summaryrefslogtreecommitdiff
path: root/net/sctp/protocol.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/sctp/protocol.c')
-rw-r--r--net/sctp/protocol.c369
1 files changed, 231 insertions, 138 deletions
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 4e0eeb113ef5..2c3398f75d76 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
* (C) Copyright IBM Corp. 2001, 2004
* Copyright (c) 1999-2000 Cisco, Inc.
@@ -10,22 +11,6 @@
*
* Initialization/cleanup for SCTP protocol support.
*
- * This SCTP implementation is free software;
- * you can redistribute it and/or modify it under the terms of
- * the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This SCTP implementation is distributed in the hope that it
- * will be useful, but WITHOUT ANY WARRANTY; without even the implied
- * ************************
- * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- * See the GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNU CC; see the file COPYING. If not, see
- * <http://www.gnu.org/licenses/>.
- *
* Please send any bug reports or fixes you make to the
* email address(es):
* lksctp developers <linux-sctp@vger.kernel.org>
@@ -48,8 +33,8 @@
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/highmem.h>
-#include <linux/swap.h>
#include <linux/slab.h>
+#include <net/flow.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
@@ -59,6 +44,9 @@
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
+#include <net/inet_sock.h>
+#include <net/udp_tunnel.h>
+#include <net/inet_dscp.h>
#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
@@ -96,7 +84,7 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist,
return;
}
- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
+ in_dev_for_each_ifa_rcu(ifa, in_dev) {
/* Add the address to the local list. */
addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
if (addr) {
@@ -163,7 +151,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp,
* sock as well as the remote peer.
*/
if (addr->a.sa.sa_family == AF_INET &&
- !(copy_flags & SCTP_ADDR4_PEERSUPP))
+ (!(copy_flags & SCTP_ADDR4_ALLOWED) ||
+ !(copy_flags & SCTP_ADDR4_PEERSUPP)))
continue;
if (addr->a.sa.sa_family == AF_INET6 &&
(!(copy_flags & SCTP_ADDR6_ALLOWED) ||
@@ -197,12 +186,9 @@ static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk)
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt) {
- newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+ newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) +
inet_opt->opt.optlen, GFP_ATOMIC);
- if (newopt)
- memcpy(newopt, inet_opt, sizeof(*inet_opt) +
- inet_opt->opt.optlen);
- else
+ if (!newopt)
pr_err("%s: Failed to copy ip options\n", __func__);
}
RCU_INIT_POINTER(newinet->inet_opt, newopt);
@@ -242,6 +228,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb,
sa->sin_port = sh->dest;
sa->sin_addr.s_addr = ip_hdr(skb)->daddr;
}
+ memset(sa->sin_zero, 0, sizeof(sa->sin_zero));
}
/* Initialize an sctp_addr from a socket. */
@@ -250,6 +237,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk)
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = 0;
addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr;
+ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}
/* Initialize sk->sk_rcv_saddr from sctp_addr. */
@@ -265,13 +253,19 @@ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
}
/* Initialize a sctp_addr from an address parameter. */
-static void sctp_v4_from_addr_param(union sctp_addr *addr,
+static bool sctp_v4_from_addr_param(union sctp_addr *addr,
union sctp_addr_param *param,
__be16 port, int iif)
{
+ if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param))
+ return false;
+
addr->v4.sin_family = AF_INET;
addr->v4.sin_port = port;
addr->v4.sin_addr.s_addr = param->v4.addr.s_addr;
+ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
+
+ return true;
}
/* Initialize an address parameter from a sctp_addr and return the length
@@ -296,6 +290,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4,
saddr->v4.sin_family = AF_INET;
saddr->v4.sin_port = port;
saddr->v4.sin_addr.s_addr = fl4->saddr;
+ memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero));
}
/* Compare two addresses exactly. */
@@ -318,6 +313,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port)
addr->v4.sin_family = AF_INET;
addr->v4.sin_addr.s_addr = htonl(INADDR_ANY);
addr->v4.sin_port = port;
+ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
}
/* Is this a wildcard address? */
@@ -355,14 +351,17 @@ static int sctp_v4_addr_valid(union sctp_addr *addr,
/* Should this be available for binding? */
static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
{
- struct net *net = sock_net(&sp->inet.sk);
- int ret = inet_addr_type(net, addr->v4.sin_addr.s_addr);
-
+ struct sock *sk = &sp->inet.sk;
+ struct net *net = sock_net(sk);
+ int tb_id = RT_TABLE_LOCAL;
+ int ret;
+ tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ?: tb_id;
+ ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id);
if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
ret != RTN_LOCAL &&
- !sp->inet.freebind &&
- !net->ipv4.sysctl_ip_nonlocal_bind)
+ !inet_test_bit(FREEBIND, sk) &&
+ !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
return 0;
if (ipv6_only_sock(sctp_opt2sk(sp)))
@@ -381,7 +380,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
* Level 3 - private addresses.
* Level 4 - global addresses
* For INIT and INIT-ACK address list, let L be the level of
- * of requested destination address, sender and receiver
+ * requested destination address, sender and receiver
* SHOULD include all of its addresses with level greater
* than or equal to L.
*
@@ -401,7 +400,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
retval = SCTP_SCOPE_LINK;
} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
- ipv4_is_private_192(addr->v4.sin_addr.s_addr)) {
+ ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
+ ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_PRIVATE;
} else {
retval = SCTP_SCOPE_GLOBAL;
@@ -419,36 +419,45 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
{
struct sctp_association *asoc = t->asoc;
struct rtable *rt;
- struct flowi4 *fl4 = &fl->u.ip4;
+ struct flowi _fl;
+ struct flowi4 *fl4 = &_fl.u.ip4;
struct sctp_bind_addr *bp;
struct sctp_sockaddr_entry *laddr;
struct dst_entry *dst = NULL;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
- __u8 tos = inet_sk(sk)->tos;
+ dscp_t dscp;
if (t->dscp & SCTP_DSCP_SET_MASK)
- tos = t->dscp & SCTP_DSCP_VAL_MASK;
- memset(fl4, 0x0, sizeof(struct flowi4));
+ dscp = inet_dsfield_to_dscp(t->dscp);
+ else
+ dscp = inet_sk_dscp(inet_sk(sk));
+
+ memset(&_fl, 0x0, sizeof(_fl));
fl4->daddr = daddr->v4.sin_addr.s_addr;
fl4->fl4_dport = daddr->v4.sin_port;
fl4->flowi4_proto = IPPROTO_SCTP;
if (asoc) {
- fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
+ fl4->flowi4_dscp = dscp;
+ fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk);
fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
fl4->fl4_sport = htons(asoc->base.bind_addr.port);
}
if (saddr) {
fl4->saddr = saddr->v4.sin_addr.s_addr;
- fl4->fl4_sport = saddr->v4.sin_port;
+ if (!fl4->fl4_sport)
+ fl4->fl4_sport = saddr->v4.sin_port;
}
pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr,
&fl4->saddr);
rt = ip_route_output_key(sock_net(sk), fl4);
- if (!IS_ERR(rt))
+ if (!IS_ERR(rt)) {
dst = &rt->dst;
+ t->dst = dst;
+ memcpy(fl, &_fl, sizeof(_fl));
+ }
/* If there is no association or if a source address is passed, no
* more validation is required.
@@ -495,9 +504,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
continue;
fl4->fl4_sport = laddr->a.v4.sin_port;
- flowi4_update_output(fl4,
- asoc->base.sk->sk_bound_dev_if,
- RT_CONN_FLAGS_TOS(asoc->base.sk, tos),
+ flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if,
daddr->v4.sin_addr.s_addr,
laddr->a.v4.sin_addr.s_addr);
@@ -511,27 +518,33 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
false);
if (!odev || odev->ifindex != fl4->flowi4_oif) {
- if (!dst)
+ if (!dst) {
dst = &rt->dst;
- else
+ t->dst = dst;
+ memcpy(fl, &_fl, sizeof(_fl));
+ } else {
dst_release(&rt->dst);
+ }
continue;
}
dst_release(dst);
dst = &rt->dst;
+ t->dst = dst;
+ memcpy(fl, &_fl, sizeof(_fl));
break;
}
out_unlock:
rcu_read_unlock();
out:
- t->dst = dst;
- if (dst)
+ if (dst) {
pr_debug("rt_dst:%pI4, rt_src:%pI4\n",
- &fl4->daddr, &fl4->saddr);
- else
+ &fl->u.ip4.daddr, &fl->u.ip4.saddr);
+ } else {
+ t->dst = NULL;
pr_debug("no route\n");
+ }
}
/* For v4, the source address is cached in the route entry(dst). So no need
@@ -542,7 +555,7 @@ static void sctp_v4_get_saddr(struct sctp_sock *sk,
struct flowi *fl)
{
union sctp_addr *saddr = &t->saddr;
- struct rtable *rt = (struct rtable *)t->dst;
+ struct rtable *rt = dst_rtable(t->dst);
if (rt) {
saddr->v4.sin_family = AF_INET;
@@ -556,49 +569,21 @@ static int sctp_v4_skb_iif(const struct sk_buff *skb)
return inet_iif(skb);
}
-/* Was this packet marked by Explicit Congestion Notification? */
-static int sctp_v4_is_ce(const struct sk_buff *skb)
+static int sctp_v4_skb_sdif(const struct sk_buff *skb)
{
- return INET_ECN_is_ce(ip_hdr(skb)->tos);
+ return inet_sdif(skb);
}
-/* Create and initialize a new sk for the socket returned by accept(). */
-static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
- struct sctp_association *asoc,
- bool kern)
+/* Was this packet marked by Explicit Congestion Notification? */
+static int sctp_v4_is_ce(const struct sk_buff *skb)
{
- struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
- sk->sk_prot, kern);
- struct inet_sock *newinet;
-
- if (!newsk)
- goto out;
-
- sock_init_data(NULL, newsk);
-
- sctp_copy_sock(newsk, sk, asoc);
- sock_reset_flag(newsk, SOCK_ZAPPED);
-
- sctp_v4_copy_ip_options(sk, newsk);
-
- newinet = inet_sk(newsk);
-
- newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;
-
- sk_refcnt_debug_inc(newsk);
-
- if (newsk->sk_prot->init(newsk)) {
- sk_common_release(newsk);
- newsk = NULL;
- }
-
-out:
- return newsk;
+ return INET_ECN_is_ce(ip_hdr(skb)->tos);
}
static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
{
/* No address mapping for V4 sockets */
+ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
return sizeof(struct sockaddr_in);
}
@@ -615,7 +600,7 @@ static void sctp_v4_ecn_capable(struct sock *sk)
static void sctp_addr_wq_timeout_handler(struct timer_list *t)
{
- struct net *net = from_timer(net, t, sctp.addr_wq_timer);
+ struct net *net = timer_container_of(net, t, sctp.addr_wq_timer);
struct sctp_sockaddr_entry *addrw, *temp;
struct sctp_sock *sp;
@@ -679,7 +664,7 @@ static void sctp_free_addr_wq(struct net *net)
struct sctp_sockaddr_entry *temp;
spin_lock_bh(&net->sctp.addr_wq_lock);
- del_timer(&net->sctp.addr_wq_timer);
+ timer_delete(&net->sctp.addr_wq_timer);
list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) {
list_del(&addrw->list);
kfree(addrw);
@@ -723,6 +708,20 @@ void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cm
*/
spin_lock_bh(&net->sctp.addr_wq_lock);
+
+ /* Avoid searching the queue or modifying it if there are no consumers,
+ * as it can lead to performance degradation if addresses are modified
+ * en-masse.
+ *
+ * If the queue already contains some events, update it anyway to avoid
+ * ugly races between new sessions and new address events.
+ */
+ if (list_empty(&net->sctp.auto_asconf_splist) &&
+ list_empty(&net->sctp.addr_waitq)) {
+ spin_unlock_bh(&net->sctp.addr_wq_lock);
+ return;
+ }
+
/* Offsets existing events in addr_wq */
addrw = sctp_addr_wq_lookup(net, addr);
if (addrw) {
@@ -793,10 +792,10 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
if (addr->a.sa.sa_family == AF_INET &&
addr->a.v4.sin_addr.s_addr ==
ifa->ifa_local) {
- sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
found = 1;
addr->valid = 0;
list_del_rcu(&addr->list);
+ sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
break;
}
}
@@ -837,6 +836,75 @@ static int sctp_ctl_sock_init(struct net *net)
return 0;
}
+static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;
+
+ skb_set_transport_header(skb, sizeof(struct udphdr));
+ sctp_rcv(skb);
+ return 0;
+}
+
+int sctp_udp_sock_start(struct net *net)
+{
+ struct udp_tunnel_sock_cfg tuncfg = {NULL};
+ struct udp_port_cfg udp_conf = {0};
+ struct socket *sock;
+ int err;
+
+ udp_conf.family = AF_INET;
+ udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+ udp_conf.local_udp_port = htons(net->sctp.udp_port);
+ err = udp_sock_create(net, &udp_conf, &sock);
+ if (err) {
+ pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
+ return err;
+ }
+
+ tuncfg.encap_type = 1;
+ tuncfg.encap_rcv = sctp_udp_rcv;
+ tuncfg.encap_err_lookup = sctp_udp_v4_err;
+ setup_udp_tunnel_sock(net, sock, &tuncfg);
+ net->sctp.udp4_sock = sock->sk;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ memset(&udp_conf, 0, sizeof(udp_conf));
+
+ udp_conf.family = AF_INET6;
+ udp_conf.local_ip6 = in6addr_any;
+ udp_conf.local_udp_port = htons(net->sctp.udp_port);
+ udp_conf.use_udp6_rx_checksums = true;
+ udp_conf.ipv6_v6only = true;
+ err = udp_sock_create(net, &udp_conf, &sock);
+ if (err) {
+ pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
+ udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+ net->sctp.udp4_sock = NULL;
+ return err;
+ }
+
+ tuncfg.encap_type = 1;
+ tuncfg.encap_rcv = sctp_udp_rcv;
+ tuncfg.encap_err_lookup = sctp_udp_v6_err;
+ setup_udp_tunnel_sock(net, sock, &tuncfg);
+ net->sctp.udp6_sock = sock->sk;
+#endif
+
+ return 0;
+}
+
+void sctp_udp_sock_stop(struct net *net)
+{
+ if (net->sctp.udp4_sock) {
+ udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+ net->sctp.udp4_sock = NULL;
+ }
+ if (net->sctp.udp6_sock) {
+ udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
+ net->sctp.udp6_sock = NULL;
+ }
+}
+
/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
@@ -968,25 +1036,45 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
}
/* Wrapper routine that calls the ip transmit routine. */
-static inline int sctp_v4_xmit(struct sk_buff *skb,
- struct sctp_transport *transport)
+static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
- struct inet_sock *inet = inet_sk(skb->sk);
- __u8 dscp = inet->tos;
+ struct dst_entry *dst = dst_clone(t->dst);
+ struct flowi4 *fl4 = &t->fl.u.ip4;
+ struct sock *sk = skb->sk;
+ struct inet_sock *inet = inet_sk(sk);
+ __u8 dscp = READ_ONCE(inet->tos);
+ __be16 df = 0;
pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
- skb->len, &transport->fl.u.ip4.saddr,
- &transport->fl.u.ip4.daddr);
+ skb->len, &fl4->saddr, &fl4->daddr);
+
+ if (t->dscp & SCTP_DSCP_SET_MASK)
+ dscp = t->dscp & SCTP_DSCP_VAL_MASK;
- if (transport->dscp & SCTP_DSCP_SET_MASK)
- dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
+ inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO
+ : IP_PMTUDISC_DONT;
+ SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
- inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
- IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
+ if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+ skb_dst_set(skb, dst);
+ return __ip_queue_xmit(sk, skb, &t->fl, dscp);
+ }
+
+ if (skb_is_gso(skb))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
- SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
+ if (ip_dont_fragment(sk, dst) && !skb->ignore_df)
+ df = htons(IP_DF);
- return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
+ skb->encapsulation = 1;
+ skb_reset_inner_mac_header(skb);
+ skb_reset_inner_transport_header(skb);
+ skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+ udp_tunnel_xmit_skb(dst_rtable(dst), sk, skb, fl4->saddr,
+ fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
+ sctp_sk(sk)->udp_port, t->encap_port, false, false,
+ 0);
+ return 0;
}
static struct sctp_af sctp_af_inet;
@@ -999,7 +1087,6 @@ static struct sctp_pf sctp_pf_inet = {
.bind_verify = sctp_inet_bind_verify,
.send_verify = sctp_inet_send_verify,
.supported_addrs = sctp_inet_supported_addrs,
- .create_accept_sk = sctp_v4_create_accept_sk,
.addr_to_user = sctp_v4_addr_to_user,
.to_sk_saddr = sctp_v4_to_sk_saddr,
.to_sk_daddr = sctp_v4_to_sk_daddr,
@@ -1024,6 +1111,7 @@ static const struct proto_ops inet_seqpacket_ops = {
.getname = inet_getname, /* Semantics are different. */
.poll = sctp_poll,
.ioctl = inet_ioctl,
+ .gettstamp = sock_gettstamp,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown, /* Looks harmless. */
.setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
@@ -1031,11 +1119,6 @@ static const struct proto_ops inet_seqpacket_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_sock_common_setsockopt,
- .compat_getsockopt = compat_sock_common_getsockopt,
-#endif
};
/* Registration with AF_INET family. */
@@ -1054,12 +1137,17 @@ static struct inet_protosw sctp_stream_protosw = {
.flags = SCTP_PROTOSW_FLAG
};
+static int sctp4_rcv(struct sk_buff *skb)
+{
+ SCTP_INPUT_CB(skb)->encap_port = 0;
+ return sctp_rcv(skb);
+}
+
/* Register with IP layer. */
static const struct net_protocol sctp_protocol = {
- .handler = sctp_rcv,
+ .handler = sctp4_rcv,
.err_handler = sctp_v4_err,
.no_policy = 1,
- .netns_ok = 1,
.icmp_strict_tag_validation = 1,
};
@@ -1083,16 +1171,13 @@ static struct sctp_af sctp_af_inet = {
.available = sctp_v4_available,
.scope = sctp_v4_scope,
.skb_iif = sctp_v4_skb_iif,
+ .skb_sdif = sctp_v4_skb_sdif,
.is_ce = sctp_v4_is_ce,
.seq_dump_addr = sctp_v4_seq_dump_addr,
.ecn_capable = sctp_v4_ecn_capable,
.net_header_len = sizeof(struct iphdr),
.sockaddr_len = sizeof(struct sockaddr_in),
.ip_options_len = sctp_v4_ip_options_len,
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_ip_setsockopt,
- .compat_getsockopt = compat_ip_getsockopt,
-#endif
};
struct sctp_pf *sctp_get_pf_specific(sa_family_t family)
@@ -1217,21 +1302,22 @@ static int __net_init sctp_defaults_init(struct net *net)
/* Whether Cookie Preservative is enabled(1) or not(0) */
net->sctp.cookie_preserve_enable = 1;
- /* Default sctp sockets to use md5 as their hmac alg */
-#if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5)
- net->sctp.sctp_hmac_alg = "md5";
-#elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1)
- net->sctp.sctp_hmac_alg = "sha1";
-#else
- net->sctp.sctp_hmac_alg = NULL;
-#endif
+ /* Whether cookie authentication is enabled(1) or not(0) */
+ net->sctp.cookie_auth_enable =
+ !IS_ENABLED(CONFIG_SCTP_DEFAULT_COOKIE_HMAC_NONE);
/* Max.Burst - 4 */
net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST;
+ /* Disable of Primary Path Switchover by default */
+ net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX;
+
/* Enable pf state by default */
net->sctp.pf_enable = 1;
+ /* Ignore pf exposure feature by default */
+ net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET;
+
/* Association.Max.Retrans - 10 attempts
* Path.Max.Retrans - 5 attempts (per destination address)
* Max.Init.Retransmits - 8 attempts
@@ -1266,6 +1352,15 @@ static int __net_init sctp_defaults_init(struct net *net)
/* Disable AUTH by default. */
net->sctp.auth_enable = 0;
+ /* Enable ECN by default. */
+ net->sctp.ecn_enable = 1;
+
+ /* Set UDP tunneling listening port to 0 by default */
+ net->sctp.udp_port = 0;
+
+ /* Set remote encap port to 0 by default */
+ net->sctp.encap_port = 0;
+
/* Set SCOPE policy to enabled */
net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;
@@ -1275,6 +1370,10 @@ static int __net_init sctp_defaults_init(struct net *net)
/* Initialize maximum autoclose timeout. */
net->sctp.max_autoclose = INT_MAX / HZ;
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ net->sctp.l3mdev_accept = 1;
+#endif
+
status = sctp_sysctl_net_register(net);
if (status)
goto err_sysctl_register;
@@ -1348,7 +1447,7 @@ static int __net_init sctp_ctrlsock_init(struct net *net)
return status;
}
-static void __net_init sctp_ctrlsock_exit(struct net *net)
+static void __net_exit sctp_ctrlsock_exit(struct net *net)
{
/* Free the control endpoint. */
inet_ctl_sock_destroy(net->sctp.ctl_sock);
@@ -1362,31 +1461,25 @@ static struct pernet_operations sctp_ctrlsock_ops = {
/* Initialize the universe into something sensible. */
static __init int sctp_init(void)
{
- int i;
- int status = -EINVAL;
- unsigned long goal;
- unsigned long limit;
unsigned long nr_pages = totalram_pages();
+ unsigned long limit;
+ unsigned long goal;
+ int max_entry_order;
+ int num_entries;
int max_share;
+ int status;
int order;
- int num_entries;
- int max_entry_order;
+ int i;
sock_skb_cb_check_size(sizeof(struct sctp_ulpevent));
/* Allocate bind_bucket and chunk caches. */
status = -ENOBUFS;
- sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket",
- sizeof(struct sctp_bind_bucket),
- 0, SLAB_HWCACHE_ALIGN,
- NULL);
+ sctp_bucket_cachep = KMEM_CACHE(sctp_bind_bucket, SLAB_HWCACHE_ALIGN);
if (!sctp_bucket_cachep)
goto out;
- sctp_chunk_cachep = kmem_cache_create("sctp_chunk",
- sizeof(struct sctp_chunk),
- 0, SLAB_HWCACHE_ALIGN,
- NULL);
+ sctp_chunk_cachep = KMEM_CACHE(sctp_chunk, SLAB_HWCACHE_ALIGN);
if (!sctp_chunk_cachep)
goto err_chunk_cachep;
@@ -1413,11 +1506,11 @@ static __init int sctp_init(void)
limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7);
max_share = min(4UL*1024*1024, limit);
- sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */
+ sysctl_sctp_rmem[0] = PAGE_SIZE; /* give each asoc 1 page min */
sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1);
sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share);
- sysctl_sctp_wmem[0] = SK_MEM_QUANTUM;
+ sysctl_sctp_wmem[0] = PAGE_SIZE;
sysctl_sctp_wmem[1] = 16*1024;
sysctl_sctp_wmem[2] = max(64*1024, max_share);
@@ -1478,10 +1571,10 @@ static __init int sctp_init(void)
num_entries = (1UL << order) * PAGE_SIZE /
sizeof(struct sctp_bind_hashbucket);
- /* And finish by rounding it down to the nearest power of two
- * this wastes some memory of course, but its needed because
+ /* And finish by rounding it down to the nearest power of two.
+ * This wastes some memory of course, but it's needed because
* the hash function operates based on the assumption that
- * that the number of entries is a power of two
+ * the number of entries is a power of two.
*/
sctp_port_hashsize = rounddown_pow_of_two(num_entries);