summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c8
-rw-r--r--net/ipv6/addrconf_core.c8
-rw-r--r--net/ipv6/af_inet6.c2
-rw-r--r--net/ipv6/ah6.c3
-rw-r--r--net/ipv6/calipso.c2
-rw-r--r--net/ipv6/icmp.c15
-rw-r--r--net/ipv6/inet6_hashtables.c6
-rw-r--r--net/ipv6/ip6_fib.c16
-rw-r--r--net/ipv6/ip6_gre.c33
-rw-r--r--net/ipv6/ip6_output.c4
-rw-r--r--net/ipv6/ip6_tunnel.c4
-rw-r--r--net/ipv6/ip6_vti.c8
-rw-r--r--net/ipv6/ndisc.c7
-rw-r--r--net/ipv6/netfilter.c6
-rw-r--r--net/ipv6/netfilter/ip6t_NPT.c39
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c10
-rw-r--r--net/ipv6/netfilter/nf_log_ipv6.c8
-rw-r--r--net/ipv6/reassembly.c17
-rw-r--r--net/ipv6/route.c6
-rw-r--r--net/ipv6/sit.c2
-rw-r--r--net/ipv6/syncookies.c10
-rw-r--r--net/ipv6/tcp_ipv6.c27
-rw-r--r--net/ipv6/udp_offload.c17
-rw-r--r--net/ipv6/xfrm6_tunnel.c4
25 files changed, 199 insertions, 65 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 01146b66d666..8b6eb384bac7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5022,8 +5022,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
return -EMSGSIZE;
if (args->netnsid >= 0 &&
- nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 ||
@@ -5054,8 +5056,10 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
return -EMSGSIZE;
if (args->netnsid >= 0 &&
- nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 ||
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 9ebf3fe0d2b1..c70c192bc91b 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -191,6 +191,13 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt,
return -EAFNOSUPPORT;
}
+static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
+{
+ kfree_skb(skb);
+ return -EAFNOSUPPORT;
+}
+
const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow,
.ipv6_route_input = eafnosupport_ipv6_route_input,
@@ -201,6 +208,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
.fib6_nh_init = eafnosupport_fib6_nh_init,
.ip6_del_rt = eafnosupport_ip6_del_rt,
+ .ipv6_fragment = eafnosupport_ipv6_fragment,
};
EXPORT_SYMBOL_GPL(ipv6_stub);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 0306509ab063..e648fbebb167 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -661,6 +661,7 @@ 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,
@@ -1026,6 +1027,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
.xfrm6_rcv_encap = xfrm6_rcv_encap,
#endif
.nd_tbl = &nd_tbl,
+ .ipv6_fragment = ip6_fragment,
};
static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index d88d97617f7e..440080da805b 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -588,7 +588,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
memset(ah->auth_data, 0, ahp->icv_trunc_len);
- if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN))
+ err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN);
+ if (err)
goto out_free;
ip6h->priority = 0;
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 8d3f66c310db..78f766019b7e 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -761,7 +761,7 @@ static int calipso_genopt(unsigned char *buf, u32 start, u32 buf_len,
calipso[1] = len - 2;
*(__be32 *)(calipso + 2) = htonl(doi_def->doi);
calipso[6] = (len - CALIPSO_HDR_LEN) / 4;
- calipso[7] = secattr->attr.mls.lvl,
+ calipso[7] = secattr->attr.mls.lvl;
crc = ~crc_ccitt(0xffff, calipso, len);
calipso[8] = crc & 0xff;
calipso[9] = (crc >> 8) & 0xff;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 83b251151b5c..8956144ea65e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -158,7 +158,13 @@ static bool is_ineligible(const struct sk_buff *skb)
tp = skb_header_pointer(skb,
ptr+offsetof(struct icmp6hdr, icmp6_type),
sizeof(_type), &_type);
- if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
+
+ /* Based on RFC 8200, Section 4.5 Fragment Header, return
+ * false if this is a fragment packet with no icmp header info.
+ */
+ if (!tp && frag_off != 0)
+ return false;
+ else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
return true;
}
return false;
@@ -501,8 +507,11 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (__ipv6_addr_needs_scope_id(addr_type)) {
iif = icmp6_iif(skb);
} else {
- dst = skb_dst(skb);
- iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev);
+ /*
+ * The source device is used for looking up which routing table
+ * to use for sending an ICMP error.
+ */
+ iif = l3mdev_master_ifindex(skb->dev);
}
/*
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 2d3add9e6116..55c290d55605 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum,
const struct in6_addr *daddr,
- const int dif, const int sdif, bool exact_dif)
+ const int dif, const int sdif)
{
int score = -1;
@@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
const __be16 sport, const struct in6_addr *daddr,
const unsigned short hnum, const int dif, const int sdif)
{
- bool exact_dif = inet6_exact_dif_match(net, skb);
struct inet_connection_sock *icsk;
struct sock *sk, *result = NULL;
int score, hiscore = 0;
inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
sk = (struct sock *)icsk;
- score = compute_score(sk, net, hnum, daddr, dif, sdif,
- exact_dif);
+ score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
result = lookup_reuseport(net, sk, skb, doff,
saddr, sport, daddr, hnum);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4a664ad4f4d4..605cdd38a919 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1812,10 +1812,14 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
children = 0;
child = NULL;
- if (fn_r)
- child = fn_r, children |= 1;
- if (fn_l)
- child = fn_l, children |= 2;
+ if (fn_r) {
+ child = fn_r;
+ children |= 1;
+ }
+ if (fn_l) {
+ child = fn_l;
+ children |= 2;
+ }
if (children == 3 || FIB6_SUBTREE(fn)
#ifdef CONFIG_IPV6_SUBTREES
@@ -2618,8 +2622,10 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
iter->skip = *pos;
if (iter->tbl) {
+ loff_t p = 0;
+
ipv6_route_seq_setup_walk(iter, net);
- return ipv6_route_seq_next(seq, NULL, pos);
+ return ipv6_route_seq_next(seq, NULL, &p);
} else {
return NULL;
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3a57fb9ce049..931b186d2e48 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -707,6 +707,17 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
return 0;
}
+static struct ip_tunnel_info *skb_tunnel_info_txcheck(struct sk_buff *skb)
+{
+ struct ip_tunnel_info *tun_info;
+
+ tun_info = skb_tunnel_info(skb);
+ if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX)))
+ return ERR_PTR(-EINVAL);
+
+ return tun_info;
+}
+
static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
struct net_device *dev, __u8 dsfield,
struct flowi6 *fl6, int encap_limit,
@@ -734,10 +745,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
const struct ip_tunnel_key *key;
__be16 flags;
- tun_info = skb_tunnel_info(skb);
- if (unlikely(!tun_info ||
- !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET6))
+ tun_info = skb_tunnel_info_txcheck(skb);
+ if (IS_ERR(tun_info) ||
+ unlikely(ip_tunnel_info_af(tun_info) != AF_INET6))
return -EINVAL;
key = &tun_info->key;
@@ -908,7 +918,8 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
tx_err:
- stats->tx_errors++;
+ if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb)))
+ stats->tx_errors++;
stats->tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
@@ -917,6 +928,7 @@ tx_err:
static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
+ struct ip_tunnel_info *tun_info = NULL;
struct ip6_tnl *t = netdev_priv(dev);
struct dst_entry *dst = skb_dst(skb);
struct net_device_stats *stats;
@@ -964,15 +976,13 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
* for native mode, call prepare_ip6gre_xmit_{ipv4,ipv6}.
*/
if (t->parms.collect_md) {
- struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
struct erspan_metadata *md;
__be32 tun_id;
- tun_info = skb_tunnel_info(skb);
- if (unlikely(!tun_info ||
- !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
- ip_tunnel_info_af(tun_info) != AF_INET6))
+ tun_info = skb_tunnel_info_txcheck(skb);
+ if (IS_ERR(tun_info) ||
+ unlikely(ip_tunnel_info_af(tun_info) != AF_INET6))
goto tx_err;
key = &tun_info->key;
@@ -1065,7 +1075,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
tx_err:
stats = &t->dev->stats;
- stats->tx_errors++;
+ if (!IS_ERR(tun_info))
+ stats->tx_errors++;
stats->tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2689498157d1..749ad72386b2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -468,8 +468,6 @@ int ip6_forward(struct sk_buff *skb)
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
- /* Force OUTPUT device used as source address */
- skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
@@ -1492,7 +1490,7 @@ emsgsize:
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
- * Note that we may need to "move" the data from the tail of
+ * Note that we may need to "move" the data from the tail
* of the buffer to the new fragment when we split
* the message.
*
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0217e5bf3bc..648db3fe508f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1271,6 +1271,8 @@ route_lookup:
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
+ skb_set_inner_ipproto(skb, proto);
+
err = ip6_tnl_encap(skb, t, &proto, fl6);
if (err)
return err;
@@ -1280,8 +1282,6 @@ route_lookup:
ipv6_push_frag_opts(skb, &opt.ops, &proto);
}
- skb_set_inner_ipproto(skb, proto);
-
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index fac01b80a104..5f9c4fdc120d 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -347,7 +347,6 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
struct net_device *dev;
- struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
const struct xfrm_mode *inner_mode;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
@@ -390,12 +389,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
skb->dev = dev;
-
- tstats = this_cpu_ptr(dev->tstats);
- u64_stats_update_begin(&tstats->syncp);
- tstats->rx_packets++;
- tstats->rx_bytes += skb->len;
- u64_stats_update_end(&tstats->syncp);
+ dev_sw_netstats_rx_add(dev, skb->len);
return 0;
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 27f29b957ee7..76717478f173 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);
+static int ndisc_is_multicast(const void *pkey);
static const struct neigh_ops ndisc_generic_ops = {
.family = AF_INET6,
@@ -115,6 +116,7 @@ struct neigh_table nd_tbl = {
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
+ .is_multicast = ndisc_is_multicast,
.allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
@@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb)
kfree_skb(skb);
}
+static int ndisc_is_multicast(const void *pkey)
+{
+ return ipv6_addr_is_multicast((struct in6_addr *)pkey);
+}
+
static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
{
struct inet6_dev *idev = __in6_dev_get(skb->dev);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0e942d082d..ab9a279dd6d4 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -20,10 +20,10 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include "../bridge/br_private.h"
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
- struct sock *sk = sk_to_full_sk(skb->sk);
+ struct sock *sk = sk_to_full_sk(sk_partial);
unsigned int hh_len;
struct dst_entry *dst;
int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
- return ip6_route_me_harder(entry->state.net, skb);
+ return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
}
return 0;
}
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 9ee077bf4f49..787c74aa85e3 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -77,16 +77,43 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt,
return true;
}
+static struct ipv6hdr *icmpv6_bounced_ipv6hdr(struct sk_buff *skb,
+ struct ipv6hdr *_bounced_hdr)
+{
+ if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6)
+ return NULL;
+
+ if (!icmpv6_is_err(icmp6_hdr(skb)->icmp6_type))
+ return NULL;
+
+ return skb_header_pointer(skb,
+ skb_transport_offset(skb) + sizeof(struct icmp6hdr),
+ sizeof(struct ipv6hdr),
+ _bounced_hdr);
+}
+
static unsigned int
ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_npt_tginfo *npt = par->targinfo;
+ struct ipv6hdr _bounced_hdr;
+ struct ipv6hdr *bounced_hdr;
+ struct in6_addr bounced_pfx;
if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) {
icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, saddr));
return NF_DROP;
}
+
+ /* rewrite dst addr of bounced packet which was sent to dst range */
+ bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr);
+ if (bounced_hdr) {
+ ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->daddr, npt->src_pfx_len);
+ if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0)
+ ip6t_npt_map_pfx(npt, &bounced_hdr->daddr);
+ }
+
return XT_CONTINUE;
}
@@ -94,12 +121,24 @@ static unsigned int
ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_npt_tginfo *npt = par->targinfo;
+ struct ipv6hdr _bounced_hdr;
+ struct ipv6hdr *bounced_hdr;
+ struct in6_addr bounced_pfx;
if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) {
icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
offsetof(struct ipv6hdr, daddr));
return NF_DROP;
}
+
+ /* rewrite src addr of bounced packet which was sent from dst range */
+ bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr);
+ if (bounced_hdr) {
+ ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->saddr, npt->src_pfx_len);
+ if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0)
+ ip6t_npt_map_pfx(npt, &bounced_hdr->saddr);
+ }
+
return XT_CONTINUE;
}
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 1a2748611e00..cee74803d7a1 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
- err = ip6_route_me_harder(state->net, skb);
+ err = ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index fed9666a2f7d..c129ad334eb3 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -355,6 +355,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
ipv6_hdr(skb)->payload_len = htons(payload_len);
ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
+ IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
/* Yes, and fold redundant checksum back. 8) */
if (skb->ip_summed == CHECKSUM_COMPLETE)
@@ -439,6 +440,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
u16 savethdr = skb->transport_header;
+ u8 nexthdr = NEXTHDR_FRAGMENT;
int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
struct frag_queue *fq;
@@ -454,6 +456,14 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
return 0;
+ /* Discard the first fragment if it does not include all headers
+ * RFC 8200, Section 4.5
+ */
+ if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) {
+ pr_debug("Drop incomplete fragment\n");
+ return 0;
+ }
+
if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
return -ENOMEM;
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index da64550a5707..8210ff34ed9b 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -297,9 +297,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m,
switch (dev->type) {
case ARPHRD_ETHER:
- nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
- eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
- ntohs(eth_hdr(skb)->h_proto));
+ nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+ eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+ nf_log_dump_vlan(m, skb);
+ nf_log_buf_add(m, "MACPROTO=%04x ",
+ ntohs(eth_hdr(skb)->h_proto));
return;
default:
break;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1f5d4d196dcc..47a0dc46cbdb 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -42,6 +42,8 @@
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
#include <net/sock.h>
#include <net/snmp.h>
@@ -322,6 +324,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ u8 nexthdr;
int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
@@ -351,6 +354,20 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
+ /* RFC 8200, Section 4.5 Fragment Header:
+ * If the first fragment does not include all headers through an
+ * Upper-Layer header, then that fragment should be discarded and
+ * an ICMP Parameter Problem, Code 3, message should be sent to
+ * the source of the fragment, with the Pointer field set to zero.
+ */
+ nexthdr = hdr->nexthdr;
+ if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) {
+ __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+ return -1;
+ }
+
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fb075d9545b9..7e0ce7af8234 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2745,7 +2745,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (confirm_neigh)
dst_confirm_neigh(dst, daddr);
- mtu = max_t(u32, mtu, IPV6_MIN_MTU);
+ if (mtu < IPV6_MIN_MTU)
+ return;
if (mtu >= dst_mtu(dst))
return;
@@ -5284,9 +5285,10 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
{
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
+ int last_err = 0;
int remaining;
int attrlen;
- int err = 1, last_err = 0;
+ int err;
remaining = cfg->fc_mp_len;
rtnh = (struct rtnexthop *)cfg->fc_mp;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e2c34c0ac97..5e7983cb6154 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1128,7 +1128,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
if (tdev && !netif_is_l3_master(tdev)) {
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
- dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
dev->mtu = tdev->mtu - t_hlen;
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
@@ -1426,7 +1425,6 @@ static void ipip6_tunnel_setup(struct net_device *dev)
dev->priv_destructor = ipip6_dev_free;
dev->type = ARPHRD_SIT;
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
dev->min_mtu = IPV6_MIN_MTU;
dev->max_mtu = IP6_MAX_MTU - t_hlen;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e796a64be308..9b6cae1e49d9 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -136,7 +136,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
- int mss;
+ int full_space, mss;
struct dst_entry *dst;
__u8 rcv_wscale;
u32 tsoff = 0;
@@ -241,7 +241,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
}
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
- tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ full_space = tcp_full_space(sk);
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
+
+ tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 305870a72352..8db59f4e5f13 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -458,7 +458,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
case TCP_SYN_SENT:
case TCP_SYN_RECV:
/* Only in fast or simultaneous open. If a fast open socket is
- * is already accepted it is treated as a connected one below.
+ * already accepted it is treated as a connected one below.
*/
if (fastopen && !fastopen->sk)
break;
@@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type)
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = tcp_inet6_sk(sk);
@@ -509,13 +510,14 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi6 *fl6 = &fl->u.ip6;
struct sk_buff *skb;
int err = -ENOMEM;
+ u8 tclass;
/* First, grab a route. */
if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
IPPROTO_TCP)) == NULL)
goto done;
- skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+ skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
@@ -527,9 +529,12 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
rcu_read_lock();
opt = ireq->ipv6_opt;
+ tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tcp_rsk(req)->syn_tos : np->tclass;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass,
+ err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
+ tclass & ~INET_ECN_MASK,
sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
@@ -958,8 +963,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
- ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass,
- priority);
+ ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
+ tclass & ~INET_ECN_MASK, priority);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -1067,8 +1072,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
label = ip6_flowlabel(ipv6h);
}
- tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0,
- label, priority);
+ tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1,
+ ipv6_get_dsfield(ipv6h), label, priority);
#ifdef CONFIG_TCP_MD5SIG
out:
@@ -1121,7 +1126,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
- 0, 0, sk->sk_priority);
+ ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority);
}
@@ -1309,6 +1314,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
if (np->repflow)
newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
+ /* Set ToS of the new socket based upon the value of incoming SYN. */
+ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
+
/* Clone native IPv6 options from listening socket (if any)
Yes, keeping reference count would be much more clever,
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 584157a07759..f9e888d1b9af 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -111,12 +111,22 @@ out:
return segs;
}
+static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+ return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+ &iph->daddr, dport, inet6_iif(skb),
+ inet6_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
@@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 1;
rcu_read_lock();
- sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udpv6_encap_needed_key))
+ sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 25b7ebda2fab..f696d46e6910 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -303,13 +303,13 @@ static const struct xfrm_type xfrm6_tunnel_type = {
static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
static int __net_init xfrm6_tunnel_net_init(struct net *net)