diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 17 | ||||
-rw-r--r-- | net/ipv6/datagram.c | 10 | ||||
-rw-r--r-- | net/ipv6/fib6_rules.c | 1 | ||||
-rw-r--r-- | net/ipv6/ip6_fib.c | 45 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 6 | ||||
-rw-r--r-- | net/ipv6/ip6_vti.c | 3 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 9 | ||||
-rw-r--r-- | net/ipv6/ping.c | 5 | ||||
-rw-r--r-- | net/ipv6/route.c | 9 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 88 | ||||
-rw-r--r-- | net/ipv6/udp.c | 10 |
11 files changed, 127 insertions, 76 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0169ccf5aa4f..17a025847999 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4536,6 +4536,22 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) return 0; } +static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = { + [IFLA_INET6_ADDR_GEN_MODE] = { .type = NLA_U8 }, + [IFLA_INET6_TOKEN] = { .len = sizeof(struct in6_addr) }, +}; + +static int inet6_validate_link_af(const struct net_device *dev, + const struct nlattr *nla) +{ + struct nlattr *tb[IFLA_INET6_MAX + 1]; + + if (dev && !__in6_dev_get(dev)) + return -EAFNOSUPPORT; + + return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy); +} + static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) { int err = -EINVAL; @@ -5351,6 +5367,7 @@ static struct rtnl_af_ops inet6_ops = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, .get_link_af_size = inet6_get_link_af_size, + .validate_link_af = inet6_validate_link_af, .set_link_af = inet6_set_link_af, }; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 2cdc38338be3..11e3945eeac7 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -383,11 +383,10 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; - sin->sin6_family = AF_UNSPEC; + memset(sin, 0, sizeof(*sin)); + if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) { sin->sin6_family = AF_INET6; - sin->sin6_flowinfo = 0; - sin->sin6_port = 0; if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { @@ -398,12 +397,9 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { - struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); - sin->sin6_scope_id = 0; - if (inet->cmsg_flags) + if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index b4d5e1d97c1b..27ca79682efb 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto again; flp6->saddr = saddr; } + err = rt->dst.error; goto out; } again: diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b2d1838897c9..f1c6d5e98322 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -659,6 +659,29 @@ static int fib6_commit_metrics(struct dst_entry *dst, return 0; } +static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, + struct net *net) +{ + if (atomic_read(&rt->rt6i_ref) != 1) { + /* This route is used as dummy address holder in some split + * nodes. It is not leaked, but it still holds other resources, + * which must be released in time. So, scan ascendant nodes + * and replace dummy references to this route with references + * to still alive ones. + */ + while (fn) { + if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { + fn->leaf = fib6_find_prefix(net, fn); + atomic_inc(&fn->leaf->rt6i_ref); + rt6_release(rt); + } + fn = fn->parent; + } + /* No more references are possible at this point. */ + BUG_ON(atomic_read(&rt->rt6i_ref) != 1); + } +} + /* * Insert routing information in a node. */ @@ -807,11 +830,12 @@ add: rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); inet6_rt_notify(RTM_NEWROUTE, rt, info); - rt6_release(iter); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); } return 0; @@ -1322,24 +1346,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fn = fib6_repair_tree(net, fn); } - if (atomic_read(&rt->rt6i_ref) != 1) { - /* This route is used as dummy address holder in some split - * nodes. It is not leaked, but it still holds other resources, - * which must be released in time. So, scan ascendant nodes - * and replace dummy references to this route with references - * to still alive ones. - */ - while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); - rt6_release(rt); - } - fn = fn->parent; - } - /* No more references are possible at this point. */ - BUG_ON(atomic_read(&rt->rt6i_ref) != 1); - } + fib6_purge_rt(rt, fn, net); inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 8e950c250ada..7b5cb003ee22 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -555,7 +555,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; @@ -1296,7 +1297,8 @@ emsgsize: if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO) && + (sk->sk_type == SOCK_DGRAM)) { err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index bcda14de7f84..2459b7b0f705 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -271,8 +271,7 @@ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, static void vti6_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net *net = dev_net(dev); - struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 4cb45c1079a2..a46c50423aec 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1215,7 +1215,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + /* Only set hop_limit on the interface if it is higher than + * the current hop_limit. + */ + if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + } else { + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + } if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 5b7a1ed2aba9..2d452a382128 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -102,9 +102,10 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in6 *, u, msg->msg_name); - if (msg->msg_namelen < sizeof(struct sockaddr_in6) || - u->sin6_family != AF_INET6) { + if (msg->msg_namelen < sizeof(*u)) return -EINVAL; + if (u->sin6_family != AF_INET6) { + return -EAFNOSUPPORT; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != u->sin6_scope_id) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a318dd89b6d9..2d9aca57e7c7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,7 +141,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) u32 *p = NULL; if (!(rt->dst.flags & DST_HOST)) - return NULL; + return dst_cow_metrics_generic(dst, old); peer = rt6_get_peer_create(rt); if (peer) { @@ -1150,12 +1150,9 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct net *net = dev_net(dst->dev); rt6->rt6i_flags |= RTF_MODIFIED; - if (mtu < IPV6_MIN_MTU) { - u32 features = dst_metric(dst, RTAX_FEATURES); + if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - features |= RTAX_FEATURE_ALLFRAG; - dst_metric_set(dst, RTAX_FEATURES, features); - } + dst_metric_set(dst, RTAX_MTU, mtu); rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index dc495ae2ead0..a3f9f11abf4c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -787,16 +787,16 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .queue_hash_add = inet6_csk_reqsk_queue_hash_add, }; -static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 tsval, u32 tsecr, int oif, - struct tcp_md5sig_key *key, int rst, u8 tclass, - u32 label) +static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq, + u32 ack, u32 win, u32 tsval, u32 tsecr, + int oif, struct tcp_md5sig_key *key, int rst, + u8 tclass, u32 label) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; struct sk_buff *buff; struct flowi6 fl6; - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); struct sock *ctl_sk = net->ipv6.tcp_sk; unsigned int tot_len = sizeof(struct tcphdr); struct dst_entry *dst; @@ -946,7 +946,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) (th->doff << 2); oif = sk ? sk->sk_bound_dev_if : 0; - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG release_sk1: @@ -957,13 +957,13 @@ release_sk1: #endif } -static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 tsval, u32 tsecr, int oif, +static void tcp_v6_send_ack(struct sock *sk, struct sk_buff *skb, u32 seq, + u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, u32 label) { - tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass, - label); + tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, key, 0, + tclass, label); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -971,11 +971,11 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, (tw->tw_flowlabel << 12)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } @@ -986,10 +986,10 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? + tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, - req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, + tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); } @@ -1385,6 +1385,37 @@ ipv6_pktoptions: return 0; } +static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, + const struct tcphdr *th) +{ + /* This is tricky: we move IP6CB at its correct location into + * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because + * _decode_session6() uses IP6CB(). + * barrier() makes sure compiler won't play aliasing games. + */ + memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), + sizeof(struct inet6_skb_parm)); + barrier(); + + TCP_SKB_CB(skb)->seq = ntohl(th->seq); + TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + + skb->len - th->doff*4); + TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); + TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); + TCP_SKB_CB(skb)->tcp_tw_isn = 0; + TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); + TCP_SKB_CB(skb)->sacked = 0; +} + +static void tcp_v6_restore_cb(struct sk_buff *skb) +{ + /* We need to move header back to the beginning if xfrm6_policy_check() + * and tcp_v6_fill_cb() are going to be called again. + */ + memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, + sizeof(struct inet6_skb_parm)); +} + static int tcp_v6_rcv(struct sk_buff *skb) { const struct tcphdr *th; @@ -1416,24 +1447,9 @@ static int tcp_v6_rcv(struct sk_buff *skb) th = tcp_hdr(skb); hdr = ipv6_hdr(skb); - /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() - * barrier() makes sure compiler wont play fool^Waliasing games. - */ - memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), - sizeof(struct inet6_skb_parm)); - barrier(); - - TCP_SKB_CB(skb)->seq = ntohl(th->seq); - TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + - skb->len - th->doff*4); - TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); - TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); - TCP_SKB_CB(skb)->tcp_tw_isn = 0; - TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); - TCP_SKB_CB(skb)->sacked = 0; sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest, - tcp_v6_iif(skb)); + inet6_iif(skb)); if (!sk) goto no_tcp_socket; @@ -1449,6 +1465,8 @@ process: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; + tcp_v6_fill_cb(skb, hdr, th); + #ifdef CONFIG_TCP_MD5SIG if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard_and_relse; @@ -1480,6 +1498,8 @@ no_tcp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; + tcp_v6_fill_cb(skb, hdr, th); + if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) { csum_error: TCP_INC_STATS_BH(net, TCP_MIB_CSUMERRORS); @@ -1503,6 +1523,8 @@ do_time_wait: goto discard_it; } + tcp_v6_fill_cb(skb, hdr, th); + if (skb->len < (th->doff<<2)) { inet_twsk_put(inet_twsk(sk)); goto bad_packet; @@ -1526,6 +1548,7 @@ do_time_wait: inet_twsk_deschedule(tw, &tcp_death_row); inet_twsk_put(tw); sk = sk2; + tcp_v6_restore_cb(skb); goto process; } /* Fall through to ACK */ @@ -1534,6 +1557,7 @@ do_time_wait: tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: + tcp_v6_restore_cb(skb); goto no_tcp_socket; case TCP_TW_SUCCESS: ; @@ -1568,7 +1592,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f6ba535b6feb..dd530f0e5a8a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -514,10 +514,8 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -721,7 +719,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || - (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) || + (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; if (!inet6_mc_check(sk, loc_addr, rmt_addr)) return false; |