goto late_failure;
dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->sport, inet->dport);
err = dccp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
__sk_dst_reset(sk);
failure:
inet->dport = 0;
sk->sk_route_caps = 0;
return err;
}
/*
* All SKB's seen here are completely headerless. It is our
* job to build the DCCP header, and pass the packet down to
* IP so it can do the same plus pass the packet off to the
* device.
*/
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
if (likely(skb != NULL)) {
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
struct dccp_hdr *dh;
/* XXX For now we're using only 48 bits sequence numbers */
const u32 dccp_header_size = sizeof(*dh) +
sizeof(struct dccp_hdr_ext) +
dccp_packet_hdr_len(dcb->dccpd_type);
int err, set_ack = 1;
u64 ackno = dp->dccps_gsr;
dccp_inc_seqno(&dp->dccps_gss);
switch (dcb->dccpd_type) {
case DCCP_PKT_DATA:
set_ack = 0;
/* fall through */
case DCCP_PKT_DATAACK:
break;
case DCCP_PKT_REQUEST:
set_ack = 0;
/* fall through */
case DCCP_PKT_SYNC:
case DCCP_PKT_SYNCACK:
ackno = dcb->dccpd_seq;
/* fall through */
default:
/*
* Only data packets should come through with skb->sk
* set.
*/
WARN_ON(skb->sk);
skb_set_owner_w(skb, sk);
break;
}
dcb->dccpd_seq = dp->dccps_gss;
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return -EPROTO;
}
/* Build DCCP header and checksum it. */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_type = dcb->dccpd_type;
dh->dccph_sport = inet->sport;
dh->dccph_dport = inet->dport;
dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4;
dh->dccph_ccval = dcb->dccpd_ccval;
dh->dccph_cscov = dp->dccps_pcslen;
/* XXX For now we're using only 48 bits sequence numbers */
dh->dccph_x = 1;
dp->dccps_awh = dp->dccps_gss;
dccp_hdr_set_seq(dh, dp->dccps_gss);
if (set_ack)
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);
switch (dcb->dccpd_type) {
case DCCP_PKT_REQUEST:
dccp_hdr_request(skb)->dccph_req_service =
dp->dccps_service;
break;
case DCCP_PKT_RESET:
dccp_hdr_reset(skb)->dccph_reset_code =
dcb->dccpd_reset_code;
break;
}
icsk->icsk_af_ops->send_check(sk, 0, skb);
if (set_ack)
dccp_event_ack_sent(sk);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
return net_xmit_eval(err);
}
return -ENOBUFS;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
__be16 orig_sport, orig_dport;
__be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
struct ip_options_rcu *inet_opt;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
inet_opt = rcu_dereference_protected(inet->inet_opt,
sock_owned_by_user(sk));
if (inet_opt != NULL && inet_opt->opt.srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet_opt->opt.faddr;
}
orig_sport = inet->inet_sport;
orig_dport = usin->sin_port;
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
orig_sport, orig_dport, sk, true);
if (IS_ERR(rt))
return PTR_ERR(rt);
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet_opt == NULL || !inet_opt->opt.srr)
daddr = fl4->daddr;
if (inet->inet_saddr == 0)
inet->inet_saddr = fl4->saddr;
inet->inet_rcv_saddr = inet->inet_saddr;
inet->inet_dport = usin->sin_port;
inet->inet_daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
if (IS_ERR(rt)) {
rt = NULL;
goto failure;
}
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
inet->inet_id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
goto out;
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct rt6_info *rt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
usin->sin6_addr = flowlabel->dst;
fl6_sock_release(flowlabel);
}
}
if(ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 0x1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if(addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
if (tp->rx_opt.ts_recent_stamp &&
!ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
np->daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &ipv6_mapped;
sk->sk_backlog_rcv = tcp_v4_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &ipv6_specific;
sk->sk_backlog_rcv = tcp_v6_do_rcv;
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
goto failure;
} else {
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&np->rcv_saddr);
}
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = np->daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
final_p = fl6_update_dst(&fl6, np->opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
np->rcv_saddr = *saddr;
}
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
__ip6_dst_store(sk, dst, NULL, NULL);
rt = (struct rt6_info *) dst;
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) {
struct inet_peer *peer = rt6_get_peer(rt);
if (peer) {
inet_peer_refcheck(peer);
if ((u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
}
}
icsk->icsk_ext_hdr_len = 0;
if (np->opt)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->opt->opt_nflen);
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
inet->inet_dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
err = inet6_hash_connect(&tcp_death_row, sk);
if (err)
goto late_failure;
if (!tp->write_seq)
tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
np->daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
err = tcp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
tcp_set_state(sk, TCP_CLOSE);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
int val, valbool;
int retv = -ENOPROTOOPT;
if (optval == NULL)
val=0;
else {
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
} else
val = 0;
}
valbool = (val!=0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
lock_sock(sk);
switch (optname) {
case IPV6_ADDRFORM:
if (optlen < sizeof(int))
goto e_inval;
if (val == PF_INET) {
struct ipv6_txoptions *opt;
struct sk_buff *pktopt;
if (sk->sk_type == SOCK_RAW)
break;
if (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_UDPLITE) {
struct udp_sock *up = udp_sk(sk);
if (up->pending == AF_INET6) {
retv = -EBUSY;
break;
}
} else if (sk->sk_protocol != IPPROTO_TCP)
break;
if (sk->sk_state != TCP_ESTABLISHED) {
retv = -ENOTCONN;
break;
}
if (ipv6_only_sock(sk) ||
!ipv6_addr_v4mapped(&np->daddr)) {
retv = -EADDRNOTAVAIL;
break;
}
fl6_free_socklist(sk);
ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
* remove it from the refcnt debug socks count in the
* original family...
*/
sk_refcnt_debug_dec(sk);
if (sk->sk_protocol == IPPROTO_TCP) {
struct inet_connection_sock *icsk = inet_csk(sk);
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, &tcp_prot, 1);
local_bh_enable();
sk->sk_prot = &tcp_prot;
icsk->icsk_af_ops = &ipv4_specific;
sk->sk_socket->ops = &inet_stream_ops;
sk->sk_family = PF_INET;
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
} else {
struct proto *prot = &udp_prot;
if (sk->sk_protocol == IPPROTO_UDPLITE)
prot = &udplite_prot;
local_bh_disable();
sock_prot_inuse_add(net, sk->sk_prot, -1);
sock_prot_inuse_add(net, prot, 1);
local_bh_enable();
sk->sk_prot = prot;
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
opt = xchg(&np->opt, NULL);
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
sk->sk_destruct = inet_sock_destruct;
/*
* ... and add it to the refcnt debug socks count
* in the new family. -acme
*/
sk_refcnt_debug_inc(sk);
module_put(THIS_MODULE);
retv = 0;
break;
}
goto e_inval;
case IPV6_V6ONLY:
if (optlen < sizeof(int) ||
inet_sk(sk)->inet_num)
goto e_inval;
np->ipv6only = valbool;
retv = 0;
break;
case IPV6_RECVPKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxinfo = valbool;
retv = 0;
break;
case IPV6_2292PKTINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxoinfo = valbool;
retv = 0;
break;
case IPV6_RECVHOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxhlim = valbool;
retv = 0;
break;
case IPV6_2292HOPLIMIT:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxohlim = valbool;
retv = 0;
break;
case IPV6_RECVRTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.srcrt = valbool;
retv = 0;
break;
case IPV6_2292RTHDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.osrcrt = valbool;
retv = 0;
break;
case IPV6_RECVHOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.hopopts = valbool;
retv = 0;
break;
case IPV6_2292HOPOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.ohopopts = valbool;
retv = 0;
break;
case IPV6_RECVDSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.dstopts = valbool;
retv = 0;
break;
case IPV6_2292DSTOPTS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.odstopts = valbool;
retv = 0;
break;
case IPV6_TCLASS:
if (optlen < sizeof(int))
goto e_inval;
if (val < -1 || val > 0xff)
goto e_inval;
/* RFC 3542, 6.5: default traffic class of 0x0 */
if (val == -1)
val = 0;
np->tclass = val;
retv = 0;
break;
case IPV6_RECVTCLASS:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxtclass = valbool;
retv = 0;
break;
case IPV6_FLOWINFO:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxflow = valbool;
retv = 0;
break;
case IPV6_RECVPATHMTU:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxpmtu = valbool;
retv = 0;
break;
case IPV6_TRANSPARENT:
if (!capable(CAP_NET_ADMIN)) {
retv = -EPERM;
break;
}
if (optlen < sizeof(int))
goto e_inval;
/* we don't have a separate transparent bit for IPV6 we use the one in the IPv4 socket */
inet_sk(sk)->transparent = valbool;
retv = 0;
break;
case IPV6_RECVORIGDSTADDR:
if (optlen < sizeof(int))
goto e_inval;
np->rxopt.bits.rxorigdstaddr = valbool;
retv = 0;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
struct ipv6_txoptions *opt;
/* remove any sticky options header with a zero option
* length, per RFC3542.
*/
if (optlen == 0)
optval = NULL;
else if (optval == NULL)
goto e_inval;
else if (optlen < sizeof(struct ipv6_opt_hdr) ||
optlen & 0x7 || optlen > 8 * 255)
goto e_inval;
/* hop-by-hop / destination options are privileged option */
retv = -EPERM;
if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW))
break;
opt = ipv6_renew_options(sk, np->opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
retv = PTR_ERR(opt);
break;
}
/* routing header option needs extra check */
retv = -EINVAL;
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
goto sticky_done;
break;
#endif
default:
goto sticky_done;
}
}
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_PKTINFO:
{
struct in6_pktinfo pkt;
if (optlen == 0)
goto e_inval;
else if (optlen < sizeof(struct in6_pktinfo) || optval == NULL)
goto e_inval;
if (copy_from_user(&pkt, optval, sizeof(struct in6_pktinfo))) {
retv = -EFAULT;
break;
}
if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
ipv6_addr_copy(&np->sticky_pktinfo.ipi6_addr, &pkt.ipi6_addr);
retv = 0;
break;
}
case IPV6_2292PKTOPTIONS:
{
struct ipv6_txoptions *opt = NULL;
struct msghdr msg;
struct flowi6 fl6;
int junk;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
if (optlen == 0)
goto update;
/* 1K is probably excessive
* 1K is surely not enough, 2K per standard header is 16K.
*/
retv = -EINVAL;
if (optlen > 64*1024)
break;
opt = sock_kmalloc(sk, sizeof(*opt) + optlen, GFP_KERNEL);
retv = -ENOBUFS;
if (opt == NULL)
break;
memset(opt, 0, sizeof(*opt));
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
goto done;
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
retv = datagram_send_ctl(net, &msg, &fl6, opt, &junk, &junk,
&junk);
if (retv)
goto done;
update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
if (opt)
sock_kfree_s(sk, opt, opt->tot_len);
break;
}
case IPV6_UNICAST_HOPS:
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->hop_limit = val;
retv = 0;
break;
case IPV6_MULTICAST_HOPS:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val > 255 || val < -1)
goto e_inval;
np->mcast_hops = val;
retv = 0;
break;
case IPV6_MULTICAST_LOOP:
if (optlen < sizeof(int))
goto e_inval;
if (val != valbool)
goto e_inval;
np->mc_loop = valbool;
retv = 0;
break;
case IPV6_MULTICAST_IF:
if (sk->sk_type == SOCK_STREAM)
break;
if (optlen < sizeof(int))
goto e_inval;
if (val) {
struct net_device *dev;
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != val)
goto e_inval;
dev = dev_get_by_index(net, val);
if (!dev) {
retv = -ENODEV;
break;
}
dev_put(dev);
}
np->mcast_oif = val;
retv = 0;
break;
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EPROTO;
if (inet_sk(sk)->is_icsk)
break;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_ADD_MEMBERSHIP)
retv = ipv6_sock_mc_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
else
retv = ipv6_sock_mc_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_multiaddr);
break;
}
case IPV6_JOIN_ANYCAST:
case IPV6_LEAVE_ANYCAST:
{
struct ipv6_mreq mreq;
if (optlen < sizeof(struct ipv6_mreq))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&mreq, optval, sizeof(struct ipv6_mreq)))
break;
if (optname == IPV6_JOIN_ANYCAST)
retv = ipv6_sock_ac_join(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
else
retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr);
break;
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
{
struct group_req greq;
struct sockaddr_in6 *psin6;
if (optlen < sizeof(struct group_req))
goto e_inval;
retv = -EFAULT;
if (copy_from_user(&greq, optval, sizeof(struct group_req)))
break;
if (greq.gr_group.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
psin6 = (struct sockaddr_in6 *)&greq.gr_group;
if (optname == MCAST_JOIN_GROUP)
retv = ipv6_sock_mc_join(sk, greq.gr_interface,
&psin6->sin6_addr);
else
retv = ipv6_sock_mc_drop(sk, greq.gr_interface,
&psin6->sin6_addr);
break;
}
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
{
struct group_source_req greqs;
int omode, add;
if (optlen < sizeof(struct group_source_req))
goto e_inval;
if (copy_from_user(&greqs, optval, sizeof(greqs))) {
retv = -EFAULT;
break;
}
if (greqs.gsr_group.ss_family != AF_INET6 ||
greqs.gsr_source.ss_family != AF_INET6) {
retv = -EADDRNOTAVAIL;
break;
}
if (optname == MCAST_BLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 1;
} else if (optname == MCAST_UNBLOCK_SOURCE) {
omode = MCAST_EXCLUDE;
add = 0;
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
&psin6->sin6_addr);
/* prior join w/ different source is ok */
if (retv && retv != -EADDRINUSE)
break;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
retv = ip6_mc_source(add, omode, sk, &greqs);
break;
}
case MCAST_MSFILTER:
{
extern int sysctl_mld_max_msf;
struct group_filter *gsf;
if (optlen < GROUP_FILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
retv = -ENOBUFS;
break;
}
gsf = kmalloc(optlen,GFP_KERNEL);
if (!gsf) {
retv = -ENOBUFS;
break;
}
retv = -EFAULT;
if (copy_from_user(gsf, optval, optlen)) {
kfree(gsf);
break;
}
/* numsrc >= (4G-140)/128 overflow in 32 bits */
if (gsf->gf_numsrc >= 0x1ffffffU ||
gsf->gf_numsrc > sysctl_mld_max_msf) {
kfree(gsf);
retv = -ENOBUFS;
break;
}
if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
kfree(gsf);
retv = -EINVAL;
break;
}
retv = ip6_mc_msfilter(sk, gsf);
kfree(gsf);
break;
}
case IPV6_ROUTER_ALERT:
if (optlen < sizeof(int))
goto e_inval;
retv = ip6_ra_control(sk, val);
break;
case IPV6_MTU_DISCOVER:
if (optlen < sizeof(int))
goto e_inval;
if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE)
goto e_inval;
np->pmtudisc = val;
retv = 0;
break;
case IPV6_MTU:
if (optlen < sizeof(int))
goto e_inval;
if (val && val < IPV6_MIN_MTU)
goto e_inval;
np->frag_size = val;
retv = 0;
break;
case IPV6_RECVERR:
if (optlen < sizeof(int))
goto e_inval;
np->recverr = valbool;
if (!val)
skb_queue_purge(&sk->sk_error_queue);
retv = 0;
break;
case IPV6_FLOWINFO_SEND:
if (optlen < sizeof(int))
goto e_inval;
np->sndflow = valbool;
retv = 0;
break;
case IPV6_FLOWLABEL_MGR:
retv = ipv6_flowlabel_opt(sk, optval, optlen);
break;
case IPV6_IPSEC_POLICY:
case IPV6_XFRM_POLICY:
retv = -EPERM;
if (!capable(CAP_NET_ADMIN))
break;
retv = xfrm_user_policy(sk, optname, optval, optlen);
break;
case IPV6_ADDR_PREFERENCES:
{
unsigned int pref = 0;
unsigned int prefmask = ~0;
if (optlen < sizeof(int))
goto e_inval;
retv = -EINVAL;
/* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */
switch (val & (IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP|
IPV6_PREFER_SRC_PUBTMP_DEFAULT)) {
case IPV6_PREFER_SRC_PUBLIC:
pref |= IPV6_PREFER_SRC_PUBLIC;
break;
case IPV6_PREFER_SRC_TMP:
pref |= IPV6_PREFER_SRC_TMP;
break;
case IPV6_PREFER_SRC_PUBTMP_DEFAULT:
break;
case 0:
goto pref_skip_pubtmp;
default:
goto e_inval;
}
prefmask &= ~(IPV6_PREFER_SRC_PUBLIC|
IPV6_PREFER_SRC_TMP);
pref_skip_pubtmp:
/* check HOME/COA conflicts */
switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) {
case IPV6_PREFER_SRC_HOME:
break;
case IPV6_PREFER_SRC_COA:
pref |= IPV6_PREFER_SRC_COA;
case 0:
goto pref_skip_coa;
default:
goto e_inval;
}
prefmask &= ~IPV6_PREFER_SRC_COA;
pref_skip_coa:
/* check CGA/NONCGA conflicts */
switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) {
case IPV6_PREFER_SRC_CGA:
case IPV6_PREFER_SRC_NONCGA:
case 0:
break;
default:
goto e_inval;
}
np->srcprefs = (np->srcprefs & prefmask) | pref;
retv = 0;
break;
}
case IPV6_MINHOPCOUNT:
if (optlen < sizeof(int))
goto e_inval;
if (val < 0 || val > 255)
goto e_inval;
np->min_hopcount = val;
retv = 0;
break;
case IPV6_DONTFRAG:
np->dontfrag = valbool;
retv = 0;
break;
}
release_sock(sk);
return retv;
e_inval:
release_sock(sk);
return -EINVAL;
}
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr*)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct ipv6_pinfo *np;
struct sock *sk;
int err;
struct tcp_sock *tp;
__u32 seq;
struct net *net = dev_net(skb->dev);
sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
th->dest, &hdr->saddr, th->source, skb->dev->ifindex);
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
goto out;
}
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
goto out;
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = np->daddr;
fl6.saddr = np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
if (IS_ERR(dst)) {
sk->sk_err_soft = -PTR_ERR(dst);
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
}
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
switch (sk->sk_state) {
struct request_sock *req, **prev;
case TCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
&hdr->saddr, inet6_iif(skb));
if (!req)
goto out;
WARN_ON(req->sk != NULL);
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV:
if (!sock_owned_by_user(sk)) {
sk->sk_err = err;
sk->sk_error_report(sk);
tcp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *newnp;
const struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst,
req_unhash, own_req);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newnp->saddr = newsk->sk_v6_rcv_saddr;
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, dccp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (!dst) {
struct flowi6 fl6;
dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP);
if (!dst)
goto out;
}
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out_nonewsk;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, dccp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
newnp->saddr = ireq->ir_v6_loc_addr;
newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* Clone native IPv6 options from listening socket (if any)
*
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (opt)
inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (__inet_inherit_port(sk, newsk) < 0) {
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto out;
}
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
/* Clone pktoptions received with SYN, if we own the req */
if (*own_req && ireq->pktopts) {
newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
return newsk;
out_overflow:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
dst_release(dst);
out:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
}
/**
* dump_common_audit_data - helper to dump common audit data
* @a : common audit data
*
*/
static void dump_common_audit_data(struct audit_buffer *ab,
struct common_audit_data *a)
{
struct task_struct *tsk = current;
/*
* To keep stack sizes in check force programers to notice if they
* start making this union too large! See struct lsm_network_audit
* as an example of how to deal with large data.
*/
BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2);
audit_log_format(ab, " pid=%d comm=", tsk->pid);
audit_log_untrustedstring(ab, tsk->comm);
switch (a->type) {
case LSM_AUDIT_DATA_NONE:
return;
case LSM_AUDIT_DATA_IPC:
audit_log_format(ab, " key=%d ", a->u.ipc_id);
break;
case LSM_AUDIT_DATA_CAP:
audit_log_format(ab, " capability=%d ", a->u.cap);
break;
case LSM_AUDIT_DATA_PATH: {
struct inode *inode;
audit_log_d_path(ab, " path=", &a->u.path);
inode = a->u.path.dentry->d_inode;
if (inode) {
audit_log_format(ab, " dev=");
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
}
break;
}
case LSM_AUDIT_DATA_DENTRY: {
struct inode *inode;
audit_log_format(ab, " name=");
audit_log_untrustedstring(ab, a->u.dentry->d_name.name);
inode = a->u.dentry->d_inode;
if (inode) {
audit_log_format(ab, " dev=");
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
}
break;
}
case LSM_AUDIT_DATA_INODE: {
struct dentry *dentry;
struct inode *inode;
inode = a->u.inode;
dentry = d_find_alias(inode);
if (dentry) {
audit_log_format(ab, " name=");
audit_log_untrustedstring(ab,
dentry->d_name.name);
dput(dentry);
}
audit_log_format(ab, " dev=");
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
break;
}
case LSM_AUDIT_DATA_TASK:
tsk = a->u.tsk;
if (tsk && tsk->pid) {
audit_log_format(ab, " pid=%d comm=", tsk->pid);
audit_log_untrustedstring(ab, tsk->comm);
}
break;
case LSM_AUDIT_DATA_NET:
if (a->u.net->sk) {
struct sock *sk = a->u.net->sk;
struct unix_sock *u;
int len = 0;
char *p = NULL;
switch (sk->sk_family) {
case AF_INET: {
struct inet_sock *inet = inet_sk(sk);
print_ipv4_addr(ab, inet->inet_rcv_saddr,
inet->inet_sport,
"laddr", "lport");
print_ipv4_addr(ab, inet->inet_daddr,
inet->inet_dport,
"faddr", "fport");
break;
}
case AF_INET6: {
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *inet6 = inet6_sk(sk);
print_ipv6_addr(ab, &inet6->rcv_saddr,
inet->inet_sport,
"laddr", "lport");
print_ipv6_addr(ab, &inet6->daddr,
inet->inet_dport,
"faddr", "fport");
break;
}
case AF_UNIX:
u = unix_sk(sk);
if (u->path.dentry) {
audit_log_d_path(ab, " path=", &u->path);
break;
}
if (!u->addr)
break;
len = u->addr->len-sizeof(short);
p = &u->addr->name->sun_path[0];
audit_log_format(ab, " path=");
if (*p)
audit_log_untrustedstring(ab, p);
else
audit_log_n_hex(ab, p, len);
break;
}
}
switch (a->u.net->family) {
case AF_INET:
print_ipv4_addr(ab, a->u.net->v4info.saddr,
a->u.net->sport,
"saddr", "src");
print_ipv4_addr(ab, a->u.net->v4info.daddr,
a->u.net->dport,
"daddr", "dest");
break;
case AF_INET6:
print_ipv6_addr(ab, &a->u.net->v6info.saddr,
a->u.net->sport,
"saddr", "src");
print_ipv6_addr(ab, &a->u.net->v6info.daddr,
a->u.net->dport,
"daddr", "dest");
break;
}
if (a->u.net->netif > 0) {
struct net_device *dev;
/* NOTE: we always use init's namespace */
dev = dev_get_by_index(&init_net, a->u.net->netif);
if (dev) {
audit_log_format(ab, " netif=%s", dev->name);
dev_put(dev);
}
}
break;
#ifdef CONFIG_KEYS
case LSM_AUDIT_DATA_KEY:
audit_log_format(ab, " key_serial=%u", a->u.key_struct.key);
if (a->u.key_struct.key_desc) {
audit_log_format(ab, " key_desc=");
audit_log_untrustedstring(ab, a->u.key_struct.key_desc);
}
break;
#endif
case LSM_AUDIT_DATA_KMOD:
audit_log_format(ab, " kmod=");
audit_log_untrustedstring(ab, a->u.kmod_name);
break;
} /* switch (a->type) */
}
static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
void *from, size_t length,
struct rtable **rtp,
unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct iphdr *iph;
struct sk_buff *skb;
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
int hlen, tlen;
if (length > rt->dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
rt->dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
hlen = LL_RESERVED_SPACE(rt->dst.dev);
tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, &rt->dst);
*rtp = NULL;
skb_reset_network_header(skb);
iph = ip_hdr(skb);
skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
skb->transport_header = skb->network_header;
err = -EFAULT;
if (memcpy_fromiovecend((void *)iph, from, 0, length))
goto error_free;
iphlen = iph->ihl * 4;
err = -EINVAL;
if (iphlen > length)
goto error_free;
if (iphlen >= sizeof(*iph)) {
if (!iph->saddr)
iph->saddr = fl4->saddr;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(iph, &rt->dst, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
if (iph->protocol == IPPROTO_ICMP)
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL,
rt->dst.dev, dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
out:
return 0;
error_free:
kfree_skb(skb);
error:
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
return err;
}
int ip6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb, *tmp_skb;
struct sk_buff **tail_skb;
struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6hdr *hdr;
struct ipv6_txoptions *opt = np->cork.opt;
struct rt6_info *rt = np->cork.rt;
struct flowi *fl = &inet->cork.fl;
unsigned char proto = fl->proto;
int err = 0;
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
goto out;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
if (skb->data < skb->nh.raw)
__skb_pull(skb, skb->nh.raw - skb->data);
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
__skb_pull(tmp_skb, skb->h.raw - skb->nh.raw);
*tail_skb = tmp_skb;
tail_skb = &(tmp_skb->next);
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
__sock_put(tmp_skb->sk);
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
}
ipv6_addr_copy(final_dst, &fl->fl6_dst);
__skb_pull(skb, skb->h.raw - skb->nh.raw);
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
skb->nh.ipv6h = hdr = (struct ipv6hdr*) skb_push(skb, sizeof(struct ipv6hdr));
*(u32*)hdr = fl->fl6_flowlabel | htonl(0x60000000);
if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN)
hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
else
hdr->payload_len = 0;
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
ipv6_addr_copy(&hdr->daddr, final_dst);
skb->dst = dst_clone(&rt->u.dst);
IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output);
if (err) {
if (err > 0)
err = np->recverr ? net_xmit_errno(err) : 0;
if (err)
goto error;
}
out:
inet->cork.flags &= ~IPCORK_OPT;
if (np->cork.opt) {
kfree(np->cork.opt);
np->cork.opt = NULL;
}
if (np->cork.rt) {
dst_release(&np->cork.rt->u.dst);
np->cork.rt = NULL;
inet->cork.flags &= ~IPCORK_ALLFRAG;
}
memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
return err;
error:
goto out;
}
