aboutsummaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c112
-rw-r--r--net/ipv6/addrlabel.c28
-rw-r--r--net/ipv6/af_inet6.c22
-rw-r--r--net/ipv6/anycast.c5
-rw-r--r--net/ipv6/esp6_offload.c6
-rw-r--r--net/ipv6/fib6_notifier.c2
-rw-r--r--net/ipv6/fib6_rules.c2
-rw-r--r--net/ipv6/ila/ila_xlat.c15
-rw-r--r--net/ipv6/ioam6.c14
-rw-r--r--net/ipv6/ioam6_iptunnel.c6
-rw-r--r--net/ipv6/ip6_fib.c41
-rw-r--r--net/ipv6/ip6_output.c24
-rw-r--r--net/ipv6/ip6_tunnel.c4
-rw-r--r--net/ipv6/ip6mr.c79
-rw-r--r--net/ipv6/netfilter/Kconfig9
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c15
-rw-r--r--net/ipv6/raw.c2
-rw-r--r--net/ipv6/route.c74
-rw-r--r--net/ipv6/seg6_local.c14
-rw-r--r--net/ipv6/tcp_ipv6.c21
-rw-r--r--net/ipv6/udp.c121
-rw-r--r--net/ipv6/xfrm6_policy.c31
22 files changed, 396 insertions, 251 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 94dceac52884..c489a1e6aec9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1016,7 +1016,7 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp)
static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr)
{
- u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+ u32 val = __ipv6_addr_jhash(addr, net_hash_mix(net));
return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
}
@@ -2570,6 +2570,24 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
return idev;
}
+static void delete_tempaddrs(struct inet6_dev *idev,
+ struct inet6_ifaddr *ifp)
+{
+ struct inet6_ifaddr *ift, *tmp;
+
+ write_lock_bh(&idev->lock);
+ list_for_each_entry_safe(ift, tmp, &idev->tempaddr_list, tmp_list) {
+ if (ift->ifpub != ifp)
+ continue;
+
+ in6_ifa_hold(ift);
+ write_unlock_bh(&idev->lock);
+ ipv6_del_addr(ift);
+ write_lock_bh(&idev->lock);
+ }
+ write_unlock_bh(&idev->lock);
+}
+
static void manage_tempaddrs(struct inet6_dev *idev,
struct inet6_ifaddr *ifp,
__u32 valid_lft, __u32 prefered_lft,
@@ -3124,11 +3142,12 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
in6_ifa_hold(ifp);
read_unlock_bh(&idev->lock);
- if (!(ifp->flags & IFA_F_TEMPORARY) &&
- (ifa_flags & IFA_F_MANAGETEMPADDR))
- manage_tempaddrs(idev, ifp, 0, 0, false,
- jiffies);
ipv6_del_addr(ifp);
+
+ if (!(ifp->flags & IFA_F_TEMPORARY) &&
+ (ifp->flags & IFA_F_MANAGETEMPADDR))
+ delete_tempaddrs(idev, ifp);
+
addrconf_verify_rtnl(net);
if (ipv6_addr_is_multicast(pfx)) {
ipv6_mc_config(net->ipv6.mc_autojoin_sk,
@@ -4793,7 +4812,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!pfx)
return -EINVAL;
- ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
+ ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags);
/* We ignore other flags so far. */
ifa_flags &= IFA_F_MANAGETEMPADDR;
@@ -4952,14 +4971,12 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp,
}
if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) {
- if (was_managetempaddr &&
- !(ifp->flags & IFA_F_MANAGETEMPADDR)) {
- cfg->valid_lft = 0;
- cfg->preferred_lft = 0;
- }
- manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft,
- cfg->preferred_lft, !was_managetempaddr,
- jiffies);
+ if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR))
+ delete_tempaddrs(ifp->idev, ifp);
+ else
+ manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft,
+ cfg->preferred_lft, !was_managetempaddr,
+ jiffies);
}
addrconf_verify_rtnl(net);
@@ -5018,10 +5035,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
return -ENODEV;
}
- if (tb[IFA_FLAGS])
- cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]);
- else
- cfg.ifa_flags = ifm->ifa_flags;
+ cfg.ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags);
/* We ignore other flags so far. */
cfg.ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS |
@@ -7406,6 +7420,27 @@ static struct rtnl_af_ops inet6_ops __read_mostly = {
.set_link_af = inet6_set_link_af,
};
+static const struct rtnl_msg_handler addrconf_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETLINK,
+ .dumpit = inet6_dump_ifinfo, .flags = RTNL_FLAG_DUMP_UNLOCKED},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWADDR,
+ .doit = inet6_rtm_newaddr},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELADDR,
+ .doit = inet6_rtm_deladdr},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETADDR,
+ .doit = inet6_rtm_getaddr, .dumpit = inet6_dump_ifaddr,
+ .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETMULTICAST,
+ .dumpit = inet6_dump_ifmcaddr,
+ .flags = RTNL_FLAG_DUMP_UNLOCKED},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETANYCAST,
+ .dumpit = inet6_dump_ifacaddr,
+ .flags = RTNL_FLAG_DUMP_UNLOCKED},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETNETCONF,
+ .doit = inet6_netconf_get_devconf, .dumpit = inet6_netconf_dump_devconf,
+ .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED},
+};
+
/*
* Init / cleanup code
*/
@@ -7447,44 +7482,14 @@ int __init addrconf_init(void)
addrconf_verify(&init_net);
- rtnl_af_register(&inet6_ops);
+ err = rtnl_af_register(&inet6_ops);
+ if (err)
+ goto erraf;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETLINK,
- NULL, inet6_dump_ifinfo, RTNL_FLAG_DUMP_UNLOCKED);
- if (err < 0)
+ err = rtnl_register_many(addrconf_rtnl_msg_handlers);
+ if (err)
goto errout;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDR,
- inet6_rtm_newaddr, NULL, 0);
- if (err < 0)
- goto errout;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDR,
- inet6_rtm_deladdr, NULL, 0);
- if (err < 0)
- goto errout;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR,
- inet6_rtm_getaddr, inet6_dump_ifaddr,
- RTNL_FLAG_DOIT_UNLOCKED |
- RTNL_FLAG_DUMP_UNLOCKED);
- if (err < 0)
- goto errout;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST,
- NULL, inet6_dump_ifmcaddr,
- RTNL_FLAG_DUMP_UNLOCKED);
- if (err < 0)
- goto errout;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST,
- NULL, inet6_dump_ifacaddr,
- RTNL_FLAG_DUMP_UNLOCKED);
- if (err < 0)
- goto errout;
- err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF,
- inet6_netconf_get_devconf,
- inet6_netconf_dump_devconf,
- RTNL_FLAG_DOIT_UNLOCKED |
- RTNL_FLAG_DUMP_UNLOCKED);
- if (err < 0)
- goto errout;
err = ipv6_addr_label_rtnl_register();
if (err < 0)
goto errout;
@@ -7493,6 +7498,7 @@ int __init addrconf_init(void)
errout:
rtnl_unregister_all(PF_INET6);
rtnl_af_unregister(&inet6_ops);
+erraf:
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
destroy_workqueue(addrconf_wq);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index acd70b5992a7..ab054f329e12 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -634,23 +634,17 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
return err;
}
+static const struct rtnl_msg_handler ipv6_adddr_label_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWADDRLABEL,
+ .doit = ip6addrlbl_newdel, .flags = RTNL_FLAG_DOIT_UNLOCKED},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELADDRLABEL,
+ .doit = ip6addrlbl_newdel, .flags = RTNL_FLAG_DOIT_UNLOCKED},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETADDRLABEL,
+ .doit = ip6addrlbl_get, .dumpit = ip6addrlbl_dump,
+ .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED},
+};
+
int __init ipv6_addr_label_rtnl_register(void)
{
- int ret;
-
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDRLABEL,
- ip6addrlbl_newdel,
- NULL, RTNL_FLAG_DOIT_UNLOCKED);
- if (ret < 0)
- return ret;
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDRLABEL,
- ip6addrlbl_newdel,
- NULL, RTNL_FLAG_DOIT_UNLOCKED);
- if (ret < 0)
- return ret;
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDRLABEL,
- ip6addrlbl_get,
- ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED |
- RTNL_FLAG_DUMP_UNLOCKED);
- return ret;
+ return rtnl_register_many(ipv6_adddr_label_rtnl_msg_handlers);
}
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index ba69b86f1c7d..f60ec8b0f8ea 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -252,31 +252,29 @@ lookup_protocol:
*/
inet->inet_sport = htons(inet->inet_num);
err = sk->sk_prot->hash(sk);
- if (err) {
- sk_common_release(sk);
- goto out;
- }
+ if (err)
+ goto out_sk_release;
}
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
- if (err) {
- sk_common_release(sk);
- goto out;
- }
+ if (err)
+ goto out_sk_release;
}
if (!kern) {
err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk);
- if (err) {
- sk_common_release(sk);
- goto out;
- }
+ if (err)
+ goto out_sk_release;
}
out:
return err;
out_rcu_unlock:
rcu_read_unlock();
goto out;
+out_sk_release:
+ sk_common_release(sk);
+ sock->sk = NULL;
+ goto out;
}
static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 0627c4c18d1a..562cace50ca9 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -49,9 +49,10 @@ static DEFINE_SPINLOCK(acaddr_hash_lock);
static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);
-static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr)
+static u32 inet6_acaddr_hash(const struct net *net,
+ const struct in6_addr *addr)
{
- u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+ u32 val = __ipv6_addr_jhash(addr, net_hash_mix(net));
return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
}
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 919ebfabbe4e..7b41fb4f00b5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -80,9 +80,9 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
if (sp->len == XFRM_MAX_DEPTH)
goto out_reset;
- x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
- (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
- spi, IPPROTO_ESP, AF_INET6);
+ x = xfrm_input_state_lookup(dev_net(skb->dev), skb->mark,
+ (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
+ spi, IPPROTO_ESP, AF_INET6);
if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) {
/* non-offload path will record the error and audit log */
diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c
index f87ae33e1d01..949b72610df7 100644
--- a/net/ipv6/fib6_notifier.c
+++ b/net/ipv6/fib6_notifier.c
@@ -22,7 +22,7 @@ int call_fib6_notifiers(struct net *net, enum fib_event_type event_type,
return call_fib_notifiers(net, event_type, info);
}
-static unsigned int fib6_seq_read(struct net *net)
+static unsigned int fib6_seq_read(const struct net *net)
{
return fib6_tables_seq_read(net) + fib6_rules_seq_read(net);
}
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 04a9ed5e8310..c85c1627cb16 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -56,7 +56,7 @@ int fib6_rules_dump(struct net *net, struct notifier_block *nb,
return fib_rules_dump(net, nb, AF_INET6, extack);
}
-unsigned int fib6_rules_seq_read(struct net *net)
+unsigned int fib6_rules_seq_read(const struct net *net)
{
return fib_rules_seq_read(net, AF_INET6);
}
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 534a4498e280..7646e401c630 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -105,16 +105,11 @@ static int parse_nl_config(struct genl_info *info,
xp->ip.locator_match.v64 = (__force __be64)nla_get_u64(
info->attrs[ILA_ATTR_LOCATOR_MATCH]);
- if (info->attrs[ILA_ATTR_CSUM_MODE])
- xp->ip.csum_mode = nla_get_u8(info->attrs[ILA_ATTR_CSUM_MODE]);
- else
- xp->ip.csum_mode = ILA_CSUM_NO_ACTION;
-
- if (info->attrs[ILA_ATTR_IDENT_TYPE])
- xp->ip.ident_type = nla_get_u8(
- info->attrs[ILA_ATTR_IDENT_TYPE]);
- else
- xp->ip.ident_type = ILA_ATYPE_USE_FORMAT;
+ xp->ip.csum_mode = nla_get_u8_default(info->attrs[ILA_ATTR_CSUM_MODE],
+ ILA_CSUM_NO_ACTION);
+
+ xp->ip.ident_type = nla_get_u8_default(info->attrs[ILA_ATTR_IDENT_TYPE],
+ ILA_ATYPE_USE_FORMAT);
if (info->attrs[ILA_ATTR_IFINDEX])
xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]);
diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c
index 08c929513065..a84d332f952f 100644
--- a/net/ipv6/ioam6.c
+++ b/net/ipv6/ioam6.c
@@ -135,15 +135,11 @@ static int ioam6_genl_addns(struct sk_buff *skb, struct genl_info *info)
ns->id = id;
- if (!info->attrs[IOAM6_ATTR_NS_DATA])
- data32 = IOAM6_U32_UNAVAILABLE;
- else
- data32 = nla_get_u32(info->attrs[IOAM6_ATTR_NS_DATA]);
-
- if (!info->attrs[IOAM6_ATTR_NS_DATA_WIDE])
- data64 = IOAM6_U64_UNAVAILABLE;
- else
- data64 = nla_get_u64(info->attrs[IOAM6_ATTR_NS_DATA_WIDE]);
+ data32 = nla_get_u32_default(info->attrs[IOAM6_ATTR_NS_DATA],
+ IOAM6_U32_UNAVAILABLE);
+
+ data64 = nla_get_u64_default(info->attrs[IOAM6_ATTR_NS_DATA_WIDE],
+ IOAM6_U64_UNAVAILABLE);
ns->data = cpu_to_be32(data32);
ns->data_wide = cpu_to_be64(data64);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index beb6b4cfc551..9d8422e350f8 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -142,10 +142,8 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
}
}
- if (!tb[IOAM6_IPTUNNEL_MODE])
- mode = IOAM6_IPTUNNEL_MODE_INLINE;
- else
- mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]);
+ mode = nla_get_u8_default(tb[IOAM6_IPTUNNEL_MODE],
+ IOAM6_IPTUNNEL_MODE_INLINE);
if (tb[IOAM6_IPTUNNEL_SRC] && mode == IOAM6_IPTUNNEL_MODE_INLINE) {
NL_SET_ERR_MSG(extack, "no tunnel src expected with this mode");
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index eb111d20615c..c134ba202c4c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -198,16 +198,9 @@ static void node_free_immediate(struct net *net, struct fib6_node *fn)
net->ipv6.rt6_stats->fib_nodes--;
}
-static void node_free_rcu(struct rcu_head *head)
-{
- struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
-
- kmem_cache_free(fib6_node_kmem, fn);
-}
-
static void node_free(struct net *net, struct fib6_node *fn)
{
- call_rcu(&fn->rcu, node_free_rcu);
+ kfree_rcu(fn, rcu);
net->ipv6.rt6_stats->fib_nodes--;
}
@@ -345,17 +338,17 @@ static void __net_init fib6_tables_init(struct net *net)
#endif
-unsigned int fib6_tables_seq_read(struct net *net)
+unsigned int fib6_tables_seq_read(const struct net *net)
{
unsigned int h, fib_seq = 0;
rcu_read_lock();
for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
- struct hlist_head *head = &net->ipv6.fib_table_hash[h];
- struct fib6_table *tb;
+ const struct hlist_head *head = &net->ipv6.fib_table_hash[h];
+ const struct fib6_table *tb;
hlist_for_each_entry_rcu(tb, head, tb6_hlist)
- fib_seq += tb->fib_seq;
+ fib_seq += READ_ONCE(tb->fib_seq);
}
rcu_read_unlock();
@@ -400,7 +393,7 @@ int call_fib6_entry_notifiers(struct net *net,
.rt = rt,
};
- rt->fib6_table->fib_seq++;
+ WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1);
return call_fib6_notifiers(net, event_type, &info.info);
}
@@ -416,7 +409,7 @@ int call_fib6_multipath_entry_notifiers(struct net *net,
.nsiblings = nsiblings,
};
- rt->fib6_table->fib_seq++;
+ WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1);
return call_fib6_notifiers(net, event_type, &info.info);
}
@@ -427,7 +420,7 @@ int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt)
.nsiblings = rt->fib6_nsiblings,
};
- rt->fib6_table->fib_seq++;
+ WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1);
return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info);
}
@@ -1190,8 +1183,8 @@ next_iter:
while (sibling) {
if (sibling->fib6_metric == rt->fib6_metric &&
rt6_qualify_for_ecmp(sibling)) {
- list_add_tail(&rt->fib6_siblings,
- &sibling->fib6_siblings);
+ list_add_tail_rcu(&rt->fib6_siblings,
+ &sibling->fib6_siblings);
break;
}
sibling = rcu_dereference_protected(sibling->fib6_next,
@@ -1252,7 +1245,7 @@ add:
fib6_siblings)
sibling->fib6_nsiblings--;
rt->fib6_nsiblings = 0;
- list_del_init(&rt->fib6_siblings);
+ list_del_rcu(&rt->fib6_siblings);
rt6_multipath_rebalance(next_sibling);
return err;
}
@@ -1970,7 +1963,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
&rt->fib6_siblings, fib6_siblings)
sibling->fib6_nsiblings--;
rt->fib6_nsiblings = 0;
- list_del_init(&rt->fib6_siblings);
+ list_del_rcu(&rt->fib6_siblings);
rt6_multipath_rebalance(next_sibling);
}
@@ -2500,6 +2493,12 @@ static struct pernet_operations fib6_net_ops = {
.exit = fib6_net_exit,
};
+static const struct rtnl_msg_handler fib6_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
+ .dumpit = inet6_dump_fib,
+ .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE},
+};
+
int __init fib6_init(void)
{
int ret = -ENOMEM;
@@ -2513,9 +2512,7 @@ int __init fib6_init(void)
if (ret)
goto out_kmem_cache_create;
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL,
- inet6_dump_fib, RTNL_FLAG_DUMP_UNLOCKED |
- RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
+ ret = rtnl_register_many(fib6_rtnl_msg_handlers);
if (ret)
goto out_unregister_subsys;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f26841f1490f..f7b4608bb316 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -127,7 +127,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
nexthop = rt6_nexthop(dst_rt6_info(dst), daddr);
neigh = __ipv6_neigh_lookup_noref(dev, nexthop);
- if (unlikely(IS_ERR_OR_NULL(neigh))) {
+ if (IS_ERR_OR_NULL(neigh)) {
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dev, false);
if (IS_ERR(neigh)) {
@@ -1401,8 +1401,11 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
cork->base.gso_size = ipc6->gso_size;
cork->base.tx_flags = 0;
cork->base.mark = ipc6->sockc.mark;
- sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
-
+ sock_tx_timestamp(sk, &ipc6->sockc, &cork->base.tx_flags);
+ if (ipc6->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) {
+ cork->base.flags |= IPCORK_TS_OPT_ID;
+ cork->base.ts_opt_id = ipc6->sockc.ts_opt_id;
+ }
cork->base.length = 0;
cork->base.transmit_time = ipc6->sockc.transmit_time;
@@ -1433,7 +1436,7 @@ static int __ip6_append_data(struct sock *sk,
bool zc = false;
u32 tskey = 0;
struct rt6_info *rt = dst_rt6_info(cork->dst);
- bool paged, hold_tskey, extra_uref = false;
+ bool paged, hold_tskey = false, extra_uref = false;
struct ipv6_txoptions *opt = v6_cork->opt;
int csummode = CHECKSUM_NONE;
unsigned int maxnonfragsize, headersize;
@@ -1543,10 +1546,15 @@ emsgsize:
flags &= ~MSG_SPLICE_PAGES;
}
- hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP &&
- READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID;
- if (hold_tskey)
- tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+ if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
+ if (cork->flags & IPCORK_TS_OPT_ID) {
+ tskey = cork->ts_opt_id;
+ } else {
+ tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+ hold_tskey = true;
+ }
+ }
/*
* Let's try using as much space as possible.
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b60e13c42bca..48fd53b98972 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -630,8 +630,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
skb_dst_set(skb2, &rt->dst);
} else {
- if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
- skb2->dev) ||
+ if (ip_route_input(skb2, eiph->daddr, eiph->saddr,
+ ip4h_dscp(eiph), skb2->dev) ||
skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
goto out;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 2ce4ae0d8dc3..7f1902ac3586 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -108,6 +108,11 @@ static void ipmr_expire_process(struct timer_list *t);
lockdep_rtnl_is_held() || \
list_empty(&net->ipv6.mr6_tables))
+static bool ip6mr_can_free_table(struct net *net)
+{
+ return !check_net(net) || !net->ipv6.mr6_rules_ops;
+}
+
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -125,7 +130,7 @@ static struct mr_table *ip6mr_mr_table_iter(struct net *net,
return ret;
}
-static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
+static struct mr_table *__ip6mr_get_table(struct net *net, u32 id)
{
struct mr_table *mrt;
@@ -136,6 +141,16 @@ static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
return NULL;
}
+static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
+{
+ struct mr_table *mrt;
+
+ rcu_read_lock();
+ mrt = __ip6mr_get_table(net, id);
+ rcu_read_unlock();
+ return mrt;
+}
+
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr_table **mrt)
{
@@ -177,7 +192,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
arg->table = fib_rule_get_table(rule, arg);
- mrt = ip6mr_get_table(rule->fr_net, arg->table);
+ mrt = __ip6mr_get_table(rule->fr_net, arg->table);
if (!mrt)
return -EAGAIN;
res->mrt = mrt;
@@ -276,7 +291,7 @@ static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack);
}
-static unsigned int ip6mr_rules_seq_read(struct net *net)
+static unsigned int ip6mr_rules_seq_read(const struct net *net)
{
return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR);
}
@@ -291,6 +306,11 @@ EXPORT_SYMBOL(ip6mr_rule_default);
#define ip6mr_for_each_table(mrt, net) \
for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
+static bool ip6mr_can_free_table(struct net *net)
+{
+ return !check_net(net);
+}
+
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -304,6 +324,8 @@ static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
return net->ipv6.mrt6;
}
+#define __ip6mr_get_table ip6mr_get_table
+
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr_table **mrt)
{
@@ -335,7 +357,7 @@ static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
return 0;
}
-static unsigned int ip6mr_rules_seq_read(struct net *net)
+static unsigned int ip6mr_rules_seq_read(const struct net *net)
{
return 0;
}
@@ -382,7 +404,7 @@ static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
{
struct mr_table *mrt;
- mrt = ip6mr_get_table(net, id);
+ mrt = __ip6mr_get_table(net, id);
if (mrt)
return mrt;
@@ -392,6 +414,10 @@ static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
static void ip6mr_free_table(struct mr_table *mrt)
{
+ struct net *net = read_pnet(&mrt->net);
+
+ WARN_ON_ONCE(!ip6mr_can_free_table(net));
+
timer_shutdown_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC);
@@ -411,13 +437,15 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
struct net *net = seq_file_net(seq);
struct mr_table *mrt;
- mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
- if (!mrt)
+ rcu_read_lock();
+ mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (!mrt) {
+ rcu_read_unlock();
return ERR_PTR(-ENOENT);
+ }
iter->mrt = mrt;
- rcu_read_lock();
return mr_vif_seq_start(seq, pos);
}
@@ -1260,11 +1288,9 @@ static int ip6mr_device_event(struct notifier_block *this,
return NOTIFY_DONE;
}
-static unsigned int ip6mr_seq_read(struct net *net)
+static unsigned int ip6mr_seq_read(const struct net *net)
{
- ASSERT_RTNL();
-
- return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net);
+ return READ_ONCE(net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net);
}
static int ip6mr_dump(struct net *net, struct notifier_block *nb,
@@ -1369,6 +1395,12 @@ static struct pernet_operations ip6mr_net_ops = {
.exit_batch = ip6mr_net_exit_batch,
};
+static const struct rtnl_msg_handler ip6mr_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = RTNL_FAMILY_IP6MR,
+ .msgtype = RTM_GETROUTE,
+ .doit = ip6mr_rtm_getroute, .dumpit = ip6mr_rtm_dumproute},
+};
+
int __init ip6_mr_init(void)
{
int err;
@@ -1391,9 +1423,8 @@ int __init ip6_mr_init(void)
goto add_proto_fail;
}
#endif
- err = rtnl_register_module(THIS_MODULE, RTNL_FAMILY_IP6MR, RTM_GETROUTE,
- ip6mr_rtm_getroute, ip6mr_rtm_dumproute, 0);
- if (err == 0)
+ err = rtnl_register_many(ip6mr_rtnl_msg_handlers);
+ if (!err)
return 0;
#ifdef CONFIG_IPV6_PIMSM_V2
@@ -1408,9 +1439,9 @@ reg_pernet_fail:
return err;
}
-void ip6_mr_cleanup(void)
+void __init ip6_mr_cleanup(void)
{
- rtnl_unregister(RTNL_FAMILY_IP6MR, RTM_GETROUTE);
+ rtnl_unregister_many(ip6mr_rtnl_msg_handlers);
#ifdef CONFIG_IPV6_PIMSM_V2
inet6_del_protocol(&pim6_protocol, IPPROTO_PIM);
#endif
@@ -2275,11 +2306,13 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
struct mfc6_cache *cache;
struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
- mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
- if (!mrt)
+ rcu_read_lock();
+ mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (!mrt) {
+ rcu_read_unlock();
return -ENOENT;
+ }
- rcu_read_lock();
cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr);
if (!cache && skb->dev) {
int vif = ip6mr_find_vif(mrt, skb->dev);
@@ -2557,9 +2590,9 @@ static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
src = nla_get_in6_addr(tb[RTA_SRC]);
if (tb[RTA_DST])
grp = nla_get_in6_addr(tb[RTA_DST]);
- tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0;
+ tableid = nla_get_u32_default(tb[RTA_TABLE], 0);
- mrt = ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT);
+ mrt = __ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT);
if (!mrt) {
NL_SET_ERR_MSG_MOD(extack, "MR table does not exist");
return -ENOENT;
@@ -2606,7 +2639,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
if (filter.table_id) {
struct mr_table *mrt;
- mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
+ mrt = __ip6mr_get_table(sock_net(skb->sk), filter.table_id);
if (!mrt) {
if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
return skb->len;
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index f3c8e2d918e1..e087a8e97ba7 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -8,7 +8,14 @@ menu "IPv6: Netfilter Configuration"
# old sockopt interface and eval loop
config IP6_NF_IPTABLES_LEGACY
- tristate
+ tristate "Legacy IP6 tables support"
+ depends on INET && IPV6
+ select NETFILTER_XTABLES
+ default n
+ help
+ ip6tables is a legacy packet classifier.
+ This is not needed if you are using iptables over nftables
+ (iptables-nft).
config NF_SOCKET_IPV6
tristate "IPv6 socket lookup support"
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 7db0437140bf..9ae2b2725bf9 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -268,12 +268,12 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
int hook)
{
- struct sk_buff *nskb;
- struct tcphdr _otcph;
- const struct tcphdr *otcph;
- unsigned int otcplen, hh_len;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct dst_entry *dst = NULL;
+ const struct tcphdr *otcph;
+ struct sk_buff *nskb;
+ struct tcphdr _otcph;
+ unsigned int otcplen;
struct flowi6 fl6;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
@@ -312,9 +312,8 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
if (IS_ERR(dst))
return;
- hh_len = (dst->dev->hard_header_len + 15)&~15;
- nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
- + sizeof(struct tcphdr) + dst->trailer_len,
+ nskb = alloc_skb(LL_MAX_HEADER + sizeof(struct ipv6hdr) +
+ sizeof(struct tcphdr) + dst->trailer_len,
GFP_ATOMIC);
if (!nskb) {
@@ -327,7 +326,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
nskb->mark = fl6.flowi6_mark;
- skb_reserve(nskb, hh_len + dst->header_len);
+ skb_reserve(nskb, LL_MAX_HEADER);
nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst));
nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 608fa9d05b55..8476a3944a88 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -629,7 +629,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
skb->ip_summed = CHECKSUM_NONE;
- skb_setup_tx_timestamp(skb, sockc->tsflags);
+ skb_setup_tx_timestamp(skb, sockc);
if (flags & MSG_CONFIRM)
skb_set_dst_pending_confirm(skb, 1);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b4251915585f..63d7681c929f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -374,6 +374,7 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
{
struct rt6_info *rt = dst_rt6_info(dst);
struct inet6_dev *idev = rt->rt6i_idev;
+ struct fib6_info *from;
if (idev && idev->dev != blackhole_netdev) {
struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev);
@@ -383,6 +384,8 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
in6_dev_put(idev);
}
}
+ from = unrcu_pointer(xchg(&rt->from, NULL));
+ fib6_info_release(from);
}
static bool __rt6_check_expired(const struct rt6_info *rt)
@@ -413,8 +416,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
struct flowi6 *fl6, int oif, bool have_oif_match,
const struct sk_buff *skb, int strict)
{
- struct fib6_info *sibling, *next_sibling;
struct fib6_info *match = res->f6i;
+ struct fib6_info *sibling;
if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
goto out;
@@ -440,8 +443,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
goto out;
- list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
- fib6_siblings) {
+ list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+ fib6_siblings) {
const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
@@ -1455,7 +1458,6 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
struct rt6_exception *rt6_ex)
{
- struct fib6_info *from;
struct net *net;
if (!bucket || !rt6_ex)
@@ -1467,8 +1469,6 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
/* purge completely the exception to allow releasing the held resources:
* some [sk] cache may keep the dst around for unlimited time
*/
- from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL));
- fib6_info_release(from);
dst_dev_put(&rt6_ex->rt6i->dst);
hlist_del_rcu(&rt6_ex->hlist);
@@ -5195,14 +5195,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
* nexthop. Since sibling routes are always added at the end of
* the list, find the first sibling of the last route appended
*/
+ rcu_read_lock();
+
if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
- rt = list_first_entry(&rt_last->fib6_siblings,
- struct fib6_info,
- fib6_siblings);
+ rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
+ struct fib6_info,
+ fib6_siblings);
}
if (rt)
inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
+
+ rcu_read_unlock();
}
static bool ip6_route_mpath_should_notify(const struct fib6_info *rt)
@@ -5547,17 +5551,21 @@ 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;
+ struct fib6_info *sibling;
nexthop_len = 0;
if (f6i->fib6_nsiblings) {
rt6_nh_nlmsg_size(nh, &nexthop_len);
- list_for_each_entry_safe(sibling, next_sibling,
- &f6i->fib6_siblings, fib6_siblings) {
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+ fib6_siblings) {
rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
}
+
+ rcu_read_unlock();
}
nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
}
@@ -5721,7 +5729,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
goto nla_put_failure;
} else if (rt->fib6_nsiblings) {
- struct fib6_info *sibling, *next_sibling;
+ struct fib6_info *sibling;
struct nlattr *mp;
mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
@@ -5733,14 +5741,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
0) < 0)
goto nla_put_failure;
- list_for_each_entry_safe(sibling, next_sibling,
- &rt->fib6_siblings, fib6_siblings) {
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(sibling, &rt->fib6_siblings,
+ fib6_siblings) {
if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
sibling->fib6_nh->fib_nh_weight,
- AF_INET6, 0) < 0)
+ AF_INET6, 0) < 0) {
+ rcu_read_unlock();
+
goto nla_put_failure;
+ }
}
+ rcu_read_unlock();
+
nla_nest_end(skb, mp);
} else if (rt->nh) {
if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
@@ -6177,7 +6192,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
err = -ENOBUFS;
seq = info->nlh ? info->nlh->nlmsg_seq : 0;
- skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+ skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
if (!skb)
goto errout;
@@ -6190,7 +6205,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
goto errout;
}
rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
- info->nlh, gfp_any());
+ info->nlh, GFP_ATOMIC);
return;
errout:
rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
@@ -6680,6 +6695,15 @@ static void bpf_iter_unregister(void)
#endif
#endif
+static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE,
+ .doit = inet6_rtm_newroute},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE,
+ .doit = inet6_rtm_delroute},
+ {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
+ .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
+};
+
int __init ip6_route_init(void)
{
int ret;
@@ -6722,19 +6746,7 @@ int __init ip6_route_init(void)
if (ret)
goto fib6_rules_init;
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWROUTE,
- inet6_rtm_newroute, NULL, 0);
- if (ret < 0)
- goto out_register_late_subsys;
-
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELROUTE,
- inet6_rtm_delroute, NULL, 0);
- if (ret < 0)
- goto out_register_late_subsys;
-
- ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE,
- inet6_rtm_getroute, NULL,
- RTNL_FLAG_DOIT_UNLOCKED);
+ ret = rtnl_register_many(ip6_route_rtnl_msg_handlers);
if (ret < 0)
goto out_register_late_subsys;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index c74705ead984..ac1dbd492c22 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -954,10 +954,10 @@ static int input_action_end_dx4_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
+ enum skb_drop_reason reason;
struct seg6_local_lwt *slwt;
struct iphdr *iph;
__be32 nhaddr;
- int err;
slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
@@ -967,9 +967,9 @@ static int input_action_end_dx4_finish(struct net *net, struct sock *sk,
skb_dst_drop(skb);
- err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
- if (err) {
- kfree_skb(skb);
+ reason = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
+ if (reason) {
+ kfree_skb_reason(skb, reason);
return -EINVAL;
}
@@ -1174,8 +1174,8 @@ drop:
static int input_action_end_dt4(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
+ enum skb_drop_reason reason;
struct iphdr *iph;
- int err;
if (!decap_and_validate(skb, IPPROTO_IPIP))
goto drop;
@@ -1193,8 +1193,8 @@ static int input_action_end_dt4(struct sk_buff *skb,
iph = ip_hdr(skb);
- err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev);
- if (unlikely(err))
+ reason = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev);
+ if (unlikely(reason))
goto drop;
return dst_input(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d71ab4e1efe1..2debdf085a3b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -967,6 +967,9 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
}
if (sk) {
+ /* unconstify the socket only to attach it to buff with care. */
+ skb_set_owner_edemux(buff, (struct sock *)sk);
+
if (sk->sk_state == TCP_TIME_WAIT)
mark = inet_twsk(sk)->tw_mark;
else
@@ -1169,8 +1172,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
goto out;
if (aoh)
- key.ao_key = tcp_ao_established_key(ao_info,
- aoh->rnext_keyid, -1);
+ key.ao_key = tcp_ao_established_key(sk, ao_info,
+ aoh->rnext_keyid, -1);
}
}
if (key.ao_key) {
@@ -1618,7 +1621,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
by tcp. Feel free to propose better solution.
--ANK (980728)
*/
- if (np->rxopt.all)
+ if (np->rxopt.all && sk->sk_state != TCP_LISTEN)
opt_skb = skb_clone_and_charge_r(skb, sk);
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
@@ -1656,8 +1659,6 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (reason)
goto reset;
}
- if (opt_skb)
- __kfree_skb(opt_skb);
return 0;
}
} else
@@ -2177,6 +2178,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
const struct tcp_sock *tp = tcp_sk(sp);
const struct inet_connection_sock *icsk = inet_csk(sp);
const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
+ u8 icsk_pending;
int rx_queue;
int state;
@@ -2185,12 +2187,13 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
destp = ntohs(inet->inet_dport);
srcp = ntohs(inet->inet_sport);
- if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
- icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
- icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+ icsk_pending = smp_load_acquire(&icsk->icsk_pending);
+ if (icsk_pending == ICSK_TIME_RETRANS ||
+ icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+ icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
timer_expires = icsk->icsk_timeout;
- } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+ } else if (icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
timer_expires = icsk->icsk_timeout;
} else if (timer_pending(&sp->sk_timer)) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 52dfbb2ff1a8..d766fd798ecf 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -110,8 +110,19 @@ void udp_v6_rehash(struct sock *sk)
u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
+ u16 new_hash4;
- udp_lib_rehash(sk, new_hash);
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) {
+ new_hash4 = udp_ehashfn(sock_net(sk),
+ sk->sk_rcv_saddr, sk->sk_num,
+ sk->sk_daddr, sk->sk_dport);
+ } else {
+ new_hash4 = udp6_ehashfn(sock_net(sk),
+ &sk->sk_v6_rcv_saddr, sk->sk_num,
+ &sk->sk_v6_daddr, sk->sk_dport);
+ }
+
+ udp_lib_rehash(sk, new_hash, new_hash4);
}
static int compute_score(struct sock *sk, const struct net *net,
@@ -216,6 +227,74 @@ rescore:
return result;
}
+#if IS_ENABLED(CONFIG_BASE_SMALL)
+static struct sock *udp6_lib_lookup4(const struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned int hnum, int dif, int sdif,
+ struct udp_table *udptable)
+{
+ return NULL;
+}
+
+static void udp6_hash4(struct sock *sk)
+{
+}
+#else /* !CONFIG_BASE_SMALL */
+static struct sock *udp6_lib_lookup4(const struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr,
+ unsigned int hnum, int dif, int sdif,
+ struct udp_table *udptable)
+{
+ const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
+ const struct hlist_nulls_node *node;
+ struct udp_hslot *hslot4;
+ unsigned int hash4, slot;
+ struct udp_sock *up;
+ struct sock *sk;
+
+ hash4 = udp6_ehashfn(net, daddr, hnum, saddr, sport);
+ slot = hash4 & udptable->mask;
+ hslot4 = &udptable->hash4[slot];
+
+begin:
+ udp_lrpa_for_each_entry_rcu(up, node, &hslot4->nulls_head) {
+ sk = (struct sock *)up;
+ if (inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
+ return sk;
+ }
+
+ /* if the nulls value we got at the end of this lookup is not the
+ * expected one, we must restart lookup. We probably met an item that
+ * was moved to another chain due to rehash.
+ */
+ if (get_nulls_value(node) != slot)
+ goto begin;
+
+ return NULL;
+}
+
+static void udp6_hash4(struct sock *sk)
+{
+ struct net *net = sock_net(sk);
+ unsigned int hash;
+
+ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) {
+ udp4_hash4(sk);
+ return;
+ }
+
+ if (sk_unhashed(sk) || ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+ return;
+
+ hash = udp6_ehashfn(net, &sk->sk_v6_rcv_saddr, sk->sk_num,
+ &sk->sk_v6_daddr, sk->sk_dport);
+
+ udp_lib_hash4(sk, hash);
+}
+#endif /* CONFIG_BASE_SMALL */
+
/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(const struct net *net,
const struct in6_addr *saddr, __be16 sport,
@@ -224,13 +303,19 @@ struct sock *__udp6_lib_lookup(const struct net *net,
struct sk_buff *skb)
{
unsigned short hnum = ntohs(dport);
- unsigned int hash2, slot2;
struct udp_hslot *hslot2;
struct sock *result, *sk;
+ unsigned int hash2;
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
- slot2 = hash2 & udptable->mask;
- hslot2 = &udptable->hash2[slot2];
+ hslot2 = udp_hashslot2(udptable, hash2);
+
+ if (udp_has_hash4(hslot2)) {
+ result = udp6_lib_lookup4(net, saddr, sport, daddr, hnum,
+ dif, sdif, udptable);
+ if (result) /* udp6_lib_lookup4 return sk or NULL */
+ return result;
+ }
/* Lookup connected or non-wildcard sockets */
result = udp6_lib_lookup2(net, saddr, sport,
@@ -257,8 +342,7 @@ struct sock *__udp6_lib_lookup(const struct net *net,
/* Lookup wildcard sockets */
hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
- slot2 = hash2 & udptable->mask;
- hslot2 = &udptable->hash2[slot2];
+ hslot2 = udp_hashslot2(udptable, hash2);
result = udp6_lib_lookup2(net, saddr, sport,
&in6addr_any, hnum, dif, sdif,
@@ -859,7 +943,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
udptable->mask;
hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
- hslot = &udptable->hash2[hash2];
+ hslot = &udptable->hash2[hash2].hslot;
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
}
@@ -1065,14 +1149,13 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
{
struct udp_table *udptable = net->ipv4.udp_table;
unsigned short hnum = ntohs(loc_port);
- unsigned int hash2, slot2;
struct udp_hslot *hslot2;
+ unsigned int hash2;
__portpair ports;
struct sock *sk;
hash2 = ipv6_portaddr_hash(net, loc_addr, hnum);
- slot2 = hash2 & udptable->mask;
- hslot2 = &udptable->hash2[slot2];
+ hslot2 = udp_hashslot2(udptable, hash2);
ports = INET_COMBINED_PORTS(rmt_port, hnum);
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
@@ -1169,6 +1252,18 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}
+static int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int res;
+
+ lock_sock(sk);
+ res = __ip6_datagram_connect(sk, uaddr, addr_len);
+ if (!res)
+ udp6_hash4(sk);
+ release_sock(sk);
+ return res;
+}
+
/**
* udp6_hwcsum_outgoing - handle outgoing HW checksumming
* @sk: socket we are sending on
@@ -1266,8 +1361,10 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
cork->gso_size);
+
+ /* Don't checksum the payload, skb will get segmented */
+ goto csum_partial;
}
- goto csum_partial;
}
if (is_udplite)
@@ -1762,7 +1859,7 @@ struct proto udpv6_prot = {
.owner = THIS_MODULE,
.close = udp_lib_close,
.pre_connect = udpv6_pre_connect,
- .connect = ip6_datagram_connect,
+ .connect = udpv6_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
.init = udpv6_init_sock,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index b1d81c4270ab..1f19b6f14484 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -23,23 +23,24 @@
#include <net/ip6_route.h>
#include <net/l3mdev.h>
-static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
- const xfrm_address_t *saddr,
- const xfrm_address_t *daddr,
- u32 mark)
+static struct dst_entry *xfrm6_dst_lookup(const struct xfrm_dst_lookup_params *params)
{
struct flowi6 fl6;
struct dst_entry *dst;
int err;
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_l3mdev = l3mdev_master_ifindex_by_index(net, oif);
- fl6.flowi6_mark = mark;
- memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
- if (saddr)
- memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
+ fl6.flowi6_l3mdev = l3mdev_master_ifindex_by_index(params->net,
+ params->oif);
+ fl6.flowi6_mark = params->mark;
+ memcpy(&fl6.daddr, params->daddr, sizeof(fl6.daddr));
+ if (params->saddr)
+ memcpy(&fl6.saddr, params->saddr, sizeof(fl6.saddr));
- dst = ip6_route_output(net, NULL, &fl6);
+ fl6.flowi4_proto = params->ipproto;
+ fl6.uli = params->uli;
+
+ dst = ip6_route_output(params->net, NULL, &fl6);
err = dst->error;
if (dst->error) {
@@ -50,15 +51,14 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
return dst;
}
-static int xfrm6_get_saddr(struct net *net, int oif,
- xfrm_address_t *saddr, xfrm_address_t *daddr,
- u32 mark)
+static int xfrm6_get_saddr(xfrm_address_t *saddr,
+ const struct xfrm_dst_lookup_params *params)
{
struct dst_entry *dst;
struct net_device *dev;
struct inet6_dev *idev;
- dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark);
+ dst = xfrm6_dst_lookup(params);
if (IS_ERR(dst))
return -EHOSTUNREACH;
@@ -68,7 +68,8 @@ static int xfrm6_get_saddr(struct net *net, int oif,
return -EHOSTUNREACH;
}
dev = idev->dev;
- ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6);
+ ipv6_dev_get_saddr(dev_net(dev), dev, &params->daddr->in6, 0,
+ &saddr->in6);
dst_release(dst);
return 0;
}
Powered by cgit, Gruvboxed by Blaster4385.