static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
int optlen)
{
struct tcp_md5sig cmd;
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
if (optlen < sizeof(cmd))
return -EINVAL;
if (copy_from_user(&cmd, optval, sizeof(cmd)))
return -EFAULT;
if (sin6->sin6_family != AF_INET6)
return -EINVAL;
if (!cmd.tcpm_keylen) {
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
AF_INET);
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
AF_INET6);
}
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
return -EINVAL;
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
struct dst_entry *dst,
bool create)
{
struct tcp_metrics_block *tm;
struct inetpeer_addr saddr, daddr;
unsigned int hash;
struct net *net;
if (sk->sk_family == AF_INET) {
saddr.family = AF_INET;
saddr.addr.a4 = inet_sk(sk)->inet_saddr;
daddr.family = AF_INET;
daddr.addr.a4 = inet_sk(sk)->inet_daddr;
hash = (__force unsigned int) daddr.addr.a4;
}
#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) {
saddr.family = AF_INET;
saddr.addr.a4 = inet_sk(sk)->inet_saddr;
daddr.family = AF_INET;
daddr.addr.a4 = inet_sk(sk)->inet_daddr;
hash = (__force unsigned int) daddr.addr.a4;
} else {
saddr.family = AF_INET6;
*(struct in6_addr *)saddr.addr.a6 = sk->sk_v6_rcv_saddr;
daddr.family = AF_INET6;
*(struct in6_addr *)daddr.addr.a6 = sk->sk_v6_daddr;
hash = ipv6_addr_hash(&sk->sk_v6_daddr);
}
}
#endif
else
return NULL;
net = dev_net(dst->dev);
hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
tm = __tcp_get_metrics(&saddr, &daddr, net, hash);
if (tm == TCP_METRICS_RECLAIM_PTR)
tm = NULL;
if (!tm && create)
tm = tcpm_new(dst, &saddr, &daddr, hash);
else
tcpm_check_stamp(tm, dst);
return tm;
}
static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
{
struct tcp_metrics_block *tm;
struct inetpeer_addr saddr, daddr;
unsigned int hash;
struct net *net;
if (tw->tw_family == AF_INET) {
saddr.family = AF_INET;
saddr.addr.a4 = tw->tw_rcv_saddr;
daddr.family = AF_INET;
daddr.addr.a4 = tw->tw_daddr;
hash = (__force unsigned int) daddr.addr.a4;
}
#if IS_ENABLED(CONFIG_IPV6)
else if (tw->tw_family == AF_INET6) {
if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) {
saddr.family = AF_INET;
saddr.addr.a4 = tw->tw_rcv_saddr;
daddr.family = AF_INET;
daddr.addr.a4 = tw->tw_daddr;
hash = (__force unsigned int) daddr.addr.a4;
} else {
saddr.family = AF_INET6;
*(struct in6_addr *)saddr.addr.a6 = tw->tw_v6_rcv_saddr;
daddr.family = AF_INET6;
*(struct in6_addr *)daddr.addr.a6 = tw->tw_v6_daddr;
hash = ipv6_addr_hash(&tw->tw_v6_daddr);
}
}
#endif
else
return NULL;
net = twsk_net(tw);
hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm;
tm = rcu_dereference(tm->tcpm_next)) {
if (addr_same(&tm->tcpm_saddr, &saddr) &&
addr_same(&tm->tcpm_daddr, &daddr))
break;
}
return tm;
}
void ip6_datagram_release_cb(struct sock *sk)
{
struct dst_entry *dst;
if (ipv6_addr_v4mapped(&sk->sk_v6_daddr))
return;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) {
rcu_read_unlock();
return;
}
rcu_read_unlock();
ip6_datagram_dst_update(sk, false);
}
int sc_capwap_connect(const union capwap_addr* sockaddr, struct sc_capwap_sessionid_element* sessionid, uint16_t mtu) {
TRACEKMOD("### sc_capwap_connect\n");
if ((sc_localaddr.ss.ss_family != AF_INET) && (sc_localaddr.ss.ss_family != AF_INET6)) {
return -ENONET;
}
/* AC address */
if ((sockaddr->ss.ss_family == AF_INET6) && ipv6_addr_v4mapped(&sockaddr->sin6.sin6_addr)) {
return -EINVAL;
} else if ((sc_localaddr.ss.ss_family == AF_INET) && (sockaddr->ss.ss_family == AF_INET6)) {
return -EINVAL;
}
/* */
memcpy(&sc_acsession.peeraddr, sockaddr, sizeof(union capwap_addr));
memcpy(&sc_acsession.sessionid, sessionid, sizeof(struct sc_capwap_sessionid_element));
sc_acsession.mtu = mtu;
return sc_capwap_sendkeepalive();
}
static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
char *buf, const int buflen)
{
const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
const struct in6_addr *addr = &sin6->sin6_addr;
/*
* RFC 4291, Section 2.2.2
*
* Shorthanded ANY address
*/
if (ipv6_addr_any(addr))
return snprintf(buf, buflen, "::");
/*
* RFC 4291, Section 2.2.2
*
* Shorthanded loopback address
*/
if (ipv6_addr_loopback(addr))
return snprintf(buf, buflen, "::1");
/*
* RFC 4291, Section 2.2.3
*
* Special presentation address format for mapped v4
* addresses.
*/
if (ipv6_addr_v4mapped(addr))
return snprintf(buf, buflen, "::ffff:%pI4",
&addr->s6_addr32[3]);
/*
* RFC 4291, Section 2.2.1
*/
return snprintf(buf, buflen, "%pI6c", addr);
}
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 (valbool && !ns_capable(net->user_ns, CAP_NET_ADMIN) &&
!ns_capable(net->user_ns, CAP_NET_RAW)) {
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 && !ns_capable(net->user_ns, 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 IS_ENABLED(CONFIG_IPV6_MIP6)
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;
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 = ip6_datagram_send_ctl(net, sk, &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 == -1 ? IPV6_DEFAULT_MCASTHOPS : 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_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) {
np->ucast_oif = 0;
retv = 0;
break;
}
dev = dev_get_by_index(net, ifindex);
retv = -EADDRNOTAVAIL;
if (!dev)
break;
dev_put(dev);
retv = -EINVAL;
if (sk->sk_bound_dev_if)
break;
np->ucast_oif = ifindex;
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:
{
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 (!ns_capable(net->user_ns, 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 bool ipv6_mapped_addr_any(const struct in6_addr *a)
{
return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
}
static inline int ipv6_mapped_addr_any(const struct in6_addr *a)
{
return (ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0));
}
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
const struct inet_sock *inet = inet_sk(sk);
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(!handler);
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
goto errout;
/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
* hence this needs to be included regardless of socket family.
*/
if (ext & (1 << (INET_DIAG_TOS - 1)))
if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
goto errout;
#if IS_ENABLED(CONFIG_IPV6)
if (r->idiag_family == AF_INET6) {
if (ext & (1 << (INET_DIAG_TCLASS - 1)))
if (nla_put_u8(skb, INET_DIAG_TCLASS,
inet6_sk(sk)->tclass) < 0)
goto errout;
if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
goto errout;
}
#endif
r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
r->idiag_inode = sock_i_ino(sk);
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
.idiag_wmem = sk->sk_wmem_queued,
.idiag_fmem = sk->sk_forward_alloc,
.idiag_tmem = sk_wmem_alloc_get(sk),
};
if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
}
#define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
}
#undef EXPIRES_IN_MS
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
attr = nla_reserve(skb, INET_DIAG_INFO,
handler->idiag_info_size);
if (!attr)
goto errout;
info = nla_data(attr);
}
if (ext & (1 << (INET_DIAG_CONG - 1))) {
int err = 0;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops)
err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
rcu_read_unlock();
if (err < 0)
goto errout;
}
handler->idiag_get_info(sk, r, info);
if (sk->sk_state < TCP_TIME_WAIT) {
union tcp_cc_info info;
size_t sz = 0;
int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
out:
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
static int inet_csk_diag_fill(struct sock *sk,
struct sk_buff *skb,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
return inet_sk_diag_fill(sk, inet_csk(sk), skb, req,
user_ns, portid, seq, nlmsg_flags, unlh);
}
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
tmo = tw->tw_timer.expires - jiffies;
if (tmo < 0)
tmo = 0;
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = inet_reqsk(sk)->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
const struct inet_diag_req_v2 *r,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
nlmsg_flags, unlh);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
struct inet_hashinfo *hashinfo,
const struct inet_diag_req_v2 *req)
{
struct sock *sk;
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
req->id.idiag_dport, req->id.idiag_src[3],
req->id.idiag_sport, req->id.idiag_if);
else
sk = inet6_lookup(net, hashinfo,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else
return ERR_PTR(-EINVAL);
if (!sk)
return ERR_PTR(-ENOENT);
if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
sock_gen_put(sk);
return ERR_PTR(-ENOENT);
}
return sk;
}
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = inet_diag_find_one_icsk(net, hashinfo, req);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
}
err = sk_diag_fill(sk, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
goto out;
}
err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
if (sk)
sock_gen_put(sk);
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
const struct inet_diag_handler *handler;
int err;
handler = inet_diag_lock_handler(req->sdiag_protocol);
if (IS_ERR(handler))
err = PTR_ERR(handler);
else if (cmd == SOCK_DIAG_BY_FAMILY)
err = handler->dump_one(in_skb, nlh, req);
else if (cmd == SOCK_DESTROY_BACKPORT && handler->destroy)
err = handler->destroy(in_skb, req);
else
err = -EOPNOTSUPP;
inet_diag_unlock_handler(handler);
return err;
}
static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
int words = bits >> 5;
bits &= 0x1f;
if (words) {
if (memcmp(a1, a2, words << 2))
return 0;
}
if (bits) {
__be32 w1, w2;
__be32 mask;
w1 = a1[words];
w2 = a2[words];
mask = htonl((0xffffffff) << (32 - bits));
if ((w1 ^ w2) & mask)
return 0;
}
return 1;
}
static inline int qedr_gsi_build_header(struct qedr_dev *dev,
struct qedr_qp *qp,
struct ib_send_wr *swr,
struct ib_ud_header *udh,
int *roce_mode)
{
bool has_vlan = false, has_grh_ipv6 = true;
struct rdma_ah_attr *ah_attr = &get_qedr_ah(ud_wr(swr)->ah)->attr;
const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr);
union ib_gid sgid;
int send_size = 0;
u16 vlan_id = 0;
u16 ether_type;
struct ib_gid_attr sgid_attr;
int rc;
int ip_ver = 0;
bool has_udp = false;
int i;
send_size = 0;
for (i = 0; i < swr->num_sge; ++i)
send_size += swr->sg_list[i].length;
rc = ib_get_cached_gid(qp->ibqp.device, rdma_ah_get_port_num(ah_attr),
grh->sgid_index, &sgid, &sgid_attr);
if (rc) {
DP_ERR(dev,
"gsi post send: failed to get cached GID (port=%d, ix=%d)\n",
rdma_ah_get_port_num(ah_attr),
grh->sgid_index);
return rc;
}
if (sgid_attr.ndev) {
vlan_id = rdma_vlan_dev_vlan_id(sgid_attr.ndev);
if (vlan_id < VLAN_CFI_MASK)
has_vlan = true;
dev_put(sgid_attr.ndev);
}
if (!memcmp(&sgid, &zgid, sizeof(sgid))) {
DP_ERR(dev, "gsi post send: GID not found GID index %d\n",
grh->sgid_index);
return -ENOENT;
}
has_udp = (sgid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP);
if (!has_udp) {
/* RoCE v1 */
ether_type = ETH_P_IBOE;
*roce_mode = ROCE_V1;
} else if (ipv6_addr_v4mapped((struct in6_addr *)&sgid)) {
/* RoCE v2 IPv4 */
ip_ver = 4;
ether_type = ETH_P_IP;
has_grh_ipv6 = false;
*roce_mode = ROCE_V2_IPV4;
} else {
/* RoCE v2 IPv6 */
ip_ver = 6;
ether_type = ETH_P_IPV6;
*roce_mode = ROCE_V2_IPV6;
}
rc = ib_ud_header_init(send_size, false, true, has_vlan,
has_grh_ipv6, ip_ver, has_udp, 0, udh);
if (rc) {
DP_ERR(dev, "gsi post send: failed to init header\n");
return rc;
}
/* ENET + VLAN headers */
ether_addr_copy(udh->eth.dmac_h, ah_attr->roce.dmac);
ether_addr_copy(udh->eth.smac_h, dev->ndev->dev_addr);
if (has_vlan) {
udh->eth.type = htons(ETH_P_8021Q);
udh->vlan.tag = htons(vlan_id);
udh->vlan.type = htons(ether_type);
} else {
udh->eth.type = htons(ether_type);
}
/* BTH */
udh->bth.solicited_event = !!(swr->send_flags & IB_SEND_SOLICITED);
udh->bth.pkey = QEDR_ROCE_PKEY_DEFAULT;
udh->bth.destination_qpn = htonl(ud_wr(swr)->remote_qpn);
udh->bth.psn = htonl((qp->sq_psn++) & ((1 << 24) - 1));
udh->bth.opcode = IB_OPCODE_UD_SEND_ONLY;
/* DETH */
udh->deth.qkey = htonl(0x80010000);
udh->deth.source_qpn = htonl(QEDR_GSI_QPN);
if (has_grh_ipv6) {
/* GRH / IPv6 header */
udh->grh.traffic_class = grh->traffic_class;
udh->grh.flow_label = grh->flow_label;
udh->grh.hop_limit = grh->hop_limit;
udh->grh.destination_gid = grh->dgid;
memcpy(&udh->grh.source_gid.raw, &sgid.raw,
sizeof(udh->grh.source_gid.raw));
} else {
/* IPv4 header */
u32 ipv4_addr;
udh->ip4.protocol = IPPROTO_UDP;
udh->ip4.tos = htonl(grh->flow_label);
udh->ip4.frag_off = htons(IP_DF);
udh->ip4.ttl = grh->hop_limit;
ipv4_addr = qedr_get_ipv4_from_gid(sgid.raw);
udh->ip4.saddr = ipv4_addr;
ipv4_addr = qedr_get_ipv4_from_gid(grh->dgid.raw);
udh->ip4.daddr = ipv4_addr;
/* note: checksum is calculated by the device */
}
/* UDP */
if (has_udp) {
udh->udp.sport = htons(QEDR_ROCE_V2_UDP_SPORT);
udh->udp.dport = htons(ROCE_V2_UDP_DPORT);
udh->udp.csum = 0;
/* UDP length is untouched hence is zero */
}
return 0;
}
int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc,
bool allow_ipv6)
{
int err, val;
struct cmsghdr *cmsg;
struct net *net = sock_net(sk);
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
#if IS_ENABLED(CONFIG_IPV6)
if (allow_ipv6 &&
cmsg->cmsg_level == SOL_IPV6 &&
cmsg->cmsg_type == IPV6_PKTINFO) {
struct in6_pktinfo *src_info;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info)))
return -EINVAL;
src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
if (!ipv6_addr_v4mapped(&src_info->ipi6_addr))
return -EINVAL;
ipc->oif = src_info->ipi6_ifindex;
ipc->addr = src_info->ipi6_addr.s6_addr32[3];
continue;
}
#endif
if (cmsg->cmsg_level == SOL_SOCKET) {
err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc);
if (err)
return err;
continue;
}
if (cmsg->cmsg_level != SOL_IP)
continue;
switch (cmsg->cmsg_type) {
case IP_RETOPTS:
err = cmsg->cmsg_len - sizeof(struct cmsghdr);
/* Our caller is responsible for freeing ipc->opt */
err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
err < 40 ? err : 40);
if (err)
return err;
break;
case IP_PKTINFO:
{
struct in_pktinfo *info;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo)))
return -EINVAL;
info = (struct in_pktinfo *)CMSG_DATA(cmsg);
ipc->oif = info->ipi_ifindex;
ipc->addr = info->ipi_spec_dst.s_addr;
break;
}
case IP_TTL:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(int)))
return -EINVAL;
val = *(int *)CMSG_DATA(cmsg);
if (val < 1 || val > 255)
return -EINVAL;
ipc->ttl = val;
break;
case IP_TOS:
if (cmsg->cmsg_len == CMSG_LEN(sizeof(int)))
val = *(int *)CMSG_DATA(cmsg);
else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8)))
val = *(u8 *)CMSG_DATA(cmsg);
else
return -EINVAL;
if (val < 0 || val > 255)
return -EINVAL;
ipc->tos = val;
ipc->priority = rt_tos2priority(ipc->tos);
break;
default:
return -EINVAL;
}
}
return 0;
}
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh,
bool net_admin)
{
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
handler = inet_diag_table[req->sdiag_protocol];
BUG_ON(!handler);
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin))
goto errout;
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
.idiag_wmem = sk->sk_wmem_queued,
.idiag_fmem = sk->sk_forward_alloc,
.idiag_tmem = sk_wmem_alloc_get(sk),
};
if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
/*
* RAW sockets might have user-defined protocols assigned,
* so report the one supplied on socket creation.
*/
if (sk->sk_type == SOCK_RAW) {
if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
goto errout;
}
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
}
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires =
jiffies_to_msecs(icsk->icsk_timeout - jiffies);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_to_msecs(icsk->icsk_timeout - jiffies);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_to_msecs(sk->sk_timer.expires - jiffies);
} else {
r->idiag_timer = 0;
r->idiag_expires = 0;
}
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
attr = nla_reserve_64bit(skb, INET_DIAG_INFO,
handler->idiag_info_size,
INET_DIAG_PAD);
if (!attr)
goto errout;
info = nla_data(attr);
}
if (ext & (1 << (INET_DIAG_CONG - 1))) {
int err = 0;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops)
err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
rcu_read_unlock();
if (err < 0)
goto errout;
}
handler->idiag_get_info(sk, r, info);
if (ext & (1 << (INET_DIAG_INFO - 1)) && handler->idiag_get_aux)
if (handler->idiag_get_aux(sk, net_admin, skb) < 0)
goto errout;
if (sk->sk_state < TCP_TIME_WAIT) {
union tcp_cc_info info;
size_t sz = 0;
int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
u32 classid = 0;
#ifdef CONFIG_SOCK_CGROUP_DATA
classid = sock_cgroup_classid(&sk->sk_cgrp_data);
#endif
if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
goto errout;
}
out:
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
static int inet_csk_diag_fill(struct sock *sk,
struct sk_buff *skb,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh,
bool net_admin)
{
return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns,
portid, seq, nlmsg_flags, unlh, net_admin);
}
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
tmo = tw->tw_timer.expires - jiffies;
if (tmo < 0)
tmo = 0;
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
nlmsg_end(skb, nlh);
return 0;
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh, bool net_admin)
{
struct request_sock *reqsk = inet_reqsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = reqsk->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0;
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
inet_rsk(reqsk)->ir_mark))
return -EMSGSIZE;
nlmsg_end(skb, nlh);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
const struct inet_diag_req_v2 *r,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh, bool net_admin)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, portid, seq,
nlmsg_flags, unlh, net_admin);
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
nlmsg_flags, unlh, net_admin);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
struct inet_hashinfo *hashinfo,
const struct inet_diag_req_v2 *req)
{
struct sock *sk;
rcu_read_lock();
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3],
req->id.idiag_dport, req->id.idiag_src[3],
req->id.idiag_sport, req->id.idiag_if);
else
sk = inet6_lookup(net, hashinfo, NULL, 0,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else {
rcu_read_unlock();
return ERR_PTR(-EINVAL);
}
rcu_read_unlock();
if (!sk)
return ERR_PTR(-ENOENT);
if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
sock_gen_put(sk);
return ERR_PTR(-ENOENT);
}
return sk;
}
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN);
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = inet_diag_find_one_icsk(net, hashinfo, req);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
}
err = sk_diag_fill(sk, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh, net_admin);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
goto out;
}
err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
if (sk)
sock_gen_put(sk);
return err;
}
static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
struct rt6_info *rt;
#endif
int err;
int flags = 0;
/* The correct way to handle this would be to do
* ip6_route_get_saddr, and then ip6_route_output; however,
* the route-specific preferred source forces the
* ip6_route_output call _before_ ip6_route_get_saddr.
*
* In source specific routing (no src=any default route),
* ip6_route_output will fail given src=any saddr, though, so
* that's why we try it again later.
*/
if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
struct rt6_info *rt;
bool had_dst = *dst != NULL;
if (!had_dst)
*dst = ip6_route_output(net, sk, fl6);
rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
/* If we had an erroneous initial result, pretend it
* never existed and let the SA-enabled version take
* over.
*/
if (!had_dst && (*dst)->error) {
dst_release(*dst);
*dst = NULL;
}
if (fl6->flowi6_oif)
flags |= RT6_LOOKUP_F_IFACE;
}
if (!*dst)
*dst = ip6_route_output_flags(net, sk, fl6, flags);
err = (*dst)->error;
if (err)
goto out_err_release;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
n = __ipv6_neigh_lookup_noref(rt->dst.dev,
rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
if (err) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
int redirect;
ifp = ipv6_get_ifaddr(net, &fl6->saddr,
(*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(net, sk, &fl_gw6);
err = (*dst)->error;
if (err)
goto out_err_release;
}
}
#endif
if (ipv6_addr_v4mapped(&fl6->saddr) &&
!(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) {
err = -EAFNOSUPPORT;
goto out_err_release;
}
return 0;
out_err_release:
dst_release(*dst);
*dst = NULL;
if (err == -ENETUNREACH)
IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
return err;
}
int __ip6_datagram_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 ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *daddr, old_daddr;
__be32 fl6_flowlabel = 0;
__be32 old_fl6_flowlabel;
__be16 old_dport;
int addr_type;
int err;
if (usin->sin6_family == AF_INET) {
if (__ipv6_only_sock(sk))
return -EAFNOSUPPORT;
err = __ip4_datagram_connect(sk, uaddr, addr_len);
goto ipv4_connected;
}
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
if (np->sndflow)
fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
if (ipv6_addr_any(&usin->sin6_addr)) {
/*
* connect to self
*/
if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
&usin->sin6_addr);
else
usin->sin6_addr = in6addr_loopback;
}
addr_type = ipv6_addr_type(&usin->sin6_addr);
daddr = &usin->sin6_addr;
if (addr_type & IPV6_ADDR_MAPPED) {
struct sockaddr_in sin;
if (__ipv6_only_sock(sk)) {
err = -ENETUNREACH;
goto out;
}
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = daddr->s6_addr32[3];
sin.sin_port = usin->sin6_port;
err = __ip4_datagram_connect(sk,
(struct sockaddr *) &sin,
sizeof(sin));
ipv4_connected:
if (err)
goto out;
ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr);
if (ipv6_addr_any(&np->saddr) ||
ipv6_mapped_addr_any(&np->saddr))
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) ||
ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) {
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&sk->sk_v6_rcv_saddr);
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
goto out;
}
if (__ipv6_addr_needs_scope_id(addr_type)) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) {
err = -EINVAL;
goto out;
}
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST))
sk->sk_bound_dev_if = np->mcast_oif;
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if) {
err = -EINVAL;
goto out;
}
}
/* save the current peer information before updating it */
old_daddr = sk->sk_v6_daddr;
old_fl6_flowlabel = np->flow_label;
old_dport = inet->inet_dport;
sk->sk_v6_daddr = *daddr;
np->flow_label = fl6_flowlabel;
inet->inet_dport = usin->sin6_port;
/*
* Check for a route to destination an obtain the
* destination cache for it.
*/
err = ip6_datagram_dst_update(sk, true);
if (err) {
/* Restore the socket peer info, to keep it consistent with
* the old socket state
*/
sk->sk_v6_daddr = old_daddr;
np->flow_label = old_fl6_flowlabel;
inet->inet_dport = old_dport;
goto out;
}
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
out:
return err;
}
int set_up_connection(struct pingpong_context *ctx,
struct perftest_parameters *user_param,
struct pingpong_dest *my_dest)
{
int num_of_qps = user_param->num_of_qps;
int num_of_qps_per_port = user_param->num_of_qps / 2;
int i;
int is_ipv4;
union ibv_gid temp_gid;
union ibv_gid temp_gid2;
struct ibv_port_attr attr;
srand48(getpid() * time(NULL));
/*in xrc with bidirectional,
there are send qps and recv qps. the actual number of send/recv qps
is num_of_qps / 2.
*/
if ( (user_param->connection_type == DC || user_param->use_xrc) && (user_param->duplex || user_param->tst == LAT)) {
num_of_qps /= 2;
num_of_qps_per_port = num_of_qps / 2;
}
if (user_param->gid_index != -1) {
if (ibv_query_port(ctx->context,user_param->ib_port,&attr))
return 0;
if (user_param->use_gid_user) {
if (ibv_query_gid(ctx->context,user_param->ib_port,user_param->gid_index,&temp_gid)) {
return -1;
}
} else {
for (i=0 ; i < attr.gid_tbl_len; i++) {
if (ibv_query_gid(ctx->context,user_param->ib_port,i,&temp_gid)) {
return -1;
}
is_ipv4 = ipv6_addr_v4mapped((struct in6_addr *)temp_gid.raw);
if ((user_param->ipv6 && !is_ipv4) || (!user_param->ipv6 && is_ipv4)) {
user_param->gid_index = i;
break;
}
}
}
}
if (user_param->dualport==ON) {
if (user_param->gid_index2 != -1) {
if (ibv_query_port(ctx->context,user_param->ib_port2,&attr))
return 0;
if (user_param->use_gid_user) {
if (ibv_query_gid(ctx->context,user_param->ib_port2,user_param->gid_index,&temp_gid2))
return -1;
} else {
for (i=0 ; i < attr.gid_tbl_len; i++) {
if (ibv_query_gid(ctx->context,user_param->ib_port2,i,&temp_gid2)) {
return -1;
}
is_ipv4 = ipv6_addr_v4mapped((struct in6_addr *)temp_gid2.raw);
if ((user_param->ipv6 && !is_ipv4) || (!user_param->ipv6 && is_ipv4)) {
user_param->gid_index = i;
break;
}
}
}
}
}
for (i = 0; i < user_param->num_of_qps; i++) {
if (user_param->dualport == ON) {
/*first half of qps are for ib_port and second half are for ib_port2
in xrc with bidirectional, the first half of qps are xrc_send qps and
the second half are xrc_recv qps. the first half of the send/recv qps
are for ib_port1 and the second half are for ib_port2
*/
if (i % num_of_qps < num_of_qps_per_port) {
my_dest[i].lid = ctx_get_local_lid(ctx->context,user_param->ib_port);
my_dest[i].gid_index = user_param->gid_index;
} else {
my_dest[i].lid = ctx_get_local_lid(ctx->context,user_param->ib_port2);
my_dest[i].gid_index = user_param->gid_index2;
}
/*single-port case*/
} else {
my_dest[i].lid = ctx_get_local_lid(ctx->context,user_param->ib_port);
my_dest[i].gid_index = user_param->gid_index;
}
my_dest[i].qpn = ctx->qp[i]->qp_num;
my_dest[i].psn = lrand48() & 0xffffff;
my_dest[i].rkey = ctx->mr->rkey;
/* Each qp gives his receive buffer address.*/
my_dest[i].out_reads = user_param->out_reads;
my_dest[i].vaddr = (uintptr_t)ctx->buf + (user_param->num_of_qps + i)*BUFF_SIZE(ctx->size,ctx->cycle_buffer);
if (user_param->dualport==ON) {
if (i % num_of_qps < num_of_qps_per_port)
memcpy(my_dest[i].gid.raw,temp_gid.raw ,16);
else
memcpy(my_dest[i].gid.raw,temp_gid2.raw ,16);
} else {
memcpy(my_dest[i].gid.raw,temp_gid.raw ,16);
}
/*
We do not fail test upon lid above RoCE.
if ( (user_param->gid_index < 0) || ((user_param->gid_index2 < 0) && (user_param->dualport == ON)) ){
if (!my_dest[i].lid) {
fprintf(stderr," Local lid 0x0 detected. Is an SM running? \n");
return -1;
}
}
*/
}
#ifdef HAVE_XRCD
if (user_param->use_xrc) {
for (i=0; i < user_param->num_of_qps; i++) {
if (ibv_get_srq_num(ctx->srq,&(my_dest[i].srqn))) {
fprintf(stderr, "Couldn't get SRQ number\n");
return 1;
}
}
}
#endif
#ifdef HAVE_DC
if(user_param->machine == SERVER || user_param->duplex || user_param->tst == LAT) {
if (user_param->connection_type == DC) {
for (i=0; i < user_param->num_of_qps; i++) {
if (ibv_get_srq_num(ctx->srq, &(my_dest[i].srqn))) {
fprintf(stderr, "Couldn't get SRQ number\n");
return 1;
}
}
}
}
#endif
return 0;
}