summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c30
-rw-r--r--net/ipv4/fib_frontend.c22
-rw-r--r--net/ipv4/inet_connection_sock.c36
-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/tcp_input.c33
-rw-r--r--net/ipv4/tcp_metrics.c14
-rw-r--r--net/ipv4/udp.c3
10 files changed, 94 insertions, 92 deletions
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/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/ip_gre.c b/net/ipv4/ip_gre.c
index 0162fb955b33..9cee986ac6b8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1013,15 +1013,14 @@ 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),
};
@@ -1540,15 +1539,14 @@ 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),
};
@@ -1559,16 +1557,14 @@ 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 5ed63d250950..02d70ca99db1 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -452,15 +452,14 @@ 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/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_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/udp.c b/net/ipv4/udp.c
index ef29df8648e4..784ced0b9150 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;
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-21 23:08:18 +0100