aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/inet_connection_sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/inet_connection_sock.c')
-rw-r--r--net/ipv4/inet_connection_sock.c166
1 files changed, 100 insertions, 66 deletions
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e4fa9e5833e4..92b31d251da8 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,17 +24,19 @@
#include <net/addrconf.h>
#if IS_ENABLED(CONFIG_IPV6)
-/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6
- * only, and any IPv4 addresses if not IPv6 only
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
- * and 0.0.0.0 equals to 0.0.0.0 only
+/* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses
+ * if IPv6 only, and any IPv4 addresses
+ * if not IPv6 only
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
+ * and 0.0.0.0 equals to 0.0.0.0 only
*/
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)
+ bool match_sk1_wildcard,
+ bool match_sk2_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;
@@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
- if (!sk1_rcv_saddr || !sk2_rcv_saddr)
- return match_wildcard;
+ return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+ (match_sk2_wildcard && !sk2_rcv_saddr);
}
return false;
}
@@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
return true;
- if (addr_type2 == IPV6_ADDR_ANY && match_wildcard &&
+ if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
!(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
return true;
- if (addr_type == IPV6_ADDR_ANY && match_wildcard &&
+ if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
!(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
return true;
@@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
}
#endif
-/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- * 0.0.0.0 only equals to 0.0.0.0
+/* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses
+ * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
+ * 0.0.0.0 only equals to 0.0.0.0
*/
static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
- bool sk2_ipv6only, bool match_wildcard)
+ bool sk2_ipv6only, bool match_sk1_wildcard,
+ bool match_sk2_wildcard)
{
if (!sk2_ipv6only) {
if (sk1_rcv_saddr == sk2_rcv_saddr)
return true;
- if (!sk1_rcv_saddr || !sk2_rcv_saddr)
- return match_wildcard;
+ return (match_sk1_wildcard && !sk1_rcv_saddr) ||
+ (match_sk2_wildcard && !sk2_rcv_saddr);
}
return false;
}
@@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
sk2->sk_rcv_saddr,
ipv6_only_sock(sk),
ipv6_only_sock(sk2),
+ match_wildcard,
match_wildcard);
#endif
return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
- ipv6_only_sock(sk2), match_wildcard);
+ ipv6_only_sock(sk2), match_wildcard,
+ match_wildcard);
}
EXPORT_SYMBOL(inet_rcv_saddr_equal);
@@ -273,10 +278,61 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb,
tb->fast_rcv_saddr,
sk->sk_rcv_saddr,
tb->fast_ipv6_only,
- ipv6_only_sock(sk), true);
+ ipv6_only_sock(sk), true, false);
#endif
return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr,
- ipv6_only_sock(sk), true);
+ ipv6_only_sock(sk), true, false);
+}
+
+void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
+ struct sock *sk)
+{
+ kuid_t uid = sock_i_uid(sk);
+ bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
+
+ if (hlist_empty(&tb->owners)) {
+ tb->fastreuse = reuse;
+ if (sk->sk_reuseport) {
+ tb->fastreuseport = FASTREUSEPORT_ANY;
+ tb->fastuid = uid;
+ tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+ tb->fast_ipv6_only = ipv6_only_sock(sk);
+ tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+ tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+ } else {
+ tb->fastreuseport = 0;
+ }
+ } else {
+ if (!reuse)
+ tb->fastreuse = 0;
+ if (sk->sk_reuseport) {
+ /* We didn't match or we don't have fastreuseport set on
+ * the tb, but we have sk_reuseport set on this socket
+ * and we know that there are no bind conflicts with
+ * this socket in this tb, so reset our tb's reuseport
+ * settings so that any subsequent sockets that match
+ * our current socket will be put on the fast path.
+ *
+ * If we reset we need to set FASTREUSEPORT_STRICT so we
+ * do extra checking for all subsequent sk_reuseport
+ * socks.
+ */
+ if (!sk_reuseport_match(tb, sk)) {
+ tb->fastreuseport = FASTREUSEPORT_STRICT;
+ tb->fastuid = uid;
+ tb->fast_rcv_saddr = sk->sk_rcv_saddr;
+ tb->fast_ipv6_only = ipv6_only_sock(sk);
+ tb->fast_sk_family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+ tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
+#endif
+ }
+ } else {
+ tb->fastreuseport = 0;
+ }
+ }
}
/* Obtain a reference to a local port for the given sock,
@@ -291,7 +347,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
- kuid_t uid = sock_i_uid(sk);
int l3mdev;
l3mdev = inet_sk_bound_l3mdev(sk);
@@ -328,49 +383,8 @@ tb_found:
goto fail_unlock;
}
success:
- if (hlist_empty(&tb->owners)) {
- tb->fastreuse = reuse;
- if (sk->sk_reuseport) {
- tb->fastreuseport = FASTREUSEPORT_ANY;
- tb->fastuid = uid;
- tb->fast_rcv_saddr = sk->sk_rcv_saddr;
- tb->fast_ipv6_only = ipv6_only_sock(sk);
- tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
- tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
- } else {
- tb->fastreuseport = 0;
- }
- } else {
- if (!reuse)
- tb->fastreuse = 0;
- if (sk->sk_reuseport) {
- /* We didn't match or we don't have fastreuseport set on
- * the tb, but we have sk_reuseport set on this socket
- * and we know that there are no bind conflicts with
- * this socket in this tb, so reset our tb's reuseport
- * settings so that any subsequent sockets that match
- * our current socket will be put on the fast path.
- *
- * If we reset we need to set FASTREUSEPORT_STRICT so we
- * do extra checking for all subsequent sk_reuseport
- * socks.
- */
- if (!sk_reuseport_match(tb, sk)) {
- tb->fastreuseport = FASTREUSEPORT_STRICT;
- tb->fastuid = uid;
- tb->fast_rcv_saddr = sk->sk_rcv_saddr;
- tb->fast_ipv6_only = ipv6_only_sock(sk);
- tb->fast_sk_family = sk->sk_family;
-#if IS_ENABLED(CONFIG_IPV6)
- tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-#endif
- }
- } else {
- tb->fastreuseport = 0;
- }
- }
+ inet_csk_update_fastreuse(tb, sk);
+
if (!inet_csk(sk)->icsk_bind_hash)
inet_bind_hash(sk, tb, port);
WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
@@ -482,8 +496,28 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
}
spin_unlock_bh(&queue->fastopenq.lock);
}
+
out:
release_sock(sk);
+ if (newsk && mem_cgroup_sockets_enabled) {
+ int amt;
+
+ /* atomically get the memory usage, set and charge the
+ * newsk->sk_memcg.
+ */
+ lock_sock(newsk);
+
+ /* The socket has not been accepted yet, no need to look at
+ * newsk->sk_wmem_queued.
+ */
+ amt = sk_mem_pages(newsk->sk_forward_alloc +
+ atomic_read(&newsk->sk_rmem_alloc));
+ mem_cgroup_sk_alloc(newsk);
+ if (newsk->sk_memcg && amt)
+ mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
+
+ release_sock(newsk);
+ }
if (req)
reqsk_put(req);
return newsk;
@@ -907,7 +941,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
percpu_counter_inc(sk->sk_prot->orphan_count);
if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
- BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+ BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
BUG_ON(sk != req->rsk_listener);
/* Paranoid, to prevent race condition if
@@ -916,7 +950,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
* Also to satisfy an assertion in
* tcp_v4_destroy_sock().
*/
- tcp_sk(child)->fastopen_rsk = NULL;
+ RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL);
}
inet_csk_destroy_sock(child);
}
@@ -1087,7 +1121,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu)
if (!dst)
goto out;
}
- dst->ops->update_pmtu(dst, sk, NULL, mtu);
+ dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
dst = __sk_dst_check(sk, 0);
if (!dst)
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-20 15:59:07 +0000