summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c86
-rw-r--r--net/ipv6/addrlabel.c8
-rw-r--r--net/ipv6/af_inet6.c2
-rw-r--r--net/ipv6/calipso.c21
-rw-r--r--net/ipv6/esp6.c53
-rw-r--r--net/ipv6/exthdrs.c3
-rw-r--r--net/ipv6/fib6_rules.c57
-rw-r--r--net/ipv6/icmp.c7
-rw-r--r--net/ipv6/ila/ila_lwt.c4
-rw-r--r--net/ipv6/inet6_connection_sock.c16
-rw-r--r--net/ipv6/inet6_hashtables.c40
-rw-r--r--net/ipv6/ioam6_iptunnel.c82
-rw-r--r--net/ipv6/ip6_fib.c119
-rw-r--r--net/ipv6/ip6_flowlabel.c2
-rw-r--r--net/ipv6/ip6_gre.c51
-rw-r--r--net/ipv6/ip6_output.c16
-rw-r--r--net/ipv6/ip6_tunnel.c45
-rw-r--r--net/ipv6/ip6_vti.c42
-rw-r--r--net/ipv6/ip6mr.c16
-rw-r--r--net/ipv6/ndisc.c8
-rw-r--r--net/ipv6/netfilter.c12
-rw-r--r--net/ipv6/netfilter/ip6_tables.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c27
-rw-r--r--net/ipv6/netfilter/nf_dup_ipv6.c6
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c23
-rw-r--r--net/ipv6/netfilter/nft_fib_ipv6.c36
-rw-r--r--net/ipv6/ping.c3
-rw-r--r--net/ipv6/raw.c15
-rw-r--r--net/ipv6/reassembly.c29
-rw-r--r--net/ipv6/route.c468
-rw-r--r--net/ipv6/rpl_iptunnel.c14
-rw-r--r--net/ipv6/seg6_hmac.c13
-rw-r--r--net/ipv6/seg6_iptunnel.c14
-rw-r--r--net/ipv6/sit.c46
-rw-r--r--net/ipv6/tcp_ipv6.c72
-rw-r--r--net/ipv6/tcpv6_offload.c25
-rw-r--r--net/ipv6/udp.c14
-rw-r--r--net/ipv6/udp_offload.c7
-rw-r--r--net/ipv6/xfrm6_input.c18
39 files changed, 904 insertions, 618 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ac8cc1076536..43b19adfbf88 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -80,6 +80,7 @@
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/l3mdev.h>
+#include <net/netdev_lock.h>
#include <linux/if_tunnel.h>
#include <linux/rtnetlink.h>
#include <linux/netconf.h>
@@ -312,7 +313,7 @@ static inline bool addrconf_link_ready(const struct net_device *dev)
static void addrconf_del_rs_timer(struct inet6_dev *idev)
{
- if (del_timer(&idev->rs_timer))
+ if (timer_delete(&idev->rs_timer))
__in6_dev_put(idev);
}
@@ -377,6 +378,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
int err = -ENOMEM;
ASSERT_RTNL();
+ netdev_ops_assert_locked(dev);
if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev)
return ERR_PTR(-EINVAL);
@@ -402,7 +404,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
return ERR_PTR(err);
}
if (ndev->cnf.forwarding)
- dev_disable_lro(dev);
+ netif_disable_lro(dev);
/* We refer to the device */
netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL);
@@ -3152,10 +3154,13 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
rtnl_net_lock(net);
dev = __dev_get_by_index(net, ireq.ifr6_ifindex);
- if (dev)
+ if (dev) {
+ netdev_lock_ops(dev);
err = inet6_addr_add(net, dev, &cfg, 0, 0, NULL);
- else
+ netdev_unlock_ops(dev);
+ } else {
err = -ENODEV;
+ }
rtnl_net_unlock(net);
return err;
}
@@ -3209,16 +3214,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
- int scope, plen, offset = 0;
+ int scope, plen;
u32 pflags = 0;
ASSERT_RTNL();
memset(&addr, 0, sizeof(struct in6_addr));
- /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
- if (idev->dev->addr_len == sizeof(struct in6_addr))
- offset = sizeof(struct in6_addr) - 4;
- memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+ memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
scope = IPV6_ADDR_COMPATv4;
@@ -3529,7 +3531,13 @@ static void addrconf_gre_config(struct net_device *dev)
return;
}
- if (dev->type == ARPHRD_ETHER) {
+ /* Generate the IPv6 link-local address using addrconf_addr_gen(),
+ * unless we have an IPv4 GRE device not bound to an IP address and
+ * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+ * case). Such devices fall back to add_v4_addrs() instead.
+ */
+ if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
addrconf_addr_gen(idev, true);
return;
}
@@ -5026,9 +5034,10 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!dev) {
NL_SET_ERR_MSG_MOD(extack, "Unable to find the interface");
err = -ENODEV;
- goto unlock;
+ goto unlock_rtnl;
}
+ netdev_lock_ops(dev);
idev = ipv6_find_idev(dev);
if (IS_ERR(idev)) {
err = PTR_ERR(idev);
@@ -5065,6 +5074,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
in6_ifa_put(ifa);
unlock:
+ netdev_unlock_ops(dev);
+unlock_rtnl:
rtnl_net_unlock(net);
return err;
@@ -5338,12 +5349,12 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
struct ifaddrmsg *ifm;
int err, i;
- if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ ifm = nlmsg_payload(nlh, sizeof(*ifm));
+ if (!ifm) {
NL_SET_ERR_MSG_MOD(extack, "Invalid header for address dump request");
return -EINVAL;
}
- ifm = nlmsg_data(nlh);
if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address dump request");
return -EINVAL;
@@ -5476,7 +5487,8 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
struct ifaddrmsg *ifm;
int i, err;
- if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ ifm = nlmsg_payload(nlh, sizeof(*ifm));
+ if (!ifm) {
NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request");
return -EINVAL;
}
@@ -5485,7 +5497,6 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
ifa_ipv6_policy, extack);
- ifm = nlmsg_data(nlh);
if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
return -EINVAL;
@@ -5784,6 +5795,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
}
}
+static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb,
+ struct inet6_dev *idev)
+{
+ struct nlattr *nla;
+
+ nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
+ if (!nla)
+ goto nla_put_failure;
+ snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
+
+ nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
+ if (!nla)
+ goto nla_put_failure;
+ snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
u32 ext_filter_mask)
{
@@ -5806,18 +5838,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
/* XXX - MC not implemented */
- if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
- return 0;
-
- nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
- if (!nla)
- goto nla_put_failure;
- snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
-
- nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
- if (!nla)
- goto nla_put_failure;
- snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+ if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) {
+ if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0)
+ goto nla_put_failure;
+ }
nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
if (!nla)
@@ -6091,7 +6115,8 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
{
struct ifinfomsg *ifm;
- if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ ifm = nlmsg_payload(nlh, sizeof(*ifm));
+ if (!ifm) {
NL_SET_ERR_MSG_MOD(extack, "Invalid header for link dump request");
return -EINVAL;
}
@@ -6101,7 +6126,6 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
return -EINVAL;
}
- ifm = nlmsg_data(nlh);
if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
ifm->ifi_change || ifm->ifi_index) {
NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for dump request");
@@ -6503,7 +6527,9 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write,
if (idev->cnf.addr_gen_mode != new_val) {
WRITE_ONCE(idev->cnf.addr_gen_mode, new_val);
+ netdev_lock_ops(idev->dev);
addrconf_init_auto_addrs(idev->dev);
+ netdev_unlock_ops(idev->dev);
}
} else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) {
struct net_device *dev;
@@ -6515,7 +6541,9 @@ static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write,
idev->cnf.addr_gen_mode != new_val) {
WRITE_ONCE(idev->cnf.addr_gen_mode,
new_val);
+ netdev_lock_ops(idev->dev);
addrconf_init_auto_addrs(idev->dev);
+ netdev_unlock_ops(idev->dev);
}
}
}
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index ab054f329e12..fb63ffbcfc64 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -473,12 +473,12 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh,
{
struct ifaddrlblmsg *ifal;
- if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+ ifal = nlmsg_payload(nlh, sizeof(*ifal));
+ if (!ifal) {
NL_SET_ERR_MSG_MOD(extack, "Invalid header for address label dump request");
return -EINVAL;
}
- ifal = nlmsg_data(nlh);
if (ifal->__ifal_reserved || ifal->ifal_prefixlen ||
ifal->ifal_flags || ifal->ifal_index || ifal->ifal_seq) {
NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address label dump request");
@@ -543,7 +543,8 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
struct ifaddrlblmsg *ifal;
int i, err;
- if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+ ifal = nlmsg_payload(nlh, sizeof(*ifal));
+ if (!ifal) {
NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request");
return -EINVAL;
}
@@ -552,7 +553,6 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
return nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb,
IFAL_MAX, ifal_policy, extack);
- ifal = nlmsg_data(nlh);
if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) {
NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request");
return -EINVAL;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f60ec8b0f8ea..acaff1296783 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -715,6 +715,7 @@ const struct proto_ops inet6_stream_ops = {
#endif
.set_rcvlowat = tcp_set_rcvlowat,
};
+EXPORT_SYMBOL_GPL(inet6_stream_ops);
const struct proto_ops inet6_dgram_ops = {
.family = PF_INET6,
@@ -881,7 +882,6 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
}
return false;
}
-EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
static struct packet_type ipv6_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index dbcea9fee626..62618a058b8f 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1072,8 +1072,13 @@ static int calipso_sock_getattr(struct sock *sk,
struct ipv6_opt_hdr *hop;
int opt_len, len, ret_val = -ENOMSG, offset;
unsigned char *opt;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+
+ if (!pinfo)
+ return -EAFNOSUPPORT;
+ txopts = txopt_get(pinfo);
if (!txopts || !txopts->hopopt)
goto done;
@@ -1125,8 +1130,13 @@ static int calipso_sock_setattr(struct sock *sk,
{
int ret_val;
struct ipv6_opt_hdr *old, *new;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+
+ if (!pinfo)
+ return -EAFNOSUPPORT;
+ txopts = txopt_get(pinfo);
old = NULL;
if (txopts)
old = txopts->hopopt;
@@ -1153,8 +1163,13 @@ static int calipso_sock_setattr(struct sock *sk,
static void calipso_sock_delattr(struct sock *sk)
{
struct ipv6_opt_hdr *new_hop;
- struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+ struct ipv6_pinfo *pinfo = inet6_sk(sk);
+ struct ipv6_txoptions *txopts;
+
+ if (!pinfo)
+ return;
+ txopts = txopt_get(pinfo);
if (!txopts || !txopts->hopopt)
goto done;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 9e73944e3b53..72adfc107b55 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
}
#ifdef CONFIG_INET6_ESPINTCP
-struct esp_tcp_sk {
- struct sock *sk;
- struct rcu_head rcu;
-};
-
-static void esp_free_tcp_sk(struct rcu_head *head)
-{
- struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);
-
- sock_put(esk->sk);
- kfree(esk);
-}
-
static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
{
struct xfrm_encap_tmpl *encap = x->encap;
struct net *net = xs_net(x);
- struct esp_tcp_sk *esk;
__be16 sport, dport;
- struct sock *nsk;
struct sock *sk;
- sk = rcu_dereference(x->encap_sk);
- if (sk && sk->sk_state == TCP_ESTABLISHED)
- return sk;
-
spin_lock_bh(&x->lock);
sport = encap->encap_sport;
dport = encap->encap_dport;
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (sk && sk == nsk) {
- esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
- if (!esk) {
- spin_unlock_bh(&x->lock);
- return ERR_PTR(-ENOMEM);
- }
- RCU_INIT_POINTER(x->encap_sk, NULL);
- esk->sk = sk;
- call_rcu(&esk->rcu, esp_free_tcp_sk);
- }
spin_unlock_bh(&x->lock);
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6,
@@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x)
return ERR_PTR(-EINVAL);
}
- spin_lock_bh(&x->lock);
- nsk = rcu_dereference_protected(x->encap_sk,
- lockdep_is_held(&x->lock));
- if (encap->encap_sport != sport ||
- encap->encap_dport != dport) {
- sock_put(sk);
- sk = nsk ?: ERR_PTR(-EREMCHG);
- } else if (sk == nsk) {
- sock_put(sk);
- } else {
- rcu_assign_pointer(x->encap_sk, sk);
- }
- spin_unlock_bh(&x->lock);
-
return sk;
}
@@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
sk = esp6_find_tcp_sk(x);
err = PTR_ERR_OR_ZERO(sk);
- if (err)
+ if (err) {
+ kfree_skb(skb);
goto out;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
err = espintcp_push_skb(sk, skb);
bh_unlock_sock(sk);
+ sock_put(sk);
+
out:
rcu_read_unlock();
return err;
@@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x,
if (IS_ERR(sk))
return ERR_CAST(sk);
+ sock_put(sk);
+
*lenp = htons(len);
esph = (struct ip_esp_hdr *)(lenp + 1);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 6789623b2b0d..457de0745a33 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -1204,10 +1204,9 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
{
struct ipv6_txoptions *opt2;
- opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC);
+ opt2 = sock_kmemdup(sk, opt, opt->tot_len, GFP_ATOMIC);
if (opt2) {
long dif = (char *)opt2 - (char *)opt;
- memcpy(opt2, opt, opt->tot_len);
if (opt2->hopopt)
*((char **)&opt2->hopopt) += dif;
if (opt2->dst0opt)
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 67d39114d9a6..fd5f7112a51f 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -29,6 +29,7 @@ struct fib6_rule {
__be32 flowlabel;
__be32 flowlabel_mask;
dscp_t dscp;
+ dscp_t dscp_mask;
u8 dscp_full:1; /* DSCP or TOS selector */
};
@@ -331,7 +332,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
return 0;
}
- if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel))
+ if ((r->dscp ^ ip6_dscp(fl6->flowlabel)) & r->dscp_mask)
return 0;
if ((r->flowlabel ^ flowi6_get_flowlabel(fl6)) & r->flowlabel_mask)
@@ -340,12 +341,12 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
return 0;
- if (fib_rule_port_range_set(&rule->sport_range) &&
- !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport))
+ if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask,
+ fl6->fl6_sport))
return 0;
- if (fib_rule_port_range_set(&rule->dport_range) &&
- !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport))
+ if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask,
+ fl6->fl6_dport))
return 0;
return 1;
@@ -360,11 +361,35 @@ static int fib6_nl2rule_dscp(const struct nlattr *nla, struct fib6_rule *rule6,
}
rule6->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+ rule6->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK);
rule6->dscp_full = true;
return 0;
}
+static int fib6_nl2rule_dscp_mask(const struct nlattr *nla,
+ struct fib6_rule *rule6,
+ struct netlink_ext_ack *extack)
+{
+ dscp_t dscp_mask;
+
+ if (!rule6->dscp_full) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Cannot specify DSCP mask without DSCP value");
+ return -EINVAL;
+ }
+
+ dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+ if (rule6->dscp & ~dscp_mask) {
+ NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask");
+ return -EINVAL;
+ }
+
+ rule6->dscp_mask = dscp_mask;
+
+ return 0;
+}
+
static int fib6_nl2rule_flowlabel(struct nlattr **tb, struct fib6_rule *rule6,
struct netlink_ext_ack *extack)
{
@@ -399,9 +424,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
+ struct fib6_rule *rule6 = (struct fib6_rule *)rule;
+ struct net *net = rule->fr_net;
int err = -EINVAL;
- struct net *net = sock_net(skb->sk);
- struct fib6_rule *rule6 = (struct fib6_rule *) rule;
if (!inet_validate_dscp(frh->tos)) {
NL_SET_ERR_MSG(extack,
@@ -409,10 +434,15 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
goto errout;
}
rule6->dscp = inet_dsfield_to_dscp(frh->tos);
+ rule6->dscp_mask = frh->tos ? inet_dsfield_to_dscp(INET_DSCP_MASK) : 0;
if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0)
goto errout;
+ if (tb[FRA_DSCP_MASK] &&
+ fib6_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule6, extack) < 0)
+ goto errout;
+
if ((tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) &&
fib6_nl2rule_flowlabel(tb, rule6, extack) < 0)
goto errout;
@@ -482,6 +512,14 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
return 0;
}
+ if (tb[FRA_DSCP_MASK]) {
+ dscp_t dscp_mask;
+
+ dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2);
+ if (!rule6->dscp_full || rule6->dscp_mask != dscp_mask)
+ return 0;
+ }
+
if (tb[FRA_FLOWLABEL] &&
nla_get_be32(tb[FRA_FLOWLABEL]) != rule6->flowlabel)
return 0;
@@ -512,7 +550,9 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
if (rule6->dscp_full) {
frh->tos = 0;
if (nla_put_u8(skb, FRA_DSCP,
- inet_dscp_to_dsfield(rule6->dscp) >> 2))
+ inet_dscp_to_dsfield(rule6->dscp) >> 2) ||
+ nla_put_u8(skb, FRA_DSCP_MASK,
+ inet_dscp_to_dsfield(rule6->dscp_mask) >> 2))
goto nla_put_failure;
} else {
frh->tos = inet_dscp_to_dsfield(rule6->dscp);
@@ -539,6 +579,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
return nla_total_size(16) /* dst */
+ nla_total_size(16) /* src */
+ nla_total_size(1) /* dscp */
+ + nla_total_size(1) /* dscp mask */
+ nla_total_size(4) /* flowlabel */
+ nla_total_size(4); /* flowlabel mask */
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4d14ab7f7e99..3fd19a84b358 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -957,12 +957,9 @@ static int icmpv6_rcv(struct sk_buff *skb)
break;
case ICMPV6_ECHO_REPLY:
- reason = ping_rcv(skb);
- break;
-
case ICMPV6_EXT_ECHO_REPLY:
- reason = ping_rcv(skb);
- break;
+ ping_rcv(skb);
+ return 0;
case ICMPV6_PKT_TOOBIG:
/* BUGGG_FUTURE: if packet contains rthdr, we cannot update
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ff7e734e335b..7d574f5132e2 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -88,13 +88,15 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
goto drop;
}
- if (ilwt->connected) {
+ /* cache only if we don't create a dst reference loop */
+ if (ilwt->connected && orig_dst->lwtstate != dst->lwtstate) {
local_bh_disable();
dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
local_bh_enable();
}
}
+ skb_dst_drop(skb);
skb_dst_set(skb, dst);
return dst_output(net, sk, skb);
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 80043e46117c..8f500eaf33cf 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -54,21 +54,6 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
return dst;
}
-EXPORT_SYMBOL(inet6_csk_route_req);
-
-void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
-{
- struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
-
- sin6->sin6_family = AF_INET6;
- sin6->sin6_addr = sk->sk_v6_daddr;
- sin6->sin6_port = inet_sk(sk)->inet_dport;
- /* We do not store received flowlabel for TCP */
- sin6->sin6_flowinfo = 0;
- sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
- sk->sk_bound_dev_if);
-}
-EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
static inline
struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
@@ -151,4 +136,3 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
dst = inet6_csk_route_socket(sk, &fl6);
return IS_ERR(dst) ? NULL : dst;
}
-EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 9ec05e354baa..76ee521189eb 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -35,8 +35,8 @@ u32 inet6_ehashfn(const struct net *net,
lhash = (__force u32)laddr->s6_addr32[3];
fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret);
- return __inet6_ehashfn(lhash, lport, fhash, fport,
- inet6_ehash_secret + net_hash_mix(net));
+ return lport + __inet6_ehashfn(lhash, 0, fhash, fport,
+ inet6_ehash_secret + net_hash_mix(net));
}
EXPORT_SYMBOL_GPL(inet6_ehashfn);
@@ -263,7 +263,9 @@ EXPORT_SYMBOL_GPL(inet6_lookup);
static int __inet6_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, const __u16 lport,
- struct inet_timewait_sock **twp)
+ struct inet_timewait_sock **twp,
+ bool rcu_lookup,
+ u32 hash)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
@@ -273,14 +275,26 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
struct net *net = sock_net(sk);
const int sdif = l3mdev_master_ifindex_by_index(net, dif);
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
- const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
- inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
- spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
- struct sock *sk2;
- const struct hlist_nulls_node *node;
struct inet_timewait_sock *tw = NULL;
+ const struct hlist_nulls_node *node;
+ struct sock *sk2;
+ spinlock_t *lock;
+
+ if (rcu_lookup) {
+ sk_nulls_for_each(sk2, node, &head->chain) {
+ if (sk2->sk_hash != hash ||
+ !inet6_match(net, sk2, saddr, daddr,
+ ports, dif, sdif))
+ continue;
+ if (sk2->sk_state == TCP_TIME_WAIT)
+ break;
+ return -EADDRNOTAVAIL;
+ }
+ return 0;
+ }
+ lock = inet_ehash_lockp(hinfo, hash);
spin_lock(lock);
sk_nulls_for_each(sk2, node, &head->chain) {
@@ -339,11 +353,19 @@ static u64 inet6_sk_port_offset(const struct sock *sk)
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
+ const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+ const struct in6_addr *saddr = &sk->sk_v6_daddr;
+ const struct inet_sock *inet = inet_sk(sk);
+ const struct net *net = sock_net(sk);
u64 port_offset = 0;
+ u32 hash_port0;
if (!inet_sk(sk)->inet_num)
port_offset = inet6_sk_port_offset(sk);
- return __inet_hash_connect(death_row, sk, port_offset,
+
+ hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport);
+
+ return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
__inet6_check_established);
}
EXPORT_SYMBOL_GPL(inet6_hash_connect);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 2c383c12a431..40df8bdfaacd 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -38,6 +38,7 @@ struct ioam6_lwt_freq {
};
struct ioam6_lwt {
+ struct dst_entry null_dst;
struct dst_cache cache;
struct ioam6_lwt_freq freq;
atomic_t pkt_cnt;
@@ -177,6 +178,14 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
if (err)
goto free_lwt;
+ /* This "fake" dst_entry will be stored in a dst_cache, which will call
+ * dst_hold() and dst_release() on it. We must ensure that dst_destroy()
+ * will never be called. For that, its initial refcount is 1 and +1 when
+ * it is stored in the cache. Then, +1/-1 each time we read the cache
+ * and release it. Long story short, we're fine.
+ */
+ dst_init(&ilwt->null_dst, NULL, NULL, DST_OBSOLETE_NONE, DST_NOCOUNT);
+
atomic_set(&ilwt->pkt_cnt, 0);
ilwt->freq.k = freq_k;
ilwt->freq.n = freq_n;
@@ -336,8 +345,8 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
- struct in6_addr orig_daddr;
+ struct dst_entry *orig_dst = skb_dst(skb);
+ struct dst_entry *dst = NULL;
struct ioam6_lwt *ilwt;
int err = -EINVAL;
u32 pkt_cnt;
@@ -345,19 +354,28 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
- ilwt = ioam6_lwt_state(dst->lwtstate);
+ ilwt = ioam6_lwt_state(orig_dst->lwtstate);
/* Check for insertion frequency (i.e., "k over n" insertions) */
pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt);
if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k)
goto out;
- orig_daddr = ipv6_hdr(skb)->daddr;
-
local_bh_disable();
- cache_dst = dst_cache_get(&ilwt->cache);
+ dst = dst_cache_get(&ilwt->cache);
local_bh_enable();
+ /* This is how we notify that the destination does not change after
+ * transformation and that we need to use orig_dst instead of the cache
+ */
+ if (dst == &ilwt->null_dst) {
+ dst_release(dst);
+
+ dst = orig_dst;
+ /* keep refcount balance: dst_release() is called at the end */
+ dst_hold(dst);
+ }
+
switch (ilwt->mode) {
case IOAM6_IPTUNNEL_MODE_INLINE:
do_inline:
@@ -365,7 +383,7 @@ do_inline:
if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
goto out;
- err = ioam6_do_inline(net, skb, &ilwt->tuninfo, cache_dst);
+ err = ioam6_do_inline(net, skb, &ilwt->tuninfo, dst);
if (unlikely(err))
goto drop;
@@ -375,7 +393,7 @@ do_encap:
/* Encapsulation (ip6ip6) */
err = ioam6_do_encap(net, skb, &ilwt->tuninfo,
ilwt->has_tunsrc, &ilwt->tunsrc,
- &ilwt->tundst, cache_dst);
+ &ilwt->tundst, dst);
if (unlikely(err))
goto drop;
@@ -393,7 +411,7 @@ do_encap:
goto drop;
}
- if (unlikely(!cache_dst)) {
+ if (unlikely(!dst)) {
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct flowi6 fl6;
@@ -404,40 +422,54 @@ do_encap:
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = hdr->nexthdr;
- cache_dst = ip6_route_output(net, NULL, &fl6);
- if (cache_dst->error) {
- err = cache_dst->error;
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (dst->error) {
+ err = dst->error;
goto drop;
}
- /* cache only if we don't create a dst reference loop */
- if (dst->lwtstate != cache_dst->lwtstate) {
- local_bh_disable();
- dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
- local_bh_enable();
- }
-
- err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
+ /* If the destination is the same after transformation (which is
+ * a valid use case for IOAM), then we don't want to add it to
+ * the cache in order to avoid a reference loop. Instead, we add
+ * our fake dst_entry to the cache as a way to detect this case.
+ * Otherwise, we add the resolved destination to the cache.
+ */
+ local_bh_disable();
+ if (orig_dst->lwtstate == dst->lwtstate)
+ dst_cache_set_ip6(&ilwt->cache,
+ &ilwt->null_dst, &fl6.saddr);
+ else
+ dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr);
+ local_bh_enable();
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
if (unlikely(err))
goto drop;
}
- if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
+ /* avoid lwtunnel_output() reentry loop when destination is the same
+ * after transformation (e.g., with the inline mode)
+ */
+ if (orig_dst->lwtstate != dst->lwtstate) {
skb_dst_drop(skb);
- skb_dst_set(skb, cache_dst);
+ skb_dst_set(skb, dst);
return dst_output(net, sk, skb);
}
out:
- dst_release(cache_dst);
- return dst->lwtstate->orig_output(net, sk, skb);
+ dst_release(dst);
+ return orig_dst->lwtstate->orig_output(net, sk, skb);
drop:
- dst_release(cache_dst);
+ dst_release(dst);
kfree_skb(skb);
return err;
}
static void ioam6_destroy_state(struct lwtunnel_state *lwt)
{
+ /* Since the refcount of per-cpu dst_entry caches will never be 0 (see
+ * why above) when our "fake" dst_entry is used, it is not necessary to
+ * remove them before calling dst_cache_destroy()
+ */
dst_cache_destroy(&ioam6_lwt_state(lwt)->cache);
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index c134ba202c4c..7094d7708686 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -249,40 +249,52 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
struct fib6_table *fib6_new_table(struct net *net, u32 id)
{
- struct fib6_table *tb;
+ struct fib6_table *tb, *new_tb;
if (id == 0)
id = RT6_TABLE_MAIN;
+
tb = fib6_get_table(net, id);
if (tb)
return tb;
- tb = fib6_alloc_table(net, id);
- if (tb)
- fib6_link_table(net, tb);
+ new_tb = fib6_alloc_table(net, id);
+ if (!new_tb)
+ return NULL;
+
+ spin_lock_bh(&net->ipv6.fib_table_hash_lock);
+
+ tb = fib6_get_table(net, id);
+ if (unlikely(tb)) {
+ spin_unlock_bh(&net->ipv6.fib_table_hash_lock);
+ kfree(new_tb);
+ return tb;
+ }
+
+ fib6_link_table(net, new_tb);
+
+ spin_unlock_bh(&net->ipv6.fib_table_hash_lock);
- return tb;
+ return new_tb;
}
EXPORT_SYMBOL_GPL(fib6_new_table);
struct fib6_table *fib6_get_table(struct net *net, u32 id)
{
- struct fib6_table *tb;
struct hlist_head *head;
- unsigned int h;
+ struct fib6_table *tb;
- if (id == 0)
+ if (!id)
id = RT6_TABLE_MAIN;
- h = id & (FIB6_TABLE_HASHSZ - 1);
- rcu_read_lock();
- head = &net->ipv6.fib_table_hash[h];
- hlist_for_each_entry_rcu(tb, head, tb6_hlist) {
- if (tb->tb6_id == id) {
- rcu_read_unlock();
+
+ head = &net->ipv6.fib_table_hash[id & (FIB6_TABLE_HASHSZ - 1)];
+
+ /* See comment in fib6_link_table(). RCU is not required,
+ * but rcu_dereference_raw() is used to avoid data-race.
+ */
+ hlist_for_each_entry_rcu(tb, head, tb6_hlist, true)
+ if (tb->tb6_id == id)
return tb;
- }
- }
- rcu_read_unlock();
return NULL;
}
@@ -1015,8 +1027,9 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
.table = table
};
- nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from,
- &arg);
+ rcu_read_lock();
+ nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg);
+ rcu_read_unlock();
} else {
struct fib6_nh *fib6_nh;
@@ -1034,8 +1047,14 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
rt6_flush_exceptions(rt);
fib6_drop_pcpu_from(rt, table);
- if (rt->nh && !list_empty(&rt->nh_list))
- list_del_init(&rt->nh_list);
+ if (rt->nh) {
+ spin_lock(&rt->nh->lock);
+
+ if (!list_empty(&rt->nh_list))
+ list_del_init(&rt->nh_list);
+
+ spin_unlock(&rt->nh->lock);
+ }
if (refcount_read(&rt->fib6_ref) != 1) {
/* This route is used as dummy address holder in some split
@@ -1069,8 +1088,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
- struct nl_info *info,
- struct netlink_ext_ack *extack)
+ struct nl_info *info, struct netlink_ext_ack *extack,
+ struct list_head *purge_list)
{
struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&rt->fib6_table->tb6_lock));
@@ -1203,7 +1222,9 @@ next_iter:
fib6_nsiblings++;
}
BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+ rcu_read_lock();
rt6_multipath_rebalance(temp_sibling);
+ rcu_read_unlock();
}
/*
@@ -1246,7 +1267,9 @@ add:
sibling->fib6_nsiblings--;
rt->fib6_nsiblings = 0;
list_del_rcu(&rt->fib6_siblings);
+ rcu_read_lock();
rt6_multipath_rebalance(next_sibling);
+ rcu_read_unlock();
return err;
}
}
@@ -1294,10 +1317,9 @@ add:
}
nsiblings = iter->fib6_nsiblings;
iter->fib6_node = NULL;
- fib6_purge_rt(iter, fn, info->nl_net);
+ list_add(&iter->purge_link, purge_list);
if (rcu_access_pointer(fn->rr_ptr) == iter)
fn->rr_ptr = NULL;
- fib6_info_release(iter);
if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
@@ -1310,10 +1332,9 @@ add:
if (rt6_qualify_for_ecmp(iter)) {
*ins = iter->fib6_next;
iter->fib6_node = NULL;
- fib6_purge_rt(iter, fn, info->nl_net);
+ list_add(&iter->purge_link, purge_list);
if (rcu_access_pointer(fn->rr_ptr) == iter)
fn->rr_ptr = NULL;
- fib6_info_release(iter);
nsiblings--;
info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
} else {
@@ -1329,6 +1350,28 @@ add:
return 0;
}
+static int fib6_add_rt2node_nh(struct fib6_node *fn, struct fib6_info *rt,
+ struct nl_info *info, struct netlink_ext_ack *extack,
+ struct list_head *purge_list)
+{
+ int err;
+
+ spin_lock(&rt->nh->lock);
+
+ if (rt->nh->dead) {
+ NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+ err = -EINVAL;
+ } else {
+ err = fib6_add_rt2node(fn, rt, info, extack, purge_list);
+ if (!err)
+ list_add(&rt->nh_list, &rt->nh->f6i_list);
+ }
+
+ spin_unlock(&rt->nh->lock);
+
+ return err;
+}
+
static void fib6_start_gc(struct net *net, struct fib6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
@@ -1383,6 +1426,7 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->fib6_table;
+ LIST_HEAD(purge_list);
struct fib6_node *fn;
#ifdef CONFIG_IPV6_SUBTREES
struct fib6_node *pn = NULL;
@@ -1485,10 +1529,19 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
}
#endif
- err = fib6_add_rt2node(fn, rt, info, extack);
+ if (rt->nh)
+ err = fib6_add_rt2node_nh(fn, rt, info, extack, &purge_list);
+ else
+ err = fib6_add_rt2node(fn, rt, info, extack, &purge_list);
if (!err) {
- if (rt->nh)
- list_add(&rt->nh_list, &rt->nh->f6i_list);
+ struct fib6_info *iter, *next;
+
+ list_for_each_entry_safe(iter, next, &purge_list, purge_link) {
+ list_del(&iter->purge_link);
+ fib6_purge_rt(iter, fn, info->nl_net);
+ fib6_info_release(iter);
+ }
+
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
if (rt->fib6_flags & RTF_EXPIRES)
@@ -2383,7 +2436,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
round_jiffies(now
+ net->ipv6.sysctl.ip6_rt_gc_interval));
else
- del_timer(&net->ipv6.ip6_fib_timer);
+ timer_delete(&net->ipv6.ip6_fib_timer);
spin_unlock_bh(&net->ipv6.fib6_gc_lock);
}
@@ -2423,6 +2476,8 @@ static int __net_init fib6_net_init(struct net *net)
if (!net->ipv6.fib_table_hash)
goto out_rt6_stats;
+ spin_lock_init(&net->ipv6.fib_table_hash_lock);
+
net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl),
GFP_KERNEL);
if (!net->ipv6.fib6_main_tbl)
@@ -2470,7 +2525,7 @@ static void fib6_net_exit(struct net *net)
{
unsigned int i;
- del_timer_sync(&net->ipv6.ip6_fib_timer);
+ timer_delete_sync(&net->ipv6.ip6_fib_timer);
for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
struct hlist_head *head = &net->ipv6.fib_table_hash[i];
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index eca07e10e21f..a3ff575798dd 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -907,6 +907,6 @@ int ip6_flowlabel_init(void)
void ip6_flowlabel_cleanup(void)
{
static_key_deferred_flush(&ipv6_flowlabel_exclusive);
- del_timer(&ip6_fl_gc_timer);
+ timer_delete(&ip6_fl_gc_timer);
unregister_pernet_subsys(&ip6_flowlabel_net_ops);
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 235808cfec70..2dc9dcffe2ca 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -43,6 +43,7 @@
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/netdev_lock.h>
#include <net/rtnetlink.h>
#include <net/ipv6.h>
@@ -1498,7 +1499,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
tunnel = netdev_priv(dev);
tunnel->dev = dev;
- tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
@@ -1570,7 +1570,7 @@ static struct inet6_protocol ip6gre_protocol __read_mostly = {
.flags = INET6_PROTO_FINAL,
};
-static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
+static void __net_exit ip6gre_exit_rtnl_net(struct net *net, struct list_head *head)
{
struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
struct net_device *dev, *aux;
@@ -1587,16 +1587,16 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
for (h = 0; h < IP6_GRE_HASH_SIZE; h++) {
struct ip6_tnl *t;
- t = rtnl_dereference(ign->tunnels[prio][h]);
+ t = rtnl_net_dereference(net, ign->tunnels[prio][h]);
while (t) {
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
if (!net_eq(dev_net(t->dev), net))
- unregister_netdevice_queue(t->dev,
- head);
- t = rtnl_dereference(t->next);
+ unregister_netdevice_queue(t->dev, head);
+
+ t = rtnl_net_dereference(net, t->next);
}
}
}
@@ -1621,7 +1621,7 @@ static int __net_init ip6gre_init_net(struct net *net)
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
- ign->fb_tunnel_dev->netns_local = true;
+ ign->fb_tunnel_dev->netns_immutable = true;
ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;
@@ -1640,19 +1640,9 @@ err_alloc_dev:
return err;
}
-static void __net_exit ip6gre_exit_batch_rtnl(struct list_head *net_list,
- struct list_head *dev_to_kill)
-{
- struct net *net;
-
- ASSERT_RTNL();
- list_for_each_entry(net, net_list, exit_list)
- ip6gre_destroy_tunnels(net, dev_to_kill);
-}
-
static struct pernet_operations ip6gre_net_ops = {
.init = ip6gre_init_net,
- .exit_batch_rtnl = ip6gre_exit_batch_rtnl,
+ .exit_rtnl = ip6gre_exit_rtnl_net,
.id = &ip6gre_net_id,
.size = sizeof(struct ip6gre_net),
};
@@ -1882,7 +1872,6 @@ static int ip6erspan_tap_init(struct net_device *dev)
tunnel = netdev_priv(dev);
tunnel->dev = dev;
- tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
@@ -1971,7 +1960,7 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
return ret;
}
-static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
+static int ip6gre_newlink_common(struct net *link_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
@@ -1992,7 +1981,7 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
eth_hw_addr_random(dev);
nt->dev = dev;
- nt->net = dev_net(dev);
+ nt->net = link_net;
err = register_netdevice(dev);
if (err)
@@ -2005,12 +1994,14 @@ out:
return err;
}
-static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
+static int ip6gre_newlink(struct net_device *dev,
+ struct rtnl_newlink_params *params,
struct netlink_ext_ack *extack)
{
+ struct net *net = params->link_net ? : dev_net(dev);
struct ip6_tnl *nt = netdev_priv(dev);
- struct net *net = dev_net(dev);
+ struct nlattr **data = params->data;
+ struct nlattr **tb = params->tb;
struct ip6gre_net *ign;
int err;
@@ -2025,7 +2016,7 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
return -EEXIST;
}
- err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+ err = ip6gre_newlink_common(net, dev, tb, data, extack);
if (!err) {
ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
ip6gre_tunnel_link_md(ign, nt);
@@ -2241,12 +2232,14 @@ static void ip6erspan_tap_setup(struct net_device *dev)
netif_keep_dst(dev);
}
-static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
+static int ip6erspan_newlink(struct net_device *dev,
+ struct rtnl_newlink_params *params,
struct netlink_ext_ack *extack)
{
+ struct net *net = params->link_net ? : dev_net(dev);
struct ip6_tnl *nt = netdev_priv(dev);
- struct net *net = dev_net(dev);
+ struct nlattr **data = params->data;
+ struct nlattr **tb = params->tb;
struct ip6gre_net *ign;
int err;
@@ -2262,7 +2255,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
return -EEXIST;
}
- err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+ err = ip6gre_newlink_common(net, dev, tb, data, extack);
if (!err) {
ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]);
ip6erspan_tunnel_link_md(ign, nt);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d577bf2f3053..7bd29a9ff0db 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -259,7 +259,7 @@ bool ip6_autoflowlabel(struct net *net, const struct sock *sk)
}
/*
- * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP and SCTP)
* Note : socket lock is not held for SYNACK packets, but might be modified
* by calls to skb_set_owner_w() and ipv6_local_error(),
* which are using proper atomic operations or spinlocks.
@@ -1386,6 +1386,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
}
v6_cork->hop_limit = ipc6->hlimit;
v6_cork->tclass = ipc6->tclass;
+ v6_cork->dontfrag = ipc6->dontfrag;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
@@ -1421,7 +1422,7 @@ static int __ip6_append_data(struct sock *sk,
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, size_t length, int transhdrlen,
- unsigned int flags, struct ipcm6_cookie *ipc6)
+ unsigned int flags)
{
struct sk_buff *skb, *skb_prev = NULL;
struct inet_cork *cork = &cork_full->base;
@@ -1475,7 +1476,7 @@ static int __ip6_append_data(struct sock *sk,
if (headersize + transhdrlen > mtu)
goto emsgsize;
- if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
+ if (cork->length + length > mtu - headersize && v6_cork->dontfrag &&
(sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_ICMPV6 ||
sk->sk_protocol == IPPROTO_RAW)) {
@@ -1523,7 +1524,8 @@ emsgsize:
uarg = msg->msg_ubuf;
}
} else if (sock_flag(sk, SOCK_ZEROCOPY)) {
- uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb));
+ uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb),
+ false);
if (!uarg)
return -ENOBUFS;
extra_uref = !skb_zcopy(skb); /* only ref on new uarg */
@@ -1855,7 +1857,7 @@ int ip6_append_data(struct sock *sk,
return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
&np->cork, sk_page_frag(sk), getfrag,
- from, length, transhdrlen, flags, ipc6);
+ from, length, transhdrlen, flags);
}
EXPORT_SYMBOL_GPL(ip6_append_data);
@@ -2054,13 +2056,11 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
ip6_cork_release(cork, &v6_cork);
return ERR_PTR(err);
}
- if (ipc6->dontfrag < 0)
- ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk);
err = __ip6_append_data(sk, &queue, cork, &v6_cork,
&current->task_frag, getfrag, from,
length + exthdrlen, transhdrlen + exthdrlen,
- flags, ipc6);
+ flags);
if (err) {
__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
return ERR_PTR(err);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 48fd53b98972..894d3158a6f0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -52,6 +52,7 @@
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/netdev_lock.h>
#include <net/dst_metadata.h>
#include <net/inet_dscp.h>
@@ -253,8 +254,7 @@ static void ip6_dev_free(struct net_device *dev)
static int ip6_tnl_create2(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
- struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ struct ip6_tnl_net *ip6n = net_generic(t->net, ip6_tnl_net_id);
int err;
dev->rtnl_link_ops = &ip6_link_ops;
@@ -1878,7 +1878,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
int t_hlen;
t->dev = dev;
- t->net = dev_net(dev);
ret = dst_cache_init(&t->dst_cache, GFP_KERNEL);
if (ret)
@@ -1940,6 +1939,7 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ t->net = net;
t->parms.proto = IPPROTO_IPV6;
rcu_assign_pointer(ip6n->tnls_wc[0], t);
@@ -2002,17 +2002,22 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
}
-static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
+static int ip6_tnl_newlink(struct net_device *dev,
+ struct rtnl_newlink_params *params,
struct netlink_ext_ack *extack)
{
- struct net *net = dev_net(dev);
- struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ struct nlattr **data = params->data;
+ struct nlattr **tb = params->tb;
struct ip_tunnel_encap ipencap;
+ struct ip6_tnl_net *ip6n;
struct ip6_tnl *nt, *t;
+ struct net *net;
int err;
+ net = params->link_net ? : dev_net(dev);
+ ip6n = net_generic(net, ip6_tnl_net_id);
nt = netdev_priv(dev);
+ nt->net = net;
if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
err = ip6_tnl_encap_setup(nt, &ipencap);
@@ -2205,7 +2210,7 @@ static struct xfrm6_tunnel mplsip6_handler __read_mostly = {
.priority = 1,
};
-static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
+static void __net_exit ip6_tnl_exit_rtnl_net(struct net *net, struct list_head *list)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
struct net_device *dev, *aux;
@@ -2217,25 +2222,27 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head
unregister_netdevice_queue(dev, list);
for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) {
- t = rtnl_dereference(ip6n->tnls_r_l[h]);
+ t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]);
while (t) {
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
if (!net_eq(dev_net(t->dev), net))
unregister_netdevice_queue(t->dev, list);
- t = rtnl_dereference(t->next);
+
+ t = rtnl_net_dereference(net, t->next);
}
}
- t = rtnl_dereference(ip6n->tnls_wc[0]);
+ t = rtnl_net_dereference(net, ip6n->tnls_wc[0]);
while (t) {
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
if (!net_eq(dev_net(t->dev), net))
unregister_netdevice_queue(t->dev, list);
- t = rtnl_dereference(t->next);
+
+ t = rtnl_net_dereference(net, t->next);
}
}
@@ -2261,7 +2268,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
- ip6n->fb_tnl_dev->netns_local = true;
+ ip6n->fb_tnl_dev->netns_immutable = true;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
@@ -2282,19 +2289,9 @@ err_alloc_dev:
return err;
}
-static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list,
- struct list_head *dev_to_kill)
-{
- struct net *net;
-
- ASSERT_RTNL();
- list_for_each_entry(net, net_list, exit_list)
- ip6_tnl_destroy_tunnels(net, dev_to_kill);
-}
-
static struct pernet_operations ip6_tnl_net_ops = {
.init = ip6_tnl_init_net,
- .exit_batch_rtnl = ip6_tnl_exit_batch_rtnl,
+ .exit_rtnl = ip6_tnl_exit_rtnl_net,
.id = &ip6_tnl_net_id,
.size = sizeof(struct ip6_tnl_net),
};
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 590737c27537..40464a88bca6 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -45,6 +45,7 @@
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/netdev_lock.h>
#include <linux/etherdevice.h>
#define IP6_VTI_HASH_SIZE_SHIFT 5
@@ -177,8 +178,7 @@ vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t)
static int vti6_tnl_create2(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
- struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+ struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
int err;
dev->rtnl_link_ops = &vti6_link_ops;
@@ -925,7 +925,6 @@ static inline int vti6_dev_init_gen(struct net_device *dev)
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
- t->net = dev_net(dev);
netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
netdev_lockdep_set_classes(dev);
return 0;
@@ -958,6 +957,7 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev)
struct net *net = dev_net(dev);
struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+ t->net = net;
t->parms.proto = IPPROTO_IPV6;
rcu_assign_pointer(ip6n->tnls_wc[0], t);
@@ -997,17 +997,20 @@ static void vti6_netlink_parms(struct nlattr *data[],
parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
}
-static int vti6_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
+static int vti6_newlink(struct net_device *dev,
+ struct rtnl_newlink_params *params,
struct netlink_ext_ack *extack)
{
- struct net *net = dev_net(dev);
+ struct nlattr **data = params->data;
struct ip6_tnl *nt;
+ struct net *net;
+ net = params->link_net ? : dev_net(dev);
nt = netdev_priv(dev);
vti6_netlink_parms(data, &nt->parms);
nt->parms.proto = IPPROTO_IPV6;
+ nt->net = net;
if (vti6_locate(net, &nt->parms, 0))
return -EEXIST;
@@ -1109,21 +1112,21 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
.get_link_net = ip6_tnl_get_link_net,
};
-static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n,
- struct list_head *list)
+static void __net_exit vti6_exit_rtnl_net(struct net *net, struct list_head *list)
{
- int h;
+ struct vti6_net *ip6n = net_generic(net, vti6_net_id);
struct ip6_tnl *t;
+ int h;
for (h = 0; h < IP6_VTI_HASH_SIZE; h++) {
- t = rtnl_dereference(ip6n->tnls_r_l[h]);
+ t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]);
while (t) {
unregister_netdevice_queue(t->dev, list);
- t = rtnl_dereference(t->next);
+ t = rtnl_net_dereference(net, t->next);
}
}
- t = rtnl_dereference(ip6n->tnls_wc[0]);
+ t = rtnl_net_dereference(net, ip6n->tnls_wc[0]);
if (t)
unregister_netdevice_queue(t->dev, list);
}
@@ -1167,22 +1170,9 @@ err_alloc_dev:
return err;
}
-static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list,
- struct list_head *dev_to_kill)
-{
- struct vti6_net *ip6n;
- struct net *net;
-
- ASSERT_RTNL();
- list_for_each_entry(net, net_list, exit_list) {
- ip6n = net_generic(net, vti6_net_id);
- vti6_destroy_tunnels(ip6n, dev_to_kill);
- }
-}
-
static struct pernet_operations vti6_net_ops = {
.init = vti6_init_net,
- .exit_batch_rtnl = vti6_exit_batch_rtnl,
+ .exit_rtnl = vti6_exit_rtnl_net,
.id = &vti6_net_id,
.size = sizeof(struct vti6_net),
};
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 535e9f72514c..3276cde5ebd7 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -108,11 +108,6 @@ 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_initialized(net);
-}
-
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
@@ -306,11 +301,6 @@ 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)
{
@@ -416,7 +406,7 @@ static void ip6mr_free_table(struct mr_table *mrt)
{
struct net *net = read_pnet(&mrt->net);
- WARN_ON_ONCE(!ip6mr_can_free_table(net));
+ WARN_ON_ONCE(!mr_can_free_table(net));
timer_shutdown_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
@@ -668,7 +658,7 @@ static void reg_vif_setup(struct net_device *dev)
dev->flags = IFF_NOARP;
dev->netdev_ops = &reg_vif_netdev_ops;
dev->needs_free_netdev = true;
- dev->netns_local = true;
+ dev->netns_immutable = true;
}
static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
@@ -1526,7 +1516,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
}
}
if (list_empty(&mrt->mfc_unres_queue))
- del_timer(&mrt->ipmr_expire_timer);
+ timer_delete(&mrt->ipmr_expire_timer);
spin_unlock_bh(&mfc_unres_lock);
if (found) {
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 8699d1a188dc..ecb5c4b8518f 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1680,7 +1680,7 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
{
struct net_device *dev = skb->dev;
- struct net *net = dev_net(dev);
+ struct net *net = dev_net_rcu(dev);
struct sock *sk = net->ipv6.ndisc_sk;
int optlen = 0;
struct inet_peer *peer;
@@ -1695,8 +1695,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
bool ret;
- if (netif_is_l3_master(skb->dev)) {
- dev = dev_get_by_index_rcu(dev_net(skb->dev), IPCB(skb)->iif);
+ if (netif_is_l3_master(dev)) {
+ dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
if (!dev)
return;
}
@@ -1734,10 +1734,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
goto release;
}
- rcu_read_lock();
peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
- rcu_read_unlock();
if (!ret)
goto release;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 581ce055bf52..4541836ee3da 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -164,20 +164,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct ip6_fraglist_iter iter;
struct sk_buff *frag2;
- if (first_len - hlen > mtu ||
- skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
+ if (first_len - hlen > mtu)
goto blackhole;
- if (skb_cloned(skb))
+ if (skb_cloned(skb) ||
+ skb_headroom(skb) < (hroom + sizeof(struct frag_hdr)))
goto slow_path;
skb_walk_frags(skb, frag2) {
- if (frag2->len > mtu ||
- skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
+ if (frag2->len > mtu)
goto blackhole;
/* Partially cloned skb? */
- if (skb_shared(frag2))
+ if (skb_shared(frag2) ||
+ skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr)))
goto slow_path;
}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7d5602950ae7..d585ac3c1113 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -292,7 +292,7 @@ ip6t_do_table(void *priv, struct sk_buff *skb,
* but it is no problem since absolute verdict is issued by these.
*/
if (static_key_false(&xt_tee_enabled))
- jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated);
+ jumpstack += private->stacksize * current->in_nf_duplicate;
e = get_entry(table_base, private->hook_entry[hook]);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 4120e67a8ce6..d6bd8f7079bb 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -123,7 +123,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
#endif
static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
- struct sk_buff *prev_tail, struct net_device *dev);
+ struct sk_buff *prev_tail, struct net_device *dev,
+ int *refs);
static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
@@ -167,7 +168,8 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
- const struct frag_hdr *fhdr, int nhoff)
+ const struct frag_hdr *fhdr, int nhoff,
+ int *refs)
{
unsigned int payload_len;
struct net_device *dev;
@@ -221,7 +223,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
* this case. -DaveM
*/
pr_debug("end of fragment not rounded to 8 bytes.\n");
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
return -EPROTO;
}
if (end > fq->q.len) {
@@ -287,7 +289,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
- err = nf_ct_frag6_reasm(fq, skb, prev, dev);
+ err = nf_ct_frag6_reasm(fq, skb, prev, dev, refs);
skb->_skb_refdst = orefdst;
/* After queue has assumed skb ownership, only 0 or
@@ -301,7 +303,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
return -EINPROGRESS;
insert_error:
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
err:
skb_dst_drop(skb);
return -EINVAL;
@@ -315,13 +317,14 @@ err:
* the last and the first frames arrived and all the bits are here.
*/
static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
- struct sk_buff *prev_tail, struct net_device *dev)
+ struct sk_buff *prev_tail, struct net_device *dev,
+ int *refs)
{
void *reasm_data;
int payload_len;
u8 ecn;
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
@@ -372,7 +375,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
return 0;
err:
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
return -EINVAL;
}
@@ -447,6 +450,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
struct frag_hdr *fhdr;
struct frag_queue *fq;
struct ipv6hdr *hdr;
+ int refs = 0;
u8 prevhdr;
/* Jumbo payload inhibits frag. header */
@@ -473,23 +477,26 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
hdr = ipv6_hdr(skb);
fhdr = (struct frag_hdr *)skb_transport_header(skb);
+ rcu_read_lock();
fq = fq_find(net, fhdr->identification, user, hdr,
skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
+ rcu_read_unlock();
pr_debug("Can't find and can't create new queue\n");
return -ENOMEM;
}
spin_lock_bh(&fq->q.lock);
- ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff);
+ ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff, &refs);
if (ret == -EPROTO) {
skb->transport_header = savethdr;
ret = 0;
}
spin_unlock_bh(&fq->q.lock);
- inet_frag_put(&fq->q);
+ rcu_read_unlock();
+ inet_frag_putn(&fq->q, refs);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 0c39c77fe8a8..b903c62c00c9 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -48,7 +48,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
const struct in6_addr *gw, int oif)
{
local_bh_disable();
- if (this_cpu_read(nf_skb_duplicated))
+ if (current->in_nf_duplicate)
goto out;
skb = pskb_copy(skb, GFP_ATOMIC);
if (skb == NULL)
@@ -64,9 +64,9 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
--iph->hop_limit;
}
if (nf_dup_ipv6_route(net, skb, gw, oif)) {
- __this_cpu_write(nf_skb_duplicated, true);
+ current->in_nf_duplicate = true;
ip6_local_out(net, skb->sk, skb);
- __this_cpu_write(nf_skb_duplicated, false);
+ current->in_nf_duplicate = false;
} else {
kfree_skb(skb);
}
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index a7690ec62325..9ea5ef56cb27 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -103,6 +103,10 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
struct sk_buff *data_skb = NULL;
int doff = 0;
int thoff = 0, tproto;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn const *ct;
+#endif
tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
if (tproto < 0) {
@@ -136,6 +140,25 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
return NULL;
}
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ /* Do the lookup with the original socket address in
+ * case this is a reply packet of an established
+ * SNAT-ted connection.
+ */
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct &&
+ ((tproto != IPPROTO_ICMPV6 &&
+ ctinfo == IP_CT_ESTABLISHED_REPLY) ||
+ (tproto == IPPROTO_ICMPV6 &&
+ ctinfo == IP_CT_RELATED_REPLY)) &&
+ (ct->status & IPS_SRC_NAT_DONE)) {
+ daddr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
+ dport = (tproto == IPPROTO_TCP) ?
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
+ }
+#endif
+
return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
sport, dport, indev);
}
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c9f1634b3838..421036a3605b 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -50,6 +50,7 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
fl6->flowi6_mark = pkt->skb->mark;
fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK;
+ fl6->flowi6_l3mdev = nft_fib_l3mdev_master_ifindex_rcu(pkt, dev);
return lookup_flags;
}
@@ -73,8 +74,6 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
else if (priv->flags & NFTA_FIB_F_OIF)
dev = nft_out(pkt);
- fl6.flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev);
-
nft_fib6_flowi_init(&fl6, priv, pkt, dev, iph);
if (dev && nf_ipv6_chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
@@ -158,6 +157,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
{
const struct nft_fib *priv = nft_expr_priv(expr);
int noff = skb_network_offset(pkt->skb);
+ const struct net_device *found = NULL;
const struct net_device *oif = NULL;
u32 *dest = &regs->data[priv->dreg];
struct ipv6hdr *iph, _iph;
@@ -165,11 +165,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
.flowi6_iif = LOOPBACK_IFINDEX,
.flowi6_proto = pkt->tprot,
.flowi6_uid = sock_net_uid(nft_net(pkt), NULL),
- .flowi6_l3mdev = l3mdev_master_ifindex_rcu(nft_in(pkt)),
};
struct rt6_info *rt;
int lookup_flags;
+ if (nft_fib_can_skip(pkt)) {
+ nft_fib_store_result(dest, priv, nft_in(pkt));
+ return;
+ }
+
if (priv->flags & NFTA_FIB_F_IIF)
oif = nft_in(pkt);
else if (priv->flags & NFTA_FIB_F_OIF)
@@ -181,17 +185,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
return;
}
- lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
-
- if (nft_hook(pkt) == NF_INET_PRE_ROUTING ||
- nft_hook(pkt) == NF_INET_INGRESS) {
- if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) ||
- nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) {
- nft_fib_store_result(dest, priv, nft_in(pkt));
- return;
- }
+ if (nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) {
+ nft_fib_store_result(dest, priv, nft_in(pkt));
+ return;
}
+ lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph);
+
*dest = 0;
rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, pkt->skb,
lookup_flags);
@@ -202,11 +202,15 @@ 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 &&
- l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
- goto put_rt_err;
+ if (!oif) {
+ found = rt->rt6i_idev->dev;
+ } else {
+ if (oif == rt->rt6i_idev->dev ||
+ l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex)
+ found = oif;
+ }
- nft_fib_store_result(dest, priv, rt->rt6i_idev->dev);
+ nft_fib_store_result(dest, priv, found);
put_rt_err:
ip6_rt_put(rt);
}
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 46b8adf6e7f8..84d90dd8b3f0 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -119,9 +119,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
return -EINVAL;
ipcm6_init_sk(&ipc6, sk);
- ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
- ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
- ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
fl6.flowi6_oif = oif;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a45aba090aa4..fda640ebd53f 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -769,19 +769,16 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
hdrincl = inet_test_bit(HDRINCL, sk);
+ ipcm6_init_sk(&ipc6, sk);
+
/*
* Get and verify the address.
*/
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
+ fl6.flowi6_mark = ipc6.sockc.mark;
fl6.flowi6_uid = sk->sk_uid;
- ipcm6_init(&ipc6);
- ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
- ipc6.sockc.mark = fl6.flowi6_mark;
- ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
-
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
@@ -891,9 +888,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (hdrincl)
fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
@@ -904,9 +898,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (ipc6.hlimit < 0)
ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (ipc6.dontfrag < 0)
- ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
-
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index a48be617a8ab..49740898bc13 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -68,7 +68,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
- struct sk_buff *prev_tail, struct net_device *dev);
+ struct sk_buff *prev_tail, struct net_device *dev,
+ int *refs);
static void ip6_frag_expire(struct timer_list *t)
{
@@ -105,7 +106,7 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
struct frag_hdr *fhdr, int nhoff,
- u32 *prob_offset)
+ u32 *prob_offset, int *refs)
{
struct net *net = dev_net(skb_dst(skb)->dev);
int offset, end, fragsize;
@@ -220,7 +221,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
unsigned long orefdst = skb->_skb_refdst;
skb->_skb_refdst = 0UL;
- err = ip6_frag_reasm(fq, skb, prev_tail, dev);
+ err = ip6_frag_reasm(fq, skb, prev_tail, dev, refs);
skb->_skb_refdst = orefdst;
return err;
}
@@ -238,7 +239,7 @@ insert_error:
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASM_OVERLAPS);
discard_fq:
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
err:
@@ -254,7 +255,8 @@ err:
* the last and the first frames arrived and all the bits are here.
*/
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
- struct sk_buff *prev_tail, struct net_device *dev)
+ struct sk_buff *prev_tail, struct net_device *dev,
+ int *refs)
{
struct net *net = fq->q.fqdir->net;
unsigned int nhoff;
@@ -262,7 +264,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
int payload_len;
u8 ecn;
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
ecn = ip_frag_ecn_table[fq->ecn];
if (unlikely(ecn == 0xff))
@@ -303,9 +305,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
skb_postpush_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
- rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS);
- rcu_read_unlock();
fq->q.rb_fragments = RB_ROOT;
fq->q.fragments_tail = NULL;
fq->q.last_run_head = NULL;
@@ -317,10 +317,8 @@ out_oversize:
out_oom:
net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
out_fail:
- rcu_read_lock();
__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS);
- rcu_read_unlock();
- inet_frag_kill(&fq->q);
+ inet_frag_kill(&fq->q, refs);
return -1;
}
@@ -377,19 +375,21 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
}
iif = skb->dev ? skb->dev->ifindex : 0;
+ rcu_read_lock();
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
u32 prob_offset = 0;
- int ret;
+ int ret, refs = 0;
spin_lock(&fq->q.lock);
fq->iif = iif;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
- &prob_offset);
+ &prob_offset, &refs);
spin_unlock(&fq->q.lock);
- inet_frag_put(&fq->q);
+ rcu_read_unlock();
+ inet_frag_putn(&fq->q, refs);
if (prob_offset) {
__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
IPSTATS_MIB_INHDRERRORS);
@@ -398,6 +398,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
}
return ret;
}
+ rcu_read_unlock();
__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
kfree_skb(skb);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ef2d23a1e3d5..0143262094b0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -412,12 +412,37 @@ static bool rt6_check_expired(const struct rt6_info *rt)
return false;
}
+static struct fib6_info *
+rt6_multipath_first_sibling_rcu(const struct fib6_info *rt)
+{
+ struct fib6_info *iter;
+ struct fib6_node *fn;
+
+ fn = rcu_dereference(rt->fib6_node);
+ if (!fn)
+ goto out;
+ iter = rcu_dereference(fn->leaf);
+ if (!iter)
+ goto out;
+
+ while (iter) {
+ if (iter->fib6_metric == rt->fib6_metric &&
+ rt6_qualify_for_ecmp(iter))
+ return iter;
+ iter = rcu_dereference(iter->fib6_next);
+ }
+
+out:
+ return NULL;
+}
+
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 *match = res->f6i;
+ struct fib6_info *first, *match = res->f6i;
struct fib6_info *sibling;
+ int hash;
if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
goto out;
@@ -440,16 +465,25 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
return;
}
- if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
+ first = rt6_multipath_first_sibling_rcu(match);
+ if (!first)
goto out;
- list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+ hash = fl6->mp_hash;
+ if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) {
+ if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+ strict) >= 0)
+ match = first;
+ goto out;
+ }
+
+ list_for_each_entry_rcu(sibling, &first->fib6_siblings,
fib6_siblings) {
const struct fib6_nh *nh = sibling->fib6_nh;
int nh_upper_bound;
nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
- if (fl6->mp_hash > nh_upper_bound)
+ if (hash > nh_upper_bound)
continue;
if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
break;
@@ -1737,6 +1771,7 @@ out:
if (!err) {
spin_lock_bh(&f6i->fib6_table->tb6_lock);
fib6_update_sernum(net, f6i);
+ fib6_add_gc_list(f6i);
spin_unlock_bh(&f6i->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
@@ -1785,11 +1820,13 @@ static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
void rt6_flush_exceptions(struct fib6_info *f6i)
{
- if (f6i->nh)
- nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
- f6i);
- else
+ if (f6i->nh) {
+ rcu_read_lock();
+ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i);
+ rcu_read_unlock();
+ } else {
fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
+ }
}
/* Find cached rt in the hash table inside passed in rt
@@ -2457,8 +2494,12 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
hash_keys.basic.ip_proto = fl6->flowi6_proto;
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
- if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
- hash_keys.ports.src = fl6->fl6_sport;
+ if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) {
+ if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+ hash_keys.ports.src = (__force __be16)get_random_u16();
+ else
+ hash_keys.ports.src = fl6->fl6_sport;
+ }
if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
hash_keys.ports.dst = fl6->fl6_dport;
@@ -2512,7 +2553,10 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
hash_keys.addrs.v6addrs.src = fl6->saddr;
hash_keys.addrs.v6addrs.dst = fl6->daddr;
- hash_keys.ports.src = fl6->fl6_sport;
+ if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+ hash_keys.ports.src = (__force __be16)get_random_u16();
+ else
+ hash_keys.ports.src = fl6->fl6_sport;
hash_keys.ports.dst = fl6->fl6_dport;
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
@@ -3644,7 +3688,8 @@ out:
in6_dev_put(idev);
if (err) {
- lwtstate_put(fib6_nh->fib_nh_lws);
+ fib_nh_common_release(&fib6_nh->nh_common);
+ fib6_nh->nh_common.nhc_pcpu_rth_output = NULL;
fib6_nh->fib_nh_lws = NULL;
netdev_put(dev, dev_tracker);
}
@@ -3693,61 +3738,14 @@ void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
}
static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
- gfp_t gfp_flags,
- struct netlink_ext_ack *extack)
+ gfp_t gfp_flags,
+ struct netlink_ext_ack *extack)
{
struct net *net = cfg->fc_nlinfo.nl_net;
- struct fib6_info *rt = NULL;
- struct nexthop *nh = NULL;
struct fib6_table *table;
- struct fib6_nh *fib6_nh;
- int err = -EINVAL;
- int addr_type;
-
- /* RTF_PCPU is an internal flag; can not be set by userspace */
- if (cfg->fc_flags & RTF_PCPU) {
- NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
- goto out;
- }
-
- /* RTF_CACHE is an internal flag; can not be set by userspace */
- if (cfg->fc_flags & RTF_CACHE) {
- NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
- goto out;
- }
-
- if (cfg->fc_type > RTN_MAX) {
- NL_SET_ERR_MSG(extack, "Invalid route type");
- goto out;
- }
-
- if (cfg->fc_dst_len > 128) {
- NL_SET_ERR_MSG(extack, "Invalid prefix length");
- goto out;
- }
- if (cfg->fc_src_len > 128) {
- NL_SET_ERR_MSG(extack, "Invalid source address length");
- goto out;
- }
-#ifndef CONFIG_IPV6_SUBTREES
- if (cfg->fc_src_len) {
- NL_SET_ERR_MSG(extack,
- "Specifying source address requires IPV6_SUBTREES to be enabled");
- goto out;
- }
-#endif
- if (cfg->fc_nh_id) {
- nh = nexthop_find_by_id(net, cfg->fc_nh_id);
- if (!nh) {
- NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
- goto out;
- }
- err = fib6_check_nexthop(nh, cfg, extack);
- if (err)
- goto out;
- }
+ struct fib6_info *rt;
+ int err;
- err = -ENOBUFS;
if (cfg->fc_nlinfo.nlh &&
!(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
table = fib6_get_table(net, cfg->fc_table);
@@ -3758,22 +3756,22 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
} else {
table = fib6_new_table(net, cfg->fc_table);
}
+ if (!table) {
+ err = -ENOBUFS;
+ goto err;
+ }
- if (!table)
- goto out;
-
- err = -ENOMEM;
- rt = fib6_info_alloc(gfp_flags, !nh);
- if (!rt)
- goto out;
+ rt = fib6_info_alloc(gfp_flags, !cfg->fc_nh_id);
+ if (!rt) {
+ err = -ENOMEM;
+ goto err;
+ }
rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
extack);
if (IS_ERR(rt->fib6_metrics)) {
err = PTR_ERR(rt->fib6_metrics);
- /* Do not leave garbage there. */
- rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
- goto out_free;
+ goto free;
}
if (cfg->fc_flags & RTF_ADDRCONF)
@@ -3781,12 +3779,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (cfg->fc_flags & RTF_EXPIRES)
fib6_set_expires(rt, jiffies +
- clock_t_to_jiffies(cfg->fc_expires));
+ clock_t_to_jiffies(cfg->fc_expires));
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
- rt->fib6_protocol = cfg->fc_protocol;
+ rt->fib6_protocol = cfg->fc_protocol;
rt->fib6_table = table;
rt->fib6_metric = cfg->fc_metric;
rt->fib6_type = cfg->fc_type ? : RTN_UNICAST;
@@ -3799,21 +3797,54 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
rt->fib6_src.plen = cfg->fc_src_len;
#endif
- if (nh) {
- if (rt->fib6_src.plen) {
- NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ return rt;
+free:
+ kfree(rt);
+err:
+ return ERR_PTR(err);
+}
+
+static int ip6_route_info_create_nh(struct fib6_info *rt,
+ struct fib6_config *cfg,
+ gfp_t gfp_flags,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = cfg->fc_nlinfo.nl_net;
+ struct fib6_nh *fib6_nh;
+ int err;
+
+ if (cfg->fc_nh_id) {
+ struct nexthop *nh;
+
+ rcu_read_lock();
+
+ nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+ if (!nh) {
+ err = -EINVAL;
+ NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
goto out_free;
}
+
+ err = fib6_check_nexthop(nh, cfg, extack);
+ if (err)
+ goto out_free;
+
if (!nexthop_get(nh)) {
NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+ err = -ENOENT;
goto out_free;
}
+
rt->nh = nh;
fib6_nh = nexthop_fib6_nh(rt->nh);
+
+ rcu_read_unlock();
} else {
+ int addr_type;
+
err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack);
if (err)
- goto out;
+ goto out_release;
fib6_nh = rt->fib6_nh;
@@ -3832,21 +3863,21 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
NL_SET_ERR_MSG(extack, "Invalid source address");
err = -EINVAL;
- goto out;
+ goto out_release;
}
rt->fib6_prefsrc.addr = cfg->fc_prefsrc;
rt->fib6_prefsrc.plen = 128;
- } else
- rt->fib6_prefsrc.plen = 0;
+ }
- return rt;
-out:
+ return 0;
+out_release:
fib6_info_release(rt);
- return ERR_PTR(err);
+ return err;
out_free:
+ rcu_read_unlock();
ip_fib_metrics_put(rt->fib6_metrics);
kfree(rt);
- return ERR_PTR(err);
+ return err;
}
int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
@@ -3859,6 +3890,10 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
if (IS_ERR(rt))
return PTR_ERR(rt);
+ err = ip6_route_info_create_nh(rt, cfg, gfp_flags, extack);
+ if (err)
+ return err;
+
err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack);
fib6_info_release(rt);
@@ -4087,9 +4122,9 @@ static int ip6_route_del(struct fib6_config *cfg,
if (rt->nh) {
if (!fib6_info_hold_safe(rt))
continue;
- rcu_read_unlock();
- return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+ err = __ip6_del_rt(rt, &cfg->fc_nlinfo);
+ break;
}
if (cfg->fc_nh_id)
continue;
@@ -4104,13 +4139,13 @@ static int ip6_route_del(struct fib6_config *cfg,
continue;
if (!fib6_info_hold_safe(rt))
continue;
- rcu_read_unlock();
/* if gateway was specified only delete the one hop */
if (cfg->fc_flags & RTF_GATEWAY)
- return __ip6_del_rt(rt, &cfg->fc_nlinfo);
-
- return __ip6_del_rt_siblings(rt, cfg);
+ err = __ip6_del_rt(rt, &cfg->fc_nlinfo);
+ else
+ err = __ip6_del_rt_siblings(rt, cfg);
+ break;
}
}
rcu_read_unlock();
@@ -4444,6 +4479,53 @@ void rt6_purge_dflt_routers(struct net *net)
rcu_read_unlock();
}
+static int fib6_config_validate(struct fib6_config *cfg,
+ struct netlink_ext_ack *extack)
+{
+ /* RTF_PCPU is an internal flag; can not be set by userspace */
+ if (cfg->fc_flags & RTF_PCPU) {
+ NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
+ goto errout;
+ }
+
+ /* RTF_CACHE is an internal flag; can not be set by userspace */
+ if (cfg->fc_flags & RTF_CACHE) {
+ NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
+ goto errout;
+ }
+
+ if (cfg->fc_type > RTN_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid route type");
+ goto errout;
+ }
+
+ if (cfg->fc_dst_len > 128) {
+ NL_SET_ERR_MSG(extack, "Invalid prefix length");
+ goto errout;
+ }
+
+#ifdef CONFIG_IPV6_SUBTREES
+ if (cfg->fc_src_len > 128) {
+ NL_SET_ERR_MSG(extack, "Invalid source address length");
+ goto errout;
+ }
+
+ if (cfg->fc_nh_id && cfg->fc_src_len) {
+ NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ goto errout;
+ }
+#else
+ if (cfg->fc_src_len) {
+ NL_SET_ERR_MSG(extack,
+ "Specifying source address requires IPV6_SUBTREES to be enabled");
+ goto errout;
+ }
+#endif
+ return 0;
+errout:
+ return -EINVAL;
+}
+
static void rtmsg_to_fib6_config(struct net *net,
struct in6_rtmsg *rtmsg,
struct fib6_config *cfg)
@@ -4479,9 +4561,12 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
rtmsg_to_fib6_config(net, rtmsg, &cfg);
- rtnl_lock();
switch (cmd) {
case SIOCADDRT:
+ err = fib6_config_validate(&cfg, NULL);
+ if (err)
+ break;
+
/* Only do the default setting of fc_metric in route adding */
if (cfg.fc_metric == 0)
cfg.fc_metric = IP6_RT_PRIO_USER;
@@ -4491,7 +4576,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
err = ip6_route_del(&cfg, NULL);
break;
}
- rtnl_unlock();
+
return err;
}
@@ -4581,6 +4666,7 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
.fc_ignore_dev_down = true,
};
struct fib6_info *f6i;
+ int err;
if (anycast) {
cfg.fc_type = RTN_ANYCAST;
@@ -4591,14 +4677,19 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
}
f6i = ip6_route_info_create(&cfg, gfp_flags, extack);
- if (!IS_ERR(f6i)) {
- f6i->dst_nocount = true;
+ if (IS_ERR(f6i))
+ return f6i;
- if (!anycast &&
- (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
- READ_ONCE(idev->cnf.disable_policy)))
- f6i->dst_nopolicy = true;
- }
+ err = ip6_route_info_create_nh(f6i, &cfg, gfp_flags, extack);
+ if (err)
+ return ERR_PTR(err);
+
+ f6i->dst_nocount = true;
+
+ if (!anycast &&
+ (READ_ONCE(net->ipv6.devconf_all->disable_policy) ||
+ READ_ONCE(idev->cnf.disable_policy)))
+ f6i->dst_nopolicy = true;
return f6i;
}
@@ -5013,12 +5104,60 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_FLOWLABEL] = { .type = NLA_BE32 },
};
+static int rtm_to_fib6_multipath_config(struct fib6_config *cfg,
+ struct netlink_ext_ack *extack,
+ bool newroute)
+{
+ struct rtnexthop *rtnh;
+ int remaining;
+
+ remaining = cfg->fc_mp_len;
+ rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+ if (!rtnh_ok(rtnh, remaining)) {
+ NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops");
+ return -EINVAL;
+ }
+
+ do {
+ bool has_gateway = cfg->fc_flags & RTF_GATEWAY;
+ int attrlen = rtnh_attrlen(rtnh);
+
+ if (attrlen > 0) {
+ struct nlattr *nla, *attrs;
+
+ attrs = rtnh_attrs(rtnh);
+ nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+ if (nla) {
+ if (nla_len(nla) < sizeof(cfg->fc_gateway)) {
+ NL_SET_ERR_MSG(extack,
+ "Invalid IPv6 address in RTA_GATEWAY");
+ return -EINVAL;
+ }
+
+ has_gateway = true;
+ }
+ }
+
+ if (newroute && (cfg->fc_nh_id || !has_gateway)) {
+ NL_SET_ERR_MSG(extack,
+ "Device only routes can not be added for IPv6 using the multipath API.");
+ return -EINVAL;
+ }
+
+ rtnh = rtnh_next(rtnh, &remaining);
+ } while (rtnh_ok(rtnh, remaining));
+
+ return lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack);
+}
+
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct rtmsg *rtm;
+ bool newroute = nlh->nlmsg_type == RTM_NEWROUTE;
struct nlattr *tb[RTA_MAX+1];
+ struct rtmsg *rtm;
unsigned int pref;
int err;
@@ -5127,8 +5266,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
- err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
- cfg->fc_mp_len, extack);
+ err = rtm_to_fib6_multipath_config(cfg, extack, newroute);
if (err < 0)
goto errout;
}
@@ -5169,29 +5307,28 @@ errout:
struct rt6_nh {
struct fib6_info *fib6_info;
struct fib6_config r_cfg;
- struct list_head next;
+ struct list_head list;
};
-static int ip6_route_info_append(struct net *net,
- struct list_head *rt6_nh_list,
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
struct fib6_info *rt,
struct fib6_config *r_cfg)
{
struct rt6_nh *nh;
- int err = -EEXIST;
- list_for_each_entry(nh, rt6_nh_list, next) {
+ list_for_each_entry(nh, rt6_nh_list, list) {
/* check if fib6_info already exists */
if (rt6_duplicate_nexthop(nh->fib6_info, rt))
- return err;
+ return -EEXIST;
}
nh = kzalloc(sizeof(*nh), GFP_KERNEL);
if (!nh)
return -ENOMEM;
+
nh->fib6_info = rt;
memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
- list_add_tail(&nh->next, rt6_nh_list);
+ list_add_tail(&nh->list, rt6_nh_list);
return 0;
}
@@ -5247,37 +5384,26 @@ out:
return should_notify;
}
-static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla,
- struct netlink_ext_ack *extack)
-{
- if (nla_len(nla) < sizeof(*gw)) {
- NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY");
- return -EINVAL;
- }
-
- *gw = nla_get_in6_addr(nla);
-
- return 0;
-}
-
static int ip6_route_multipath_add(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
struct fib6_info *rt_notif = NULL, *rt_last = NULL;
struct nl_info *info = &cfg->fc_nlinfo;
+ struct rt6_nh *nh, *nh_safe;
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
- struct fib6_info *rt;
+ LIST_HEAD(rt6_nh_list);
struct rt6_nh *err_nh;
- struct rt6_nh *nh, *nh_safe;
+ struct fib6_info *rt;
__u16 nlflags;
int remaining;
int attrlen;
- int err = 1;
+ int replace;
int nhn = 0;
- int replace = (cfg->fc_nlinfo.nlh &&
- (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
- LIST_HEAD(rt6_nh_list);
+ int err;
+
+ replace = (cfg->fc_nlinfo.nlh &&
+ (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE;
if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND)
@@ -5300,18 +5426,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
if (nla) {
- err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
- extack);
- if (err)
- goto cleanup;
-
+ r_cfg.fc_gateway = nla_get_in6_addr(nla);
r_cfg.fc_flags |= RTF_GATEWAY;
}
- r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
- /* RTA_ENCAP_TYPE length checked in
- * lwtunnel_valid_encap_type_attr
- */
+ r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
if (nla)
r_cfg.fc_encap_type = nla_get_u16(nla);
@@ -5324,18 +5443,16 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
rt = NULL;
goto cleanup;
}
- if (!rt6_qualify_for_ecmp(rt)) {
- err = -EINVAL;
- NL_SET_ERR_MSG(extack,
- "Device only routes can not be added for IPv6 using the multipath API.");
- fib6_info_release(rt);
+
+ err = ip6_route_info_create_nh(rt, &r_cfg, GFP_KERNEL, extack);
+ if (err) {
+ rt = NULL;
goto cleanup;
}
rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1;
- err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
- rt, &r_cfg);
+ err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
if (err) {
fib6_info_release(rt);
goto cleanup;
@@ -5344,12 +5461,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
rtnh = rtnh_next(rtnh, &remaining);
}
- if (list_empty(&rt6_nh_list)) {
- NL_SET_ERR_MSG(extack,
- "Invalid nexthop configuration - no valid nexthops");
- return -EINVAL;
- }
-
/* for add and replace send one notification with all nexthops.
* Skip the notification in fib6_add_rt2node and send one with
* the full route when done
@@ -5362,7 +5473,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
info->skip_notify_kernel = 1;
err_nh = NULL;
- list_for_each_entry(nh, &rt6_nh_list, next) {
+ list_for_each_entry(nh, &rt6_nh_list, list) {
err = __ip6_ins_rt(nh->fib6_info, info, extack);
if (err) {
@@ -5430,16 +5541,16 @@ add_errout:
ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags);
/* Delete routes that were already added */
- list_for_each_entry(nh, &rt6_nh_list, next) {
+ list_for_each_entry(nh, &rt6_nh_list, list) {
if (err_nh == nh)
break;
ip6_route_del(&nh->r_cfg, extack);
}
cleanup:
- list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+ list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, list) {
fib6_info_release(nh->fib6_info);
- list_del(&nh->next);
+ list_del(&nh->list);
kfree(nh);
}
@@ -5471,21 +5582,15 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
if (nla) {
- err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
- extack);
- if (err) {
- last_err = err;
- goto next_rtnh;
- }
-
+ r_cfg.fc_gateway = nla_get_in6_addr(nla);
r_cfg.fc_flags |= RTF_GATEWAY;
}
}
+
err = ip6_route_del(&r_cfg, extack);
if (err)
last_err = err;
-next_rtnh:
rtnh = rtnh_next(rtnh, &remaining);
}
@@ -5502,15 +5607,20 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
- if (cfg.fc_nh_id &&
- !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
- NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
- return -EINVAL;
+ if (cfg.fc_nh_id) {
+ rcu_read_lock();
+ err = !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id);
+ rcu_read_unlock();
+
+ if (err) {
+ NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+ return -EINVAL;
+ }
}
- if (cfg.fc_mp)
+ if (cfg.fc_mp) {
return ip6_route_multipath_del(&cfg, extack);
- else {
+ } else {
cfg.fc_delete_all_nh = 1;
return ip6_route_del(&cfg, extack);
}
@@ -5526,6 +5636,10 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ err = fib6_config_validate(&cfg, extack);
+ if (err)
+ return err;
+
if (cfg.fc_metric == 0)
cfg.fc_metric = IP6_RT_PRIO_USER;
@@ -5990,7 +6104,8 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
struct rtmsg *rtm;
int i, err;
- if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+ rtm = nlmsg_payload(nlh, sizeof(*rtm));
+ if (!rtm) {
NL_SET_ERR_MSG_MOD(extack,
"Invalid header for get route request");
return -EINVAL;
@@ -6000,7 +6115,6 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
rtm_ipv6_policy, extack);
- rtm = nlmsg_data(nlh);
if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) ||
(rtm->rtm_dst_len && rtm->rtm_dst_len != 128) ||
rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope ||
@@ -6215,6 +6329,8 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
err = -ENOBUFS;
seq = info->nlh ? info->nlh->nlmsg_seq : 0;
+ rcu_read_lock();
+
skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
if (!skb)
goto errout;
@@ -6227,10 +6343,14 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
kfree_skb(skb);
goto errout;
}
+
+ rcu_read_unlock();
+
rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
info->nlh, GFP_ATOMIC);
return;
errout:
+ rcu_read_unlock();
rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
}
@@ -6720,9 +6840,9 @@ static void bpf_iter_unregister(void)
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},
+ .doit = inet6_rtm_newroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE,
- .doit = inet6_rtm_delroute},
+ .doit = inet6_rtm_delroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
.doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
};
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 0ac4283acdf2..7c05ac846646 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -262,10 +262,18 @@ static int rpl_input(struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
+ struct lwtunnel_state *lwtst;
struct rpl_lwt *rlwt;
int err;
- rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
+ /* We cannot dereference "orig_dst" once ip6_route_input() or
+ * skb_dst_drop() is called. However, in order to detect a dst loop, we
+ * need the address of its lwtstate. So, save the address of lwtstate
+ * now and use it later as a comparison.
+ */
+ lwtst = orig_dst->lwtstate;
+
+ rlwt = rpl_lwt_lwtunnel(lwtst);
local_bh_disable();
dst = dst_cache_get(&rlwt->cache);
@@ -280,7 +288,9 @@ static int rpl_input(struct sk_buff *skb)
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
- if (!dst->error) {
+
+ /* cache only if we don't create a dst reference loop */
+ if (!dst->error && lwtst != dst->lwtstate) {
local_bh_disable();
dst_cache_set_ip6(&rlwt->cache, dst,
&ipv6_hdr(skb)->saddr);
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index bbf5b84a70fc..f78ecb6ad838 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -40,7 +40,14 @@
#include <net/seg6_hmac.h>
#include <linux/random.h>
-static DEFINE_PER_CPU(char [SEG6_HMAC_RING_SIZE], hmac_ring);
+struct hmac_storage {
+ local_lock_t bh_lock;
+ char hmac_ring[SEG6_HMAC_RING_SIZE];
+};
+
+static DEFINE_PER_CPU(struct hmac_storage, hmac_storage) = {
+ .bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
{
@@ -187,7 +194,8 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
*/
local_bh_disable();
- ring = this_cpu_ptr(hmac_ring);
+ local_lock_nested_bh(&hmac_storage.bh_lock);
+ ring = this_cpu_ptr(hmac_storage.hmac_ring);
off = ring;
/* source address */
@@ -212,6 +220,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
dgsize = __do_hmac(hinfo, ring, plen, tmp_out,
SEG6_HMAC_MAX_DIGESTSIZE);
+ local_unlock_nested_bh(&hmac_storage.bh_lock);
local_bh_enable();
if (dgsize < 0)
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 33833b2064c0..51583461ae29 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -472,10 +472,18 @@ static int seg6_input_core(struct net *net, struct sock *sk,
{
struct dst_entry *orig_dst = skb_dst(skb);
struct dst_entry *dst = NULL;
+ struct lwtunnel_state *lwtst;
struct seg6_lwt *slwt;
int err;
- slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+ /* We cannot dereference "orig_dst" once ip6_route_input() or
+ * skb_dst_drop() is called. However, in order to detect a dst loop, we
+ * need the address of its lwtstate. So, save the address of lwtstate
+ * now and use it later as a comparison.
+ */
+ lwtst = orig_dst->lwtstate;
+
+ slwt = seg6_lwt_lwtunnel(lwtst);
local_bh_disable();
dst = dst_cache_get(&slwt->cache);
@@ -490,7 +498,9 @@ static int seg6_input_core(struct net *net, struct sock *sk,
if (!dst) {
ip6_route_input(skb);
dst = skb_dst(skb);
- if (!dst->error) {
+
+ /* cache only if we don't create a dst reference loop */
+ if (!dst->error && lwtst != dst->lwtstate) {
local_bh_disable();
dst_cache_set_ip6(&slwt->cache, dst,
&ipv6_hdr(skb)->saddr);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 39bd8951bfca..a72dbca9e8fc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -51,6 +51,7 @@
#include <net/dsfield.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/netdev_lock.h>
#include <net/inet_dscp.h>
/*
@@ -201,8 +202,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
static int ipip6_tunnel_create(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
- struct sit_net *sitn = net_generic(net, sit_net_id);
+ struct sit_net *sitn = net_generic(t->net, sit_net_id);
int err;
__dev_addr_set(dev, &t->parms.iph.saddr, 4);
@@ -269,6 +269,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
nt = netdev_priv(dev);
+ nt->net = net;
nt->parms = *parms;
if (ipip6_tunnel_create(dev) < 0)
goto failed_free;
@@ -1449,7 +1450,6 @@ static int ipip6_tunnel_init(struct net_device *dev)
int err;
tunnel->dev = dev;
- tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ipip6_tunnel_bind_dev(dev);
@@ -1550,19 +1550,23 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
}
#endif
-static int ipip6_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
+static int ipip6_newlink(struct net_device *dev,
+ struct rtnl_newlink_params *params,
struct netlink_ext_ack *extack)
{
- struct net *net = dev_net(dev);
+ struct nlattr **data = params->data;
+ struct nlattr **tb = params->tb;
struct ip_tunnel *nt;
struct ip_tunnel_encap ipencap;
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd ip6rd;
#endif
+ struct net *net;
int err;
+ net = params->link_net ? : dev_net(dev);
nt = netdev_priv(dev);
+ nt->net = net;
if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
err = ip_tunnel_encap_setup(nt, &ipencap);
@@ -1800,8 +1804,7 @@ static struct xfrm_tunnel mplsip_handler __read_mostly = {
};
#endif
-static void __net_exit sit_destroy_tunnels(struct net *net,
- struct list_head *head)
+static void __net_exit sit_exit_rtnl_net(struct net *net, struct list_head *head)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
struct net_device *dev, *aux;
@@ -1816,15 +1819,15 @@ static void __net_exit sit_destroy_tunnels(struct net *net,
for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) {
struct ip_tunnel *t;
- t = rtnl_dereference(sitn->tunnels[prio][h]);
+ t = rtnl_net_dereference(net, sitn->tunnels[prio][h]);
while (t) {
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
if (!net_eq(dev_net(t->dev), net))
- unregister_netdevice_queue(t->dev,
- head);
- t = rtnl_dereference(t->next);
+ unregister_netdevice_queue(t->dev, head);
+
+ t = rtnl_net_dereference(net, t->next);
}
}
}
@@ -1856,7 +1859,10 @@ static int __net_init sit_init_net(struct net *net)
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
- sitn->fb_tunnel_dev->netns_local = true;
+ sitn->fb_tunnel_dev->netns_immutable = true;
+
+ t = netdev_priv(sitn->fb_tunnel_dev);
+ t->net = net;
err = register_netdev(sitn->fb_tunnel_dev);
if (err)
@@ -1865,8 +1871,6 @@ static int __net_init sit_init_net(struct net *net)
ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
- t = netdev_priv(sitn->fb_tunnel_dev);
-
strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
return 0;
@@ -1876,19 +1880,9 @@ err_alloc_dev:
return err;
}
-static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list,
- struct list_head *dev_to_kill)
-{
- struct net *net;
-
- ASSERT_RTNL();
- list_for_each_entry(net, net_list, exit_list)
- sit_destroy_tunnels(net, dev_to_kill);
-}
-
static struct pernet_operations sit_net_ops = {
.init = sit_init_net,
- .exit_batch_rtnl = sit_exit_batch_rtnl,
+ .exit_rtnl = sit_exit_rtnl_net,
.id = &sit_net_id,
.size = sizeof(struct sit_net),
};
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2debdf085a3b..e8e68a142649 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -267,6 +267,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6.fl6_sport)
+ fl6.flowi6_flags = FLOWI_FLAG_ANY_SPORT;
fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
@@ -376,7 +378,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net_rcu(skb->dev);
struct request_sock *fastopen;
struct ipv6_pinfo *np;
struct tcp_sock *tp;
@@ -798,6 +800,8 @@ static void tcp_v6_init_req(struct request_sock *req,
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+ ireq->ir_rmt_addr = LOOPBACK4_IPV6;
+ ireq->ir_loc_addr = LOOPBACK4_IPV6;
/* So that link locals have meaning */
if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
@@ -864,16 +868,16 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
int oif, int rst, u8 tclass, __be32 label,
u32 priority, u32 txhash, struct tcp_key *key)
{
- const struct tcphdr *th = tcp_hdr(skb);
- struct tcphdr *t1;
- struct sk_buff *buff;
- struct flowi6 fl6;
- struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
- struct sock *ctl_sk = net->ipv6.tcp_sk;
+ struct net *net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev);
unsigned int tot_len = sizeof(struct tcphdr);
+ struct sock *ctl_sk = net->ipv6.tcp_sk;
+ const struct tcphdr *th = tcp_hdr(skb);
__be32 mrst = 0, *topt;
struct dst_entry *dst;
- __u32 mark = 0;
+ struct sk_buff *buff;
+ struct tcphdr *t1;
+ struct flowi6 fl6;
+ u32 mark = 0;
if (tsecr)
tot_len += TCPOLEN_TSTAMP_ALIGNED;
@@ -997,7 +1001,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
if (!IS_ERR(dst)) {
skb_dst_set(buff, dst);
ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
- tclass & ~INET_ECN_MASK, priority);
+ tclass, priority);
TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
if (rst)
TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -1039,7 +1043,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
if (!sk && !ipv6_unicast_destination(skb))
return;
- net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
+ net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev);
/* Invalid TCP option size or twice included auth */
if (tcp_parse_auth_options(th, &md5_hash_location, &aoh))
return;
@@ -1133,7 +1137,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
trace_tcp_send_reset(sk, skb, reason);
tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
- ipv6_get_dsfield(ipv6h), label, priority, txhash,
+ ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK,
+ label, priority, txhash,
&key);
#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
@@ -1153,11 +1158,16 @@ static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
tclass, label, priority, txhash, key);
}
-static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
+static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb,
+ enum tcp_tw_status tw_status)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
+ u8 tclass = tw->tw_tclass;
struct tcp_key key = {};
+
+ if (tw_status == TCP_TW_ACK_OOW)
+ tclass &= ~INET_ECN_MASK;
#ifdef CONFIG_TCP_AO
struct tcp_ao_info *ao_info;
@@ -1201,7 +1211,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_tw_tsval(tcptw),
READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,
- &key, tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel),
+ &key, tclass, cpu_to_be32(tw->tw_flowlabel),
tw->tw_priority, tw->tw_txhash);
#ifdef CONFIG_TCP_AO
@@ -1277,8 +1287,9 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_nxt,
tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
tcp_rsk_tsval(tcp_rsk(req)),
- READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
- &key, ipv6_get_dsfield(ipv6_hdr(skb)), 0,
+ req->ts_recent, sk->sk_bound_dev_if,
+ &key, ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK,
+ 0,
READ_ONCE(sk->sk_priority),
READ_ONCE(tcp_rsk(req)->txhash));
if (tcp_key_is_ao(&key))
@@ -1451,10 +1462,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
ip6_dst_store(newsk, dst, NULL, NULL);
- newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
newnp->saddr = ireq->ir_v6_loc_addr;
- newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
- newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
@@ -1507,9 +1515,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
tcp_initialize_rcv_mss(newsk);
- newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
- newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
-
#ifdef CONFIG_TCP_MD5SIG
l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
@@ -1735,7 +1740,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff*4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
- TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+ TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th);
TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
TCP_SKB_CB(skb)->sacked = 0;
TCP_SKB_CB(skb)->has_rxtstamp =
@@ -1744,7 +1749,9 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
{
+ struct net *net = dev_net_rcu(skb->dev);
enum skb_drop_reason drop_reason;
+ enum tcp_tw_status tw_status;
int sdif = inet6_sdif(skb);
int dif = inet6_iif(skb);
const struct tcphdr *th;
@@ -1753,7 +1760,6 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
bool refcounted;
int ret;
u32 isn;
- struct net *net = dev_net(skb->dev);
drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
if (skb->pkt_type != PACKET_HOST)
@@ -1832,7 +1838,8 @@ lookup:
th = (const struct tcphdr *)skb->data;
hdr = ipv6_hdr(skb);
tcp_v6_fill_cb(skb, hdr, th);
- nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
+ nsk = tcp_check_req(sk, skb, req, false, &req_stolen,
+ &drop_reason);
} else {
drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
}
@@ -1965,7 +1972,9 @@ do_time_wait:
goto csum_error;
}
- switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) {
+ tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn,
+ &drop_reason);
+ switch (tw_status) {
case TCP_TW_SYN:
{
struct sock *sk2;
@@ -1990,7 +1999,8 @@ do_time_wait:
/* to ACK */
fallthrough;
case TCP_TW_ACK:
- tcp_v6_timewait_ack(sk, skb);
+ case TCP_TW_ACK_OOW:
+ tcp_v6_timewait_ack(sk, skb, tw_status);
break;
case TCP_TW_RST:
tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET);
@@ -2004,7 +2014,7 @@ do_time_wait:
void tcp_v6_early_demux(struct sk_buff *skb)
{
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net_rcu(skb->dev);
const struct ipv6hdr *hdr;
const struct tcphdr *th;
struct sock *sk;
@@ -2061,8 +2071,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = {
.net_header_len = sizeof(struct ipv6hdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
- .addr2sockaddr = inet6_csk_addr2sockaddr,
- .sockaddr_len = sizeof(struct sockaddr_in6),
.mtu_reduced = tcp_v6_mtu_reduced,
};
@@ -2095,8 +2103,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
.net_header_len = sizeof(struct iphdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
- .addr2sockaddr = inet6_csk_addr2sockaddr,
- .sockaddr_len = sizeof(struct sockaddr_in6),
.mtu_reduced = tcp_v4_mtu_reduced,
};
@@ -2192,10 +2198,10 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
icsk_pending == ICSK_TIME_REO_TIMEOUT ||
icsk_pending == ICSK_TIME_LOSS_PROBE) {
timer_active = 1;
- timer_expires = icsk->icsk_timeout;
+ timer_expires = icsk_timeout(icsk);
} else if (icsk_pending == ICSK_TIME_PROBE0) {
timer_active = 4;
- timer_expires = icsk->icsk_timeout;
+ timer_expires = icsk_timeout(icsk);
} else if (timer_pending(&sp->sk_timer)) {
timer_active = 2;
timer_expires = sp->sk_timer.expires;
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index a45bf17cb2a1..a8a04f441e78 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -35,14 +35,14 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
inet6_get_iif_sdif(skb, &iif, &sdif);
hdr = skb_gro_network_header(skb);
- net = dev_net(skb->dev);
+ net = dev_net_rcu(skb->dev);
sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
&hdr->saddr, th->source,
&hdr->daddr, ntohs(th->dest),
iif, sdif);
NAPI_GRO_CB(skb)->is_flist = !sk;
if (sk)
- sock_put(sk);
+ sock_gen_put(sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
}
@@ -94,14 +94,23 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
}
static void __tcpv6_gso_segment_csum(struct sk_buff *seg,
+ struct in6_addr *oldip,
+ const struct in6_addr *newip,
__be16 *oldport, __be16 newport)
{
- struct tcphdr *th;
+ struct tcphdr *th = tcp_hdr(seg);
+
+ if (!ipv6_addr_equal(oldip, newip)) {
+ inet_proto_csum_replace16(&th->check, seg,
+ oldip->s6_addr32,
+ newip->s6_addr32,
+ true);
+ *oldip = *newip;
+ }
if (*oldport == newport)
return;
- th = tcp_hdr(seg);
inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
*oldport = newport;
}
@@ -129,10 +138,10 @@ static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs)
th2 = tcp_hdr(seg);
iph2 = ipv6_hdr(seg);
- iph2->saddr = iph->saddr;
- iph2->daddr = iph->daddr;
- __tcpv6_gso_segment_csum(seg, &th2->source, th->source);
- __tcpv6_gso_segment_csum(seg, &th2->dest, th->dest);
+ __tcpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+ &th2->source, th->source);
+ __tcpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+ &th2->dest, th->dest);
}
return segs;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c6ea438b5c75..7317f8e053f1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/ip6_tunnel.h>
+#include <net/udp_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
@@ -586,7 +587,7 @@ csum_copy_err:
SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
@@ -1494,11 +1495,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int is_udplite = IS_UDPLITE(sk);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
- ipcm6_init(&ipc6);
+ ipcm6_init_sk(&ipc6, sk);
ipc6.gso_size = READ_ONCE(up->gso_size);
- ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
- ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
- ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
/* destination address check */
if (sin6) {
@@ -1704,9 +1702,6 @@ do_udp_sendmsg:
security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
- if (ipc6.tclass < 0)
- ipc6.tclass = np->tclass;
-
fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);
dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
@@ -1752,8 +1747,6 @@ back_from_confirm:
WRITE_ONCE(up->pending, AF_INET6);
do_append_data:
- if (ipc6.dontfrag < 0)
- ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
up->len += ulen;
err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
&ipc6, fl6, dst_rt6_info(dst),
@@ -1833,6 +1826,7 @@ void udpv6_destroy_sock(struct sock *sk)
if (udp_test_bit(ENCAP_ENABLED, sk)) {
static_branch_dec(&udpv6_encap_needed_key);
udp_encap_disable();
+ udp_tunnel_cleanup_gro(sk);
}
}
}
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b41152dd4246..d8445ac1b2e4 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -117,9 +117,14 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
__be16 dport)
{
const struct ipv6hdr *iph = skb_gro_network_header(skb);
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net_rcu(skb->dev);
+ struct sock *sk;
int iif, sdif;
+ sk = udp_tunnel_sk(net, true);
+ if (sk && dport == htons(sk->sk_num))
+ return sk;
+
inet6_get_iif_sdif(skb, &iif, &sdif);
return __udp6_lib_lookup(net, &iph->saddr, sport,
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 4abc5e9d6322..841c81abaaf4 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
int offset = skb_gro_offset(skb);
const struct net_offload *ops;
struct sk_buff *pp = NULL;
- int ret;
+ int len, dlen;
+ __u8 *udpdata;
+ __be32 *udpdata32;
if (skb->protocol == htons(ETH_P_IP))
return xfrm4_gro_udp_encap_rcv(sk, head, skb);
- offset = offset - sizeof(struct udphdr);
-
- if (!pskb_pull(skb, offset))
+ len = skb->len - offset;
+ dlen = offset + min(len, 8);
+ udpdata = skb_gro_header(skb, dlen, offset);
+ udpdata32 = (__be32 *)udpdata;
+ if (unlikely(!udpdata))
return NULL;
rcu_read_lock();
@@ -194,11 +198,10 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
if (!ops || !ops->callbacks.gro_receive)
goto out;
- ret = __xfrm6_udp_encap_rcv(sk, skb, false);
- if (ret)
+ /* check if it is a keepalive or IKE packet */
+ if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0)
goto out;
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->proto = IPPROTO_UDP;
pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
@@ -208,7 +211,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head,
out:
rcu_read_unlock();
- skb_push(skb, offset);
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 1;