diff options
Diffstat (limited to 'net/ipv6')
-rw-r--r-- | net/ipv6/addrconf.c | 46 | ||||
-rw-r--r-- | net/ipv6/af_inet6.c | 20 | ||||
-rw-r--r-- | net/ipv6/ah6.c | 2 | ||||
-rw-r--r-- | net/ipv6/calipso.c | 14 | ||||
-rw-r--r-- | net/ipv6/esp6.c | 4 | ||||
-rw-r--r-- | net/ipv6/esp6_offload.c | 17 | ||||
-rw-r--r-- | net/ipv6/icmp.c | 18 | ||||
-rw-r--r-- | net/ipv6/ip6_fib.c | 7 | ||||
-rw-r--r-- | net/ipv6/ip6_gre.c | 16 | ||||
-rw-r--r-- | net/ipv6/ip6_icmp.c | 12 | ||||
-rw-r--r-- | net/ipv6/ip6_input.c | 13 | ||||
-rw-r--r-- | net/ipv6/ip6_offload.c | 1 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 6 | ||||
-rw-r--r-- | net/ipv6/ip6_tunnel.c | 20 | ||||
-rw-r--r-- | net/ipv6/ip6_vti.c | 12 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 12 | ||||
-rw-r--r-- | net/ipv6/netfilter/ip6_tables.c | 18 | ||||
-rw-r--r-- | net/ipv6/netfilter/nft_dup_ipv6.c | 18 | ||||
-rw-r--r-- | net/ipv6/raw.c | 2 | ||||
-rw-r--r-- | net/ipv6/route.c | 116 | ||||
-rw-r--r-- | net/ipv6/seg6_local.c | 67 | ||||
-rw-r--r-- | net/ipv6/sit.c | 6 | ||||
-rw-r--r-- | net/ipv6/sysctl_net_ipv6.c | 9 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 11 | ||||
-rw-r--r-- | net/ipv6/udp.c | 11 | ||||
-rw-r--r-- | net/ipv6/udp_offload.c | 2 |
26 files changed, 304 insertions, 176 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index eff2cacd5209..a9e53f5942fa 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -205,6 +205,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, + .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, @@ -2467,8 +2469,9 @@ static void addrconf_add_mroute(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, - .fc_type = RTN_UNICAST, + .fc_type = RTN_MULTICAST, .fc_nlinfo.nl_net = dev_net(dev), + .fc_protocol = RTPROT_KERNEL, }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); @@ -5475,6 +5478,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_RA_DEFRTR_METRIC] = cnf->ra_defrtr_metric; array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF @@ -5665,7 +5669,8 @@ static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev, return 0; } -static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) +static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token, + struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct net_device *dev = idev->dev; @@ -5676,12 +5681,29 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) if (!token) return -EINVAL; - if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) + + if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG_MOD(extack, "Device is loopback"); return -EINVAL; - if (!ipv6_accept_ra(idev)) + } + + if (dev->flags & IFF_NOARP) { + NL_SET_ERR_MSG_MOD(extack, + "Device does not do neighbour discovery"); + return -EINVAL; + } + + if (!ipv6_accept_ra(idev)) { + NL_SET_ERR_MSG_MOD(extack, + "Router advertisement is disabled on device"); return -EINVAL; - if (idev->cnf.rtr_solicits == 0) + } + + if (idev->cnf.rtr_solicits == 0) { + NL_SET_ERR_MSG(extack, + "Router solicitation is disabled on device"); return -EINVAL; + } write_lock_bh(&idev->lock); @@ -5789,7 +5811,8 @@ static int inet6_validate_link_af(const struct net_device *dev, return 0; } -static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) +static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); struct nlattr *tb[IFLA_INET6_MAX + 1]; @@ -5802,7 +5825,8 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) BUG(); if (tb[IFLA_INET6_TOKEN]) { - err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); + err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), + extack); if (err) return err; } @@ -6668,6 +6692,14 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { + .procname = "ra_defrtr_metric", + .data = &ipv6_devconf.ra_defrtr_metric, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = (void *)SYSCTL_ONE, + }, + { .procname = "accept_ra_min_hop_limit", .data = &ipv6_devconf.accept_ra_min_hop_limit, .maxlen = sizeof(int), diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8e9c3e9ea36e..802f5111805a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -295,7 +295,8 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, return -EINVAL; snum = ntohs(addr->sin6_port); - if (snum && inet_port_requires_bind_service(net, snum) && + if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && + snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; @@ -439,6 +440,7 @@ out_unlock: int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; + u32 flags = BIND_WITH_LOCK; int err = 0; /* If the socket has its own bind function then use it. */ @@ -451,11 +453,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + BPF_CGROUP_INET6_BIND, &flags); if (err) return err; - return __inet6_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); + return __inet6_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet6_bind); @@ -527,18 +530,19 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = sk->sk_v6_daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, + BPF_CGROUP_INET6_GETPEERNAME, + NULL); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; - } - if (cgroup_bpf_enabled) BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - peer ? BPF_CGROUP_INET6_GETPEERNAME : - BPF_CGROUP_INET6_GETSOCKNAME, + BPF_CGROUP_INET6_GETSOCKNAME, NULL); + } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); return sizeof(*sin); @@ -661,7 +665,6 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, - .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, @@ -954,6 +957,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; + net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 440080da805b..080ee7f44c64 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -316,7 +316,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err) } kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 51184a70ac7e..1578ed9e97d8 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -83,6 +83,9 @@ struct calipso_map_cache_entry { static struct calipso_map_cache_bkt *calipso_cache; +static void calipso_cache_invalidate(void); +static void calipso_doi_putdef(struct calipso_doi *doi_def); + /* Label Mapping Cache Functions */ @@ -444,15 +447,10 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&calipso_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&calipso_doi_list_lock); - call_rcu(&doi_def->rcu, calipso_doi_free_rcu); + calipso_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -508,10 +506,8 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&calipso_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&calipso_doi_list_lock); + calipso_cache_invalidate(); call_rcu(&doi_def->rcu, calipso_doi_free_rcu); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 2b804fcebcc6..727d791ed5e6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -314,7 +314,7 @@ static void esp_output_done(struct crypto_async_request *base, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } } @@ -788,7 +788,7 @@ int esp6_input_done2(struct sk_buff *skb, int err) int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); int hdr_len = skb_network_header_len(skb); - if (!xo || (xo && !(xo->flags & CRYPTO_DONE))) + if (!xo || !(xo->flags & CRYPTO_DONE)) kfree(ESP_SKB_CB(skb)->tmp); if (unlikely(err)) diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 1ca516fb30e1..4af56affaafd 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -254,9 +254,11 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb, skb->encap_hdr_csum = 1; if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) - esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); + esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK | + NETIF_F_SCTP_CRC); else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) - esp_features = features & ~NETIF_F_CSUM_MASK; + esp_features = features & ~(NETIF_F_CSUM_MASK | + NETIF_F_SCTP_CRC); xo->flags |= XFRM_GSO_SEGMENT; @@ -346,8 +348,17 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features ipv6_hdr(skb)->payload_len = htons(len); - if (hw_offload) + if (hw_offload) { + if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) + return -ENOMEM; + + xo = xfrm_offload(skb); + if (!xo) + return -EINVAL; + + xo->flags |= XFRM_XMIT; return 0; + } err = esp6_output_tail(x, skb, &esp); if (err) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f3d05866692e..fd1f896115c1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -331,10 +331,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st } #if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -351,7 +350,7 @@ static void mip6_addr_swap(struct sk_buff *skb) } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -446,7 +445,8 @@ static int icmp6_iif(const struct sk_buff *skb) * Send an ICMP message in response to a packet in error */ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -542,7 +542,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) goto out_bh_enable; - mip6_addr_swap(skb); + mip6_addr_swap(skb, parm); sk = icmpv6_xmit_lock(net); if (!sk) @@ -559,7 +559,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, /* select a more meaningful saddr from input if */ struct net_device *in_netdev; - in_netdev = dev_get_by_index(net, IP6CB(skb)->iif); + in_netdev = dev_get_by_index(net, parm->iif); if (in_netdev) { ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr, inet6_sk(sk)->srcprefs, @@ -640,7 +640,7 @@ EXPORT_SYMBOL(icmp6_send); */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); } @@ -697,10 +697,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index f43e27555725..679699e953f1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -499,7 +499,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb, hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); - if (err < 0) + if (err) goto out; } } @@ -507,7 +507,8 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb, out: kfree(w); - return err; + /* The tree traversal function should never return a positive value. */ + return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) @@ -2485,7 +2486,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh(rt->nh); + fib6_nh = nexthop_fib6_nh_bh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c3bc89b6b1a1..1baf43aacb2e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -678,8 +678,8 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); return -1; } *encap_limit = tel->encap_limit - 1; @@ -805,8 +805,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); return -1; } @@ -837,7 +837,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) &mtu, skb->protocol); if (err != 0) { if (err == -EMSGSIZE) - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -1; } @@ -1063,10 +1063,10 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) { if (skb->protocol == htons(ETH_P_IP)) - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); else - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } goto tx_err; diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 70c8c2f36c98..9e3574880cb0 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -33,23 +33,25 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) } EXPORT_SYMBOL(inet6_unregister_icmp_sender); -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send; rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); if (send) - send(skb, type, code, info, NULL); + send(skb, type, code, info, NULL, parm); rcu_read_unlock(); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(__icmpv6_send); #endif #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_conntrack.h> void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { + struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; struct in6_addr orig_ip; @@ -57,7 +59,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) ct = nf_ct_get(skb_in, &ctinfo); if (!ct || !(ct->status & IPS_SRC_NAT)) { - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); return; } @@ -72,7 +74,7 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) orig_ip = ipv6_hdr(skb_in)->saddr; ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; - icmpv6_send(skb_in, type, code, info); + __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: consume_skb(cloned_skb); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index e96304d8a4a7..80256717868e 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -32,6 +32,7 @@ #include <net/sock.h> #include <net/snmp.h> +#include <net/udp.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -44,7 +45,6 @@ #include <net/inet_ecn.h> #include <net/dst_metadata.h> -INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *)); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -245,16 +245,6 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; - /* While RFC4291 is not explicit about v4mapped addresses - * in IPv6 headers, it seems clear linux dual-stack - * model can not deal properly with these. - * Security models could be fooled by ::ffff:127.0.0.1 for example. - * - * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02 - */ - if (ipv6_addr_v4mapped(&hdr->saddr)) - goto err; - skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); @@ -352,7 +342,6 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, ip6_sublist_rcv(&sublist, curr_dev, curr_net); } -INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *)); /* diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index a80f90bf3ae7..1b9827ff8ccf 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -15,6 +15,7 @@ #include <net/inet_common.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/gro.h> #include "ip6_offload.h" diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 077d43af8226..ff4f9ebcf7f6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -217,6 +217,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } +EXPORT_SYMBOL(ip6_output); bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) { @@ -1510,7 +1511,7 @@ emsgsize: csummode = CHECKSUM_PARTIAL; if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb)); + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ @@ -1754,8 +1755,7 @@ alloc_new_skb: error_efault: err = -EFAULT; error: - if (uarg) - sock_zerocopy_put_abort(uarg, extra_uref); + net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a7950baa05e5..42fe7db6bbb3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1332,8 +1332,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, tel = (void *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { - icmpv6_send(skb, ICMPV6_PARAMPROB, - ICMPV6_HDR_FIELD, offset + 2); + icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, + ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; @@ -1385,11 +1385,11 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, if (err == -EMSGSIZE) switch (protocol) { case IPPROTO_IPIP: - icmp_send(skb, ICMP_DEST_UNREACH, - ICMP_FRAG_NEEDED, htonl(mtu)); + icmp_ndo_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); break; case IPPROTO_IPV6: - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); break; default: break; @@ -2244,6 +2244,16 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head t = rtnl_dereference(t->next); } } + + t = rtnl_dereference(ip6n->tnls_wc[0]); + while (t) { + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, list); + t = rtnl_dereference(t->next); + } } static int __net_init ip6_tnl_init_net(struct net *net) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0225fd694192..e0cc32e45880 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -494,7 +494,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } if (dst->flags & DST_XFRM_QUEUE) - goto queued; + goto xmit; x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) @@ -521,17 +521,19 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } err = -EMSGSIZE; goto tx_err_dst_release; } -queued: +xmit: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 76717478f173..c467c6419893 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1173,6 +1173,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; struct fib6_info *rt = NULL; + u32 defrtr_usr_metric; struct net *net; int lifetime; struct ndisc_options ndopts; @@ -1303,18 +1304,21 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } } - if (rt && lifetime == 0) { + /* Set default route metric as specified by user */ + defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; + /* delete the route if lifetime is 0 or if metric needs change */ + if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } - ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", - rt, lifetime, skb->dev->name); + ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", + rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, - skb->dev, pref); + skb->dev, pref, defrtr_usr_metric); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 0d453fa9e327..eb2b5404806c 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; @@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; @@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - struct xt_table_info *private = xt_table_get_private_protected(t); + struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1443,6 +1443,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; @@ -1552,7 +1554,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; @@ -1598,7 +1600,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 8b5193efb1f1..3a00d95e964e 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -13,8 +13,8 @@ #include <net/netfilter/ipv6/nf_dup_ipv6.h> struct nft_dup_ipv6 { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_dev:8; + u8 sreg_addr; + u8 sreg_dev; }; static void nft_dup_ipv6_eval(const struct nft_expr *expr, @@ -38,16 +38,16 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in6_addr)); + err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + sizeof(struct in6_addr)); if (err < 0) return err; - if (tb[NFTA_DUP_SREG_DEV] != NULL) { - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); - } - return 0; + if (tb[NFTA_DUP_SREG_DEV]) + err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + &priv->sreg_dev, sizeof(int)); + + return err; } static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 1f56d9aae589..bf3646b57c68 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -298,7 +298,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && - !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { + !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 188e114b29b4..373d48073106 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -81,9 +81,11 @@ enum rt6_nud_state { RT6_NUD_SUCCEED = 1 }; -static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); +INDIRECT_CALLABLE_SCOPE +struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_mtu(const struct dst_entry *dst); +INDIRECT_CALLABLE_SCOPE +unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -258,34 +260,16 @@ static struct dst_ops ip6_dst_ops_template = { .confirm_neigh = ip6_confirm_neigh, }; -static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) -{ - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); - - return mtu ? : dst->dev->mtu; -} - -static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu, - bool confirm_neigh) -{ -} - -static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb) -{ -} - static struct dst_ops ip6_dst_blackhole_ops = { - .family = AF_INET6, - .destroy = ip6_dst_destroy, - .check = ip6_dst_check, - .mtu = ip6_blackhole_mtu, - .default_advmss = ip6_default_advmss, - .update_pmtu = ip6_rt_blackhole_update_pmtu, - .redirect = ip6_rt_blackhole_redirect, - .cow_metrics = dst_cow_metrics_generic, - .neigh_lookup = ip6_dst_neigh_lookup, + .family = AF_INET6, + .default_advmss = ip6_default_advmss, + .neigh_lookup = ip6_dst_neigh_lookup, + .check = ip6_dst_check, + .destroy = ip6_dst_destroy, + .cow_metrics = dst_cow_metrics_generic, + .update_pmtu = dst_blackhole_update_pmtu, + .redirect = dst_blackhole_redirect, + .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { @@ -2611,7 +2595,8 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, return NULL; } -static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) +INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, + u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; @@ -2641,6 +2626,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) return dst_ret; } +EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) { @@ -3089,7 +3075,7 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_mtu(const struct dst_entry *dst) +INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { struct inet6_dev *idev; unsigned int mtu; @@ -3111,6 +3097,7 @@ out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it @@ -4252,11 +4239,12 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, - unsigned int pref) + unsigned int pref, + u32 defrtr_usr_metric) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, - .fc_metric = IP6_RT_PRIO_USER, + .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), @@ -5221,9 +5209,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, * nexthops have been replaced by first new, the rest should * be added to it. */ - cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | - NLM_F_REPLACE); - cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; + if (cfg->fc_nlinfo.nlh) { + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | + NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; + } nhn++; } @@ -5613,6 +5603,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_flags |= RTM_F_OFFLOAD; if (rt->trap) rtm->rtm_flags |= RTM_F_TRAP; + if (rt->offload_failed) + rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) @@ -6063,6 +6055,58 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } +void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, + bool offload, bool trap, bool offload_failed) +{ + struct sk_buff *skb; + int err; + + if (f6i->offload == offload && f6i->trap == trap && + f6i->offload_failed == offload_failed) + return; + + f6i->offload = offload; + f6i->trap = trap; + + /* 2 means send notifications only if offload_failed was changed. */ + if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && + f6i->offload_failed == offload_failed) + return; + + f6i->offload_failed = offload_failed; + + if (!rcu_access_pointer(f6i->fib6_node)) + /* The route was removed from the tree, do not send + * notfication. + */ + return; + + if (!net->ipv6.sysctl.fib_notify_on_flag_change) + return; + + skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout; + } + + err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, + 0, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); + return; + +errout: + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); +} +EXPORT_SYMBOL(fib6_info_hw_flags_set); + static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index b07f7c1c82a4..c2a0c78e84d4 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -31,6 +31,8 @@ #include <linux/etherdevice.h> #include <linux/bpf.h> +#define SEG6_F_ATTR(i) BIT(i) + struct seg6_local_lwt; /* callbacks used for customizing the creation and destruction of a behavior */ @@ -660,8 +662,8 @@ seg6_end_dt_mode seg6_end_dt6_parse_mode(struct seg6_local_lwt *slwt) unsigned long parsed_optattrs = slwt->parsed_optattrs; bool legacy, vrfmode; - legacy = !!(parsed_optattrs & (1 << SEG6_LOCAL_TABLE)); - vrfmode = !!(parsed_optattrs & (1 << SEG6_LOCAL_VRFTABLE)); + legacy = !!(parsed_optattrs & SEG6_F_ATTR(SEG6_LOCAL_TABLE)); + vrfmode = !!(parsed_optattrs & SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE)); if (!(legacy ^ vrfmode)) /* both are absent or present: invalid DT6 mode */ @@ -883,32 +885,32 @@ static struct seg6_action_desc seg6_action_table[] = { }, { .action = SEG6_LOCAL_ACTION_END_X, - .attrs = (1 << SEG6_LOCAL_NH6), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6), .input = input_action_end_x, }, { .action = SEG6_LOCAL_ACTION_END_T, - .attrs = (1 << SEG6_LOCAL_TABLE), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_TABLE), .input = input_action_end_t, }, { .action = SEG6_LOCAL_ACTION_END_DX2, - .attrs = (1 << SEG6_LOCAL_OIF), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_OIF), .input = input_action_end_dx2, }, { .action = SEG6_LOCAL_ACTION_END_DX6, - .attrs = (1 << SEG6_LOCAL_NH6), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH6), .input = input_action_end_dx6, }, { .action = SEG6_LOCAL_ACTION_END_DX4, - .attrs = (1 << SEG6_LOCAL_NH4), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_NH4), .input = input_action_end_dx4, }, { .action = SEG6_LOCAL_ACTION_END_DT4, - .attrs = (1 << SEG6_LOCAL_VRFTABLE), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), #ifdef CONFIG_NET_L3_MASTER_DEV .input = input_action_end_dt4, .slwt_ops = { @@ -920,30 +922,30 @@ static struct seg6_action_desc seg6_action_table[] = { .action = SEG6_LOCAL_ACTION_END_DT6, #ifdef CONFIG_NET_L3_MASTER_DEV .attrs = 0, - .optattrs = (1 << SEG6_LOCAL_TABLE) | - (1 << SEG6_LOCAL_VRFTABLE), + .optattrs = SEG6_F_ATTR(SEG6_LOCAL_TABLE) | + SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), .slwt_ops = { .build_state = seg6_end_dt6_build, }, #else - .attrs = (1 << SEG6_LOCAL_TABLE), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_TABLE), #endif .input = input_action_end_dt6, }, { .action = SEG6_LOCAL_ACTION_END_B6, - .attrs = (1 << SEG6_LOCAL_SRH), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), .input = input_action_end_b6, }, { .action = SEG6_LOCAL_ACTION_END_B6_ENCAP, - .attrs = (1 << SEG6_LOCAL_SRH), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), .input = input_action_end_b6_encap, .static_headroom = sizeof(struct ipv6hdr), }, { .action = SEG6_LOCAL_ACTION_END_BPF, - .attrs = (1 << SEG6_LOCAL_BPF), + .attrs = SEG6_F_ATTR(SEG6_LOCAL_BPF), .input = input_action_end_bpf, }, @@ -1366,7 +1368,7 @@ static void __destroy_attrs(unsigned long parsed_attrs, int max_parsed, * attribute; otherwise, we call the destroy() callback. */ for (i = 0; i < max_parsed; ++i) { - if (!(parsed_attrs & (1 << i))) + if (!(parsed_attrs & SEG6_F_ATTR(i))) continue; param = &seg6_action_params[i]; @@ -1395,7 +1397,7 @@ static int parse_nla_optional_attrs(struct nlattr **attrs, int err, i; for (i = 0; i < SEG6_LOCAL_MAX + 1; ++i) { - if (!(desc->optattrs & (1 << i)) || !attrs[i]) + if (!(desc->optattrs & SEG6_F_ATTR(i)) || !attrs[i]) continue; /* once here, the i-th attribute is provided by the @@ -1408,7 +1410,7 @@ static int parse_nla_optional_attrs(struct nlattr **attrs, goto parse_optattrs_err; /* current attribute has been correctly parsed */ - parsed_optattrs |= (1 << i); + parsed_optattrs |= SEG6_F_ATTR(i); } /* store in the tunnel state all the optional attributed successfully @@ -1494,7 +1496,7 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) /* parse the required attributes */ for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { - if (desc->attrs & (1 << i)) { + if (desc->attrs & SEG6_F_ATTR(i)) { if (!attrs[i]) return -EINVAL; @@ -1599,7 +1601,7 @@ static int seg6_local_fill_encap(struct sk_buff *skb, attrs = slwt->desc->attrs | slwt->parsed_optattrs; for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { - if (attrs & (1 << i)) { + if (attrs & SEG6_F_ATTR(i)) { param = &seg6_action_params[i]; err = param->put(skb, slwt); if (err < 0) @@ -1620,30 +1622,30 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt) attrs = slwt->desc->attrs | slwt->parsed_optattrs; - if (attrs & (1 << SEG6_LOCAL_SRH)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_SRH)) nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3); - if (attrs & (1 << SEG6_LOCAL_TABLE)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_TABLE)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_NH4)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_NH4)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_NH6)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_NH6)) nlsize += nla_total_size(16); - if (attrs & (1 << SEG6_LOCAL_IIF)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_IIF)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_OIF)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_OIF)) nlsize += nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_BPF)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_BPF)) nlsize += nla_total_size(sizeof(struct nlattr)) + nla_total_size(MAX_PROG_NAME) + nla_total_size(4); - if (attrs & (1 << SEG6_LOCAL_VRFTABLE)) + if (attrs & SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE)) nlsize += nla_total_size(4); return nlsize; @@ -1670,7 +1672,7 @@ static int seg6_local_cmp_encap(struct lwtunnel_state *a, return 1; for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { - if (attrs_a & (1 << i)) { + if (attrs_a & SEG6_F_ATTR(i)) { param = &seg6_action_params[i]; if (param->cmp(slwt_a, slwt_b)) return 1; @@ -1692,6 +1694,15 @@ static const struct lwtunnel_encap_ops seg6_local_ops = { int __init seg6_local_init(void) { + /* If the max total number of defined attributes is reached, then your + * kernel build stops here. + * + * This check is required to avoid arithmetic overflows when processing + * behavior attributes and the maximum number of defined attributes + * exceeds the allowed value. + */ + BUILD_BUG_ON(SEG6_LOCAL_MAX + 1 > BITS_PER_TYPE(unsigned long)); + return lwtunnel_encap_add_ops(&seg6_local_ops, LWTUNNEL_ENCAP_SEG6_LOCAL); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 93636867aee2..9fdccf0718b5 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -987,7 +987,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } @@ -1867,9 +1867,9 @@ static void __net_exit sit_destroy_tunnels(struct net *net, if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); - for (prio = 1; prio < 4; prio++) { + for (prio = 0; prio < 4; prio++) { int h; - for (h = 0; h < IP6_SIT_HASH_SIZE; h++) { + for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 5b60a4bdd36a..263ab43ed06b 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -160,6 +160,15 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "fib_notify_on_flag_change", + .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &two, + }, { } }; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0e1509b02cb3..d0f007741e8e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1175,6 +1175,11 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); @@ -1420,6 +1425,8 @@ out: return NULL; } +INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, + u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -1473,7 +1480,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || - dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, + dst, np->rx_dst_cookie) == NULL) { dst_release(dst); sk->sk_rx_dst = NULL; } @@ -2121,6 +2129,7 @@ struct proto tcpv6_prot = { .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, + .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b9f3dfdd2383..d25e5a9252fd 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -409,9 +409,8 @@ try_again: } *addr_len = sizeof(*sin6); - if (cgroup_bpf_enabled) - BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, - (struct sockaddr *)sin6); + BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, + (struct sockaddr *)sin6); } if (udp_sk(sk)->gro_enabled) @@ -1462,7 +1461,7 @@ do_udp_sendmsg: fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; - if (cgroup_bpf_enabled && !connected) { + if (cgroup_bpf_enabled(BPF_CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, &fl6.saddr); if (err) @@ -1608,8 +1607,10 @@ void udpv6_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) + if (up->encap_enabled) { static_branch_dec(&udpv6_encap_needed_key); + udp_encap_disable(); + } } inet6_destroy_sock(sk); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index c7bd7b1a04c1..faa823c24292 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -42,7 +42,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) - return __udp_gso_segment(skb, features); + return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) |