aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c9
-rw-r--r--net/ipv4/devinet.c30
-rw-r--r--net/ipv4/fib_frontend.c22
-rw-r--r--net/ipv4/fib_semantics.c15
-rw-r--r--net/ipv4/inet_connection_sock.c36
-rw-r--r--net/ipv4/inetpeer.c11
-rw-r--r--net/ipv4/ip_gre.c22
-rw-r--r--net/ipv4/ip_tunnel.c12
-rw-r--r--net/ipv4/ip_vti.c7
-rw-r--r--net/ipv4/ipip.c7
-rw-r--r--net/ipv4/ipmr.c261
-rw-r--r--net/ipv4/sysctl_net_ipv4.c60
-rw-r--r--net/ipv4/tcp.c6
-rw-r--r--net/ipv4/tcp_fastopen.c105
-rw-r--r--net/ipv4/tcp_input.c33
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv4/tcp_metrics.c14
-rw-r--r--net/ipv4/tcp_vegas.c2
-rw-r--r--net/ipv4/udp.c3
19 files changed, 463 insertions, 202 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e31108e5ef79..43a1bbed7a42 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
unsigned char old_state;
- int err;
+ int err, tcp_fastopen;
lock_sock(sk);
@@ -217,11 +217,12 @@ int inet_listen(struct socket *sock, int backlog)
* because the socket was in TCP_LISTEN state previously but
* was shutdown() rather than close().
*/
- if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
- (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+ tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
+ (tcp_fastopen & TFO_SERVER_ENABLE) &&
!inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
fastopen_queue_tune(sk, backlog);
- tcp_fastopen_init_key_once(true);
+ tcp_fastopen_init_key_once(sock_net(sk));
}
err = inet_csk_listen_start(sk, backlog);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7adc0616599..7ce22a2c07ce 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa)
*/
struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
{
- u32 hash = inet_addr_hash(net, addr);
struct net_device *result = NULL;
struct in_ifaddr *ifa;
rcu_read_lock();
- hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
- if (ifa->ifa_local == addr) {
- struct net_device *dev = ifa->ifa_dev->dev;
-
- if (!net_eq(dev_net(dev), net))
- continue;
- result = dev;
- break;
- }
- }
- if (!result) {
+ ifa = inet_lookup_ifaddr_rcu(net, addr);
+ if (!ifa) {
struct flowi4 fl4 = { .daddr = addr };
struct fib_result res = { 0 };
struct fib_table *local;
@@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
!fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
res.type == RTN_LOCAL)
result = FIB_RES_DEV(res);
+ } else {
+ result = ifa->ifa_dev->dev;
}
if (result && devref)
dev_hold(result);
@@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
}
EXPORT_SYMBOL(__ip_dev_find);
+/* called under RCU lock */
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
+{
+ u32 hash = inet_addr_hash(net, addr);
+ struct in_ifaddr *ifa;
+
+ hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
+ if (ifa->ifa_local == addr &&
+ net_eq(dev_net(ifa->ifa_dev->dev), net))
+ return ifa;
+
+ return NULL;
+}
+
static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 37819ab4cc74..f02819134ba2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -345,9 +345,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
if (res.type != RTN_UNICAST &&
(res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
goto e_inval;
- if (!rpf && !fib_num_tclassid_users(net) &&
- (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
- goto last_resort;
fib_combine_itag(itag, &res);
dev_match = false;
@@ -402,13 +399,26 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
struct in_device *idev, u32 *itag)
{
int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
+ struct net *net = dev_net(dev);
- if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
- IN_DEV_ACCEPT_LOCAL(idev) &&
+ if (!r && !fib_num_tclassid_users(net) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
+ if (IN_DEV_ACCEPT_LOCAL(idev))
+ goto ok;
+ /* if no local routes are added from user space we can check
+ * for local addresses looking-up the ifaddr table
+ */
+ if (net->ipv4.fib_has_custom_local_routes)
+ goto full_check;
+ if (inet_lookup_ifaddr_rcu(net, src))
+ return -EINVAL;
+
+ok:
*itag = 0;
return 0;
}
+
+full_check:
return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
}
@@ -759,6 +769,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
}
err = fib_table_insert(net, tb, &cfg, extack);
+ if (!err && cfg.fc_type == RTN_LOCAL)
+ net->ipv4.fib_has_custom_local_routes = true;
errout:
return err;
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 57a5d48acee8..467b3c15395f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -601,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi)
atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
} endfor_nexthops(fi);
}
-
-static inline void fib_add_weight(struct fib_info *fi,
- const struct fib_nh *nh)
-{
- fi->fib_weight += nh->nh_weight;
-}
-
#else /* CONFIG_IP_ROUTE_MULTIPATH */
#define fib_rebalance(fi) do { } while (0)
-#define fib_add_weight(fi, nh) do { } while (0)
#endif /* CONFIG_IP_ROUTE_MULTIPATH */
@@ -774,8 +766,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
* |
* |-> {local prefix} (terminal node)
*/
-static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
- struct fib_nh *nh, struct netlink_ext_ack *extack)
+static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
+ struct netlink_ext_ack *extack)
{
int err = 0;
struct net *net;
@@ -1258,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
int linkdown = 0;
change_nexthops(fi) {
- err = fib_check_nh(cfg, fi, nexthop_nh, extack);
+ err = fib_check_nh(cfg, nexthop_nh, extack);
if (err != 0)
goto failure;
if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
@@ -1275,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
change_nexthops(fi) {
fib_info_update_nh_saddr(net, nexthop_nh);
- fib_add_weight(fi, nexthop_nh);
} endfor_nexthops(fi)
fib_rebalance(fi);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c039c937ba90..8a91ebbf0c01 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -39,11 +39,11 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg);
* IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
* and 0.0.0.0 equals to 0.0.0.0 only
*/
-static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
- const struct in6_addr *sk2_rcv_saddr6,
- __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk1_ipv6only, bool sk2_ipv6only,
- bool match_wildcard)
+static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
+ const struct in6_addr *sk2_rcv_saddr6,
+ __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+ bool sk1_ipv6only, bool sk2_ipv6only,
+ bool match_wildcard)
{
int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
@@ -52,29 +52,29 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
- return 1;
+ return true;
if (!sk1_rcv_saddr || !sk2_rcv_saddr)
return match_wildcard;
}
- return 0;
+ return false;
}
if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
- return 1;
+ return true;
if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
- return 1;
+ return true;
if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
!(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
- return 1;
+ return true;
if (sk2_rcv_saddr6 &&
ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
- return 1;
+ return true;
- return 0;
+ return false;
}
#endif
@@ -82,20 +82,20 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
* match_wildcard == false: addresses must be exactly the same, i.e.
* 0.0.0.0 only equals to 0.0.0.0
*/
-static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk2_ipv6only, bool match_wildcard)
+static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
+ bool sk2_ipv6only, bool match_wildcard)
{
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
- return 1;
+ return true;
if (!sk1_rcv_saddr || !sk2_rcv_saddr)
return match_wildcard;
}
- return 0;
+ return false;
}
-int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
- bool match_wildcard)
+bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
+ bool match_wildcard)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b20c8ac64081..914d56928578 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -284,14 +284,17 @@ EXPORT_SYMBOL(inet_peer_xrlim_allow);
void inetpeer_invalidate_tree(struct inet_peer_base *base)
{
- struct inet_peer *p, *n;
+ struct rb_node *p = rb_first(&base->rb_root);
- rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) {
- inet_putpeer(p);
+ while (p) {
+ struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node);
+
+ p = rb_next(p);
+ rb_erase(&peer->rb_node, &base->rb_root);
+ inet_putpeer(peer);
cond_resched();
}
- base->rb_root = RB_ROOT;
base->total = 0;
}
EXPORT_SYMBOL(inetpeer_invalidate_tree);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 467e44d7587d..dc2317776499 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1011,15 +1011,14 @@ static int __net_init ipgre_init_net(struct net *net)
return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
}
-static void __net_exit ipgre_exit_net(struct net *net)
+static void __net_exit ipgre_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
- ip_tunnel_delete_net(itn, &ipgre_link_ops);
+ ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops);
}
static struct pernet_operations ipgre_net_ops = {
.init = ipgre_init_net,
- .exit = ipgre_exit_net,
+ .exit_batch = ipgre_exit_batch_net,
.id = &ipgre_net_id,
.size = sizeof(struct ip_tunnel_net),
};
@@ -1542,15 +1541,14 @@ static int __net_init ipgre_tap_init_net(struct net *net)
return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0");
}
-static void __net_exit ipgre_tap_exit_net(struct net *net)
+static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
- ip_tunnel_delete_net(itn, &ipgre_tap_ops);
+ ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops);
}
static struct pernet_operations ipgre_tap_net_ops = {
.init = ipgre_tap_init_net,
- .exit = ipgre_tap_exit_net,
+ .exit_batch = ipgre_tap_exit_batch_net,
.id = &gre_tap_net_id,
.size = sizeof(struct ip_tunnel_net),
};
@@ -1561,16 +1559,14 @@ static int __net_init erspan_init_net(struct net *net)
&erspan_link_ops, "erspan0");
}
-static void __net_exit erspan_exit_net(struct net *net)
+static void __net_exit erspan_exit_batch_net(struct list_head *net_list)
{
- struct ip_tunnel_net *itn = net_generic(net, erspan_net_id);
-
- ip_tunnel_delete_net(itn, &erspan_link_ops);
+ ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops);
}
static struct pernet_operations erspan_net_ops = {
.init = erspan_init_net,
- .exit = erspan_exit_net,
+ .exit_batch = erspan_exit_batch_net,
.id = &erspan_net_id,
.size = sizeof(struct ip_tunnel_net),
};
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad664ac..fe6fee728ce4 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1061,16 +1061,22 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
}
}
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
+void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
+ struct rtnl_link_ops *ops)
{
+ struct ip_tunnel_net *itn;
+ struct net *net;
LIST_HEAD(list);
rtnl_lock();
- ip_tunnel_destroy(itn, &list, ops);
+ list_for_each_entry(net, net_list, exit_list) {
+ itn = net_generic(net, id);
+ ip_tunnel_destroy(itn, &list, ops);
+ }
unregister_netdevice_many(&list);
rtnl_unlock();
}
-EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
+EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p, __u32 fwmark)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 89453cf62158..58465c0a8682 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -453,15 +453,14 @@ static int __net_init vti_init_net(struct net *net)
return 0;
}
-static void __net_exit vti_exit_net(struct net *net)
+static void __net_exit vti_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- ip_tunnel_delete_net(itn, &vti_link_ops);
+ ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops);
}
static struct pernet_operations vti_net_ops = {
.init = vti_init_net,
- .exit = vti_exit_net,
+ .exit_batch = vti_exit_batch_net,
.id = &vti_net_id,
.size = sizeof(struct ip_tunnel_net),
};
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index fb1ad22b5e29..1e47818e38c7 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -634,15 +634,14 @@ static int __net_init ipip_init_net(struct net *net)
return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
}
-static void __net_exit ipip_exit_net(struct net *net)
+static void __net_exit ipip_exit_batch_net(struct list_head *list_net)
{
- struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
- ip_tunnel_delete_net(itn, &ipip_link_ops);
+ ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
- .exit = ipip_exit_net,
+ .exit_batch = ipip_exit_batch_net,
.id = &ipip_net_id,
.size = sizeof(struct ip_tunnel_net),
};
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c9b3e6e069ae..b3ee01b0551b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -67,6 +67,7 @@
#include <net/fib_rules.h>
#include <linux/netconf.h>
#include <net/nexthop.h>
+#include <net/switchdev.h>
struct ipmr_rule {
struct fib_rule common;
@@ -264,6 +265,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
fib_rules_unregister(net->ipv4.mr_rules_ops);
rtnl_unlock();
}
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+ return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR);
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+ return fib_rules_seq_read(net, RTNL_FAMILY_IPMR);
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+ return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
#else
#define ipmr_for_each_table(mrt, net) \
for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
@@ -298,6 +315,22 @@ static void __net_exit ipmr_rules_exit(struct net *net)
net->ipv4.mrt = NULL;
rtnl_unlock();
}
+
+static int ipmr_rules_dump(struct net *net, struct notifier_block *nb)
+{
+ return 0;
+}
+
+static unsigned int ipmr_rules_seq_read(struct net *net)
+{
+ return 0;
+}
+
+bool ipmr_rule_default(const struct fib_rule *rule)
+{
+ return true;
+}
+EXPORT_SYMBOL(ipmr_rule_default);
#endif
static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -587,6 +620,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
}
#endif
+static int call_ipmr_vif_entry_notifier(struct notifier_block *nb,
+ struct net *net,
+ enum fib_event_type event_type,
+ struct vif_device *vif,
+ vifi_t vif_index, u32 tb_id)
+{
+ struct vif_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .dev = vif->dev,
+ .vif_index = vif_index,
+ .vif_flags = vif->flags,
+ .tb_id = tb_id,
+ };
+
+ return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_vif_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct vif_device *vif,
+ vifi_t vif_index, u32 tb_id)
+{
+ struct vif_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .dev = vif->dev,
+ .vif_index = vif_index,
+ .vif_flags = vif->flags,
+ .tb_id = tb_id,
+ };
+
+ ASSERT_RTNL();
+ net->ipv4.ipmr_seq++;
+ return call_fib_notifiers(net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb,
+ struct net *net,
+ enum fib_event_type event_type,
+ struct mfc_cache *mfc, u32 tb_id)
+{
+ struct mfc_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .mfc = mfc,
+ .tb_id = tb_id
+ };
+
+ return call_fib_notifier(nb, net, event_type, &info.info);
+}
+
+static int call_ipmr_mfc_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct mfc_cache *mfc, u32 tb_id)
+{
+ struct mfc_entry_notifier_info info = {
+ .info = {
+ .family = RTNL_FAMILY_IPMR,
+ .net = net,
+ },
+ .mfc = mfc,
+ .tb_id = tb_id
+ };
+
+ ASSERT_RTNL();
+ net->ipv4.ipmr_seq++;
+ return call_fib_notifiers(net, event_type, &info.info);
+}
+
/**
* vif_delete - Delete a VIF entry
* @notify: Set to 1, if the caller is a notifier_call
@@ -594,6 +703,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
static int vif_delete(struct mr_table *mrt, int vifi, int notify,
struct list_head *head)
{
+ struct net *net = read_pnet(&mrt->net);
struct vif_device *v;
struct net_device *dev;
struct in_device *in_dev;
@@ -603,6 +713,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
v = &mrt->vif_table[vifi];
+ if (VIF_EXISTS(mrt, vifi))
+ call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi,
+ mrt->id);
+
write_lock_bh(&mrt_lock);
dev = v->dev;
v->dev = NULL;
@@ -652,10 +766,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head)
kmem_cache_free(mrt_cachep, c);
}
-static inline void ipmr_cache_free(struct mfc_cache *c)
+void ipmr_cache_free(struct mfc_cache *c)
{
call_rcu(&c->rcu, ipmr_cache_free_rcu);
}
+EXPORT_SYMBOL(ipmr_cache_free);
/* Destroy an unresolved cache entry, killing queued skbs
* and reporting error to netlink readers.
@@ -754,6 +869,9 @@ static int vif_add(struct net *net, struct mr_table *mrt,
struct vifctl *vifc, int mrtsock)
{
int vifi = vifc->vifc_vifi;
+ struct switchdev_attr attr = {
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
+ };
struct vif_device *v = &mrt->vif_table[vifi];
struct net_device *dev;
struct in_device *in_dev;
@@ -828,6 +946,13 @@ static int vif_add(struct net *net, struct mr_table *mrt,
/* Fill in the VIF structures */
+ attr.orig_dev = dev;
+ if (!switchdev_port_attr_get(dev, &attr)) {
+ memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len);
+ v->dev_parent_id.id_len = attr.u.ppid.id_len;
+ } else {
+ v->dev_parent_id.id_len = 0;
+ }
v->rate_limit = vifc->vifc_rate_limit;
v->local = vifc->vifc_lcl_addr.s_addr;
v->remote = vifc->vifc_rmt_addr.s_addr;
@@ -851,6 +976,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
if (vifi+1 > mrt->maxvif)
mrt->maxvif = vifi+1;
write_unlock_bh(&mrt_lock);
+ call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id);
return 0;
}
@@ -949,6 +1075,7 @@ static struct mfc_cache *ipmr_cache_alloc(void)
if (c) {
c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXVIFS;
+ refcount_set(&c->mfc_un.res.refcount, 1);
}
return c;
}
@@ -1150,6 +1277,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
{
+ struct net *net = read_pnet(&mrt->net);
struct mfc_cache *c;
/* The entries are added/deleted only under RTNL */
@@ -1161,8 +1289,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
return -ENOENT;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
list_del_rcu(&c->list);
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
- ipmr_cache_free(c);
+ ipmr_cache_put(c);
return 0;
}
@@ -1189,6 +1318,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c,
+ mrt->id);
mroute_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1238,6 +1369,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
ipmr_cache_resolve(net, mrt, uc, c);
ipmr_cache_free(uc);
}
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id);
mroute_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1245,6 +1377,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
/* Close the multicast socket, and clear the vif tables etc */
static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
+ struct net *net = read_pnet(&mrt->net);
struct mfc_cache *c, *tmp;
LIST_HEAD(list);
int i;
@@ -1263,8 +1396,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
continue;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
list_del_rcu(&c->list);
+ call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c,
+ mrt->id);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
- ipmr_cache_free(c);
+ ipmr_cache_put(c);
}
if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
@@ -1724,10 +1859,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
return dst_output(net, sk, skb);
}
+#ifdef CONFIG_NET_SWITCHDEV
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+ int in_vifi, int out_vifi)
+{
+ struct vif_device *out_vif = &mrt->vif_table[out_vifi];
+ struct vif_device *in_vif = &mrt->vif_table[in_vifi];
+
+ if (!skb->offload_mr_fwd_mark)
+ return false;
+ if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len)
+ return false;
+ return netdev_phys_item_id_same(&out_vif->dev_parent_id,
+ &in_vif->dev_parent_id);
+}
+#else
+static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt,
+ int in_vifi, int out_vifi)
+{
+ return false;
+}
+#endif
+
/* Processing handlers for ipmr_forward */
static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
- struct sk_buff *skb, struct mfc_cache *c, int vifi)
+ int in_vifi, struct sk_buff *skb,
+ struct mfc_cache *c, int vifi)
{
const struct iphdr *iph = ip_hdr(skb);
struct vif_device *vif = &mrt->vif_table[vifi];
@@ -1748,6 +1906,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
goto out_free;
}
+ if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi))
+ goto out_free;
+
if (vif->flags & VIFF_TUNNEL) {
rt = ip_route_output_ports(net, &fl4, NULL,
vif->remote, vif->local,
@@ -1925,8 +2086,8 @@ forward:
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ipmr_queue_xmit(net, mrt, skb2, cache,
- psend);
+ ipmr_queue_xmit(net, mrt, true_vifi,
+ skb2, cache, psend);
}
psend = ct;
}
@@ -1937,9 +2098,10 @@ last_forward:
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
- ipmr_queue_xmit(net, mrt, skb2, cache, psend);
+ ipmr_queue_xmit(net, mrt, true_vifi, skb2,
+ cache, psend);
} else {
- ipmr_queue_xmit(net, mrt, skb, cache, psend);
+ ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend);
return;
}
}
@@ -2156,6 +2318,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
return -EMSGSIZE;
+ if (c->mfc_flags & MFC_OFFLOAD)
+ rtm->rtm_flags |= RTNH_F_OFFLOAD;
+
if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH)))
return -EMSGSIZE;
@@ -3048,14 +3213,87 @@ static const struct net_protocol pim_protocol = {
};
#endif
+static unsigned int ipmr_seq_read(struct net *net)
+{
+ ASSERT_RTNL();
+
+ return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net);
+}
+
+static int ipmr_dump(struct net *net, struct notifier_block *nb)
+{
+ struct mr_table *mrt;
+ int err;
+
+ err = ipmr_rules_dump(net, nb);
+ if (err)
+ return err;
+
+ ipmr_for_each_table(mrt, net) {
+ struct vif_device *v = &mrt->vif_table[0];
+ struct mfc_cache *mfc;
+ int vifi;
+
+ /* Notifiy on table VIF entries */
+ read_lock(&mrt_lock);
+ for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
+ if (!v->dev)
+ continue;
+
+ call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD,
+ v, vifi, mrt->id);
+ }
+ read_unlock(&mrt_lock);
+
+ /* Notify on table MFC entries */
+ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
+ call_ipmr_mfc_entry_notifier(nb, net,
+ FIB_EVENT_ENTRY_ADD, mfc,
+ mrt->id);
+ }
+
+ return 0;
+}
+
+static const struct fib_notifier_ops ipmr_notifier_ops_template = {
+ .family = RTNL_FAMILY_IPMR,
+ .fib_seq_read = ipmr_seq_read,
+ .fib_dump = ipmr_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __net_init ipmr_notifier_init(struct net *net)
+{
+ struct fib_notifier_ops *ops;
+
+ net->ipv4.ipmr_seq = 0;
+
+ ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+ net->ipv4.ipmr_notifier_ops = ops;
+
+ return 0;
+}
+
+static void __net_exit ipmr_notifier_exit(struct net *net)
+{
+ fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops);
+ net->ipv4.ipmr_notifier_ops = NULL;
+}
+
/* Setup for IP multicast routing */
static int __net_init ipmr_net_init(struct net *net)
{
int err;
+ err = ipmr_notifier_init(net);
+ if (err)
+ goto ipmr_notifier_fail;
+
err = ipmr_rules_init(net);
if (err < 0)
- goto fail;
+ goto ipmr_rules_fail;
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
@@ -3072,7 +3310,9 @@ proc_cache_fail:
proc_vif_fail:
ipmr_rules_exit(net);
#endif
-fail:
+ipmr_rules_fail:
+ ipmr_notifier_exit(net);
+ipmr_notifier_fail:
return err;
}
@@ -3082,6 +3322,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
remove_proc_entry("ip_mr_cache", net->proc_net);
remove_proc_entry("ip_mr_vif", net->proc_net);
#endif
+ ipmr_notifier_exit(net);
ipmr_rules_exit(net);
}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0d3c038d7b04..cac8dd309f39 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -251,10 +251,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
return ret;
}
-static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
+static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
+ struct net *net = container_of(table->data, struct net,
+ ipv4.sysctl_tcp_fastopen);
struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
struct tcp_fastopen_context *ctxt;
int ret;
@@ -265,7 +267,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
return -ENOMEM;
rcu_read_lock();
- ctxt = rcu_dereference(tcp_fastopen_ctx);
+ ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctxt)
memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
else
@@ -282,12 +284,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
ret = -EINVAL;
goto bad_key;
}
- /* Generate a dummy secret but don't publish it. This
- * is needed so we don't regenerate a new key on the
- * first invocation of tcp_fastopen_cookie_gen
- */
- tcp_fastopen_init_key_once(false);
- tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+ tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH);
}
bad_key:
@@ -358,11 +355,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ struct net *net = container_of(table->data, struct net,
+ ipv4.sysctl_tcp_fastopen_blackhole_timeout);
int ret;
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (write && ret == 0)
- tcp_fastopen_active_timeout_reset();
+ atomic_set(&net->ipv4.tfo_active_disable_times, 0);
return ret;
}
@@ -401,27 +400,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
- .procname = "tcp_fastopen",
- .data = &sysctl_tcp_fastopen,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "tcp_fastopen_key",
- .mode = 0600,
- .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
- .proc_handler = proc_tcp_fastopen_key,
- },
- {
- .procname = "tcp_fastopen_blackhole_timeout_sec",
- .data = &sysctl_tcp_fastopen_blackhole_timeout,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_tfo_blackhole_detect_timeout,
- .extra1 = &zero,
- },
- {
.procname = "tcp_abort_on_overflow",
.data = &sysctl_tcp_abort_on_overflow,
.maxlen = sizeof(int),
@@ -1085,6 +1063,28 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "tcp_fastopen",
+ .data = &init_net.ipv4.sysctl_tcp_fastopen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "tcp_fastopen_key",
+ .mode = 0600,
+ .data = &init_net.ipv4.sysctl_tcp_fastopen,
+ .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
+ .proc_handler = proc_tcp_fastopen_key,
+ },
+ {
+ .procname = "tcp_fastopen_blackhole_timeout_sec",
+ .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tfo_blackhole_detect_timeout,
+ .extra1 = &zero,
+ },
#ifdef CONFIG_IP_ROUTE_MULTIPATH
{
.procname = "fib_multipath_use_neigh",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402720ab..23225c98d287 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1126,7 +1126,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
- if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+ if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
(uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
@@ -2749,7 +2749,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_FASTOPEN:
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
TCPF_LISTEN))) {
- tcp_fastopen_init_key_once(true);
+ tcp_fastopen_init_key_once(net);
fastopen_queue_tune(sk, val);
} else {
@@ -2759,7 +2759,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_FASTOPEN_CONNECT:
if (val > 1 || val < 0) {
err = -EINVAL;
- } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+ } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
if (sk->sk_state == TCP_CLOSE)
tp->fastopen_connect = val;
else
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e3c33220c418..de470e7e586f 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -9,15 +9,18 @@
#include <net/inetpeer.h>
#include <net/tcp.h>
-int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE;
-
-struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
-
-static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
-
-void tcp_fastopen_init_key_once(bool publish)
+void tcp_fastopen_init_key_once(struct net *net)
{
- static u8 key[TCP_FASTOPEN_KEY_LENGTH];
+ u8 key[TCP_FASTOPEN_KEY_LENGTH];
+ struct tcp_fastopen_context *ctxt;
+
+ rcu_read_lock();
+ ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
+ if (ctxt) {
+ rcu_read_unlock();
+ return;
+ }
+ rcu_read_unlock();
/* tcp_fastopen_reset_cipher publishes the new context
* atomically, so we allow this race happening here.
@@ -25,8 +28,8 @@ void tcp_fastopen_init_key_once(bool publish)
* All call sites of tcp_fastopen_cookie_gen also check
* for a valid cookie, so this is an acceptable risk.
*/
- if (net_get_random_once(key, sizeof(key)) && publish)
- tcp_fastopen_reset_cipher(key, sizeof(key));
+ get_random_bytes(key, sizeof(key));
+ tcp_fastopen_reset_cipher(net, key, sizeof(key));
}
static void tcp_fastopen_ctx_free(struct rcu_head *head)
@@ -37,7 +40,22 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head)
kfree(ctx);
}
-int tcp_fastopen_reset_cipher(void *key, unsigned int len)
+void tcp_fastopen_ctx_destroy(struct net *net)
+{
+ struct tcp_fastopen_context *ctxt;
+
+ spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+ ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+ lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+ rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL);
+ spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
+
+ if (ctxt)
+ call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free);
+}
+
+int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len)
{
int err;
struct tcp_fastopen_context *ctx, *octx;
@@ -61,26 +79,27 @@ error: kfree(ctx);
}
memcpy(ctx->key, key, len);
- spin_lock(&tcp_fastopen_ctx_lock);
+ spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
- octx = rcu_dereference_protected(tcp_fastopen_ctx,
- lockdep_is_held(&tcp_fastopen_ctx_lock));
- rcu_assign_pointer(tcp_fastopen_ctx, ctx);
- spin_unlock(&tcp_fastopen_ctx_lock);
+ octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx,
+ lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock));
+ rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx);
+ spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock);
if (octx)
call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
return err;
}
-static bool __tcp_fastopen_cookie_gen(const void *path,
+static bool __tcp_fastopen_cookie_gen(struct net *net,
+ const void *path,
struct tcp_fastopen_cookie *foc)
{
struct tcp_fastopen_context *ctx;
bool ok = false;
rcu_read_lock();
- ctx = rcu_dereference(tcp_fastopen_ctx);
+ ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctx) {
crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
foc->len = TCP_FASTOPEN_COOKIE_SIZE;
@@ -96,7 +115,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
*
* XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
*/
-static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+static bool tcp_fastopen_cookie_gen(struct net *net,
+ struct request_sock *req,
struct sk_buff *syn,
struct tcp_fastopen_cookie *foc)
{
@@ -104,7 +124,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
const struct iphdr *iph = ip_hdr(syn);
__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
- return __tcp_fastopen_cookie_gen(path, foc);
+ return __tcp_fastopen_cookie_gen(net, path, foc);
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -112,13 +132,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req,
const struct ipv6hdr *ip6h = ipv6_hdr(syn);
struct tcp_fastopen_cookie tmp;
- if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+ if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) {
struct in6_addr *buf = &tmp.addr;
int i;
for (i = 0; i < 4; i++)
buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
- return __tcp_fastopen_cookie_gen(buf, foc);
+ return __tcp_fastopen_cookie_gen(net, buf, foc);
}
}
#endif
@@ -279,25 +299,26 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc)
{
- struct tcp_fastopen_cookie valid_foc = { .len = -1 };
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+ int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ struct tcp_fastopen_cookie valid_foc = { .len = -1 };
struct sock *child;
if (foc->len == 0) /* Client requests a cookie */
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
- if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+ if (!((tcp_fastopen & TFO_SERVER_ENABLE) &&
(syn_data || foc->len >= 0) &&
tcp_fastopen_queue_check(sk))) {
foc->len = -1;
return NULL;
}
- if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+ if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
goto fastopen;
if (foc->len >= 0 && /* Client presents or requests a cookie */
- tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+ tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) &&
foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
foc->len == valid_foc.len &&
!memcmp(foc->val, valid_foc.val, foc->len)) {
@@ -347,7 +368,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
return false;
}
- if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+ if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
cookie->len = -1;
return true;
}
@@ -401,25 +422,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect);
* TFO connection with data exchanges.
*/
-/* Default to 1hr */
-unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60;
-static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0);
-static unsigned long tfo_active_disable_stamp __read_mostly;
-
/* Disable active TFO and record current jiffies and
* tfo_active_disable_times
*/
void tcp_fastopen_active_disable(struct sock *sk)
{
- atomic_inc(&tfo_active_disable_times);
- tfo_active_disable_stamp = jiffies;
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE);
-}
+ struct net *net = sock_net(sk);
-/* Reset tfo_active_disable_times to 0 */
-void tcp_fastopen_active_timeout_reset(void)
-{
- atomic_set(&tfo_active_disable_times, 0);
+ atomic_inc(&net->ipv4.tfo_active_disable_times);
+ net->ipv4.tfo_active_disable_stamp = jiffies;
+ NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
}
/* Calculate timeout for tfo active disable
@@ -428,17 +440,18 @@ void tcp_fastopen_active_timeout_reset(void)
*/
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
- int tfo_da_times = atomic_read(&tfo_active_disable_times);
- int multiplier;
+ unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+ int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
unsigned long timeout;
+ int multiplier;
if (!tfo_da_times)
return false;
/* Limit timout to max: 2^6 * initial timeout */
multiplier = 1 << min(tfo_da_times - 1, 6);
- timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ;
- if (time_before(jiffies, tfo_active_disable_stamp + timeout))
+ timeout = multiplier * tfo_bh_timeout * HZ;
+ if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
return true;
/* Mark check bit so we can check for successful active TFO
@@ -474,10 +487,10 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk)
}
}
} else if (tp->syn_fastopen_ch &&
- atomic_read(&tfo_active_disable_times)) {
+ atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) {
dst = sk_dst_get(sk);
if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)))
- tcp_fastopen_active_timeout_reset();
+ atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0);
dst_release(dst);
}
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5d7656beeee..db9bb46b5776 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2333,9 +2333,9 @@ static bool tcp_any_retrans_done(const struct sock *sk)
return false;
}
-#if FASTRETRANS_DEBUG > 1
static void DBGUNDO(struct sock *sk, const char *msg)
{
+#if FASTRETRANS_DEBUG > 1
struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
@@ -2357,10 +2357,8 @@ static void DBGUNDO(struct sock *sk, const char *msg)
tp->packets_out);
}
#endif
-}
-#else
-#define DBGUNDO(x...) do { } while (0)
#endif
+}
static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
@@ -4268,11 +4266,6 @@ static void tcp_sack_remove(struct tcp_sock *tp)
tp->rx_opt.num_sacks = num_sacks;
}
-enum tcp_queue {
- OOO_QUEUE,
- RCV_QUEUE,
-};
-
/**
* tcp_try_coalesce - try to merge skb to prior one
* @sk: socket
@@ -4288,7 +4281,6 @@ enum tcp_queue {
* Returns true if caller should free @from instead of queueing it
*/
static bool tcp_try_coalesce(struct sock *sk,
- enum tcp_queue dest,
struct sk_buff *to,
struct sk_buff *from,
bool *fragstolen)
@@ -4313,10 +4305,7 @@ static bool tcp_try_coalesce(struct sock *sk,
if (TCP_SKB_CB(from)->has_rxtstamp) {
TCP_SKB_CB(to)->has_rxtstamp = true;
- if (dest == OOO_QUEUE)
- TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp;
- else
- to->tstamp = from->tstamp;
+ to->tstamp = from->tstamp;
}
return true;
@@ -4353,9 +4342,6 @@ static void tcp_ofo_queue(struct sock *sk)
}
p = rb_next(p);
rb_erase(&skb->rbnode, &tp->out_of_order_queue);
- /* Replace tstamp which was stomped by rbnode */
- if (TCP_SKB_CB(skb)->has_rxtstamp)
- skb->tstamp = TCP_SKB_CB(skb)->swtstamp;
if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
SOCK_DEBUG(sk, "ofo packet was already received\n");
@@ -4367,8 +4353,7 @@ static void tcp_ofo_queue(struct sock *sk)
TCP_SKB_CB(skb)->end_seq);
tail = skb_peek_tail(&sk->sk_receive_queue);
- eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE,
- tail, skb, &fragstolen);
+ eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (!eaten)
@@ -4422,10 +4407,6 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
return;
}
- /* Stash tstamp to avoid being stomped on by rbnode */
- if (TCP_SKB_CB(skb)->has_rxtstamp)
- TCP_SKB_CB(skb)->swtstamp = skb->tstamp;
-
/* Disable header prediction. */
tp->pred_flags = 0;
inet_csk_schedule_ack(sk);
@@ -4453,7 +4434,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb,
+ if (tcp_try_coalesce(sk, tp->ooo_last_skb,
skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
@@ -4504,7 +4485,7 @@ coalesce_done:
__kfree_skb(skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
+ } else if (tcp_try_coalesce(sk, skb1,
skb, &fragstolen)) {
goto coalesce_done;
}
@@ -4556,7 +4537,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
__skb_pull(skb, hdrlen);
eaten = (tail &&
- tcp_try_coalesce(sk, RCV_QUEUE, tail,
+ tcp_try_coalesce(sk, tail,
skb, fragstolen)) ? 1 : 0;
tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
if (!eaten) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 85164d4d3e53..c7460fd90884 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2473,6 +2473,11 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_window_scaling = 1;
net->ipv4.sysctl_tcp_timestamps = 1;
+ net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
+ spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
+ net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+ atomic_set(&net->ipv4.tfo_active_disable_times, 0);
+
return 0;
fail:
tcp_sk_exit(net);
@@ -2482,7 +2487,12 @@ fail:
static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
+ struct net *net;
+
inet_twsk_purge(&tcp_hashinfo, AF_INET);
+
+ list_for_each_entry(net, net_exit_list, exit_list)
+ tcp_fastopen_ctx_destroy(net);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 102b2c90bb80..0ab78abc811b 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -892,10 +892,14 @@ static void tcp_metrics_flush_all(struct net *net)
for (row = 0; row < max_rows; row++, hb++) {
struct tcp_metrics_block __rcu **pp;
+ bool match;
+
spin_lock_bh(&tcp_metrics_lock);
pp = &hb->chain;
for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
- if (net_eq(tm_net(tm), net)) {
+ match = net ? net_eq(tm_net(tm), net) :
+ !atomic_read(&tm_net(tm)->count);
+ if (match) {
*pp = tm->tcpm_next;
kfree_rcu(tm, rcu_head);
} else {
@@ -1018,14 +1022,14 @@ static int __net_init tcp_net_metrics_init(struct net *net)
return 0;
}
-static void __net_exit tcp_net_metrics_exit(struct net *net)
+static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_list)
{
- tcp_metrics_flush_all(net);
+ tcp_metrics_flush_all(NULL);
}
static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
- .init = tcp_net_metrics_init,
- .exit = tcp_net_metrics_exit,
+ .init = tcp_net_metrics_init,
+ .exit_batch = tcp_net_metrics_exit_batch,
};
void __init tcp_metrics_init(void)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 218cfcc77650..ee113ff15fd0 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event);
static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
{
- return min(tp->snd_ssthresh, tp->snd_cwnd-1);
+ return min(tp->snd_ssthresh, tp->snd_cwnd);
}
static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5676237d2b0f..eb0359bdaa11 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1212,8 +1212,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
if (likely(partial)) {
up->forward_deficit += size;
size = up->forward_deficit;
- if (size < (sk->sk_rcvbuf >> 2) &&
- !skb_queue_empty(&up->reader_queue))
+ if (size < (sk->sk_rcvbuf >> 2))
return;
} else {
size += up->forward_deficit;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.