summaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/datagram.c21
-rw-r--r--net/ipv6/ip6_checksum.c5
-rw-r--r--net/ipv6/ip6_gre.c8
-rw-r--r--net/ipv6/ip6_output.c15
-rw-r--r--net/ipv6/ip6_tunnel.c12
-rw-r--r--net/ipv6/ip6_vti.c36
-rw-r--r--net/ipv6/ipv6_sockglue.c10
-rw-r--r--net/ipv6/ndisc.c3
-rw-r--r--net/ipv6/netfilter.c9
-rw-r--r--net/ipv6/netfilter/ip6_tables.c4
-rw-r--r--net/ipv6/netfilter/ip6t_REJECT.c4
-rw-r--r--net/ipv6/netfilter/ip6t_rpfilter.c10
-rw-r--r--net/ipv6/netfilter/ip6t_srh.c6
-rw-r--r--net/ipv6/netfilter/nf_flow_table_ipv6.c2
-rw-r--r--net/ipv6/netfilter/nf_nat_l3proto_ipv6.c4
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c6
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c12
-rw-r--r--net/ipv6/route.c92
-rw-r--r--net/ipv6/seg6_iptunnel.c23
-rw-r--r--net/ipv6/sit.c9
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/ipv6/xfrm6_mode_tunnel.c3
-rw-r--r--net/ipv6/xfrm6_output.c2
-rw-r--r--net/ipv6/xfrm6_policy.c5
24 files changed, 184 insertions, 119 deletions
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index fbf08ce3f5ab..a9f7eca0b6a3 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
- struct in6_addr *daddr;
+ struct in6_addr *daddr, old_daddr;
+ __be32 fl6_flowlabel = 0;
+ __be32 old_fl6_flowlabel;
+ __be16 old_dport;
int addr_type;
int err;
- __be32 fl6_flowlabel = 0;
if (usin->sin6_family == AF_INET) {
if (__ipv6_only_sock(sk))
@@ -238,9 +240,13 @@ ipv4_connected:
}
}
+ /* save the current peer information before updating it */
+ old_daddr = sk->sk_v6_daddr;
+ old_fl6_flowlabel = np->flow_label;
+ old_dport = inet->inet_dport;
+
sk->sk_v6_daddr = *daddr;
np->flow_label = fl6_flowlabel;
-
inet->inet_dport = usin->sin6_port;
/*
@@ -250,11 +256,12 @@ ipv4_connected:
err = ip6_datagram_dst_update(sk, true);
if (err) {
- /* Reset daddr and dport so that udp_v6_early_demux()
- * fails to find this socket
+ /* Restore the socket peer info, to keep it consistent with
+ * the old socket state
*/
- memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
- inet->inet_dport = 0;
+ sk->sk_v6_daddr = old_daddr;
+ np->flow_label = old_fl6_flowlabel;
+ inet->inet_dport = old_dport;
goto out;
}
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index ec43d18b5ff9..547515e8450a 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -73,6 +73,11 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
err = udplite_checksum_init(skb, uh);
if (err)
return err;
+
+ if (UDP_SKB_CB(skb)->partial_cov) {
+ skb->csum = ip6_compute_pseudo(skb, proto);
+ return 0;
+ }
}
/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3c353125546d..1bbd0930063e 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -126,7 +126,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
struct ip6_tnl *t, *cand = NULL;
struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
int dev_type = (gre_proto == htons(ETH_P_TEB) ||
- gre_proto == htons(ETH_P_ERSPAN)) ?
+ gre_proto == htons(ETH_P_ERSPAN) ||
+ gre_proto == htons(ETH_P_ERSPAN2)) ?
ARPHRD_ETHER : ARPHRD_IP6GRE;
int score, cand_score = 4;
@@ -902,6 +903,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
truncate = true;
}
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto tx_err;
+
t->parms.o_flags &= ~TUNNEL_KEY;
IPCB(skb)->flags = 0;
@@ -944,6 +948,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
md->u.md2.dir,
get_hwid(&md->u.md2),
truncate, false);
+ } else {
+ goto tx_err;
}
} else {
switch (skb->protocol) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 997c7f19ad62..5cb18c8ba9b2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
if (skb->ignore_df)
return false;
- if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+ if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
return false;
return true;
@@ -1246,7 +1246,7 @@ static int __ip6_append_data(struct sock *sk,
const struct sockcm_cookie *sockc)
{
struct sk_buff *skb, *skb_prev = NULL;
- unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
+ unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
int exthdrlen = 0;
int dst_exthdrlen = 0;
int hh_len;
@@ -1282,6 +1282,12 @@ static int __ip6_append_data(struct sock *sk,
sizeof(struct frag_hdr) : 0) +
rt->rt6i_nfheader_len;
+ /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit
+ * the first fragment
+ */
+ if (headersize + transhdrlen > mtu)
+ goto emsgsize;
+
if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
(sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_RAW)) {
@@ -1297,9 +1303,8 @@ static int __ip6_append_data(struct sock *sk,
if (cork->length + length > maxnonfragsize - headersize) {
emsgsize:
- ipv6_local_error(sk, EMSGSIZE, fl6,
- mtu - headersize +
- sizeof(struct ipv6hdr));
+ pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0);
+ ipv6_local_error(sk, EMSGSIZE, fl6, pmtu);
return -EMSGSIZE;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4b15fe928278..6e0f21eed88a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1982,14 +1982,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
{
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- struct ip6_tnl *nt, *t;
struct ip_tunnel_encap ipencap;
+ struct ip6_tnl *nt, *t;
+ int err;
nt = netdev_priv(dev);
if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
- int err = ip6_tnl_encap_setup(nt, &ipencap);
-
+ err = ip6_tnl_encap_setup(nt, &ipencap);
if (err < 0)
return err;
}
@@ -2005,7 +2005,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
return -EEXIST;
}
- return ip6_tnl_create2(dev);
+ err = ip6_tnl_create2(dev);
+ if (!err && tb[IFLA_MTU])
+ ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
+
+ return err;
}
static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index fa3ae1cb50d3..ce18cd20389d 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -622,11 +622,12 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
}
-static void vti6_link_config(struct ip6_tnl *t)
+static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu)
{
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
struct net_device *tdev = NULL;
+ int mtu;
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -640,6 +641,11 @@ static void vti6_link_config(struct ip6_tnl *t)
else
dev->flags &= ~IFF_POINTOPOINT;
+ if (keep_mtu && dev->mtu) {
+ dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu);
+ return;
+ }
+
if (p->flags & IP6_TNL_F_CAP_XMIT) {
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
@@ -656,20 +662,25 @@ static void vti6_link_config(struct ip6_tnl *t)
tdev = __dev_get_by_index(t->net, p->link);
if (tdev)
- dev->mtu = max_t(int, tdev->mtu - dev->hard_header_len,
- IPV6_MIN_MTU);
+ mtu = tdev->mtu - sizeof(struct ipv6hdr);
+ else
+ mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr);
+
+ dev->mtu = max_t(int, mtu, IPV6_MIN_MTU);
}
/**
* vti6_tnl_change - update the tunnel parameters
* @t: tunnel to be changed
* @p: tunnel configuration parameters
+ * @keep_mtu: MTU was set from userspace, don't re-compute it
*
* Description:
* vti6_tnl_change() updates the tunnel parameters
**/
static int
-vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
+vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p,
+ bool keep_mtu)
{
t->parms.laddr = p->laddr;
t->parms.raddr = p->raddr;
@@ -679,11 +690,12 @@ vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
t->parms.proto = p->proto;
t->parms.fwmark = p->fwmark;
dst_cache_reset(&t->dst_cache);
- vti6_link_config(t);
+ vti6_link_config(t, keep_mtu);
return 0;
}
-static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
+static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p,
+ bool keep_mtu)
{
struct net *net = dev_net(t->dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
@@ -691,7 +703,7 @@ static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
vti6_tnl_unlink(ip6n, t);
synchronize_net();
- err = vti6_tnl_change(t, p);
+ err = vti6_tnl_change(t, p, keep_mtu);
vti6_tnl_link(ip6n, t);
netdev_state_change(t->dev);
return err;
@@ -804,7 +816,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
} else
t = netdev_priv(dev);
- err = vti6_update(t, &p1);
+ err = vti6_update(t, &p1, false);
}
if (t) {
err = 0;
@@ -866,10 +878,8 @@ static void vti6_dev_setup(struct net_device *dev)
dev->priv_destructor = vti6_dev_free;
dev->type = ARPHRD_TUNNEL6;
- dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
- dev->mtu = ETH_DATA_LEN;
dev->min_mtu = IPV6_MIN_MTU;
- dev->max_mtu = IP_MAX_MTU;
+ dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr);
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
netif_keep_dst(dev);
@@ -905,7 +915,7 @@ static int vti6_dev_init(struct net_device *dev)
if (err)
return err;
- vti6_link_config(t);
+ vti6_link_config(t, true);
return 0;
}
@@ -1010,7 +1020,7 @@ static int vti6_changelink(struct net_device *dev, struct nlattr *tb[],
} else
t = netdev_priv(dev);
- return vti6_update(t, &p);
+ return vti6_update(t, &p, tb && tb[IFLA_MTU]);
}
static size_t vti6_get_size(const struct net_device *dev)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d78d41fc4b1a..24535169663d 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1367,10 +1367,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
if (get_user(len, optlen))
return -EFAULT;
- lock_sock(sk);
- err = nf_getsockopt(sk, PF_INET6, optname, optval,
- &len);
- release_sock(sk);
+ err = nf_getsockopt(sk, PF_INET6, optname, optval, &len);
if (err >= 0)
err = put_user(len, optlen);
}
@@ -1409,10 +1406,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
if (get_user(len, optlen))
return -EFAULT;
- lock_sock(sk);
- err = compat_nf_getsockopt(sk, PF_INET6,
- optname, optval, &len);
- release_sock(sk);
+ err = compat_nf_getsockopt(sk, PF_INET6, optname, optval, &len);
if (err >= 0)
err = put_user(len, optlen);
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f61a5b613b52..ba5e04c6ae17 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1554,7 +1554,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
*(opt++) = (rd_len >> 3);
opt += 6;
- memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8);
+ skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt,
+ rd_len - 8);
}
void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d95ceca7ff8f..531d6957af36 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -21,18 +21,19 @@
int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct sock *sk = sk_to_full_sk(skb->sk);
unsigned int hh_len;
struct dst_entry *dst;
struct flowi6 fl6 = {
- .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
+ .flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
- .flowi6_uid = sock_net_uid(net, skb->sk),
+ .flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
};
int err;
- dst = ip6_route_output(net, skb->sk, &fl6);
+ dst = ip6_route_output(net, sk, &fl6);
err = dst->error;
if (err) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
@@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
skb_dst_set(skb, NULL);
- dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
+ dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_set(skb, dst);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index af4c917e0836..62358b93bbac 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -352,6 +352,10 @@ ip6t_do_table(struct sk_buff *skb,
}
if (table_base + v != ip6t_next_entry(e) &&
!(e->ipv6.flags & IP6T_F_GOTO)) {
+ if (unlikely(stackidx >= private->stacksize)) {
+ verdict = NF_DROP;
+ break;
+ }
jumpstack[stackidx++] = e;
}
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index fa51a205918d..38dea8ff680f 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -85,14 +85,14 @@ static int reject_tg6_check(const struct xt_tgchk_param *par)
const struct ip6t_entry *e = par->entryinfo;
if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) {
- pr_info("ECHOREPLY is not supported.\n");
+ pr_info_ratelimited("ECHOREPLY is not supported\n");
return -EINVAL;
} else if (rejinfo->with == IP6T_TCP_RESET) {
/* Must specify that it's a TCP packet */
if (!(e->ipv6.flags & IP6T_F_PROTO) ||
e->ipv6.proto != IPPROTO_TCP ||
(e->ipv6.invflags & XT_INV_PROTO)) {
- pr_info("TCP_RESET illegal for non-tcp\n");
+ pr_info_ratelimited("TCP_RESET illegal for non-tcp\n");
return -EINVAL;
}
}
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index b12e61b7b16c..91ed25a24b79 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
}
fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
- if ((flags & XT_RPFILTER_LOOSE) == 0) {
- fl6.flowi6_oif = dev->ifindex;
- lookup_flags |= RT6_LOOKUP_F_IFACE;
- }
rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags);
if (rt->dst.error)
@@ -103,14 +99,14 @@ static int rpfilter_check(const struct xt_mtchk_param *par)
unsigned int options = ~XT_RPFILTER_OPTION_MASK;
if (info->flags & options) {
- pr_info("unknown options encountered");
+ pr_info_ratelimited("unknown options\n");
return -EINVAL;
}
if (strcmp(par->table, "mangle") != 0 &&
strcmp(par->table, "raw") != 0) {
- pr_info("match only valid in the \'raw\' "
- "or \'mangle\' tables, not \'%s\'.\n", par->table);
+ pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n",
+ par->table);
return -EINVAL;
}
diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c
index 9642164107ce..33719d5560c8 100644
--- a/net/ipv6/netfilter/ip6t_srh.c
+++ b/net/ipv6/netfilter/ip6t_srh.c
@@ -122,12 +122,14 @@ static int srh_mt6_check(const struct xt_mtchk_param *par)
const struct ip6t_srh *srhinfo = par->matchinfo;
if (srhinfo->mt_flags & ~IP6T_SRH_MASK) {
- pr_err("unknown srh match flags %X\n", srhinfo->mt_flags);
+ pr_info_ratelimited("unknown srh match flags %X\n",
+ srhinfo->mt_flags);
return -EINVAL;
}
if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) {
- pr_err("unknown srh invflags %X\n", srhinfo->mt_invflags);
+ pr_info_ratelimited("unknown srh invflags %X\n",
+ srhinfo->mt_invflags);
return -EINVAL;
}
diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c
index d346705d6ee6..207cb35569b1 100644
--- a/net/ipv6/netfilter/nf_flow_table_ipv6.c
+++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c
@@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
if (skb->len <= mtu)
return false;
- if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
+ if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
return false;
return true;
diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
index bed57ee65f7b..6b7f075f811f 100644
--- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c
@@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
target, maniptype))
return false;
+
+ /* must reload, offset might have changed */
+ ipv6h = (void *)skb->data + iphdroff;
+
manip_addr:
if (maniptype == NF_NAT_MANIP_SRC)
ipv6h->saddr = target->src.u3.in6;
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index ebb2bf84232a..f14de4b6d639 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -116,9 +116,11 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
}
if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
- struct udphdr _hdr, *hp;
+ struct tcphdr _hdr;
+ struct udphdr *hp;
- hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+ hp = skb_header_pointer(skb, thoff, tproto == IPPROTO_UDP ?
+ sizeof(*hp) : sizeof(_hdr), &_hdr);
if (hp == NULL)
return NULL;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index cc5174c7254c..62fc84d7bdff 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
}
*dest = 0;
- again:
rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags);
if (rt->dst.error)
goto put_rt_err;
@@ -189,15 +188,8 @@ 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) {
- /* multipath route? Try again with F_IFACE */
- if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) {
- lookup_flags |= RT6_LOOKUP_F_IFACE;
- fl6.flowi6_oif = oif->ifindex;
- ip6_rt_put(rt);
- goto again;
- }
- }
+ if (oif && oif != rt->rt6i_idev->dev)
+ goto put_rt_err;
switch (priv->result) {
case NFT_FIB_RESULT_OIF:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9dcfadddd800..fc74352fac12 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -128,7 +128,7 @@ struct uncached_list {
static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
-static void rt6_uncached_list_add(struct rt6_info *rt)
+void rt6_uncached_list_add(struct rt6_info *rt)
{
struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
@@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt)
spin_unlock_bh(&ul->lock);
}
-static void rt6_uncached_list_del(struct rt6_info *rt)
+void rt6_uncached_list_del(struct rt6_info *rt)
{
if (!list_empty(&rt->rt6i_uncached)) {
struct uncached_list *ul = rt->rt6i_uncached_list;
@@ -919,6 +919,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct rt6_info *rt, *rt_cache;
struct fib6_node *fn;
+ if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+ flags &= ~RT6_LOOKUP_F_IFACE;
+
rcu_read_lock();
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
@@ -1509,7 +1512,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
}
}
-static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
+static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
+ struct rt6_info *rt, int mtu)
+{
+ /* If the new MTU is lower than the route PMTU, this new MTU will be the
+ * lowest MTU in the path: always allow updating the route PMTU to
+ * reflect PMTU decreases.
+ *
+ * If the new MTU is higher, and the route PMTU is equal to the local
+ * MTU, this means the old MTU is the lowest in the path, so allow
+ * updating it: if other nodes now have lower MTUs, PMTU discovery will
+ * handle this.
+ */
+
+ if (dst_mtu(&rt->dst) >= mtu)
+ return true;
+
+ if (dst_mtu(&rt->dst) == idev->cnf.mtu6)
+ return true;
+
+ return false;
+}
+
+static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
+ struct rt6_info *rt, int mtu)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1518,20 +1544,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
lockdep_is_held(&rt6_exception_lock));
- if (bucket) {
- for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
- hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
- struct rt6_info *entry = rt6_ex->rt6i;
- /* For RTF_CACHE with rt6i_pmtu == 0
- * (i.e. a redirected route),
- * the metrics of its rt->dst.from has already
- * been updated.
- */
- if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu)
- entry->rt6i_pmtu = mtu;
- }
- bucket++;
+ if (!bucket)
+ return;
+
+ for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+ hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+ struct rt6_info *entry = rt6_ex->rt6i;
+
+ /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected
+ * route), the metrics of its rt->dst.from have already
+ * been updated.
+ */
+ if (entry->rt6i_pmtu &&
+ rt6_mtu_change_route_allowed(idev, entry, mtu))
+ entry->rt6i_pmtu = mtu;
}
+ bucket++;
}
}
@@ -1601,11 +1629,10 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
struct neighbour *neigh;
__u8 neigh_flags = 0;
- neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway);
- if (neigh) {
+ neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ if (neigh)
neigh_flags = neigh->flags;
- neigh_release(neigh);
- }
+
if (!(neigh_flags & NTF_ROUTER)) {
RT6_TRACE("purging route %p via non-router but gateway\n",
rt);
@@ -1629,7 +1656,8 @@ void rt6_age_exceptions(struct rt6_info *rt,
if (!rcu_access_pointer(rt->rt6i_exception_bucket))
return;
- spin_lock_bh(&rt6_exception_lock);
+ rcu_read_lock_bh();
+ spin_lock(&rt6_exception_lock);
bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
lockdep_is_held(&rt6_exception_lock));
@@ -1643,7 +1671,8 @@ void rt6_age_exceptions(struct rt6_info *rt,
bucket++;
}
}
- spin_unlock_bh(&rt6_exception_lock);
+ spin_unlock(&rt6_exception_lock);
+ rcu_read_unlock_bh();
}
struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
@@ -3809,25 +3838,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
Since RFC 1981 doesn't include administrative MTU increase
update PMTU increase is a MUST. (i.e. jumbo frame)
*/
- /*
- If new MTU is less than route PMTU, this new MTU will be the
- lowest MTU in the path, update the route PMTU to reflect PMTU
- decreases; if new MTU is greater than route PMTU, and the
- old MTU is the lowest MTU in the path, update the route PMTU
- to reflect the increase. In this case if the other nodes' MTU
- also have the lowest MTU, TOO BIG MESSAGE will be lead to
- PMTU discovery.
- */
if (rt->dst.dev == arg->dev &&
- dst_metric_raw(&rt->dst, RTAX_MTU) &&
!dst_metric_locked(&rt->dst, RTAX_MTU)) {
spin_lock_bh(&rt6_exception_lock);
- if (dst_mtu(&rt->dst) >= arg->mtu ||
- (dst_mtu(&rt->dst) < arg->mtu &&
- dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+ if (dst_metric_raw(&rt->dst, RTAX_MTU) &&
+ rt6_mtu_change_route_allowed(idev, rt, arg->mtu))
dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
- }
- rt6_exceptions_update_pmtu(rt, arg->mtu);
+ rt6_exceptions_update_pmtu(idev, rt, arg->mtu);
spin_unlock_bh(&rt6_exception_lock);
}
return 0;
@@ -4099,6 +4116,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
r_cfg.fc_encap_type = nla_get_u16(nla);
}
+ r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK);
rt = ip6_route_info_create(&r_cfg, extack);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index bd6cc688bd19..f343e6f0fc95 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -16,6 +16,7 @@
#include <linux/net.h>
#include <linux/module.h>
#include <net/ip.h>
+#include <net/ip_tunnels.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
@@ -93,7 +94,8 @@ static void set_tun_src(struct net *net, struct net_device *dev,
/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
{
- struct net *net = dev_net(skb_dst(skb)->dev);
+ struct dst_entry *dst = skb_dst(skb);
+ struct net *net = dev_net(dst->dev);
struct ipv6hdr *hdr, *inner_hdr;
struct ipv6_sr_hdr *isrh;
int hdrlen, tot_len, err;
@@ -134,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
isrh->nexthdr = proto;
hdr->daddr = isrh->segments[isrh->first_segment];
- set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr);
+ set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr);
#ifdef CONFIG_IPV6_SEG6_HMAC
if (sr_has_hmac(isrh)) {
@@ -210,11 +212,6 @@ static int seg6_do_srh(struct sk_buff *skb)
tinfo = seg6_encap_lwtunnel(dst->lwtstate);
- if (likely(!skb->encapsulation)) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
-
switch (tinfo->mode) {
case SEG6_IPTUN_MODE_INLINE:
if (skb->protocol != htons(ETH_P_IPV6))
@@ -223,10 +220,12 @@ static int seg6_do_srh(struct sk_buff *skb)
err = seg6_do_srh_inline(skb, tinfo->srh);
if (err)
return err;
-
- skb_reset_inner_headers(skb);
break;
case SEG6_IPTUN_MODE_ENCAP:
+ err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
+ if (err)
+ return err;
+
if (skb->protocol == htons(ETH_P_IPV6))
proto = IPPROTO_IPV6;
else if (skb->protocol == htons(ETH_P_IP))
@@ -238,6 +237,8 @@ static int seg6_do_srh(struct sk_buff *skb)
if (err)
return err;
+ skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+ skb_set_inner_protocol(skb, skb->protocol);
skb->protocol = htons(ETH_P_IPV6);
break;
case SEG6_IPTUN_MODE_L2ENCAP:
@@ -261,8 +262,6 @@ static int seg6_do_srh(struct sk_buff *skb)
ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
- skb_set_inner_protocol(skb, skb->protocol);
-
return 0;
}
@@ -418,7 +417,7 @@ static int seg6_build_state(struct nlattr *nla,
slwt = seg6_lwt_lwtunnel(newts);
- err = dst_cache_init(&slwt->cache, GFP_KERNEL);
+ err = dst_cache_init(&slwt->cache, GFP_ATOMIC);
if (err) {
kfree(newts);
return err;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3873d3877135..0195598f7bb5 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -182,7 +182,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel *t = netdev_priv(dev);
- if (t->dev == sitn->fb_tunnel_dev) {
+ if (dev == sitn->fb_tunnel_dev) {
ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
t->ip6rd.relay_prefix = 0;
t->ip6rd.prefixlen = 16;
@@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
if (err < 0)
return err;
+ if (tb[IFLA_MTU]) {
+ u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+
+ if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len)
+ dev->mtu = mtu;
+ }
+
#ifdef CONFIG_IPV6_SIT_6RD
if (ipip6_netlink_6rd_parms(data, &ip6rd))
err = ipip6_tunnel_update_6rd(nt, &ip6rd);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e7a3a6b6cf56..e997141aed8c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -217,6 +217,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
treq->snt_isn = cookie;
treq->ts_off = 0;
treq->txhash = net_tx_rndhash();
+ if (IS_ENABLED(CONFIG_SMC))
+ ireq->smc_ok = 0;
/*
* We need to lookup the dst_entry to get the correct window size.
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index bb935a3b7fea..de1b0b8c53b0 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -92,7 +92,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
- eth_hdr(skb)->h_proto = skb->protocol;
+ if (skb->mac_len)
+ eth_hdr(skb)->h_proto = skb->protocol;
err = 0;
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 8ae87d4ec5ff..5959ce9620eb 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
if ((!skb_is_gso(skb) && skb->len > mtu) ||
(skb_is_gso(skb) &&
- skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) {
+ !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) {
skb->dev = dst->dev;
skb->protocol = htons(ETH_P_IPV6);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 09fb44ee3b45..416fe67271a9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
+ INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached);
+ rt6_uncached_list_add(&xdst->u.rt6);
+ atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache);
return 0;
}
@@ -244,6 +247,8 @@ static void xfrm6_dst_destroy(struct dst_entry *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);
xfrm_dst_destroy(xdst);
}
OpenPOWER on IntegriCloud