summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/bluetooth/hci_core.c1
-rw-r--r--net/bluetooth/hci_event.c13
-rw-r--r--net/bridge/br_netfilter_hooks.c1
-rw-r--r--net/can/j1939/address-claim.c40
-rw-r--r--net/can/j1939/transport.c4
-rw-r--r--net/core/net_namespace.c2
-rw-r--r--net/core/skbuff.c5
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/inet_hashtables.c17
-rw-r--r--net/ipv4/inet_timewait_sock.c8
-rw-r--r--net/ipv4/metrics.c2
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_bpf.c4
-rw-r--r--net/l2tp/l2tp_core.c116
-rw-r--r--net/netfilter/nf_conntrack_proto_sctp.c118
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c10
-rw-r--r--net/netfilter/nf_conntrack_standalone.c8
-rw-r--r--net/netfilter/nft_set_rbtree.c332
-rw-r--r--net/netlink/af_netlink.c38
-rw-r--r--net/netrom/af_netrom.c5
-rw-r--r--net/netrom/nr_timer.c1
-rw-r--r--net/nfc/llcp_core.c1
-rw-r--r--net/openvswitch/datapath.c12
-rw-r--r--net/qrtr/ns.c5
-rw-r--r--net/rds/message.c6
-rw-r--r--net/sched/sch_taprio.c2
-rw-r--r--net/sctp/bind_addr.c6
-rw-r--r--net/x25/af_x25.c6
-rw-r--r--net/xfrm/xfrm_compat.c4
-rw-r--r--net/xfrm/xfrm_input.c3
30 files changed, 477 insertions, 297 deletions
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 2af1477a05ca..08c473aa0113 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1623,6 +1623,7 @@ setup_failed:
hdev->flush(hdev);
if (hdev->sent_cmd) {
+ cancel_delayed_work_sync(&hdev->cmd_timer);
kfree_skb(hdev->sent_cmd);
hdev->sent_cmd = NULL;
}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 954b29605c94..eb111504afc6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4307,6 +4307,19 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
struct hci_ev_sync_conn_complete *ev = (void *) skb->data;
struct hci_conn *conn;
+ switch (ev->link_type) {
+ case SCO_LINK:
+ case ESCO_LINK:
+ break;
+ default:
+ /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type
+ * for HCI_Synchronous_Connection_Complete is limited to
+ * either SCO or eSCO
+ */
+ bt_dev_err(hdev, "Ignoring connect complete event for invalid link type");
+ return;
+ }
+
BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
hci_dev_lock(hdev);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index a718204c4bfd..f3c7cfba31e1 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -871,6 +871,7 @@ static unsigned int ip_sabotage_in(void *priv,
if (nf_bridge && !nf_bridge->in_prerouting &&
!netif_is_l3_master(skb->dev) &&
!netif_is_l3_slave(skb->dev)) {
+ nf_bridge_info_free(skb);
state->okfn(state->net, state->sk, skb);
return NF_STOLEN;
}
diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c
index f33c47327927..ca4ad6cdd5cb 100644
--- a/net/can/j1939/address-claim.c
+++ b/net/can/j1939/address-claim.c
@@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb)
* leaving this function.
*/
ecu = j1939_ecu_get_by_name_locked(priv, name);
+
+ if (ecu && ecu->addr == skcb->addr.sa) {
+ /* The ISO 11783-5 standard, in "4.5.2 - Address claim
+ * requirements", states:
+ * d) No CF shall begin, or resume, transmission on the
+ * network until 250 ms after it has successfully claimed
+ * an address except when responding to a request for
+ * address-claimed.
+ *
+ * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim
+ * prioritization" show that the CF begins the transmission
+ * after 250 ms from the first AC (address-claimed) message
+ * even if it sends another AC message during that time window
+ * to resolve the address contention with another CF.
+ *
+ * As stated in "4.4.2.3 - Address-claimed message":
+ * In order to successfully claim an address, the CF sending
+ * an address claimed message shall not receive a contending
+ * claim from another CF for at least 250 ms.
+ *
+ * As stated in "4.4.3.2 - NAME management (NM) message":
+ * 1) A commanding CF can
+ * d) request that a CF with a specified NAME transmit
+ * the address-claimed message with its current NAME.
+ * 2) A target CF shall
+ * d) send an address-claimed message in response to a
+ * request for a matching NAME
+ *
+ * Taking the above arguments into account, the 250 ms wait is
+ * requested only during network initialization.
+ *
+ * Do not restart the timer on AC message if both the NAME and
+ * the address match and so if the address has already been
+ * claimed (timer has expired) or the AC message has been sent
+ * to resolve the contention with another CF (timer is still
+ * running).
+ */
+ goto out_ecu_put;
+ }
+
if (!ecu && j1939_address_is_unicast(skcb->addr.sa))
ecu = j1939_ecu_create_locked(priv, name);
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 78f6a9110699..57d6aac7f435 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1087,10 +1087,6 @@ static bool j1939_session_deactivate(struct j1939_session *session)
bool active;
j1939_session_list_lock(priv);
- /* This function should be called with a session ref-count of at
- * least 2.
- */
- WARN_ON_ONCE(kref_read(&session->kref) < 2);
active = j1939_session_deactivate_locked(session);
j1939_session_list_unlock(priv);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a3b7d965e9c0..e05dd4f3279a 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -155,12 +155,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
return 0;
if (ops->id && ops->size) {
-cleanup:
ng = rcu_dereference_protected(net->gen,
lockdep_is_held(&pernet_ops_rwsem));
ng->ptr[*ops->id] = NULL;
}
+cleanup:
kfree(data);
out:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b627ffe4f492..34f580f96823 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3688,7 +3688,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
skb_shinfo(skb)->frag_list = NULL;
- do {
+ while (list_skb) {
nskb = list_skb;
list_skb = list_skb->next;
@@ -3732,8 +3732,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
if (skb_needs_linearize(nskb, features) &&
__skb_linearize(nskb))
goto err_linearize;
-
- } while (list_skb);
+ }
skb->truesize = skb->truesize - delta_truesize;
skb->data_len = skb->data_len - delta_len;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ab9fcc6231b8..4e94796ccdbd 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -30,6 +30,7 @@
#include <linux/slab.h>
#include <linux/netlink.h>
#include <linux/hash.h>
+#include <linux/nospec.h>
#include <net/arp.h>
#include <net/ip.h>
@@ -1021,6 +1022,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
if (type > RTAX_MAX)
return false;
+ type = array_index_nospec(type, RTAX_MAX + 1);
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
bool ecn_ca = false;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index c68a1dae25ca..2615b72118d1 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -571,8 +571,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
- ret = sk_nulls_del_node_init_rcu(osk);
- } else if (found_dup_sk) {
+ ret = sk_hashed(osk);
+ if (ret) {
+ /* Before deleting the node, we insert a new one to make
+ * sure that the look-up-sk process would not miss either
+ * of them and that at least one node would exist in ehash
+ * table all the time. Otherwise there's a tiny chance
+ * that lookup process could find nothing in ehash table.
+ */
+ __sk_nulls_add_node_tail_rcu(sk, list);
+ sk_nulls_del_node_init_rcu(osk);
+ }
+ goto unlock;
+ }
+ if (found_dup_sk) {
*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
if (*found_dup_sk)
ret = false;
@@ -581,6 +593,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+unlock:
spin_unlock(lock);
return ret;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index c411c87ae865..a00102d7c7fd 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -81,10 +81,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
- struct hlist_nulls_head *list)
+static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw,
+ struct hlist_nulls_head *list)
{
- hlist_nulls_add_head_rcu(&tw->tw_node, list);
+ hlist_nulls_add_tail_rcu(&tw->tw_node, list);
}
static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
@@ -120,7 +120,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
spin_lock(lock);
- inet_twsk_add_node_rcu(tw, &ehead->chain);
+ inet_twsk_add_node_tail_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 3205d5f7c8c9..4966ac2aaf87 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/netlink.h>
+#include <linux/nospec.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
#include <net/ip.h>
@@ -28,6 +29,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
return -EINVAL;
}
+ type = array_index_nospec(type, RTAX_MAX + 1);
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cc588bc2b11d..6a0560a735ce 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -432,6 +432,7 @@ void tcp_init_sock(struct sock *sk)
/* There's a bubble in the pipe until at least the first ACK. */
tp->app_limited = ~0U;
+ tp->rate_app_limited = 1;
/* See draft-stevens-tcpca-spec-01 for discussion of the
* initialization of these values.
@@ -2837,6 +2838,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->last_oow_ack_time = 0;
/* There's a bubble in the pipe until at least the first ACK. */
tp->app_limited = ~0U;
+ tp->rate_app_limited = 1;
tp->rack.mstamp = 0;
tp->rack.advanced = 0;
tp->rack.reo_wnd_steps = 1;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 6a1685461f89..926e29e84b40 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -6,6 +6,7 @@
#include <linux/bpf.h>
#include <linux/init.h>
#include <linux/wait.h>
+#include <linux/util_macros.h>
#include <net/inet_common.h>
#include <net/tls.h>
@@ -642,10 +643,9 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
*/
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
{
- int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
struct proto *prot = newsk->sk_prot;
- if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
+ if (is_insidevar(prot, tcp_bpf_prots))
newsk->sk_prot = sk->sk_prot_creator;
}
#endif /* CONFIG_BPF_STREAM_PARSER */
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index dc8987ed08ad..a4b793d1b7d7 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -104,9 +104,9 @@ static struct workqueue_struct *l2tp_wq;
/* per-net private data for this module */
static unsigned int l2tp_net_id;
struct l2tp_net {
- struct list_head l2tp_tunnel_list;
- /* Lock for write access to l2tp_tunnel_list */
- spinlock_t l2tp_tunnel_list_lock;
+ /* Lock for write access to l2tp_tunnel_idr */
+ spinlock_t l2tp_tunnel_idr_lock;
+ struct idr l2tp_tunnel_idr;
struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2];
/* Lock for write access to l2tp_session_hlist */
spinlock_t l2tp_session_hlist_lock;
@@ -208,13 +208,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
struct l2tp_tunnel *tunnel;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id &&
- refcount_inc_not_zero(&tunnel->ref_count)) {
- rcu_read_unlock_bh();
-
- return tunnel;
- }
+ tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id);
+ if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) {
+ rcu_read_unlock_bh();
+ return tunnel;
}
rcu_read_unlock_bh();
@@ -224,13 +221,14 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
{
- const struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_net *pn = l2tp_pernet(net);
+ unsigned long tunnel_id, tmp;
struct l2tp_tunnel *tunnel;
int count = 0;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth &&
+ idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+ if (tunnel && ++count > nth &&
refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
@@ -1043,7 +1041,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
nf_reset_ct(skb);
- bh_lock_sock(sk);
+ bh_lock_sock_nested(sk);
if (sock_owned_by_user(sk)) {
kfree_skb(skb);
ret = NET_XMIT_DROP;
@@ -1150,8 +1148,10 @@ static void l2tp_tunnel_destruct(struct sock *sk)
}
/* Remove hooks into tunnel socket */
+ write_lock_bh(&sk->sk_callback_lock);
sk->sk_destruct = tunnel->old_sk_destruct;
sk->sk_user_data = NULL;
+ write_unlock_bh(&sk->sk_callback_lock);
/* Call the original destructor */
if (sk->sk_destruct)
@@ -1227,6 +1227,15 @@ static void l2tp_udp_encap_destroy(struct sock *sk)
l2tp_tunnel_delete(tunnel);
}
+static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
+}
+
/* Workqueue tunnel deletion function */
static void l2tp_tunnel_del_work(struct work_struct *work)
{
@@ -1234,7 +1243,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
del_work);
struct sock *sk = tunnel->sock;
struct socket *sock = sk->sk_socket;
- struct l2tp_net *pn;
l2tp_tunnel_closeall(tunnel);
@@ -1248,12 +1256,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
}
}
- /* Remove the tunnel struct from the tunnel list */
- pn = l2tp_pernet(tunnel->l2tp_net);
- spin_lock_bh(&pn->l2tp_tunnel_list_lock);
- list_del_rcu(&tunnel->list);
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-
+ l2tp_tunnel_remove(tunnel->l2tp_net, tunnel);
/* drop initial ref */
l2tp_tunnel_dec_refcount(tunnel);
@@ -1384,8 +1387,6 @@ out:
return err;
}
-static struct lock_class_key l2tp_socket_class;
-
int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id,
struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
{
@@ -1455,12 +1456,19 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
struct l2tp_tunnel_cfg *cfg)
{
- struct l2tp_tunnel *tunnel_walk;
- struct l2tp_net *pn;
+ struct l2tp_net *pn = l2tp_pernet(net);
+ u32 tunnel_id = tunnel->tunnel_id;
struct socket *sock;
struct sock *sk;
int ret;
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id,
+ GFP_ATOMIC);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
+ if (ret)
+ return ret == -ENOSPC ? -EEXIST : ret;
+
if (tunnel->fd < 0) {
ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id,
tunnel->peer_tunnel_id, cfg,
@@ -1471,30 +1479,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
sock = sockfd_lookup(tunnel->fd, &ret);
if (!sock)
goto err;
-
- ret = l2tp_validate_socket(sock->sk, net, tunnel->encap);
- if (ret < 0)
- goto err_sock;
}
- tunnel->l2tp_net = net;
- pn = l2tp_pernet(net);
-
sk = sock->sk;
- sock_hold(sk);
- tunnel->sock = sk;
-
- spin_lock_bh(&pn->l2tp_tunnel_list_lock);
- list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) {
- if (tunnel_walk->tunnel_id == tunnel->tunnel_id) {
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
- sock_put(sk);
- ret = -EEXIST;
- goto err_sock;
- }
- }
- list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+ lock_sock(sk);
+ write_lock_bh(&sk->sk_callback_lock);
+ ret = l2tp_validate_socket(sk, net, tunnel->encap);
+ if (ret < 0)
+ goto err_inval_sock;
+ rcu_assign_sk_user_data(sk, tunnel);
+ write_unlock_bh(&sk->sk_callback_lock);
if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
struct udp_tunnel_sock_cfg udp_cfg = {
@@ -1505,15 +1499,20 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
};
setup_udp_tunnel_sock(net, sock, &udp_cfg);
- } else {
- sk->sk_user_data = tunnel;
}
tunnel->old_sk_destruct = sk->sk_destruct;
sk->sk_destruct = &l2tp_tunnel_destruct;
- lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class,
- "l2tp_sock");
sk->sk_allocation = GFP_ATOMIC;
+ release_sock(sk);
+
+ sock_hold(sk);
+ tunnel->sock = sk;
+ tunnel->l2tp_net = net;
+
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
trace_register_tunnel(tunnel);
@@ -1522,12 +1521,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
return 0;
-err_sock:
+err_inval_sock:
+ write_unlock_bh(&sk->sk_callback_lock);
+ release_sock(sk);
+
if (tunnel->fd < 0)
sock_release(sock);
else
sockfd_put(sock);
err:
+ l2tp_tunnel_remove(net, tunnel);
return ret;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_register);
@@ -1641,8 +1644,8 @@ static __net_init int l2tp_init_net(struct net *net)
struct l2tp_net *pn = net_generic(net, l2tp_net_id);
int hash;
- INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
- spin_lock_init(&pn->l2tp_tunnel_list_lock);
+ idr_init(&pn->l2tp_tunnel_idr);
+ spin_lock_init(&pn->l2tp_tunnel_idr_lock);
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]);
@@ -1656,11 +1659,13 @@ static __net_exit void l2tp_exit_net(struct net *net)
{
struct l2tp_net *pn = l2tp_pernet(net);
struct l2tp_tunnel *tunnel = NULL;
+ unsigned long tunnel_id, tmp;
int hash;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- l2tp_tunnel_delete(tunnel);
+ idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+ if (tunnel)
+ l2tp_tunnel_delete(tunnel);
}
rcu_read_unlock_bh();
@@ -1670,6 +1675,7 @@ static __net_exit void l2tp_exit_net(struct net *net)
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash]));
+ idr_destroy(&pn->l2tp_tunnel_idr);
}
static struct pernet_operations l2tp_net_ops = {
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 7626f3e1c70a..cec4b16170a0 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -27,22 +27,16 @@
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_conntrack_timeout.h>
-/* FIXME: Examine ipfilter's timeouts and conntrack transitions more
- closely. They're more complex. --RR
-
- And so for me for SCTP :D -Kiran */
-
static const char *const sctp_conntrack_names[] = {
- "NONE",
- "CLOSED",
- "COOKIE_WAIT",
- "COOKIE_ECHOED",
- "ESTABLISHED",
- "SHUTDOWN_SENT",
- "SHUTDOWN_RECD",
- "SHUTDOWN_ACK_SENT",
- "HEARTBEAT_SENT",
- "HEARTBEAT_ACKED",
+ [SCTP_CONNTRACK_NONE] = "NONE",
+ [SCTP_CONNTRACK_CLOSED] = "CLOSED",
+ [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT",
+ [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED",
+ [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED",
+ [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT",
+ [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD",
+ [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT",
+ [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT",
};
#define SECS * HZ
@@ -54,12 +48,11 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
[SCTP_CONNTRACK_CLOSED] = 10 SECS,
[SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS,
[SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS,
- [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS,
+ [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS,
[SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000,
[SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000,
[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS,
[SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS,
- [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS,
};
#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1
@@ -73,7 +66,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
#define sSR SCTP_CONNTRACK_SHUTDOWN_RECD
#define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT
#define sHS SCTP_CONNTRACK_HEARTBEAT_SENT
-#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED
#define sIV SCTP_CONNTRACK_MAX
/*
@@ -96,9 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite
CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of
the SHUTDOWN chunk. Connection is closed.
HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow.
-HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to
- that of the HEARTBEAT chunk. Secondary connection is
- established.
*/
/* TODO
@@ -115,33 +104,33 @@ cookie echoed to closed.
static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
-/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
-/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
-/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
-/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA},
-/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/
-/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */
-/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */
-/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA},
-/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA},
-/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
+/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW},
+/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},
+/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL},
+/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA},
+/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/
+/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */
+/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
+/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL},
+/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
+/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
},
{
/* REPLY */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */
-/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
-/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL},
-/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR},
-/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA},
-/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA},
-/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */
-/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA},
-/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA},
-/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA},
-/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA}
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
+/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */
+/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV},
+/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV},
+/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV},
+/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV},
+/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV},
+/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
+/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV},
+/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV},
+/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
+/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES},
}
};
@@ -412,22 +401,29 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) {
/* Special cases of Verification tag check (Sec 8.5.1) */
if (sch->type == SCTP_CID_INIT) {
- /* Sec 8.5.1 (A) */
+ /* (A) vtag MUST be zero */
if (sh->vtag != 0)
goto out_unlock;
} else if (sch->type == SCTP_CID_ABORT) {
- /* Sec 8.5.1 (B) */
- if (sh->vtag != ct->proto.sctp.vtag[dir] &&
- sh->vtag != ct->proto.sctp.vtag[!dir])
+ /* (B) vtag MUST match own vtag if T flag is unset OR
+ * MUST match peer's vtag if T flag is set
+ */
+ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) ||
+ ((sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[!dir]))
goto out_unlock;
} else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) {
- /* Sec 8.5.1 (C) */
- if (sh->vtag != ct->proto.sctp.vtag[dir] &&
- sh->vtag != ct->proto.sctp.vtag[!dir] &&
- sch->flags & SCTP_CHUNK_FLAG_T)
+ /* (C) vtag MUST match own vtag if T flag is unset OR
+ * MUST match peer's vtag if T flag is set
+ */
+ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) ||
+ ((sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[!dir]))
goto out_unlock;
} else if (sch->type == SCTP_CID_COOKIE_ECHO) {
- /* Sec 8.5.1 (D) */
+ /* (D) vtag must be same as init_vtag as found in INIT_ACK */
if (sh->vtag != ct->proto.sctp.vtag[dir])
goto out_unlock;
} else if (sch->type == SCTP_CID_HEARTBEAT) {
@@ -501,8 +497,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
}
ct->proto.sctp.state = new_state;
- if (old_state != new_state)
+ if (old_state != new_state) {
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
+ if (new_state == SCTP_CONNTRACK_ESTABLISHED &&
+ !test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
+ nf_conntrack_event_cache(IPCT_ASSURED, ct);
+ }
}
spin_unlock_bh(&ct->lock);
@@ -516,14 +516,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
- if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED &&
- dir == IP_CT_DIR_REPLY &&
- new_state == SCTP_CONNTRACK_ESTABLISHED) {
- pr_debug("Setting assured bit\n");
- set_bit(IPS_ASSURED_BIT, &ct->status);
- nf_conntrack_event_cache(IPCT_ASSURED, ct);
- }
-
return NF_ACCEPT;
out_unlock:
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 3f785bdfa942..c1d02c0b4f00 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1158,6 +1158,16 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
+
+ if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) {
+ /* do not renew timeout on SYN retransmit.
+ *
+ * Else port reuse by client or NAT middlebox can keep
+ * entry alive indefinitely (including nat info).
+ */
+ return NF_ACCEPT;
+ }
+
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index a7f88cdf3f87..e12b52019a55 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -583,7 +583,6 @@ enum nf_ct_sysctl_index {
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT,
- NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED,
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST,
@@ -853,12 +852,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = {
- .procname = "nf_conntrack_sctp_timeout_heartbeat_acked",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = {
@@ -987,7 +980,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
XASSIGN(SHUTDOWN_RECD, sn);
XASSIGN(SHUTDOWN_ACK_SENT, sn);
XASSIGN(HEARTBEAT_SENT, sn);
- XASSIGN(HEARTBEAT_ACKED, sn);
#undef XASSIGN
#endif
}
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 94a5446c5eae..4b9a499fe8f4 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe)
return !nft_rbtree_interval_end(rbe);
}
-static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
- const struct nft_rbtree_elem *interval)
+static int nft_rbtree_cmp(const struct nft_set *set,
+ const struct nft_rbtree_elem *e1,
+ const struct nft_rbtree_elem *e2)
{
- return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0;
+ return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext),
+ set->klen);
}
static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
@@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
const struct nft_rbtree_elem *rbe, *interval = NULL;
u8 genmask = nft_genmask_cur(net);
const struct rb_node *parent;
- const void *this;
int d;
parent = rcu_dereference_raw(priv->root.rb_node);
@@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- this = nft_set_ext_key(&rbe->ext);
- d = memcmp(this, key, set->klen);
+ d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen);
if (d < 0) {
parent = rcu_dereference_raw(parent->rb_left);
if (interval &&
- nft_rbtree_equal(set, this, interval) &&
+ !nft_rbtree_cmp(set, rbe, interval) &&
nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_start(interval))
continue;
@@ -214,154 +214,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set,
return rbe;
}
+static int nft_rbtree_gc_elem(const struct nft_set *__set,
+ struct nft_rbtree *priv,
+ struct nft_rbtree_elem *rbe)
+{
+ struct nft_set *set = (struct nft_set *)__set;
+ struct rb_node *prev = rb_prev(&rbe->node);
+ struct nft_rbtree_elem *rbe_prev;
+ struct nft_set_gc_batch *gcb;
+
+ gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC);
+ if (!gcb)
+ return -ENOMEM;
+
+ /* search for expired end interval coming before this element. */
+ do {
+ rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
+ if (nft_rbtree_interval_end(rbe_prev))
+ break;
+
+ prev = rb_prev(prev);
+ } while (prev != NULL);
+
+ rb_erase(&rbe_prev->node, &priv->root);
+ rb_erase(&rbe->node, &priv->root);
+ atomic_sub(2, &set->nelems);
+
+ nft_set_gc_batch_add(gcb, rbe);
+ nft_set_gc_batch_complete(gcb);
+
+ return 0;
+}
+
+static bool nft_rbtree_update_first(const struct nft_set *set,
+ struct nft_rbtree_elem *rbe,
+ struct rb_node *first)
+{
+ struct nft_rbtree_elem *first_elem;
+
+ first_elem = rb_entry(first, struct nft_rbtree_elem, node);
+ /* this element is closest to where the new element is to be inserted:
+ * update the first element for the node list path.
+ */
+ if (nft_rbtree_cmp(set, rbe, first_elem) < 0)
+ return true;
+
+ return false;
+}
+
static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree_elem *new,
struct nft_set_ext **ext)
{
- bool overlap = false, dup_end_left = false, dup_end_right = false;
+ struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL;
+ struct rb_node *node, *parent, **p, *first = NULL;
struct nft_rbtree *priv = nft_set_priv(set);
u8 genmask = nft_genmask_next(net);
- struct nft_rbtree_elem *rbe;
- struct rb_node *parent, **p;
- int d;
+ int d, err;
- /* Detect overlaps as we descend the tree. Set the flag in these cases:
- *
- * a1. _ _ __>| ?_ _ __| (insert end before existing end)
- * a2. _ _ ___| ?_ _ _>| (insert end after existing end)
- * a3. _ _ ___? >|_ _ __| (insert start before existing end)
- *
- * and clear it later on, as we eventually reach the points indicated by
- * '?' above, in the cases described below. We'll always meet these
- * later, locally, due to tree ordering, and overlaps for the intervals
- * that are the closest together are always evaluated last.
- *
- * b1. _ _ __>| !_ _ __| (insert end before existing start)
- * b2. _ _ ___| !_ _ _>| (insert end after existing start)
- * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf)
- * '--' no nodes falling in this range
- * b4. >|_ _ ! (insert start before existing start)
- *
- * Case a3. resolves to b3.:
- * - if the inserted start element is the leftmost, because the '0'
- * element in the tree serves as end element
- * - otherwise, if an existing end is found immediately to the left. If
- * there are existing nodes in between, we need to further descend the
- * tree before we can conclude the new start isn't causing an overlap
- *
- * or to b4., which, preceded by a3., means we already traversed one or
- * more existing intervals entirely, from the right.
- *
- * For a new, rightmost pair of elements, we'll hit cases b3. and b2.,
- * in that order.
- *
- * The flag is also cleared in two special cases:
- *
- * b5. |__ _ _!|<_ _ _ (insert start right before existing end)
- * b6. |__ _ >|!__ _ _ (insert end right after existing start)
- *
- * which always happen as last step and imply that no further
- * overlapping is possible.
- *
- * Another special case comes from the fact that start elements matching
- * an already existing start element are allowed: insertion is not
- * performed but we return -EEXIST in that case, and the error will be
- * cleared by the caller if NLM_F_EXCL is not present in the request.
- * This way, request for insertion of an exact overlap isn't reported as
- * error to userspace if not desired.
- *
- * However, if the existing start matches a pre-existing start, but the
- * end element doesn't match the corresponding pre-existing end element,
- * we need to report a partial overlap. This is a local condition that
- * can be noticed without need for a tracking flag, by checking for a
- * local duplicated end for a corresponding start, from left and right,
- * separately.
+ /* Descend the tree to search for an existing element greater than the
+ * key value to insert that is greater than the new element. This is the
+ * first element to walk the ordered elements to find possible overlap.
*/
-
parent = NULL;
p = &priv->root.rb_node;
while (*p != NULL) {
parent = *p;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- d = memcmp(nft_set_ext_key(&rbe->ext),
- nft_set_ext_key(&new->ext),
- set->klen);
+ d = nft_rbtree_cmp(set, rbe, new);
+
if (d < 0) {
p = &parent->rb_left;
-
- if (nft_rbtree_interval_start(new)) {
- if (nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext) && !*p)
- overlap = false;
- } else {
- if (dup_end_left && !*p)
- return -ENOTEMPTY;
-
- overlap = nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext,
- genmask) &&
- !nft_set_elem_expired(&rbe->ext);
-
- if (overlap) {
- dup_end_right = true;
- continue;
- }
- }
} else if (d > 0) {
- p = &parent->rb_right;
+ if (!first ||
+ nft_rbtree_update_first(set, rbe, first))
+ first = &rbe->node;
- if (nft_rbtree_interval_end(new)) {
- if (dup_end_right && !*p)
- return -ENOTEMPTY;
-
- overlap = nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext,
- genmask) &&
- !nft_set_elem_expired(&rbe->ext);
-
- if (overlap) {
- dup_end_left = true;
- continue;
- }
- } else if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext)) {
- overlap = nft_rbtree_interval_end(rbe);
- }
+ p = &parent->rb_right;
} else {
- if (nft_rbtree_interval_end(rbe) &&
- nft_rbtree_interval_start(new)) {
+ if (nft_rbtree_interval_end(rbe))
p = &parent->rb_left;
-
- if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext))
- overlap = false;
- } else if (nft_rbtree_interval_start(rbe) &&
- nft_rbtree_interval_end(new)) {
+ else
p = &parent->rb_right;
+ }
+ }
+
+ if (!first)
+ first = rb_first(&priv->root);
+
+ /* Detect overlap by going through the list of valid tree nodes.
+ * Values stored in the tree are in reversed order, starting from
+ * highest to lowest value.
+ */
+ for (node = first; node != NULL; node = rb_next(node)) {
+ rbe = rb_entry(node, struct nft_rbtree_elem, node);
- if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext))
- overlap = false;
- } else if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext)) {
- *ext = &rbe->ext;
- return -EEXIST;
- } else {
- overlap = false;
- if (nft_rbtree_interval_end(rbe))
- p = &parent->rb_left;
- else
- p = &parent->rb_right;
+ if (!nft_set_elem_active(&rbe->ext, genmask))
+ continue;
+
+ /* perform garbage collection to avoid bogus overlap reports. */
+ if (nft_set_elem_expired(&rbe->ext)) {
+ err = nft_rbtree_gc_elem(set, priv, rbe);
+ if (err < 0)
+ return err;
+
+ continue;
+ }
+
+ d = nft_rbtree_cmp(set, rbe, new);
+ if (d == 0) {
+ /* Matching end element: no need to look for an
+ * overlapping greater or equal element.
+ */
+ if (nft_rbtree_interval_end(rbe)) {
+ rbe_le = rbe;
+ break;
+ }
+
+ /* first element that is greater or equal to key value. */
+ if (!rbe_ge) {
+ rbe_ge = rbe;
+ continue;
+ }
+
+ /* this is a closer more or equal element, update it. */
+ if (nft_rbtree_cmp(set, rbe_ge, new) != 0) {
+ rbe_ge = rbe;
+ continue;
+ }
+
+ /* element is equal to key value, make sure flags are
+ * the same, an existing more or equal start element
+ * must not be replaced by more or equal end element.
+ */
+ if ((nft_rbtree_interval_start(new) &&
+ nft_rbtree_interval_start(rbe_ge)) ||
+ (nft_rbtree_interval_end(new) &&
+ nft_rbtree_interval_end(rbe_ge))) {
+ rbe_ge = rbe;
+ continue;
}
+ } else if (d > 0) {
+ /* annotate element greater than the new element. */
+ rbe_ge = rbe;
+ continue;
+ } else if (d < 0) {
+ /* annotate element less than the new element. */
+ rbe_le = rbe;
+ break;
}
+ }
- dup_end_left = dup_end_right = false;
+ /* - new start element matching existing start element: full overlap
+ * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
+ */
+ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) &&
+ nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) {
+ *ext = &rbe_ge->ext;
+ return -EEXIST;
}
- if (overlap)
+ /* - new end element matching existing end element: full overlap
+ * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
+ */
+ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) &&
+ nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) {
+ *ext = &rbe_le->ext;
+ return -EEXIST;
+ }
+
+ /* - new start element with existing closest, less or equal key value
+ * being a start element: partial overlap, reported as -ENOTEMPTY.
+ * Anonymous sets allow for two consecutive start element since they
+ * are constant, skip them to avoid bogus overlap reports.
+ */
+ if (!nft_set_is_anonymous(set) && rbe_le &&
+ nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new))
+ return -ENOTEMPTY;
+
+ /* - new end element with existing closest, less or equal key value
+ * being a end element: partial overlap, reported as -ENOTEMPTY.
+ */
+ if (rbe_le &&
+ nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new))
return -ENOTEMPTY;
+ /* - new end element with existing closest, greater or equal key value
+ * being an end element: partial overlap, reported as -ENOTEMPTY
+ */
+ if (rbe_ge &&
+ nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new))
+ return -ENOTEMPTY;
+
+ /* Accepted element: pick insertion point depending on key value */
+ parent = NULL;
+ p = &priv->root.rb_node;
+ while (*p != NULL) {
+ parent = *p;
+ rbe = rb_entry(parent, struct nft_rbtree_elem, node);
+ d = nft_rbtree_cmp(set, rbe, new);
+
+ if (d < 0)
+ p = &parent->rb_left;
+ else if (d > 0)
+ p = &parent->rb_right;
+ else if (nft_rbtree_interval_end(rbe))
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+ }
+
rb_link_node_rcu(&new->node, parent, p);
rb_insert_color(&new->node, &priv->root);
return 0;
@@ -500,23 +562,37 @@ static void nft_rbtree_gc(struct work_struct *work)
struct nft_rbtree *priv;
struct rb_node *node;
struct nft_set *set;
+ struct net *net;
+ u8 genmask;
priv = container_of(work, struct nft_rbtree, gc_work.work);
set = nft_set_container_of(priv);
+ net = read_pnet(&set->net);
+ genmask = nft_genmask_cur(net);
write_lock_bh(&priv->lock);
write_seqcount_begin(&priv->count);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
+ if (!nft_set_elem_active(&rbe->ext, genmask))
+ continue;
+
+ /* elements are reversed in the rbtree for historical reasons,
+ * from highest to lowest value, that is why end element is
+ * always visited before the start element.
+ */
if (nft_rbtree_interval_end(rbe)) {
rbe_end = rbe;
continue;
}
if (!nft_set_elem_expired(&rbe->ext))
continue;
- if (nft_set_elem_mark_busy(&rbe->ext))
+
+ if (nft_set_elem_mark_busy(&rbe->ext)) {
+ rbe_end = NULL;
continue;
+ }
if (rbe_prev) {
rb_erase(&rbe_prev->node, &priv->root);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d96a610929d9..2104fbdd63d2 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -570,7 +570,9 @@ static int netlink_insert(struct sock *sk, u32 portid)
if (nlk_sk(sk)->bound)
goto err;
- nlk_sk(sk)->portid = portid;
+ /* portid can be read locklessly from netlink_getname(). */
+ WRITE_ONCE(nlk_sk(sk)->portid, portid);
+
sock_hold(sk);
err = __netlink_insert(table, sk);
@@ -1079,9 +1081,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
return -EINVAL;
if (addr->sa_family == AF_UNSPEC) {
- sk->sk_state = NETLINK_UNCONNECTED;
- nlk->dst_portid = 0;
- nlk->dst_group = 0;
+ /* paired with READ_ONCE() in netlink_getsockbyportid() */
+ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED);
+ /* dst_portid and dst_group can be read locklessly */
+ WRITE_ONCE(nlk->dst_portid, 0);
+ WRITE_ONCE(nlk->dst_group, 0);
return 0;
}
if (addr->sa_family != AF_NETLINK)
@@ -1102,9 +1106,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
err = netlink_autobind(sock);
if (err == 0) {
- sk->sk_state = NETLINK_CONNECTED;
- nlk->dst_portid = nladdr->nl_pid;
- nlk->dst_group = ffs(nladdr->nl_groups);
+ /* paired with READ_ONCE() in netlink_getsockbyportid() */
+ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED);
+ /* dst_portid and dst_group can be read locklessly */
+ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid);
+ WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups));
}
return err;
@@ -1121,10 +1127,12 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
nladdr->nl_pad = 0;
if (peer) {
- nladdr->nl_pid = nlk->dst_portid;
- nladdr->nl_groups = netlink_group_mask(nlk->dst_group);
+ /* Paired with WRITE_ONCE() in netlink_connect() */
+ nladdr->nl_pid = READ_ONCE(nlk->dst_portid);
+ nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group));
} else {
- nladdr->nl_pid = nlk->portid;
+ /* Paired with WRITE_ONCE() in netlink_insert() */
+ nladdr->nl_pid = READ_ONCE(nlk->portid);
netlink_lock_table();
nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
netlink_unlock_table();
@@ -1151,8 +1159,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
- if (sock->sk_state == NETLINK_CONNECTED &&
- nlk->dst_portid != nlk_sk(ssk)->portid) {
+ /* dst_portid and sk_state can be changed in netlink_connect() */
+ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED &&
+ READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
@@ -1888,8 +1897,9 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
goto out;
netlink_skb_flags |= NETLINK_SKB_DST;
} else {
- dst_portid = nlk->dst_portid;
- dst_group = nlk->dst_group;
+ /* Paired with WRITE_ONCE() in netlink_connect() */
+ dst_portid = READ_ONCE(nlk->dst_portid);
+ dst_group = READ_ONCE(nlk->dst_group);
}
/* Paired with WRITE_ONCE() in netlink_insert() */
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index e5c8a295e640..5c04da4cfbad 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -400,6 +400,11 @@ static int nr_listen(struct socket *sock, int backlog)
struct sock *sk = sock->sk;
lock_sock(sk);
+ if (sock->state != SS_UNCONNECTED) {
+ release_sock(sk);
+ return -EINVAL;
+ }
+
if (sk->sk_state != TCP_LISTEN) {
memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN);
sk->sk_max_ack_backlog = backlog;
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index a8da88db7893..4e7c968cde2d 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -121,6 +121,7 @@ static void nr_heartbeat_expiry(struct timer_list *t)
is accepted() it isn't 'dead' so doesn't get removed. */
if (sock_flag(sk, SOCK_DESTROY) ||
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
+ sock_hold(sk);
bh_unlock_sock(sk);
nr_destroy_socket(sk);
goto out;
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index cc997518f79d..edadebb3efd2 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -159,6 +159,7 @@ static void local_cleanup(struct nfc_llcp_local *local)
cancel_work_sync(&local->rx_work);
cancel_work_sync(&local->timeout_work);
kfree_skb(local->rx_pending);
+ local->rx_pending = NULL;
del_timer_sync(&local->sdreq_timer);
cancel_work_sync(&local->sdreq_timeout_work);
nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 435f7f1be614..b625ab5e9a43 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -964,14 +964,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
key = kzalloc(sizeof(*key), GFP_KERNEL);
if (!key) {
error = -ENOMEM;
- goto err_kfree_key;
+ goto err_kfree_flow;
}
ovs_match_init(&match, key, false, &mask);
error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY],
a[OVS_FLOW_ATTR_MASK], log);
if (error)
- goto err_kfree_flow;
+ goto err_kfree_key;
ovs_flow_mask_key(&new_flow->key, key, true, &mask);
@@ -979,14 +979,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
key, log);
if (error)
- goto err_kfree_flow;
+ goto err_kfree_key;
/* Validate actions. */
error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS],
&new_flow->key, &acts, log);
if (error) {
OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
- goto err_kfree_flow;
+ goto err_kfree_key;
}
reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false,
@@ -1086,10 +1086,10 @@ err_unlock_ovs:
kfree_skb(reply);
err_kfree_acts:
ovs_nla_free_flow_actions(acts);
-err_kfree_flow:
- ovs_flow_free(new_flow, false);
err_kfree_key:
kfree(key);
+err_kfree_flow:
+ ovs_flow_free(new_flow, false);
error:
return error;
}
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index e760d4a38faf..fe81e0385168 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -83,7 +83,10 @@ static struct qrtr_node *node_get(unsigned int node_id)
node->id = node_id;
- radix_tree_insert(&nodes, node_id, node);
+ if (radix_tree_insert(&nodes, node_id, node)) {
+ kfree(node);
+ return NULL;
+ }
return node;
}
diff --git a/net/rds/message.c b/net/rds/message.c
index 799034e0f513..b363ef13c75e 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs,
spin_lock_irqsave(&q->lock, flags);
head = &q->zcookie_head;
if (!list_empty(head)) {
- info = list_entry(head, struct rds_msg_zcopy_info,
- rs_zcookie_next);
- if (info && rds_zcookie_add(info, cookie)) {
+ info = list_first_entry(head, struct rds_msg_zcopy_info,
+ rs_zcookie_next);
+ if (rds_zcookie_add(info, cookie)) {
spin_unlock_irqrestore(&q->lock, flags);
kfree(rds_info_from_znotifier(znotif));
/* caller invokes rds_wake_sk_sleep() */
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 7f33b31c7b8b..e25fe44899ff 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1621,6 +1621,7 @@ static void taprio_reset(struct Qdisc *sch)
int i;
hrtimer_cancel(&q->advance_timer);
+
if (q->qdiscs) {
for (i = 0; i < dev->num_tx_queues; i++)
if (q->qdiscs[i])
@@ -1642,6 +1643,7 @@ static void taprio_destroy(struct Qdisc *sch)
* happens in qdisc_create(), after taprio_init() has been called.
*/
hrtimer_cancel(&q->advance_timer);
+ qdisc_synchronize(sch);
taprio_disable_offload(dev, q, NULL);
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 59e653b528b1..6b95d3ba8fe1 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -73,6 +73,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest,
}
}
+ /* If somehow no addresses were found that can be used with this
+ * scope, it's an error.
+ */
+ if (list_empty(&dest->address_list))
+ error = -ENETUNREACH;
+
out:
if (error)
sctp_bind_addr_clean(dest);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index d231d4620c38..161dc194e634 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -492,6 +492,12 @@ static int x25_listen(struct socket *sock, int backlog)
int rc = -EOPNOTSUPP;
lock_sock(sk);
+ if (sock->state != SS_UNCONNECTED) {
+ rc = -EINVAL;
+ release_sock(sk);
+ return rc;
+ }
+
if (sk->sk_state != TCP_LISTEN) {
memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN);
sk->sk_max_ack_backlog = backlog;
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index a0f62fa02e06..8cbf45a8bcdc 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -5,6 +5,7 @@
* Based on code and translator idea by: Florian Westphal <fw@strlen.de>
*/
#include <linux/compat.h>
+#include <linux/nospec.h>
#include <linux/xfrm.h>
#include <net/xfrm.h>
@@ -302,7 +303,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
nla_for_each_attr(nla, attrs, len, remaining) {
int err;
- switch (type) {
+ switch (nlh_src->nlmsg_type) {
case XFRM_MSG_NEWSPDINFO:
err = xfrm_nla_cpy(dst, nla, nla_len(nla));
break;
@@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
NL_SET_ERR_MSG(extack, "Bad attribute");
return -EOPNOTSUPP;
}
+ type = array_index_nospec(type, XFRMA_MAX + 1);
if (nla_len(nla) < compat_policy[type].len) {
NL_SET_ERR_MSG(extack, "Attribute bad length");
return -EOPNOTSUPP;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 77e82033ad70..fef99a1c5df1 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -277,8 +277,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
- ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
- ipipv6_hdr(skb));
+ ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb));
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip6_ecn_decapsulate(skb);