summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ax25/af_ax25.c3
-rw-r--r--net/batman-adv/distributed-arp-table.c5
-rw-r--r--net/batman-adv/routing.c19
-rw-r--r--net/batman-adv/translation-table.c16
-rw-r--r--net/bluetooth/af_bluetooth.c6
-rw-r--r--net/bluetooth/sco.c3
-rw-r--r--net/bluetooth/smp.c7
-rw-r--r--net/bridge/br_stp_if.c7
-rw-r--r--net/caif/caif_socket.c4
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dst.c3
-rw-r--r--net/core/neighbour.c4
-rw-r--r--net/core/netclassid_cgroup.c28
-rw-r--r--net/core/netprio_cgroup.c9
-rw-r--r--net/core/scm.c2
-rw-r--r--net/core/skbuff.c5
-rw-r--r--net/core/sock.c19
-rw-r--r--net/core/stream.c6
-rw-r--r--net/dccp/ipv6.c37
-rw-r--r--net/dccp/proto.c3
-rw-r--r--net/decnet/af_decnet.c11
-rw-r--r--net/dns_resolver/dns_query.c2
-rw-r--r--net/hsr/hsr_device.c2
-rw-r--r--net/ipv4/af_inet.c3
-rw-r--r--net/ipv4/fib_frontend.c9
-rw-r--r--net/ipv4/fou.c3
-rw-r--r--net/ipv4/igmp.c5
-rw-r--r--net/ipv4/ipip.c3
-rw-r--r--net/ipv4/ipmr.c23
-rw-r--r--net/ipv4/netfilter/Kconfig1
-rw-r--r--net/ipv4/raw.c7
-rw-r--r--net/ipv4/tcp.c7
-rw-r--r--net/ipv4/tcp_input.c26
-rw-r--r--net/ipv4/tcp_ipv4.c8
-rw-r--r--net/ipv4/tcp_output.c23
-rw-r--r--net/ipv4/tcp_timer.c14
-rw-r--r--net/ipv4/udp.c8
-rw-r--r--net/ipv4/xfrm4_policy.c46
-rw-r--r--net/ipv6/addrconf.c21
-rw-r--r--net/ipv6/addrlabel.c2
-rw-r--r--net/ipv6/af_inet6.c18
-rw-r--r--net/ipv6/datagram.c4
-rw-r--r--net/ipv6/exthdrs.c3
-rw-r--r--net/ipv6/icmp.c14
-rw-r--r--net/ipv6/inet6_connection_sock.c21
-rw-r--r--net/ipv6/ip6_gre.c8
-rw-r--r--net/ipv6/ip6_tunnel.c2
-rw-r--r--net/ipv6/ip6mr.c19
-rw-r--r--net/ipv6/ipv6_sockglue.c33
-rw-r--r--net/ipv6/ndisc.c14
-rw-r--r--net/ipv6/netfilter/Kconfig1
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c5
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/reassembly.c10
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/ipv6/tcp_ipv6.c35
-rw-r--r--net/ipv6/udp.c8
-rw-r--r--net/ipv6/xfrm6_policy.c53
-rw-r--r--net/irda/af_irda.c3
-rw-r--r--net/iucv/af_iucv.c2
-rw-r--r--net/l2tp/l2tp_ip6.c8
-rw-r--r--net/mac80211/agg-tx.c3
-rw-r--r--net/mac80211/cfg.c11
-rw-r--r--net/mac80211/ieee80211_i.h4
-rw-r--r--net/mac80211/iface.c5
-rw-r--r--net/mac80211/main.c3
-rw-r--r--net/mac80211/mesh_pathtbl.c8
-rw-r--r--net/mac80211/mlme.c17
-rw-r--r--net/mac80211/rx.c3
-rw-r--r--net/mac80211/scan.c9
-rw-r--r--net/mac80211/util.c113
-rw-r--r--net/mac80211/vht.c10
-rw-r--r--net/mpls/af_mpls.c43
-rw-r--r--net/mpls/mpls_iptunnel.c4
-rw-r--r--net/netfilter/nf_tables_api.c99
-rw-r--r--net/netfilter/nf_tables_netdev.c2
-rw-r--r--net/netfilter/nfnetlink.c4
-rw-r--r--net/netfilter/nfnetlink_queue.c9
-rw-r--r--net/netfilter/nft_ct.c1
-rw-r--r--net/nfc/llcp_sock.c2
-rw-r--r--net/openvswitch/conntrack.c22
-rw-r--r--net/openvswitch/dp_notify.c2
-rw-r--r--net/openvswitch/flow_netlink.c5
-rw-r--r--net/openvswitch/vport-geneve.c1
-rw-r--r--net/openvswitch/vport-gre.c1
-rw-r--r--net/openvswitch/vport-netdev.c8
-rw-r--r--net/openvswitch/vport.c8
-rw-r--r--net/openvswitch/vport.h8
-rw-r--r--net/packet/af_packet.c4
-rw-r--r--net/rds/connection.c6
-rw-r--r--net/rds/send.c4
-rw-r--r--net/rfkill/core.c6
-rw-r--r--net/rxrpc/ar-ack.c4
-rw-r--r--net/rxrpc/ar-output.c2
-rw-r--r--net/sched/sch_api.c25
-rw-r--r--net/sched/sch_generic.c6
-rw-r--r--net/sched/sch_mq.c4
-rw-r--r--net/sched/sch_mqprio.c4
-rw-r--r--net/sctp/ipv6.c24
-rw-r--r--net/sctp/outqueue.c2
-rw-r--r--net/sctp/sm_make_chunk.c4
-rw-r--r--net/sctp/sm_statefuns.c9
-rw-r--r--net/sctp/socket.c65
-rw-r--r--net/socket.c23
-rw-r--r--net/sunrpc/sched.c6
-rw-r--r--net/sunrpc/svc.c13
-rw-r--r--net/sunrpc/xprtsock.c14
-rw-r--r--net/tipc/link.c2
-rw-r--r--net/tipc/socket.c10
-rw-r--r--net/tipc/udp_media.c7
-rw-r--r--net/unix/af_unix.c347
-rw-r--r--net/wireless/nl80211.c5
-rw-r--r--net/wireless/reg.c5
-rw-r--r--net/xfrm/xfrm_policy.c88
115 files changed, 1133 insertions, 646 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index ae3a47f9d1d5..fbd0acf80b13 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -805,6 +805,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
struct sock *sk;
ax25_cb *ax25;
+ if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ return -EINVAL;
+
if (!net_eq(net, &init_net))
return -EAFNOSUPPORT;
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 83bc1aaf5800..a49c705fb86b 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -566,6 +566,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
int select;
batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key;
struct batadv_dat_candidate *res;
+ struct batadv_dat_entry dat;
if (!bat_priv->orig_hash)
return NULL;
@@ -575,7 +576,9 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
if (!res)
return NULL;
- ip_key = (batadv_dat_addr_t)batadv_hash_dat(&ip_dst,
+ dat.ip = ip_dst;
+ dat.vid = 0;
+ ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat,
BATADV_DAT_ADDR_MAX);
batadv_dbg(BATADV_DBG_DAT, bat_priv,
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 8d990b070a2e..3207667e69de 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -836,6 +836,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
u8 *orig_addr;
struct batadv_orig_node *orig_node = NULL;
int check, hdr_size = sizeof(*unicast_packet);
+ enum batadv_subtype subtype;
bool is4addr;
unicast_packet = (struct batadv_unicast_packet *)skb->data;
@@ -863,10 +864,20 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
/* packet for me */
if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) {
if (is4addr) {
- batadv_dat_inc_counter(bat_priv,
- unicast_4addr_packet->subtype);
- orig_addr = unicast_4addr_packet->src;
- orig_node = batadv_orig_hash_find(bat_priv, orig_addr);
+ subtype = unicast_4addr_packet->subtype;
+ batadv_dat_inc_counter(bat_priv, subtype);
+
+ /* Only payload data should be considered for speedy
+ * join. For example, DAT also uses unicast 4addr
+ * types, but those packets should not be considered
+ * for speedy join, since the clients do not actually
+ * reside at the sending originator.
+ */
+ if (subtype == BATADV_P_DATA) {
+ orig_addr = unicast_4addr_packet->src;
+ orig_node = batadv_orig_hash_find(bat_priv,
+ orig_addr);
+ }
}
if (batadv_dat_snoop_incoming_arp_request(bat_priv, skb,
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4228b10c47ea..76f19ba62462 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -68,13 +68,15 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv,
unsigned short vid, const char *message,
bool roaming);
-/* returns 1 if they are the same mac addr */
+/* returns 1 if they are the same mac addr and vid */
static int batadv_compare_tt(const struct hlist_node *node, const void *data2)
{
const void *data1 = container_of(node, struct batadv_tt_common_entry,
hash_entry);
+ const struct batadv_tt_common_entry *tt1 = data1;
+ const struct batadv_tt_common_entry *tt2 = data2;
- return batadv_compare_eth(data1, data2);
+ return (tt1->vid == tt2->vid) && batadv_compare_eth(data1, data2);
}
/**
@@ -1427,9 +1429,15 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
}
/* if the client was temporary added before receiving the first
- * OGM announcing it, we have to clear the TEMP flag
+ * OGM announcing it, we have to clear the TEMP flag. Also,
+ * remove the previous temporary orig node and re-add it
+ * if required. If the orig entry changed, the new one which
+ * is a non-temporary entry is preferred.
*/
- common->flags &= ~BATADV_TT_CLIENT_TEMP;
+ if (common->flags & BATADV_TT_CLIENT_TEMP) {
+ batadv_tt_global_del_orig_list(tt_global_entry);
+ common->flags &= ~BATADV_TT_CLIENT_TEMP;
+ }
/* the change can carry possible "attribute" flags like the
* TT_CLIENT_WIFI, therefore they have to be copied in the
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index a3bffd1ec2b4..70306cc9d814 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -271,11 +271,11 @@ static long bt_sock_data_wait(struct sock *sk, long timeo)
if (signal_pending(current) || !timeo)
break;
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
}
__set_current_state(TASK_RUNNING);
@@ -441,7 +441,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,
if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk))
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
return mask;
}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index fe129663bd3f..f52bcbf2e58c 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -526,6 +526,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr,
if (!addr || addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ if (addr_len < sizeof(struct sockaddr_sco))
+ return -EINVAL;
+
lock_sock(sk);
if (sk->sk_state != BT_OPEN) {
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index c91353841e40..ffed8a1d4f27 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -3027,8 +3027,13 @@ static void smp_ready_cb(struct l2cap_chan *chan)
BT_DBG("chan %p", chan);
+ /* No need to call l2cap_chan_hold() here since we already own
+ * the reference taken in smp_new_conn_cb(). This is just the
+ * first time that we tie it to a specific pointer. The code in
+ * l2cap_core.c ensures that there's no risk this function wont
+ * get called if smp_new_conn_cb was previously called.
+ */
conn->smp = chan;
- l2cap_chan_hold(chan);
if (hcon->type == ACL_LINK && test_bit(HCI_CONN_ENCRYPT, &hcon->flags))
bredr_pairing(chan);
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 5396ff08af32..8a7ada8bb947 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -39,7 +39,7 @@ void br_init_port(struct net_bridge_port *p)
struct switchdev_attr attr = {
.id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME,
.flags = SWITCHDEV_F_SKIP_EOPNOTSUPP | SWITCHDEV_F_DEFER,
- .u.ageing_time = p->br->ageing_time,
+ .u.ageing_time = jiffies_to_clock_t(p->br->ageing_time),
};
int err;
@@ -142,7 +142,10 @@ static void br_stp_start(struct net_bridge *br)
char *envp[] = { NULL };
struct net_bridge_port *p;
- r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+ if (net_eq(dev_net(br->dev), &init_net))
+ r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+ else
+ r = -ENOENT;
spin_lock_bh(&br->lock);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index cc858919108e..aa209b1066c9 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -323,7 +323,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
!timeo)
break;
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
@@ -331,7 +331,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
if (sock_flag(sk, SOCK_DEAD))
break;
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
}
finish_wait(sk_sleep(sk), &wait);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 617088aee21d..d62af69ad844 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -785,7 +785,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
if (sock_writeable(sk))
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
return mask;
}
diff --git a/net/core/dst.c b/net/core/dst.c
index e6dc77252fe9..a1656e3b8d72 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -301,12 +301,13 @@ void dst_release(struct dst_entry *dst)
{
if (dst) {
int newrefcnt;
+ unsigned short nocache = dst->flags & DST_NOCACHE;
newrefcnt = atomic_dec_return(&dst->__refcnt);
if (unlikely(newrefcnt < 0))
net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
__func__, dst, newrefcnt);
- if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE))
+ if (!newrefcnt && unlikely(nocache))
call_rcu(&dst->rcu_head, dst_destroy_rcu);
}
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e6af42da28d9..f18ae91b652e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2215,7 +2215,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
ndm->ndm_pad2 = 0;
ndm->ndm_flags = pn->flags | NTF_PROXY;
ndm->ndm_type = RTN_UNICAST;
- ndm->ndm_ifindex = pn->dev->ifindex;
+ ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
ndm->ndm_state = NUD_NONE;
if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2333,7 +2333,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
if (h > s_h)
s_idx = 0;
for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
- if (dev_net(n->dev) != net)
+ if (pneigh_net(n) != net)
continue;
if (idx < s_idx)
goto next;
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6441f47b1a8f..d9ee8d08a3a6 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -56,7 +56,7 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
kfree(css_cls_state(css));
}
-static int update_classid(const void *v, struct file *file, unsigned n)
+static int update_classid_sock(const void *v, struct file *file, unsigned n)
{
int err;
struct socket *sock = sock_from_file(file, &err);
@@ -67,18 +67,27 @@ static int update_classid(const void *v, struct file *file, unsigned n)
return 0;
}
-static void cgrp_attach(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static void update_classid(struct cgroup_subsys_state *css, void *v)
{
- struct cgroup_cls_state *cs = css_cls_state(css);
- void *v = (void *)(unsigned long)cs->classid;
+ struct css_task_iter it;
struct task_struct *p;
- cgroup_taskset_for_each(p, tset) {
+ css_task_iter_start(css, &it);
+ while ((p = css_task_iter_next(&it))) {
task_lock(p);
- iterate_fd(p->files, 0, update_classid, v);
+ iterate_fd(p->files, 0, update_classid_sock, v);
task_unlock(p);
}
+ css_task_iter_end(&it);
+}
+
+static void cgrp_attach(struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys_state *css;
+
+ cgroup_taskset_first(tset, &css);
+ update_classid(css,
+ (void *)(unsigned long)css_cls_state(css)->classid);
}
static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -89,8 +98,11 @@ static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
u64 value)
{
- css_cls_state(css)->classid = (u32) value;
+ struct cgroup_cls_state *cs = css_cls_state(css);
+
+ cs->classid = (u32)value;
+ update_classid(css, (void *)(unsigned long)cs->classid);
return 0;
}
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index cbd0a199bf52..40fd09fe06ae 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n)
return 0;
}
-static void net_prio_attach(struct cgroup_subsys_state *css,
- struct cgroup_taskset *tset)
+static void net_prio_attach(struct cgroup_taskset *tset)
{
struct task_struct *p;
- void *v = (void *)(unsigned long)css->cgroup->id;
+ struct cgroup_subsys_state *css;
+
+ cgroup_taskset_for_each(p, css, tset) {
+ void *v = (void *)(unsigned long)css->cgroup->id;
- cgroup_taskset_for_each(p, tset) {
task_lock(p);
iterate_fd(p->files, 0, update_netprio, v);
task_unlock(p);
diff --git a/net/core/scm.c b/net/core/scm.c
index 3b6899b7d810..8a1741b14302 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
err = put_user(cmlen, &cm->cmsg_len);
if (!err) {
cmlen = CMSG_SPACE(i*sizeof(int));
+ if (msg->msg_controllen < cmlen)
+ cmlen = msg->msg_controllen;
msg->msg_control += cmlen;
msg->msg_controllen -= cmlen;
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 152b9c70e252..b2df375ec9c2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3643,7 +3643,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
serr->ee.ee_info = tstype;
if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
serr->ee.ee_data = skb_shinfo(skb)->tskey;
- if (sk->sk_protocol == IPPROTO_TCP)
+ if (sk->sk_protocol == IPPROTO_TCP &&
+ sk->sk_type == SOCK_STREAM)
serr->ee.ee_data -= sk->sk_tskey;
}
@@ -4268,7 +4269,7 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
return NULL;
}
- memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len,
+ memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN,
2 * ETH_ALEN);
skb->mac_header += VLAN_HLEN;
return skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e4dd54bfb5a..0d91f7dca751 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -433,8 +433,6 @@ static bool sock_needs_netstamp(const struct sock *sk)
}
}
-#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
-
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
@@ -874,7 +872,8 @@ set_rcvbuf:
if (val & SOF_TIMESTAMPING_OPT_ID &&
!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
- if (sk->sk_protocol == IPPROTO_TCP) {
+ if (sk->sk_protocol == IPPROTO_TCP &&
+ sk->sk_type == SOCK_STREAM) {
if (sk->sk_state != TCP_ESTABLISHED) {
ret = -EINVAL;
break;
@@ -1530,7 +1529,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
skb_queue_head_init(&newsk->sk_receive_queue);
skb_queue_head_init(&newsk->sk_write_queue);
- spin_lock_init(&newsk->sk_dst_lock);
rwlock_init(&newsk->sk_callback_lock);
lockdep_set_class_and_name(&newsk->sk_callback_lock,
af_callback_keys + newsk->sk_family,
@@ -1553,7 +1551,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
*/
is_charged = sk_filter_charge(newsk, filter);
- if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk))) {
+ if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
newsk->sk_destruct = NULL;
@@ -1607,7 +1605,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
- __sk_dst_set(sk, dst);
+ sk_dst_set(sk, dst);
sk->sk_route_caps = dst->dev->features;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
@@ -1815,7 +1813,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
- clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
for (;;) {
if (!timeo)
break;
@@ -1861,7 +1859,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
break;
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
if (!timeo)
@@ -2048,9 +2046,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
DEFINE_WAIT(wait);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
finish_wait(sk_sleep(sk), &wait);
return rc;
}
@@ -2388,7 +2386,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
} else
sk->sk_wq = NULL;
- spin_lock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
diff --git a/net/core/stream.c b/net/core/stream.c
index d70f77a0c889..b96f7a79e544 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -39,7 +39,7 @@ void sk_stream_write_space(struct sock *sk)
wake_up_interruptible_poll(&wq->wait, POLLOUT |
POLLWRNORM | POLLWRBAND);
if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
- sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT);
+ sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
rcu_read_unlock();
}
}
@@ -126,7 +126,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
while (1) {
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
@@ -139,7 +139,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
}
if (signal_pending(current))
goto do_interrupted;
- clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (sk_stream_memory_free(sk) && !vm_wait)
break;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index db5fc2440a23..9c6d0508e63a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
&ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
fl6.daddr = ireq->ir_v6_rmt_addr;
- err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ rcu_read_lock();
+ err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ np->tclass);
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
@@ -387,6 +392,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *newnp;
const struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
@@ -453,7 +459,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
* comment in that function for the gory details. -acme
*/
- __ip6_dst_store(newsk, dst, NULL, NULL);
+ ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
newdp6 = (struct dccp6_sock *)newsk;
@@ -488,13 +494,15 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
- if (np->opt != NULL)
- newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ }
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- if (newnp->opt != NULL)
- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
- newnp->opt->opt_flen);
+ if (opt)
+ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+ opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
@@ -757,6 +765,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
+ struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -856,7 +865,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
@@ -873,12 +883,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
- __ip6_dst_store(sk, dst, NULL, NULL);
+ ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
- if (np->opt != NULL)
- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
- np->opt->opt_nflen);
+ if (opt)
+ icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b5cf13a28009..41e65804ddf5 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -339,8 +339,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,
if (sk_stream_is_writeable(sk)) {
mask |= POLLOUT | POLLWRNORM;
} else { /* send SIGIO later */
- set_bit(SOCK_ASYNC_NOSPACE,
- &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
/* Race breaker. If space is freed after
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 675cf94e04f8..13d6b1a6e0fc 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
{
struct sock *sk;
+ if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ return -EINVAL;
+
if (!net_eq(net, &init_net))
return -EAFNOSUPPORT;
@@ -1747,9 +1750,9 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
}
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target));
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
finish_wait(sk_sleep(sk), &wait);
}
@@ -2004,10 +2007,10 @@ static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
}
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
sk_wait_event(sk, &timeo,
!dn_queue_too_long(scp, queue, flags));
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
finish_wait(sk_sleep(sk), &wait);
continue;
}
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index 4677b6fa6dda..ecc28cff08ab 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -67,7 +67,7 @@
* Returns the size of the result on success, -ve error code otherwise.
*/
int dns_query(const char *type, const char *name, size_t namelen,
- const char *options, char **_result, time_t *_expiry)
+ const char *options, char **_result, time64_t *_expiry)
{
struct key *rkey;
const struct user_key_payload *upayload;
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 35a9788bb3ae..c7d1adca30d8 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -312,7 +312,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, u8 type)
return;
out:
- WARN_ON_ONCE("HSR: Could not send supervision frame\n");
+ WARN_ONCE(1, "HSR: Could not send supervision frame\n");
kfree_skb(skb);
}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 11c4ca13ec3b..5c5db6636704 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -257,6 +257,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
int try_loading_module = 0;
int err;
+ if (protocol < 0 || protocol >= IPPROTO_MAX)
+ return -EINVAL;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index cc8f3e506cde..473447593060 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1155,6 +1155,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_changeupper_info *info;
struct in_device *in_dev;
struct net *net = dev_net(dev);
unsigned int flags;
@@ -1193,6 +1194,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
case NETDEV_CHANGEMTU:
rt_cache_flush(net);
break;
+ case NETDEV_CHANGEUPPER:
+ info = ptr;
+ /* flush all routes if dev is linked to or unlinked from
+ * an L3 master device (e.g., VRF)
+ */
+ if (info->upper_dev && netif_is_l3_master(info->upper_dev))
+ fib_disable_ip(dev, NETDEV_DOWN, true);
+ break;
}
return NOTIFY_DONE;
}
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index e0fcbbbcfe54..bd903fe0f750 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -24,6 +24,7 @@ struct fou {
u16 type;
struct udp_offload udp_offloads;
struct list_head list;
+ struct rcu_head rcu;
};
#define FOU_F_REMCSUM_NOPARTIAL BIT(0)
@@ -417,7 +418,7 @@ static void fou_release(struct fou *fou)
list_del(&fou->list);
udp_tunnel_sock_release(sock);
- kfree(fou);
+ kfree_rcu(fou, rcu);
}
static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6baf36e11808..05e4cba14162 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2126,7 +2126,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
ASSERT_RTNL();
in_dev = ip_mc_find_dev(net, imr);
- if (!in_dev) {
+ if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) {
ret = -ENODEV;
goto out;
}
@@ -2147,7 +2147,8 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
*imlp = iml->next_rcu;
- ip_mc_dec_group(in_dev, group);
+ if (in_dev)
+ ip_mc_dec_group(in_dev, group);
/* decrease mem now to avoid the memleak warning */
atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index f34c31defafe..a09fb0dec725 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -253,9 +253,6 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
p.i_key = p.o_key = 0;
p.i_flags = p.o_flags = 0;
- if (p.iph.ttl)
- p.iph.frag_off |= htons(IP_DF);
-
err = ip_tunnel_ioctl(dev, &p, cmd);
if (err)
return err;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 92dd4b74d513..c3a38353f5dc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -350,7 +350,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
static void ipmr_free_table(struct mr_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -441,10 +441,6 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
return dev;
failure:
- /* allow the register to be completed before unregistering. */
- rtnl_unlock();
- rtnl_lock();
-
unregister_netdevice(dev);
return NULL;
}
@@ -540,10 +536,6 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
return dev;
failure:
- /* allow the register to be completed before unregistering. */
- rtnl_unlock();
- rtnl_lock();
-
unregister_netdevice(dev);
return NULL;
}
@@ -1208,7 +1200,7 @@ 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)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1217,8 +1209,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
/* Shut down all active vif entries */
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif_table[i].flags & VIFF_STATIC))
- vif_delete(mrt, i, 0, &list);
+ if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+ continue;
+ vif_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
@@ -1226,7 +1219,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
for (i = 0; i < MFC_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
list_del_rcu(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1261,7 +1254,7 @@ static void mrtsock_destruct(struct sock *sk)
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
}
}
rtnl_unlock();
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index a35584176535..c187c60e3e0c 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -60,6 +60,7 @@ config NFT_REJECT_IPV4
config NFT_DUP_IPV4
tristate "IPv4 nf_tables packet duplication support"
+ depends on !NF_CONNTRACK || NF_CONNTRACK
select NF_DUP_IPV4
help
This module enables IPv4 packet duplication support for nf_tables.
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 63e5be0abd86..bc35f1842512 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -601,8 +601,11 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
- if (!saddr && ipc.oif)
- l3mdev_get_saddr(net, ipc.oif, &fl4);
+ if (!saddr && ipc.oif) {
+ err = l3mdev_get_saddr(net, ipc.oif, &fl4);
+ if (err < 0)
+ goto done;
+ }
if (!inet->hdrincl) {
rfv.msg = msg;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c1728771cf89..c82cca18c90f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -517,8 +517,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (sk_stream_is_writeable(sk)) {
mask |= POLLOUT | POLLWRNORM;
} else { /* send SIGIO later */
- set_bit(SOCK_ASYNC_NOSPACE,
- &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
/* Race breaker. If space is freed after
@@ -906,7 +905,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
goto out_err;
}
- clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
mss_now = tcp_send_mss(sk, &size_goal, flags);
copied = 0;
@@ -1134,7 +1133,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
}
/* This should be in poll */
- clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
mss_now = tcp_send_mss(sk, &size_goal, flags);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fdd88c3803a6..d4c51158470f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2478,6 +2478,9 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
int newly_acked_sacked = prior_unsacked -
(tp->packets_out - tp->sacked_out);
+ if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
+ return;
+
tp->prr_delivered += newly_acked_sacked;
if (delta < 0) {
u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
@@ -4481,19 +4484,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
{
struct sk_buff *skb;
+ int err = -ENOMEM;
+ int data_len = 0;
bool fragstolen;
if (size == 0)
return 0;
- skb = alloc_skb(size, sk->sk_allocation);
+ if (size > PAGE_SIZE) {
+ int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+ data_len = npages << PAGE_SHIFT;
+ size = data_len + (size & ~PAGE_MASK);
+ }
+ skb = alloc_skb_with_frags(size - data_len, data_len,
+ PAGE_ALLOC_COSTLY_ORDER,
+ &err, sk->sk_allocation);
if (!skb)
goto err;
+ skb_put(skb, size - data_len);
+ skb->data_len = data_len;
+ skb->len = size;
+
if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
goto err_free;
- if (memcpy_from_msg(skb_put(skb, size), msg, size))
+ err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+ if (err)
goto err_free;
TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4509,7 +4527,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
err_free:
kfree_skb(skb);
err:
- return -ENOMEM;
+ return err;
+
}
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5667,6 +5686,7 @@ discard:
}
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ tp->copied_seq = tp->rcv_nxt;
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ba09016d1bfd..d8841a2f1569 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -921,7 +921,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
}
md5sig = rcu_dereference_protected(tp->md5sig_info,
- sock_owned_by_user(sk));
+ sock_owned_by_user(sk) ||
+ lockdep_is_held(&sk->sk_lock.slock));
if (!md5sig) {
md5sig = kmalloc(sizeof(*md5sig), gfp);
if (!md5sig)
@@ -1492,7 +1493,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
if (likely(sk->sk_rx_dst))
skb_dst_drop(skb);
else
- skb_dst_force(skb);
+ skb_dst_force_safe(skb);
__skb_queue_tail(&tp->ucopy.prequeue, skb);
tp->ucopy.memory += skb->truesize;
@@ -1720,8 +1721,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- if (dst) {
- dst_hold(dst);
+ if (dst && dst_hold_safe(dst)) {
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cb7ca569052c..9bfc39ff2285 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3150,7 +3150,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
- int syn_loss = 0, space, err = 0, copied;
+ int syn_loss = 0, space, err = 0;
unsigned long last_syn_loss = 0;
struct sk_buff *syn_data;
@@ -3188,17 +3188,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
goto fallback;
syn_data->ip_summed = CHECKSUM_PARTIAL;
memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
- copied = copy_from_iter(skb_put(syn_data, space), space,
- &fo->data->msg_iter);
- if (unlikely(!copied)) {
- kfree_skb(syn_data);
- goto fallback;
- }
- if (copied != space) {
- skb_trim(syn_data, copied);
- space = copied;
+ if (space) {
+ int copied = copy_from_iter(skb_put(syn_data, space), space,
+ &fo->data->msg_iter);
+ if (unlikely(!copied)) {
+ kfree_skb(syn_data);
+ goto fallback;
+ }
+ if (copied != space) {
+ skb_trim(syn_data, copied);
+ space = copied;
+ }
}
-
/* No more data pending in inet_wait_for_connect() */
if (space == fo->size)
fo->data = NULL;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c9c716a483e4..193ba1fa8a9a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -168,7 +168,7 @@ static int tcp_write_timeout(struct sock *sk)
dst_negative_advice(sk);
if (tp->syn_fastopen || tp->syn_data)
tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
- if (tp->syn_data)
+ if (tp->syn_data && icsk->icsk_retransmits == 1)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
}
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
syn_set = true;
} else {
if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+ /* Some middle-boxes may black-hole Fast Open _after_
+ * the handshake. Therefore we conservatively disable
+ * Fast Open on this path on recurring timeouts with
+ * few or zero bytes acked after Fast Open.
+ */
+ if (tp->syn_data_acked &&
+ tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+ tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+ if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+ }
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24ec14f9825c..c43890848641 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -100,7 +100,6 @@
#include <linux/slab.h>
#include <net/tcp_states.h>
#include <linux/skbuff.h>
-#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
@@ -1026,8 +1025,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flow_flags,
faddr, saddr, dport, inet->inet_sport);
- if (!saddr && ipc.oif)
- l3mdev_get_saddr(net, ipc.oif, fl4);
+ if (!saddr && ipc.oif) {
+ err = l3mdev_get_saddr(net, ipc.oif, fl4);
+ if (err < 0)
+ goto out;
+ }
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 1e0c3c835a63..7b0edb37a115 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -259,7 +259,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
xfrm_dst_ifdown(dst, dev);
}
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
.family = AF_INET,
.gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
@@ -273,7 +273,7 @@ static struct dst_ops xfrm4_dst_ops = {
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.family = AF_INET,
- .dst_ops = &xfrm4_dst_ops,
+ .dst_ops = &xfrm4_dst_ops_template,
.dst_lookup = xfrm4_dst_lookup,
.get_saddr = xfrm4_get_saddr,
.decode_session = _decode_session4,
@@ -295,7 +295,7 @@ static struct ctl_table xfrm4_policy_table[] = {
{ }
};
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
@@ -323,7 +323,7 @@ err_alloc:
return -ENOMEM;
}
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
{
struct ctl_table *table;
@@ -335,12 +335,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
if (!net_eq(net, &init_net))
kfree(table);
}
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+ return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+ int ret;
+
+ memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+ sizeof(xfrm4_dst_ops_template));
+ ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+ if (ret)
+ return ret;
+
+ ret = xfrm4_net_sysctl_init(net);
+ if (ret)
+ dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+ return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+ xfrm4_net_sysctl_exit(net);
+ dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
static struct pernet_operations __net_initdata xfrm4_net_ops = {
.init = xfrm4_net_init,
.exit = xfrm4_net_exit,
};
-#endif
static void __init xfrm4_policy_init(void)
{
@@ -349,13 +381,9 @@ static void __init xfrm4_policy_init(void)
void __init xfrm4_init(void)
{
- dst_entries_init(&xfrm4_dst_ops);
-
xfrm4_state_init();
xfrm4_policy_init();
xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
register_pernet_subsys(&xfrm4_net_ops);
-#endif
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d84742f003a9..1f21087accab 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -350,6 +350,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
setup_timer(&ndev->rs_timer, addrconf_rs_timer,
(unsigned long)ndev);
memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
+
+ if (ndev->cnf.stable_secret.initialized)
+ ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
+ else
+ ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64;
+
ndev->cnf.mtu6 = dev->mtu;
ndev->cnf.sysctl = NULL;
ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
@@ -2455,7 +2461,7 @@ ok:
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
if (in6_dev->cnf.optimistic_dad &&
!net->ipv6.devconf_all->forwarding && sllao)
- addr_flags = IFA_F_OPTIMISTIC;
+ addr_flags |= IFA_F_OPTIMISTIC;
#endif
/* Do not allow to create too much of autoconfigured
@@ -3642,7 +3648,7 @@ static void addrconf_dad_work(struct work_struct *w)
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
- ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, NULL);
+ ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any);
out:
in6_ifa_put(ifp);
rtnl_unlock();
@@ -5363,13 +5369,10 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write,
goto out;
}
- if (!write) {
- err = snprintf(str, sizeof(str), "%pI6",
- &secret->secret);
- if (err >= sizeof(str)) {
- err = -EIO;
- goto out;
- }
+ err = snprintf(str, sizeof(str), "%pI6", &secret->secret);
+ if (err >= sizeof(str)) {
+ err = -EIO;
+ goto out;
}
err = proc_dostring(&lctl, write, buffer, lenp, ppos);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 882124ebb438..a8f6986dcbe5 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -552,7 +552,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh)
rcu_read_lock();
p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
- if (p && ip6addrlbl_hold(p))
+ if (p && !ip6addrlbl_hold(p))
p = NULL;
lseq = ip6addrlbl_table.seq;
rcu_read_unlock();
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 44bb66bde0e2..9f5137cd604e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
int try_loading_module = 0;
int err;
+ if (protocol < 0 || protocol >= IPPROTO_MAX)
+ return -EINVAL;
+
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
@@ -428,9 +431,11 @@ void inet6_destroy_sock(struct sock *sk)
/* Free tx options */
- opt = xchg(&np->opt, NULL);
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
}
EXPORT_SYMBOL_GPL(inet6_destroy_sock);
@@ -659,7 +664,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+ &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
@@ -668,7 +676,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
return PTR_ERR(dst);
}
- __ip6_dst_store(sk, dst, NULL, NULL);
+ ip6_dst_store(sk, dst, NULL, NULL);
}
return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index d70b0238f468..517c55b01ba8 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- opt = flowlabel ? flowlabel->opt : np->opt;
+ rcu_read_lock();
+ opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
final_p = fl6_update_dst(&fl6, opt, &final);
+ rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index ce203b0402be..ea7c4d64a00a 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
*((char **)&opt2->dst1opt) += dif;
if (opt2->srcrt)
*((char **)&opt2->srcrt) += dif;
+ atomic_set(&opt2->refcnt, 1);
}
return opt2;
}
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
return ERR_PTR(-ENOBUFS);
memset(opt2, 0, tot_len);
-
+ atomic_set(&opt2->refcnt, 1);
opt2->tot_len = tot_len;
p = (char *)(opt2 + 1);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 36c5a98b0472..0a37ddc7af51 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -834,11 +834,6 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
}
-/*
- * Special lock-class for __icmpv6_sk:
- */
-static struct lock_class_key icmpv6_socket_sk_dst_lock_key;
-
static int __net_init icmpv6_sk_init(struct net *net)
{
struct sock *sk;
@@ -860,15 +855,6 @@ static int __net_init icmpv6_sk_init(struct net *net)
net->ipv6.icmp_sk[i] = sk;
- /*
- * Split off their lock-class, because sk->sk_dst_lock
- * gets used from softirqs, which is safe for
- * __icmpv6_sk (because those never get directly used
- * via userspace syscalls), but unsafe for normal sockets.
- */
- lockdep_set_class(&sk->sk_dst_lock,
- &icmpv6_socket_sk_dst_lock_key);
-
/* Enough space for 2 64K ICMP packets, including
* sk_buff struct overhead.
*/
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 5d1c7cee2cb2..a7ca2cde2ecb 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -78,7 +78,9 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = proto;
fl6->daddr = ireq->ir_v6_rmt_addr;
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
fl6->saddr = ireq->ir_v6_loc_addr;
fl6->flowi6_oif = ireq->ir_iif;
fl6->flowi6_mark = ireq->ir_mark;
@@ -109,14 +111,6 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
static inline
-void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst,
- const struct in6_addr *daddr,
- const struct in6_addr *saddr)
-{
- __ip6_dst_store(sk, dst, daddr, saddr);
-}
-
-static inline
struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
{
return __sk_dst_check(sk, cookie);
@@ -142,14 +136,16 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
fl6->fl6_dport = inet->inet_dport;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
dst = __inet6_csk_dst_check(sk, np->dst_cookie);
if (!dst) {
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
if (!IS_ERR(dst))
- __inet6_csk_dst_store(sk, dst, NULL, NULL);
+ ip6_dst_store(sk, dst, NULL, NULL);
}
return dst;
}
@@ -175,7 +171,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
/* Restore final destination back after routing done */
fl6.daddr = sk->sk_v6_daddr;
- res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+ np->tclass);
rcu_read_unlock();
return res;
}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3c7b9310b33f..e5ea177d34c6 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1571,13 +1571,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
return -EEXIST;
} else {
t = nt;
-
- ip6gre_tunnel_unlink(ign, t);
- ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
- ip6gre_tunnel_link(ign, t);
- netdev_state_change(dev);
}
+ ip6gre_tunnel_unlink(ign, t);
+ ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]);
+ ip6gre_tunnel_link(ign, t);
return 0;
}
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index eabffbb89795..137fca42aaa6 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -177,7 +177,7 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t)
int i;
for_each_possible_cpu(i)
- ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL);
+ ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
}
EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index ad19136086dd..a10e77103c88 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
int cmd);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -334,7 +334,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
static void ip6mr_free_table(struct mr6_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -765,10 +765,6 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
return dev;
failure:
- /* allow the register to be completed before unregistering. */
- rtnl_unlock();
- rtnl_lock();
-
unregister_netdevice(dev);
return NULL;
}
@@ -1542,7 +1538,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1552,8 +1548,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
* Shut down all active vif entries
*/
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
- mif6_delete(mrt, i, &list);
+ if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+ continue;
+ mif6_delete(mrt, i, &list);
}
unregister_netdevice_many(&list);
@@ -1562,7 +1559,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
*/
for (i = 0; i < MFC6_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
write_lock_bh(&mrt_lock);
list_del(&c->list);
@@ -1625,7 +1622,7 @@ int ip6mr_sk_done(struct sock *sk)
net->ipv6.devconf_all);
write_unlock_bh(&mrt_lock);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
err = 0;
break;
}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e6956917c9..4449ad1f8114 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
}
- opt = xchg(&inet6_sk(sk)->opt, opt);
+ opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+ opt);
sk_dst_reset(sk);
return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
sk->sk_socket->ops = &inet_dgram_ops;
sk->sk_family = PF_INET;
}
- opt = xchg(&np->opt, NULL);
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+ NULL);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
pktopt = xchg(&np->pktoptions, NULL);
kfree_skb(pktopt);
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
break;
- opt = ipv6_renew_options(sk, np->opt, optname,
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ opt = ipv6_renew_options(sk, opt, optname,
(struct ipv6_opt_hdr __user *)optval,
optlen);
if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = 0;
opt = ipv6_update_options(sk, opt);
sticky_done:
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
break;
}
@@ -486,6 +493,7 @@ sticky_done:
break;
memset(opt, 0, sizeof(*opt));
+ atomic_set(&opt->refcnt, 1);
opt->tot_len = sizeof(*opt) + optlen;
retv = -EFAULT;
if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
retv = 0;
opt = ipv6_update_options(sk, opt);
done:
- if (opt)
- sock_kfree_s(sk, opt, opt->tot_len);
+ if (opt) {
+ atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+ txopt_put(opt);
+ }
break;
}
case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
+ struct ipv6_txoptions *opt;
lock_sock(sk);
- len = ipv6_getsockopt_sticky(sk, np->opt,
- optname, optval, len);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 3e0f855e1bea..84afb9a77278 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -556,8 +556,7 @@ static void ndisc_send_unsol_na(struct net_device *dev)
}
void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
- const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct sk_buff *oskb)
+ const struct in6_addr *daddr, const struct in6_addr *saddr)
{
struct sk_buff *skb;
struct in6_addr addr_buf;
@@ -593,9 +592,6 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
dev->dev_addr);
- if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb)
- skb_dst_copy(skb, oskb);
-
ndisc_send_skb(skb, daddr, saddr);
}
@@ -682,12 +678,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
"%s: trying to ucast probe in NUD_INVALID: %pI6\n",
__func__, target);
}
- ndisc_send_ns(dev, target, target, saddr, skb);
+ ndisc_send_ns(dev, target, target, saddr);
} else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
neigh_app_ns(neigh);
} else {
addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(dev, target, &mcaddr, saddr, skb);
+ ndisc_send_ns(dev, target, &mcaddr, saddr);
}
}
@@ -1187,7 +1183,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
*/
if (!in6_dev->cnf.accept_ra_from_local &&
ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
- NULL, 0)) {
+ in6_dev->dev, 0)) {
ND_PRINTK(2, info,
"RA from local address detected on dev: %s: default router ignored\n",
skb->dev->name);
@@ -1341,7 +1337,7 @@ skip_linkparms:
#ifdef CONFIG_IPV6_ROUTE_INFO
if (!in6_dev->cnf.accept_ra_from_local &&
ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
- NULL, 0)) {
+ in6_dev->dev, 0)) {
ND_PRINTK(2, info,
"RA from local address detected on dev: %s: router info ignored.\n",
skb->dev->name);
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index f6a024e141e5..e10a04c9cdc7 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -49,6 +49,7 @@ config NFT_REJECT_IPV6
config NFT_DUP_IPV6
tristate "IPv6 nf_tables packet duplication support"
+ depends on !NF_CONNTRACK || NF_CONNTRACK
select NF_DUP_IPV6
help
This module enables IPv6 packet duplication support for nf_tables.
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index d5efeb87350e..bab4441ed4e4 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
/* Creation primitives. */
static inline struct frag_queue *fq_find(struct net *net, __be32 id,
u32 user, struct in6_addr *src,
- struct in6_addr *dst, u8 ecn)
+ struct in6_addr *dst, int iif, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
arg.user = user;
arg.src = src;
arg.dst = dst;
+ arg.iif = iif;
arg.ecn = ecn;
local_bh_disable();
@@ -601,7 +602,7 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
fhdr = (struct frag_hdr *)skb_transport_header(clone);
fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- ip6_frag_ecn(hdr));
+ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
goto ret_orig;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index dc65ec198f7c..99140986e887 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -733,6 +733,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions opt_space;
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
@@ -839,8 +840,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
}
- if (!opt)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -906,6 +909,7 @@ done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
return err < 0 ? err : len;
do_confirm:
dst_confirm(dst);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 44e21a03cfc3..45f5ae51de65 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
return fq->id == arg->id &&
fq->user == arg->user &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst);
+ ipv6_addr_equal(&fq->daddr, arg->dst) &&
+ (arg->iif == fq->iif ||
+ !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)));
}
EXPORT_SYMBOL(ip6_frag_match);
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
static struct frag_queue *
fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, u8 ecn)
+ const struct in6_addr *dst, int iif, u8 ecn)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
+ arg.iif = iif;
arg.ecn = ecn;
hash = inet6_hash_frag(id, src, dst);
@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
}
fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- ip6_frag_ecn(hdr));
+ skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
if (fq) {
int ret;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6f01fe122abd..826e6aa44f8d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -523,7 +523,7 @@ static void rt6_probe_deferred(struct work_struct *w)
container_of(w, struct __rt6_probe_work, work);
addrconf_addr_solict_mult(&work->target, &mcaddr);
- ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL);
+ ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL);
dev_put(work->dev);
kfree(work);
}
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bb8f2fa1c7fb..eaf7ac496d50 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -222,7 +222,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = ireq->ir_v6_rmt_addr;
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c5429a636f1a..6b8a8a9091fa 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- if (dst) {
+ if (dst && dst_hold_safe(dst)) {
const struct rt6_info *rt = (const struct rt6_info *)dst;
- dst_hold(dst);
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
@@ -120,6 +119,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
+ struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
@@ -235,7 +235,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
- final_p = fl6_update_dst(&fl6, np->opt, &final);
+ opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+ final_p = fl6_update_dst(&fl6, opt, &final);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -255,7 +256,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
sk->sk_gso_type = SKB_GSO_TCPV6;
- __ip6_dst_store(sk, dst, NULL, NULL);
+ ip6_dst_store(sk, dst, NULL, NULL);
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp &&
@@ -263,9 +264,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
tcp_fetch_timewait_stamp(sk, dst);
icsk->icsk_ext_hdr_len = 0;
- if (np->opt)
- icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
- np->opt->opt_nflen);
+ if (opt)
+ icsk->icsk_ext_hdr_len = opt->opt_flen +
+ opt->opt_nflen;
tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
@@ -461,7 +462,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
- err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+ err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+ np->tclass);
err = net_xmit_eval(err);
}
@@ -972,6 +974,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
struct inet_request_sock *ireq;
struct ipv6_pinfo *newnp;
const struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt;
struct tcp6_sock *newtcp6sk;
struct inet_sock *newinet;
struct tcp_sock *newtp;
@@ -1056,7 +1059,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
*/
newsk->sk_gso_type = SKB_GSO_TCPV6;
- __ip6_dst_store(newsk, dst, NULL, NULL);
+ ip6_dst_store(newsk, dst, NULL, NULL);
inet6_sk_rx_dst_set(newsk, skb);
newtcp6sk = (struct tcp6_sock *)newsk;
@@ -1098,13 +1101,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
but we make one more one thing there: reattach optmem
to newsk.
*/
- if (np->opt)
- newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+ opt = rcu_dereference(np->opt);
+ if (opt) {
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ }
inet_csk(newsk)->icsk_ext_hdr_len = 0;
- if (newnp->opt)
- inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
- newnp->opt->opt_flen);
+ if (opt)
+ inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+ opt->opt_flen;
tcp_ca_openreq_child(newsk, dst);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 01bcb49619ee..9da3287a3923 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1110,6 +1110,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
struct ipv6_txoptions *opt = NULL;
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct flowi6 fl6;
struct dst_entry *dst;
@@ -1263,8 +1264,10 @@ do_udp_sendmsg:
opt = NULL;
connected = 0;
}
- if (!opt)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -1373,6 +1376,7 @@ release_dst:
out:
dst_release(dst);
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
if (!err)
return len;
/*
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 5643423fe67a..c074771a10f7 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -279,7 +279,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
xfrm_dst_ifdown(dst, dev);
}
-static struct dst_ops xfrm6_dst_ops = {
+static struct dst_ops xfrm6_dst_ops_template = {
.family = AF_INET6,
.gc = xfrm6_garbage_collect,
.update_pmtu = xfrm6_update_pmtu,
@@ -293,7 +293,7 @@ static struct dst_ops xfrm6_dst_ops = {
static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.family = AF_INET6,
- .dst_ops = &xfrm6_dst_ops,
+ .dst_ops = &xfrm6_dst_ops_template,
.dst_lookup = xfrm6_dst_lookup,
.get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
@@ -325,7 +325,7 @@ static struct ctl_table xfrm6_policy_table[] = {
{ }
};
-static int __net_init xfrm6_net_init(struct net *net)
+static int __net_init xfrm6_net_sysctl_init(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
@@ -353,7 +353,7 @@ err_alloc:
return -ENOMEM;
}
-static void __net_exit xfrm6_net_exit(struct net *net)
+static void __net_exit xfrm6_net_sysctl_exit(struct net *net)
{
struct ctl_table *table;
@@ -365,24 +365,52 @@ static void __net_exit xfrm6_net_exit(struct net *net)
if (!net_eq(net, &init_net))
kfree(table);
}
+#else /* CONFIG_SYSCTL */
+static int inline xfrm6_net_sysctl_init(struct net *net)
+{
+ return 0;
+}
+
+static void inline xfrm6_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm6_net_init(struct net *net)
+{
+ int ret;
+
+ memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template,
+ sizeof(xfrm6_dst_ops_template));
+ ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops);
+ if (ret)
+ return ret;
+
+ ret = xfrm6_net_sysctl_init(net);
+ if (ret)
+ dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+
+ return ret;
+}
+
+static void __net_exit xfrm6_net_exit(struct net *net)
+{
+ xfrm6_net_sysctl_exit(net);
+ dst_entries_destroy(&net->xfrm.xfrm6_dst_ops);
+}
static struct pernet_operations xfrm6_net_ops = {
.init = xfrm6_net_init,
.exit = xfrm6_net_exit,
};
-#endif
int __init xfrm6_init(void)
{
int ret;
- dst_entries_init(&xfrm6_dst_ops);
-
ret = xfrm6_policy_init();
- if (ret) {
- dst_entries_destroy(&xfrm6_dst_ops);
+ if (ret)
goto out;
- }
ret = xfrm6_state_init();
if (ret)
goto out_policy;
@@ -391,9 +419,7 @@ int __init xfrm6_init(void)
if (ret)
goto out_state;
-#ifdef CONFIG_SYSCTL
register_pernet_subsys(&xfrm6_net_ops);
-#endif
out:
return ret;
out_state:
@@ -405,11 +431,8 @@ out_policy:
void xfrm6_fini(void)
{
-#ifdef CONFIG_SYSCTL
unregister_pernet_subsys(&xfrm6_net_ops);
-#endif
xfrm6_protocol_fini();
xfrm6_policy_fini();
xfrm6_state_fini();
- dst_entries_destroy(&xfrm6_dst_ops);
}
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index e6aa48b5395c..923abd6b3064 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1086,6 +1086,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol,
struct sock *sk;
struct irda_sock *self;
+ if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+ return -EINVAL;
+
if (net != &init_net)
return -EAFNOSUPPORT;
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index fcb2752419c6..435608c4306d 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1483,7 +1483,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
if (sock_writeable(sk) && iucv_below_msglim(sk))
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
return mask;
}
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index aca38d8aed8e..a2c8747d2936 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
struct in6_addr *daddr, *final_p, final;
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions *opt = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
opt = NULL;
}
- if (opt == NULL)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
+ txopt_put(opt_to_free);
return err < 0 ? err : len;
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index a758eb84e8f0..ff757181b0a8 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -500,7 +500,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
/* send AddBA request */
ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
tid_tx->dialog_token, start_seq_num,
- local->hw.max_tx_aggregation_subframes,
+ IEEE80211_MAX_AMPDU_BUF,
tid_tx->timeout);
}
@@ -926,6 +926,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK;
tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6;
+ buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes);
mutex_lock(&sta->ampdu_mlme.mtx);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index c2bd1b6a6922..c12f348138ac 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1169,8 +1169,7 @@ static int sta_apply_parameters(struct ieee80211_local *local,
* rc isn't initialized here yet, so ignore it
*/
__ieee80211_vht_handle_opmode(sdata, sta,
- params->opmode_notif,
- band, false);
+ params->opmode_notif, band);
}
if (ieee80211_vif_is_mesh(&sdata->vif))
@@ -3454,8 +3453,12 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
goto out_unlock;
}
} else {
- /* for cookie below */
- ack_skb = skb;
+ /* Assign a dummy non-zero cookie, it's not sent to
+ * userspace in this case but we rely on its value
+ * internally in the need_offchan case to distinguish
+ * mgmt-tx from remain-on-channel.
+ */
+ *cookie = 0xffffffff;
}
if (!need_offchan) {
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index d832bd59236b..5322b4c71630 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1709,10 +1709,10 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta);
void ieee80211_sta_set_rx_nss(struct sta_info *sta);
u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, u8 opmode,
- enum ieee80211_band band, bool nss_only);
+ enum ieee80211_band band);
void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, u8 opmode,
- enum ieee80211_band band, bool nss_only);
+ enum ieee80211_band band);
void ieee80211_apply_vhtcap_overrides(struct ieee80211_sub_if_data *sdata,
struct ieee80211_sta_vht_cap *vht_cap);
void ieee80211_get_vht_mask_from_cap(__le16 vht_cap,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d0dc1bfaeec2..c9e325d2e120 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -76,7 +76,8 @@ bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
bool update_bss)
{
- if (__ieee80211_recalc_txpower(sdata) || update_bss)
+ if (__ieee80211_recalc_txpower(sdata) ||
+ (update_bss && ieee80211_sdata_running(sdata)))
ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER);
}
@@ -1861,6 +1862,7 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata)
unregister_netdevice(sdata->dev);
} else {
cfg80211_unregister_wdev(&sdata->wdev);
+ ieee80211_teardown_sdata(sdata);
kfree(sdata);
}
}
@@ -1870,7 +1872,6 @@ void ieee80211_sdata_stop(struct ieee80211_sub_if_data *sdata)
if (WARN_ON_ONCE(!test_bit(SDATA_STATE_RUNNING, &sdata->state)))
return;
ieee80211_do_stop(sdata, true);
- ieee80211_teardown_sdata(sdata);
}
void ieee80211_remove_interfaces(struct ieee80211_local *local)
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 858f6b1cb149..175ffcf7fb06 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -541,8 +541,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
NL80211_FEATURE_HT_IBSS |
NL80211_FEATURE_VIF_TXPOWER |
NL80211_FEATURE_MAC_ON_CREATE |
- NL80211_FEATURE_USERSPACE_MPM |
- NL80211_FEATURE_FULL_AP_CLIENT_STATE;
+ NL80211_FEATURE_USERSPACE_MPM;
if (!ops->hw_scan)
wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index b890e225a8f1..b3b44a5dd375 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -779,10 +779,8 @@ void mesh_plink_broken(struct sta_info *sta)
static void mesh_path_node_reclaim(struct rcu_head *rp)
{
struct mpath_node *node = container_of(rp, struct mpath_node, rcu);
- struct ieee80211_sub_if_data *sdata = node->mpath->sdata;
del_timer_sync(&node->mpath->timer);
- atomic_dec(&sdata->u.mesh.mpaths);
kfree(node->mpath);
kfree(node);
}
@@ -790,8 +788,9 @@ static void mesh_path_node_reclaim(struct rcu_head *rp)
/* needs to be called with the corresponding hashwlock taken */
static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node)
{
- struct mesh_path *mpath;
- mpath = node->mpath;
+ struct mesh_path *mpath = node->mpath;
+ struct ieee80211_sub_if_data *sdata = node->mpath->sdata;
+
spin_lock(&mpath->state_lock);
mpath->flags |= MESH_PATH_RESOLVING;
if (mpath->is_gate)
@@ -799,6 +798,7 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node)
hlist_del_rcu(&node->list);
call_rcu(&node->rcu, mesh_path_node_reclaim);
spin_unlock(&mpath->state_lock);
+ atomic_dec(&sdata->u.mesh.mpaths);
atomic_dec(&tbl->entries);
}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index b140cc6651f4..3aa04344942b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1379,21 +1379,26 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
*/
if (has_80211h_pwr &&
(!has_cisco_pwr || pwr_level_80211h <= pwr_level_cisco)) {
+ new_ap_level = pwr_level_80211h;
+
+ if (sdata->ap_power_level == new_ap_level)
+ return 0;
+
sdata_dbg(sdata,
"Limiting TX power to %d (%d - %d) dBm as advertised by %pM\n",
pwr_level_80211h, chan_pwr, pwr_reduction_80211h,
sdata->u.mgd.bssid);
- new_ap_level = pwr_level_80211h;
} else { /* has_cisco_pwr is always true here. */
+ new_ap_level = pwr_level_cisco;
+
+ if (sdata->ap_power_level == new_ap_level)
+ return 0;
+
sdata_dbg(sdata,
"Limiting TX power to %d dBm as advertised by %pM\n",
pwr_level_cisco, sdata->u.mgd.bssid);
- new_ap_level = pwr_level_cisco;
}
- if (sdata->ap_power_level == new_ap_level)
- return 0;
-
sdata->ap_power_level = new_ap_level;
if (__ieee80211_recalc_txpower(sdata))
return BSS_CHANGED_TXPOWER;
@@ -3575,7 +3580,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
if (sta && elems.opmode_notif)
ieee80211_vht_handle_opmode(sdata, sta, *elems.opmode_notif,
- rx_status->band, true);
+ rx_status->band);
mutex_unlock(&local->sta_mtx);
changed |= ieee80211_handle_pwr_constr(sdata, chan, mgmt,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 8bae5de0dc44..82af407fea7a 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2736,8 +2736,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode;
ieee80211_vht_handle_opmode(rx->sdata, rx->sta,
- opmode, status->band,
- false);
+ opmode, status->band);
goto handled;
}
default:
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 4aeca4b0c3cb..a413e52f7691 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -597,8 +597,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
/* We need to ensure power level is at max for scanning. */
ieee80211_hw_config(local, 0);
- if ((req->channels[0]->flags &
- IEEE80211_CHAN_NO_IR) ||
+ if ((req->channels[0]->flags & (IEEE80211_CHAN_NO_IR |
+ IEEE80211_CHAN_RADAR)) ||
!req->n_ssids) {
next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
} else {
@@ -645,7 +645,7 @@ ieee80211_scan_get_channel_time(struct ieee80211_channel *chan)
* TODO: channel switching also consumes quite some time,
* add that delay as well to get a better estimation
*/
- if (chan->flags & IEEE80211_CHAN_NO_IR)
+ if (chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR))
return IEEE80211_PASSIVE_CHANNEL_TIME;
return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME;
}
@@ -777,7 +777,8 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
*
* In any case, it is not necessary for a passive scan.
*/
- if (chan->flags & IEEE80211_CHAN_NO_IR || !scan_req->n_ssids) {
+ if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) ||
+ !scan_req->n_ssids) {
*next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
local->next_scan_state = SCAN_DECISION;
return;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 74058020b7d6..33344f5a66a8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1641,6 +1641,29 @@ void ieee80211_stop_device(struct ieee80211_local *local)
drv_stop(local);
}
+static void ieee80211_flush_completed_scan(struct ieee80211_local *local,
+ bool aborted)
+{
+ /* It's possible that we don't handle the scan completion in
+ * time during suspend, so if it's still marked as completed
+ * here, queue the work and flush it to clean things up.
+ * Instead of calling the worker function directly here, we
+ * really queue it to avoid potential races with other flows
+ * scheduling the same work.
+ */
+ if (test_bit(SCAN_COMPLETED, &local->scanning)) {
+ /* If coming from reconfiguration failure, abort the scan so
+ * we don't attempt to continue a partial HW scan - which is
+ * possible otherwise if (e.g.) the 2.4 GHz portion was the
+ * completed scan, and a 5 GHz portion is still pending.
+ */
+ if (aborted)
+ set_bit(SCAN_ABORTED, &local->scanning);
+ ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0);
+ flush_delayed_work(&local->scan_work);
+ }
+}
+
static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local)
{
struct ieee80211_sub_if_data *sdata;
@@ -1660,6 +1683,8 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local)
local->suspended = false;
local->in_reconfig = false;
+ ieee80211_flush_completed_scan(local, true);
+
/* scheduled scan clearly can't be running any more, but tell
* cfg80211 and clear local state
*/
@@ -1698,6 +1723,27 @@ static void ieee80211_assign_chanctx(struct ieee80211_local *local,
mutex_unlock(&local->chanctx_mtx);
}
+static void ieee80211_reconfig_stations(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_local *local = sdata->local;
+ struct sta_info *sta;
+
+ /* add STAs back */
+ mutex_lock(&local->sta_mtx);
+ list_for_each_entry(sta, &local->sta_list, list) {
+ enum ieee80211_sta_state state;
+
+ if (!sta->uploaded || sta->sdata != sdata)
+ continue;
+
+ for (state = IEEE80211_STA_NOTEXIST;
+ state < sta->sta_state; state++)
+ WARN_ON(drv_sta_state(local, sta->sdata, sta, state,
+ state + 1));
+ }
+ mutex_unlock(&local->sta_mtx);
+}
+
int ieee80211_reconfig(struct ieee80211_local *local)
{
struct ieee80211_hw *hw = &local->hw;
@@ -1833,50 +1879,11 @@ int ieee80211_reconfig(struct ieee80211_local *local)
WARN_ON(drv_add_chanctx(local, ctx));
mutex_unlock(&local->chanctx_mtx);
- list_for_each_entry(sdata, &local->interfaces, list) {
- if (!ieee80211_sdata_running(sdata))
- continue;
- ieee80211_assign_chanctx(local, sdata);
- }
-
sdata = rtnl_dereference(local->monitor_sdata);
if (sdata && ieee80211_sdata_running(sdata))
ieee80211_assign_chanctx(local, sdata);
}
- /* add STAs back */
- mutex_lock(&local->sta_mtx);
- list_for_each_entry(sta, &local->sta_list, list) {
- enum ieee80211_sta_state state;
-
- if (!sta->uploaded)
- continue;
-
- /* AP-mode stations will be added later */
- if (sta->sdata->vif.type == NL80211_IFTYPE_AP)
- continue;
-
- for (state = IEEE80211_STA_NOTEXIST;
- state < sta->sta_state; state++)
- WARN_ON(drv_sta_state(local, sta->sdata, sta, state,
- state + 1));
- }
- mutex_unlock(&local->sta_mtx);
-
- /* reconfigure tx conf */
- if (hw->queues >= IEEE80211_NUM_ACS) {
- list_for_each_entry(sdata, &local->interfaces, list) {
- if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
- sdata->vif.type == NL80211_IFTYPE_MONITOR ||
- !ieee80211_sdata_running(sdata))
- continue;
-
- for (i = 0; i < IEEE80211_NUM_ACS; i++)
- drv_conf_tx(local, sdata, i,
- &sdata->tx_conf[i]);
- }
- }
-
/* reconfigure hardware */
ieee80211_hw_config(local, ~0);
@@ -1889,6 +1896,22 @@ int ieee80211_reconfig(struct ieee80211_local *local)
if (!ieee80211_sdata_running(sdata))
continue;
+ ieee80211_assign_chanctx(local, sdata);
+
+ switch (sdata->vif.type) {
+ case NL80211_IFTYPE_AP_VLAN:
+ case NL80211_IFTYPE_MONITOR:
+ break;
+ default:
+ ieee80211_reconfig_stations(sdata);
+ /* fall through */
+ case NL80211_IFTYPE_AP: /* AP stations are handled later */
+ for (i = 0; i < IEEE80211_NUM_ACS; i++)
+ drv_conf_tx(local, sdata, i,
+ &sdata->tx_conf[i]);
+ break;
+ }
+
/* common change flags for all interface types */
changed = BSS_CHANGED_ERP_CTS_PROT |
BSS_CHANGED_ERP_PREAMBLE |
@@ -2074,17 +2097,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
mb();
local->resuming = false;
- /* It's possible that we don't handle the scan completion in
- * time during suspend, so if it's still marked as completed
- * here, queue the work and flush it to clean things up.
- * Instead of calling the worker function directly here, we
- * really queue it to avoid potential races with other flows
- * scheduling the same work.
- */
- if (test_bit(SCAN_COMPLETED, &local->scanning)) {
- ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0);
- flush_delayed_work(&local->scan_work);
- }
+ ieee80211_flush_completed_scan(local, false);
if (local->open_count && !reconfig_due_to_wowlan)
drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_SUSPEND);
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index ff1c798921a6..c38b2f07a919 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -378,7 +378,7 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta)
u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, u8 opmode,
- enum ieee80211_band band, bool nss_only)
+ enum ieee80211_band band)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_supported_band *sband;
@@ -401,9 +401,6 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
changed |= IEEE80211_RC_NSS_CHANGED;
}
- if (nss_only)
- return changed;
-
switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) {
case IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ:
sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_20;
@@ -430,13 +427,12 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, u8 opmode,
- enum ieee80211_band band, bool nss_only)
+ enum ieee80211_band band)
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band];
- u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode,
- band, nss_only);
+ u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, band);
if (changed > 0)
rate_control_rate_update(local, sband, sta, changed);
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c70d750148b6..c32fc411a911 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -27,6 +27,8 @@
*/
#define MAX_MP_SELECT_LABELS 4
+#define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1)
+
static int zero = 0;
static int label_limit = (1 << 20) - 1;
@@ -317,7 +319,13 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
}
}
- err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb);
+ /* If via wasn't specified then send out using device address */
+ if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC)
+ err = neigh_xmit(NEIGH_LINK_TABLE, out_dev,
+ out_dev->dev_addr, skb);
+ else
+ err = neigh_xmit(nh->nh_via_table, out_dev,
+ mpls_nh_via(rt, nh), skb);
if (err)
net_dbg_ratelimited("%s: packet transmission failed: %d\n",
__func__, err);
@@ -534,6 +542,10 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
if (!mpls_dev_get(dev))
goto errout;
+ if ((nh->nh_via_table == NEIGH_LINK_TABLE) &&
+ (dev->addr_len != nh->nh_via_alen))
+ goto errout;
+
RCU_INIT_POINTER(nh->nh_dev, dev);
return 0;
@@ -592,10 +604,14 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt,
goto errout;
}
- err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table,
- __mpls_nh_via(rt, nh));
- if (err)
- goto errout;
+ if (via) {
+ err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table,
+ __mpls_nh_via(rt, nh));
+ if (err)
+ goto errout;
+ } else {
+ nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC;
+ }
err = mpls_nh_assign_dev(net, rt, nh, oif);
if (err)
@@ -677,9 +693,6 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg,
nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST);
}
- if (!nla_via)
- goto errout;
-
err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
rtnh->rtnh_ifindex, nla_via,
nla_newdst);
@@ -1118,6 +1131,7 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->rc_label = LABEL_NOT_SPECIFIED;
cfg->rc_protocol = rtm->rtm_protocol;
+ cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC;
cfg->rc_nlflags = nlh->nlmsg_flags;
cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->rc_nlinfo.nlh = nlh;
@@ -1231,7 +1245,8 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
nla_put_labels(skb, RTA_NEWDST, nh->nh_labels,
nh->nh_label))
goto nla_put_failure;
- if (nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
+ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC &&
+ nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
nh->nh_via_alen))
goto nla_put_failure;
dev = rtnl_dereference(nh->nh_dev);
@@ -1257,7 +1272,8 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
nh->nh_labels,
nh->nh_label))
goto nla_put_failure;
- if (nla_put_via(skb, nh->nh_via_table,
+ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC &&
+ nla_put_via(skb, nh->nh_via_table,
mpls_nh_via(rt, nh),
nh->nh_via_alen))
goto nla_put_failure;
@@ -1319,7 +1335,8 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
if (nh->nh_dev)
payload += nla_total_size(4); /* RTA_OIF */
- payload += nla_total_size(2 + nh->nh_via_alen); /* RTA_VIA */
+ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) /* RTA_VIA */
+ payload += nla_total_size(2 + nh->nh_via_alen);
if (nh->nh_labels) /* RTA_NEWDST */
payload += nla_total_size(nh->nh_labels * 4);
} else {
@@ -1328,7 +1345,9 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
for_nexthops(rt) {
nhsize += nla_total_size(sizeof(struct rtnexthop));
- nhsize += nla_total_size(2 + nh->nh_via_alen);
+ /* RTA_VIA */
+ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC)
+ nhsize += nla_total_size(2 + nh->nh_via_alen);
if (nh->nh_labels)
nhsize += nla_total_size(nh->nh_labels * 4);
} endfor_nexthops(rt);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 67591aef9cae..64afd3d0b144 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -54,10 +54,10 @@ int mpls_output(struct net *net, struct sock *sk, struct sk_buff *skb)
unsigned int ttl;
/* Obtain the ttl */
- if (skb->protocol == htons(ETH_P_IP)) {
+ if (dst->ops->family == AF_INET) {
ttl = ip_hdr(skb)->ttl;
rt = (struct rtable *)dst;
- } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ } else if (dst->ops->family == AF_INET6) {
ttl = ipv6_hdr(skb)->hop_limit;
rt6 = (struct rt6_info *)dst;
} else {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 93cc4737018f..2cb429d34c03 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -89,6 +89,7 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
}
static void nft_ctx_init(struct nft_ctx *ctx,
+ struct net *net,
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
struct nft_af_info *afi,
@@ -96,7 +97,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
struct nft_chain *chain,
const struct nlattr * const *nla)
{
- ctx->net = sock_net(skb->sk);
+ ctx->net = net;
ctx->afi = afi;
ctx->table = table;
ctx->chain = chain;
@@ -672,15 +673,14 @@ err:
return ret;
}
-static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_newtable(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
const struct nlattr *name;
struct nft_af_info *afi;
struct nft_table *table;
- struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
u32 flags = 0;
struct nft_ctx ctx;
@@ -706,7 +706,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
- nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
return nf_tables_updtable(&ctx);
}
@@ -730,7 +730,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
INIT_LIST_HEAD(&table->sets);
table->flags = flags;
- nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
if (err < 0)
goto err3;
@@ -810,18 +810,17 @@ out:
return err;
}
-static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_deltable(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi;
struct nft_table *table;
- struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
- nft_ctx_init(&ctx, skb, nlh, NULL, NULL, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, NULL, NULL, NULL, nla);
if (family == AF_UNSPEC || nla[NFTA_TABLE_NAME] == NULL)
return nft_flush(&ctx, family);
@@ -1221,8 +1220,8 @@ static void nf_tables_chain_destroy(struct nft_chain *chain)
}
}
-static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_newchain(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
@@ -1232,7 +1231,6 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
struct nft_chain *chain;
struct nft_base_chain *basechain = NULL;
struct nlattr *ha[NFTA_HOOK_MAX + 1];
- struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
struct net_device *dev = NULL;
u8 policy = NF_ACCEPT;
@@ -1313,7 +1311,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
return PTR_ERR(stats);
}
- nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN,
sizeof(struct nft_trans_chain));
if (trans == NULL) {
@@ -1461,7 +1459,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
if (err < 0)
goto err1;
- nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN);
if (err < 0)
goto err2;
@@ -1476,15 +1474,14 @@ err1:
return err;
}
-static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_delchain(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi;
struct nft_table *table;
struct nft_chain *chain;
- struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
struct nft_ctx ctx;
@@ -1506,7 +1503,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
if (chain->use > 0)
return -EBUSY;
- nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
return nft_delchain(&ctx);
}
@@ -2010,13 +2007,12 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
static struct nft_expr_info *info;
-static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_newrule(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi;
- struct net *net = sock_net(skb->sk);
struct nft_table *table;
struct nft_chain *chain;
struct nft_rule *rule, *old_rule = NULL;
@@ -2075,7 +2071,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
return PTR_ERR(old_rule);
}
- nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
n = 0;
size = 0;
@@ -2176,13 +2172,12 @@ err1:
return err;
}
-static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_delrule(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi;
- struct net *net = sock_net(skb->sk);
struct nft_table *table;
struct nft_chain *chain = NULL;
struct nft_rule *rule;
@@ -2205,7 +2200,7 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
return PTR_ERR(chain);
}
- nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, chain, nla);
if (chain) {
if (nla[NFTA_RULE_HANDLE]) {
@@ -2344,12 +2339,11 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
[NFTA_SET_DESC_SIZE] = { .type = NLA_U32 },
};
-static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
+static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
- struct net *net = sock_net(skb->sk);
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi = NULL;
struct nft_table *table = NULL;
@@ -2371,7 +2365,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
return -ENOENT;
}
- nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
return 0;
}
@@ -2623,6 +2617,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
+ struct net *net = sock_net(skb->sk);
const struct nft_set *set;
struct nft_ctx ctx;
struct sk_buff *skb2;
@@ -2630,7 +2625,7 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
int err;
/* Verify existence before starting dump */
- err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
+ err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla);
if (err < 0)
return err;
@@ -2693,14 +2688,13 @@ static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
return 0;
}
-static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_newset(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
const struct nft_set_ops *ops;
struct nft_af_info *afi;
- struct net *net = sock_net(skb->sk);
struct nft_table *table;
struct nft_set *set;
struct nft_ctx ctx;
@@ -2798,7 +2792,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
if (IS_ERR(table))
return PTR_ERR(table);
- nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla);
set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME]);
if (IS_ERR(set)) {
@@ -2882,8 +2876,8 @@ static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set
nft_set_destroy(set);
}
-static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_delset(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
@@ -2896,7 +2890,7 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
if (nla[NFTA_SET_TABLE] == NULL)
return -EINVAL;
- err = nft_ctx_init_from_setattr(&ctx, skb, nlh, nla);
+ err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla);
if (err < 0)
return err;
@@ -3024,7 +3018,7 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX +
[NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 },
};
-static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
+static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
const struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
@@ -3033,7 +3027,6 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
struct nft_af_info *afi;
struct nft_table *table;
- struct net *net = sock_net(skb->sk);
afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
if (IS_ERR(afi))
@@ -3045,7 +3038,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
if (!trans && (table->flags & NFT_TABLE_INACTIVE))
return -ENOENT;
- nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
+ nft_ctx_init(ctx, net, skb, nlh, afi, table, NULL, nla);
return 0;
}
@@ -3135,6 +3128,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct net *net = sock_net(skb->sk);
const struct nft_set *set;
struct nft_set_dump_args args;
struct nft_ctx ctx;
@@ -3150,8 +3144,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
if (err < 0)
return err;
- err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla,
- false);
+ err = nft_ctx_init_from_elemattr(&ctx, net, cb->skb, cb->nlh,
+ (void *)nla, false);
if (err < 0)
return err;
@@ -3212,11 +3206,12 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
+ struct net *net = sock_net(skb->sk);
const struct nft_set *set;
struct nft_ctx ctx;
int err;
- err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
+ err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false);
if (err < 0)
return err;
@@ -3528,11 +3523,10 @@ err1:
return err;
}
-static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
- struct net *net = sock_net(skb->sk);
const struct nlattr *attr;
struct nft_set *set;
struct nft_ctx ctx;
@@ -3541,7 +3535,7 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
return -EINVAL;
- err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true);
+ err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, true);
if (err < 0)
return err;
@@ -3623,8 +3617,8 @@ err1:
return err;
}
-static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
- const struct nlmsghdr *nlh,
+static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
+ struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[])
{
const struct nlattr *attr;
@@ -3635,7 +3629,7 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
return -EINVAL;
- err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
+ err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, false);
if (err < 0)
return err;
@@ -4030,7 +4024,8 @@ static int nf_tables_abort(struct sk_buff *skb)
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
- list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+ list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
+ list) {
switch (trans->msg_type) {
case NFT_MSG_NEWTABLE:
if (nft_trans_table_update(trans)) {
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
index 7b9c053ba750..edb3502f2016 100644
--- a/net/netfilter/nf_tables_netdev.c
+++ b/net/netfilter/nf_tables_netdev.c
@@ -94,7 +94,7 @@ nft_do_chain_netdev(void *priv, struct sk_buff *skb,
{
struct nft_pktinfo pkt;
- switch (eth_hdr(skb)->h_proto) {
+ switch (skb->protocol) {
case htons(ETH_P_IP):
nft_netdev_set_pktinfo_ipv4(&pkt, skb, state);
break;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 46453ab318db..77afe913d03d 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -295,8 +295,6 @@ replay:
if (!skb)
return netlink_ack(oskb, nlh, -ENOMEM);
- skb->sk = oskb->sk;
-
nfnl_lock(subsys_id);
ss = rcu_dereference_protected(table[subsys_id].subsys,
lockdep_is_held(&table[subsys_id].mutex));
@@ -381,7 +379,7 @@ replay:
goto ack;
if (nc->call_batch) {
- err = nc->call_batch(net->nfnl, skb, nlh,
+ err = nc->call_batch(net, net->nfnl, skb, nlh,
(const struct nlattr **)cda);
}
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 7d81d280cb4f..861c6615253b 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -365,8 +365,9 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
break;
}
+ nfnl_ct = rcu_dereference(nfnl_ct_hook);
+
if (queue->flags & NFQA_CFG_F_CONNTRACK) {
- nfnl_ct = rcu_dereference(nfnl_ct_hook);
if (nfnl_ct != NULL) {
ct = nfnl_ct->get_ct(entskb, &ctinfo);
if (ct != NULL)
@@ -1064,9 +1065,10 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
if (entry == NULL)
return -ENOENT;
+ /* rcu lock already held from nfnl->call_rcu. */
+ nfnl_ct = rcu_dereference(nfnl_ct_hook);
+
if (nfqa[NFQA_CT]) {
- /* rcu lock already held from nfnl->call_rcu. */
- nfnl_ct = rcu_dereference(nfnl_ct_hook);
if (nfnl_ct != NULL)
ct = nfqnl_ct_parse(nfnl_ct, nlh, nfqa, entry, &ctinfo);
}
@@ -1417,6 +1419,7 @@ static int __init nfnetlink_queue_init(void)
cleanup_netlink_notifier:
netlink_unregister_notifier(&nfqnl_rtnl_notifier);
+ unregister_pernet_subsys(&nfnl_queue_net_ops);
out:
return status;
}
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 8cbca3432f90..939921532764 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -366,6 +366,7 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
goto nla_put_failure;
switch (priv->key) {
+ case NFT_CT_L3PROTOCOL:
case NFT_CT_PROTOCOL:
case NFT_CT_SRC:
case NFT_CT_DST:
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index b7de0da46acd..ecf0a0196f18 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -572,7 +572,7 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock,
if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED)
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
pr_debug("mask 0x%x\n", mask);
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index c2cc11168fd5..e004067ec24a 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -53,6 +53,8 @@ struct ovs_conntrack_info {
struct md_labels labels;
};
+static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info);
+
static u16 key_to_nfproto(const struct sw_flow_key *key)
{
switch (ntohs(key->eth.type)) {
@@ -141,6 +143,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state,
* previously sent the packet to conntrack via the ct action.
*/
static void ovs_ct_update_key(const struct sk_buff *skb,
+ const struct ovs_conntrack_info *info,
struct sw_flow_key *key, bool post_ct)
{
const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
@@ -158,13 +161,15 @@ static void ovs_ct_update_key(const struct sk_buff *skb,
zone = nf_ct_zone(ct);
} else if (post_ct) {
state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
+ if (info)
+ zone = &info->zone;
}
__ovs_ct_update_key(key, state, zone, ct);
}
void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
{
- ovs_ct_update_key(skb, key, false);
+ ovs_ct_update_key(skb, NULL, key, false);
}
int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb)
@@ -418,7 +423,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
}
}
- ovs_ct_update_key(skb, key, true);
+ ovs_ct_update_key(skb, info, key, true);
return 0;
}
@@ -693,6 +698,10 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
OVS_NLERR(log, "Failed to allocate conntrack template");
return -ENOMEM;
}
+
+ __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
+ nf_conntrack_get(&ct_info.ct->ct_general);
+
if (helper) {
err = ovs_ct_add_helper(&ct_info, helper, key, log);
if (err)
@@ -704,11 +713,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
if (err)
goto err_free_ct;
- __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
- nf_conntrack_get(&ct_info.ct->ct_general);
return 0;
err_free_ct:
- nf_conntrack_free(ct_info.ct);
+ __ovs_ct_free_action(&ct_info);
return err;
}
@@ -750,6 +757,11 @@ void ovs_ct_free_action(const struct nlattr *a)
{
struct ovs_conntrack_info *ct_info = nla_data(a);
+ __ovs_ct_free_action(ct_info);
+}
+
+static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
+{
if (ct_info->helper)
module_put(ct_info->helper->me);
if (ct_info->ct)
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index a7a80a6b77b0..653d073bae45 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -58,7 +58,7 @@ void ovs_dp_notify_wq(struct work_struct *work)
struct hlist_node *n;
hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
- if (vport->ops->type != OVS_VPORT_TYPE_NETDEV)
+ if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
continue;
if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH))
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 907d6fd28ede..d1bd4a45ca2d 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2434,7 +2434,10 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
if (!start)
return -EMSGSIZE;
- err = ovs_nla_put_tunnel_info(skb, tun_info);
+ err = ip_tun_to_nlattr(skb, &tun_info->key,
+ ip_tunnel_info_opts(tun_info),
+ tun_info->options_len,
+ ip_tunnel_info_af(tun_info));
if (err)
return err;
nla_nest_end(skb, start);
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index efb736bb6855..e41cd12d9b2d 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -117,7 +117,6 @@ static struct vport_ops ovs_geneve_vport_ops = {
.destroy = ovs_netdev_tunnel_destroy,
.get_options = geneve_get_options,
.send = dev_queue_xmit,
- .owner = THIS_MODULE,
};
static int __init ovs_geneve_tnl_init(void)
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index c3257d78d3d2..7f8897f33a67 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -89,7 +89,6 @@ static struct vport_ops ovs_gre_vport_ops = {
.create = gre_create,
.send = dev_queue_xmit,
.destroy = ovs_netdev_tunnel_destroy,
- .owner = THIS_MODULE,
};
static int __init ovs_gre_tnl_init(void)
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index b327368a3848..6b0190b987ec 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -180,9 +180,13 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
ovs_netdev_detach_dev(vport);
- /* Early release so we can unregister the device */
+ /* We can be invoked by both explicit vport deletion and
+ * underlying netdev deregistration; delete the link only
+ * if it's not already shutting down.
+ */
+ if (vport->dev->reg_state == NETREG_REGISTERED)
+ rtnl_delete_link(vport->dev);
dev_put(vport->dev);
- rtnl_delete_link(vport->dev);
vport->dev = NULL;
rtnl_unlock();
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 0ac0fd004d7e..31cbc8c5c7db 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -71,7 +71,7 @@ static struct hlist_head *hash_bucket(const struct net *net, const char *name)
return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
}
-int ovs_vport_ops_register(struct vport_ops *ops)
+int __ovs_vport_ops_register(struct vport_ops *ops)
{
int err = -EEXIST;
struct vport_ops *o;
@@ -87,7 +87,7 @@ errout:
ovs_unlock();
return err;
}
-EXPORT_SYMBOL_GPL(ovs_vport_ops_register);
+EXPORT_SYMBOL_GPL(__ovs_vport_ops_register);
void ovs_vport_ops_unregister(struct vport_ops *ops)
{
@@ -256,8 +256,8 @@ int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
*
* @vport: vport to delete.
*
- * Detaches @vport from its datapath and destroys it. It is possible to fail
- * for reasons such as lack of memory. ovs_mutex must be held.
+ * Detaches @vport from its datapath and destroys it. ovs_mutex must
+ * be held.
*/
void ovs_vport_del(struct vport *vport)
{
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index bdfd82a7c064..8ea3a96980ac 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -196,7 +196,13 @@ static inline const char *ovs_vport_name(struct vport *vport)
return vport->dev->name;
}
-int ovs_vport_ops_register(struct vport_ops *ops);
+int __ovs_vport_ops_register(struct vport_ops *ops);
+#define ovs_vport_ops_register(ops) \
+ ({ \
+ (ops)->owner = THIS_MODULE; \
+ __ovs_vport_ops_register(ops); \
+ })
+
void ovs_vport_ops_unregister(struct vport_ops *ops);
static inline struct rtable *ovs_tunnel_route_lookup(struct net *net,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1cf928fb573e..992396aa635c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2329,8 +2329,8 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
static bool ll_header_truncated(const struct net_device *dev, int len)
{
/* net device doesn't like empty head */
- if (unlikely(len <= dev->hard_header_len)) {
- net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n",
+ if (unlikely(len < dev->hard_header_len)) {
+ net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
current->comm, len, dev->hard_header_len);
return true;
}
diff --git a/net/rds/connection.c b/net/rds/connection.c
index d4564036a339..e3b118cae81d 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -186,12 +186,6 @@ static struct rds_connection *__rds_conn_create(struct net *net,
}
}
- if (trans == NULL) {
- kmem_cache_free(rds_conn_slab, conn);
- conn = ERR_PTR(-ENODEV);
- goto out;
- }
-
conn->c_trans = trans;
ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index 827155c2ead1..c9cdb358ea88 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1013,11 +1013,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
release_sock(sk);
}
- /* racing with another thread binding seems ok here */
+ lock_sock(sk);
if (daddr == 0 || rs->rs_bound_addr == 0) {
+ release_sock(sk);
ret = -ENOTCONN; /* XXX not a great errno */
goto out;
}
+ release_sock(sk);
if (payload_len > rds_sk_sndbuf(rs)) {
ret = -EMSGSIZE;
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index b41e9ea2ffff..f53bf3b6558b 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -49,7 +49,6 @@
struct rfkill {
spinlock_t lock;
- const char *name;
enum rfkill_type type;
unsigned long state;
@@ -73,6 +72,7 @@ struct rfkill {
struct delayed_work poll_work;
struct work_struct uevent_work;
struct work_struct sync_work;
+ char name[];
};
#define to_rfkill(d) container_of(d, struct rfkill, dev)
@@ -876,14 +876,14 @@ struct rfkill * __must_check rfkill_alloc(const char *name,
if (WARN_ON(type == RFKILL_TYPE_ALL || type >= NUM_RFKILL_TYPES))
return NULL;
- rfkill = kzalloc(sizeof(*rfkill), GFP_KERNEL);
+ rfkill = kzalloc(sizeof(*rfkill) + strlen(name) + 1, GFP_KERNEL);
if (!rfkill)
return NULL;
spin_lock_init(&rfkill->lock);
INIT_LIST_HEAD(&rfkill->node);
rfkill->type = type;
- rfkill->name = name;
+ strcpy(rfkill->name, name);
rfkill->ops = ops;
rfkill->data = ops_data;
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c
index e0547f521f20..adc555e0323d 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/ar-ack.c
@@ -723,8 +723,10 @@ process_further:
if ((call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY ||
call->state == RXRPC_CALL_SERVER_AWAIT_ACK) &&
- hard > tx)
+ hard > tx) {
+ call->acks_hard = tx;
goto all_acked;
+ }
smp_rmb();
rxrpc_rotate_tx_window(call, hard - 1);
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index a40d3afe93b7..14c4e12c47b0 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -531,7 +531,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
/* this should be in poll */
- clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
return -EPIPE;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f43c8f33f09e..b5c2cf2aa6d4 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
}
/* We know handle. Find qdisc among all qdisc's attached to device
- (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
*/
static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
root->handle == handle)
return root;
- list_for_each_entry(q, &root->list, list) {
+ list_for_each_entry_rcu(q, &root->list, list) {
if (q->handle == handle)
return q;
}
@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
struct Qdisc *root = qdisc_dev(q)->qdisc;
WARN_ON_ONCE(root == &noop_qdisc);
- list_add_tail(&q->list, &root->list);
+ ASSERT_RTNL();
+ list_add_tail_rcu(&q->list, &root->list);
}
}
EXPORT_SYMBOL(qdisc_list_add);
void qdisc_list_del(struct Qdisc *q)
{
- if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
- list_del(&q->list);
+ if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+ ASSERT_RTNL();
+ list_del_rcu(&q->list);
+ }
}
EXPORT_SYMBOL(qdisc_list_del);
@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
if (n == 0)
return;
drops = max_t(int, n, 0);
+ rcu_read_lock();
while ((parentid = sch->parent)) {
if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
- return;
+ break;
+ if (sch->flags & TCQ_F_NOPARENT)
+ break;
+ /* TODO: perform the search on a per txq basis */
sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
if (sch == NULL) {
- WARN_ON(parentid != TC_H_ROOT);
- return;
+ WARN_ON_ONCE(parentid != TC_H_ROOT);
+ break;
}
cops = sch->ops->cl_ops;
if (cops->qlen_notify) {
@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
sch->q.qlen -= n;
__qdisc_qstats_drop(sch, drops);
}
+ rcu_read_unlock();
}
EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index cb5d4ad32946..16bc83b2842a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -658,8 +658,10 @@ static void qdisc_rcu_free(struct rcu_head *head)
{
struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
- if (qdisc_is_percpu_stats(qdisc))
+ if (qdisc_is_percpu_stats(qdisc)) {
free_percpu(qdisc->cpu_bstats);
+ free_percpu(qdisc->cpu_qstats);
+ }
kfree((char *) qdisc - qdisc->padded);
}
@@ -737,7 +739,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
return;
}
if (!netif_is_multiqueue(dev))
- qdisc->flags |= TCQ_F_ONETXQUEUE;
+ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
dev_queue->qdisc_sleeping = qdisc;
}
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3cbaecd283a..3e82f047caaf 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
if (qdisc == NULL)
goto err;
priv->qdiscs[ntx] = qdisc;
- qdisc->flags |= TCQ_F_ONETXQUEUE;
+ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
sch->flags |= TCQ_F_MQROOT;
@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
*old = dev_graft_qdisc(dev_queue, new);
if (new)
- new->flags |= TCQ_F_ONETXQUEUE;
+ new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 3811a745452c..ad70ecf57ce7 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
goto err;
}
priv->qdiscs[i] = qdisc;
- qdisc->flags |= TCQ_F_ONETXQUEUE;
+ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
/* If the mqprio options indicate that hardware should own
@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
*old = dev_graft_qdisc(dev_queue, new);
if (new)
- new->flags |= TCQ_F_ONETXQUEUE;
+ new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e917d27328ea..ec529121f38a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -209,6 +209,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
struct sock *sk = skb->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
struct flowi6 *fl6 = &transport->fl.u.ip6;
+ int res;
pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
skb->len, &fl6->saddr, &fl6->daddr);
@@ -220,7 +221,10 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
- return ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+ rcu_read_lock();
+ res = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass);
+ rcu_read_unlock();
+ return res;
}
/* Returns the dst cache entry for the given source and destination ip
@@ -262,7 +266,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
pr_debug("src=%pI6 - ", &fl6->saddr);
}
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ rcu_read_lock();
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+ rcu_read_unlock();
+
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
if (!asoc || saddr)
goto out;
@@ -316,14 +323,13 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
}
}
}
- rcu_read_unlock();
-
if (baddr) {
fl6->saddr = baddr->v6.sin6_addr;
fl6->fl6_sport = baddr->v6.sin6_port;
- final_p = fl6_update_dst(fl6, np->opt, &final);
+ final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
}
+ rcu_read_unlock();
out:
if (!IS_ERR_OR_NULL(dst)) {
@@ -635,6 +641,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
struct sock *newsk;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct sctp6_sock *newsctp6sk;
+ struct ipv6_txoptions *opt;
newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
if (!newsk)
@@ -654,6 +661,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+ rcu_read_lock();
+ opt = rcu_dereference(np->opt);
+ if (opt)
+ opt = ipv6_dup_options(newsk, opt);
+ RCU_INIT_POINTER(newnp->opt, opt);
+ rcu_read_unlock();
+
/* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname()
* and getpeername().
*/
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 7e8f0a117106..c0380cfb16ae 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -324,6 +324,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
"illegal chunk");
+ sctp_chunk_hold(chunk);
sctp_outq_tail_data(q, chunk);
if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
@@ -1251,6 +1252,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
*/
sack_a_rwnd = ntohl(sack->a_rwnd);
+ asoc->peer.zero_window_announced = !sack_a_rwnd;
outstanding = q->outstanding_bytes;
if (outstanding < sack_a_rwnd)
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 763e06a55155..5d6a03fad378 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep,
/* Set an expiration time for the cookie. */
cookie->c.expiration = ktime_add(asoc->cookie_life,
- ktime_get());
+ ktime_get_real());
/* Copy the peer's init packet. */
memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr,
@@ -1780,7 +1780,7 @@ no_hmac:
if (sock_flag(ep->base.sk, SOCK_TIMESTAMP))
kt = skb_get_ktime(skb);
else
- kt = ktime_get();
+ kt = ktime_get_real();
if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
/*
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 6f46aa16cb76..22c2bf367d7e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort(
retval = SCTP_DISPOSITION_CONSUME;
- sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+ if (abort)
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
/* Even if we can't send the ABORT due to low memory delete the
* TCB. This is a departure from our typical NOMEM handling.
@@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort(
SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT));
retval = SCTP_DISPOSITION_CONSUME;
- sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
+ if (abort)
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort));
sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
SCTP_STATE(SCTP_STATE_CLOSED));
@@ -5412,7 +5414,8 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(struct net *net,
SCTP_INC_STATS(net, SCTP_MIB_T3_RTX_EXPIREDS);
if (asoc->overall_error_count >= asoc->max_retrans) {
- if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) {
+ if (asoc->peer.zero_window_announced &&
+ asoc->state == SCTP_STATE_SHUTDOWN_PENDING) {
/*
* We are here likely because the receiver had its rwnd
* closed for a while and we have not been able to
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 897c01c029ca..ef1d90fdc773 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -972,7 +972,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
return -EFAULT;
/* Alloc space for the address array in kernel memory. */
- kaddrs = kmalloc(addrs_size, GFP_KERNEL);
+ kaddrs = kmalloc(addrs_size, GFP_USER | __GFP_NOWARN);
if (unlikely(!kaddrs))
return -ENOMEM;
@@ -1301,8 +1301,9 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
int addrs_size,
sctp_assoc_t *assoc_id)
{
- int err = 0;
struct sockaddr *kaddrs;
+ gfp_t gfp = GFP_KERNEL;
+ int err = 0;
pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n",
__func__, sk, addrs, addrs_size);
@@ -1315,7 +1316,9 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
return -EFAULT;
/* Alloc space for the address array in kernel memory. */
- kaddrs = kmalloc(addrs_size, GFP_KERNEL);
+ if (sk->sk_socket->file)
+ gfp = GFP_USER | __GFP_NOWARN;
+ kaddrs = kmalloc(addrs_size, gfp);
if (unlikely(!kaddrs))
return -ENOMEM;
@@ -1513,8 +1516,7 @@ static void sctp_close(struct sock *sk, long timeout)
struct sctp_chunk *chunk;
chunk = sctp_make_abort_user(asoc, NULL, 0);
- if (chunk)
- sctp_primitive_ABORT(net, asoc, chunk);
+ sctp_primitive_ABORT(net, asoc, chunk);
} else
sctp_primitive_SHUTDOWN(net, asoc, NULL);
}
@@ -1952,8 +1954,6 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
/* Now send the (possibly) fragmented message. */
list_for_each_entry(chunk, &datamsg->chunks, frag_list) {
- sctp_chunk_hold(chunk);
-
/* Do accounting for the write space. */
sctp_set_owner_w(chunk);
@@ -1966,15 +1966,13 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
* breaks.
*/
err = sctp_primitive_SEND(net, asoc, datamsg);
+ sctp_datamsg_put(datamsg);
/* Did the lower layer accept the chunk? */
- if (err) {
- sctp_datamsg_free(datamsg);
+ if (err)
goto out_free;
- }
pr_debug("%s: we sent primitively\n", __func__);
- sctp_datamsg_put(datamsg);
err = msg_len;
if (unlikely(wait_connect)) {
@@ -4928,7 +4926,7 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
to = optval + offsetof(struct sctp_getaddrs, addrs);
space_left = len - offsetof(struct sctp_getaddrs, addrs);
- addrs = kmalloc(space_left, GFP_KERNEL);
+ addrs = kmalloc(space_left, GFP_USER | __GFP_NOWARN);
if (!addrs)
return -ENOMEM;
@@ -5777,7 +5775,7 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len,
len = sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num;
- ids = kmalloc(len, GFP_KERNEL);
+ ids = kmalloc(len, GFP_USER | __GFP_NOWARN);
if (unlikely(!ids))
return -ENOMEM;
@@ -6458,7 +6456,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (sctp_writeable(sk)) {
mask |= POLLOUT | POLLWRNORM;
} else {
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
/*
* Since the socket is not locked, the buffer
* might be made available after the writeable check and
@@ -6801,26 +6799,30 @@ no_packet:
static void __sctp_write_space(struct sctp_association *asoc)
{
struct sock *sk = asoc->base.sk;
- struct socket *sock = sk->sk_socket;
- if ((sctp_wspace(asoc) > 0) && sock) {
- if (waitqueue_active(&asoc->wait))
- wake_up_interruptible(&asoc->wait);
+ if (sctp_wspace(asoc) <= 0)
+ return;
- if (sctp_writeable(sk)) {
- wait_queue_head_t *wq = sk_sleep(sk);
+ if (waitqueue_active(&asoc->wait))
+ wake_up_interruptible(&asoc->wait);
- if (wq && waitqueue_active(wq))
- wake_up_interruptible(wq);
+ if (sctp_writeable(sk)) {
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq) {
+ if (waitqueue_active(&wq->wait))
+ wake_up_interruptible(&wq->wait);
/* Note that we try to include the Async I/O support
* here by modeling from the current TCP/UDP code.
* We have not tested with it yet.
*/
if (!(sk->sk_shutdown & SEND_SHUTDOWN))
- sock_wake_async(sock,
- SOCK_WAKE_SPACE, POLL_OUT);
+ sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
}
+ rcu_read_unlock();
}
}
@@ -7163,6 +7165,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
newsk->sk_type = sk->sk_type;
newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
newsk->sk_flags = sk->sk_flags;
+ newsk->sk_tsflags = sk->sk_tsflags;
newsk->sk_no_check_tx = sk->sk_no_check_tx;
newsk->sk_no_check_rx = sk->sk_no_check_rx;
newsk->sk_reuse = sk->sk_reuse;
@@ -7195,6 +7198,11 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
newinet->mc_ttl = 1;
newinet->mc_index = 0;
newinet->mc_list = NULL;
+
+ if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
+ net_enable_timestamp();
+
+ security_sk_clone(sk, newsk);
}
static inline void sctp_copy_descendant(struct sock *sk_to,
@@ -7375,6 +7383,13 @@ struct proto sctp_prot = {
#if IS_ENABLED(CONFIG_IPV6)
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+ sctp_destroy_sock(sk);
+ inet6_destroy_sock(sk);
+}
+
struct proto sctpv6_prot = {
.name = "SCTPv6",
.owner = THIS_MODULE,
@@ -7384,7 +7399,7 @@ struct proto sctpv6_prot = {
.accept = sctp_accept,
.ioctl = sctp_ioctl,
.init = sctp_init_sock,
- .destroy = sctp_destroy_sock,
+ .destroy = sctp_v6_destroy_sock,
.shutdown = sctp_shutdown,
.setsockopt = sctp_setsockopt,
.getsockopt = sctp_getsockopt,
diff --git a/net/socket.c b/net/socket.c
index dd2c247c99e3..d730ef9dfbf0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -257,6 +257,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
}
init_waitqueue_head(&wq->wait);
wq->fasync_list = NULL;
+ wq->flags = 0;
RCU_INIT_POINTER(ei->socket.wq, wq);
ei->socket.state = SS_UNCONNECTED;
@@ -1056,27 +1057,20 @@ static int sock_fasync(int fd, struct file *filp, int on)
return 0;
}
-/* This function may be called only under socket lock or callback_lock or rcu_lock */
+/* This function may be called only under rcu_lock */
-int sock_wake_async(struct socket *sock, int how, int band)
+int sock_wake_async(struct socket_wq *wq, int how, int band)
{
- struct socket_wq *wq;
-
- if (!sock)
- return -1;
- rcu_read_lock();
- wq = rcu_dereference(sock->wq);
- if (!wq || !wq->fasync_list) {
- rcu_read_unlock();
+ if (!wq || !wq->fasync_list)
return -1;
- }
+
switch (how) {
case SOCK_WAKE_WAITD:
- if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
+ if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags))
break;
goto call_kill;
case SOCK_WAKE_SPACE:
- if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
+ if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags))
break;
/* fall through */
case SOCK_WAKE_IO:
@@ -1086,7 +1080,7 @@ call_kill:
case SOCK_WAKE_URG:
kill_fasync(&wq->fasync_list, SIGURG, band);
}
- rcu_read_unlock();
+
return 0;
}
EXPORT_SYMBOL(sock_wake_async);
@@ -1702,6 +1696,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
/* We assume all kernel code knows the size of sockaddr_storage */
msg.msg_namelen = 0;
+ msg.msg_iocb = NULL;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index f14f24ee9983..73ad57a59989 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -250,11 +250,11 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue)
}
EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
-static int rpc_wait_bit_killable(struct wait_bit_key *key)
+static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode)
{
- if (fatal_signal_pending(current))
- return -ERESTARTSYS;
freezable_schedule_unsafe();
+ if (signal_pending_state(mode, current))
+ return -ERESTARTSYS;
return 0;
}
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index bc5b7b5032ca..cc9852897395 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1364,6 +1364,19 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg));
memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res));
+ /* Adjust the argument buffer length */
+ rqstp->rq_arg.len = req->rq_private_buf.len;
+ if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
+ rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
+ rqstp->rq_arg.page_len = 0;
+ } else if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len +
+ rqstp->rq_arg.page_len)
+ rqstp->rq_arg.page_len = rqstp->rq_arg.len -
+ rqstp->rq_arg.head[0].iov_len;
+ else
+ rqstp->rq_arg.len = rqstp->rq_arg.head[0].iov_len +
+ rqstp->rq_arg.page_len;
+
/* reset result send buffer "put" position */
resv->iov_len = 0;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1d1a70498910..2ffaf6a79499 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -398,7 +398,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
if (unlikely(!sock))
return -ENOTSOCK;
- clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+ clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags);
if (base != 0) {
addr = NULL;
addrlen = 0;
@@ -442,7 +442,7 @@ static void xs_nospace_callback(struct rpc_task *task)
struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt);
transport->inet->sk_write_pending--;
- clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+ clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
}
/**
@@ -467,7 +467,7 @@ static int xs_nospace(struct rpc_task *task)
/* Don't race with disconnect */
if (xprt_connected(xprt)) {
- if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
+ if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) {
/*
* Notify TCP that we're limited by the application
* window size
@@ -478,7 +478,7 @@ static int xs_nospace(struct rpc_task *task)
xprt_wait_for_buffer_space(task, xs_nospace_callback);
}
} else {
- clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+ clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
ret = -ENOTCONN;
}
@@ -626,7 +626,7 @@ process_status:
case -EPERM:
/* When the server has died, an ICMP port unreachable message
* prompts ECONNREFUSED. */
- clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+ clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
}
return status;
@@ -715,7 +715,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
case -EADDRINUSE:
case -ENOBUFS:
case -EPIPE:
- clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+ clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
}
return status;
@@ -1618,7 +1618,7 @@ static void xs_write_space(struct sock *sk)
if (unlikely(!(xprt = xprt_from_sock(sk))))
return;
- if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0)
+ if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0)
return;
xprt_write_space(xprt);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 9efbdbde2b08..91aea071ab27 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -191,6 +191,7 @@ void tipc_link_add_bc_peer(struct tipc_link *snd_l,
snd_l->ackers++;
rcv_l->acked = snd_l->snd_nxt - 1;
+ snd_l->state = LINK_ESTABLISHED;
tipc_link_build_bc_init_msg(uc_l, xmitq);
}
@@ -206,6 +207,7 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
rcv_l->state = LINK_RESET;
if (!snd_l->ackers) {
tipc_link_reset(snd_l);
+ snd_l->state = LINK_RESET;
__skb_queue_purge(xmitq);
}
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 552dbaba9cf3..b53246fb0412 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -105,6 +105,7 @@ struct tipc_sock {
static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static void tipc_data_ready(struct sock *sk);
static void tipc_write_space(struct sock *sk);
+static void tipc_sock_destruct(struct sock *sk);
static int tipc_release(struct socket *sock);
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p);
@@ -381,6 +382,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
+ sk->sk_destruct = tipc_sock_destruct;
tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
tsk->sent_unacked = 0;
atomic_set(&tsk->dupl_rcvcnt, 0);
@@ -470,9 +472,6 @@ static int tipc_release(struct socket *sock)
tipc_node_remove_conn(net, dnode, tsk->portid);
}
- /* Discard any remaining (connection-based) messages in receive queue */
- __skb_queue_purge(&sk->sk_receive_queue);
-
/* Reject any messages that accumulated in backlog queue */
sock->state = SS_DISCONNECTING;
release_sock(sk);
@@ -1515,6 +1514,11 @@ static void tipc_data_ready(struct sock *sk)
rcu_read_unlock();
}
+static void tipc_sock_destruct(struct sock *sk)
+{
+ __skb_queue_purge(&sk->sk_receive_queue);
+}
+
/**
* filter_connect - Handle all incoming messages for a connection-based socket
* @tsk: TIPC socket
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index ad2719ad4c1b..70c03271b798 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -158,8 +158,11 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
struct rtable *rt;
- if (skb_headroom(skb) < UDP_MIN_HEADROOM)
- pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+ if (skb_headroom(skb) < UDP_MIN_HEADROOM) {
+ err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+ if (err)
+ goto tx_error;
+ }
skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
ub = rcu_dereference_rtnl(b->media_ptr);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 955ec152cb71..ef05cd9403d4 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -326,6 +326,118 @@ found:
return s;
}
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+ void *key)
+{
+ struct unix_sock *u;
+ wait_queue_head_t *u_sleep;
+
+ u = container_of(q, struct unix_sock, peer_wake);
+
+ __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+ q);
+ u->peer_wake.private = NULL;
+
+ /* relaying can only happen while the wq still exists */
+ u_sleep = sk_sleep(&u->sk);
+ if (u_sleep)
+ wake_up_interruptible_poll(u_sleep, key);
+
+ return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+ int rc;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ rc = 0;
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (!u->peer_wake.private) {
+ u->peer_wake.private = other;
+ __add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+ rc = 1;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+ return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+ struct sock *other)
+{
+ struct unix_sock *u, *u_other;
+
+ u = unix_sk(sk);
+ u_other = unix_sk(other);
+ spin_lock(&u_other->peer_wait.lock);
+
+ if (u->peer_wake.private == other) {
+ __remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+ u->peer_wake.private = NULL;
+ }
+
+ spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+ struct sock *other)
+{
+ unix_dgram_peer_wake_disconnect(sk, other);
+ wake_up_interruptible_poll(sk_sleep(sk),
+ POLLOUT |
+ POLLWRNORM |
+ POLLWRBAND);
+}
+
+/* preconditions:
+ * - unix_peer(sk) == other
+ * - association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+ int connected;
+
+ connected = unix_dgram_peer_wake_connect(sk, other);
+
+ if (unix_recvq_full(other))
+ return 1;
+
+ if (connected)
+ unix_dgram_peer_wake_disconnect(sk, other);
+
+ return 0;
+}
+
static int unix_writable(const struct sock *sk)
{
return sk->sk_state != TCP_LISTEN &&
@@ -431,6 +543,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
skpair->sk_state_change(skpair);
sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
}
+
+ unix_dgram_peer_wake_disconnect(sk, skpair);
sock_put(skpair); /* It may now die */
unix_peer(sk) = NULL;
}
@@ -666,6 +780,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
INIT_LIST_HEAD(&u->link);
mutex_init(&u->readlock); /* single task reading lock */
init_waitqueue_head(&u->peer_wait);
+ init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
unix_insert_socket(unix_sockets_unbound(sk), sk);
out:
if (sk == NULL)
@@ -838,32 +953,20 @@ fail:
return NULL;
}
-static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode,
+ struct path *res)
{
- struct dentry *dentry;
- struct path path;
- int err = 0;
- /*
- * Get the parent directory, calculate the hash for last
- * component.
- */
- dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
- err = PTR_ERR(dentry);
- if (IS_ERR(dentry))
- return err;
+ int err;
- /*
- * All right, let's create it.
- */
- err = security_path_mknod(&path, dentry, mode, 0);
+ err = security_path_mknod(path, dentry, mode, 0);
if (!err) {
- err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
+ err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
if (!err) {
- res->mnt = mntget(path.mnt);
+ res->mnt = mntget(path->mnt);
res->dentry = dget(dentry);
}
}
- done_path_create(&path, dentry);
+
return err;
}
@@ -874,10 +977,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
char *sun_path = sunaddr->sun_path;
- int err;
+ int err, name_err;
unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
+ struct path path;
+ struct dentry *dentry;
err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
@@ -893,14 +998,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out;
addr_len = err;
+ name_err = 0;
+ dentry = NULL;
+ if (sun_path[0]) {
+ /* Get the parent directory, calculate the hash for last
+ * component.
+ */
+ dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+
+ if (IS_ERR(dentry)) {
+ /* delay report until after 'already bound' check */
+ name_err = PTR_ERR(dentry);
+ dentry = NULL;
+ }
+ }
+
err = mutex_lock_interruptible(&u->readlock);
if (err)
- goto out;
+ goto out_path;
err = -EINVAL;
if (u->addr)
goto out_up;
+ if (name_err) {
+ err = name_err == -EEXIST ? -EADDRINUSE : name_err;
+ goto out_up;
+ }
+
err = -ENOMEM;
addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
if (!addr)
@@ -911,11 +1036,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
addr->hash = hash ^ sk->sk_type;
atomic_set(&addr->refcnt, 1);
- if (sun_path[0]) {
- struct path path;
+ if (dentry) {
+ struct path u_path;
umode_t mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = unix_mknod(sun_path, mode, &path);
+ err = unix_mknod(dentry, &path, mode, &u_path);
if (err) {
if (err == -EEXIST)
err = -EADDRINUSE;
@@ -923,9 +1048,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
goto out_up;
}
addr->hash = UNIX_HASH_SIZE;
- hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1);
+ hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
spin_lock(&unix_table_lock);
- u->path = path;
+ u->path = u_path;
list = &unix_socket_table[hash];
} else {
spin_lock(&unix_table_lock);
@@ -948,6 +1073,10 @@ out_unlock:
spin_unlock(&unix_table_lock);
out_up:
mutex_unlock(&u->readlock);
+out_path:
+ if (dentry)
+ done_path_create(&path, dentry);
+
out:
return err;
}
@@ -1033,6 +1162,8 @@ restart:
if (unix_peer(sk)) {
struct sock *old_peer = unix_peer(sk);
unix_peer(sk) = other;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
unix_state_double_unlock(sk, other);
if (other != old_peer)
@@ -1434,6 +1565,14 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
return err;
}
+static bool unix_passcred_enabled(const struct socket *sock,
+ const struct sock *other)
+{
+ return test_bit(SOCK_PASSCRED, &sock->flags) ||
+ !other->sk_socket ||
+ test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+}
+
/*
* Some apps rely on write() giving SCM_CREDENTIALS
* We include credentials if source or destination socket
@@ -1444,14 +1583,41 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
{
if (UNIXCB(skb).pid)
return;
- if (test_bit(SOCK_PASSCRED, &sock->flags) ||
- !other->sk_socket ||
- test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
+ if (unix_passcred_enabled(sock, other)) {
UNIXCB(skb).pid = get_pid(task_tgid(current));
current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
}
}
+static int maybe_init_creds(struct scm_cookie *scm,
+ struct socket *socket,
+ const struct sock *other)
+{
+ int err;
+ struct msghdr msg = { .msg_controllen = 0 };
+
+ err = scm_send(socket, &msg, scm, false);
+ if (err)
+ return err;
+
+ if (unix_passcred_enabled(socket, other)) {
+ scm->pid = get_pid(task_tgid(current));
+ current_uid_gid(&scm->creds.uid, &scm->creds.gid);
+ }
+ return err;
+}
+
+static bool unix_skb_scm_eq(struct sk_buff *skb,
+ struct scm_cookie *scm)
+{
+ const struct unix_skb_parms *u = &UNIXCB(skb);
+
+ return u->pid == scm->pid &&
+ uid_eq(u->uid, scm->creds.uid) &&
+ gid_eq(u->gid, scm->creds.gid) &&
+ unix_secdata_eq(scm, skb);
+}
+
/*
* Send AF_UNIX data.
*/
@@ -1472,6 +1638,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
struct scm_cookie scm;
int max_level;
int data_len = 0;
+ int sk_locked;
wait_for_unix_gc();
err = scm_send(sock, msg, &scm, false);
@@ -1550,12 +1717,14 @@ restart:
goto out_free;
}
+ sk_locked = 0;
unix_state_lock(other);
+restart_locked:
err = -EPERM;
if (!unix_may_send(sk, other))
goto out_unlock;
- if (sock_flag(other, SOCK_DEAD)) {
+ if (unlikely(sock_flag(other, SOCK_DEAD))) {
/*
* Check with 1003.1g - what should
* datagram error
@@ -1563,10 +1732,14 @@ restart:
unix_state_unlock(other);
sock_put(other);
+ if (!sk_locked)
+ unix_state_lock(sk);
+
err = 0;
- unix_state_lock(sk);
if (unix_peer(sk) == other) {
unix_peer(sk) = NULL;
+ unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
unix_state_unlock(sk);
unix_dgram_disconnected(sk, other);
@@ -1592,21 +1765,38 @@ restart:
goto out_unlock;
}
- if (unix_peer(other) != sk && unix_recvq_full(other)) {
- if (!timeo) {
- err = -EAGAIN;
- goto out_unlock;
+ if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+ if (timeo) {
+ timeo = unix_wait_for_peer(other, timeo);
+
+ err = sock_intr_errno(timeo);
+ if (signal_pending(current))
+ goto out_free;
+
+ goto restart;
}
- timeo = unix_wait_for_peer(other, timeo);
+ if (!sk_locked) {
+ unix_state_unlock(other);
+ unix_state_double_lock(sk, other);
+ }
- err = sock_intr_errno(timeo);
- if (signal_pending(current))
- goto out_free;
+ if (unix_peer(sk) != other ||
+ unix_dgram_peer_wake_me(sk, other)) {
+ err = -EAGAIN;
+ sk_locked = 1;
+ goto out_unlock;
+ }
- goto restart;
+ if (!sk_locked) {
+ sk_locked = 1;
+ goto restart_locked;
+ }
}
+ if (unlikely(sk_locked))
+ unix_state_unlock(sk);
+
if (sock_flag(other, SOCK_RCVTSTAMP))
__net_timestamp(skb);
maybe_add_creds(skb, sock, other);
@@ -1620,6 +1810,8 @@ restart:
return len;
out_unlock:
+ if (sk_locked)
+ unix_state_unlock(sk);
unix_state_unlock(other);
out_free:
kfree_skb(skb);
@@ -1741,8 +1933,10 @@ out_err:
static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
int offset, size_t size, int flags)
{
- int err = 0;
- bool send_sigpipe = true;
+ int err;
+ bool send_sigpipe = false;
+ bool init_scm = true;
+ struct scm_cookie scm;
struct sock *other, *sk = socket->sk;
struct sk_buff *skb, *newskb = NULL, *tail = NULL;
@@ -1760,7 +1954,7 @@ alloc_skb:
newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
&err, 0);
if (!newskb)
- return err;
+ goto err;
}
/* we must acquire readlock as we modify already present
@@ -1769,12 +1963,12 @@ alloc_skb:
err = mutex_lock_interruptible(&unix_sk(other)->readlock);
if (err) {
err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
- send_sigpipe = false;
goto err;
}
if (sk->sk_shutdown & SEND_SHUTDOWN) {
err = -EPIPE;
+ send_sigpipe = true;
goto err_unlock;
}
@@ -1783,17 +1977,27 @@ alloc_skb:
if (sock_flag(other, SOCK_DEAD) ||
other->sk_shutdown & RCV_SHUTDOWN) {
err = -EPIPE;
+ send_sigpipe = true;
goto err_state_unlock;
}
+ if (init_scm) {
+ err = maybe_init_creds(&scm, socket, other);
+ if (err)
+ goto err_state_unlock;
+ init_scm = false;
+ }
+
skb = skb_peek_tail(&other->sk_receive_queue);
if (tail && tail == skb) {
skb = newskb;
- } else if (!skb) {
- if (newskb)
+ } else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
+ if (newskb) {
skb = newskb;
- else
+ } else {
+ tail = skb;
goto alloc_skb;
+ }
} else if (newskb) {
/* this is fast path, we don't necessarily need to
* call to kfree_skb even though with newskb == NULL
@@ -1814,6 +2018,9 @@ alloc_skb:
atomic_add(size, &sk->sk_wmem_alloc);
if (newskb) {
+ err = unix_scm_to_skb(&scm, skb, false);
+ if (err)
+ goto err_state_unlock;
spin_lock(&other->sk_receive_queue.lock);
__skb_queue_tail(&other->sk_receive_queue, newskb);
spin_unlock(&other->sk_receive_queue.lock);
@@ -1823,7 +2030,7 @@ alloc_skb:
mutex_unlock(&unix_sk(other)->readlock);
other->sk_data_ready(other);
-
+ scm_destroy(&scm);
return size;
err_state_unlock:
@@ -1834,6 +2041,8 @@ err:
kfree_skb(newskb);
if (send_sigpipe && !(flags & MSG_NOSIGNAL))
send_sig(SIGPIPE, current, 0);
+ if (!init_scm)
+ scm_destroy(&scm);
return err;
}
@@ -1996,7 +2205,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
!timeo)
break;
- set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
unix_state_unlock(sk);
timeo = freezable_schedule_timeout(timeo);
unix_state_lock(sk);
@@ -2004,7 +2213,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
if (sock_flag(sk, SOCK_DEAD))
break;
- clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
}
finish_wait(sk_sleep(sk), &wait);
@@ -2061,14 +2270,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state)
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
- err = mutex_lock_interruptible(&u->readlock);
- if (unlikely(err)) {
- /* recvmsg() in non blocking mode is supposed to return -EAGAIN
- * sk_rcvtimeo is not honored by mutex_lock_interruptible()
- */
- err = noblock ? -EAGAIN : -ERESTARTSYS;
- goto out;
- }
+ mutex_lock(&u->readlock);
if (flags & MSG_PEEK)
skip = sk_peek_offset(sk, flags);
@@ -2112,12 +2314,12 @@ again:
timeo = unix_stream_data_wait(sk, timeo, last,
last_len);
- if (signal_pending(current) ||
- mutex_lock_interruptible(&u->readlock)) {
+ if (signal_pending(current)) {
err = sock_intr_errno(timeo);
goto out;
}
+ mutex_lock(&u->readlock);
continue;
unlock:
unix_state_unlock(sk);
@@ -2137,10 +2339,7 @@ unlock:
if (check_creds) {
/* Never glue messages from different writers */
- if ((UNIXCB(skb).pid != scm.pid) ||
- !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
- !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
- !unix_secdata_eq(&scm, skb))
+ if (!unix_skb_scm_eq(skb, &scm))
break;
} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
/* Copy credentials */
@@ -2476,20 +2675,22 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
return mask;
writable = unix_writable(sk);
- other = unix_peer_get(sk);
- if (other) {
- if (unix_peer(other) != sk) {
- sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
- if (unix_recvq_full(other))
- writable = 0;
- }
- sock_put(other);
+ if (writable) {
+ unix_state_lock(sk);
+
+ other = unix_peer(sk);
+ if (other && unix_peer(other) != sk &&
+ unix_recvq_full(other) &&
+ unix_dgram_peer_wake_me(sk, other))
+ writable = 0;
+
+ unix_state_unlock(sk);
}
if (writable)
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
- set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
return mask;
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c71e274c810a..75b0d23ee882 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7941,8 +7941,10 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
if (nla_get_flag(info->attrs[NL80211_ATTR_USE_RRM])) {
if (!(rdev->wiphy.features &
NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES) ||
- !(rdev->wiphy.features & NL80211_FEATURE_QUIET))
+ !(rdev->wiphy.features & NL80211_FEATURE_QUIET)) {
+ kzfree(connkeys);
return -EINVAL;
+ }
connect.flags |= ASSOC_REQ_USE_RRM;
}
@@ -9503,6 +9505,7 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
if (new_triggers.tcp && new_triggers.tcp->sock)
sock_release(new_triggers.tcp->sock);
kfree(new_triggers.tcp);
+ kfree(new_triggers.nd_config);
return err;
}
#endif
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2e8d6f39ed56..06d050da0d94 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3029,6 +3029,7 @@ int set_regdom(const struct ieee80211_regdomain *rd,
break;
default:
WARN(1, "invalid initiator %d\n", lr->initiator);
+ kfree(rd);
return -EINVAL;
}
@@ -3221,8 +3222,10 @@ int __init regulatory_init(void)
/* We always try to get an update for the static regdomain */
err = regulatory_hint_core(cfg80211_world_regdom->alpha2);
if (err) {
- if (err == -ENOMEM)
+ if (err == -ENOMEM) {
+ platform_device_unregister(reg_pdev);
return err;
+ }
/*
* N.B. kobject_uevent_env() can fail mainly for when we're out
* memory which is handled and propagated appropriately above
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 09bfcbac63bb..b5e665b3cfb0 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -303,6 +303,14 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
}
EXPORT_SYMBOL(xfrm_policy_alloc);
+static void xfrm_policy_destroy_rcu(struct rcu_head *head)
+{
+ struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu);
+
+ security_xfrm_policy_free(policy->security);
+ kfree(policy);
+}
+
/* Destroy xfrm_policy: descendant resources must be released to this moment. */
void xfrm_policy_destroy(struct xfrm_policy *policy)
@@ -312,8 +320,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer))
BUG();
- security_xfrm_policy_free(policy->security);
- kfree(policy);
+ call_rcu(&policy->rcu, xfrm_policy_destroy_rcu);
}
EXPORT_SYMBOL(xfrm_policy_destroy);
@@ -1214,8 +1221,10 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
struct xfrm_policy *pol;
struct net *net = sock_net(sk);
+ rcu_read_lock();
read_lock_bh(&net->xfrm.xfrm_policy_lock);
- if ((pol = sk->sk_policy[dir]) != NULL) {
+ pol = rcu_dereference(sk->sk_policy[dir]);
+ if (pol != NULL) {
bool match = xfrm_selector_match(&pol->selector, fl,
sk->sk_family);
int err = 0;
@@ -1239,6 +1248,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
}
out:
read_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ rcu_read_unlock();
return pol;
}
@@ -1307,13 +1317,14 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
#endif
write_lock_bh(&net->xfrm.xfrm_policy_lock);
- old_pol = sk->sk_policy[dir];
- sk->sk_policy[dir] = pol;
+ old_pol = rcu_dereference_protected(sk->sk_policy[dir],
+ lockdep_is_held(&net->xfrm.xfrm_policy_lock));
if (pol) {
pol->curlft.add_time = get_seconds();
pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
xfrm_sk_policy_link(pol, dir);
}
+ rcu_assign_pointer(sk->sk_policy[dir], pol);
if (old_pol) {
if (pol)
xfrm_policy_requeue(old_pol, pol);
@@ -1361,17 +1372,26 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
return newp;
}
-int __xfrm_sk_clone_policy(struct sock *sk)
+int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk)
{
- struct xfrm_policy *p0 = sk->sk_policy[0],
- *p1 = sk->sk_policy[1];
+ const struct xfrm_policy *p;
+ struct xfrm_policy *np;
+ int i, ret = 0;
- sk->sk_policy[0] = sk->sk_policy[1] = NULL;
- if (p0 && (sk->sk_policy[0] = clone_policy(p0, 0)) == NULL)
- return -ENOMEM;
- if (p1 && (sk->sk_policy[1] = clone_policy(p1, 1)) == NULL)
- return -ENOMEM;
- return 0;
+ rcu_read_lock();
+ for (i = 0; i < 2; i++) {
+ p = rcu_dereference(osk->sk_policy[i]);
+ if (p) {
+ np = clone_policy(p, i);
+ if (unlikely(!np)) {
+ ret = -ENOMEM;
+ break;
+ }
+ rcu_assign_pointer(sk->sk_policy[i], np);
+ }
+ }
+ rcu_read_unlock();
+ return ret;
}
static int
@@ -2198,6 +2218,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
xdst = NULL;
route = NULL;
+ sk = sk_const_to_full_sk(sk);
if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
num_pols = 1;
pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
@@ -2477,6 +2498,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
}
pol = NULL;
+ sk = sk_to_full_sk(sk);
if (sk && sk->sk_policy[dir]) {
pol = xfrm_sk_policy_lookup(sk, dir, &fl);
if (IS_ERR(pol)) {
@@ -2804,7 +2826,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
{
- struct net *net;
int err = 0;
if (unlikely(afinfo == NULL))
return -EINVAL;
@@ -2835,26 +2856,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
}
spin_unlock(&xfrm_policy_afinfo_lock);
- rtnl_lock();
- for_each_net(net) {
- struct dst_ops *xfrm_dst_ops;
-
- switch (afinfo->family) {
- case AF_INET:
- xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
- break;
-#if IS_ENABLED(CONFIG_IPV6)
- case AF_INET6:
- xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
- break;
-#endif
- default:
- BUG();
- }
- *xfrm_dst_ops = *afinfo->dst_ops;
- }
- rtnl_unlock();
-
return err;
}
EXPORT_SYMBOL(xfrm_policy_register_afinfo);
@@ -2890,22 +2891,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo)
}
EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
-static void __net_init xfrm_dst_ops_init(struct net *net)
-{
- struct xfrm_policy_afinfo *afinfo;
-
- rcu_read_lock();
- afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]);
- if (afinfo)
- net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if IS_ENABLED(CONFIG_IPV6)
- afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]);
- if (afinfo)
- net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
-#endif
- rcu_read_unlock();
-}
-
static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -3054,7 +3039,6 @@ static int __net_init xfrm_net_init(struct net *net)
rv = xfrm_policy_init(net);
if (rv < 0)
goto out_policy;
- xfrm_dst_ops_init(net);
rv = xfrm_sysctl_init(net);
if (rv < 0)
goto out_sysctl;