summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c56
-rw-r--r--net/ipv6/addrlabel.c1
-rw-r--r--net/ipv6/af_inet6.c17
-rw-r--r--net/ipv6/datagram.c2
-rw-r--r--net/ipv6/esp6.c9
-rw-r--r--net/ipv6/esp6_offload.c3
-rw-r--r--net/ipv6/exthdrs_core.c2
-rw-r--r--net/ipv6/icmp.c5
-rw-r--r--net/ipv6/ila/ila_xlat.c1
-rw-r--r--net/ipv6/inet6_hashtables.c4
-rw-r--r--net/ipv6/ip6_fib.c6
-rw-r--r--net/ipv6/ip6_flowlabel.c2
-rw-r--r--net/ipv6/ip6_gre.c68
-rw-r--r--net/ipv6/ip6_input.c26
-rw-r--r--net/ipv6/ip6_output.c22
-rw-r--r--net/ipv6/ip6_tunnel.c14
-rw-r--r--net/ipv6/ip6_vti.c4
-rw-r--r--net/ipv6/ip6mr.c2
-rw-r--r--net/ipv6/ipv6_sockglue.c27
-rw-r--r--net/ipv6/ndisc.c3
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_tproxy_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nft_dup_ipv6.c18
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c6
-rw-r--r--net/ipv6/ping.c3
-rw-r--r--net/ipv6/raw.c9
-rw-r--r--net/ipv6/route.c34
-rw-r--r--net/ipv6/seg6.c5
-rw-r--r--net/ipv6/seg6_hmac.c2
-rw-r--r--net/ipv6/seg6_iptunnel.c5
-rw-r--r--net/ipv6/seg6_local.c2
-rw-r--r--net/ipv6/sit.c26
-rw-r--r--net/ipv6/syncookies.c10
-rw-r--r--net/ipv6/tcp_ipv6.c41
-rw-r--r--net/ipv6/udp.c40
-rw-r--r--net/ipv6/udp_impl.h1
-rw-r--r--net/ipv6/udplite.c11
-rw-r--r--net/ipv6/xfrm6_policy.c10
38 files changed, 312 insertions, 189 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 92b32d131e1c..c523236d934e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -313,9 +313,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp)
static void addrconf_mod_rs_timer(struct inet6_dev *idev,
unsigned long when)
{
- if (!timer_pending(&idev->rs_timer))
+ if (!mod_timer(&idev->rs_timer, jiffies + when))
in6_dev_hold(idev);
- mod_timer(&idev->rs_timer, jiffies + when);
}
static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp,
@@ -789,6 +788,7 @@ static void dev_forward_change(struct inet6_dev *idev)
{
struct net_device *dev;
struct inet6_ifaddr *ifa;
+ LIST_HEAD(tmp_addr_list);
if (!idev)
return;
@@ -807,14 +807,24 @@ static void dev_forward_change(struct inet6_dev *idev)
}
}
+ read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
if (ifa->flags&IFA_F_TENTATIVE)
continue;
+ list_add_tail(&ifa->if_list_aux, &tmp_addr_list);
+ }
+ read_unlock_bh(&idev->lock);
+
+ while (!list_empty(&tmp_addr_list)) {
+ ifa = list_first_entry(&tmp_addr_list,
+ struct inet6_ifaddr, if_list_aux);
+ list_del(&ifa->if_list_aux);
if (idev->cnf.forwarding)
addrconf_join_anycast(ifa);
else
addrconf_leave_anycast(ifa);
}
+
inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_FORWARDING,
dev->ifindex, &idev->cnf);
@@ -1091,10 +1101,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
goto out;
}
- if (net->ipv6.devconf_all->disable_policy ||
- idev->cnf.disable_policy)
- f6i->dst_nopolicy = true;
-
neigh_parms_data_state_setall(idev->nd_parms);
ifa->addr = *cfg->pfx;
@@ -1361,7 +1367,7 @@ retry:
* idev->desync_factor if it's larger
*/
cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
- max_desync_factor = min_t(__u32,
+ max_desync_factor = min_t(long,
idev->cnf.max_desync_factor,
cnf_temp_preferred_lft - regen_advance);
@@ -2535,12 +2541,18 @@ static void manage_tempaddrs(struct inet6_dev *idev,
ipv6_ifa_notify(0, ift);
}
- if ((create || list_empty(&idev->tempaddr_list)) &&
- idev->cnf.use_tempaddr > 0) {
+ /* Also create a temporary address if it's enabled but no temporary
+ * address currently exists.
+ * However, we get called with valid_lft == 0, prefered_lft == 0, create == false
+ * as part of cleanup (ie. deleting the mngtmpaddr).
+ * We don't want that to result in creating a new temporary ip address.
+ */
+ if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft))
+ create = true;
+
+ if (create && idev->cnf.use_tempaddr > 0) {
/* When a new public address is created as described
* in [ADDRCONF], also create a new temporary address.
- * Also create a temporary address if it's enabled but
- * no temporary address currently exists.
*/
read_unlock_bh(&idev->lock);
ipv6_create_tempaddr(ifp, NULL, false);
@@ -3713,7 +3725,8 @@ static int addrconf_ifdown(struct net_device *dev, int how)
unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN;
struct net *net = dev_net(dev);
struct inet6_dev *idev;
- struct inet6_ifaddr *ifa, *tmp;
+ struct inet6_ifaddr *ifa;
+ LIST_HEAD(tmp_addr_list);
bool keep_addr = false;
bool was_ready;
int state, i;
@@ -3805,16 +3818,23 @@ restart:
write_lock_bh(&idev->lock);
}
- list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
+ list_for_each_entry(ifa, &idev->addr_list, if_list)
+ list_add_tail(&ifa->if_list_aux, &tmp_addr_list);
+ write_unlock_bh(&idev->lock);
+
+ while (!list_empty(&tmp_addr_list)) {
struct fib6_info *rt = NULL;
bool keep;
+ ifa = list_first_entry(&tmp_addr_list,
+ struct inet6_ifaddr, if_list_aux);
+ list_del(&ifa->if_list_aux);
+
addrconf_del_dad_work(ifa);
keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
!addr_is_local(&ifa->addr);
- write_unlock_bh(&idev->lock);
spin_lock_bh(&ifa->lock);
if (keep) {
@@ -3845,15 +3865,14 @@ restart:
addrconf_leave_solict(ifa->idev, &ifa->addr);
}
- write_lock_bh(&idev->lock);
if (!keep) {
+ write_lock_bh(&idev->lock);
list_del_rcu(&ifa->if_list);
+ write_unlock_bh(&idev->lock);
in6_ifa_put(ifa);
}
}
- write_unlock_bh(&idev->lock);
-
/* Step 5: Discard anycast and multicast list */
if (how) {
ipv6_ac_destroy_dev(idev);
@@ -4184,7 +4203,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
send_rs = send_mld &&
ipv6_accept_ra(ifp->idev) &&
ifp->idev->cnf.rtr_solicits != 0 &&
- (dev->flags&IFF_LOOPBACK) == 0;
+ (dev->flags & IFF_LOOPBACK) == 0 &&
+ (dev->type != ARPHRD_TUNNEL);
read_unlock_bh(&ifp->idev->lock);
/* While dad is in progress mld report's source address is in6_addrany.
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 8a22486cf270..17ac45aa7194 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -437,6 +437,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh,
{
struct ifaddrlblmsg *ifal = nlmsg_data(nlh);
ifal->ifal_family = AF_INET6;
+ ifal->__ifal_reserved = 0;
ifal->ifal_prefixlen = prefixlen;
ifal->ifal_flags = 0;
ifal->ifal_index = ifindex;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 942da168f18f..a5fc9444c728 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -104,6 +104,13 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
}
+void inet6_sock_destruct(struct sock *sk)
+{
+ inet6_cleanup_sock(sk);
+ inet_sock_destruct(sk);
+}
+EXPORT_SYMBOL_GPL(inet6_sock_destruct);
+
static int inet6_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
@@ -196,7 +203,7 @@ lookup_protocol:
inet->hdrincl = 1;
}
- sk->sk_destruct = inet_sock_destruct;
+ sk->sk_destruct = inet6_sock_destruct;
sk->sk_family = PF_INET6;
sk->sk_protocol = protocol;
@@ -222,7 +229,7 @@ lookup_protocol:
inet->mc_list = NULL;
inet->rcv_tos = 0;
- if (net->ipv4.sysctl_ip_no_pmtu_disc)
+ if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
@@ -498,6 +505,12 @@ void inet6_destroy_sock(struct sock *sk)
}
EXPORT_SYMBOL_GPL(inet6_destroy_sock);
+void inet6_cleanup_sock(struct sock *sk)
+{
+ inet6_destroy_sock(sk);
+}
+EXPORT_SYMBOL_GPL(inet6_cleanup_sock);
+
/*
* This does both peername and sockname.
*/
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 390bedde21a5..06261603e083 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -50,7 +50,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
- fl6->flowlabel = np->flow_label;
+ fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6->flowi6_uid = sk->sk_uid;
if (!fl6->flowi6_oif)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 79f117e33b80..a1cdb43e7216 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -230,10 +230,9 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
- unsigned int allocsz;
- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
- if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+ if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+ ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
goto cow;
if (!skb_cloned(skb)) {
@@ -507,7 +506,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 1c532638b2ad..e19c1844276f 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -314,6 +314,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features
secpath_reset(skb);
+ if (skb_needs_linearize(skb, skb->dev->features) &&
+ __skb_linearize(skb))
+ return -ENOMEM;
return 0;
}
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index da46c4284676..49e31e4ae7b7 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -143,6 +143,8 @@ int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type)
optlen = 1;
break;
default:
+ if (len < 2)
+ goto bad;
optlen = nh[offset + 1] + 2;
if (optlen > len)
goto bad;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 3db10cae7b17..169467b5c98a 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -410,7 +410,10 @@ static struct net_device *icmp6_dev(const struct sk_buff *skb)
if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
const struct rt6_info *rt6 = skb_rt6_info(skb);
- if (rt6)
+ /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.),
+ * and ip6_null_entry could be set to skb if no route is found.
+ */
+ if (rt6 && rt6->rt6i_idev)
dev = rt6->rt6i_idev->dev;
}
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 5fc1f4e0c0cf..10f1367eb4ca 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -477,6 +477,7 @@ int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info)
rcu_read_lock();
+ ret = -ESRCH;
ila = ila_lookup_by_params(&xp, ilan);
if (ila) {
ret = ila_dump_info(ila,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index ab12e00f6bff..528c78bc920e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -262,7 +262,7 @@ not_unique:
return -EADDRNOTAVAIL;
}
-static u32 inet6_sk_port_offset(const struct sock *sk)
+static u64 inet6_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
@@ -274,7 +274,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk)
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- u32 port_offset = 0;
+ u64 port_offset = 0;
if (!inet_sk(sk)->inet_num)
port_offset = inet6_sk_port_offset(sk);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ef55489651f8..d74a825c50f0 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1433,13 +1433,9 @@ out:
if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
pn_leaf = fib6_find_prefix(info->nl_net, table,
pn);
-#if RT6_DEBUG >= 2
- if (!pn_leaf) {
- WARN_ON(!pn_leaf);
+ if (!pn_leaf)
pn_leaf =
info->nl_net->ipv6.fib6_null_entry;
- }
-#endif
fib6_info_hold(pn_leaf);
rcu_assign_pointer(pn->leaf, pn_leaf);
}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index d64b83e85642..e6e1190a6ed9 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -535,7 +535,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
{
- int uninitialized_var(err);
+ int err;
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e550db28aabb..2d34bd98fcce 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -711,6 +711,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
{
struct ip6_tnl *tunnel = netdev_priv(dev);
__be16 protocol;
+ __be16 flags;
if (dev->type == ARPHRD_ETHER)
IPCB(skb)->flags = 0;
@@ -720,16 +721,12 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
else
fl6->daddr = tunnel->parms.raddr;
- if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
- return -ENOMEM;
-
/* Push GRE header. */
protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto;
if (tunnel->parms.collect_md) {
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
- __be16 flags;
int tun_hlen;
tun_info = skb_tunnel_info(skb);
@@ -751,19 +748,25 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
(TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ);
tun_hlen = gre_calc_hlen(flags);
+ if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen))
+ return -ENOMEM;
+
gre_build_header(skb, tun_hlen,
flags, protocol,
tunnel_id_to_key32(tun_info->key.tun_id),
- (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++)
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno))
: 0);
} else {
- if (tunnel->parms.o_flags & TUNNEL_SEQ)
- tunnel->o_seqno++;
+ if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen))
+ return -ENOMEM;
- gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
+ flags = tunnel->parms.o_flags;
+
+ gre_build_header(skb, tunnel->tun_hlen, flags,
protocol, tunnel->parms.o_key,
- htonl(tunnel->o_seqno));
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno))
+ : 0);
}
return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
@@ -927,7 +930,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
__be16 proto;
__u32 mtu;
int nhoff;
- int thoff;
if (!pskb_inet_may_pull(skb))
goto tx_err;
@@ -939,19 +941,26 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
goto tx_err;
if (skb->len > dev->mtu + dev->hard_header_len) {
- pskb_trim(skb, dev->mtu + dev->hard_header_len);
+ if (pskb_trim(skb, dev->mtu + dev->hard_header_len))
+ goto tx_err;
truncate = true;
}
- nhoff = skb_network_header(skb) - skb_mac_header(skb);
+ nhoff = skb_network_offset(skb);
if (skb->protocol == htons(ETH_P_IP) &&
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_offset(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
goto tx_err;
@@ -995,12 +1004,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
ntohl(tun_id),
ntohl(md->u.index), truncate,
false);
+ proto = htons(ETH_P_ERSPAN);
} else if (md->version == 2) {
erspan_build_header_v2(skb,
ntohl(tun_id),
md->u.md2.dir,
get_hwid(&md->u.md2),
truncate, false);
+ proto = htons(ETH_P_ERSPAN2);
} else {
goto tx_err;
}
@@ -1023,25 +1034,26 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
break;
}
- if (t->parms.erspan_ver == 1)
+ if (t->parms.erspan_ver == 1) {
erspan_build_header(skb, ntohl(t->parms.o_key),
t->parms.index,
truncate, false);
- else if (t->parms.erspan_ver == 2)
+ proto = htons(ETH_P_ERSPAN);
+ } else if (t->parms.erspan_ver == 2) {
erspan_build_header_v2(skb, ntohl(t->parms.o_key),
t->parms.dir,
t->parms.hwid,
truncate, false);
- else
+ proto = htons(ETH_P_ERSPAN2);
+ } else {
goto tx_err;
+ }
fl6.daddr = t->parms.raddr;
}
/* Push GRE header. */
- proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN)
- : htons(ETH_P_ERSPAN2);
- gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++));
+ gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno)));
/* TooBig packet may have updated dst->dev's mtu */
if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
@@ -1132,14 +1144,16 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
dev->needed_headroom = dst_len;
if (set_mtu) {
- dev->mtu = rt->dst.dev->mtu - t_hlen;
+ int mtu = rt->dst.dev->mtu - t_hlen;
+
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu -= 8;
+ mtu -= 8;
if (dev->type == ARPHRD_ETHER)
- dev->mtu -= ETH_HLEN;
+ mtu -= ETH_HLEN;
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+ WRITE_ONCE(dev->mtu, mtu);
}
}
ip6_rt_put(rt);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index e6c4966aa956..ebf90bce063a 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -44,21 +44,25 @@
#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 *));
+void udp_v6_early_demux(struct sk_buff *);
+void tcp_v6_early_demux(struct sk_buff *);
static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
- void (*edemux)(struct sk_buff *skb);
-
- if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
- const struct inet6_protocol *ipprot;
-
- ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
- if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
- INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
- udp_v6_early_demux, skb);
+ if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
+ !skb_dst(skb) && !skb->sk) {
+ switch (ipv6_hdr(skb)->nexthdr) {
+ case IPPROTO_TCP:
+ if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
+ tcp_v6_early_demux(skb);
+ break;
+ case IPPROTO_UDP:
+ if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
+ udp_v6_early_demux(skb);
+ break;
+ }
}
+
if (!skb_valid_dst(skb))
ip6_route_input(skb);
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5585e3a94f3c..d3455585e6a8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -130,7 +130,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
if (lwtunnel_xmit_redirect(dst->lwtstate)) {
int res = lwtunnel_xmit(skb);
- if (res < 0 || res == LWTUNNEL_XMIT_DONE)
+ if (res != LWTUNNEL_XMIT_CONTINUE)
return res;
}
@@ -177,7 +177,13 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
int err;
skb_mark_not_on_list(segs);
- err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+ /* Last GSO segment can be smaller than gso_size (and MTU).
+ * Adding a fragment header would produce an "atomic fragment",
+ * which is considered harmful (RFC-8021). Avoid that.
+ */
+ err = segs->len > mtu ?
+ ip6_fragment(net, sk, segs, ip6_finish_output2) :
+ ip6_finish_output2(net, sk, segs);
if (err && ret == 0)
ret = err;
}
@@ -919,6 +925,9 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
if (err < 0)
goto fail;
+ /* We prevent @rt from being freed. */
+ rcu_read_lock();
+
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
@@ -942,6 +951,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
if (err == 0) {
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGOKS);
+ rcu_read_unlock();
return 0;
}
@@ -949,6 +959,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGFAILS);
+ rcu_read_unlock();
return err;
slow_path_clean:
@@ -1850,8 +1861,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+ u8 icmp6_type;
- ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+ if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl)
+ icmp6_type = fl6->fl6_icmp_type;
+ else
+ icmp6_type = icmp6_hdr(skb)->icmp6_type;
+ ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 878a08c40fff..b97611894882 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1201,8 +1201,8 @@ route_lookup:
*/
max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr)
+ dst->header_len + t->hlen;
- if (max_headroom > dev->needed_headroom)
- dev->needed_headroom = max_headroom;
+ if (max_headroom > READ_ONCE(dev->needed_headroom))
+ WRITE_ONCE(dev->needed_headroom, max_headroom);
err = ip6_tnl_encap(skb, t, &proto, fl6);
if (err)
@@ -1430,6 +1430,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
struct __ip6_tnl_parm *p = &t->parms;
struct flowi6 *fl6 = &t->fl.u.ip6;
int t_hlen;
+ int mtu;
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -1472,12 +1473,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
dev->hard_header_len = rt->dst.dev->hard_header_len +
t_hlen;
- dev->mtu = rt->dst.dev->mtu - t_hlen;
+ mtu = rt->dst.dev->mtu - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu -= 8;
+ mtu -= 8;
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+ WRITE_ONCE(dev->mtu, mtu);
}
ip6_rt_put(rt);
}
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 8b44d3b53844..e4cd6909e9bb 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -558,12 +558,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
vti6_addr_conflict(t, ipv6_hdr(skb)))
goto tx_err;
- xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET6);
break;
case htons(ETH_P_IP):
- xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ xfrm_decode_session(skb, &fl, AF_INET);
break;
default:
goto tx_err;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6248e00c2bf7..6642bc7b9870 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1065,7 +1065,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
- skb_push(skb, -skb_network_offset(pkt));
+ __skb_pull(skb, skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 5352c7e68c42..86c550d63543 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -164,15 +164,18 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
rtnl_lock();
lock_sock(sk);
+ /* Another thread has converted the socket into IPv4 with
+ * IPV6_ADDRFORM concurrently.
+ */
+ if (unlikely(sk->sk_family != AF_INET6))
+ goto unlock;
+
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;
@@ -203,7 +206,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
}
- fl6_free_socklist(sk);
__ipv6_sock_mc_close(sk);
__ipv6_sock_ac_close(sk);
@@ -238,14 +240,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
- opt = xchg((__force struct ipv6_txoptions **)&np->opt,
- NULL);
- if (opt) {
- atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
- txopt_put(opt);
- }
- pktopt = xchg(&np->pktoptions, NULL);
- kfree_skb(pktopt);
+
+ /* Disable all options not to allocate memory anymore,
+ * but there is still a race. See the lockless path
+ * in udpv6_sendmsg() and ipv6_local_rxpmtu().
+ */
+ np->rxopt.all = 0;
+
+ inet6_cleanup_sock(sk);
/*
* ... and add it to the refcnt debug socks count
@@ -924,6 +926,7 @@ pref_skip_coa:
break;
}
+unlock:
release_sock(sk);
if (needs_rtnl)
rtnl_unlock();
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 118e19cabb72..74977ec77c57 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -196,7 +196,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
static inline int ndisc_is_useropt(const struct net_device *dev,
struct nd_opt_hdr *opt)
{
- return opt->nd_opt_type == ND_OPT_RDNSS ||
+ return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
+ opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL ||
opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
ndisc_ops_is_useropt(dev, opt->nd_opt_type);
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index 69c021704abd..aa5bb8789ba0 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -97,7 +97,7 @@ nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
const struct net_device *indev)
{
- __be16 uninitialized_var(dport), uninitialized_var(sport);
+ __be16 dport, sport;
const struct in6_addr *daddr = NULL, *saddr = NULL;
struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var;
struct sk_buff *data_skb = NULL;
diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c
index 34d51cd426b0..00761924f276 100644
--- a/net/ipv6/netfilter/nf_tproxy_ipv6.c
+++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c
@@ -63,7 +63,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
lport ? lport : hp->dest,
skb->dev, NF_TPROXY_LOOKUP_LISTENER);
if (sk2) {
- inet_twsk_deschedule_put(inet_twsk(sk));
+ nf_tproxy_twsk_deschedule_put(inet_twsk(sk));
sk = sk2;
}
}
diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c
index 2af32200507d..c4aa8d27e040 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/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 7ece86afd079..03dbd16f9ad5 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -37,6 +37,9 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) {
lookup_flags |= RT6_LOOKUP_F_IFACE;
fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev);
+ } else if ((priv->flags & NFTA_FIB_F_IIF) &&
+ (netif_is_l3_master(dev) || netif_is_l3_slave(dev))) {
+ fl6->flowi6_oif = dev->ifindex;
}
if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST)
@@ -179,7 +182,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
goto put_rt_err;
- if (oif && oif != rt->rt6i_idev->dev)
+ if (oif && oif != rt->rt6i_idev->dev &&
+ l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
goto put_rt_err;
nft_fib_store_result(dest, priv, rt->rt6i_idev->dev);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 98ac32b49d8c..91f352427dca 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -96,7 +96,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
addr_type = ipv6_addr_type(daddr);
if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) ||
(addr_type & IPV6_ADDR_MAPPED) ||
- (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if))
+ (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if &&
+ l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if))
return -EINVAL;
/* TODO: use ip6_datagram_send_ctl to get options from cmsg */
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 828dd95840b4..731485b18de3 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -539,6 +539,7 @@ csum_copy_err:
static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct raw6_sock *rp)
{
+ struct ipv6_txoptions *opt;
struct sk_buff *skb;
int err = 0;
int offset;
@@ -556,6 +557,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
offset = rp->offset;
total_len = inet_sk(sk)->cork.base.length;
+ opt = inet6_sk(sk)->cork.opt;
+ total_len -= opt ? opt->opt_flen : 0;
+
if (offset >= total_len - 1) {
err = -EINVAL;
ip6_flush_pending_frames(sk);
@@ -824,7 +828,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
@@ -1252,8 +1257,6 @@ static void raw6_destroy(struct sock *sk)
lock_sock(sk);
ip6_flush_pending_frames(sk);
release_sock(sk);
-
- inet6_destroy_sock(sk);
}
static int rawv6_init_sk(struct sock *sk)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 619d9dffa9e4..209d52ebbd19 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4483,8 +4483,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
}
f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
- if (!IS_ERR(f6i))
+ if (!IS_ERR(f6i)) {
f6i->dst_nocount = true;
+
+ if (!anycast &&
+ (net->ipv6.devconf_all->disable_policy ||
+ idev->cnf.disable_policy))
+ f6i->dst_nopolicy = true;
+ }
+
return f6i;
}
@@ -5401,16 +5408,17 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i)
nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
&nexthop_len);
} else {
+ struct fib6_info *sibling, *next_sibling;
struct fib6_nh *nh = f6i->fib6_nh;
nexthop_len = 0;
if (f6i->fib6_nsiblings) {
- nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
- + NLA_ALIGN(sizeof(struct rtnexthop))
- + nla_total_size(16) /* RTA_GATEWAY */
- + lwtunnel_get_encap_size(nh->fib_nh_lws);
+ rt6_nh_nlmsg_size(nh, &nexthop_len);
- nexthop_len *= f6i->fib6_nsiblings;
+ list_for_each_entry_safe(sibling, next_sibling,
+ &f6i->fib6_siblings, fib6_siblings) {
+ rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
+ }
}
nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
}
@@ -6352,10 +6360,16 @@ static void __net_exit ip6_route_net_exit(struct net *net)
static int __net_init ip6_route_net_init_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops,
- sizeof(struct ipv6_route_iter));
- proc_create_net_single("rt6_stats", 0444, net->proc_net,
- rt6_stats_seq_show, NULL);
+ if (!proc_create_net("ipv6_route", 0, net->proc_net,
+ &ipv6_route_seq_ops,
+ sizeof(struct ipv6_route_iter)))
+ return -ENOMEM;
+
+ if (!proc_create_net_single("rt6_stats", 0444, net->proc_net,
+ rt6_stats_seq_show, NULL)) {
+ remove_proc_entry("ipv6_route", net->proc_net);
+ return -ENOMEM;
+ }
#endif
return 0;
}
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 75421a472d25..f5c448c276fe 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -125,6 +125,11 @@ static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
goto out_unlock;
}
+ if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
if (hinfo) {
err = seg6_hmac_info_del(net, hmackeyid);
if (err)
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index ffcfcd2b128f..65394abf4736 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -401,7 +401,6 @@ int __init seg6_hmac_init(void)
{
return seg6_hmac_init_algo();
}
-EXPORT_SYMBOL(seg6_hmac_init);
int __net_init seg6_hmac_net_init(struct net *net)
{
@@ -411,7 +410,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
return 0;
}
-EXPORT_SYMBOL(seg6_hmac_net_init);
void seg6_hmac_exit(void)
{
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 6954db1fd26e..b626e0b62a54 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -171,6 +171,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, tot_len);
return 0;
@@ -223,6 +225,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
}
#endif
+ hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+
skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
return 0;
@@ -284,7 +288,6 @@ static int seg6_do_srh(struct sk_buff *skb)
break;
}
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
return 0;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 802eebf8ac4b..ef5b5cee2201 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -421,7 +421,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
@@ -453,7 +452,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
if (err)
goto drop;
- ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 16e75a996b74..8d704ea94693 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -310,9 +310,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) :
NULL;
- rcu_read_lock();
-
- ca = t->prl_count < cmax ? t->prl_count : cmax;
+ ca = min(t->prl_count, cmax);
if (!kp) {
/* We don't try hard to allocate much memory for
@@ -327,7 +325,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
}
}
- c = 0;
+ rcu_read_lock();
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
@@ -339,7 +337,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
if (kprl.addr != htonl(INADDR_ANY))
break;
}
-out:
+
rcu_read_unlock();
len = sizeof(*kp) * c;
@@ -348,7 +346,7 @@ out:
ret = -EFAULT;
kfree(kp);
-
+out:
return ret;
}
@@ -1056,12 +1054,13 @@ tx_err:
static void ipip6_tunnel_bind_dev(struct net_device *dev)
{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ int t_hlen = tunnel->hlen + sizeof(struct iphdr);
struct net_device *tdev = NULL;
- struct ip_tunnel *tunnel;
+ int hlen = LL_MAX_HEADER;
const struct iphdr *iph;
struct flowi4 fl4;
- tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
if (iph->daddr) {
@@ -1084,12 +1083,15 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
if (tdev && !netif_is_l3_master(tdev)) {
- int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+ int mtu;
- dev->mtu = tdev->mtu - t_hlen;
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
+ mtu = tdev->mtu - t_hlen;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+ WRITE_ONCE(dev->mtu, mtu);
+ hlen = tdev->hard_header_len + tdev->needed_headroom;
}
+ dev->needed_headroom = t_hlen + hlen;
}
static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p,
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 37ab254f7b92..8c3beffbaf06 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
__u8 rcv_wscale;
u32 tsoff = 0;
- if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
+ !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
@@ -179,14 +180,15 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
treq->af_specific = &tcp_request_sock_ipv6_ops;
treq->tfo_listener = false;
- if (security_inet_conn_request(sk, skb, req))
- goto out_free;
-
req->mss = mss;
ireq->ir_rmt_port = th->source;
ireq->ir_num = ntohs(th->dest);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+
+ if (security_inet_conn_request(sk, skb, req))
+ goto out_free;
+
if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 063898cae3e5..7cb622d300aa 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -106,7 +106,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
if (dst && dst_hold_safe(dst)) {
const struct rt6_info *rt = (const struct rt6_info *)dst;
- sk->sk_rx_dst = dst;
+ rcu_assign_pointer(sk->sk_rx_dst, dst);
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
}
@@ -264,6 +264,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
+ fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
@@ -334,6 +335,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
late_failure:
tcp_set_state(sk, TCP_CLOSE);
+ if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+ inet_reset_saddr(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
@@ -1316,14 +1319,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
/* Clone pktoptions received with SYN, if we own the req */
if (ireq->pktopts) {
- newnp->pktoptions = skb_clone(ireq->pktopts,
- sk_gfp_mask(sk, GFP_ATOMIC));
+ newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
- if (newnp->pktoptions) {
+ if (newnp->pktoptions)
tcp_v6_restore_cb(newnp->pktoptions);
- skb_set_owner_r(newnp->pktoptions, newsk);
- }
}
} else {
if (!req_unhash && found_dup_sk) {
@@ -1391,18 +1391,21 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
--ANK (980728)
*/
if (np->rxopt.all)
- opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
+ opt_skb = skb_clone_and_charge_r(skb, sk);
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
- struct dst_entry *dst = sk->sk_rx_dst;
+ struct dst_entry *dst;
+
+ dst = rcu_dereference_protected(sk->sk_rx_dst,
+ lockdep_sock_is_held(sk));
sock_rps_save_rxhash(sk, 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) {
+ RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
dst_release(dst);
- sk->sk_rx_dst = NULL;
}
}
@@ -1470,7 +1473,6 @@ ipv6_pktoptions:
if (np->repflow)
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
- skb_set_owner_r(opt_skb, sk);
tcp_v6_restore_cb(opt_skb);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
@@ -1726,7 +1728,7 @@ do_time_wait:
goto discard_it;
}
-INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
+void tcp_v6_early_demux(struct sk_buff *skb)
{
const struct ipv6hdr *hdr;
const struct tcphdr *th;
@@ -1753,7 +1755,7 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk_fullsock(sk)) {
- struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+ struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie);
@@ -1846,12 +1848,6 @@ static int tcp_v6_init_sock(struct sock *sk)
return 0;
}
-static void tcp_v6_destroy_sock(struct sock *sk)
-{
- tcp_v4_destroy_sock(sk);
- inet6_destroy_sock(sk);
-}
-
#ifdef CONFIG_PROC_FS
/* Proc filesystem TCPv6 sock list dumping. */
static void get_openreq6(struct seq_file *seq,
@@ -2044,7 +2040,7 @@ struct proto tcpv6_prot = {
.accept = inet_csk_accept,
.ioctl = tcp_ioctl,
.init = tcp_v6_init_sock,
- .destroy = tcp_v6_destroy_sock,
+ .destroy = tcp_v4_destroy_sock,
.shutdown = tcp_shutdown,
.setsockopt = tcp_setsockopt,
.getsockopt = tcp_getsockopt,
@@ -2081,12 +2077,7 @@ struct proto tcpv6_prot = {
.diag_destroy = tcp_abort,
};
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol tcpv6_protocol = {
- .early_demux = tcp_v6_early_demux,
- .early_demux_handler = tcp_v6_early_demux,
+static const struct inet6_protocol tcpv6_protocol = {
.handler = tcp_v6_rcv,
.err_handler = tcp_v6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 040869f45682..93eb62221975 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -54,6 +54,19 @@
#include <trace/events/skb.h>
#include "udp_impl.h"
+static void udpv6_destruct_sock(struct sock *sk)
+{
+ udp_destruct_common(sk);
+ inet6_sock_destruct(sk);
+}
+
+int udpv6_init_sock(struct sock *sk)
+{
+ skb_queue_head_init(&udp_sk(sk)->reader_queue);
+ sk->sk_destruct = udpv6_destruct_sock;
+ return 0;
+}
+
static u32 udp6_ehashfn(const struct net *net,
const struct in6_addr *laddr,
const u16 lport,
@@ -74,7 +87,7 @@ static u32 udp6_ehashfn(const struct net *net,
fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
return __inet6_ehashfn(lhash, lport, fhash, fport,
- udp_ipv6_hash_secret + net_hash_mix(net));
+ udp6_ehash_secret + net_hash_mix(net));
}
int udp_v6_get_port(struct sock *sk, unsigned short snum)
@@ -889,7 +902,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
struct dst_entry *dst = skb_dst(skb);
int ret;
- if (unlikely(sk->sk_rx_dst != dst))
+ if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp6_sk_rx_dst_set(sk, dst);
if (!uh->check && !udp_sk(sk)->no_check6_rx) {
@@ -973,7 +986,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
return NULL;
}
-INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb)
+void udp_v6_early_demux(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
const struct udphdr *uh;
@@ -1001,7 +1014,7 @@ INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_efree;
- dst = READ_ONCE(sk->sk_rx_dst);
+ dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
@@ -1283,9 +1296,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
msg->msg_name = &sin;
msg->msg_namelen = sizeof(sin);
do_udp_sendmsg:
- if (__ipv6_only_sock(sk))
- return -ENETUNREACH;
- return udp_sendmsg(sk, msg, len);
+ err = __ipv6_only_sock(sk) ?
+ -ENETUNREACH : udp_sendmsg(sk, msg, len);
+ msg->msg_name = sin6;
+ msg->msg_namelen = addr_len;
+ return err;
}
}
@@ -1558,8 +1573,6 @@ void udpv6_destroy_sock(struct sock *sk)
udp_encap_disable();
}
}
-
- inet6_destroy_sock(sk);
}
/*
@@ -1603,12 +1616,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
}
#endif
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol udpv6_protocol = {
- .early_demux = udp_v6_early_demux,
- .early_demux_handler = udp_v6_early_demux,
+static const struct inet6_protocol udpv6_protocol = {
.handler = udpv6_rcv,
.err_handler = udpv6_err,
.flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
@@ -1668,7 +1676,7 @@ struct proto udpv6_prot = {
.connect = ip6_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
- .init = udp_init_sock,
+ .init = udpv6_init_sock,
.destroy = udpv6_destroy_sock,
.setsockopt = udpv6_setsockopt,
.getsockopt = udpv6_getsockopt,
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 20e324b6f358..16516bd69250 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -12,6 +12,7 @@ int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int);
int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
__be32, struct udp_table *);
+int udpv6_init_sock(struct sock *sk);
int udp_v6_get_port(struct sock *sk, unsigned short snum);
void udp_v6_rehash(struct sock *sk);
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index bf7a7acd39b1..6f6215f4d81d 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -12,6 +12,13 @@
#include <linux/proc_fs.h>
#include "udp_impl.h"
+static int udplitev6_sk_init(struct sock *sk)
+{
+ udpv6_init_sock(sk);
+ udp_sk(sk)->pcflag = UDPLITE_BIT;
+ return 0;
+}
+
static int udplitev6_rcv(struct sk_buff *skb)
{
return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
@@ -38,7 +45,7 @@ struct proto udplitev6_prot = {
.connect = ip6_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
- .init = udplite_sk_init,
+ .init = udplitev6_sk_init,
.destroy = udpv6_destroy_sock,
.setsockopt = udpv6_setsockopt,
.getsockopt = udpv6_getsockopt,
@@ -50,6 +57,8 @@ struct proto udplitev6_prot = {
.get_port = udp_v6_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
+ .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
+ .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp6_sock),
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index af7a4b8b1e9c..4c3aa97f23fa 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -120,11 +120,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- if (likely(xdst->u.rt6.rt6i_idev))
- in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
if (xdst->u.rt6.rt6i_uncached_list)
rt6_uncached_list_del(&xdst->u.rt6);
+ if (likely(xdst->u.rt6.rt6i_idev))
+ in6_dev_put(xdst->u.rt6.rt6i_idev);
xfrm_dst_destroy(xdst);
}
@@ -289,9 +289,13 @@ int __init xfrm6_init(void)
if (ret)
goto out_state;
- register_pernet_subsys(&xfrm6_net_ops);
+ ret = register_pernet_subsys(&xfrm6_net_ops);
+ if (ret)
+ goto out_protocol;
out:
return ret;
+out_protocol:
+ xfrm6_protocol_fini();
out_state:
xfrm6_state_fini();
out_policy:
generated by cgit v1.2.3 (git 2.0.4) at 2025-10-23 15:17:11 +0000