summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c60
-rw-r--r--net/ipv6/addrconf_core.c8
-rw-r--r--net/ipv6/af_inet6.c2
-rw-r--r--net/ipv6/inet6_hashtables.c6
-rw-r--r--net/ipv6/ip6_fib.c12
-rw-r--r--net/ipv6/ip6_tunnel.c10
-rw-r--r--net/ipv6/netfilter.c3
-rw-r--r--net/ipv6/netfilter/ip6t_NPT.c39
-rw-r--r--net/ipv6/sysctl_net_ipv6.c3
-rw-r--r--net/ipv6/tcp_ipv6.c25
10 files changed, 110 insertions, 58 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8e761b8c47c6..01146b66d666 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1893,12 +1893,13 @@ EXPORT_SYMBOL(ipv6_chk_addr);
* 2. does the address exist on the specific device
* (skip_dev_check = false)
*/
-int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
- const struct net_device *dev, bool skip_dev_check,
- int strict, u32 banned_flags)
+static struct net_device *
+__ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+ const struct net_device *dev, bool skip_dev_check,
+ int strict, u32 banned_flags)
{
unsigned int hash = inet6_addr_hash(net, addr);
- const struct net_device *l3mdev;
+ struct net_device *l3mdev, *ndev;
struct inet6_ifaddr *ifp;
u32 ifp_flags;
@@ -1909,10 +1910,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
dev = NULL;
hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
- if (!net_eq(dev_net(ifp->idev->dev), net))
+ ndev = ifp->idev->dev;
+ if (!net_eq(dev_net(ndev), net))
continue;
- if (l3mdev_master_dev_rcu(ifp->idev->dev) != l3mdev)
+ if (l3mdev_master_dev_rcu(ndev) != l3mdev)
continue;
/* Decouple optimistic from tentative for evaluation here.
@@ -1923,15 +1925,23 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
: ifp->flags;
if (ipv6_addr_equal(&ifp->addr, addr) &&
!(ifp_flags&banned_flags) &&
- (!dev || ifp->idev->dev == dev ||
+ (!dev || ndev == dev ||
!(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
rcu_read_unlock();
- return 1;
+ return ndev;
}
}
rcu_read_unlock();
- return 0;
+ return NULL;
+}
+
+int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+ const struct net_device *dev, bool skip_dev_check,
+ int strict, u32 banned_flags)
+{
+ return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check,
+ strict, banned_flags) ? 1 : 0;
}
EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
@@ -1990,35 +2000,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
*
* The caller should be protected by RCU, or RTNL.
*/
-struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr)
+struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr,
+ struct net_device *dev)
{
- unsigned int hash = inet6_addr_hash(net, addr);
- struct inet6_ifaddr *ifp, *result = NULL;
- struct net_device *dev = NULL;
-
- rcu_read_lock();
- hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
- if (net_eq(dev_net(ifp->idev->dev), net) &&
- ipv6_addr_equal(&ifp->addr, addr)) {
- result = ifp;
- break;
- }
- }
-
- if (!result) {
- struct rt6_info *rt;
-
- rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
- if (rt) {
- dev = rt->dst.dev;
- ip6_rt_put(rt);
- }
- } else {
- dev = result->idev->dev;
- }
- rcu_read_unlock();
-
- return dev;
+ return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1,
+ IFA_F_TENTATIVE);
}
EXPORT_SYMBOL(ipv6_dev_find);
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/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 25a90f3f705c..44d68ed70f24 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
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f635914f42ec..a0217e5bf3bc 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -915,7 +915,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
struct metadata_dst *tun_dst,
bool log_ecn_err)
{
- return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate,
+ int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
+ const struct ipv6hdr *ipv6h,
+ struct sk_buff *skb);
+
+ dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate;
+ if (tpi->proto == htons(ETH_P_IP))
+ dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate;
+
+ return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
log_ecn_err);
}
EXPORT_SYMBOL(ip6_tnl_rcv);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 409e79b84a83..6d0e942d082d 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = {
.route_input = ip6_route_input,
.fragment = ip6_fragment,
.reroute = nf_ip6_reroute,
-#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
- .br_defrag = nf_ct_frag6_gather,
-#endif
#if IS_MODULE(CONFIG_IPV6)
.br_fragment = br_ip6_fragment,
#endif
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/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index fac2135aa47b..5b60a4bdd36a 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -21,6 +21,7 @@
#include <net/calipso.h>
#endif
+static int two = 2;
static int flowlabel_reflect_max = 0x7;
static int auto_flowlabels_min;
static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
@@ -150,7 +151,7 @@ static struct ctl_table ipv6_table_template[] = {
.mode = 0644,
.proc_handler = proc_rt6_multipath_hash_policy,
.extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE,
+ .extra2 = &two,
},
{
.procname = "seg6_flowlabel",
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 305870a72352..862058dce6d0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -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,
generated by cgit (git 2.34.1) at 2025-06-09 04:26:47 +0000